Dynamic updates to applicability reports for AI / ML models.

Abstract

The user equipment (UE) (110) sends a first completion message indicating whether the model is applicable to the function configured on the UE (110). In a second message, the UE (110) reports that the applicability of the model to the above function on the UE (110) has changed. The first completion message and the second message are received by the network node (120).

Description

Technical Field

[0001] This application claims priority to U.S. Provisional Patent Application No. 63 / 457,765, filed on April 6, 2023, the entire content of which is incorporated herein by reference.

[0002] Embodiments of the present disclosure generally relate to wireless communication networks, and more particularly, to modeling wireless communication network characteristics using artificial intelligence (AI) and / or machine learning (ML) techniques.

Background Art

[0003] Artificial intelligence (AI) and machine learning (ML) have been studied as promising tools for optimizing the design of the air interface in wireless communication networks. Exemplary use cases include using autoencoders for channel state information (CSI) compression to reduce feedback overhead and improve channel prediction accuracy, using deep neural networks to classify line-of-sight (LOS) and non-line-of-sight (NLOS) conditions to improve positioning accuracy, using reinforcement learning for beam selection (e.g., on the network side and / or UE side) to reduce signaling overhead and beam alignment latency, and using deep reinforcement learning to learn optimal precoding policies for complex multiple-input multiple-output (MIMO) precoding problems.

[0004] The 3GPP New Radio (NR) standardization work is expected to explore the benefits of extending the air interface with features that enable improved support of AI / ML-based algorithms for improved performance and / or reduced complexity / overhead. By examining a few selected use cases (CSI feedback, beam management, and positioning), a foundation for future air interface use cases leveraging AI / ML techniques may soon be built.

Summary of the Invention

[0005] This disclosure generally aims to improve the usefulness of AI / ML models when modeling PHYs in wireless communication networks.

[0006] Certain embodiments of this disclosure include a method implemented by a user device (UE). The method includes sending a first completion message indicating whether the model is applicable to a function configured on the UE. The method further includes reporting in a second message that the applicability of the model to the aforementioned function on the UE has changed.

[0007] In some embodiments, the first completion message includes an RRC setup completion message, an RRC restart completion message, or an RRC reconfiguration completion message.

[0008] In some embodiments, reporting a change in the applicability of a model includes indicating that the model is no longer applicable. In some such embodiments, reporting a change in the applicability of a model includes indicating an alternative model that is applicable and associated with the above-mentioned function. In other embodiments, reporting a change in the applicability of a model includes indicating that the model is still applicable.

[0009] In some embodiments, reporting a change in the applicability of a model includes providing causal values ​​that indicate why the model is applicable or not applicable.

[0010] In some embodiments, reporting that the applicability of the model has changed is in response to receiving a third message which configures the reporting to occur. In some such embodiments, the third message includes an RRC restart message, an RRC setup message, or an RRC reconfiguration message.

[0011] In some embodiments, the first completion message indicates multiple models, each of which is associated with a corresponding function configured in the UE.

[0012] In some embodiments, the second message reports applicability relationship information for multiple models.

[0013] Other embodiments include a UE. This UE is configured to send a first completion message indicating whether the model is applicable to the functionality configured in this UE. In a second message, this UE is further configured to report that the applicability of the model to the above functionality of UE(110) has changed.

[0014] In some embodiments, the UE comprises an interface circuit and a processing circuit communicatively connected to the interface circuit. The processing circuit is configured to send a first completion message via the interface circuit. The processing circuit is further configured to report via the interface circuit that the applicability of the model has changed.

[0015] In some embodiments, the UE (or the processing circuit of the UE) is further configured to perform one of the methods described above.

[0016] Another embodiment includes a computer program that, when executed on the processing circuit of the UE, provides instructions to cause the UE to perform one of the methods described above.

[0017] Further embodiments include a carrier containing the aforementioned computer program. This carrier is one of the following: an electronic signal, an optical signal, a wireless signal, or a computer-readable storage medium.

[0018] Other embodiments include methods implemented by network nodes. These methods include receiving a first completion message from the UE indicating whether the model is applicable to a function configured in the UE. These methods further include receiving a second message from the UE indicating that the applicability of the model to the UE's function has changed.

[0019] In some embodiments, the first completion message includes an RRC setup completion message, an RRC restart completion message, or an RRC reconfiguration completion message.

[0020] In some embodiments, a report indicating a change in the applicability of a model to the above-mentioned functionality of the UE includes a report that the model is not applicable. In some such embodiments, a report indicating a change in the applicability of a model to the above-mentioned functionality of the UE includes a report that an alternative model associated with the above-mentioned functionality is applicable. In other embodiments, a report indicating a change in the applicability of a model to the above-mentioned functionality of the UE includes a report that the model is applicable.

[0021] In some embodiments, a report indicating a change in the applicability of the model to the above-mentioned functions of the UE includes a causal value indicating why the model is applicable or not applicable.

[0022] In some embodiments, the method further includes sending a third message that configures the UE to send the above report. Receiving the second message is a response to sending the third message. In some such embodiments, the third message includes an RRC restart message, an RRC setup message, or an RRC reconfiguration message.

[0023] In some embodiments, the first completion message indicates multiple models, each of which is associated with a corresponding function configured in the UE.

[0024] In some embodiments, the second message reports applicability relationship information regarding a plurality of models.

[0025] Other embodiments include a network node. This network node is configured to receive, from a UE, a first completion message indicating whether a model is applicable to a function set for the UE. This network node is further configured to receive, from the UE in a second message, a report indicating that the applicability of the model to the above-mentioned function of the UE has changed.

[0026] In some embodiments, this network node includes an interface circuit and a processing circuit communicatively connected to the interface circuit. The processing circuit is configured to receive the first completion message from the UE via the interface circuit. The processing circuit is further configured to receive the above-mentioned report from the UE in the second message via the interface circuit.

[0027] In some embodiments, this network node (or the processing circuit of this network node) is further configured to implement any one of the network node methods described above.

[0028] Still other embodiments include a computer program that, when executed on a processing circuit of a network node, causes the network node to perform any one of the network node methods described above.

[0029] Other embodiments include a carrier containing the computer program. This carrier is one of an electronic signal, an optical signal, a wireless signal, or a computer-readable storage medium.

[0030] Aspects of the present disclosure are shown by way of example and are not limited by the accompanying drawings in which like reference numerals indicate like elements. In general, the use of reference numbers should be considered to refer to the illustrated subject matter according to one or more embodiments, although the description of a particular instance of an element shown will be by adding a letter designation to its reference number (for example, in contrast to the description of particular instances 120a, 120b of a network node, generally the description of network node 120).

Brief Description of the Drawings

[0031] [Figure 1] It is a logical block diagram showing an example of model life cycle management according to one or more embodiments of the present disclosure. [Figure 2] It is a signaling diagram showing examples of various embodiments of the present disclosure. [Figure 3] It is a signaling diagram showing examples of various embodiments of the present disclosure. [Figure 4] It is a signaling diagram showing examples of various embodiments of the present disclosure. [Figure 5] It is a signaling diagram showing examples of various embodiments of the present disclosure. [Figure 6] It is a signaling diagram showing examples of various embodiments of the present disclosure. [Figure 7] It is a signaling diagram showing examples of various embodiments of the present disclosure. [Figure 8] It is a signaling diagram showing examples of various embodiments of the present disclosure. [Figure 9] It is a signaling diagram showing examples of various embodiments of the present disclosure. [Figure 10] It is a signaling diagram showing examples of various embodiments of the present disclosure. [Figure 11] It is a flowchart showing an exemplary method implemented by a UE according to one or more embodiments of the present disclosure. [Figure 12] It is a flowchart showing an exemplary method implemented by a network node according to one or more embodiments of the present disclosure. [Figure 13] This is a schematic block diagram showing an exemplary UE according to one or more embodiments of the present disclosure. [Figure 14] This is a schematic block diagram showing an exemplary network node according to one or more embodiments of the present disclosure. [Figure 15] This is a schematic block diagram showing an example of a communication system according to several embodiments. [Figure 16] This is a schematic block diagram showing an exemplary UE according to one or more embodiments of the present disclosure. [Figure 17] This is a schematic block diagram showing an exemplary network node according to one or more embodiments of the present disclosure. [Figure 18] This is a schematic block diagram showing an exemplary host according to one or more embodiments of the present disclosure. [Figure 19] This is a schematic block diagram illustrating an exemplary virtualization environment according to one or more embodiments of the present disclosure. [Figure 20] This is a schematic block diagram illustrating communication between a host, a network node, and a UE according to one or more embodiments of the present disclosure. [Modes for carrying out the invention]

[0032] Figure 1 shows an exemplary high-level logic diagram of AI / ML model lifecycle management (LCM) at the physical layer (PHY) of a wireless communication network. As shown in Figure 1, the model LCM may include a model lifecycle manager and several stages. These stages include a data acquisition stage, a model training stage, a model deployment stage, a model inference stage, and a model monitoring stage. Each of these stages operates on inputs provided by the model lifecycle manager.

[0033] The data acquisition phase collects input data (raw or pre-processed data) and provides it to the model training, model inference, and model monitoring phases. No AI / ML algorithm-specific data preparation (e.g., data ingestion and data refinement) is performed during the data acquisition phase.

[0034] The model training phase involves training the AI / ML model using characterized data from the training dataset and validation dataset. The model deployment phase converts the AI / ML model into an executable format and delivers it to the target user device (UE), where model inference is performed.

[0035] The model inference phase uses the deployed AI / ML model to produce a set of outputs based on a set of characterized inputs. The model monitoring phase involves monitoring data and model drift, or performance metrics, after the model has been deployed. Based on the monitored performance, decisions such as model activation, deactivation, switching, fallback, and / or selection may be made.

[0036] In developing 3GPP standards, it may be useful to adopt the following provisions (although it may not always be necessary): • Data collection: The process of collecting data by network nodes, management entities, or UEs for the purposes of AI / ML model training, data analysis, and inference. • AI / ML model: A data-driven algorithm that applies AI / ML techniques to generate a set of outputs based on a set of inputs. • AI / ML model training: The process of training an AI / ML model in a data-driven manner (for example, by learning input / output relationships) and obtaining the trained AI / ML model for inference. • AI / ML model inference: The process of using a trained AI / ML model to produce a set of outputs based on a set of inputs. • AI / ML Model Validation: A training subprocess in which the quality of the AI / ML model is evaluated using a different dataset than the one used for model training. This helps in selecting model parameters that generalize beyond the dataset used for model training. • AI / ML Model Testing: A training subprocess in which the performance of the final AI / ML model is evaluated using a different dataset than the one used for model training and validation. In contrast to AI / ML model validation, model testing does not involve subsequent tuning of the model. • UE-side (AI / ML) model: An AI / ML model whose inference is performed entirely within the UE. • Network-side (AI / ML) models: AI / ML models in which the inference is performed entirely within the network (NW). • One-sided (AI / ML) model: UE-side (AI / ML) model or NW-side (AI / ML) model. • Two-sided (AI / ML) model: A pair of AI / ML models in which joint inference is performed. Here, joint inference includes AI / ML inference performed jointly across the UE and NW. For example, the first part of the inference may be performed by the UE and then the remaining part by the gNB (or vice versa). • AI / ML Model Transfer: Delivery of AI / ML models over an AI interface, for example, by transferring parameters of a model structure known at the receiving end, or by transferring a new model with parameters. The delivery may include a complete or partial model. • Model Download: Transferring models from the network to the Unreal Engine. • Model Upload: Transferring models from UE to NW. • Federative Learning / Federative Training: A machine learning technique for training AI / ML models across multiple distributed edge nodes (e.g., UE, gNB) that each perform local model training using local data samples. The technique uses multiple interactions of the models but does not exchange local data samples. • Offline field data: Data collected from the field and used for offline training of AI / ML models. • Online field data: Data collected from the field and used for online training of AI / ML models. • Model monitoring: A procedure for monitoring the inference performance of AI / ML models. • Supervised learning: The process of training a model from inputs and their corresponding labels. • Unsupervised learning: The process of training a model without labeled data. • Semi-supervised learning: A process of training a model using a mixture of labeled and unlabeled data. Reinforcement Learning (RL): The process of training an AI / ML model using inputs (also known as states) and feedback signals (also known as rewards) generated from the model's output (also known as actions) in the environment in which it interacts. • Model activation: Enabling an AI / ML model for a specific function. • Model deactivation: Disabling the AI / ML model for specific functions. • Model Identification: Identification of AI / ML models for a common understanding between the network and the user interface (UE). Information about the AI / ML model may (or may not) be shared during model identification. • Function Identification: Identifying AI / ML functions for a common understanding between the network and the user interface (UE). Information about AI / ML functions may (or may not) be shared during function identification. These functions may be identified, for example, with various different levels of granularity depending on the embodiment.

[0037] To enable the development of models applicable to specific conditions (e.g., scenarios, settings, sites, device types, etc.), it may be useful to consider ways of associating datasets with specific applicability conditions. For example, supporting signaling of network-side applicability information may be used for UE-side data collection. Correspondingly, supporting signaling of UE-side applicability information may be used for network-side data collection. In this disclosure, what information is described as an “applicability relationship” may include whether or not a model is applicable. That is, a message reporting that a model is not applicable should generally be considered an “applicability relationship.”

[0038] It may be useful to define and consider applicable conditions for features / models, at least for the UE-side model and the UE portions of both models. These applicable conditions can be used, for example, to enable the development of scenarios, configurations, sites, and / or other specific models, and, where necessary, to report the applicability of models to the network. It may also be useful to consider whether and how the UE reports applicable conditions for supported features, and, where necessary, for supported models and / or supported features. Additionally or alternatively, it may be useful to consider whether and how performance requirements for features / models should be defined (and possibly as part of the applicable conditions), and to consider potential improvements to legacy UE reporting features.

[0039] Procedures, protocols, and signaling for (one or more) bidirectional CSI use cases may also be useful. One such exemplary use case may involve ensuring that the UE-side model and the gNB-side model are configured and / or applied based on their applicable settings and / or scenarios. Another such example may involve ensuring that the models are properly matched on both the UE and gNB sides, for example, that when a CSI encoder is used on the UE, the corresponding CSI decoder is used on the gNB. Yet another such example may involve achieving simultaneous activation, deactivation, and / or switching of bidirectional models.

[0040] While models can generally be useful, the adoption of such techniques can encounter practical difficulties. For example, an AI / ML model for a given function (e.g., beam management, CSI, positioning) may be applicable under some conditions but not all. This is especially true for models on the UE side.

[0041] For example, a UE capable of performing AI / ML on a PHY for beam management functions might be equipped with an AI / ML model that has not been trained on several datasets associated with one or more beam configurations and / or one or more network areas (e.g., wide coverage, lower frequency layers). In such cases, the accuracy may be insufficient. Therefore, the model may be deemed unapplicable. In fact, under certain conditions, it may even be impossible to use that AI / ML model at all.

[0042] Even if a UE is equipped with an AI / ML model for a given function (e.g., CSI, beam management, positioning) and should report applicability (e.g., as part of its capabilities), various issues can still arise. For example, AI / ML model applicability can be dynamic (e.g., depending on where the UE is located) and can change after model training in response to new conditions. In one particular example, an AI / ML model might not work at one location, but when the UE moves, that AI / ML model might work at another cell where the UE has moved. As an addition or alternative, the applicability of an AI / ML model may only work under certain settings that the network has configured for the UE.

[0043] Furthermore, UE capability reporting traditionally does not involve the dynamic characteristics of AI / ML models, such as the applicability described above. Consequently, traditional UE capability signaling mechanisms (e.g., using Radio Resource Control (RRC) signaling) currently lack the ability to handle scenarios where a model is initially applicable and then subsequently becomes unapplicable. For example, if an RRCReconfigurationComplete message is sent to a UE whose AI / ML model-based capabilities are configured in an RRCReconfiguration message, the UE will no longer have an RRC-based means to notify the network that its AI / ML model is no longer applicable.

[0044] To address the challenges described above, embodiments of the present disclosure include a UE configured to report changes in previously reported applicability information relating to at least one AI / ML model associated with a function. According to the method, the UE sends messages reporting updates to the applicability information of at least one AI / ML model associated with a function configured in the UE. For example, in a first report, the UE indicates that the model is non-applicable. However, upon subsequent detection of a change in applicability, the UE reports second applicability information (for example, that the model is applicable).

[0045] The first applicability information may be reported in completion messages (e.g., messages indicating that a state transition to connection is complete, or messages indicating that reconfiguration is complete in response to an RRCReconfiguration message received while the UE was already connected). The second applicability information may be reported in UE support information. Such methods would complement the UE capabilities on the network side with precise information on whether the AI / ML model functionality on the UE side is applicable. In one such example, the UE may signal whether the AI / ML model functionality can be used under certain conditions, for example, in a given cell or set of serving cells, under the current configuration of a given UE.

[0046] Embodiments of this disclosure further include reporting causal values ​​associated with inferences about whether an AI-ML model can be applied to a function. Certain embodiments also include several configuration options for reporting methods that a UE may use to report when the applicability of an AI-ML model to a function is no longer valid.

[0047] Figure 2 is a signaling diagram illustrating an exemplary message flow according to a particular embodiment of the present disclosure. In this example, network node 120 sends a model configuration message to UE 110 (step 210). The model configuration message configures and / or activates one or more UE-side AI / ML models. In response, UE 110 sends a first completion message to network node 120 (step 220). The first completion message indicates that one or more UE-side AI / ML models have been successfully applied. Network node 120 then sends a report configuration message to UE 110 (step 230). The report configuration message configures its UE to report the applicability (or lack thereof) of the (one or more) models. In response, UE 110 sends a second completion message to network node 120 (step 240).

[0048] UE110 then determines that one or more of the models (one or more) are no longer applicable (step 250). In response, UE110 sends a model applicability status message to network node 120 (step 260). The model applicability status message indicates that one or more models are no longer applicable. In some embodiments, the model applicability status message also includes a cause value indicating why that model is no longer applicable. In other embodiments, the applicability status message additionally or alternatively includes a designation of another model associated with the function that is applicable (for example, that other model may therefore be used instead).

[0049] The messages used to communicate between UE110 and network node 120 can take various forms depending on the embodiment. Therefore, certain embodiments use RRC signaling for this purpose. For example, one or both of the completion messages could be an RRC setup completion message, an RRC restart completion message, or an RRC reconfiguration completion message. As another example, a model applicability status message could be an RRC restart message, an RCE setup message, or an RRC reconfiguration message. These RRC messages, other RRC messages, or appropriate messages of another protocol may also be used, in addition to or as an alternative to, any of the messages shown in any of the embodiments described herein (for example, the embodiments shown in Figures 2 to 10).

[0050] While the example in Figure 2 shows the model configuration message and the report configuration message as separate messages, it should be noted that in some embodiments, a single configuration message may be used to provide similar functionality.

[0051] Accordingly, certain embodiments of this disclosure enable the network to remain continuously aware of the applicability status of the AI / ML model for the corresponding function while a given RRC configuration (received, for example, in an RRC setup message, RRC restart message, or RRC reconfiguration message) is applied by the UE110. Thus, changes in the applicability criteria of that model within the cell's coverage area can be dynamically taken into account by the network in its decision-making.

[0052] In this disclosure, the terms “ML model,” “AI model,” “AI / ML model,” or simply “model” are interchangeable. A model may be implemented at a first node (for example, the UE in the case of a model on the UE side). In some embodiments, a model may direct a feature version to a second node. If the model is updated, the feature version may be modified by the first node.

[0053] The models disclosed herein correspond to the ability to receive one or more inputs (e.g., measurements, (one or more) settings) and may provide one or more predictions or estimates of a certain type (e.g., time-domain and / or spatial-domain predictions of beam measurements) as an outcome. In one example, an ML model corresponds to the ability to receive a measurement of a reference signal (e.g., transmitted on beam X) as input at time instance t0 and may provide a prediction of the reference signal at timer t0+T as an outcome. In another example, an ML model corresponds to the ability to receive a measurement of a reference signal X (e.g., transmitted on beam x), such as a synchronous signal block (SSB) with index "x", and may provide a prediction of another reference signal Y (e.g., transmitted on beam x), such as an SSB with index "x", transmitted on a different beam. Another example is an ML model for aiding CSI estimation, in which case the ML model is a unique ML model with respect to the UE and a certain ML model within the NW side. Together, both ML models provide a shared network. The function of the ML model on the UE would be to compress the channel input, and the function of the ML model on the NW side would be to decompress the output received from the UE. A similar approach can be applied for positioning, where the input could be some form of channel impulse related to a certain temporal reference point (generally, a TP (transmitting point)). The NW side's objective would be to detect different peaks in the impulse response that reflect the multipath experienced by the radio signal arriving at the UE. For positioning, another approach is to input multiple sets of measurements into the ML network and derive an estimated position of the UE based on them. Another ML model would be one that should be able to assist the UE in channel estimation or interference estimation for channel estimation. Channel estimation, for example, is for PDSCH and can be associated with a specific set of reference signal patterns transmitted from the NW to the UE.The ML model then becomes part of the receiver chain within the UE and may not be directly visible in the reference signal pattern, such as being set up / scheduled for use between the NW and the UE. Another example of an ML model for CSI estimation is to predict a suitable CQI, precoding matrix indicator (PMI), rank indicator (RI), CSI reference signal (CRS) resource indicator (CRI), or similar value for the future.

[0054] The network may comprise general network nodes, gNBs, base stations, units within base stations for handling at least some ML operations, relay nodes, core network nodes, core network nodes for handling at least some ML operations, devices supporting D2D (device-to-device) communication, location management functions (LMFs), or other types of location servers.

[0055] With respect to time, frequency, and / or space, the output of an AI / ML model may be in a different time instance, a different frequency location, a different spatial direction, or a combination of time / frequency / space, than the model input. In the time domain example, an ML model may have the capability to receive a measurement of a reference signal (e.g., transmitted on beam X) as input in time instance t0, and provide a prediction of the reference signal as an outcome in time instance t0+T. In the space domain example, an ML model may have the capability to receive a measurement of a reference signal X (e.g., transmitted on beam x, such as an SSB with index "x") as input, and provide an estimate or prediction of the link quality of another reference signal transmitted on a different beam (e.g., reference signal Y transmitted on beam y) as an outcome.

[0056] Regarding the model structure, the ML model can be entirely contained within the UE or separated between the UE and the network. An example of a separated structure is an ML model for aiding CSI estimation, where a possible setup of the ML model is a separated model, comprising an intrinsic submodel within the UE and a submodel on the NW side, which cooperate to produce the desired outcome for the entire ML model. The function of the submodel in the UE would be to compress the channel input, and the function of the submodel on the NW side would be to decompress the output received from the UE. It is even possible to apply something similar for positioning, where the input could be some form of channel impulse related to a certain temporal reference point. The objective on the NW side would be to detect different peaks in the impulse response corresponding to different receiving directions of the radio signal on the UE side.

[0057] One example of a model included within the UE is for improved positioning, where, for instance, an ML model implemented in the UE can take multiple sets of measurements (each corresponding to a downlink signal from a different network node) as input and derive an estimated position of the UE based on them.

[0058] Regarding utility for PHYs, ML models can be used for many functions, including (e.g.) channel estimation, LOS / NLOS classification, beam selection, UE location estimation, and link adaptation. For example, an ML model may be able to assist a UE in channel estimation, which may or may not incorporate interference estimation. Channel estimation is, for example, about a physical downlink scheduled channel (PDSCH) and may be associated with a specific set of reference signal patterns transmitted from the NW to the UE. That ML model would then be part of the receiver chain within the UE and may not be directly visible in the reference signal patterns as something set / scheduled for use between the NW and the UE. Another example of an ML model for CSI estimation is to predict a favorable CQI, PMI, RI, or similar value for the future. The future may be a certain number of slots after the UE has performed its last measurement, or it may target a specific slot at a time in the future.

[0059] According to various embodiments, the UE is connected to a network in the RRC_CONNECTED state (for example, the UE may receive and transmit data and / or control information) and configured to perform a specific function by using an AI / ML model (sometimes referred to as an AI / ML model function). That function could be, for example, beam measurement prediction in the time domain. The function of the model could be, for example, for one of the following, which can also be grouped as a function area (one or more AI / ML model functions per area): · CSI report Beam management (BM) • Wireless Resource Management (RRM) measurement • Link compatibility • Sending a Hybrid Automatic Resend Request (HARQ) • Data transmission • Data reception • Power control UE positioning • Random access transmission • Energy efficiency (e.g., intermittent reception (DRX) setting)

[0060] For example, a beam management (BM) function could exist for one or more AI / ML models, where the model (e.g., in a UE) can infer one or more time-domain predictions related to BM. For example, a UE may be configured by the network to report one or more time-domain predictions and / or CSI-RS and / or phase-tracking reference signal (PTRS) measurements (e.g., on a physical uplink control channel (PUCCH) and / or physical uplink shared channel (PUSCH)) (e.g., by receiving reporting settings for AI / ML). Other examples, additionally or alternatively, may include inferring one or more frequency-domain and / or spatial-domain predictions or estimates related to beam management.

[0061] A UE is considered to have its AI / ML functionality configured when at least one action related to that functionality is configured. For example, UE110 may be configured to report BM and / or CSI and / or SSB forecasts to one configured serving cell.

[0062] As another example, the model could be for aspects related to mobility measurements (e.g., reference signal received power (RSRP), reference signal received quality (RSRQ), and received signal strength indicator (RSSI)) and / or radio link faults (RLF) (e.g., predicting RLF). Furthermore, the model could also be used to perform predictions related to radio link monitoring (RLM) relationship timers (e.g., T310) and / or counters (e.g., N310 and N311).

[0063] In particular, the model may be used for measurement, prediction, or estimation as part of the measurement framework specified in 3GPP TS38.331 §5.5, which describes how the UE performs the measurement (e.g., measurement setup), what triggers the measurement report (e.g., event-triggered reporting, periodic reporting), and what content should be included in the measurement report.

[0064] The methods disclosed above may be applicable to (one or more) AI / ML models associated with an AI / ML model function, or may be applicable to AI / ML model functions in a compatible manner.

[0065] An AI / ML model is applicable when, for a given function, the AI / ML model can be configured and used under relevant conditions (e.g., by the UE, in the case of a UE-side model). For example, an AI / ML model for a function may be considered applicable when the AI / ML model is capable of producing an output (e.g., a time-domain prediction of beam measurement with sufficient accuracy). For example, accuracy for beammeters can be quantified in terms of the mean Layer 1 (L1) RSRP difference of the top 1 predicted beam compared to an ideal beam (sweeping all beams). Alternatively, accuracy can be considered as a cumulative distribution function (CDF) percentile of the L1-RSRP difference for the top 1 predicted beam. The beam prediction accuracy percentage may have, for example, a 1 dB margin for the top 1 beam.

[0066] In another example, the UE could also receive a threshold from the NW to compare against a key performance indicator (KPI) of accuracy, in order to determine whether the model is applicable.

[0067] In another example, a model may be considered applicable if it is capable of making predictions with at least a threshold confidence value. If the UE110 can estimate how reliable each prediction is, the NW can determine, on a sample basis per input, whether or not to use that prediction. That is, the model may be considered "applicable" for some of the data it has experienced (and, in some cases, not "applicable" for others). For example, the UE may report a predicted confidence interval (downlink and / or uplink) where there exists a predicted L1-RSRP / signal-to-interference noise ratio (SINR) for the beam with probability x (e.g., there is a 95% probability that the L1-RSRP is within the SINR range of [8dB, 10dB]).

[0068] The predicted values ​​may be reported, for example, as a probability density function using a Gaussian mixture. The predictions may then be reported using parameters that describe the Gaussian components of the mixture (e.g., the mean, variability, and component weights for each component).

[0069] As an addition or alternative, a model may be considered applicable if, when it collected and trained the model in the current UE configuration / scenario, the model was not older than a certain threshold T, and / or if the NW can determine T based on, for example, a change in deployment (new beam pattern, new cell, etc.).

[0070] An AI / ML model for a function may be considered unapplicable if it either fails to produce some outputs or produces outputs that are not sufficiently accurate. If a UE has multiple AI / ML models for the same function and different models are applicable to different scenarios, an AI / ML model may be said to be unapplicable if none of the AI / ML models for that function are applicable to that function. In other cases, instead of reporting unapplicability, the UE may simply switch to another model that is applicable to that function. Similarly, an AI / ML model may be said to be applicable if at least one of the AI / ML models for that function is applicable to that function when the UE is configured.

[0071] According to this method, there may be different reasons why an AI / ML model is not applicable. These reasons may include, for example, location (e.g., geographical area), UE configuration, network configuration, and / or mobility characteristics.

[0072] Regarding location, an AI / ML model for a function may be applicable in the first area of ​​the network where the UE is registered, but the same AI / ML model for that function may not be applicable in the second area of ​​the network where the UE is registered. For example, if a UE camps in to cell A while idle and then transitions to a connected state, the AI / ML model for that function may be considered applicable to cell A. However, if the idle UE performs cell reselection and moves to cell C, the AI / ML model for that function may no longer be applicable. One reason for this may be that the training dataset used to train the AI / ML model represents the first area but not the second area.

[0073] In this context, "location" may include one or more of the following: • One or more cells (defined by one or more cell identifiers, such as a global cell identifier) • One or more tracking areas • One or more tracking area codes • One or more registration areas • One or more Wireless Access Network (RAN) based notification areas • GPS location • GPS defined area • Coverage area of ​​the list of Wireless Local Area Network (WLAN) access points (APs) • Coverage area of ​​the Bluetooth beacon list • Within a given type of deployment (e.g., small cell, large cell, indoor, outdoor) • A list of public land mobile network (PLMN) and / or non-public network (NPN) identifiers (for example, an NPN ID may indicate a specific factory setting, and the training data used in that factory may only be applicable within that factory and not elsewhere).

[0074] Regarding UE configuration, an AI / ML model for a function may be applicable when a first configuration is set in the UE (for example, using a first RRCReconfiguration message or information element (IE)). However, the same AI / ML model for that function may not be applicable when a second configuration is set in the UE (for example, using a second RRCReconfiguration message or IE). Depending on the embodiment, the first and / or second configurations may include lower layers, bearer configurations, (one or more) measurement configurations, MIMO layer configurations, etc.

[0075] Therefore, when the UE transitions to a connected state (for example) and receives a setting equivalent to the first setting, the AI / ML model for that function may be applicable. However, when the UE transitions to a connected state and receives a setting equivalent to the second setting, the AI / ML model for that function may be considered inapplicable.

[0076] One reason why one setting might be considered applicable while another is not is that the training dataset used to train an AI / ML model on a given UE setting may lead to a model that does not produce accurate (inference) outputs for one or more UE settings. For example, an AI / ML model on a feature might be applicable to predicting measurements in a first set of frequencies (e.g., frequency range 1 (FR1) and / or specific frequencies (e.g., f0, f1, f2)) but not to predicting measurements in a second set of frequencies (e.g., frequency range 2 (FR2) and / or frequencies f7, f8, f9). Another reason might be that the AI / ML model is trained using a certain CSI-RS periodicity. For example, a UE might predict a 20ms periodicity because it is possible to make channel predictions during the next 10ms (mid-measurement). However, if the UE is set to a non-periodic CSI-RS or 40ms periodicity, this could make the model inaccurate.

[0077] Network configuration aspects that may be relevant to whether a model is considered applicable may include single-beam versus multi-beam configuration, configuration information broadcast by the network, and / or beamforming patterns. For example, a network may instruct that it use AI / ML to perform beam prediction, CSI prediction, and / or positioning. That is, if a network uses a network-based AI / ML model, the network may, for example, instruct that the UE should not activate such features.

[0078] Additionally, the mobility characteristics of a UE may be relevant to whether a model is applicable. For example, an AI / ML model for a function may be applicable when the UE's mobility characteristics belong to one category, and not applicable when the UE's mobility characteristics belong to a second category. In one particular example, a UE may be slow (as classified by the UE based on sensor-based measurements of the UE and / or network-defined criteria such as speedStateReselectionPars as defined in the RRC specification, TS38.331 v17.3), and the training data used to train its AI-ML model is exclusively in this mobility class. However, if the UE is in a different mobility class when transitioning from idle to inactive, for example, the AI / ML model for its function may not be applicable. In this disclosure, idle, inactive, and connected states are states in which the UE110 is with respect to its connectivity to the network. These terms should be interpreted in accordance with 3GPP standards.

[0079] In another example, time beam forecasting may be applicable based on UE mobility. In one such example, time beam forecasting may be applicable based on whether the UE is moving at a constant or near-constant speed. In yet another example, time beam forecasting may be applicable based on the type of mobility (e.g., in a vehicle or train, which can provide a more predictable trajectory). In yet another example, time beam forecasting may be applicable based on whether the UE is rotating.

[0080] Next, features related to reporting the applicability of a model in various embodiments are described. In a set of such embodiments, after the UE sends a completion message (RRCReconfigurationComplete or RRCResumeComplete) acknowledging the applicability of the AI / ML model functionality, the UE reports the inapplicability of its AI / ML model functionality to the network if it determines that the AI / ML model functionality is no longer applicable under the current UE configuration and (one or more) existing conditions, such as the UE's location.

[0081] One option is that when the UE determines that its AI / ML model functionality is not applicable, the UE sends a UE support information message to the network node, including that instruction in the UE support information message, indicating that one or more previously acknowledged AI / ML model functionality is no longer applicable (for example, under (one or more) current scenarios and / or settings).

[0082] One option is that when the UE determines that its AI / ML model functionality is not applicable, it deactivates that AI / ML model functionality. This action may be combined with reporting an indication of inapplicability in the UE support information message.

[0083] One option is that when a UE determines that its AI / ML model functionality is not applicable, the UE autonomously switches to another AI / ML model functionality pre-configured by the network (but not previously activated). The benefit here is when a network node knows there are other potentially applicable AI / ML models and does not want to bother with (one or more) inapplicable AI / ML models. However, the UE's switching and activation actions may be combined with reporting of inapplicability indications in UE support information messages, because the NW may want to be aware of inapplicability issues (e.g., related to the model or configuration), or alternatively, because there may be cases where none of the pre-configured AI / ML model functionality are applicable.

[0084] One option is that when the UE determines that its AI / ML model functionality is not applicable, the UE releases the configuration of that AI / ML model functionality (one or more settings). This action may be combined with reporting an indication of inapplicability in the UE support information message. The benefit here is that if a network node does not wish to deal with (one or more) inapplicable AI / ML models, it does not need to deal with them because those AI / ML models will be released by the UE.

[0085] One option is that when a UE determines that its AI / ML model functionality is no longer applicable, the UE autonomously switches (one or more) settings to default settings configured by the network as a fallback function. This action may be combined with reporting an indication of applicability in a UE support information message. The benefit here is that if a network node does not wish to deal with (one or more) inapplicable AI / ML models, it does not need to deal with them, as those AI / ML models will be released by the UE and the basic functionality can still continue via a non-AI / ML model-based framework. For example, when an AI-ML model for L1-RSRP prediction for a beam management function is no longer applicable, the UE switches to reporting the actual measured L1-RSRP value instead of including the predicted L1-RSRP in the L1 report. In some embodiments, the absence of a predicted value associated with such a function is taken as an implicit indication that the AI / ML model for that function is no longer applicable; in some other embodiments, the UE explicitly includes that indication in a UE support information message; and in some embodiments, both explicit and implicit methods are used, as those indications are reported to different network nodes hosting different network functions.

[0086] In some embodiments, one or more fallback settings are specified individually for each AI / ML function. For example, a fallback setting for CSI reporting is set in the UE, which will only be applicable when an AI / ML model-based function is no longer applicable. In the case of multiple fallback settings for a given AI / ML function, the UE indicates in the report which fallback setting the UE has selected.

[0087] In some embodiments, there are one or more fallback settings applicable to all AI / ML functions configured in the UE. For example, there is a single fallback RRCReconfiguration that the UE applies when it recognizes that (in some embodiments) at least one or (in some other embodiments) all of the AI-ML model functions configured in the UE are no longer applicable. In the case of multiple fallback settings applicable to all AI / ML functions, the UE indicates in its reporting which fallback setting it has selected.

[0088] One option is for the UE to adopt one of the methods described above when it determines that its AI / ML model functionality is not applicable, and also to include instructions in the UE support information message that specify applicable settings for one or more AI / ML model functionality that would be applicable in the current configuration and scenario. For example, if the UE is configured to perform predicted L1-RSRP reporting for serving cells on F1, F2, and F3 frequencies in its configuration, the UE may indicate that it is not possible for the UE to apply such a configuration, but that it can report predicted L1-RSRP reporting for F1 and F2 frequencies based on its AI-ML model in the current configuration and scenario. The UE may indicate one or more of these recommendations or suggestions for reconfiguration to make its AI / ML model functionality applicable. For example, recommendations may include one or more of the following: • A new set of frequencies that can be predicted by the AI / ML model to which the predictive measurement is applicable. • A new set of serving cells that can be predicted by an AI / ML model to which this predictive measurement is applicable. • New reference signal settings for reporting and / or performing inference and / or prediction (for example, a network may have a UE configured to perform time-domain predictions of CSI-RS measurements, but for that cell, its AI / ML model capabilities are not applicable to CSI-RS, but its AI / ML model capabilities are applicable to (one or more) SSBs, and therefore the UE instructs the network to do so). The UE may, for example, propose a new CSI-RS periodicity. • New MIMO settings, • New CSI-MeasConfig.

[0089] One option is to provide an instruction indicating when the AI / ML model functionality is expected to become available again in terms of time, which could be due to, for example, a temporary shortage of computational resources or the arrival of new configurations. In another example, the UE might indicate that its AI / ML model functionality is available when the UE enters a low-mobility state.

[0090] In one option, each AI / ML model feature setting is associated with at least one identifier, such as a reporting setting ID. When the UE indicates that an AI / ML model feature is not applicable, the UE may include such identifiers. Consider an example where the UE has multiple reporting settings 1-6, each associated with one of three AI / ML models A, B, or C. In this example, model A is associated with predictive reporting setting ID=1 and predictive reporting setting ID=2. Model B is associated with predictive reporting setting ID=3 and predictive reporting setting ID=4. Model C is associated with predictive reporting setting ID=5 and predictive reporting setting ID=6. When it is determined that model C is not applicable, the UE may include the corresponding setting identifier and its applicability in a completion or status message, for example, as follows: • Prediction reporting setting ID=5: Not applicable. • Prediction reporting setting ID=6: Not applicable.

[0091] One option is to include causal values ​​or further applicability information in the message. In particular, UE110 may indicate one or more causal values ​​associated with an AI / ML model feature reported as inapplicable. Causal values ​​may indicate, for example: • Unapplicable network locations (for example, a UE connected to a cell where its AI / ML model functionality does not provide output, and / or provides output with insufficient accuracy and / or high error and / or uncertainty), • Inapplicable AI / ML model outputs (for example, the model cannot provide the reliability metric of its predictions required by the network to utilize its predictions. For example, the network may use the reliability of its predictions to determine how many beams should be transmitted), • AI / ML models are too old (for example, the network may determine that models older than a certain time are invalid due to network changes, etc.) • Inapplicable UE settings (for example, the UE is configured to report on frequency layers for which its AI / ML model functionality is not trained), • Inapplicable network settings (for example, the UE is connected to a network with settings that prevent its AI / ML model functionality from being trained), • Inapplicable UE mobility criteria (for example, UE trained its model using measurements while UE was a slow UE, but UE's current mobility class is fast). • Inapplicable CSI-RS configurations (for example, a network providing CSI-RS resources for channel estimation with a configuration in which its AI / ML model capabilities are not trained), • Inapplicable compute resource availability (for example, compute resources in the UE are limited, which may be affected by UE configuration and traffic patterns).

[0092] Next, features relating to the association of settings with model applicability reporting are described. In a set of embodiments, the UE is configured with additional information relating to the applicability reporting of AI / ML model functions. In some embodiments, such settings are provided for each AI / ML model function, while in some other embodiments, such settings are common to two or more or all of the AI / ML model functions.

[0093] In some embodiments, such settings are provided as part of the otherConfig field in the RRCReconfiguration message. In such embodiments, such settings are not stored after transitioning from the RRC inactive state to the RRC connected mode.

[0094] In some other embodiments, such a configuration is provided as part of an RRCReconfiguration message, which is stored in the UE context (for example, the masterCellGroup field in the RRCReconfiguration message) and restored when transitioning from an RRC inactive state to an RRC connected mode.

[0095] Such settings may include, for example, reporting criteria, such as inapplicability criteria for entering a particular state and / or inapplicability criteria for exiting a particular state. For example, the network may set instructions for the UE that indicate whether the UE should send inapplicability relation information when an AI-ML model for a function is no longer applicable, or if the UE has a set of pre-configured AI / ML models for a function, when none of those models are applicable. Once the UE understands that an AI / ML model for a function is no longer applicable, it may send a UEAssistanceInformation message with the instructions described above.

[0096] The network may configure the UE with instructions indicating whether the UE should send applicability relationship information when an AI-ML model for a function becomes applicable. Upon acknowledging that an AI / ML model for a function has become applicable, or when one or more of a pre-configured set of AI / ML models become applicable, the UE may send a UEAssistanceInformation message with instructions indicating that one or more AI / ML models for that function are again applicable. Note that the network may configure the UE with, for example, both of the above instructions or just one of them.

[0097] Reporting settings may include, as an addition or alternative, periodicity for reporting the inapplicability of AI-ML models to a feature. For example, the network may set a reporting interval for the UE such that the UE does not report this information more frequently than the network expects.

[0098] The reporting configuration may, as an addition or alternative, include a prohibition timer that prevents the reporting of two consecutive inapplicability information reports for an AI / ML model feature within a given interval. This mechanism would work to prevent the UE from sending a second inapplicability information report for the same AI / ML model feature within a given time window following the sending of a first inapplicability information report. This timer may be deactivated if, after the sending of the first inapplicability information report, the network provides a setting that affects that AI / ML model feature (for example, making that AI / ML model feature applicable, deactivated, or not configured).

[0099] Reporting settings may include the evaluation duration before reporting the inapplicability of an AI-ML model for a feature. That is, the network may set instructions for the UE that tell how long the UE should evaluate the applicability / inapplicability assessment before declaring that the AI-ML model for that feature is inapplicable. Such settings ensure that the network can take uniform actions for different UEs, even if different UEs implement different UE-based AI / ML models for the feature.

[0100] In some such embodiments, this instruction is set with respect to a time duration. In other such embodiments, this instruction is set with respect to the number of output samples of the AI / ML model for a function (e.g., a counter).

[0101] Reporting settings may include a trigger time at which the UE should consider the non-applicability criterion to be met for an AI-ML model of a feature. In other words, the network may set instructions for the UE that tell how long the UE should consider an AI-ML model to be applicable or not applicable before declaring that the AI-ML model for that feature is applicable or not applicable. Such settings ensure that the network does not receive too many reports when the output of its AI / ML model is fluctuating with high uncertainty.

[0102] Reporting settings may include whether to monitor AI / ML model features on the UE side that have been indicated as unapplicable when sending the RRCReconfigurationComplete message, which carries a list of applicable or unapplicable AI / ML model features on the UE side. For example, the network may instruct a UE to continue monitoring the applicability status of an L1-RSRP predictive relationship AI / ML model feature, even if the UE indicates that it cannot apply the AI / ML model feature. This could allow the network to be more opportunistic, for example, with respect to knowing whether a UE's AI / ML model feature has become applicable, and the network could use such features to improve UE KPIs and network KPIs.

[0103] Next, details relating to the transmission of applicability criteria after sending and receiving an RRCReconfiguration message are described. In a set of embodiments, a UE in RRC connected mode receives a configuration message (for example, an RRC reconfiguration message such as RRCReconfiguration as defined in TS38.331). The configuration message attempts to configure one or more AI / ML model functions in the UE and / or activate the UE with respect to one or more AI / ML model functions. For example, an AI / ML function may correspond to the UE being configured to report and / or perform one or more time-domain predictions of SSB and / or CSI-RS measurements. The reports may be sent to one or more serving cells of the UE. For example, measurements may be performed on resources associated with one or more of the UE's serving cells.

[0104] In another example, AI / ML functionality could correspond to the UE being configured to report and / or perform one or more spatial domain predictions for SSB and / or CSI-RS measurements. Measurements of resources associated with serving cells configured in the UE may also be performed.

[0105] As another example, the AI / ML functionality could correspond to the UE being configured to report and / or perform CSI predictions. Another example includes AI / ML functionality corresponding to the UE being configured to report and / or perform positioning predictions. The UE may be configured with models for one, some, or any combination of these functions.

[0106] In response to one or more AI / ML model functions being configured, the UE sends a completion message (e.g., an RRC reconfiguration completion message) to the network, which includes at least one instruction indicating that at least one of the configured (or to be configured / activated) AI / ML model functions is applicable. In some embodiments, the UE sends a completion message in response to determining that its AI / ML model is applicable.

[0107] The UE receives a configuration message (for example, an RRC reconfiguration message, such as the RRCReconfiguration message specified in TS38.331), and the configuration message configures the UE to report the applicability or inapplicability relating to one or more AI / ML model functions. In some embodiments, this configuration message is the same as the configuration message received to configure and / or activate one or more AI / ML model functions. In some such embodiments, if the UE receives a configuration to report applicability (or inapplicability) relationship reports for one or more AI / ML model functions, the UE considers those configurations active when the UE indicates that one or more of those AI / ML model functions are applicable.

[0108] In response to the establishment of an applicability relationship report for one or more AI / ML model functions, the UE sends a completion message (e.g., an RRC reconfiguration completion message) to the network and monitors the applicability of that one or more AI / ML model functions. In some embodiments, this completion message is the same as the completion message in which the establishment and / or activation of one or more AI / ML model functions is acknowledged.

[0109] After sending a completion message, the UE continues to monitor the applicability of one or more AI / ML models for the functionality for which it confirmed in the completion message that its AI / ML model is applicable. If the UE determines that one or more AI / ML models are not applicable for that functionality, the UE may send an instruction to the network in a message (e.g., UEAssistanceInformation). This instruction may indicate that at least one of the configured AI / ML model functionalities is not applicable.

[0110] An example is shown in the signaling diagram in Figure 3. In the example in Figure 3, the configuration / activation of the UE-side AI / ML model function was received in a different RRCReconfiguration message compared to the configuration for reporting the inapplicability of one or more of the UE-side AI / ML model functions that the UE acknowledged in the previous RRCReconfigurationComplete message.

[0111] Specifically, in step 310, UE110 receives a first RRC reconfiguration message from network node 120 to configure / activate the AI / ML model on the UE side. In step 320, UE110 sends a first RRC reconfiguration completion message to network node 120 instructing it to successfully apply the AI / ML model on the UE side. In step 330, UE110 receives a second RRC reconfiguration completion message from network node 120 to configure the reporting of applicability relationship information for the AI / ML model on the UE side. In step 340, UE110 sends a second RRC reconfiguration completion message to network node 120. In step 350, UE110 determines that the AI / ML model is not applicable for that function. In step 360, UE110 sends UE support information to network node 120, including an instruction that the AI / ML model is not applicable.

[0112] Another example is shown in the signaling diagram in Figure 4. In the example in Figure 4, the configuration / activation of UE-side AI / ML model functions and the configuration for reporting the inapplicability of one or more UE-side AI / ML model functions that the UE can currently apply are all within the same RRCReconfiguration message. In such an example, the UE would initiate monitoring of the applicability of one or more UE-side AI / ML model functions when it sends an RRCReconfigurationComplete message indicating that the one or more UE-side AI / ML model functions are currently being successfully applied. This works as an implicit way for the network to know that the UE is performing applicability monitoring for at least these UE-side AI / ML model functions.

[0113] In the example shown in Figure 4, in step 410, UE110 receives a first RRC reconfiguration message from network node 120 to configure / activate the AI / ML model on the UE side. The first RRC reconfiguration message also configures the reporting of applicability relationship information for the AI / ML model on the UE side. In step 420, UE110 sends a first RRC reconfiguration completion message to network node 120 instructing it to successfully apply the AI / ML model on the UE side. In step 430, UE110 determines that the AI / ML model is not applicable for that function. In step 440, UE110 sends UE support information to network node 120, including an instruction that the AI / ML model is not applicable.

[0114] Next, features relating to the transition of UE110 from an inactive state for configuration and reporting, according to various embodiments, are described. In a set of embodiments, a UE in an inactive state (e.g., RRC_INACTIVE) sends a request message (e.g., an RRC restart request message, such as RRCResumeRequest or RRCResumeRequest1 as defined in TS38.331) to a network (e.g., g node B), receives a response message (e.g., an RRC restart message, such as an RRCResume message as defined in TS38.331), and based on this, the UE enters a connected state (RRC_CONNECTED), and the response message (e.g., RRCResume) configures (and / or activates UE110 with respect to one or more AI / ML model functions) on UE110, or attempts to configure one or more AI / ML model functions on UE110.

[0115] For example, a first AI / ML function may correspond to the UE being configured to report and / or perform one or more time-domain predictions of SSB and / or CSI-RS measurements (for example, for a resource associated with one or more of the UE's configured serving cells) (for example, to one or more of the UE's configured serving cells). A second AI / ML function may correspond to the UE being configured to report and / or perform one or more spatial-domain predictions of SSB and / or CSI-RS measurements (for example, for a resource associated with one or more of the UE's configured serving cells) (for example, to one or more of the UE's configured serving cells). A third AI / ML function may correspond to the UE being configured to report and / or perform CSI predictions. A fourth AI / ML function may correspond to the UE being configured to report and / or perform positioning predictions.

[0116] In response to one or more AI / ML model features being configured, the UE sends a completion message (e.g., an RRC restart completion message) to the network (e.g., in response to the UE determining that the AI / ML model is applicable), which includes at least one instruction indicating that at least one of the configured (or to be configured / activated) AI / ML model features that is configured (and / or activated) is applicable.

[0117] After sending a completion message, the UE continues to monitor the applicability of one or more AI / ML models for the functionality for which the UE confirmed in the completion message that its AI / ML model is applicable. If the UE determines that one or more AI / ML models are not applicable for that functionality, the UE sends an instruction to the network in a message (e.g., UEAssistanceInformation) indicating that at least one of the configured AI / ML model functionality is not applicable. An example of an embodiment in which the UE indicates that an AI / ML model functionality is not applicable is shown in Figure 5.

[0118] It should be noted that in some embodiments, neither the AI / ML model function settings nor the settings related to reporting applicability relationship information for the AI / ML model functions are stored in the UE context. Such embodiments are similar in some respects to the embodiments described earlier, in that the UE receives a configuration message (e.g., RRCReconfiguration) that specifies the AI / ML model function settings and the settings related to reporting applicability relationship information for the AI / ML model functions.

[0119] That said, one option is that when the UE sends an RRC restart request message to target network node 120b (e.g., target node B), the AI / ML model function is not configured in UE 110. That is, UE 110 does not have its AI / ML model function configuration in its stored UE context (e.g., UE access hierarchy inactive context). In other words, its AI / ML model function configuration (e.g., a reporting configuration for the UE to report one or more time-domain predictions of beam measurements, such as an SS-RSRP prediction for a serving cell) is explicitly included in the RRC restart message. In response to that configuration, the UE determines whether its AI / ML model function is applicable.

[0120] In some embodiments, the AI / ML model feature settings that the UE receives (for example, reporting settings for the UE to report one or more time-domain predictions of beam measurements, such as SS-RSRP predictions for serving cells) are set in a subsequent RRC reconfiguration message instead of an RRC restart message. An example of such an implementation is given below. In this exemplary implementation, the UE receives its AI-ML model feature settings after sending an RRC restart complete message via an RRCReconfiguration message. Upon receiving such an RRCReconfiguration message, the UE determines that the AI-ML model feature settings are applicable at that time point, and this includes instructions in the RRCReconfigurationComplete message to indicate that the AI-ML model feature settings are applicable. After sending the RRCReconfigurationComplete message, the UE continues to monitor the applicability of the AI / ML model for (one or more) features for which the UE has confirmed in its completion message that the AI / ML model is applicable. If the UE determines that one or more AI / ML models for its functionality are not applicable, the UE sends an instruction to the network in a message (e.g., UEAssistanceInformation) indicating that at least one of the configured AI / ML model functions is not applicable. An example of an embodiment in which the UE sends an instruction that the AI / ML model function is not applicable after sending an RRC restart complete message, and subsequently after sending an RRCReconfigurationComplete message, is shown in the signaling diagram of Figure 6.

[0121] In other embodiments, AI / ML model function settings, rather than settings related to reporting applicability relationship information, are stored in the UE context. In one option, UE 110 is configured with its AI / ML model function when it sends an RRC restart request message to target network node 120b (e.g., target g node B). That is, the UE has its AI / ML model function settings in the UE's stored UE context (UE access hierarchy inactive context). The AI / ML model function is restored when the UE receives an RRC restart message (or when the UE sends an RRC restart request message), and the UE determines whether the restored AI / ML model function is applicable under the settings resulting from the UE applying the RRC restart message.

[0122] When the UE determines that its AI / ML model functionality is applicable, it sends an RRC restart complete message to the target network node, including the instruction (explicit or implicit) in the RRC restart complete message, which indicates that the AI / ML model functionality (one or more) that is configured (or should be configured / activated) during the RRC restart is applicable (for example, under (one or more) current scenarios and / or configurations).

[0123] After sending a completion message, the UE receives an RRCReconfiguration message to configure the UE to report the (in)applicability of one or more AI / ML model functions. The UE then monitors the applicability of (one or more) AI / ML models for functions for which it has confirmed in the completion message that its AI / ML model is applicable. If the UE determines that (one or more) AI / ML models are no longer applicable for that function, the UE sends an instruction to the network in a message (e.g., UEAssistanceInformation) indicating that at least one of the configured AI / ML model functions is no longer applicable. An example is shown in the signaling diagram in Figure 7.

[0124] In other embodiments, both the AI / ML model function settings and the settings related to reporting the applicability relationship information of the AI / ML model function are stored in that context. In one option, when the UE sends an RRC restart request message to a target network node (e.g., target g node B), the UE is configured with its AI / ML model function; that is, the UE has the AI / ML model function settings in its stored UE context (UE access hierarchy inactive context). The AI / ML model function is restored when the UE receives an RRC restart message (or when the UE sends an RRC restart request message), and the UE determines whether the restored AI / ML model function is applicable under the settings resulting from the UE applying the RRC restart message.

[0125] When the UE determines that its AI / ML model functionality is applicable, it sends an RRC restart complete message to the target network node, including the instruction (explicit or implicit) in the RRC restart complete message, which indicates that the AI / ML model functionality (one or more) that is configured (or should be configured / activated) during the RRC restart is applicable (for example, under (one or more) current scenarios and / or configurations).

[0126] After sending a completion message, the UE continues to monitor the applicability of (one or more) AI / ML models for the functions for which it confirmed in the completion message that its AI / ML model was applicable. If the UE determines that (one or more) AI / ML models are no longer applicable for its functions, the UE sends an instruction to the network in a message (e.g., UEAssistanceInformation) indicating that at least one of the configured AI / ML model functions is no longer applicable. An exemplary flowchart generally following such an embodiment is shown in Figure 8.

[0127] In contrast to some of the embodiments described above, other embodiments include a UE that transitions from idle mode (e.g., from inactive mode) for configuration and reporting related to the applicability of the AI / ML model for its functionality. The signaling diagram in Figure 9 shows one such example in which both the AI / ML model functionality configuration and the configuration for reporting applicability relation information are included in the setup message.

[0128] In some embodiments, an idle UE (e.g., RRC_IDLE) sends a request message (e.g., an RRC setup request message, such as RRCSetupRequest as defined in TS38.331) to a network (e.g., g node B), receives a response message (e.g., an RRC setup message, such as RRCSetup as defined in TS38.331), and based on this, the UE enters a connected state (RRC_CONNECTED), and the response message (e.g., RRCResume) attempts to configure (and / or activate the UE with respect to one or more AI / ML model functions) or configure one or more AI / ML model functions on the UE, and to monitor and report applicability relation information for those one or more AI / ML model functions.

[0129] In response to one or more AI / ML model features being configured, the UE sends a completion message to the network in the RRC setup message, such as an RRC setup completion message, which includes at least one instruction indicating that at least one of the configured AI / ML model features that has been configured (and / or activated) is applicable (or not applicable) (for example, when the UE determines that the AI / ML model is applicable or not applicable).

[0130] In response to receiving a configuration to monitor and report applicability relationship information for one or more AI / ML model functions, the UE monitors the applicability criteria for that one or more AI / ML model functions (at least for those for which the UE has affirmed the applicability of that AI / ML model function). After sending a setup complete message, the UE continues to monitor the applicability of the AI / ML model for functions for which the UE has (at least) confirmed in the completion message that the AI / ML model is applicable. If the UE determines that one or more AI / ML models are not applicable for that function, the UE sends an instruction to the network in a message (e.g., UEAssistanceInformation) indicating that at least one of the configured AI / ML model functions is not applicable.

[0131] In other embodiments, AI / ML model function settings are provided in the setup message, and settings for reporting applicability relationship information are provided during the completion of the first RRC reconfiguration. An example of such an embodiment is shown in Figure 10.

[0132] In some such embodiments, a UE in an idle state (e.g., RRC_IDLE) sends a request message (e.g., an RRC setup request message, such as RRCSetupRequest as defined in TS38.331) to a network (e.g., g node B), receives a response message (e.g., an RRC setup message, such as RRCSetup as defined in TS38.331), and based on this, the UE enters a connected state (RRC_CONNECTED), and the response message (e.g., RRCResume) either configures (and / or activates the UE with respect to one or more AI / ML model functions) or attempts to configure one or more AI / ML model functions on the UE.

[0133] In response to one or more AI / ML model features being configured, the UE sends a completion message to the network in the RRC setup message, such as an RRC setup completion message, which includes at least one instruction indicating that at least one of the configured AI / ML model features that has been configured (and / or activated) is applicable (or not applicable) (for example, when the UE determines that the AI / ML model is applicable or not applicable).

[0134] The UE receives a configuration message (for example, an RRC reconfiguration message as defined in TS38.331), which configures the UE to report an (or non-)applicability relationship for one or more AI / ML model functions that the UE deems applicable.

[0135] In response to the establishment of (non)applicability relationship reports for one or more AI / ML model functions, the UE sends a completion message to the network (e.g., an RRC reconfiguration completion message) and monitors the applicability of that one or more AI / ML model functions.

[0136] After sending a reconfiguration complete message, the UE continues to monitor the applicability of (one or more) AI / ML models for the functions for which it confirmed in the completion message that its AI / ML model is applicable. If the UE determines that (one or more) AI / ML models are not applicable for that function, the UE sends an instruction to the network in a message (e.g., UEAssistanceInformation) indicating that at least one of the configured AI / ML model functions is not applicable.

[0137] Some embodiments do not include AI / ML model function settings or settings for reporting applicability relationship information in the setup message, but such embodiments are similar to the embodiments shown in Figure 3.

[0138] In view of the foregoing, embodiments of the present disclosure include, for example, a method 150 implemented by UE 110, as shown in Figure 11. Method 150 includes sending a first completion message (block 160) indicating whether the model is applicable to a function configured in UE 110. Method 150 further includes reporting in a second message that the applicability of the model to the above function in UE has changed (block 170).

[0139] Other embodiments include, for example, method 180 implemented by network node 120, as shown in Figure 12. Method 180 includes receiving a first completion message from UE 110 indicating whether the model is applicable to a function configured in UE 110 (block 185). Method 180 further includes receiving a report from UE 110 in a second message indicating that the applicability of the model to the above function of the UE has changed (block 190).

[0140] The UE110 can be implemented, for example, as schematically shown in the example in Figure 13. The UE110 in Figure 13 comprises a processing circuit 112, a memory circuit 114, and an interface circuit 111. The processing circuit 112 is communicatively coupled to the memory circuit 114 and the interface circuit 111, for example, via a bus 115. The processing circuit 112 may comprise one or more microprocessors, microcontrollers, hardware circuits, discrete logic circuits, hardware registers, digital signal processors (DSPs), field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), or a combination thereof. For example, the processing circuit 112 may be programmable hardware capable of executing software instructions stored in the memory circuit 114, for example, as a machine-readable computer program 113. The memory circuit 114 in various embodiments may include, but are not limited to, any non-temporary machine-readable media known or that can be developed in the Art, whether volatile or non-volatile, including solid-state media (e.g., SRAM, DRAM, DDRAM, ROM, PROM, EPROM, flash memory, solid-state drives, etc.), removable storage devices (e.g., Secure Digital (SD) cards, miniSD cards, microSD cards, Memory Sticks, thumb drives, USB flash drives, ROM cartridges, Universal Media Discs), fixed drives (e.g., magnetic hard disk drives), etc., either as a whole or in any combination.

[0141] The interface circuit 111 may be a controller hub configured to control the input / output (I / O) data paths of the UE 110. Such I / O data paths may include data paths for exchanging signals over a network. The interface circuit 111 may be implemented as a single physical component, or as multiple physical components arranged sequentially or separately, any of which may be communicatively coupled with any other, or may communicate with any other via the processing circuit 112. For example, the interface circuit 111 may comprise a transmitter 116 configured to send radio communication signals and a receiver 117 configured to receive radio communication signals.

[0142] The UE 110 may be configured to implement the method 150 described above. In one example, the processing circuit 112 may be configured to send a first completion message via the interface circuit 111 indicating to the UE whether the model is applicable to the configured function. The processing circuit 112 may further be configured to report in a second message via the interface circuit 111 that the applicability of the model to the above function of the UE has changed.

[0143] Another embodiment includes a computer program 113 that, when executed on the processing circuit 112 of the UE 110, provides instructions to cause the UE 110 to perform the method 150 described above.

[0144] Another embodiment includes a carrier containing a computer program 113, which is one of the following: an electronic signal, an optical signal, a radio signal, or a computer-readable storage medium.

[0145] Similarly, a network node 120 (for example, node gB) may be implemented as schematically shown in the example in Figure 14. The network node 120 in Figure 14 comprises a processing circuit 122, a memory circuit 124, and an interface circuit 121. The processing circuit 122 is communicatively coupled to the memory circuit 124 and the interface circuit 121, for example, via a bus 125. The processing circuit 122 may comprise one or more microprocessors, microcontrollers, hardware circuits, discrete logic circuits, hardware registers, digital signal processors (DSPs), field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), or a combination thereof. For example, the processing circuit 122 may be programmable hardware capable of executing software instructions stored in the memory circuit 124, for example, as a machine-readable computer program 123. The memory circuit elements 124 of various embodiments may include, but are not limited to, any non-transient machine-readable media known or that can be developed in the Art, whether volatile or non-volatile, including solid-state media (e.g., SRAM, DRAM, DDRAM, ROM, PROM, EPROM, flash memory, solid-state drives, etc.), removable storage devices (e.g., Secure Digital (SD) cards, miniSD cards, microSD cards, Memory Sticks, thumb drives, USB flash drives, ROM cartridges, Universal Media Discs), fixed drives (e.g., magnetic hard disk drives), etc., either as a whole or in any combination.

[0146] The interface circuit 121 may be a controller hub configured to control the input / output (I / O) data paths of the network node 120. Such I / O data paths may include data paths for exchanging signals over the network. The interface circuit 121 may be implemented as a single physical component, or as multiple physical components arranged sequentially or separately, any of which may be communicatively coupled with any other, or may communicate with any other via the processing circuit 122. For example, the interface circuit 121 may comprise a transmitter 126 configured to send radio communication signals and a receiver 127 configured to receive radio communication signals.

[0147] Network node 120 may be configured to implement method 180 as described above. In one example, processing circuit 122 may be configured to receive a first completion message from UE 110 via interface circuit 121 indicating whether the model is applicable to a function configured in UE 110. Processing circuit 122 may further be configured to receive a second message from UE 110 via interface circuit 121 indicating that the applicability of the model to the above function in UE 110 has changed.

[0148] Another embodiment includes a computer program 123 that, when executed on the processing circuit 122 of the network node 120, provides instructions to cause the network node 120 to perform the method 180 described above.

[0149] Another embodiment includes a carrier containing a computer program 123, which is one of the following: an electronic signal, an optical signal, a radio signal, or a computer-readable storage medium.

[0150] The computing devices described herein (e.g., UE110, network node 120) may include the shown combinations of hardware components, but other embodiments may comprise computing devices with different combinations of components. It should be understood that these computing devices may comprise any suitable combination of hardware and / or software required to perform the tasks, features, functions, and methods disclosed herein. The determining, calculating, acquiring, or similar operations described herein may be performed by processing circuits, which process information by, for example, converting acquired information to other information, comparing acquired or converted information to information stored in the network node, and / or performing one or more operations based on the acquired or converted information and as a result of the decisions made by the processing. Furthermore, although components are shown as a single box located within a larger box, or as a single box nested within multiple boxes, in practice, the devices described herein may comprise multiple different physical components that constitute a single shown component, and functions may be separated between the distinct components.

[0151] Next, additional embodiments are described. At least some of these embodiments may be described for illustrative purposes as applicable in certain contexts and / or wireless network types, but the embodiments are similarly applicable in other contexts and / or wireless network types not explicitly described.

[0152] Figure 15 shows an example of a communication system 11100 according to several embodiments.

[0153] In this example, the communication system 11100 includes a communication network 1102 which includes an access network 1104 such as a radio access network (RAN) and a core network 1106 which includes one or more core network nodes 1108. The access network 1104 includes one or more access network nodes (one or more of which may commonly be referred to as network nodes 1110), such as network nodes 1110a and 1110b, or any other similar Third Generation Partnership Project (3GPP) access nodes or non-3GPP access points. Furthermore, as will be understood by those skilled in the art, network nodes are not necessarily limited to implementations in which the radio portion and the bandwidth portion are supplied and integrated by a single vendor. Thus, it will be understood that network nodes include separate implementations or parts thereof. For example, in some embodiments, the communication network 1102 includes one or more open RAN (ORAN) network nodes. An ORAN network node is a node in a communications network 1102 that supports the ORAN specification (for example, a specification published by the O-RAN Alliance or any similar organization) and may operate alone or in conjunction with other nodes to implement one or more functions of any node in the communications network 1102, including one or more network nodes 1110 and / or core network node 1108.

[0154] Examples of ORAN network nodes include O-CUs (including open radio units (O-RUs), open distributed units (O-DUs), open central unit (O-CU) control planes (O-CU-CPs) or O-CU user planes (O-CU-UPs), RAN intelligent controllers (near-real-time or non-real-time) hosting software or software plugins such as quasi-real-time control applications (e.g., xApps) or non-real-time control applications (e.g., rApps), or any combination thereof (the adjective "open" specifies support for the ORAN specification). Network nodes may support the specification by supporting interfaces defined by the ORAN specification, such as A1, F1, W1, E1, E2, X2, Xn interfaces, open fronthaul user plane interfaces, or open fronthaul management plane interfaces. Furthermore, ORAN access nodes may be logical nodes within physical nodes. In addition, ORAN network nodes may be implemented in a virtualized environment in which one or more network functions are virtualized (as further described below). For example, the virtualized environment may include an O-cloud computing platform organized by a service management and orchestration framework via an O-2 interface defined by the O-RAN Alliance or equivalent technology. Network node 1110 facilitates direct or indirect connectivity of user equipment (UEs) 1112a, 1112b, 1112c, and 1112d (one or more of which are commonly referred to as UE1112) to the core network 1106 over one or more wireless connections.

[0155] Exemplary wireless communication over a wireless connection involves transmitting and / or receiving wireless signals using electromagnetic waves, radio waves, infrared waves, and / or other types of signals suitable for transmitting information without using wires, cables, or other material conductors. Furthermore, in different embodiments, the communication system 1100 may include any number of wired or wireless networks, network nodes, UEs, and / or any other components or systems that can facilitate or participate in the communication of data and / or signals, whether via a wired or wireless connection. The communication system 1100 may include and / or interface with any type of communication, telecommunication, data, cellular, wireless network, and / or other similar types of systems.

[0156] UE1112 may be any of a wide variety of communication devices, including a wireless device configured, set up, and / or operable to communicate wirelessly with network node 1110 and other communication devices. Similarly, network node 1110 is configured, capable, set up, and / or operable to communicate directly or indirectly with UE1112 and with other network nodes or devices in communication network 1102 to enable and / or provide network access, such as wireless network access, and / or to perform other functions, such as administration in communication network 1102.

[0157] In the illustrated example, the core network 1106 connects network node 1110 to one or more hosts, such as host 1116. These connections may be direct or indirect, via one or more intermediate networks or devices. In other examples, network nodes may be directly coupled to hosts. The core network 1106 includes one or more core network nodes (e.g., core network node 1108) structured with hardware and software components. The characteristics of these components may be substantially similar to those described with respect to the UE, network nodes, and / or hosts, and therefore their descriptions are generally applicable to the corresponding components of core network node 1108. An exemplary core network node includes one or more functions from among the following: 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), Subscriber Identifier Decryption Function (SIDF), Unified Data Management (UDM), Security Edge Protected Proxy (SEPP), Network Exposure Function (NEF), and / or User Plane Function (UPF).

[0158] Host 1116 may be owned or under the control of a service provider other than the operator or provider of the access network 1104 and / or the communication network 1102, and may be operated by or on behalf of the service provider. Host 1116 may host a variety of applications to provide one or more services. Examples of such applications include data collection services such as extracting and compiling live and pre-recorded audio / video content, data on various ambient conditions detected by multiple UEs, analytical functions, social media, functions for controlling or possibly interacting with remote devices, functions for alarms and surveillance centers, or any other such functions performed by the server.

[0159] Overall, the communication system 1100 in Figure 15 enables connectivity between the UE, network nodes, and hosts. In this sense, the communication system may be configured to operate according to predefined rules or procedures, including, but not limited to, any other suitable wireless communication standards, such as GSM (Global System for Mobile Communications), Universal Mobile Telecommunications System (UMTS), Long Term Evolution (LTE), and / or other suitable 2G, 3G, 4G, 5G standards, or any applicable future-generation standard (e.g., 6G), wireless local area network (WLAN) standards such as the IEEE 802.11 standard (WiFi), and / or any other suitable wireless communication standards such as global interoperability for microwave access (WiMAX), Bluetooth, Z-Wave, near-field communications (NFC) ZigBee, LiFi, and / or LoRa and Sigfox, or any low-power wide area network (LPWAN) standards.

[0160] In some examples, the communication network 1102 is a cellular network implementing 3GPP standardized features. Therefore, the communication network 1102 may support network slicing to provide different logical networks to different devices connected to the communication network 1102. For example, the communication network 1102 may provide ultra-high reliability low latency communication (URLLC) services to some UEs while providing extended mobile broadband (eMBB) services to other UEs, and / or also provide massive machine-type communication (mMTC) / massive IoT services to further UEs.

[0161] In some examples, UE1112 is configured to transmit and / or receive information without direct human interaction. For example, the UE may be designed to transmit information to access network 1104 on a predetermined schedule when triggered by an internal or external event, or in response to a request from access network 1104. Furthermore, the UE may be configured to operate in single, multi-RAT, or multi-standard modes. For example, the UE may operate with one or a combination of Wi-Fi, NR (New Radio), and LTE, i.e., configured for multi-radio dual connectivity (MR-DC), such as E-UTRAN (Enhanced UMTS Terrestrial Radio Access Network) New Radio-Dual Connectivity (EN-DC).

[0162] In this example, the hub 1114 communicates with the access network 1104 to facilitate indirect communication between one or more UEs (e.g., UE1112c and / or 1112d) and a network node (e.g., network node 1110b). In some examples, the hub 1114 may be a controller, router, content source and content analysis, or any other communication device described herein with respect to the UE. For example, the hub 1114 may be a broadband router that enables access to the core network 1106 for the UE. In another example, the hub 1114 may be a controller that sends commands or instructions to one or more actuators in the UE. The commands or instructions may be received from the UE, network node 1110, or by executable code, scripts, processes, or other instructions in the hub 1114. In yet another example, the hub 1114 may be a data collector that acts as temporary storage for UE data and, in some embodiments, can perform data analysis or other processing. In yet another example, the hub 1114 may be a content source. For example, with respect to a UE that is a VR headset, display, loudspeaker, or other media distribution device, the hub 1114 can retrieve VR assets, video, audio, or other media or data related to sensory information via network nodes, which the hub 1114 then provides to the UE either directly, after performing local processing, and / or after adding additional local content. In yet another example, the hub 1114 acts as a proxy server or orchestrator for the UE, especially if one or more of the UEs are low-energy IoT devices.

[0163] Hub 1114 may have always-on / persistent or intermittent connections to network node 1110b. Hub 1114 may also allow different communication methods and / or schedules between Hub 1114 and UEs (e.g., UE 1112c and / or 1112d), and between Hub 1114 and the core network 1106. In other examples, Hub 1114 connects to the core network 1106 and / or one or more UEs via a wired connection. Furthermore, Hub 1114 may be configured to connect to an M2M service provider on the access network 1104 and / or another UE via a direct connection. In some scenarios, a UE may establish a wireless connection with network node 1110 while still connected via Hub 1114 via a wired or wireless connection. In some embodiments, Hub 1114 may be a dedicated hub, i.e., a hub whose primary function is to route communications from UEs to network node 1110b and from network node 1110b to UEs. In other embodiments, the hub 1114 may be a non-dedicated hub, i.e., a device that can operate to route communication between the UE and the network node 1110b, but can also operate as a communication start and / or end point for several data channels.

[0164] Figure 16 shows the UE1200 in several embodiments. As used herein, UE refers to a device that is capable of, configured, and / or operable of communicating wirelessly with network nodes and / or other UEs. Examples of UEs include, but are not limited to, smartphones, mobile phones, cell phones, voice over IP (VoIP) phones, wireless local loop phones, desktop computers, personal digital assistants (PDAs), wireless cameras, gaming consoles or devices, music storage devices, playback devices, wearable terminal devices, wireless endpoints, mobile stations, tablets, laptop computers, laptop embedded equipment (LEE), laptop mounted equipment (LME), smart devices, wireless customer premises equipment (CPE), vehicles, vehicle-mounted or vehicle-embedded / integrated wireless devices, etc. Other examples include any UE identified by the Third Generation Partnership Project (3GPP), including narrowband Internet of Things (NB-IoT) UEs, machine-type communications (MTC) UEs, and / or enhanced MTC (eMTC) UEs.

[0165] A UE may support device-to-device (D2D) communication by implementing 3GPP standards 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 does not necessarily have a user in the sense of a human user who owns and / or operates the associated device. Instead, a UE may represent a device (e.g., a smart sprinkler controller) that is intended to be sold to or operated by a human user, but may not be associated with a particular human user, or may not be initially associated with a particular human user. Alternatively, a UE may represent a device (e.g., a smart electricity meter) that is not intended to be sold to or operated by an end user, but may be associated with a user or may operate for the user's benefit.

[0166] The UE1200 includes a processing circuit 1202 operably coupled via bus 1204 to an input / output interface 1206, a power supply 1208, memory 1210, a communication interface 1212, and / or any other components, or any combination thereof. Some UEs may utilize all or a subset of the components shown in Figure 16. The level of integration between components may vary from UE to UE. Furthermore, some UEs may include multiple instances of components, such as multiple processors, memories, transceivers, transmitters, and receivers.

[0167] The processing circuit 1202 is configured to process instructions and data and may be configured to implement any sequential state machine capable of executing instructions stored in memory 1210 as a machine-readable computer program. The processing circuit 1202 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 with appropriate firmware, a microprocessor or digital signal processor (DSP) with appropriate software, one or more stored computer programs, a general-purpose processor, or any combination of the above. For example, the processing circuit 1202 may include multiple central processing units (CPUs).

[0168] In this example, the input / output interface 1206 may be configured to provide an input device, an output device, or one or more interfaces to one or more input and / or output devices. Examples of output devices include speakers, sound cards, video cards, displays, monitors, printers, actuators, emitters, smart cards, other output devices, or any combination thereof. Input devices may allow a user to capture information to the UE1200. Examples of input devices include touch-sensitive or presence-sensitive displays, cameras (e.g., digital cameras, digital video cameras, webcams, etc.), microphones, sensors, mice, trackballs, directional pads, trackpads, scroll wheels, smart cards, etc. A presence-sensitive display may include a capacitive or resistive touch sensor for detecting user input. Sensors may include, for example, an accelerometer, gyroscope, tilt sensor, force sensor, magnetometer, light sensor, proximity sensor, biosensor, or any combination thereof. Output devices may use the same type of interface port as input devices. For example, a Universal Serial Bus (USB) port may be used to provide input and output devices.

[0169] In some embodiments, the power supply 1208 is structured as a battery or battery pack. Other types of power sources may be used, such as an external power source (e.g., an electrical outlet), a photovoltaic device, or a battery. The power supply 1208 may further include a power circuit for distributing power from the power supply 1208 itself and / or from an external power source via an interface such as an input circuit or power cable. Distributing power may, for example, be for charging the power supply 1208. The power circuit may perform any formatting, conversion, or other modifications to the power from the power supply 1208 to make that power suitable for each component of the UE 1200 to which it is supplied.

[0170] Memory 1210 may be memory, or configured to contain memory, such as random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic disks, optical disks, hard disks, removable cartridges, flash drives, etc. In one example, memory 1210 may contain one or more application programs 1214, such as an operating system, a web browser application, a widget, a gadget engine, or other application, and corresponding data 1216. Memory 1210 may store any of a variety of operating systems or combinations of operating systems for use by UE 1200.

[0171] Memory 1210 may be configured to include several physical drive units, such as a redundant array of independent disks (RAID), flash memory, USB flash drives, external hard disk drives, thumb drives, pen drives, key drives, high-density digital versatile disk (HD-DVD) optical disk drives, internal hard disk drives, Blu-ray optical disk drives, holographic digital data storage (HDDS) optical disk drives, external mini dual in-line memory modules (DIMMs), synchronous dynamic random access memory (SDRAM), external microDIMM SDRAM, smart card memory such as a tamper-proof module in the form of a universal integrated circuit card (UICC) containing one or more subscriber identification modules (SIMs) such as USIM and / or ISIM, other memory, or any combination thereof. The UICC may be, for example, an embedded UICC (eUICC), an integrated UICC (iUICC), or a removable UICC commonly known as a "SIM card". Memory 1210 may enable UE 1200 to access instructions, application programs, etc., stored in temporary or non-temporary memory media, to offload data, or to upload data. Products such as products utilizing a communication system may be tangibly embodied as memory 1210 or within memory 1210, and memory 1210 may be a device-readable storage medium or comprise a device-readable storage medium.

[0172] The processing circuit 1202 may be configured to communicate with an access network or other networks using a communication interface 1212. The communication interface 1212 may comprise one or more communication subsystems, including an antenna 1222, or may be communicatively coupled to the antenna 1222. The communication interface 1212 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 network node in the access network). Each transceiver may include a transmitter 1218 and / or receiver 1220 suitable for providing network communication (e.g., optical, electrical, frequency-allocated, etc.). Furthermore, the transmitter 1218 and receiver 1220 may be coupled to one or more antennas (e.g., antenna 1222), sharing circuit components, software, or firmware, or alternatively, being implemented separately.

[0173] In the embodiments shown, the communication functions of the communication interface 1212 may include cellular communication, Wi-Fi communication, LPWAN communication, data communication, voice communication, multimedia communication, short-range communication such as Bluetooth, near-field communication, location-based communication such as the use of the Global Positioning System (GPS) to determine location, other similar communication functions, or any combination thereof. The communication may be implemented in accordance with one or more communication protocols and / or standards, such as IEEE 802.11, Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), GSM, LTE, New Radio (NR), UMTS, WiMAX, Ethernet, Transmission Control Protocol / Internet Protocol (TCP / IP), Synchronous Optical Networking (SONET), Asynchronous Transfer Mode (ATM), QUIC, Hypertext Transfer Protocol (HTTP), etc.

[0174] Regardless of the sensor type, the UE may provide the output of data captured by the UE's sensors to network nodes via a wireless connection through the UE's communication interface 1212. The data captured by the UE's sensors may be communicated to network nodes via another UE through a wireless connection. The output may be periodic (e.g., once every 15 minutes if reporting detected temperature), in response to a triggering event (e.g., an alarm is sent when humidity is detected), in response to a request (e.g., a user-initiated request), random (e.g., to equalize the load from reports from several sensors), or a continuous stream (e.g., a live video feed of a patient).

[0175] As another example, the UE may include an actuator, motor, or switch relating to a communication interface configured to receive radio input from a network node via a wireless connection. In response to the received radio input, the state of the actuator, motor, or switch may change. For example, the UE may include a motor that adjusts the control surface or rotor of a drone in flight according to the received input, or a robotic arm that performs a medical procedure according to the received input.

[0176] A UE, in the form of an Internet of Things (IoT) device, can be a device for use in one or more application areas, which include, but are not limited to, urban wearable technology, augmented industrial applications, and healthcare. Non-exclusive examples of such IoT devices are devices that are connected refrigerators or freezers, TVs, connected lighting devices, energy meters, robotic vacuum cleaners, voice-controlled smart speakers, home security cameras, motion detectors, thermostats, smoke detectors, door / window sensors, flood / humidity sensors, electric door locks, connected doorbells, air conditioning systems such as heat pumps, autonomous vehicles, surveillance systems, weather monitoring devices, vehicle parking monitoring devices, electric vehicle charging stations, smartwatches, fitness trackers, head-mounted displays for augmented reality (AR) or virtual reality (VR), wearables for haptic augmentation or perceptual augmentation, water sprinklers, animal or product tracking devices, sensors for monitoring plants or animals, industrial robots, unmanned aerial vehicles (UAVs), and any kind of medical device such as a heart rate monitor or remotely controlled surgical robot, or devices embedded in them. The UE in the form of an IoT device comprises circuitry and / or software depending on the intended application of the IoT device, in addition to the other components described with respect to the UE1200 shown in Figure 16.

[0177] In another specific example, in an IoT scenario, a UE may represent a machine or other device that performs monitoring and / or measurement and transmits the results of such monitoring and / or measurement to another UE and / or network node. In this case, the UE could be an M2M device, which is sometimes called an MTC device in a 3GPP context. In one specific example, the UE may implement the 3GPP NB-IoT standard. In other scenarios, the UE may represent a vehicle, such as a car, bus, truck, ship, and airplane, or other equipment capable of monitoring its operational status and / or reporting on its operational status, or other functions associated with its operation.

[0178] In practice, any number of UEs can be used together for a single use case. For example, the first UE may be the drone itself, or integrated within the drone, providing the drone's speed information (obtained through a speed sensor) to the second UE, which is the remote controller operating the drone. When the user makes changes from the remote controller, the first UE may adjust the throttle on the drone (for example, by controlling an actuator) to increase or decrease the drone's speed. The first and / or second UEs may also include two or more of the functions described above. For example, the UE may have sensors and actuators and handle the communication of data about both the speed sensor and the actuator.

[0179] Figure 17 shows a network node 1300 according to several embodiments. As used herein, a network node refers to a device that is configured, set up, and / or operable to communicate directly or indirectly with UEs in a communication network and / or with other network nodes or devices. Examples of network nodes include, but are not limited to, access points (APs) (e.g., radio access points), base stations (BSs) (e.g., radio base stations, node B, evolved node B (eNB), and NR node B (gNB)), O-RAN nodes, or components of O-RAN nodes (e.g., O-RU, O-DU, O-CU).

[0180] Base stations can be categorized based on the amount of coverage they provide (or, in other words, the base station's transmit power level), and are therefore sometimes called femto base stations, pico base stations, micro base stations, or macro base stations, depending on the amount of coverage they provide. A base station can be a relay node or relay donor node that controls relays. Network nodes may also include one or more (or all) parts of a distributed radio base station, such as a centralized digital unit, a distributed unit (e.g., one in an O-RAN access node), and / or a remote radio unit (RRU), sometimes called a remote radio head (RRH). Such remote radio units may or may not be integrated with an antenna as an antenna-integrated radio. Parts of a distributed radio base station are sometimes called nodes in a distributed antenna system (DAS).

[0181] Other examples of network nodes include multiple transmit point (multi-TRP) 5G access nodes, MSR equipment such as multi-standard radio (MSR) BS, network controllers such as radio network controllers (RNCs) or base station controllers (BSCs), base station transceiver stations (BTSs), transmit points, transmit nodes, multi-cell / multicast coordinated entities (MCEs), operation and maintenance (O&M) nodes, operation support system (OSS) nodes, self-organizing network (SON) nodes, positioning nodes (e.g., evolved serving mobile location centers (E-SMLCs)), and / or drive test minimization (MDTs).

[0182] Network node 1300 includes a processing circuit 1302, a memory 1304, a communication interface 1306, and a power supply 1308. Network node 1300 can be assembled from multiple physically distinct components (e.g., node B components and RNC components, or BTS components and BSC components), each of which may have its own respective components. In some scenarios where network node 1300 has multiple distinct components (e.g., BTS components and BSC components), one or more of the distinct components may be shared among several network nodes. For example, a single RNC may control multiple node Bs. In such a scenario, each unique node B-RNC pair may, in some cases, be considered a single distinct network node. In some embodiments, network node 1300 may be configured to support multiple radio access technologies (RATs). In such embodiments, some components may be duplicated (e.g., separate memories 1304 for different RATs), and some components may be reused (e.g., the same antenna 1310 may be shared by different RATs). The network node 1300 may also include multiple sets of various indicated components for different wireless technologies, such as GSM, WCDMA, LTE, NR, WiFi, Zigbee, Z-wave, LoRaWAN, radio frequency identification (RFID), or Bluetooth wireless technologies, which are integrated into the network node 1300. These wireless technologies may be integrated into the same or different chips or sets of chips, and other components within the network node 1300.

[0183] The processing circuit 1302 may include one or more combinations of microprocessors, controllers, microcontrollers, central processing units, digital signal processors, application-specific integrated circuits, field-programmable gate arrays, or any other suitable computing devices, resources, or combinations of hardware, software, and / or encoded logic, which are capable of operating to provide network node 1300 functionality, either on its own or in combination with other network node 1300 components such as memory 1304.

[0184] In some embodiments, the processing circuit 1302 includes a system-on-a-chip (SOC). In some embodiments, the processing circuit 1302 includes one or more of the radio frequency (RF) transceiver circuit 1312 and the baseband processing circuit 1314. In some embodiments, the radio frequency (RF) transceiver circuit 1312 and the baseband processing circuit 1314 may be on separate chips (or sets of chips), boards, or units such as radio and digital units. In alternative embodiments, some or all of the RF transceiver circuit 1312 and the baseband processing circuit 1314 may be on the same chip or set of chips, board, or unit.

[0185] Memory 1304 may include, but is not limited to, any form of volatile or non-volatile computer-readable memory, including persistent storage, solid memory, remote-mount memory, magnetic media, optical media, random-access memory (RAM), read-only memory (ROM), mass storage media (e.g., hard disk), removable storage media (e.g., flash drive, compact disc (CD), or digital video disc (DVD)), and / or any other volatile or non-volatile, non-temporary device-readable and / or computer-executable memory device for storing information, data, and / or instructions that may be used by the processing circuit 1302. Memory 1304 may store any suitable instructions, data, or information, including other instructions, that may be executed by the processing circuit 1302 and utilized by the network node 1300, including applications that include one or more computer programs, software, logic, rules, code, and tables. Memory 1304 may be used to store calculations performed by the processing circuit 1302 and / or data received via the communication interface 1306. In some embodiments, the processing circuit 1302 and the memory 1304 are integrated.

[0186] Communication interface 1306 is used in wired or wireless signaling and / or data between network nodes, access networks, and / or UEs. As shown, communication interface 1306 includes (one or more) ports / (one or more) terminals 1316 for sending and receiving data to and from the network, for example, over a wired connection. Communication interface 1306 also includes a wireless front-end circuit 1318, which is coupled to or, in some embodiments, may be part of antenna 1310. The wireless front-end circuit 1318 includes a filter 1320 and an amplifier 1322. The wireless front-end circuit 1318 may be connected to antenna 1310 and processing circuit 1302. The wireless front-end circuit may be configured to adjust signals communicated between antenna 1310 and processing circuit 1302. The wireless front-end circuit 1318 may receive digital data to be sent to other network nodes or UEs via the wireless connection. The wireless front-end circuit 1318 can convert digital data into a radio signal with appropriate channel and bandwidth parameters using a combination of the filter 1320 and / or amplifier 1322. The radio signal can then be transmitted via the antenna 1310. Similarly, when receiving data, the antenna 1310 can collect a radio signal, which is then converted into digital data by the wireless front-end circuit 1318. The digital data can then be passed to the processing circuit 1302. In other embodiments, the communication interface may comprise different components and / or different combinations of components.

[0187] In some alternative embodiments, the network node 1300 does not include a separate radio front-end circuit 1318; instead, the processing circuit 1302 includes the radio front-end circuit and is connected to the antenna 1310. Similarly, in some embodiments, all or part of the RF transceiver circuit 1312 is part of the communication interface 1306. In yet another embodiment, the communication interface 1306, as part of a radio unit (not shown), includes one or more ports or terminals 1316, the radio front-end circuit 1318, and the RF transceiver circuit 1312, and the communication interface 1306 communicates with a baseband processing circuit 1314, which is part of a digital unit (not shown).

[0188] Antenna 1310 may include one or more antennas or antenna arrays configured to transmit and / or receive radio signals. Antenna 1310 may be coupled to the radio front-end circuit 1318 and may be any type of antenna capable of wirelessly transmitting and receiving data and / or signals. In some embodiments, Antenna 1310 is separate from the network node 1300 and can be connected to the network node 1300 through an interface or port.

[0189] The antenna 1310, the communication interface 1306, and / or the processing circuit 1302 may be configured to perform any receiving operations and / or certain acquisition operations as described herein as being performed by a network node. Any information, data, and / or signals may be received from the UE, another network node, and / or any other network equipment. Similarly, the antenna 1310, the communication interface 1306, and / or the processing circuit 1302 may be configured to perform any transmitting operations as described herein as being performed by a network node. Any information, data, and / or signals may be transmitted to the UE, another network node, and / or any other network equipment.

[0190] Power supply 1308 provides power to various components of network node 1300 in a form suitable for each component (for example, at the voltage and current levels required for each respective component). Power supply 1308 may further include, or be coupled to, a power management circuit for supplying power to the components of network node 1300 to perform the functions described herein. For example, network node 1300 may be connectable to an external power source (e.g., a power grid, an electrical outlet) via an input circuit or interface such as an electrical cable, thereby the external power source supplying power to the power circuit of power supply 1308. As a further example, power supply 1308 may include a power source in the form of a battery or battery pack connected to or integrated into the power circuit. The battery may provide backup power in the event of an external power failure.

[0191] Embodiments of network node 1300 may include additional components other than those shown in Figure 17 to provide several aspects of the network node's functionality, including any of the functions described herein and / or functions necessary to support the subject matter described herein. For example, network node 1300 may include user interface equipment for enabling information input to and output from network node 1300. This may enable a user to perform diagnostic, maintenance, repair, and other administrative functions for network node 1300.

[0192] Figure 18 is a block diagram of host 1400, which may be one embodiment of host 1116 of Figure 15, according to various aspects described herein. Host 1400 as used herein may be or comprise various combinations of hardware and / or software, including standalone servers, blade servers, cloud implementation servers, distributed servers, virtual machines, containers, or processing resources in a server farm. Host 1400 may provide one or more services to one or more UEs.

[0193] The host 1400 includes a processing circuit 1402 operably coupled to an input / output interface 1406, a network interface 1408, a power supply 1410, and memory 1412 via a bus 1404. Other embodiments may include other components. The characteristics of these components may be substantially the same as those described with respect to the devices in previous figures, such as Figures 12 and 13, and therefore their descriptions are generally applicable to the corresponding components of the host 1400.

[0194] Memory 1412 may include one or more computer programs, each containing one or more host application programs 1414 and data 1416, the data 1416 of which may include user data, for example, data generated by the UE for host 1400, or data generated by host 1400 for the UE. Embodiments of host 1400 may utilize only a subset or all of the components shown. Host application programs 1414 may be implemented in a container-based architecture and may provide support for video codecs (e.g., Multipurpose Video Coding (VVC), High Efficiency Video Coding (HEVC), Advanced Video Coding (AVC), MPEG, VP9) and audio codecs (e.g., FLAC, Advanced Audio Coding (AAC), MPEG, G.711), including transcoding for multiple different classes, types, or implementations of the UE (e.g., handsets, desktop computers, wearable display systems, heads-up display systems). The host application program 1414 may also provide user authentication and license checks, and may periodically report health, route, and content availability to a central node, such as a device in the core network or a device at the edge of the core network. Thus, host 1400 may select and / or direct different hosts for over-the-top services for the UE. The host application program 1414 may support various protocols, including HTTP Live Streaming (HLS), Real-Time Messaging Protocol (RTMP), Real-Time Streaming Protocol (RTSP), and Dynamic Adaptive Streaming over HTTP (MPEG-DASH).

[0195] Figure 19 is a block diagram showing a virtualized environment 1500 in which functions implemented by several embodiments can be virtualized. In this context, virtualization means creating a virtual version of an apparatus or device, which may include virtualizing hardware platforms, storage devices, and networking resources. The virtualization used herein may apply to any device or its components described herein 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 virtualized environments 1500 hosted by one or more hardware nodes, such as network nodes, UEs, core network nodes, or hardware computing devices acting as hosts. Furthermore, in embodiments in which the virtual nodes do not require wireless connectivity (e.g., core network nodes or hosts), the nodes may be fully virtualized. In some embodiments, the virtualized environment 1500 includes components defined by the O-RAN Alliance, such as an O-cloud environment organized by a service management and orchestration framework via an O-2 interface.

[0196] Application 1502 (which may alternatively be referred to as a software instance, virtual appliance, network function, virtual node, virtual network function, etc.) runs in the virtualized environment Q400 to implement some of the features, functions, and / or benefits of some of the embodiments disclosed herein.

[0197] Hardware 1504 includes processing circuits, memory for storing software and / or instructions executable by the hardware processing circuits, and / or other hardware devices described herein, such as network interfaces and input / output interfaces. The software is executed by the processing circuits to instantiate one or more virtualization layers 1506 (also called a hypervisor or virtual machine monitor (VMM)), providing VM1508a and 1508b (one or more of which may commonly be referred to as VM1508), and / or may implement any of the functions, features, and / or benefits described with respect to some embodiments described herein. The virtualization layer 1506 may present VM1508 with a virtual operating platform that looks like networking hardware.

[0198] VM1508 features virtual processing, virtual memory, virtual networking or interfaces, and virtual storage, and may be powered by the corresponding virtualization layer 1506. Different embodiments of the virtual appliance 1502 may be implemented on one or more of the VM1508s, and the implementation may be carried out in different ways. Hardware virtualization is referred to as network function virtualization (NFV) in several contexts. NFV can be used to consolidate many types of network equipment onto industry-standard high-volume server hardware, physical switches, and physical storage, which may reside in data centers and customer premises equipment.

[0199] In the context of NFV, VM1508 can be a software implementation of a physical machine, where programs run as if they were running on a physical, non-virtualized machine. Each VM1508 and its portion of the hardware 1504 on which it runs, whether that hardware is dedicated to that VM and / or shared by that VM with other VMs in the VM, form a separate virtual network element. Furthermore, in the context of NFV, the virtual network function is responsible for handling specific network functions running in one or more VM1508s on the hardware 1504, and corresponds to application 1502.

[0200] Hardware 1504 may be implemented in a standalone network node with general or specific components. Hardware 1504 may implement some functions through virtualization. Alternatively, hardware 1504 may be part of a larger cluster of hardware (such as in a data center or CPE) where many hardware nodes cooperate and are managed via management and orchestration 1510, which oversees the lifecycle management of applications 1502. In some embodiments, hardware 1504 is coupled to one or more radio units, each including one or more transmitters and one or more receivers, which may be coupled to one or more antennas. The radio units may communicate directly with other hardware nodes via one or more suitable network interfaces and may be used in combination with virtual components to provide a virtual node with radio capabilities, such as a radio access node or base station. In some embodiments, some signaling may be provided using a control system 1512, which may be used alternatively for communication between hardware nodes and radio units.

[0201] Figure 20 shows a communication diagram of host 1602 communicating with UE 1606 via network node 1604 over a partial wireless connection, according to several embodiments. Next, exemplary implementations of various embodiments of the UE (such as UE 1112a in Figure 15 and / or UE 1200 in Figure 16), network nodes (such as network node 1110a in Figure 15 and / or network node 1300 in Figure 17), and hosts (such as host 1116 in Figure 15 and / or host 1400 in Figure 18), as described in the previous paragraph, will be described with reference to Figure 20.

[0202] Similar to host 1400, embodiments of host 1602 include hardware such as a communication interface, processing circuitry, and memory. Host 1602 also includes software that is stored in or accessible by host 1602 and executable by the processing circuitry. The software includes a host application that may be capable of operating to serve a remote user, such as UE 1606 connected via an over-the-top (OTT) connection 1650 extending between UE 1606 and host 1602. When serving a remote user, the host application may provide user data transmitted using the OTT connection 1650.

[0203] Network node 1604 includes hardware that enables network node 1604 to communicate with host 1602 and UE 1606. The connection 1660 may be direct or pass through a core network (similar to core network 1106 in Figure 15) and / or one or more other intermediate networks, such as one or more public networks, private networks, or hosted networks. For example, the intermediate network could be a backbone network or the internet.

[0204] UE1606 includes hardware and software stored in or accessible by UE1606 and executable by the UE's processing circuitry. The software includes client applications, such as a web browser or operator-specific “app,” which may be capable of operating to serve human or non-human users through UE1606, with the support of host 1602. On host 1602, the running host application may communicate with the running client application via an OTT connection 1650 that terminates at UE1606 and host 1602. When serving a user, the UE's client application may receive request data from the host's host application and provide user data in response to the request data. The OTT connection 1650 may transfer both the request data and the user data. The UE's client application may interact with the user to generate user data that the UE's client application provides to the host application via the OTT connection 1650.

[0205] The OTT connection 1650 may extend via connection 1660 between host 1602 and network node 1604, and via wireless connection 1670 between network node 1604 and UE 1606, in order to provide a connection between host 1602 and UE 1606. Connections 1660 and wireless connection 1670, which the OTT connection 1650 may provide, are depicted abstractly to illustrate communication between host 1602 and UE 1606 via network node 1604, without explicit reference to intermediary devices and the precise routing of messages through these devices.

[0206] As an example of transmitting data over the OTT connection 1650, in step 1608, host 1602 provides user data, which may be done by running a host application. In some embodiments, the user data is associated with a specific human user interacting with UE 1606. In other embodiments, the user data is associated with UE 1606 sharing data with host 1602 without explicit human interaction. In step 1610, host 1602 initiates a transmission to carry the user data toward UE 1606. Host 1602 may initiate a transmission in response to a request sent by UE 1606. The request may be triggered by human interaction with UE 1606 or by the operation of a client application running on UE 1606. The transmission may travel through network node 1604 in accordance with the teachings of embodiments described throughout this disclosure. Accordingly, in step 1612, the network node 1604 transmits the user data carried in the transmission initiated by host 1602 to UE 1606, in accordance with the teachings of the embodiments described throughout this disclosure. In step 1614, UE 1606 receives the user data carried in the transmission, which may be done by a client application running on UE 1606 associated with a host application run by host 1602.

[0207] In some examples, UE1606 runs a client application that provides user data to host 1602. User data may be provided in response to or in reaction to data received from host 1602. Thus, in step 1616, UE1606 may provide user data, which may be done by running a client application. When providing user data, the client application may further consider user input received from the user via the input / output interface of UE1606. Regardless of the particular form in which the user data is provided, UE1606 initiates a transmission of the user data to host 1602 via network node 1604 in step 1618. In step 1620, in accordance with the teachings of embodiments described throughout this disclosure, network node 1604 receives user data from UE1606 and initiates a transmission of the received user data to host 1602. In step 1622, host 1602 receives the user data carried in the transmission initiated by UE1606.

[0208] One or more of the various embodiments improve the performance of the OTT service provided to the UE 1606 by using the OTT connection 1650, in which the wireless connection 1670 forms the final segment. More precisely, the teachings of these embodiments improve resource utilization, power consumption, and / or signal quality, thereby providing benefits such as improved quality of service, improved data rates, and / or improved battery life, in particular.

[0209] In an exemplary scenario, factory status information may be collected and analyzed by host 1602. As another example, host 1602 may process audio and video data that may be extracted from the UE for use in creating maps. As yet another example, host 1602 may collect and analyze real-time data to help control vehicle congestion (e.g., control traffic signals). As yet another example, host 1602 may store surveillance video uploaded by the UE. As yet another example, host 1602 may store or control access to media content, such as video, audio, VR or AR, which host 1602 can broadcast, multicast, or unicast to the UE. As yet another example, host 1602 may be used for energy pricing, remote control of non-time-constrained electrical loads to balance generation needs, location services, presentation services (such as compiling diagrams etc. from data collected from remote devices), or any other function of collecting, extracting, storing, analyzing, and / or transmitting data.

[0210] In some embodiments, measurement procedures may be provided for the purpose of monitoring data rate, latency, and other factors, which are improved by one or more embodiments. Further optional network functions may be provided for reconfiguring the OTT connection 1650 between host 1602 and UE 1606 in response to variations in measurement results. Measurement procedures and / or network functions for reconfiguring the OTT connection may be implemented in software and hardware of host 1602 and / or UE 1606. In some embodiments, sensors (not shown) may be deployed in or in relation to other devices through which the OTT connection 1650 passes, and the sensors may participate in the measurement procedure by supplying values ​​of the monitored quantities exemplified above, or values ​​of other physical quantities that the software can calculate or estimate the monitored quantities of. Reconfiguring the OTT connection 1650 may include message formatting, retransmission settings, preferred routing, etc., and the reconfiguration does not require a direct change in the operation of network node 1604. Such procedures and functions are known and practiced in the art. In some embodiments, the measurements may involve proprietary UE signaling by host 1602 to facilitate measurements such as throughput, propagation time, and latency. The measurements may be implemented in which software uses the OTT connection 1650 to cause messages, particularly empty or "dummy" messages, to be sent while monitoring propagation time, errors, etc.

[0211] The computing devices described herein (e.g., UEs, network nodes, hosts) may include the shown combinations of hardware components, but other embodiments may comprise computing devices with different combinations of components. It should be understood that these computing devices may comprise any suitable combination of hardware and / or software required to perform the tasks, features, functions, and methods disclosed herein. The determining, calculating, retrieving, or similar operations described herein may be performed by processing circuits, which may process information by, for example, converting retrieved information into other information, comparing the retrieved or converted information with information stored in the network node, and / or performing one or more operations based on the retrieved or converted information and as a result of the processing making decisions. Furthermore, although components are illustrated as a single box located within a larger box, or as a single box nested within multiple boxes, in practice, computing devices may comprise multiple different physical components that constitute a single shown component, and functions may be separated between the distinct components. For example, a communication interface may be configured to include any of the components described herein, and / or the functions of those components may be separated between the processing circuit and the communication interface. In another example, the non-computation-intensive functions of any of such components may be implemented in software or firmware, while the computation-intensive functions may be implemented in hardware.

[0212] In some embodiments, some or all of the functions described herein may be provided by a processing circuit that executes instructions stored in memory, which in some embodiments may be a computer program product in the form of a non-temporary computer-readable storage medium. In alternative embodiments, some or all of the functions may be provided by a processing circuit without executing instructions stored in a separate or individual device-readable storage medium, such as in a hardwired manner. In any of those particular embodiments, whether or not it executes instructions stored in a non-temporary computer-readable storage medium, the processing circuit may be configured to perform the functions described. The benefits provided by such functions are enjoyed by the processing circuit alone, or by the computing device as a whole, but not limited to other components of the computing device, and / or generally by the end user and the wireless network.

Claims

1. A method (150) implemented by a user device (UE) (110), wherein the method is Sending a first completion message (160) indicating whether the model is applicable to the function set in the UE (110), In the second message, report that the applicability of the model to the function of the UE (110) has changed (170) Method (150), including the method (150).

2. The method according to claim 1, wherein the first completion message includes an RRC setup completion message, an RRC restart completion message, or an RRC reconfiguration completion message.

3. The method according to claim 1 or 2, wherein reporting that the applicability of the model has changed includes indicating that the model is no longer applicable.

4. The method according to claim 3, wherein reporting that the applicability of the aforementioned model has changed includes indicating an alternative model that is associated with and applicable to the aforementioned function.

5. The method according to claim 1 or 2, wherein reporting that the applicability of the model has changed indicates that the model is applicable.

6. The method according to any one of claims 1 to 5, wherein reporting that the applicability of the model has changed includes providing causal values ​​indicating why the model is applicable or not applicable.

7. The method according to any one of claims 1 to 6, wherein reporting that the applicability of the model has changed is in response to receiving a third message that sets the reporting to take place.

8. The method according to claim 7, wherein the third message includes an RRC restart message, an RRC setup message, or an RRC reconfiguration message.

9. The method according to any one of claims 1 to 8, wherein the first completion message indicates a plurality of models, and each of the plurality of models is associated with a corresponding function set in the UE.

10. The method according to any one of claims 1 to 9, wherein the second message reports applicability relationship information relating to a plurality of models.

11. User equipment (UE) (110), Sending a first completion message indicating whether the model is applicable to the function set in the aforementioned UE, In the second message, report that the applicability of the model to the function of the UE(110) has changed. A user device (UE) (110) configured to perform the following actions.

12. The UE according to claim 11, further configured to carry out the method (150) described in any one of claims 2 to 10.

13. User equipment (UE) (110), An interface circuit (111) and a processing circuit (112) that is communicatively connected to the interface circuit (111) The processing circuit (112) is provided with, A first completion message is transmitted via the interface circuit (111) indicating whether the model is applicable to the function set in the UE, In a second message via the interface circuit (111), it is reported that the applicability of the model to the function of the UE (110) has changed. A user device (UE) (110) configured to perform the following actions.

14. The UE according to claim 13, wherein the processing circuit (112) is further configured to carry out the method (150) according to any one of claims 2 to 10.

15. A computer program (113) that, when executed on a processing circuit (112) of a user device (UE) (110), provides instructions to cause the UE (110) to perform the method according to any one of claims 1 to 10.

16. A carrier comprising the computer program (113) described in claim 15, wherein the carrier is one of an electronic signal, an optical signal, a wireless signal, or a computer-readable storage medium.

17. A method (180) implemented by a network node (120), wherein the method is Receiving a first completion message from UE(110) indicating whether the model is applicable to the functions set in UE(110) (185), Receiving a report from the UE (110) in a second message indicating that the applicability of the model to the function of the UE (110) has changed (190) Method (180), including the method (180).

18. The method according to claim 17, wherein the first completion message includes an RRC setup completion message, an RRC restart completion message, or an RRC reconfiguration completion message.

19. The method according to claim 17 or 18, wherein the report indicating that the applicability of the model to the function of the UE(110) has changed includes an indication that the model is no longer applicable.

20. The method of claim 19, wherein the report indicating that the applicability of the model to the function of the UE(110) has changed includes an indication of an applicable alternative model associated with the function.

21. The method according to claim 17 or 18, wherein the report indicating that the applicability of the model to the function of the UE(110) has changed includes an indication that the model is applicable.

22. The method according to any one of claims 17 to 21, wherein the report indicating that the applicability of the model to the function of the UE(110) has changed includes a causal value indicating why the model is applicable or not applicable.

23. The method according to any one of claims 17 to 22, further comprising sending a third message that instructs the UE(110) to send the aforementioned report, wherein receiving the second message is in response to sending the third message.

24. The method according to claim 23, wherein the third message includes an RRC restart message, an RRC setup message, or an RRC reconfiguration message.

25. The method according to any one of claims 17 to 24, wherein the first completion message indicates a plurality of models, and each of the plurality of models is associated with a corresponding function set in the UE(110).

26. The method according to any one of claims 17 to 25, wherein the second message reports applicability relationship information relating to a plurality of models.

27. A network node (120), Receiving a first completion message from UE(110) indicating whether the model is applicable to the function set in UE(110), Receiving a report from the UE(110) in a second message indicating that the applicability of the model to the function of the UE(110) has changed. A network node (120) configured to perform this action.

28. A network node according to claim 27, further configured to carry out the method described in any one of claims 18 to 26.

29. A network node (120), An interface circuit (121) and a processing circuit (122) that is communicatively connected to the interface circuit (121) The processing circuit (122) is provided with, The interface circuit (121) receives a first completion message from the UE (110) indicating whether the model is applicable to the function set in the UE (110), The interface circuit (111) receives a second message from the UE (110) indicating that the applicability of the model to the function of the UE (110) has changed. A network node (120) configured to perform this action.

30. The network node according to claim 29, wherein the processing circuit (122) is further configured to carry out the method according to any one of claims 18 to 26.

31. A computer program (123) that, when executed on the processing circuit (112) of a network node (120), includes instructions that cause the network node (120) to perform the method according to any one of claims 17 to 26.

32. A carrier comprising the computer program (113) described in claim 31, wherein the carrier is one of an electronic signal, an optical signal, a wireless signal, or a computer-readable storage medium.

Images