Method of signaling network associated types of available AI / ML assistance information

Abstract

Systems and methods related to network associated types that signal available assistance information (e.g., artificial intelligence (AI) or machine learning (ML) assistance information) are disclosed. In one embodiment, a method performed by a node (e.g., a second network node or user equipment) includes receiving a first message from a first network node, the first message including information of a network associated type indicating available AI or ML assistance information related to the first network node that the first network node may provide. In this manner, assistance information that can be used to perform a certain task (e.g., inferring AI / ML-based actions / suggestions regarding energy conservation) may be obtained in an efficient manner.

Description

Related applications

[0001] This application claims the benefit of provisional patent application serial number 63 / 485082 filed on February 15, 2023 and provisional patent application serial number 63 / 487052 filed on February 27, 2023, the disclosures of which are hereby incorporated by reference herein in their entireties. Technical Field

[0002] The present disclosure relates to cellular communication systems, and more particularly, to systems and methods for indicating the availability of a network-associated type of artificial intelligence (AI) or machine learning (ML) assistance information. Background Art

[0003] The current fifth generation (5G) radio access network (RAN) (also known as the next generation RAN (NG-RAN)) architecture is Figure 1 The NG-RAN is depicted in [1] and described in the 3rd Generation Partnership Project (3GPP) Technical Specification (TS) 38.401 v17.2.0 as follows. The NG-RAN consists of a set of gNodeBs (gNBs) connected to the 5G Core (5GC) via a Next Generation (NG) interface. As specified in 3GPP TS 38.300 v17.3.0, the NG-RAN may also include a set of Next Generation eNodeBs (ng-eNBs), where an ng-eNB may consist of an ng-eNB Central Unit (CU) and one or more ng-eNB Distributed Units (DUs). The ng-eNB-CU and ng-eNB-DU are connected via the W1 interface. Unless otherwise specified, the general principles described here also apply to the ng-eNB and W1 interface. The gNB can support frequency division duplex (FDD) mode, time division duplex (TDD) mode, or dual-mode operation. gNBs can be interconnected via the Xn interface. A gNB may consist of a gNB-CU and one or more gNB-DUs. The gNB-CU and gNB-DUs are connected via the F1 interface. ●A gNB-DU is connected to only one gNB-CU. ●NG, Xn and F1 are logical interfaces.

[0004] For NG-RAN, the NG and Xn-C interfaces of a gNB, consisting of a gNB-CU and gNB-DU, terminate at the gNB-CU. For Evolved Universal Terrestrial Radio Access (EUTRA) - New Radio (NR) Dual Connectivity (EN-DC), the S1-U and X2-C interfaces of a gNB, consisting of a gNB-CU and gNB-DU, terminate at the gNB-CU. The gNB-CU and the connected gNB-DU are visible only to other gNBs and the 5GC acting as the gNB. Possible deployment scenarios are described in Annex A of 3GPP TS 38.401.

[0005] The node hosting the user plane portion of the NR Packet Data Convergence Protocol (PDCP) (e.g., gNB-CU, gNB-CU-User Plane (UP), and, for EN-DC, the Master eNB (MeNB) or SgNB depending on bearer split) performs user inactivity monitoring and also notifies nodes with a control plane (C-plane) connection towards the core network (e.g., via X2 E1) of its inactivity or (re)activation. The node hosting the NR Radio Link Control (RLC) (e.g., gNB-DU) may perform user inactivity monitoring and also notify nodes hosting the control plane (e.g., gNB-CU or gNB-CU Control Plane (CP)) of its inactivity or (re)activation.

[0006] Indicates uplink (UL) PDCP configuration (i.e., how the user equipment (UE) uses the UL at the secondary node) via X2-C (for EN-DC), Xn-C (for NG-RAN), and F1-C. Indicates downlink (DL) and / or UL radio link interruption / recovery via X2-U (for EN-DC), Xn-U (for NG-RAN), and F1-U.

[0007] NG-RAN is layered into the Radio Network Layer (RNL) and the Transport Network Layer (TNL).

[0008] The NG-RAN architecture (i.e., NG-RAN logical nodes and the interfaces between them) is defined as part of the RNL. For each NG-RAN interface (NG, Xn, F1), the relevant TNL protocols and functionality are specified. The TNL provides services for user plane transport and signaling transport.

[0009] It is worth mentioning that Figure 1The architecture shown in Figure 1 is the one that 3GPP has defined for 5G. Other standardization groups, such as Open RAN (ORAN), have further extended this architecture, for example by splitting the gNB-DU into two additional nodes connected by a fronthaul interface. The lower node of the split gNB-DU will contain the PHY protocol and radio frequency (RF) portion, while the upper node of the split gNB-DU will host the RLC and media access control (MAC). In ORAN, the upper node is called the O-DU, while the lower node is called the O-Radio Unit (RU).

[0010] In the current state of the art, coordination across the RAN and transport domains is typically managed in a non-real-time mode (e.g., pre-planning and provisioning the transport domain), where an alternative is to coordinate the radio and transport domains at the service coordination level. However, there are no products available on the market yet.

[0011] In situations where the allocated RAN capacity changes dynamically, it should be possible to optimize the transport capacity accordingly. Mobility load balancing is envisioned as one of the use cases that requires closer coordination between RAN and transport. It is also noted that the transport network is a contributor to the overall latency and resilience of mobile services, and this aspect is particularly important in the case of Ultra-Reliable Low Latency Communication (URLLC) services as specified by the 3GPP standards.

[0012] The 3GPP RAN3 study item (SI), "Study on Enhancements to Data Collection for NR and EN-DC," investigated the general high-level principles, functional framework, and potential use cases for an artificial intelligence (AI)-enabled RAN. The results of this study are documented in 3GPP Technical Report (TR) 37.817 v17.0.0. Standardization work based on the conclusions of the Rel-17 SI is currently underway in 3GPP Rel-18, and the related work item (WI) is described in RP-213602.

[0013] The following agreement was reached at RAN3#117bis-e: Signaling capabilities that support specific information predictions for AI / machine learning (ML) are not pursued in this release; Signaling capabilities that support specific AI / ML use cases is not pursued in this release; AI / ML capability exchange in NG-RAN may be achieved with the aid of procedures for AI / ML information request, AI / ML information response and AI / ML information request failure.

[0014] The 3GPP RAN1 working group is currently working on SI over AI / ML for the NR air interface. A description of its purpose can be found in RP-213599. Summary of the Invention

[0015] The present disclosure provides systems and methods for signaling network-associated types of available assistance information (e.g., artificial intelligence (AI) or machine learning (ML) assistance information). In one embodiment, a method performed by a node (e.g., a second network node or a user device) includes receiving a first message from a first network node, the first message including information indicating network-associated types of available AI or ML assistance that the first network node can provide. In this manner, assistance information that can be used to perform a task (e.g., inferring AI / ML-based actions / recommendations regarding energy conservation) can be obtained in an efficient manner.

[0016] In one embodiment, the method further comprises performing one or more actions using the received information. In one embodiment, the one or more actions comprise sending a request to the first network node for at least one of the indicated network-associated types of available AI or ML assistance information. In another embodiment, the one or more actions comprise sending a request to the first network node for at least one of the indicated network-associated types of available AI or ML assistance information, receiving from the first network node at least one of the indicated network-associated types of available AI or ML assistance information, and performing one or more AI or ML-related operations (e.g., updating or training an AI or ML model) based on at least one of the indicated network-associated types of available AI or ML assistance information received from the first network node. In another embodiment, the one or more actions comprise sending at least some of the received information to another node (e.g., to a network node or a user device).

[0017] In one embodiment, the network-associated type for which the AI ​​or ML assistance information is available is related to the first network node or the third network node.

[0018] In one embodiment, the node is a second network node. In one embodiment, the method further comprises, before receiving the first message, sending a request to the first network node for information indicating network-associated types of available AI or ML assistance information related to the first network node that the first network node can provide. In one embodiment, the method further comprises, before receiving the first message, sending a request to the first network node for at least one of the network-associated types of AI or ML assistance information related to the first network node that the first network node can provide. In one embodiment, the method further comprises, in response to the request, receiving an ACK, a partial ACK, or a NACK from the first network node. In one embodiment, the method further comprises, before receiving the update information from the first network node, receiving at least some of the requested at least one of the network-associated types of AI or ML assistance information related to the first network node that the first network node can provide. In another embodiment, the method further comprises, before receiving the update information from the first network node, sending a request to the first network node for (update) information indicating network-associated types of available AI or ML assistance information related to the first network node that the first network node can provide. In another embodiment, the method further comprises sending a second message to the first network node, the second message comprising information indicating a network associated type of available AI or ML assistance information related to the second network node that the second network node can provide.

[0019] In one embodiment, the node is a user equipment (e.g., a UE). In one embodiment, the method further comprises sending a request to the first network node for at least one of network-associated types of available AI or ML assistance information related to the first network node that the first network node can provide, and receiving from the first network node at least one of network-associated types of available AI or ML assistance information related to the first network node that the first network node can provide. In another embodiment, the method further comprises, before receiving the first message from the first network node, sending a request to the first network node for information indicating the network-associated types of available AI or ML assistance information related to the first network node that the first network node can provide.

[0020] Corresponding embodiments of the nodes are also disclosed.

[0021] Also disclosed are embodiments of a method performed by a first network node. In one embodiment, a method performed by the first network node includes sending a first message to a node (e.g., a second network node or a user device), the first message including information indicating a network-associated type of available artificial intelligence (AI) or machine learning (ML) assistance information related to the first network node that the first network node can provide. In one embodiment, the node is the second network node. In another embodiment, the node is a user device (e.g., a UE).

[0022] Corresponding embodiments of the first network node are also disclosed. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings incorporated in and forming a part of this specification illustrate several aspects of the disclosure and together with the description serve to explain the principles of the disclosure.

[0024] Figure 1 Describes the Next Generation Radio Access Network (NG-RAN) architecture defined in the 3rd Generation Partnership Project (3GPP) specifications;

[0025] Figure 2 An illustration of an example method performed by a first network node for exchanging what auxiliary information related to artificial intelligence (AI) or machine learning (ML) is available at the first network.

[0026] Figure 3 An illustration of an example of a method in which a first network node transmits a first message to a second network node, wherein the first message indicates a network-associated type of AI / ML assistance information available at the first network node. The second network node also transmits a second message, wherein the second message indicates a network-associated type of AI / ML assistance information available at the second node.

[0027] Figure 4 is an illustration of an example of a method in which the first network node further receives a third message including a request to provide AI / ML assistance information.

[0028] Figure 5 is an illustration of an example of a method in which the first network node, upon receiving the third message, may also transmit a fourth message and a fifth message to the second network node. Dashed lines indicate signals that are optionally transmitted in this example.

[0029] Figure 6 is an illustration of an example of a network-associated type of how a first network node may autonomously indicate an update of available AI / ML assistance information during a reporting procedure for AI / ML assistance information.

[0030] Figure 7The present invention provides an example of how a first network node may indicate an updated network-associated type of available AI / ML assistance information during a reporting procedure for AI / ML assistance information. In this case, transmission of a new first message is conditional on receipt of a second message from a second network node.

[0031] Figure 8 Another modified exemplary embodiment of the present disclosure is described.

[0032] Figure 9 Another modified exemplary embodiment of the present disclosure is described.

[0033] Figure 10 Another modified exemplary embodiment of the present disclosure is described.

[0034] Figure 11 An example of a cellular communication system according to some embodiments of the present disclosure is illustrated.

[0035] Figure 12 is a schematic block diagram of a radio access node according to some embodiments of the present disclosure.

[0036] Figure 13 This is a description of some embodiments of the present disclosure. Figure 12 A schematic block diagram of an embodiment of a virtualization of a radio access node.

[0037] Figure 14 According to some other embodiments of the present disclosure Figure 12 Schematic block diagram of a radio access node.

[0038] Figure 15 is a schematic block diagram of a user equipment device (UE) according to some embodiments of the present disclosure.

[0039] Figure 16 According to some other embodiments of the present disclosure Figure 15 Schematic block diagram of UE.

[0040] Figure 17 A telecommunications network connected to a host computer via an intermediary network is described according to some embodiments of the present disclosure.

[0041] Figure 18 is a generalized block diagram of a host computer communicating with a UE via a base station over a partially wireless connection according to some embodiments of the present disclosure.

[0042] Figure 19 is a flowchart illustrating a method implemented in a communication system according to one embodiment of the present disclosure.

[0043] Figure 20is a flowchart illustrating a method implemented in a communication system according to one embodiment of the present disclosure.

[0044] Figure 21 is a flowchart illustrating a method implemented in a communication system according to one embodiment of the present disclosure.

[0045] Figure 22 is a flowchart illustrating a method implemented in a communication system according to one embodiment of the present disclosure. DETAILED DESCRIPTION

[0046] The embodiments set forth below represent information to enable those skilled in the art to practice the described embodiments and illustrate the best mode for practicing the described embodiments. Upon reading the following description in light of the accompanying drawings, those skilled in the art will understand the concepts of the present disclosure and will recognize applications of these concepts not specifically set forth herein. It should be understood that these concepts and applications fall within the scope of the present disclosure.

[0047] Note the following about some of the terminology used in the following descriptions: -As used herein, a network node may be a radio access network (RAN) node, operation, administration and maintenance (OAM), a core network node, service management and orchestration (SMO), a network management system (NMS), a non-real-time RAN intelligent controller (non-RTRIC), a real-time RAN intelligent controller (RTRIC), a gNodeB (gNB), an eNodeB (eNB), en-gNB, a next generation eNB (ng-eNB), a gNB-central unit (CU), a gNB-CU-control plane (CP), a gNB-CU-user plane (UP), an eNB-CU, an eNB-CU-CP, an eNB-CU-UP, an integrated access and backhaul (IAB) node, an IAB-donor DU, an IAB-donor CU, an IAB-DU, an IAB-mobile terminal (MT), an open RAN (O)-CU, an O-CU-CP, an O-CU-UP, an O-DU, an O-radio unit (RU), an O-eNB, a user device, an artificial intelligence (AI) / machine learning (ML) server. Unless otherwise specified, the terms model training, model optimizing, model optimization, and model updating are used interchangeably in this article with the same meaning. Unless expressly stated otherwise, the terms model change, modification, or the like are used interchangeably herein with the same meaning. In particular, they refer to the fact that the type, structure, parameters, connectivity of the AI / ML model may have changed compared to the previous format / configuration of the AI / ML model. Unless expressly stated otherwise, the terms AI / ML model, AI / ML strategy, AI / ML algorithm, and the terms model, strategy, or algorithm are used interchangeably herein with the same meaning. - References herein to "network node" should be understood as meaning that a network node may be any kind of functional or logical entity or physical node, such as a software entity implemented in a data center or cloud, for example using one or more virtual machines, and that two network nodes may well be implemented as logical software entities in the same data center or cloud. - The terms action type, action type identifier, action type ID or type of action associated with a RAN are used interchangeably with the same meaning, i.e. an indication of the action type - The terms action instance, specific action instance, action instance identifier, action instance ID, action ID are used interchangeably with the same meaning, ie an indication of an instance of a specific action. - The terms "AI / ML", "AIML", "MLAI", "ML / AI" may be used interchangeably in this disclosure.

[0048] Embodiments of the systems and methods described herein are independent of the specific AI / ML model type or learning problem / setting (e.g., supervised learning, unsupervised learning, reinforcement learning, hybrid learning, centralized learning, federated learning, distributed learning, etc.).

[0049] Non-limiting examples of AI / ML algorithms may include supervised learning algorithms, deep learning algorithms, reinforcement learning type RAN-associated algorithms (such as DQN, A2C, A3C, etc.), contextual multi-armed bandit algorithms, autoregressive algorithms, etc., or a combination thereof.

[0050] Such algorithms may utilize function approximation models, hereinafter referred to as AI / ML models, such as neural networks (e.g., feedforward neural networks, deep neural networks, recurrent neural networks, convolutional neural networks, etc.).

[0051] Examples of reinforcement learning algorithms may include deep reinforcement learning (such as deep Q-network (DQN), proximal policy optimization (PPO), double Q-learning), actor-critic algorithms (such as advantage actor-critic algorithms, e.g., A2C or A3C, actor-critic with experience replay, etc.), policy gradient algorithms, off-policy learning algorithms, etc.

[0052] Before describing the embodiments of the present disclosure in detail, it is helpful to discuss the challenges of the existing technology. Some general protocols have been implemented for supporting AI / ML in the RAN. For example, it has been agreed that AI / ML capability exchange in the NG-RAN can be achieved through procedures for AI / ML information requests, AI / ML information responses, and AI / ML information request failures. However, it is unclear how to effectively utilize network-related AI / ML capabilities in the RAN. 1. Overview of at least some embodiments of the present disclosure

[0053] Disclosed herein are systems and methods that provide solutions to the above and / or other challenges. A method is provided for a first network node to indicate to a second network node a network-associated type of available AI / ML assistance information related to the first network node that can be provided to the second network node (e.g., Classes of RAN-related AI / ML auxiliary information type The first network node may then provide the assistance information itself in a subsequent signaling step, either as part of the same signaling procedure used to indicate the network-associated type of available AI / ML assistance information, or using a separate signaling procedure.

[0054] Although the general terminology of the associated types of AI / ML-assisted information networks is used herein, it should be clear that the embodiments described herein are applicable to any network that can be provided by the first network node. RAN with available assistance information Associated Type , and therefore not necessarily related to the support of AI / ML operations. Examples may include, for example, assistance information associated with load optimization, assistance information associated with energy saving optimization, assistance information associated with mobility optimization, etc. 1.1 Method performed by the first network node

[0055] Embodiments are disclosed relating to a method performed by a first network node to exchange with a second network node or a user device an indication of a network-associated type of available AI / ML assistance information related to the first network node that the first network node can provide. In one embodiment, the method comprises the following steps: - Transmitting a first message to a second network node or a user equipment, the first message indicating a network-associated type of available AI / ML assistance information related to the first network node that the first network node can provide, or an indication that the first network node is capable of providing AI / ML assistance information.

[0056] Variant 1: In this variant, the first message is transmitted from the first network node to the second network node.

[0057] In a variant of the method, in which a first network node transmits a first message to a second network node, the first network node may - Optionally, receiving a second message from the second network node, wherein the second message may include one or more of the following: o A network-associated type of request to a first network node indicating available AI / ML assistance information that the first network node can provide. o An indication of a network-associated type of available AI / ML assistance information related to the second network node that the second node may provide.

[0058] In one embodiment, the first message and the second message are the same type of RAN-associated messages (eg, they may be implemented with the same 3GPP message).

[0059] In one embodiment, the first network node may further perform one or more of the following steps: - receiving a third message from the second network node, the third message including providing one or more of the network-associated AI / ML assistance information indicated by the first network node to the second network node by means of the first message; ask , - transmitting a fourth message comprising a positive acknowledgement (ACK) or a negative acknowledgement (NACK) of the information requested by the second network node, - transmitting one or more fifth messages providing network associated AI / ML assistance information updates as requested by the second network node with the third message.

[0060] In one embodiment, any one of the third message, the fourth message, and the fifth message belongs to the same or different signaling procedures used to transmit the first and / or second message. For example, in one embodiment, the second message and the third message are of the same type belonging to the same signaling procedure. ask information.

[0061] Variant 2: The first message is transmitted from the first network node to the user device.

[0062] In a variation of the method, in which the first network node transmits a first message to the user device, the first network node may - optionally receiving a seventh message from the user equipment, the seventh message comprising a request to the first network node indicating a network associated type of available AI / ML assistance information that the first network node may provide. 1.2 Method performed by the second network node (in variant 1)

[0063] Also disclosed are embodiments of a method performed by the second network node. In one embodiment, the method comprises the following steps: - receiving a first message from a first network node, the first message indicating a network-associated type of available AI / ML assistance information related to the first network node that the first network node may provide, or an indication that the first network node may provide assistance information; and - Optionally, transmitting a second message to the first network node, wherein the second message may include one or more of the following: o a request to the first network node indicating a network-associated type of available AI / ML assistance information that the first network node can provide; and o An indication of a network-associated type of available AI / ML assistance information related to the second network node that the second node may provide.

[0064] Additional embodiments result from the method performed by the first network node. 1.3 Method Executed by User Device (in Variant 2)

[0065] Also disclosed are embodiments of a method performed by the second network node. In one embodiment, the method comprises the following steps: - receiving a first message from a first network node, the first message indicating a network-associated type of available AI / ML assistance information related to the first network node that the first network node may provide, or an indication that the first network node may provide such assistance information; and - Optionally, transmitting a seventh message to the first network node, the seventh message comprising a request to the first network node indicating a network associated type of available AI / ML assistance information that the first network node can provide.

[0066] Additional embodiments result from the method performed by the first network node. 1.4 Advantages

[0067] Embodiments of the present disclosure may provide numerous advantages. One advantage of at least some embodiments of the proposed solution is that auxiliary information that can be used by network nodes to perform a task (e.g., inferring AI / ML-based actions / recommendations regarding energy conservation) may be obtained in an efficient manner.

[0068] In the absence of such a solution, an iterative process can be used, where in a round-robin fashion, in a first step certain assistance information is requested, and in a second step the requesting node or user device discovers (from the response) whether such assistance information is available. This cycle is repeated for as many network-associated types of available AI / ML assistance information as the requesting node is interested in receiving.

[0069] With this solution, a node indicates to another node or to a user device the network-related type of available AI / ML assistance information it can provide. This allows another node to know in advance exactly what it can and cannot achieve if it is interested in receiving some assistance information. This reduces signaling overhead, shortens the time to obtain the desired information, and makes signaling clearer.

[0070] Furthermore, in cases where the network-relevant types of available AI / ML-assisted information change over time, the same interested nodes can quickly become aware of new situations. 2 Embodiment of Variant 1 (First Network Node and Second Network Node)

[0071] According to the present disclosure, a first network node indicates to a second network node a network-associated type of available AI / ML assistance information related to the first network node that the first network node can provide.

[0072] Figure 2 An exemplary embodiment of a process performed by a first network node and a second network node according to variant 1 is described. In other words, Figure 2 20 is an illustration of an example method performed by a first network node to exchange information about available assistance information related to AI / ML at a first network. Optional steps are represented by dashed lines / boxes. As illustrated, the first network node sends a first message to a second network node (step 202). The first message includes a network-associated type of available AI / ML assistance information related to the first network node that the first network node can provide. The second network node can use such available AI / ML assistance information to determine whether and how the second network node can obtain AI / ML assistance information from the first network node to support an AI / ML algorithm at the second network node, such as an algorithm for prediction / inference.

[0073] In one embodiment, Figure 2 As described in [ 200 ], before sending the first message, the first network node may optionally receive a second message from the second network node (step 200). The second message includes a request from the second network node to receive a network-associated type of available AI / ML assistance information types related to the first network node that the first network node can provide. In this case, in response to receiving the second message, the first network node transmits the first message.

[0074] Likewise Figure 2As described in, in one embodiment, the second network node uses the received information indicating the network-associated types of available AI / ML assistance information types that the first network node can provide related to the first network node to perform one or more actions (step 220). The one or more actions can be any desired action(s). For example, the second network node can use this received information to request at least one of the network-associated types of available AI / ML assistance information from the first network node (step 220A). The second node can then, for example, receive the at least one of the network-associated types of available AI / ML assistance information from the first network node and use this information for one or more AI / ML operations (e.g., training or updating an AI or ML model, or any action that can use the received information) (see also step 220A). As another example, the second network node can send the information received in the first message to another network node or user device (step 220B).

[0075] In one embodiment, the first message may optionally include, implicitly or explicitly, a network-associated type of request to obtain available AI / ML assistance information related to the second network node. Figure 3 In one example illustrated in , a first network node sends a first message to a second network node (step 300), and the first network node receives a second message from the second network node (step 310). The second message may optionally include a network-associated type of available AI / ML assistance information that the second network node can provide with respect to the second network node. In this case, the second message may be used to report the network-associated type of available AI / ML assistance information for the second network node (the second message being propagated in the opposite direction compared to the first message), and it may be received by the first network node in response to transmitting the first message to the second network node. In other words, the transmission of the first message implicitly triggers the second network node to transmit a second message, the second message including the network-associated type of available AI / ML assistance information that the second network node can provide with respect to the second network node. Again, the dashed line indicates the signal that is optionally transmitted in this example.

[0076] In one embodiment, the first message and the second message are included in the same logical process of the signaling interface (for example, in one implementation example, the first message is a response message of the Xn Setup XnAP process, i.e., an XN Setup Response XnAP message, and the second message is an initiation message of the Xn Setup XnAP process, i.e., an XN Setup Request XnAP message); in another implementation example, the first message and the second message are included in a signaling process designed for AI / ML, such as an "AIML Information Transfer" XnAP process.

[0077] In another embodiment, the first message and the second message are included in different logical processes of the signaling interface (for example, the second message is an initiation message of a first Class 1 process, such as an "AIML Information Report Initiation" XnAP process, and the first message is an initiation message of a second Class 2 process, such as an "AIML Information Report" XnAP process). Note: A "Class 1" process includes an initiation message, a response message, and an optional failure message, while a "Class 2" process only includes an initiation message. 2.1 Additional Signaling Aspects of Variant 1 2.1.1 Variant 1a

[0078] Figure 4 An example embodiment of variant 1a is illustrated. The dashed lines indicate signals that are optionally transmitted in this example. Figure 4 In the embodiment described in, the first network node optionally receives a second message from the second network node (step 400). The first network node sends the first message to the second node (step 410). The first network node may additionally receive a third message from the second network node (step 420). The third message includes one or more of the network-associated AI / ML assistance information indicated by the first network node to the second network node via the first message. ask Thus, upon receiving the first message of a network-associated type indicating available AI / ML assistance information that the first network node may provide, the second network node may efficiently request any of the AI / ML assistance information available at the first network node using the third message.

[0079] In one embodiment, the first message and / or the second message and the third message are included in the same logical process of the signaling interface (eg, Xn Setup XnAP process).

[0080] In one example, the second message and the third message are of the same type and are of the same logical process of the signaling interface. please beg message, but configured with different values ​​using one or more information elements. For example, the second message and the third message may be initiation messages of an AI / ML assisted information process, where - The second network node transmits a second message to request from the first network node an indication or a list of available AI / ML assistance information that the first network node can provide. o For example, this request may be indicated by a single information bit, e.g., called the type of RAN-associated available AI / ML assistance information, which may be set to a specific value (e.g., 1 or 0), as illustrated in Section 4.2. o According to one embodiment, if only the type bit of the RAN-associated available AI / ML assistance information is set to 1, this implies a request to receive assistance information of all available prediction types and associated formats (e.g., reference prediction time and / or reliability conditions). According to another embodiment, if the type bit of the RAN-associated available AI / ML assistance information is set to 1, and at least another bit associated with a specific prediction type is also set to 1 (e.g., the second bit associated with the predicted energy efficiency), this implies a request to receive assistance information only for the indicated prediction type. o The first network node replies by transmitting a first message indicating the network-associated type of available AI / ML assistance information that can be provided. Such message exchange remains valid as long as there is no change in the network-associated type of available AI / ML assistance information that can be provided by the first network node. - Upon receiving the first message, the second network node may trigger a process of obtaining network-associated AI / ML assistance information from the first network node by transmitting a third message, thereby requesting the first network node to provide one or more AI / ML assistance information of the previously indicated network-associated AI / ML assistance information. o In one embodiment, the third message may be identical to the second message, and this request may be indicated, for example, by setting one or more information bits of the third message to a specific value (eg, 1 or 0), as illustrated in Section 4.2.

[0081] In another embodiment, the first message and / or the second message and the third message are included in different logical processes of the signaling interface. For example, the first message (and optionally the second message) are included in the Xn Setup XnAP process (e.g., the first message is an XN Setup Response message, and the second message is an XN Setup Request message), while the third message is included in the AI / ML Information Report Initialization XnAP process (e.g., the third message is an AIML Information Request XnAP message). 2.1.2 Variant 1b

[0082] Figure 5 is an illustration of an example of an embodiment of a method according to variant 1b. Again, the dashed lines indicate signals that are optionally transmitted in this example. Steps 500, 510 and 520 are identical to Figure 4 Steps 400, 410 and 420 are the same. In one embodiment, Figure 5As described in

[0066] , the first network node may also transmit a fourth message (step 530). The fourth message includes a positive acknowledgement (ACK) or a negative acknowledgement (NACK) of the information requested by the second network node. When the fourth message provides a positive acknowledgement of the assistance information requested by the second network node, the first network node may additionally transmit one or more fifth messages providing the AI / ML assistance information update as requested by the second network node using the third message (step 540). In one example of this embodiment, the first message and / or the second message and the third, fourth, and fifth messages are included in the same logical process of the signaling interface (e.g., the Xn Setup XnAP process). For example, the first message (and optionally the second message) is included in the Xn Setup process, while the third, fourth, and fifth messages are included in the AI / ML Information Report Initialization XnAP process. -In another example of this embodiment, the first message and / or the second message and any one of the third, fourth and fifth messages are included in different logical processes of the signaling interface (for example, the second message is included in the AI / ML information report initiation XnAP process, and the first message is included in the AI / ML information report XnAP process).

[0083] The positive acknowledgement may be used to indicate that all AI / ML assistance information requested by the second network node is available (full success) or only part of the information is available (partial success). 2.1.3 Variant 1c

[0084] When the first network node transmits a partial positive acknowledgement or a negative acknowledgement of information requested by the second network node, the fourth message implicitly or explicitly indicates that the list of available AI / ML assistance information previously indicated by the first network node by means of the first message is outdated and / or no longer valid.

[0085] Figure 6 An example embodiment of variant 1c is illustrated. Dashed lines indicate signals that are optionally transmitted in this example. Steps 600, 610, 630, and 640 are the same or similar to steps 500, 510, 520, and 530 discussed above. Figure 6In the example illustrated in , there is a change in the network associated types of available AI / ML assistance information available at the first network node (step 620). The first network node may autonomously transmit a new first message to indicate an updated list of network associated types of available AI / ML assistance information that the first network node may provide (step 650). The new first message may be transmitted to the second network node during a procedure related to AI / ML in the RAN, such as the “AIML Assistance Information Report” XnAP procedure, before or after, or as an alternative to, transmitting the fourth message in step 640. Figure 6 In the example illustrated in , a new first message is transmitted by the first network node after the transmission of a fourth message indicating a negative or partial acknowledgement of the requested assistance information to the second network node.

[0086] In another example (not Figure 6 (Note that the first message and the fourth message may be messages of the same type (e.g., the transmission of the new first message may replace the transmission of the fourth message). That is, by transmitting an updated set of network-associated types of available AI / ML assistance information to the second network node, the first network node may implicitly or explicitly provide a negative acknowledgement of the third message received from the second network node. In another example, the fourth message may include a negative acknowledgement of the information requested by the third message and an updated list of network-associated types of available AI / ML assistance information for the first network node. 2.1.4 Variant 1d

[0087] Figure 7 An alternative example of how the first network node may indicate the network associated type of updated available AI / ML assistance information during the reporting process of AIML assistance information is shown. The dashed lines indicate signals that are optionally transmitted in this example. Steps 700, 710, 720, 730, 740 and 760 are related to Figure 6 600, 610, 620, 630, 640, and 650 are the same. In this example, upon indicating with the fourth message that one or more network-associated AI / ML assistance information requested by the second network node is no longer available (e.g., by means of a negative or partial confirmation of the requested assistance information), the first network may transmit a new first message to the second network node, the new first message having an updated list of network-associated types of available AI / ML assistance information, conditional on receiving a new second message from the second network node requesting indication of such information (step 750). 2.2 First News

[0088] The first message is sent from the first network node to the second network node and includes one or more of the following: -Indication of the network-associated types of available AI / ML assistance information of the first network node. In one example, the network-associated types of available AI / ML assistance information that the first node can provide can be represented as a list of information (e.g., enumerated types). In another example, the first network node can indicate the network-associated types of available AI / ML assistance information using a bitmap, wherein each bit in the bitmap is associated with at least one type of RAN-associated AI / ML assistance information, wherein the bit value is set to 1 (or zero) to indicate the availability of information and is otherwise set to zero (or zero or 1, respectively). - an indication that the network associated type of the available AI / ML assistance information of the first network node has not changed (is still valid) compared to the network associated type of the available AI / ML assistance information of the first network node included in the previously sent first message. This element may be included in an alternative to the network associated type of the available AI / ML assistance information of the first network node - an indication that the network associated type of the available AI / ML assistance information of the first network node provided in the first message modifies / overwrites the network associated type of the previously delivered available AI / ML assistance information of the first network node - an indication that all or at least part of the network-associated type of available AI / ML assistance information of the first network node provided in the previous first message is no longer valid - an indication that the network-associated type of the available AI / ML assistance information for the first network node provided in the first message is a supplement to the network-associated type of the available AI / ML assistance information for the first network node provided in the previous first message - one or more new and / or updated network-associated types of available AI / ML assistance information for the first network node - (Optional) Request to obtain the complete set of network-associated types of available AI / ML assistance information for the second network node - (Optional) Network-related type of request to obtain only new and / or updated available AI / ML assistance information of the second network node Conditions that trigger the transmission of the first message

[0089] In one embodiment, the first network node determines to send the first message when certain conditions are met, such as: - Determine the network-associated type of new / updated available AI / ML assistance information related to the first network node - determining that all or at least part of the network-associated types of available AI / ML assistance information related to the first network node and sent to the second network node in a previous first message are no longer valid - confirming that the network-associated type of the available AI / ML assistance information related to the first network node and sent to the second network node in the previous first message has not changed (is still valid) - determining to send (or after sending) a sixth message to the second network node, the sixth message including a request to obtain a set of one or more predictive metrics from the second network node (with / without specifying whether the metric(s) are to be used for AI / ML assistance) - determining to send a sixth message to the second network node, the sixth message including an action or suggestion obtained by means of the AI / ML reasoning function deployed at the first network node - Sending a sixth message including the AI / ML model ID to the second network node. - (implicit request from the second network node) receiving a second message from the second network node, the second message comprising available AI / ML assistance information associated with the network related to the second network node.

[0090] In one option, the first message and the third message are the same. Example of the first message of variant 1 (further detailed in section 4.1)

[0091] In a non-limiting example of implementation, the first message may be implemented by extending an existing 3GPP message, such as: -(XnAP 3GPP interface): ○XN establishment request XnAP message, XN establishment response XnAP message, XN removal request XnAP message, NG-RAN node configuration update XnAP message, NG-RAN node configuration update confirmation XnAP message, resource status request XnAP message, resource status response XnAP message, handover request XnAP message, handover request confirmation XnAP message, resource status update XnAP message, retrieve UE context request XnAP message, retrieve UE context response XnAP message. -(F1AP 3GPP interface): ○F1 establishment request F1AP message, F1 establishment response F1AP message, F1 removal request F1AP message, GNB-DU configuration update F1AP message, GNB-DU configuration update confirmation F1AP message, GNB-CU configuration update F1AP message, GNB-CU configuration update confirmation F1AP message, resource status request F1AP message, resource status response F1AP message, resource status update F1AP message. -(E1AP 3GPP interface) ○GNB-CU-UP E1 establishment request E1AP message, GNB-CU-UP establishment response E1AP message, E1 release request E1AP message, GNB-CU-CP E1 establishment request E1AP message, GNB-CU-CPE1 establishment response E1AP message, GNB-CU-UP configuration update E1AP message, GNB-CU-UP configuration update confirmation E1AP message, GNB-CU-CP configuration update E1AP message, GNB-CU-CP configuration update confirmation E1AP message, resource status request E1AP message, resource status response E1AP message, resource status update E1AP message 2.3 Second and Third Messages

[0092] The second message is sent from the second network node to the first network node and includes one or more of the following: - a request to obtain a set of network-associated types of available AI / ML assistance information for the first network node. The requested set may be a complete set or a partial set of network-associated types of available AI / ML assistance information. - Network-related type of request to obtain only new and / or updated available AI / ML assistance information for the first network node - (Optional) Network-associated type of available AI / ML assistance information for the second network node - (Optional) An indication that the network-associated type of the available AI / ML assistance information of the second network node has not changed (is still valid) compared to the network-associated type of the available AI / ML assistance information of the second network node included in the previously sent second message. This element may be included in an alternative to the network-associated type of the available AI / ML assistance information of the first network node - (Optional) An indication that the network-associated type of the available AI / ML assistance information of the second network node provided in the second message modifies / overwrites the network-associated type of the previously delivered available AI / ML assistance information of the second network node (Optional) an indication that all or at least part of the network-associated type of available AI / ML assistance information of the second network node provided in the previous second message is no longer valid - (Optional) An indication that the network-associated type of the available AI / ML assistance information of the second network node provided in the second message is a supplement to the network-associated type of the available AI / ML assistance information of the second network node provided in the previous second message - (Optional) Network-associated type of one or more new and / or updated available AI / ML assistance information for the second network node

[0093] In a non-limiting example of implementation, the second message may be implemented by extending an existing 3GPP message as indicated for the first message, for example, extending an existing 3GPP message such as an XnAP 3GPP interface, an F1AP 3GPP interface, an E1AP 3GPP interface, etc. Conditions that trigger the transmission of the second message

[0094] In one embodiment, the second network node determines to send the second message when certain conditions are met, such as: - receiving a sixth message from the first network node, the sixth message comprising a request to provide the first network node with a set of one or more prediction metrics (without specifying whether the metrics are to be used for AI / ML assistance) - receiving a sixth message from the first network node, the sixth message comprising an action or suggestion obtained by means of an AI / ML reasoning function deployed at the first network node - Receive a sixth message including the AI / ML model ID from the first network node - (implicit request from the first network node) receiving a first message from the first network node, the first message comprising a network associated type of available AI / ML assistance information related to the first network node. 2.4 Sixth Message

[0095] The sixth message is sent from the first network node to the second network node and includes one or more of the following: - A request to obtain a set of one or more prediction metrics from a second network node (with / without specifying whether the metric(s) are to be used for AI / ML assistance) In one example, the sixth message may be an XnAP resource status request message or an XnAP AIML assistance data request, including a request for one or more of the predicted load related metrics, such as predicted composite available capacity, predicted energy efficiency, predicted PRB utilization in DL / UL (for GBR / non-GBR), predicted capacity per network slice, predicted UE performance (such as UL / DL throughput), predicted - Actions or recommendations obtained with the help of AI / ML reasoning functions deployed at the first network node

[0096] In a non-limiting example of implementation, the sixth message may be implemented by extending an existing 3GPP message as indicated for the first message. 2.5 Network-related types of available AI / ML-assisted information

[0097] The network-associated types of AI / ML assistance information available to network nodes include one or more of the following: - identifier(s) of the type(s) of the AI / ML model(s) (e.g., feedforward neural network, convolutional neural network, recurrent neural network, graph neural network, attention model, autoencoder, etc.), - Identifiers of supported AI / ML algorithms (e.g., supervised learning, unsupervised learning, reinforcement learning, federated learning, etc.), - an indication of a certain number (e.g., a maximum number) of hidden layers that a certain type of AI / ML model can support, - an indication of the size (e.g., maximum size) of AI / ML models that can be supported for one or more types of supported AI / ML models, - an indication of a certain number (e.g., a maximum number) of hidden units / nodes per hidden layer that a certain type of AI / ML model can support, - Identifiers of AI / ML-supported use cases and / or AI / ML-related operations / procedures / functionalities (such as load balancing, energy saving, mobility, link adaptation, power control, antenna tilt, etc.), - Hardware indications specific to the AIML process, such as chipset type and / or model, memory capabilities, computing power, CPU, GPU, etc., - information related to the AI / ML capabilities of the network node and / or associated identifier(s), - information related to the AI / ML model requirements of the network node and / or associated identifier(s), - Information related to AI / ML model lifecycle management for network nodes and / or associated identifier(s), such as: ○ an indication of support for Test Lifecycle Management (LCM), ○ One or more indicators indicating support for LCM processes, such as: activation / deactivation of AI / ML models, switching between AI / ML models, reverting to an AI / ML model, registration of AI / ML models, update of AI / ML models, - information about measurement(s) determined or obtained by the network node and / or associated identifier(s), - information about a prediction determined or obtained by a network node and / or associated identifier(s), - Support for the provision of certain forecasts, which may include one or more of the following: ○ Information types that support prediction, o a reference prediction time that may support prediction, where the reference prediction time indicates a predicted future time at which certain information may be determined, ■ According to one embodiment, for a given type of information, prediction can be supported based on one or more reference prediction times ■ According to another embodiment, the reference prediction time may be indicated as a time offset from the time when the prediction was determined, ○ AI / ML model prediction quality or performance associated with reference prediction times for different types of information and / or different types of support that can provide predictions, ■ According to one embodiment, the AI / ML model prediction quality or performance can be expressed as the AI / ML model prediction accuracy or the AI / ML model prediction error, such as mean square error, ●Thus, different types of information and / or predictions associated with different reference prediction times may be obtained or supported with different AI / ML model prediction qualities. o An event or condition that can be configured to trigger one or more types of support for prediction. In addition, a specific support configuration for the triggering event or condition can be indicated, such as a threshold associated with a specific parameter or measurement, o the reliability condition associated with the prediction, i.e. the condition on which the provided prediction for the reference prediction time is based is reliable (or trustworthy, i.e. can be used) or unreliable, ■ According to one embodiment, the reliability condition may be associated with one or more of the following: ●The type of information that supports the prediction ●The reference forecast time to support the forecast, or ●The combination of o In some non-limiting examples, the reliability condition may be related to: coverage-related information (e.g., coverage status, or coverage index of at least one cell or one reference signal beam), energy (or power)-related information (e.g., energy efficiency index, or energy consumption index, energy consumption status, power status, or power index), DRX (discontinuous reception) or DTX (discontinuous transmission) configuration, availability and / or use of certain carrier frequencies, certain radio access technologies, use of certain transmission points, delivery of a certain type of traffic (e.g., bursty traffic, periodic traffic, delay-critical traffic), - inferred action(s) and / or associated identifier(s) determined or obtained by the network node, - an indication of support for providing feedback for actions triggered / recommended by the AI / ML model, - an indication indicating support for a certain training strategy(ies), - an indication of support for partial AI / ML model training at the UE side / network side, - an indication indicating support for inferring certain information, - an indication indicating support for using certain inferred information, - An indication indicating support for periodic / aperiodic feedback auxiliary information (e.g., for AI / ML model monitoring). 3. Embodiment of Variant 2 (First Network Node and User Equipment) 3.1 Variant 2a

[0098] The first network node sends a first message a to the UE, wherein the first message a includes information that the first network node (or a third network node via the first network node) can To UE A network-associated type that provides available AI / ML assistance information to assist AI / ML models.

[0099] In this variation, Figure 8 As described in , perform the following steps: The first network node (or a third network node via the first network node) sends a first message to the UE, the first message including an indication of a network-associated type(s) of available AI / ML assistance information that the first network node (or the third network node via the first network node) can provide to the UE to assist the AI / ML model (step 800).

[0100] Likewise Figure 8 As described in, in one embodiment, the user device uses the received information to perform one or more actions, the received information indicating the network-associated types of available AI / ML assistance information types that the first network node can provide related to the first network node. The one or more actions can be any desired (one or more) actions (step 810). For example, the user device can use this received information to request at least one of the network-associated types of available AI / ML assistance information from the first network node (step 810). The user device can then, for example, receive at least one of the network-associated types of available AI / ML assistance information from the first network node and use this information for one or more AI / ML operations (e.g., training or updating an AI or ML model, or any action that can use the received information) (see also step 810A). As another example, the user device can send the information received in the first message to another network node or another user device (step 810B). Example of the first message of variant 2 (further detailed in Section 5)

[0101] In one example of any one of Variant 2, the first message is a signaling message not associated with a certain UE; in another example of Variant 2, the first message is a signaling message associated with a certain UE.

[0102] In one example, when the first network node transmits the first message to the user equipment, the first message can be implemented and transmitted by means of a new RRC procedure / message or by reusing an existing procedure / message (such as an RRCReconfiguration message, an RRCSetup message, or an RRCResume message). 3.2 Variant 2b (Seventh and Eighth Messages)

[0103] The first network node sends a first message to the UE (or UE group), the first message including an indication that the UE (or UE group) can request the network that the first network node (or a third network node via the first network node) can provide To (one or more) UE Network-associated types of available AI / ML assistance information (on-demand) to assist AI / ML models.

[0104] In this variation, Figure 9 As described in , perform the following steps: The first network node (or a third network node via the first network node) sends a first message to a UE (or a group of UEs), the first message including (one or more) indications indicating a network-associated type that the UE (or group of UEs) may request from the first network node available AI / ML assistance information (on demand) that the first network node (or the third network node via the first network node) may provide to the UE to assist an AI / ML model (step 900). In one scenario, a first network node sends a broadcast message, such as a system information message, to a group of UEs, the system information message including at least one indication (e.g., a flag) indicating a network-associated type of available AI / ML assistance information that the UEs may request from the first network node. The first network node may also indicate a configuration (e.g., configuration of Msg1 resources) of a network-associated type of system information message(s) that the UEs need to use to request the network-associated type of available AI / ML assistance information. o In another case, the first network node sends a dedicated message to a specific UE, indicating the network-associated type for which the UE can request (on-demand) available AI / ML assistance information - The UE (or one of the UEs in the UE group) transmits a seventh message to the first network node to request the first network node (or a third network node via the first network node) to provide To UE The network type is associated with available AI / ML assistance information for the AI / ML mode (step 910). o In one example, a seventh message transmitted by the UE to the first network node by means of a new RRC procedure / message or reusing an existing procedure / message (such as an RRCSystemInfoRequest message) (e.g., see examples in section 2.7.5) - The first network node sends an eighth message including the requested information to the UE (step 920).In one example, the eighth message may be implemented using an RRC signaling procedure similar to the first message described in variant 2a above. o In one example, the eighth message is transmitted by the first network node to the UE by means of a new RRC procedure / message or reusing an existing procedure / message (such as RRCReconfiguration message, RRCSetup message, RRCResume message). 3.3 Variant 2c

[0105] exist Figure 10 In one embodiment described in , the UE transmits a seventh message to the first network node to request that the first network node (or a third network node via the first network node) provide network-associated types of available AI / ML assistance information to assist AI / ML models to one or more UEs, without receiving any prior indication from the first network node regarding the availability of the network-associated types of available AI / ML assistance information (step 1000). In this variation, the first network node may reply by transmitting a first message to the user device, the first message including the network-associated types of available AI / ML assistance information that the first network node (or a third network node via the first network node) can provide to the UE(s) to assist AI / ML operations at the user device (step 1010). Thus, in this variation, the transmission of the first message from the first network node is conditional on the prior receipt of the seventh message from the user device. 4 Example of implementation of variant 1

[0106] In this section, some examples of implementation of Variant 1 (first network node and second network node) are shown, wherein parts marked with bold, italic, and underline are related to supplements of the present disclosure. 4.1 Example of the first message

[0107] In one possible implementation example, the first message is implemented by an XN Setup Request XnAP message, which is extended to indicate a RAN-associated type (marked in bold, italics, and underline) of available AI / ML assistance information of the first network node. 9.1.3.1 XN Establishment Request

[0108] This message is sent by an NG-RAN node to a neighboring NG-RAN node to transfer application data of an Xn-C interface instance.

[0109] Direction: NG-RAN node 1 → NG-RAN node 2.

[0110] In other possible implementation examples, the first message is implemented by an AI / ML information update XnAP (or similar), including an IE of a RAN-associated type (marked in bold, italics, underline) for signaling available AI / ML assistance information of the first network node. 9.1.3.FF AI / ML Information Update

[0111] This message is sent by NG-RAN node 2 to NG-RAN node 1 to report the requested AI / ML related information.

[0112] Direction: NG-RAN node 2 → NG-RAN node 1.

[0113] A first example of a RAN-associated type (9.2.3.xx) of available AI / ML assistance information is provided below, where the information is associated with the sending network node. 9.2.3.xx RAN-related types of available AI / ML-assisted information

[0114] This IE contains the RAN-related type of available AI / ML assistance information.

[0115] A second example of a RAN-associated type (9.2.3.xx) of available AI / ML assistance information is provided below, where the available AI / ML assistance information is provided per AI / ML model. 9.2.3.xx RAN-related types of available AI / ML-assisted information

[0116] This IE contains the RAN-related type of available AI / ML assistance information. 4.2 Example of the Second Message

[0117] In one possible implementation example, the second message is implemented by an AI / ML information request XnAP (or similar). One of the IEs in the message (e.g., the Reporting Characteristics IE) is extended to include a special bit that, when set to 1, indicates a RAN-associated type request for available AI / ML assistance information of the first network node (marked in bold, italics, and underline). 9.1.3.CCAIML Information Request

[0118] This message is sent by NG-RAN node 1 to NG-RAN node 2 to initiate the requested AI / ML related information reporting according to the parameters given in the message.

[0119] Direction: NG-RAN node 1 → NG-RAN node 2.

[0120] According to one embodiment, if only the first bit (type of RAN-associated available AI / ML assistance information) is set to 1, it implies a request to receive assistance information for all available prediction types and associated formats (e.g., reference prediction time and / or reliability conditions).

[0121] According to another embodiment, if the first bit (RAN associated available AI / ML assistance information type) is set to 1, and at least another bit associated with a specific prediction type is also set to 1 (e.g., the second bit associated with predicted energy efficiency), this implies a request to receive assistance information only for the indicated prediction type. 4.3 Additional Examples of First and Second Messages

[0122] In another example related to the XnAP interface and reported below (new elements marked in bold, italics, and underline), the first network node is a first NG-RAN node (NG-RAN node 1), the second network node is a second NG-RAN node (NG-RAN node 2), and the first message and the second message are included in the same logical process of the signaling interface (e.g., Xn Setup XnAP process). The second message is an initiation message of the process (e.g., XN Setup Request XnAP message), and the first message is a response message of the same process (e.g., XN Setup Response XnAP message). In a specific example of implementation, the process text of the existing Xn Setup process is extended to include aspects regarding the available AI / ML assistance information described in the present disclosure:

[0123] If the RAN-associated type IE of available AI / ML assistance information is included in the XN setup request message, and if the NG-RAN node 2 is a gNB, the NG-RAN node 2 may include the available AI / ML assistance information IE in the XN setup response message.

[0124] In the same example, the XN Setup Request implementing the second message is extended as follows: 9.1.3.1 XN Establishment Request

[0125] This message is sent by an NG-RAN node to a neighboring NG-RAN node to transfer application data of an Xn-C interface instance.

[0126] Direction: NG-RAN node 1 → NG-RAN node 2.

[0127] In the same example, the XN Setup Response implementing the first message is extended as follows: 9.1.3.2 XN Setup Response

[0128] This message is sent by an NG-RAN node to a neighboring NG-RAN node to transfer application data of an Xn-C interface instance.

[0129] Direction: NG-RAN node 2 → NG-RAN node 1.

[0130] In yet another example related to the F1AP interface and reported below (marked in bold, italics, and underline), the first network node is a gNB-DU, the second network node is a gNB-CU, the first message is an F1 Setup Request F1AP message (from the gNB-DU to the gNB-CU), and the existing F1AP message is extended with a new Available AI / ML Assistance Information IE. The procedure text of the F1 Setup F1AP procedure is extended as follows:

[0131] If the RAN associated type IE of available AI / ML assistance information is included in the serving cell information IE in the F1 setup request message, the gNB-CU shall consider it if supported. 5 Implementation Example of Variant 2 (First Network Node and User Device)

[0132] In this section, some examples of implementation of Variant 2 (first network node and user equipment) are shown, wherein parts marked with bold, italic and underline are related to the supplement of the present disclosure. 5.1 Implementation Example of the First Message

[0133] In another implementation example, the gNB may send an RRC message (e.g., an RRCReconfiguration message) to the UE, where the RRC message is extended to indicate that the gNB may provide certain types of RAN-associated AI / ML assistance information. 5.2 Implementation Example of the Seventh Message

[0134] In an example implementation, the UE requests the RAN-associated type of available AI / ML assistance information from the RAN node by extending the RRCSystemInfoRequest RRC message. 6 Further description

[0135] Figure 11An example of a cellular communication system 1100 in which embodiments of the present disclosure may be implemented is illustrated. In the embodiments described herein, the cellular communication system 1100 is a 5G system (5GS) including a next-generation RAN (NG-RAN) and a 5G core (5GC); however, embodiments of the present disclosure may be implemented in other types of wireless communication systems, such as, for example, EPS / LTE systems, sixth-generation (6G) systems, and the like. In this example, the RAN includes base stations 1102-1 and 1102-2 that control corresponding (macro) cells 1104-1 and 1104-2, which in the 5GS include NR base stations (gNBs) and optional next-generation eNBs (ng-eNBs) (e.g., LTE RAN nodes connected to the 5GC). Base stations 1102-1 and 1102-2 are generally referred to herein collectively as a plurality of base stations 1102, and individually as base station 1102. Similarly, (macro) cells 1104-1 and 1104-2 are generally referred to herein as a plurality of (macro) cells 1104, and individually as a (macro) cell 1104. The RAN may also include a plurality of low-power nodes 1106-1 to 1106-4 that control corresponding small cells 1108-1 to 1108-4. Low-power nodes 1106-1 to 1106-4 may be small base stations (such as pico or femto base stations) or RRHs, etc. It is worth noting that, although not illustrated, one or more of small cells 1108-1 to 1108-4 may alternatively be provided by base station 1102. Low-power nodes 1106-1 to 1106-4 are generally referred to herein as a plurality of low-power nodes 1106, and individually as a low-power node 1106. Similarly, small cells 1108-1 to 1108-4 are generally referred to herein as a plurality of small cells 1108, and individually as a small cell 1108. The cellular communication system 1100 also includes a core network 1110, which is referred to as 5GC in the 5G system (5GS). A plurality of base stations 1102 (and optionally a plurality of low power nodes 1106) are connected to the core network 1110.

[0136] Multiple base stations 1102 and multiple low power nodes 1106 provide service to UEs 1112-1 through 1112-5 in corresponding multiple cells 1104 and 1108. UEs 1112-1 through 1112-5 are generally referred to herein collectively as multiple UEs 1112, and individually as UE 1112.

[0137] Note that multiple UEs 1112 may perform the functionality of user devices or UEs described above, for example, with respect to variants 1-8. Furthermore, in one embodiment, base station 1102 is an example of a first network node described above, for example, with respect to variants 1-8. Furthermore, in one embodiment, the second network node described above, for example, with respect to variants 1-8, may be, for example, another base station 1102 or a core network node.

[0138] Figure 12 1 is a schematic block diagram of a radio access node 1200 according to some embodiments of the present disclosure. Optional features are represented by dashed boxes. Radio access node 1200 may be, for example, base station 1102 or 1106, or a network node that implements all or part of the functionality of base station 1102 or gNB described herein. As illustrated, radio access node 1200 includes a control system 1202 comprising one or more processors 1204 (e.g., a central processing unit (CPU), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), and / or the like), memory 1206, and a network interface 1208. The one or more processors 1204 are also referred to herein as processing circuitry. Additionally, radio access node 1200 may include one or more radio units 1210, each comprising one or more transmitters 1212 and one or more receivers 1214 coupled to one or more antennas 1216. Radio unit 1210 may relate to or be part of radio interface circuitry. In some embodiments, the radio unit(s) 1210 are external to the control system 1202 and connected to the control system 1202 via, for example, a wired connection (e.g., a fiber optic cable). However, in some other embodiments, the radio unit(s) 1210 and potentially the antenna(s) 1216 are integrated with the control system 1202. As described herein, the one or more processors 1204 operate to provide one or more functions of the radio access node 1200. In some embodiments, the function(s) are implemented in software stored, for example, in the memory 1206 and executable by the one or more processors 1204.

[0139] Figure 13 1 is a schematic block diagram illustrating a virtualized embodiment of a radio access node 1200 according to some embodiments of the present disclosure. This discussion is equally applicable to other types of network nodes. Furthermore, other types of network nodes may have similar virtualized architectures. Again, optional features are represented by dashed boxes.

[0140] As used herein, a "virtualized" radio access node is an implementation of a radio access node 1200 in which at least a portion of the functionality of the radio access node 1200 is implemented as one or more virtual components (e.g., via one or more virtual machines executing on one or more physical processing nodes in one or more networks). As illustrated, in this example, as described above, the radio access node 1200 may include a control system 1202 and / or one or more radio units 1210. The control system 1202 may be connected to the radio unit(s) 1210 via, for example, an optical cable. The radio access node 1200 includes one or more processing nodes 1300, which are coupled to or included as part of the network(s) 1302. If present, the control system 1202 or the radio unit(s) are connected to the processing node(s) 1300 via the network 1302. Each processing node 1300 includes one or more processors 1304 (e.g., CPUs, ASICs, FPGAs, etc.), a memory 1306, and a network interface 1308.

[0141] In this example, the functionality 1310 of the radio access node 1200 described herein is implemented at the one or more processing nodes 1300 or distributed in any desired manner across the one or more processing nodes 1300 and the control system 1202 and / or the radio unit(s) 1210. In some specific embodiments, some or all of the functionality 1310 of the radio access node 1200 described herein is implemented as virtual components executed by one or more virtual machines implemented in a virtual environment(s) hosted by the processing node(s) 1300. As will be appreciated by one of ordinary skill in the art, additional signaling or communication between the processing node(s) 1300 and the control system 1202 is used to perform at least some of the desired functionality 1310. Notably, in some embodiments, the control system 1202 may not be included, in which case the radio unit(s) 1210 communicates directly with the processing node(s) 1300 via an appropriate network interface(s).

[0142] In some embodiments, a computer program comprising instructions is provided that, when executed by at least one processor, causes the at least one processor to perform the functionality of a radio access node 1200 or a node (e.g., processing node 1300) that implements one or more of the functions 1310 of the radio access node 1200 in a virtual environment according to any of the embodiments described herein. In some embodiments, a carrier comprising the aforementioned computer program product is provided. The carrier is one of an electronic signal, an optical signal, a radio signal, or a computer-readable storage medium (e.g., a non-transitory computer-readable medium such as a memory).

[0143] Figure 14 is a schematic block diagram of a radio access node 1200 according to some other embodiments of the present disclosure. The radio access node 1200 includes one or more modules 1400, each of which is implemented in software. The module(s) 1400 provide the functionality of the radio access node 1200 described herein. This discussion is also applicable to Figure 13 1300 , where module 1400 may be implemented at one of processing nodes 1300 or distributed across multiple processing nodes 1300 and / or distributed across (one or more) processing nodes 1300 and control system 1202 .

[0144] Figure 15 is a schematic block diagram of a UE 1500 according to some embodiments of the present disclosure. As illustrated, the UE 1500 includes one or more processors 1502 (e.g., CPUs, ASICs, FPGAs, and / or the like), a memory 1504, and one or more transceivers 1506, each of which includes one or more transmitters 1508 and one or more receivers 1510 coupled to one or more antennas 1512. As will be appreciated by one of ordinary skill in the art, the transceiver(s) 1506 include radio front-end circuitry connected to the antenna(s) 1512, the radio front-end circuitry being configured to condition signals passed between the antenna(s) 1512 and the processor(s) 1502. The processor 1502 is also referred to herein as processing circuitry. The transceiver 1506 is also referred to herein as radio circuitry. In some embodiments, the functionality of the UE 1500 described above may be implemented in whole or in part using software stored in the memory 1504 and executed by the processor(s) 1502. Note that the UE 1500 may include components not described in Figure 15, such as, for example, one or more user interface components (e.g., input / output interfaces including a display, buttons, a touch screen, a microphone, speaker(s), and / or the like and / or any other components for allowing information to be input into the UE 1500 and / or allowing information to be output from the UE 1500), a power source (e.g., a battery and associated power circuitry), etc.

[0145] In some embodiments, a computer program comprising instructions is provided that, when executed by at least one processor, causes the at least one processor to perform the functionality of the UE 1500 according to any of the embodiments described herein. In some embodiments, a carrier comprising the aforementioned computer program product is provided. The carrier is one of an electronic signal, an optical signal, a radio signal, or a computer-readable storage medium (e.g., a non-transitory computer-readable medium such as a memory).

[0146] Figure 16 1 is a schematic block diagram of a UE 1500 according to some other embodiments of the present disclosure. The UE 1500 includes one or more modules 1600, each of which is implemented in software. As described herein, the module(s) 1600 provide the functionality of the UE 1500.

[0147] refer to Figure 17 According to an embodiment, a communication system includes a telecommunications network 1700, such as a 3GPP-type cellular network, including an access network 1702, such as a RAN, and a core network 1704. Access network 1702 includes a plurality of base stations 1706A, 1706B, and 1706C, such as Node Bs, eNBs, gNBs, or other types of wireless access points (APs), each defining a corresponding coverage area 1708A, 1708B, and 1708C. Each base station 1706A, 1706B, and 1706C is connectable to core network 1704 via a wired or wireless connection 1710. A first UE 1712 located in coverage area 1708C is configured to wirelessly connect to or be paged by the corresponding base station 1706C. A second UE 1714 in coverage area 1708A is wirelessly connectable to the corresponding base station 1706A. Although multiple UEs 1712 , 1714 are illustrated in this example, the disclosed embodiments are equally applicable to scenarios where a sole UE is in the coverage area or where a sole UE is connecting to the corresponding base station 1706 .

[0148] The telecommunications network 1700 itself is connected to a host computer 1716, which can be embodied in the hardware and / or software of a standalone server, a cloud-enabled server, a distributed server, or as processing resources in a server farm. Host computer 1716 can be under the ownership or control of a service provider, or can be operated by or on behalf of a service provider. Connections 1718 and 1720 between telecommunications network 1700 and host computer 1716 can extend directly from core network 1704 to host computer 1716, or can be via an optional intermediary network 1722. Intermediary network 1722 can be one of a public, private, or managed network, or a combination of more than one of these networks; intermediary network 1722, if present, can be a backbone network or the Internet; in particular, intermediary network 1722 can include two or more subnetworks (not shown).

[0149] Figure 17 The communication system as a whole enables connectivity between connected UEs 1712, 1714 and a host computer 1716. The connectivity can be described as an over-the-top (OTT) connection 1724. The host computer 1716 and the connected UEs 1712, 1714 are configured to communicate data and / or signaling via the OTT connection 1724 using the access network 1702, the core network 1704, any intermediate networks 1722, and possible additional infrastructure (not shown) as intermediaries. The OTT connection 1724 can be transparent in the sense that the participating communication devices through which the OTT connection 1724 passes are unaware of the routing of uplink and downlink communications. For example, the base station 1706 may not be informed or need not be informed of the past routing of incoming downlink communications, where data originating from the host computer 1716 is to be forwarded (e.g., handed over) to the connected UE 1712. Similarly, base station 1706 need not be aware of future routing of outbound uplink communications originating from UE 1712 toward host computer 1716 .

[0150] Now refer to Figure 1818. The present invention relates to a system for transmitting data to a user of the present invention. The system 1800 includes a host computer 1802 that includes hardware 1804, including a communication interface 1806 configured to establish and maintain a wired or wireless connection with different communication devices of the communication system 1800. The host computer 1802 further includes a processing circuit 1808 that may have storage and / or processing capabilities. In particular, the processing circuit 1808 may include one or more programmable processors, ASICs, FPGAs, or a combination thereof (not shown) suitable for executing instructions. The host computer 1802 further includes software 1810 that is stored in the host computer 1802 or is accessible by the host computer 1802 and can be executed by the processing circuit 1808. The software 1810 includes a host application 1812. The host application 1812 may be operable to provide services to a remote user, such as a UE 1814 connected via an OTT connection 1816 terminating between the UE 1814 and the host computer 1802. In providing the service to the remote user, the host application 1812 may provide user data transmitted using the OTT connection 1816.

[0151] The communication system 1800 further includes a base station 1818 provided in the telecommunication system and including hardware 1820 that enables it to communicate with the host computer 1802 and with the UE 1814. The hardware 1820 may include a communication interface 1822 for establishing and maintaining wired or wireless connections with different communication devices of the communication system 1800 and hardware 1820 for establishing and maintaining connections with at least those located in the coverage area served by the base station 1818 (not in the coverage area). Figure 18 The communication interface 1822 may be configured to facilitate a connection 1828 to the host computer 1802. The connection 1828 may be direct, or it may be through a core network of the telecommunications system (not shown). Figure 18 ) and / or through one or more intermediate networks external to the telecommunications system. In the illustrated embodiment, the hardware 1820 of the base station 1818 further includes processing circuitry 1830, which may include one or more programmable processors, ASICs, FPGAs, or a combination thereof (not shown) adapted to execute instructions. The base station 1818 further has software 1832 stored internally or accessible via an external connection.

[0152] The communication system 1800 further includes the aforementioned UE 1814. The hardware 1834 of the UE 1814 may include a radio interface 1836 configured to establish and maintain a wireless connection 1826 with a base station serving the coverage area in which the UE 1814 is currently located. The hardware 1834 of the UE 1814 further includes processing circuitry 1838, which may include one or more programmable processors, ASICs, FPGAs, or a combination thereof (not shown) adapted to execute instructions. The UE 1814 further includes software 1840 stored in the UE 1814 or accessible by the UE 1814 and executable by the processing circuitry 1838. The software 1840 includes a client application 1842. The client application 1842 may be operable to provide services to a human or non-human user via the UE 1814 with the support of the host computer 1802. In host computer 1802, an executing host application 1812 can communicate with an executing client application 1842 via an OTT connection 1816 terminated between UE 1814 and host computer 1802. When providing services to a user, client application 1842 can receive request data from host application 1812 and provide user data in response to the request data. OTT connection 1816 can transmit both the request data and the user data. Client application 1842 can interact with the user to generate the user data it provides.

[0153] Notice that Figure 18 The host computer 1802, base station 1818 and UE 1814 described in Figure 17 The host computer 1716, one of the base stations 1706A, 1706B, 1706C, and one of the UEs 1712, 1714 are similar or identical. That is, the internal workings of these entities may be similar to Figure 18 As shown in , and independently, the surrounding network topology can be Figure 17 The surrounding network topology.

[0154] exist Figure 18 In FIG, an OTT connection 1816 has been abstractly drawn to illustrate communication between a host computer 1802 and a UE 1814 via a base station 1818, without explicitly mentioning any intermediate devices and the precise routing of messages via these devices. The network infrastructure can determine the routing, which can be configured to be hidden from the UE 1814 or from the service provider operating the host computer 1802, or both. While the OTT connection 1816 is active, the network infrastructure can further make decisions by which it dynamically changes the routing (e.g., based on network reconfiguration or load balancing considerations).

[0155] The wireless connection 1826 between the UE 1814 and the base station 1818 is in accordance with the teachings of the embodiments described throughout this disclosure. One or more of the various embodiments improves the performance of an OTT service provided to the UE 1814 using the OTT connection 1816, where the wireless connection 1826 forms the last leg.

[0156] The measurement process may be provided for the purpose of monitoring data rate, latency, and other factors improved by one or more embodiments. In response to changes in the measurement results, there may further be optional network functionality for reconfiguring the OTT connection 1816 between the host computer 1802 and the UE 1814. The measurement process and / or the network functionality for reconfiguring the OTT connection 1816 may be implemented in the software 1810 and hardware 1804 of the host computer 1802 or in the software 1840 and hardware 1834 of the UE 1814, or in both. In some embodiments, a sensor (not shown) may be deployed in or associated with the communication device through which the OTT connection 1816 passes; the sensor may participate in the measurement process by providing the values ​​of the monitoring quantities exemplified above or providing the values ​​of other physical quantities from which the software 1810, 1840 can calculate or estimate the monitoring quantities. Reconfiguration of the OTT connection 1816 may include message formats, retransmission settings, preferred routing, and the like; the reconfiguration need not affect the base station 1818 and may be unknown or imperceptible to the base station 1818. Such processes and functionality may be known and implemented in the art. In certain embodiments, the measurements may involve proprietary UE signaling that facilitates measurement of throughput, propagation time, latency, and the like by the host computer 1802. The measurements may be achieved because the software 1810 and 1840 uses the OTT connection 1816 to cause messages, particularly empty or "dummy" messages, to be transmitted while the software 1810 and 1840 monitors propagation time, errors, and the like.

[0157] Figure 19 is a flow chart illustrating a method implemented in a communication system according to one embodiment. The communication system includes a Figure 17 and Figure 18 For the sake of simplicity of this disclosure, only the referenced Figure 19In step 1900, the host provides user data. In sub-step 1902 of step 1900 (which may be optional), the host provides the user data by executing a host application. In step 1904, the host initiates a transmission to the UE carrying the user data. In step 1906 (which may be optional), in accordance with the teachings of the embodiments described throughout this disclosure, the base station transmits the user data carried in the host-initiated transmission to the UE. In step 1908 (which may also be optional), the UE executes a client application associated with the host application executed by the host.

[0158] Figure 20 is a flow chart illustrating a method implemented in a communication system according to one embodiment. The communication system includes a Figure 17 and Figure 18 For the sake of simplicity of this disclosure, only the referenced Figure 20 In step 2000 of the method, a host provides user data. In an optional sub-step (not shown), the host provides the user data by executing a host application. In step 2002, the host initiates a transmission to the UE carrying the user data. According to the teachings of the embodiments described throughout this disclosure, the transmission may pass through a base station. In step 2004 (which may be optional), the UE receives the user data carried in the transmission.

[0159] Figure 21 is a flow chart illustrating a method implemented in a communication system according to one embodiment. The communication system includes a Figure 17 and Figure 18 For the sake of simplicity of this disclosure, only the referenced Figure 21 . In step 2100 (which may be optional), the UE receives input data provided by the host. Additionally or alternatively, in step 2102, the UE provides user data. In sub-step 2104 (which may be optional) of step 2100, the UE provides the user data by executing a client application. In sub-step 2106 (which may be optional) of step 2102, the UE executes the client application, which provides the user data as a reaction to the received input data provided by the host. In providing the user data, the executed client application may further take into account the user input received from the user. Regardless of the specific manner in which the user data is provided, the UE initiates the transmission of the user data to the host in sub-step 2108 (which may be optional). In step 2110 of the method, the host receives the user data transmitted from the UE in accordance with the teachings of the embodiments described throughout this disclosure.

[0160] Figure 22is a flow chart illustrating a method implemented in a communication system according to one embodiment. The communication system includes a Figure 17 and Figure 18 For the sake of simplicity of this disclosure, only the referenced Figure 22 In step 2200 (which may be optional), the base station receives user data from the UE in accordance with the teachings of the embodiments described throughout this disclosure. In step 2202 (which may be optional), the base station initiates a transmission of the received user data to the host. In step 2204 (which may be optional), the host receives the user data carried in the transmission initiated by the base station.

[0161] Any appropriate steps, methods, features, functions or benefits disclosed herein may be performed by one or more functional units or modules of one or more virtual devices. Each virtual device may include a plurality of these functional units. These functional units may be implemented with the aid of processing circuits that may include one or more microprocessors or microcontrollers and other digital hardware that may include digital signal processors (DSPs), dedicated digital logic, and the like. The processing circuit may be configured to execute program code stored in a memory, which may include one or more types of memory, such as read-only memory (ROM), random access memory (RAM), cache memory, flash memory device, optical storage device, and the like. The program code stored in the memory includes program instructions for executing one or more telecommunications and / or data communication protocols and instructions for executing one or more of the technologies described herein. In some implementations, according to one or more embodiments of the present disclosure, the processing circuit may be used to cause the corresponding functional unit to perform the corresponding function.

[0162] Although the processes in the figures may illustrate a particular order of operations performed by certain embodiments of the present disclosure, it should be understood that such order is exemplary (e.g., alternative embodiments may perform operations in a different order, combine certain operations, overlap certain operations, etc.).

[0163] Some example embodiments of the present disclosure are as follows:

[0164] Embodiment 1: A method performed by a node (e.g., a second network node or a user device), comprising: receiving (210; 300; 410; 510; 610; 710; 800; 900; 1010) a first message from a first network node, the first message comprising information indicating a network-associated type of available artificial intelligence (AI) or machine learning (ML) assistance information that the first network node can provide.

[0165] Embodiment 2: The method according to embodiment 1 further includes using the received information to perform one or more actions.

[0166] Embodiment 3: The method of embodiment 2, wherein the one or more actions include sending a request to the first network node for at least one of the network-associated types of indicated available AI or ML assistance information.

[0167] Embodiment 4: A method according to embodiment 2, wherein the one or more actions include: sending a request for at least one of the indicated network-associated types of available AI or ML assistance information to the first network node; receiving the at least one of the indicated network-associated types of available AI or ML assistance information from the first network node; and performing one or more AI or ML-related operations (e.g., updating or training an AI or ML model) based on the at least one of the indicated network-associated types of available AI or ML assistance information received from the first network node.

[0168] Embodiment 5: The method of embodiment 2, wherein the one or more actions include sending at least some of the received information to another node (eg, to a network node or a user device).

[0169] Embodiment 6: The method according to any one of embodiments 1 to 5, wherein the network association type of the available AI or ML assistance information is related to the first network node or the third network node.

[0170] Embodiment 7: The method according to any one of embodiments 1 to 6, wherein the node is a second network node.

[0171] Embodiment 8: The method according to embodiment 7 further includes, before receiving the first message, sending (200; 400; 500) to the first network node a request for the information indicating the network-associated type of available AI or ML assistance information related to the first network node that the first network node can provide.

[0172] Embodiment 9: The method according to embodiment 7 or 8 also includes sending (420; 520; 630; 730) to the first network node a request for at least one of the network-associated types of the AI ​​or ML assistance information related to the first network node that the first network node can provide.

[0173] Embodiment 10: The method of embodiment 9 further comprising receiving (530) an ACK, a partial ACK, or a NACK from the first network node in response to the request.

[0174] Embodiment 11: The method according to embodiment 10 further includes receiving (540) from the first network node at least some of the requests for at least one of the network-associated types of the AI ​​or ML assistance information related to the first network node that the first network node can provide.

[0175] Embodiment 12: The method of embodiment 9 further comprising receiving (640; 740) a NACK or a partial NACK from the first network node in response to the request.

[0176] Embodiment 13: The method according to embodiment 12 further includes receiving (650; 760) from the first network node update information indicating a network-associated type of available AI or ML assistance information related to the first network node that the first network node can provide.

[0177] Embodiment 14: The method according to embodiment 13 further includes, before receiving (760) the update information from the first network node, sending (750) a request for (update) information to the first network node, the (update) information indicating a network-associated type of available AI or ML assistance information related to the first network node that the first network node can provide.

[0178] Embodiment 15: The method according to embodiment 7 further includes sending (310) a second message to the first network node, the second message including information indicating a network-associated type of available AI or ML assistance information related to the second network node that the second network node can provide.

[0179] Embodiment 16: The method according to any one of embodiments 1 to 5, wherein the node is a user equipment (eg, UE).

[0180] Embodiment 17: The method according to embodiment 16 further includes: sending (910) a request to the first network node for at least one of the network-associated types of the available AI or ML assistance information related to the first network node that the first network node can provide; and receiving (920) from the first network node the at least one of the network-associated types of the available AI or ML assistance information related to the first network node that the first network node can provide.

[0181] Embodiment 18: The method according to embodiment 16 further includes, before receiving the first message from the first network node, sending (1000) a request for the information to the first network node, the information indicating a network-associated type of available AI or ML assistance information related to the first network node that the first network node can provide.

[0182] Embodiment 19: A node suitable for executing the method described in any one of embodiments 1 to 18.

[0183] Embodiment 20: A method performed by a first network node, comprising: sending (210; 300; 410; 510; 610; 710; 800; 900; 1010) a first message to a node (e.g., a second network node or a user device), the first message comprising information indicating a network-associated type of available artificial intelligence (AI) or machine learning (ML) assistance information related to the first network node that the first network node can provide.

[0184] Embodiment 21: The method according to embodiment 20, wherein the node is a second network node.

[0185] Embodiment 22: The method according to embodiment 21 also includes, before sending the first message, receiving (200; 400; 500) from the second network node a request for the information indicating the network-associated type of available AI or ML assistance information related to the first network node that the first network node can provide.

[0186] Embodiment 23: The method according to embodiment 21 or 22 also includes receiving (420; 520; 630; 730) a request from the second network node for at least one of the network-associated types of the AI ​​or ML assistance information related to the first network node that the first network node can provide.

[0187] Embodiment 24: The method of embodiment 23 further comprising sending (530) an ACK, a partial ACK, or a NACK to the second network node in response to the request.

[0188] Embodiment 25: The method of embodiment 24 further comprises sending (540) to the second network node at least some of a request for at least one of the network-associated types of the AI ​​or ML assistance information related to the first network node that the first network node can provide.

[0189] Embodiment 26: The method of embodiment 23 further comprising sending (640; 740) a NACK or a partial NACK to the second network node in response to the request.

[0190] Embodiment 27: The method of embodiment 26, further comprising sending (650; 760) to the second network node update information indicating a network-associated type of available AI or ML assistance information related to the first network node that the first network node can provide.

[0191] Embodiment 28: The method according to embodiment 27 further includes receiving (750) a request for (update) information from the second network node before sending (760) the update information to the second network node, the (update) information indicating a network-associated type of available AI or ML assistance information related to the first network node that the first network node can provide.

[0192] Embodiment 29: The method according to embodiment 21 further includes receiving (310) a second message from the second network node, the second message including information indicating a network-associated type of available AI or ML assistance information related to the second network node that the second network node can provide.

[0193] Embodiment 30: The method of embodiment 20, wherein the node is a user equipment (eg, UE).

[0194] Embodiment 31: The method according to embodiment 30 further includes: receiving (910) a request for at least one of the network-associated types of the available AI or ML assistance information related to the first network node that can be provided by the first network node from the user device; and sending (920) to the user device the at least one of the network-associated types of the available AI or ML assistance information related to the first network node that can be provided by the first network node.

[0195] Embodiment 32: The method according to embodiment 30 further includes, before sending the first message to the user device, receiving (1000) a request for the information from the user device, the information indicating a network-associated type of available AI or ML assistance information related to the first network node that the first network node can provide.

[0196] Embodiment 33: A first network node suitable for executing the method described in any one of embodiments 20 to 32.

[0197] Those skilled in the art will recognize improvements and modifications to the embodiments of the present disclosure, and all such improvements and modifications are considered to be within the scope of the concepts disclosed herein.

Claims

1. A method performed by a node, comprising: A first message is received (210; 300; 410; 510; 610; 710; 800; 900; 1010) from a first network node, the first message comprising information indicating a network-associated type of available artificial intelligence (AI) or machine learning (ML) assistance information that the first network node can provide.

2. The method of claim 1, further comprising using the received information to perform (220; 810) one or more actions.

3. The method according to claim 2, wherein: The one or more actions include sending (220A; 810A) a request to the first network node for at least one of the network-associated types of indicated available AI or ML assistance information.

4. The method according to claim 2, wherein: The one or more actions include: sending (220A; 810A) a request to the first network node for at least one of the indicated network-associated types of available AI or ML assistance information; receiving (220A; 810A) from the first network node the at least one of the network-associated types of indicated available AI or ML assistance information; and Based on the at least one of the network-associated types of the indicated available AI or ML assistance information received from the first network node, one or more AI or ML-related operations (e.g., updating or training an AI or ML model) are performed (220A; 810A).

5. The method according to claim 2, wherein: The one or more actions include sending (220B; 810B) at least some of the received information to another node.

6. The method according to any one of claims 1 to 5, wherein The network-associated type of the available AI or ML assistance information is related to the first network node or the third network node.

7. The method according to any one of claims 1 to 6, wherein The node is a second network node.

8. The method of claim 7, further comprising, before receiving the first message, sending (200; 400; 500) to the first network node a request for the information indicating a network-associated type of available AI or ML assistance information related to the first network node that the first network node can provide.

9. The method of claim 7 or 8, further comprising sending (420; 520; 630; 730) to the first network node a request for at least one of a network-associated type of the AI ​​or ML assistance information related to the first network node that the first network node can provide.

10. The method of claim 9, further comprising receiving (530) a success, partial success, or failure from the first network node in response to the request.

11. The method of claim 10, further comprising receiving (540) from the first network node at least some of a request for at least one of a network-associated type of the AI ​​or ML assistance information related to the first network node that the first network node can provide.

12. The method of claim 9, further comprising receiving (640; 740) a failure or partial failure from the first network node in response to the request.

13. The method of claim 12, further comprising receiving (650; 760) from the first network node update information indicating a network-associated type of available AI or ML assistance information related to the first network node that the first network node can provide.

14. The method of claim 13, further comprising, before receiving (760) the update information from the first network node, sending (750) a request to the first network node for (update) information indicating a network-associated type of available AI or ML assistance information related to the first network node that the first network node can provide.

15. The method of claim 7, further comprising sending (310) a second message to the first network node, the second message comprising information indicating a network-associated type of available AI or ML assistance information related to the second network node that the second network node can provide.

16. The method according to any one of claims 1 to 5, wherein The node is a user device.

17. The method of claim 16, further comprising: sending (910) a request to the first network node for at least one of the network-associated types of the available AI or ML assistance information related to the first network node that the first network node can provide; and The at least one of the network-associated types of the available AI or ML assistance information related to the first network node that the first network node can provide is received (920) from the first network node.

18. The method of claim 16, further comprising, before receiving the first message from the first network node, sending (1000) to the first network node a request for the information indicating a network-associated type of available AI or ML assistance information related to the first network node that the first network node can provide.

19. The method according to any one of claims 1 to 18, wherein The information indicating a network-associated type of the available AI or ML assistance information that the first network node can provide includes any one or more of the following: - one or more identifiers of one or more types of supported AI / ML models, - one or more identifiers of one or more supported AI / ML algorithms, - an indication of the number of hidden layers that a certain type of AI / ML model can support, - an indication of the sizes of the AI / ML models that can be supported for one or more types of supported AI / ML models, - an indication of a certain number of hidden units or nodes per hidden layer that a certain type of AI / ML model can support, - one or more AI / ML-supported use cases and / or one or more identifiers of AI / ML-related operations, processes, or functionality, - indication of hardware dedicated to AI / ML processes, - information related to the AI / ML capabilities of said first network node and / or associated identifier(s), - information related to the AI / ML model requirements of said first network node and / or associated identifier(s), - information related to the AI / ML model lifecycle management of said first network node and / or associated identifier(s), - information about measurement(s) determined or obtained by said network node and / or associated identifier(s), - information about a prediction determined or obtained by said first network node and / or associated identifier(s), - information indicating support for providing certain predictions, - information about inferred action(s) determined or obtained by said first network node and / or associated identifier(s), - an indication of support for providing feedback for actions triggered / recommended by the AI / ML model, - an indication indicating support for a certain training strategy(ies), - an indication indicating support for partial AI / ML model training at the user device side or the network side, - an indication indicating support for inferring certain information, - an indication indicating support for using certain inferred information, - An indication indicating support for periodic or aperiodic feedback assistance.

20. A node suitable for: A first message is received (210; 300; 410; 510; 610; 710; 800; 900; 1010) from a first network node, the first message comprising information indicating a network-associated type of available artificial intelligence (AI) or machine learning (ML) assistance information that the first network node can provide.

21. The node of claim 20, further adapted to perform the method of any one of claims 2 to 19.

22. A node comprising a processing circuit, the processing circuit being configured such that the node: A first message is received (210; 300; 410; 510; 610; 710; 800; 900; 1010) from a first network node, the first message comprising information indicating a network-associated type of available artificial intelligence (AI) or machine learning (ML) assistance information that the first network node can provide.

23. The node of claim 22, wherein: The processing circuit is further configured to cause the node to perform the method of any one of claims 2 to 19.

24. A method performed by a first network node, comprising: A first message is sent (210; 300; 410; 510; 610; 710; 800; 900; 1010) to a node (e.g., a second network node or a user device), the first message including information indicating a network-associated type of available artificial intelligence (AI) or machine learning (ML) assistance information related to the first network node that the first network node can provide.

25. The method of claim 24, wherein: The node is a second network node.

26. The method of claim 25, further comprising, before sending the first message, receiving (200; 400; 500) from the second network node a request for the information indicating a network associated type of available AI or ML assistance information related to the first network node that the first network node can provide.

27. The method of claim 25 or 26, further comprising receiving (420; 520; 630; 730) a request from the second network node for at least one of a network-associated type of the AI ​​or ML assistance information related to the first network node that the first network node can provide.

28. The method of claim 27, further comprising sending (530) a success, a partial success, or a failure to the second network node in response to the request.

29. The method of claim 28, further comprising sending (540) to the second network node at least some of a request for at least one of a network-associated type of the AI ​​or ML assistance information related to the first network node that the first network node can provide.

30. The method of claim 27, further comprising sending (640; 740) a failure or partial failure to the second network node in response to the request.

31. The method of claim 30, further comprising sending (650; 760) to the second network node update information indicating a network-associated type of available AI or ML assistance information related to the first network node that the first network node can provide.

32. The method of claim 31 , further comprising, before sending (760) the update information to the second network node, receiving (750) a request from the second network node for (update) information indicating a network-associated type of available AI or ML assistance information related to the first network node that the first network node can provide.

33. The method of claim 25, further comprising receiving (310) a second message from the second network node, the second message comprising information indicating a network-associated type of available AI or ML assistance information related to the second network node that the second network node can provide.

34. The method of claim 24, wherein: The node is a user device.

35. The method of claim 34, further comprising: receiving (910) a request from the user device for at least one of a network-associated type of the available AI or ML assistance information related to the first network node that the first network node can provide; as well as The at least one of the network-associated types of the available AI or ML assistance information related to the first network node that the first network node can provide is sent (920) to the user device.

36. The method of claim 34, further comprising, before sending the first message to the user device, receiving (1000) from the user device a request for the information indicating a network-associated type of available AI or ML assistance information related to the first network node that the first network node can provide.

37. A first network node, adapted to: A first message is sent (210; 300; 410; 510; 610; 710; 800; 900; 1010) to a node (e.g., a second network node or a user device), the first message including information indicating a network-associated type of available artificial intelligence (AI) or machine learning (ML) assistance information related to the first network node that the first network node can provide.

38. The first network node according to claim 37, further adapted to perform the method according to any one of claims 25 to 36.

39. A first network node comprising a processing circuit configured to cause the first network node to: A first message is sent (210; 300; 410; 510; 610; 710; 800; 900; 1010) to a node (e.g., a second network node or a user device), the first message including information indicating a network-associated type of available artificial intelligence (AI) or machine learning (ML) assistance information related to the first network node that the first network node can provide.

40. The first network node of claim 39, wherein: The processing circuit is further configured to cause the first network node to perform the method of any one of claims 25 to 36.

Images