Radio resource control model delivery

Abstract

Aspects of the present disclosure generally relate to wireless communications. In some aspects, a user equipment (UE) may communicate with one of a first network node or a second network node to update available model information in a UE context at one or more of the first network node or the second network node. The UE may receive a model transmission from one of the first network node or the second network node via radio resource control (RRC) signaling. Numerous other aspects are described.

Description

[0001] Cross-reference to related applications

[0002] This patent application claims priority to U.S. Provisional Patent Application No. 63 / 494,124, filed April 4, 2023, entitled “RADIO RESOURCE CONTROL MODEL DELIVERY”, and U.S. Non-Provisional Patent Application No. 18 / 624,691, filed April 2, 2024, entitled “RADIO RESOURCE CONTROL MODEL DELIVERY”, which are hereby expressly incorporated by reference. Technical Field

[0003] Various aspects of this disclosure generally relate to wireless communications and technologies and apparatuses for delivering artificial intelligence and / or machine learning models via radio resource control signaling. Background Technology

[0004] Wireless communication systems are widely deployed to provide a variety of telecommunications services, such as telephone, video, data, messaging, and broadcasting. Typical wireless communication systems employ multiple access technologies that enable communication with multiple users by sharing available system resources (e.g., bandwidth, transmit power, etc.). Examples of such multiple access technologies include Code Division Multiple Access (CDMA) systems, Time Division Multiple Access (TDMA) systems, Frequency Division Multiple Access (FDMA) systems, Orthogonal Frequency Division Multiple Access (OFDMA) systems, Single Carrier Frequency Division Multiple Access (SC-FDMA) systems, Time Division Synchronous Code Division Multiple Access (TD-SCDMA) systems, and Long Term Evolution (LTE). LTE / LTE-Advanced is a collection of enhancements to the Universal Mobile Telecommunications System (UMTS) mobile standard released by the 3rd Generation Partnership Project (3GPP).

[0005] A wireless network may include one or more network nodes that support communication between wireless communication devices (e.g., user equipment (UE) or multiple UEs). A UE may communicate with network nodes via downlink and uplink communication. A "downlink" (or "DL") refers to the communication link from the network node to the UE, and an "uplink" (or "UL") refers to the communication link from the UE to the network node. Some wireless networks may support device-to-device communication, such as via local links (e.g., sidelinks (SL), wireless local area network (WLAN) links, and / or wireless personal area network (WPAN) links).

[0006] The aforementioned access technologies have been adopted in various telecommunications standards to provide a common protocol enabling different UEs to communicate at the city, country, region, and / or global levels. New Radio (NR) (which may be referred to as 5G) is a collection of enhancements to the LTE mobile standard released by 3GPP. NR is designed to better integrate with other open standards by improving spectrum efficiency, reducing costs, improving service, utilizing new spectrum, and using Orthogonal Frequency Division Multiplexing (OFDM) with Cyclic Prefix (CP) on the downlink (CP-OFDM), and using CP-OFDM and / or Single Carrier Frequency Division Multiplexing (SC-FDM) (also known as Discrete Fourier Transform Extended OFDM (DFT-s-OFDM)) on the uplink, as well as supporting beamforming, multiple-input multiple-output (MIMO) antenna technologies and carrier aggregation. Further enhancements to LTE, NR, and other radio access technologies remain useful as the demand for mobile broadband access continues to increase. Summary of the Invention

[0007] Some aspects described herein relate to a method of wireless communication performed by a user equipment (UE). This method may include communicating with one of a first or second network node to update available model information in the UE context at one or more of the first or second network nodes. This method may include receiving a model transfer from one of the first or second network nodes via Radio Resource Control (RRC) signaling.

[0008] Some aspects described herein relate to a method for wireless communication performed by a network node. This method may include: communicating with a UE. The method may include: outputting a model transmission to the UE via RRC signaling; receiving a model release request from the UE; and outputting a model release instruction to the UE to configure the UE to release one or more models.

[0009] Some aspects described herein relate to a UE for wireless communication. The UE may include memory and one or more processors coupled to the memory. The one or more processors may be configured to communicate with one of a first or second network node to update available model information in the UE context at one or more of the first or second network node. The one or more processors may be configured to receive model transmissions from one of the first or second network node via RRC signaling.

[0010] Some aspects described herein relate to a network node for wireless communication. The network node may include memory and one or more processors coupled to the memory. One or more processors may be configured to communicate with a UE. One or more processors may be configured to output artificial intelligence or machine learning (AI / ML) model transmissions to the UE via RRC signaling; receive AI / ML model release requests from the UE; and output AI / ML model release instructions to the UE to configure the UE to release one or more AI / ML models.

[0011] Some aspects described herein relate to a non-transitory computer-readable medium storing a set of instructions for wireless communication by a UE. When executed by one or more processors of the UE, the set of instructions enables the UE to communicate with one of a first or second network node to update available model information in the UE context at one or more of the first or second network nodes. When executed by one or more processors of the UE, the set of instructions also enables the UE to receive model transmissions from one of the first or second network nodes via RRC signaling.

[0012] Some aspects described herein relate to a non-transitory computer-readable medium storing a set of instructions for wireless communication by a network node. When executed by one or more processors of the network node, this set of instructions enables the network node to communicate with a UE. When executed by one or more processors of the network node, this set of instructions enables the network node to output AI / ML model transmission to the UE via RRC signaling; receive AI / ML model release requests from the UE; and output AI / ML model release instructions to the UE to configure the UE to release one or more AI / ML models.

[0013] Some aspects described herein relate to an apparatus for wireless communication. The apparatus may include components for communicating with one of a first or second network node to update available model information in the UE context at one or more of the first or second network nodes. The apparatus may also include components for receiving model transmissions from one of the first or second network nodes via RRC signaling.

[0014] Some aspects described herein relate to an apparatus for wireless communication. The apparatus may include components for communicating with a UE. The apparatus may include components for outputting AI / ML model transmission to the UE via RRC signaling; components for receiving AI / ML model release requests from the UE; and components for outputting AI / ML model release instructions to the UE to configure the UE to release one or more AI / ML models. Attached Figure Description

[0015] To gain a more detailed understanding of the features described above, reference can be made to several aspects as briefly outlined above, some of which are illustrated in the accompanying drawings. However, it should be noted that the drawings illustrate only certain typical aspects of this disclosure and should therefore not be considered as limiting its scope, as the description may allow for other equivalent aspects. The same reference numerals in different drawings may identify the same or similar elements.

[0016] Figure 1 This is a diagram illustrating an example of a wireless network according to this disclosure.

[0017] Figure 2 This is a diagram illustrating an example of communication between a network node and a user equipment (UE) in a wireless network according to this disclosure.

[0018] Figure 3 This is a diagram illustrating an example disaggregated base station architecture according to this disclosure.

[0019] Figure 4 An example of a wireless network (e.g., a wireless network) in which the UE can support additional communication modes is shown according to this disclosure.

[0020] Figure 5 This is a diagram illustrating an example architecture of a functional framework for achieving intelligence in a radio access network through data collection, according to this disclosure.

[0021] Figure 6 This is a diagram illustrating an example of the delivery of an artificial intelligence / machine learning (AI / ML) model via radio resource control (RRC) signaling, according to this disclosure.

[0022] Figures 7-19 This is a diagram illustrating various examples associated with AI / ML model delivery via RRC signaling according to this disclosure.

[0023] Figure 20 This is a diagram illustrating an example process performed by a UE according to this disclosure.

[0024] Figure 21 This is a diagram illustrating an example process performed, for example, by a network node according to this disclosure.

[0025] Figure 22 This is a diagram of an example device for wireless communication according to the present disclosure.

[0026] Figure 23 This is a diagram of an example device for wireless communication according to the present disclosure. Detailed Implementation

[0027] The terms generally include, as described herein with reference to the accompanying drawings and description, and as shown in the drawings and description, methods, apparatus, systems, computer program products, non-transitory computer-readable media, user equipment, base stations, network entities, network nodes, wireless communication devices, and / or processing systems.

[0028] The features and technical advantages of the examples according to this disclosure have been outlined quite extensively above in order to provide a better understanding of the detailed description that follows. Additional features and advantages will be described below. The disclosed concepts and specific examples can be readily used as the basis for modifying or designing other structures for performing the same purpose of this disclosure. Such equivalent constructions do not depart from the scope of the appended claims. The characteristics of the concepts disclosed herein, their organization and operation, and the associated advantages will be better understood when considered in conjunction with the accompanying drawings, based on the following description. Each drawing is provided for illustrative and descriptive purposes and not as a definition of limitation of the claims.

[0029] While aspects are described herein by way of example, those skilled in the art will understand that these aspects can be implemented in many different arrangements and scenarios. The techniques described herein can be implemented using different platform types, devices, systems, shapes, sizes, and / or package arrangements. For example, some aspects can be implemented via integrated chip embodiments or other devices based on non-modular components (e.g., end-user equipment, vehicles, communication equipment, computing devices, industrial equipment, retail / purchasing devices, medical devices, and / or artificial intelligence devices). Aspects can be implemented in chip-level components, modular components, non-modular components, non-chip-level components, device-level components, and / or system-level components. Devices combining the described aspects and features may include additional components and features for implementations and practices of the claimed and described aspects. For example, the transmission and reception of wireless signals may include one or more components for analog and digital purposes (e.g., hardware components including antennas, radio frequency (RF) chains, power amplifiers, modulators, buffers, processors, interleavers, adders, and / or summers). The aspects described herein are intended to be practiced in a variety of devices, components, systems, distributed arrangements, and / or end-user equipment of various sizes, shapes, and configurations.

[0030] User equipment (UE) can be equipped with various models or model architectures incorporating artificial intelligence (AI), such as programs that include machine learning (ML) or artificial neural network (ANN) models. Example ML models may include mathematical representations or definitions of computational capabilities for making inferences based on patterns or relationships identified in the input data. As used herein, the term "inference" can include one or more of decision, prediction, determination, or value, which can represent the output of the ML model. Computational capabilities can be defined according to certain parameters of the ML model, such as weights and biases. Weights can indicate the relationship between certain outputs of the ML model and certain input data, and biases are offsets that can indicate the starting point of the ML model's output. An example ML model operating on the input data may start at an initial output based on a bias and then update its output based on a combination of input data and weights. ML models can be deployed in one or more devices (e.g., network entities and UEs) and can be configured to enhance various aspects of a wireless communication system. For example, ML models can be trained to identify patterns or relationships in data corresponding to a network, device, air interface, etc. ML models can support operational decisions involving one or more aspects associated with wireless communication devices, networks, or services. For example, ML models can be used to support or improve aspects such as signal encoding / decoding, network routing, energy saving, transceiver circuit control, frequency synchronization, timing synchronization, channel state estimation, channel equalization, channel state feedback, modulation, demodulation, device location, beamforming, load balancing, operation and management functions, and security. However, there may be times when network nodes (such as gNBs) are unaware of which AI / ML models are available for the UE.

[0031] Some of the technologies and apparatus described herein enable a UE to communicate with one of a first or second network node to update available model information in the UE context at one or more of the first or second network nodes, and to receive model transmissions from one of the first or second network nodes via Radio Resource Control (RRC) signaling. As a result, the UE can communicate with the first or second network node which AI / ML models are available to the UE. If the UE lacks an AI / ML model for a specific feature or function, the network node can transmit an appropriate AI / ML model to the UE.

[0032] The technologies and apparatus described in this paper enable network nodes to communicate with the UE and transmit output models to the UE via RRC signaling. As a result, the network node can know which AI / ML models are available to the UE and, when appropriate, transmit any required AI / ML models to the UE.

[0033] Various aspects of this disclosure are described more fully below with reference to the accompanying drawings. However, this disclosure may be embodied in many different forms and should not be construed as limited to any particular structure or function given throughout this disclosure. These aspects are provided so that this disclosure will be thorough and complete and will fully convey the scope of this disclosure to those skilled in the art. Those skilled in the art will understand that the scope of this disclosure is intended to cover any aspect of this disclosure disclosed herein, whether implemented independently of or in combination with any other aspect of this disclosure. For example, any number of the aspects set forth herein may be used to implement an apparatus or practice. Furthermore, the scope of this disclosure is intended to cover such apparatus or methods using structures, functions, or practices of structures and functions other than or different from the aspects of this disclosure set forth herein. It should be understood that any aspect of this disclosure disclosed herein may be embodied by one or more elements of the claims.

[0034] Several aspects of a telecommunications system will now be presented with reference to various devices and techniques. These devices and techniques will be described in detail below and illustrated in the accompanying drawings by various boxes, modules, components, circuits, steps, processes, algorithms, etc. (collectively referred to as “elements”). These elements can be implemented using hardware, software, or a combination thereof. Whether these elements are implemented as hardware or software depends on the specific application and the design constraints imposed on the entire system.

[0035] While the terms commonly associated with 5G or New Radio (NR) Radio Access Technology (RAT) may be used to describe the aspects herein, the aspects of this disclosure may be applied to other RATs, such as 3G RAT, 4G RAT and / or RATs after 5G (e.g., 6G).

[0036] Figure 1This is a diagram illustrating an example of a wireless network 100 according to this disclosure. Wireless network 100 may be or may include elements of a 5G (e.g., NR) network and / or a 4G (e.g., Long Term Evolution (LTE)) network. Wireless network 100 may include one or more network nodes 110 (shown as network nodes 110a, 110b, 110c, and 110d), UE 120 or multiple UEs 120 (shown as UE 120a, UE 120b, UE 120c, UE 120d, and UE 120e), and / or other entities. Network node 110 is a network node that communicates with UE 120. As shown, network node 110 may include one or more network nodes. For example, network node 110 may be an aggregated network node, meaning that the aggregated network node is configured to utilize a radio protocol stack physically or logically integrated within a single radio access network (RAN) node (e.g., within a single device or unit). As another example, network node 110 can be a decomposed network node (sometimes called a decomposed base station), which means that network node 110 is configured to utilize a protocol stack that is physically or logically distributed among two or more nodes, such as one or more central units (CUs), one or more distributed units (DUs), or one or more radio units (RUs).

[0037] In some examples, network node 110 is or includes network nodes such as RU that communicate with UE 120 via a radio access link. In some examples, network node 110 is or includes network nodes such as DU that communicate with other network nodes 110 via a fronthaul or midhaul link. In some examples, network node 110 is or includes network nodes such as CU that communicate with other network nodes 110 via a midhaul link or with the core network via a backhaul link. In some examples, network node 110 (such as aggregated network node 110 or decomposed network node 110) may include multiple network nodes, such as one or more RUs, one or more CUs, and / or one or more DUs. Network node 110 may include, for example, NR base stations, LTE base stations, Node Bs, eNBs (e.g., in 4G), gNBs (e.g., in 5G), access points, Transmitter Receiver Points (TRPs), DUs, RUs, CUs, network mobility elements, core network nodes, network elements, network equipment, RAN nodes, or combinations thereof. In some examples, network nodes 110 can interconnect with each other or with one or more other network nodes 110 in wireless network 100 using any suitable transport network via various types of fronthaul, midhaul and / or backhaul interfaces (such as direct physical connections, air interfaces or virtual networks).

[0038] In some examples, network node 110 can provide communication coverage for a specific geographic area. In the 3rd Generation Partnership Project (3GPP), depending on the context of terminology use, the term "cell" can refer to the coverage area of ​​network node 110 and / or the network node subsystem serving that coverage area. Network node 110 can provide communication coverage for macrocells, picocells, femtocells, and / or other types of cells. A macrocell can cover a relatively large geographic area (e.g., with a radius of several kilometers) and can allow unrestricted access by UE 120 with a service subscription. A picocell can cover a relatively small geographic area and can allow unrestricted access by UE 120 with a service subscription. A femtocell can cover a relatively small geographic area (e.g., a home) and can allow restricted access by UE 120 associated with a femtocell (e.g., UE 120 in a Closed Subscriber Group (CSG)). Network node 110 of a macrocell can be referred to as a macro network node. Network node 110 of a picocell can be referred to as a pico network node. The network node 110 in the femtocell can be referred to as a femtocell network node or a home network node. Figure 1 In the example shown, network node 110a can be a macro network node of macro cell 102a, network node 110b can be a pico network node of pico cell 102b, and network node 110c can be a femto network node of femto cell 102c. A network node can support one or more (e.g., three) cells. In some examples, the cells may not necessarily be stationary, and the geographical area of ​​the cell can move depending on the location of a mobile network node 110 (e.g., a mobile network node).

[0039] In some aspects, the term "base station" or "network node" may refer to an aggregated base station, a decomposed base station, an integrated access and backhaul (IAB) node, a relay node, or one or more components thereof. For example, in some aspects, "base station" or "network node" may refer to a CU, DU, RU, a near real-time (near RT) RAN intelligent controller (RIC), or a non-real-time (non-RT) RIC, or a combination thereof. In some aspects, the term "base station" or "network node" may refer to a device configured to perform one or more functions (such as the functions described herein in conjunction with network node 110). In some aspects, the term "base station" or "network node" may refer to multiple devices configured to perform one or more functions. For example, in some distributed systems, each of multiple different devices (which may be located in the same geographical location or different geographical locations) may be configured to perform at least a portion of a function, or replicate at least a portion of the performance of a function, and the term "base station" or "network node" may refer to any one or more of those different devices. In some aspects, the term "base station" or "network node" may refer to one or more virtual base stations or one or more virtual base station functions. For example, in some aspects, two or more base station functions can be instantiated on a single device. In some aspects, the term "base station" or "network node" may refer to one function of the base station functions rather than another. In this way, a single device can include more than one base station.

[0040] Wireless network 100 may include one or more relay stations. A relay station is a network node that can receive data transmissions from upstream nodes (e.g., network node 110 or UE 120) and send data transmissions to downstream nodes (e.g., UE 120 or network node 110). A relay station may be a UE 120 capable of relaying transmissions from other UEs 120. Figure 1 In the example shown, network node 110d (e.g., a relay network node) can communicate with network node 110a (e.g., a macro network node) and UE 120d to facilitate communication between network node 110a and UE 120d. The network node 110 for relay communication can be referred to as a relay station, relay base station, relay network node, relay node, repeater, etc.

[0041] The wireless network 100 can be a heterogeneous network, comprising different types of network nodes 110, such as macro network nodes, pico network nodes, femto network nodes, relay network nodes, etc. These different types of network nodes 110 can have different transmit power levels, different coverage areas, and / or different effects on interference in the wireless network 100. For example, macro network nodes can have high transmit power levels (e.g., 5 to 40 watts), while pico network nodes, femto network nodes, and relay network nodes can have low transmit power levels (e.g., 0.1 to 2 watts).

[0042] Network controller 130 may be coupled to or communicate with a set of network nodes 110, and may provide coordination and control for these network nodes 110. Network controller 130 may communicate with network nodes 110 via a backhaul or midhaul communication link. Network nodes 110 may communicate with each other directly or indirectly via wireless or wired backhaul communication links. In some aspects, network controller 130 may be a CU or core network device, or may include a CU or core network device.

[0043] UE 120 may be distributed throughout the wireless network 100, and each UE 120 may be stationary or mobile. UE 120 may include, for example, access terminals, terminals, mobile stations, and / or subscriber units. UE 120 may be a cellular phone (e.g., a smartphone), a personal digital assistant (PDA), a wireless modem, a wireless communication device, a handheld device, a laptop computer, a cordless phone, a wireless local loop (WLL) station, a tablet device, a camera, a gaming device, a netbook, a smartbook, an ultrabook, a medical device, a biometric device, a wearable device (e.g., a smartwatch, smart clothing, smart glasses, a smart wristband, smart jewelry (e.g., a smart ring or smart bracelet)), an entertainment device (e.g., a music device, a video device, and / or a satellite radio). Vehicle components or sensors, smart meters / sensors, industrial manufacturing equipment, GPS devices, UE functions of network nodes, and / or any other suitable device configured to communicate via wireless or wired media.

[0044] Some UEs 120 can be considered Machine-Type Communication (MTC) or Evolved or Enhanced Machine-Type Communication (eMTC) UEs. MTC UEs and / or eMTC UEs may include, for example, robots, drones, remote devices, sensors, meters, monitors, and / or location tags that can communicate with network nodes, other devices (e.g., remote devices), or certain other entities. Some UEs 120 can be considered Internet of Things (IoT) devices, and / or may be implemented as NB-IoT (Narrowband IoT) devices. Some UEs 120 can be considered Customer Premises Equipment. UEs 120 may be enclosed within a housing containing components of the UE 120, such as processor components and / or memory components. In some examples, the processor components and memory components may be coupled together. For example, the processor components (e.g., one or more processors) and memory components (e.g., memory) may be operatively coupled, communicatively coupled, electronically coupled, and / or electrically coupled.

[0045] Typically, any number of wireless networks 100 can be deployed in a given geographical area. Each wireless network 100 can support a specific RAT and can operate on one or more frequencies. A RAT can be referred to as a radio technology, air interface, etc. A frequency can be referred to as a carrier, frequency channel, etc. Each frequency can support a single RAT in a given geographical area to avoid interference between wireless networks using different RATs. In some cases, NR or 5G RAT networks can be deployed.

[0046] In some examples, two or more UEs 120 (e.g., shown as UE 120a and UE 120e) may communicate directly using one or more sidelink channels (e.g., without using network node 110 as an intermediary for communication with each other). For example, UE 120 may communicate using peer-to-peer (P2P) communication, device-to-device (D2D) communication, vehicle-to-everything (V2X) protocols (e.g., which may include vehicle-to-vehicle (V2V) protocols, vehicle-to-infrastructure (V2I) protocols, or vehicle-to-pedestrian (V2P) protocols), and / or mesh networks. In such examples, UE 120 may perform scheduling operations, resource selection operations, and / or other operations described elsewhere herein as being performed by network node 110.

[0047] Devices in Wireless Network 100 can communicate using the electromagnetic spectrum, which can be subdivided into various categories, bands, channels, etc., by frequency or wavelength. For example, devices in Wireless Network 100 can communicate using one or more operating bands. In 5G NR, two initial operating bands have been designated as frequency ranges FR1 (410 MHz - 7.125 GHz) and FR2 (24.25 GHz - 52.6 GHz). It should be understood that although a portion of FR1 is greater than 6 GHz, FR1 is often referred to (interchangeably) as the "sub-6 GHz" band in various documents and articles. Similar naming issues sometimes arise with FR2; although different from the extremely high frequency (EHF) band (30 GHz - 300 GHz) designated as the "millimeter wave" band by the International Telecommunication Union (ITU), FR2 is often (interchangeably) referred to as the "millimeter wave" band in documents and articles.

[0048] The frequencies between FR1 and FR2 are generally referred to as intermediate frequency (IF) bands. Recent 5G NR studies have designated the operating bands of these IF bands as the frequency range designation FR3 (7.125 GHz - 24.25 GHz). Bands falling within FR3 can inherit FR1 and / or FR2 characteristics, and thus can effectively extend the features of FR1 and / or FR2 to IF band frequencies. Furthermore, higher frequency bands are currently being explored to extend 5G NR operation beyond 52.6 GHz. For example, three higher operating frequency bands have been designated as the frequency range designations FR4a or FR4-1 (52.6 GHz - 71 GHz), FR4 (52.6 GHz - 114.25 GHz), and FR5 (114.25 GHz - 300 GHz). Each of these higher frequency bands falls within the EHF band.

[0049] Considering the examples above, unless otherwise specified, it should be understood that the terms "sub-6 GHz," as used herein, can broadly refer to frequencies below 6 GHz, within FR1, or that may include intermediate frequency band frequencies. Furthermore, unless otherwise specified, it should be understood that the terms "millimeter wave," as used herein, can broadly refer to frequencies that may include intermediate frequency band frequencies, within FR2, FR4, FR4-a, or FR4-1 and / or FR5, or that may be within the EHF band. It is contemplated that frequencies included in these operating bands (e.g., FR1, FR2, FR3, FR4, FR4-a, FR4-1, and / or FR5) can be modified, and the techniques described herein are applicable to those modified frequency ranges.

[0050] In some aspects, UE 120 may include a communication manager 140. As described in more detail elsewhere herein, the communication manager 140 may communicate with one of the first or second network nodes to update available model information in the UE context at one or more of the first or second network nodes; and to receive model transmissions from one of the first or second network nodes via RRC signaling. Additionally or alternatively, the communication manager 140 may perform one or more other operations described herein.

[0051] In some aspects, network node 110 may include communication manager 150. As described in more detail elsewhere herein, communication manager 150 may communicate with the UE and transmit output models to the UE via RRC signaling. Additionally or alternatively, communication manager 150 may perform one or more other operations described herein.

[0052] As mentioned above, Figure 1 This is provided as an example. Other examples may be provided in conjunction with [the relevant information]. Figure 1 The descriptions are different.

[0053] Figure 2 This is a diagram illustrating example 200 of communication between network node 110 and UE 120 in a wireless network 100 according to this disclosure. Network node 110 may be equipped with a set of antennas 234a to 234t, such as T antennas (T≥1). UE 120 may be equipped with a set of antennas 252a to 252r, such as R antennas (R≥1). Network node 110 of example 200 includes one or more radio frequency components, such as antennas 234 and modem 232. In some examples, network node 110 may include an interface, communication components, or other components facilitating communication with UE 120 or other network nodes. Some network nodes 110 may not include radio frequency components facilitating direct communication with UE 120, such as one or more CUs or one or more DUs.

[0054] At network node 110, transmitting processor 220 can receive data from data source 212 intended for use with UE 120 (or a set of UEs 120). Transmitting processor 220 can select one or more modulation and coding schemes (MCS) for UE 120, at least in part, based on one or more channel quality indicators (CQIs) received from UE 120. Network node 110 can process (e.g., encode and modulate) the data for UE 120, at least in part, based on the MCS selected for UE 120, and can provide data symbols for UE 120. Transmitting processor 220 can process system information (e.g., for semi-static resource partitioning information (SRPI)) and control information (e.g., CQI requests, authorizations, and / or upper-layer signaling), and provide overhead symbols and control symbols. Transmit processor 220 can generate reference symbols for reference signals (e.g., cell-specific reference signals (CRS) or demodulation reference signals (DMRS)) and synchronization signals (e.g., primary synchronization signal (PSS) or secondary synchronization signal (SSS)). Transmit (TX) multiple-input multiple-output (MIMO) processor 230 can perform spatial processing (e.g., precoding) on ​​data symbols, control symbols, overhead symbols, and / or reference symbols where applicable, and can provide a set of output symbol streams (e.g., T output symbol streams) to a corresponding set of modems 232 (e.g., T modems) (shown as modems 232a to 232t). For example, each output symbol stream can be provided to a modulator component (shown as MOD) of modem 232. Each modem 232 can use a corresponding modulator component to process the corresponding output symbol stream (e.g., for OFDM) to obtain an output sample stream. Each modem 232 can also use a corresponding modulator component to process (e.g., convert to analog, amplify, filter, and / or up-convert) the output sample stream to obtain a downlink signal. Modems 232a to 232t can transmit a set of downlink signals (e.g., T downlink signals) via a set of corresponding antennas 234 (e.g., T antennas) (shown as antennas 234a to 234t).

[0055] At UE 120, an antenna set 252 (shown as antennas 252a to 252r) can receive downlink signals from network node 110 and / or other network nodes 110, and can provide a set of received signals (e.g., R received signals) to a modem set 254 (e.g., R modems) (shown as modems 254a to 254r). For example, each received signal can be provided to a demodulator component (shown as DEMOD) of modem 254. Each modem 254 can use a corresponding demodulator component to condition (e.g., filter, amplify, downconvert, and / or digitize) the received signal to obtain an input sample. Each modem 254 can use the demodulator component to further process the input sample (e.g., for OFDM) to obtain received symbols. A MIMO detector 256 can obtain the received symbols from modem 254, perform MIMO detection on the received symbols where applicable, and provide the detected symbols. The receiver processor 258 can process (e.g., demodulate and decode) detected symbols, provide data for decoding of the UE 120 to the data sink 260, and provide control information and system information for decoding to the controller / processor 280. The term "controller / processor" can refer to one or more controllers, one or more processors, or a combination thereof. The channel processor can determine parameters such as the Reference Signal Received Power (RSRP), Received Signal Strength Indicator (RSSI), Reference Signal Received Quality (RSRQ), and / or CQI. In some examples, one or more components of the UE 120 may be included in the housing 284.

[0056] Network controller 130 may include communication unit 294, controller / processor 290, and memory 292. Network controller 130 may include one or more devices, such as those in the core network. Network controller 130 may communicate with network node 110 via communication unit 294.

[0057] One or more antennas (e.g., antennas 234a to 234t and / or antennas 252a to 252r) may include one or more antenna panels, one or more antenna groups, an assembly of one or more antenna elements, and / or one or more antenna arrays, etc., or may be included within one or more antenna panels, one or more antenna groups, an assembly of one or more antenna elements, and / or one or more antenna arrays, etc. Antenna panels, antenna groups, an assembly of antenna elements, and / or antenna arrays may include one or more antenna elements (within a single housing or multiple housings), an assembly of coplanar antenna elements, an assembly of non-coplanar antenna elements, and / or coupled to one or more transmitting and / or receiving components (such as...) Figure 2 One or more antenna elements (one or more components).

[0058] On the uplink, at UE 120, the transmit processor 264 can receive and process data from data source 262 and control information from controller / processor 280 (e.g., for reporting including RSRP, RSSI, RSRQ, and / or CQI). The transmit processor 264 can generate reference symbols for one or more reference signals. The symbols from the transmit processor 264 can be pre-encoded by the TX MIMO processor 266 (if applicable), further processed by the modem 254 (e.g., for DFT-s-OFDM or CP-OFDM), and transmitted to network node 110. In some examples, the modem 254 of UE 120 may include a modulator and demodulator. In some examples, UE 120 includes a transceiver. The transceiver may include any combination of antenna 252, modem 254, MIMO detector 256, receive processor 258, transmit processor 264, and / or TX MIMO processor 266. The transceiver may be used by a processor (e.g., controller / processor 280) and memory 282 to execute this document (e.g., reference). Figures 4-23 ( ) any aspect of the method described in the method.

[0059] At network node 110, uplink signals from UE 120 and / or other UEs can be received by antenna 234, processed by modem 232 (e.g., a demodulator component of modem 232, shown as DEMOD), detected by MIMO detector 236 (if applicable), and further processed by receive processor 238 to obtain decoded data and control information transmitted by UE 120. Receive processor 238 can provide the decoded data to data sink 239 and the decoded control information to controller / processor 240. Network node 110 may include communication unit 244 and can communicate with network controller 130 via communication unit 244. Network node 110 may include scheduler 246 to schedule one or more UEs 120 for downlink and / or uplink communication. In some examples, modem 232 of network node 110 may include modulator and demodulator. In some examples, network node 110 includes transceiver. The transceiver may include any combination of antenna 234, modem 232, MIMO detector 236, receive processor 238, transmit processor 220, and / or TX MIMO processor 230. The transceiver may be used by a processor (e.g., controller / processor 240) and memory 242 to perform aspects of any of the methods described herein (e.g., references). Figures 4-23 ).

[0060] The controller / processor 240 of network node 110, the controller / processor 280 of UE 120 and / or Figure 2 Any other component may perform one or more techniques associated with the delivery of the AI / ML model via RRC, as described in more detail elsewhere in this document. For example, the controller / processor 240 of network node 110, the controller / processor 280 of UE 120, and / or Figure 2 Any other component can execute or direct, for example Figure 20 The process 2000, Figure 21 The operation of process 2100 and / or other processes as described herein. Memory 242 and memory 282 may store data and program code for network node 110 and UE 120, respectively. In some examples, memory 242 and / or memory 282 may include a non-transitory computer-readable medium storing one or more instructions (e.g., code and / or program code) for wireless communication. For example, one or more instructions, when executed by one or more processors of network node 110 and / or UE 120 (e.g., directly or after compilation, transformation, and / or interpretation), may cause one or more processors, UE 120, and / or network node 110 to perform or direct, for example... Figure 20 The process 2000, Figure 21 The operation of process 2100 and / or other processes as described herein. In some examples, execution instructions may include run instructions, transformation instructions, compilation instructions, and / or interpretation instructions, etc.

[0061] In some aspects, UE 120 includes components for communicating with one of the first or second network nodes to update available model information in the UE context at one or more of the first or second network nodes; and / or for receiving model transmissions from one of the first or second network nodes via RRC signaling. Components for UE 120 to perform the operations described herein may include, for example, one or more of the following: communication manager 140, antenna 252, modem 254, MIMO detector 256, receive processor 258, transmit processor 264, TXMIMO processor 266, controller / processor 280, or memory 282.

[0062] In some aspects, network node 110 includes components for communicating with UE 120; components for outputting model transmission to UE 120 via RRC signaling; components for receiving model release requests from UE; and components for outputting model release instructions to UE to configure UE to release one or more models. Components for network node 110 to perform the operations described herein may include one or more of, for example, a communication manager 150, a transmit processor 220, a TX MIMO processor 230, a modem 232, an antenna 234, a MIMO detector 236, a receive processor 238, a controller / processor 240, a memory 242, or a scheduler 246.

[0063] Although Figure 2 The boxes in the diagram are shown as different components, but the functions described above with respect to the boxes can be implemented in a single hardware, software, or combined component, or in various combinations of components. For example, the functions described with respect to the transmit processor 264, the receive processor 258, and / or the TX MIMO processor 266 can be performed by the controller / processor 280 or under the control of the controller / processor 280.

[0064] As mentioned above, Figure 2 This is provided as an example. Other examples may be provided in conjunction with [the relevant information]. Figure 2 The descriptions are different.

[0065] The deployment of communication systems (such as 5G NR systems) can be arranged in a variety of ways using various components or parts. In a 5G NR system or network, network nodes, network entities, network mobility elements, RAN nodes, core network nodes, network elements, base stations, or network equipment can be implemented in aggregated or decomposed architectures. For example, a base station (such as a Node B (NB), evolved NB (eNB), NR base station, 5G NB, access point (AP), TRP, or cell, etc.) or one or more units (or components) performing base station functions can be implemented as an aggregated base station (also known as a standalone base station or monolithic base station) or a decomposed base station. A "network entity" or "network node" can refer to a decomposed base station, or one or more units of a decomposed base station (such as one or more CUs, one or more DUs, one or more RUs, or combinations thereof).

[0066] Aggregated base stations (e.g., aggregated network nodes) can be configured to utilize a radio protocol stack that is physically or logically integrated within a single RAN node (e.g., within a single device or unit). Decomposed base stations (e.g., decomposed network nodes) can be configured to utilize a protocol stack that is physically or logically distributed across two or more units (such as one or more CUs, one or more DUs, or one or more RUs). In some examples, a CU can be implemented within a network node, and one or more DUs can be co-located with the CU, or alternatively, can be geographically or virtually distributed across one or more other network nodes. A DU can be implemented to communicate with one or more RUs. Each of the CU, DU, and RU can also be implemented as a virtual unit, such as a Virtual Central Unit (VCU), Virtual Distributed Unit (VDU), or Virtual Radio Unit (VRU), etc.

[0067] Base station operations or network designs can consider the aggregation characteristics of base station functions. For example, decomposed base stations can be utilized in IAB networks, Open Radio Access Networks (O-RAN (such as network configurations sponsored by the O-RAN Alliance)), or Virtualized Radio Access Networks (vRAN, also known as Cloud Radio Access Networks (C-RAN)) to facilitate the expansion of communication systems by dividing base station functions into one or more units that can be deployed independently. Decomposed base stations can include functions implemented in two or more units across various physical locations, as well as functions virtually implemented for at least one unit, which allows for flexibility in network design. The various units of a decomposed base station can be configured for wired or wireless communication with at least one other unit of the decomposed base station.

[0068] Figure 3 This is a diagram illustrating an example disaggregated base station architecture 300 according to this disclosure. The disaggregated base station architecture 300 may include a CU 310, which may communicate directly with the core network 320 via a backhaul link, or indirectly with the core network 320 via one or more disaggregated control units (such as near-RT RIC 325 via an E2 link, or a non-RT RIC 315 associated with a Service Management and Orchestration (SMO) framework 305, or both). The CU 310 may communicate with one or more DU 330s via a corresponding midhaul link (such as via an F1 interface). Each of the DU 330s may communicate with one or more RU 340s via a corresponding fronthaul link. Each of the RU 340s may communicate with one or more UE 120s via a corresponding radio frequency (RF) access link. In some embodiments, a UE 120 may be served simultaneously by multiple RU 340s.

[0069] Each of the units, including CU 310, DU 330, RU 340, and near-RT RIC 325, non-RT RIC 315, and SMO frame 305, may include one or more interfaces, or be coupled to one or more interfaces configured to receive or transmit signals, data, or information (collectively, signals) via wired or wireless transmission media. Each unit, or its associated processor or controller providing instructions to one or more communication interfaces of the respective unit, may be configured to communicate with one or more other units via a transmission medium. In some examples, each unit may include a wired interface and a wireless interface, the wired interface being configured to receive or transmit signals to one or more other units via a wired transmission medium, and the wireless interface may include a receiver, transmitter, or transceiver (such as an RF transceiver) being configured to receive or transmit signals to one or more other units via a wireless transmission medium, or both.

[0070] In some aspects, CU 310 can host one or more higher-level control functions. Such control functions may include RRC functions, Packet Data Convergence Protocol (PDCP) functions, or Service Data Adaptation Protocol (SDAP) functions, etc. Each control function can be implemented using an interface configured to communicate signals with other control functions hosted by CU 310. CU 310 can be configured to handle user plane functions (e.g., Central Unit-User Plane (CU-UP) functions), control plane functions (e.g., Central Unit-Control Plane (CU-CP) functions), or combinations thereof. In some implementations, CU 310 can be logically divided into one or more CU-UP units and one or more CU-CP units. CU-UP units can communicate bidirectionally with CU-CP units via an interface (such as an E1 interface when implemented in an O-RAN configuration). CU 310 can be implemented to communicate with DU 330 as needed for network control and signaling.

[0071] Each DU 330 may correspond to a logical unit including one or more base station functions for controlling the operation of one or more RU 340s. In some aspects, the DU 330 may, at least in part, host one or more of the Radio Link Control (RLC) layer, Medium Access Control (MAC) layer, and one or more high physical (PHY) layers, depending on a functional partitioning (such as that defined by 3GPP). In some aspects, the one or more high PHY layers may be implemented by one or more modules for forward error correction (FEC) encoding and decoding, scrambling, and modulation and demodulation. In some aspects, the DU 330 may further host one or more low PHY layers (such as those implemented by one or more modules for Fast Fourier Transform (FFT), Inverse FFT (iFFT), Digital Beamforming, or Physical Random Access Channel (PRACH) extraction and filtering). Each layer (which may also be referred to as a module) may be implemented using an interface configured to communicate signals with other layers (and modules) hosted by the DU 330 or with control functions hosted by the CU 310.

[0072] Each RU 340 can implement low-level functions. In some deployments, the RU 340 controlled by the DU 330 can correspond to a logical node for managed RF processing functions or low-PHY layer functions, such as performing FFT, performing iFFT, digital beamforming, or PRACH extraction and filtering based on function partitions such as lower-level function partitions (e.g., function partitions defined by 3GPP). In such an architecture, each RU 340 can be operated to handle over-the-air (OTA) communication with one or more UEs 120. In some implementations, the real-time and non-real-time aspects of control plane and user plane communication with the RU 340 can be controlled by the corresponding DU 330. In some scenarios, this configuration allows each DU 330 and CU 310 to be implemented in a cloud-based RAN architecture, such as a vRAN architecture.

[0073] SMO framework 305 can be configured to support RAN deployment and provisioning of non-virtualized and virtualized network elements. For non-virtualized network elements, SMO framework 305 can be configured to support the deployment of dedicated physical resources for RAN coverage requirements, which can be managed via operation and maintenance interfaces such as the O1 interface. For virtualized network elements, SMO framework 305 can be configured to interact with a cloud computing platform such as an open cloud (O-cloud) platform 390 to perform network element lifecycle management (LCM) (such as instantiating virtualized network elements) via a cloud computing platform interface such as the O2 interface. Such virtualized network elements may include, but are not limited to, CU 310, DU 330, RU 340, non-RT RIC 315, and near-RT RIC 325. In some implementations, SMO framework 305 can communicate with the hardware aspects of a 4G RAN such as an open eNB (O-eNB) 311 via the O1 interface. Additionally, in some implementations, the SMO framework 305 can communicate directly with each of one or more RUs 340 via a corresponding O1 interface. The SMO framework 305 may also include a non-RT RIC 315 configured to support the functionality of the SMO framework 305.

[0074] The non-RT RIC 315 can be configured to include non-real-time control and optimization of RAN elements and resources, artificial intelligence / machine learning (AI / ML) workflows including model training and updates, or policy-based guided logical functions for features / applications in the near-RT RIC 325. The non-RT RIC 315 can be coupled to or communicate with the near-RT RIC 325 (e.g., via the A1 interface). The near-RT RIC 325 can be configured to include logical functions that enable near real-time control and optimization of RAN elements and resources via action and data collection through interfaces (e.g., via the E2 interface) connecting one or more CUs 310, one or more DUs 330, or both, and the O-eNB to the near-RT RIC 325.

[0075] In some implementations, to generate an AI / ML model to be deployed in the near-RT RIC 325, the non-RT RIC 315 can receive parameters or external enrichment information from an external server. Such information can be utilized by the near-RT RIC 325 and can be received from non-network data sources or network functions at the SMO framework 305 or the non-RT RIC 315. In some examples, the non-RT RIC 315 or near-RT RIC 325 can be configured to tune RAN behavior or performance. For example, the non-RT RIC 315 can monitor long-term trends and patterns in performance and perform corrective actions using the AI / ML model via the SMO framework 305 (such as reconfiguration via the O1 interface) or via the creation of RAN management policies (such as A1 interface policies).

[0076] As mentioned above, Figure 3 This is provided as an example. Other examples may be provided in conjunction with [the relevant information]. Figure 3 The descriptions are different.

[0077] Figure 4 Example 400 of a wireless network (e.g., wireless network 100) according to this disclosure is shown, wherein a UE (e.g., UE 120) may support an additional communication mode. The UE may communicatively connect to one or more network nodes 110 in the wireless network. For example, the UE may connect to one or more network nodes 110 in a dual-connectivity configuration. In this case, a first network node 110 may serve the UE as a primary node, and a second network node 110 may serve the UE as a secondary node.

[0078] like Figure 4 As shown, the UE can support connected communication modes (e.g., RRC active mode 402), idle communication modes (e.g., RRC idle mode 404), and inactive communication modes (e.g., RRC inactive mode 406). RRC inactive mode 406 can functionally reside between RRC active mode 402 and RRC idle mode 404.

[0079] The UE can transition between different modes, at least in part, based on various commands and / or communications received from one or more network nodes 110. For example, the UE can transition from RRC active mode 402 or RRC inactive mode 406 to RRC idle mode 404, at least in part, based on receiving RRC Release (RRC) communications (e.g., RRC Release 408 for transitioning from RRC active mode 402 to RRC inactive mode 406 and RRC Release 410 for transitioning from RRC inactive mode 406 to RRC idle mode 404). As another example, the UE can transition from RRC active mode 402 to RRC inactive mode 406, at least in part, based on receiving RRC Release 408 with suspendConfig communications. As another example, the UE can transition from RRC idle mode 404 to RRC active mode 402, at least in part, based on receiving RRC Setup Request (RRC) communications 412. As another example, the UE can transition from RRC inactive mode 406 to RRC active mode 402 at least in part based on receiving RRC Resume Request communication 414.

[0080] When transitioning to RRC inactive mode 406, the UE and / or one or more network nodes 110 can store the UE context (e.g., access stratum (AS) context and / or higher-layer configuration). This allows the UE and / or one or more network nodes 110 to apply the stored UE context when the UE transitions from RRC inactive mode 406 to RRC active mode 402 in order to resume communication with one or more network nodes 110, which reduces the latency of transitioning to RRC active mode 402 compared to transitioning from RRC idle mode 404 to RRC active mode 402.

[0081] In some cases, when transitioning from RRC idle mode 404 or RRC inactive mode 406 to RRC active mode 402, the UE can communicatively connect to a new primary node (e.g., a different primary node from the last serving primary node when the UE transitioned to RRC idle mode 404 or RRC inactive mode 406). In this case, the new primary node can be responsible for identifying the UE's secondary node in a dual-connectivity configuration.

[0082] As mentioned above, Figure 4 This is provided as an example. Other examples may be provided in conjunction with [the relevant information]. Figure 4 The descriptions are different.

[0083] Figure 5This is a diagram illustrating an example architecture 500 of a functional framework for Radio Access Network (RAN) intelligence implemented through data collection according to this disclosure. In some scenarios, the functional framework for RAN intelligence can be further enhanced by data collection via use cases and / or examples. For example, principles or algorithms for RAN intelligence implemented by AI / ML and associated functional frameworks (e.g., inputs / outputs of AI functions and / or components for AI-enabled optimizations) have been utilized or studied to identify the benefits of AI-enabled RAN through possible use cases (e.g., beam management, energy saving, load balancing, mobility management and / or coverage optimization, etc.). In one example, as shown by architecture 500, the functional framework for RAN intelligence may include multiple logical entities such as a model training host 502, a model inference host 504, a data source 506, and an actor 508.

[0084] Model inference host 504 can be configured to run an AI / ML model based on inference data 512 provided by data source 506, and model inference host 504 can produce output 514 (e.g., prediction), where inference data 512 is input to actor 508 and model performance feedback 520 is input to model training host 502. Actor 508 can be a core network or RAN element or entity. For example, actor 508 can be a UE, network node, base station (e.g., gNB), CU, DU, and / or RU, etc. Additionally, actor 508 can also depend on the type of task performed by model inference host 504, the type of inference data 512 provided to model inference host 504, and / or the type of output produced by model inference host 504. For example, if output 514 from model inference host 504 is associated with beam management, actor 508 can be a UE, DU, or RU. In other examples, if output 514 from model inference host 504 is associated with Tx / Rx scheduling, actor 508 can be a CU or DU.

[0085] After actor 508 receives output 514 from model inference host 504, actor 508 can determine whether to take action based on output 514. For example, if actor 508 is a DU or RU and output 514 from model inference host 504 is associated with beam management, actor 508 can determine whether to change / modify the Tx / Rx beam based on output 514. If actor 508 determines to take action based on output 514, actor 508 can instruct action 516 to at least one subject of action 510. For example, if actor 508 determines to change / modify the Tx / Rx beam used for communication between actor 508 and subject of action 510 (e.g., UE 120), actor 508 can send a beam (re)configuration or beam switching instruction to subject of action 510. Action 508 can modify its Tx / Rx beams based on beam (re)configuration, such as switching to a new Tx / Rx beam or applying different parameters to the Tx / Rx beam. As another example, action 508 can be a UE, and output 514 from model inference host 504 can be associated with beam management. For example, output 514 can be one or more predicted measurements for one or more beams. Action 508 (e.g., UE) can determine to send a measurement report (e.g., a Layer 1 (L1) RSRP report) to network node 110.

[0086] Data source 506 can also be configured to collect data for use as training data 518 for training the ML model or as inference data 512 for feeding ML model inference operations. For example, data source 506 may collect data from one or more core network and / or RAN entities (which may include action subject 510) and provide the collected data to model training host 502 for ML model training. For example, after action subject 510 (e.g., UE 120) receives beam configuration from actor 508, action subject 510 may provide data source 506 with performance feedback 524 associated with the beam configuration, where performance feedback 524 may be used by model training host 502 to monitor or evaluate ML model performance, such as whether the output 514 (e.g., prediction) provided to actor 508 is accurate. In some examples, if the output 514 provided by actor 508 is inaccurate (or below an accuracy threshold), model training host 502 may determine to modify or retrain the ML model used by model inference host, such as via ML model deployment / update 522.

[0087] As mentioned above, Figure 5 This is provided as an example. Other examples may be provided in conjunction with [the relevant information]. Figure 5 The descriptions are different.

[0088] Figure 6 This is a diagram illustrating example 600 associated with the delivery of an AI / ML model via RRC signaling according to this disclosure. Figure 6 As shown, the first network node 110-1, the second network node 110-2, and the UE 120 can communicate with each other. The first network node 110-1 may be a portion of the source NewGeneration (NG) RAN (NG-RAN) that communicates with the UE 120 before handover is performed (e.g., the handover process is completed). The second network node 110-2 may be a portion of the target NG-RAN that communicates with the UE 120 after the handover process. The handover process may include the UE 120 handing over from the source NG-RAN to the target NG-RAN.

[0089] As shown by reference numeral 605 in the attached figure, UE 120 can send UE capability information via, for example, RRC signaling, and the first network node 110-1 can receive UE capability information via, for example, RRC signaling. The UE capability information can indicate to the first network node 110-1 the amount of memory and other resources available to UE 120.

[0090] As indicated by reference numeral 610, the first network node 110-1 can determine whether to send a new model to the UE 120, whether to instruct the UE 120 to release one or more models from its memory, and / or combinations thereof. The first network node 110-1 can determine whether to instruct the UE 120 to release one or more models from its memory based, for example, the amount of memory available at the UE 120. In some aspects, reference numeral 610 may appear at the second network node 110-2 instead of the first network node 110-1.

[0091] As shown by reference numeral 615 in the attached figure, the first network node 110-1 can send a model release command, and the UE 120 can receive the model release command. The model release command can be sent by the first network node 110-1 via RRC signaling. The model release command can instruct the UE 120 to release one or more models stored in the memory of the UE 120.

[0092] As shown by reference numeral 620 in the attached figure, the first network node 110-1 can send model transmissions via RRC signaling, and the UE 120 can receive model transmissions via RRC signaling. The model transmissions may include one or more AI / ML models to be used by the UE 120.

[0093] As shown by reference numeral 625, the first network node 110-1 can update the UE AI / ML context. The UE AI / ML context can be updated to identify the models available to UE 120 after model release shown by reference numeral 615 and model transfer shown by reference numeral 620.

[0094] As shown in the attached figure 630, the first network node 110-1 can initiate a handover from UE 120 to the second network node 110-2.

[0095] As shown by reference numeral 635 in the attached figure, the first network node 110-1 can send a handover request, and the second network node 110-2 can receive the handover request. In some aspects, the handover request may include the UE AI / ML context. Therefore, using the handover request, the second network node 110-2 can know which models are available for UE 120.

[0096] As shown by reference numeral 640 in the attached figure, the second network node 110-2 can send a handover response, and the first network node 110-1 can receive a handover response. The handover response may include or identify one or more models that are not available at UE 120.

[0097] As shown by reference numeral 645 in the attached figure, the first network node 110-1 can send an RRC reconfiguration signal, and the UE 120 can receive the RRC reconfiguration signal. The RRC reconfiguration signal may include configurations for the UE 120 to initiate communication on the target NG-RAN via the second network node 110-2.

[0098] As shown by reference numeral 650 in the attached figure, the first network node 110-1 or the second network node 110-2 may send model transmissions via RRC signaling, and the UE 120 may receive model transmissions via RRC signaling. Model transmissions may include one or more AI / ML models for use by the UE 120 when communicating via the target NG-RAN through the second network node 110-2. In some aspects, model transmissions occur only when the UE 120 does not have one or more available AI / ML models.

[0099] As mentioned above, Figure 6 This is provided as an example. Other examples may be provided in conjunction with [the relevant information]. Figure 6 The descriptions are different.

[0100] Figure 7 This is a diagram illustrating example 700 associated with the delivery of an AI / ML model via RRC signaling according to this disclosure. Figure 7As shown, the first network node 110-1, the second network node 110-2, and the UE 120 can communicate with each other. The first network node 110-1 may be a portion of the source NG-RAN that communicates with the UE 120 before the handover is performed. The second network node 110-2 may be a portion of the target NG-RAN that communicates with the UE 120 after the handover process. The handover process may include the UE 120 handing over from the source NG-RAN to the target NG-RAN.

[0101] As shown by reference numeral 705 in the attached figure, UE 120 can send UE capability information via RRC signaling, and the first network node 110-1 can receive UE capability information via RRC signaling. The UE capability information can indicate which models are supported by UE 120 and are available to UE 120.

[0102] As shown by reference numeral 710 in the attached figure, the first network node 110-1 can update the UE AI / ML context. The UE AI / ML context can be updated to identify models supported by and / or available to UE 120 based on UE capability information.

[0103] As shown by reference numeral 715 in the attached figure, the first network node 110-1 can send model transmissions via RRC signaling, and the UE 120 can receive model transmissions via RRC signaling. The model transmissions may include one or more AI / ML models to be used by the UE 120.

[0104] As shown by reference numeral 720 in the attached figure, UE 120 may experience memory problems. Therefore, UE 120 can determine that releasing one or more models can resolve the memory problem.

[0105] As shown by reference numeral 725 in the attached figure, UE 120 can send a model release request, and the first network node 110-1 can receive the model release request. The model release request can be sent via RRC (e.g., via UE Assistance Information (UAI)), and the first network node 110-1 can request the release of licenses for one or more AI / ML models from the memory of UE 120.

[0106] As shown by reference numeral 730 in the attached figure, the first network node 110-1 can send a model release response, and the UE 120 can receive the model release response. The model release response can be configured or otherwise instructs the UE 120 to release one or more models from the UE 120's memory. In some aspects, the model release response indicates which models stored in the UE 120's memory can be released.

[0107] As shown by reference numeral 735, the first network node 110-1 can update the UE AI / ML context. The UE AI / ML context can be updated to remove or otherwise exclude the model released by UE 120 after the model release response shown by reference numeral 730.

[0108] As shown by reference numeral 740 in the attached figure, the first network node 110-1 can initiate a handover from UE 120 to the second network node 110-2.

[0109] As shown by reference numeral 745 in the attached figure, the first network node 110-1 can send a handover request, and the second network node 110-2 can receive the handover request. In some aspects, the handover request may include the UE AI / ML context. Therefore, using the handover request, the second network node 110-2 can know which models are available for UE 120.

[0110] As shown by reference numeral 750 in the attached figure, the second network node 110-2 can send a handover response, and the first network node 110-1 can receive a handover response. The handover response may include or identify one or more models that are not available at UE 120.

[0111] As shown by reference numeral 755 in the attached figure, the first network node 110-1 can send an RRC reconfiguration signal, and the UE 120 can receive the RRC reconfiguration signal. The RRC reconfiguration signal may include configuration for the UE 120 to initiate communication on the target NG-RAN via the second network node 110-2.

[0112] As shown by reference numeral 760 in the attached figure, the first network node 110-1 or the second network node 110-2 may send model transmissions via RRC signaling, and the UE 120 may receive model transmissions via RRC signaling. Model transmission may include one or more AI / ML models for use by the UE 120 when communicating via the target NG-RAN through the second network node 110-2. In some aspects, model transmission occurs only when the UE 120 does not have one or more available AI / ML models.

[0113] As mentioned above, Figure 7 This is provided as an example. Other examples may be provided in conjunction with [the relevant information]. Figure 7 The descriptions are different.

[0114] Figure 8 This is a diagram illustrating example 800 associated with the delivery of an AI / ML model via RRC signaling according to this disclosure. Figure 8As shown, the first network node 110-1, the second network node 110-2, and the UE 120 can communicate with each other. The first network node 110-1 may be a portion of the source NG-RAN that communicates with the UE 120 before the handover is performed. The second network node 110-2 may be a portion of the target NG-RAN that communicates with the UE 120 after the handover process. The handover process may include the UE 120 handing over from the source NG-RAN to the target NG-RAN.

[0115] As shown by reference numeral 805 in the attached figure, the first network node 110-1 can update the UE AI / ML context. The UE AI / ML context can be updated to identify models supported by and / or available to UE 120 based on UE capability information.

[0116] As shown by reference numeral 810 in the attached figure, the first network node 110-1 can send model transmissions via RRC signaling, and the UE 120 can receive model transmissions via RRC signaling. The model transmissions may include one or more AI / ML models to be used by the UE 120.

[0117] As shown by reference numeral 820 in the attached figure, UE 120 can release one or more models. In some aspects, UE 120 can release one or more models without a model release instruction from the first network node 110-1.

[0118] As shown by reference numeral 825 in the attached figure, UE 120 can transmit model information, and the first network node 110-1 can receive the model information. In some aspects, the model information can indicate that one or more models are available or have been released. In some aspects, the model information can indicate models that are still available to UE 120 after one or more models have been released. In some aspects, the model information is transmitted from the UE to the first network node 110-1 via RRC signaling, MAC control element (MAC-CE) signaling, and / or combinations thereof.

[0119] As shown by reference numeral 830 in the attached figure, the first network node 110-1 can update the UE AI / ML context. The UE AI / ML context can be updated to remove or otherwise exclude models released by UE 120 after the model release shown by reference numeral 820.

[0120] As shown by reference numeral 835 in the attached figure, UE 120 can send measurement reports, and the first network node 110-1 can receive measurement reports. UE 120 can send measurement reports via RRC signaling, MAC-CE signaling, and / or combinations thereof.

[0121] As shown in the attached figure 840, the first network node 110-1 can initiate a handover from UE 120 to the second network node 110-2.

[0122] As shown by reference numeral 845 in the attached figure, the first network node 110-1 can send a handover request, and the second network node 110-2 can receive the handover request. In some aspects, the handover request may include the UE AI / ML context. Therefore, using the handover request, the second network node 110-2 can know which models are available for UE 120.

[0123] As shown by reference numeral 850 in the attached figure, the second network node 110-2 can send a handover response, and the first network node 110-1 can receive a handover response. The handover response may include or identify one or more models that are not available at UE 120.

[0124] As shown by reference numeral 855 in the attached figure, the first network node 110-1 can send an RRC reconfiguration signal, and the UE 120 can receive the RRC reconfiguration signal. The RRC reconfiguration signal may include configuration for the UE 120 to initiate communication on the target NG-RAN via the second network node 110-2.

[0125] As shown by reference numeral 860 in the attached figure, the first network node 110-1 or the second network node 110-2 may send model transmissions via RRC signaling, and the UE 120 may receive model transmissions via RRC signaling. Model transmissions may include one or more AI / ML models for use by the UE 120 when communicating via the target NG-RAN through the second network node 110-2. In some aspects, model transmissions occur only when the UE 120 does not have one or more available AI / ML models.

[0126] As mentioned above, Figure 8 This is provided as an example. Other examples may be provided in conjunction with [the relevant information]. Figure 8 The descriptions are different.

[0127] Figure 9 This is a diagram illustrating example 900 associated with the delivery of an AI / ML model via RRC signaling according to this disclosure. Figure 9 As shown, the first network node 110-1, the second network node 110-2, and the UE 120 can communicate with each other. The first network node 110-1 may be a portion of the source NG-RAN that communicates with the UE 120 before the handover is performed. The second network node 110-2 may be a portion of the target NG-RAN that communicates with the UE 120 after the handover process. The handover process may include the UE 120 handing over from the source NG-RAN to the target NG-RAN.

[0128] As shown by reference numeral 905 in the attached figure, UE 120 can store a list of available models. In some aspects, the list of available models can be stored in an RRC variable.

[0129] As shown by reference numeral 910 in the attached figure, UE 120 can send measurement reports, and the first network node 110-1 can receive measurement reports. UE 120 can send measurement reports via RRC signaling, MAC-CE signaling, and / or combinations thereof.

[0130] As shown in the attached figure 915, the first network node 110-1 can initiate a handover of UE 120 to the second network node 110-2.

[0131] As shown by reference numeral 920 in the attached figure, the first network node 110-1 can send a request for model information, and the UE 120 can receive the request for model information. The request for model information can be sent via RRC signaling, MAC-CE signaling, and / or combinations thereof. In some aspects, the model information includes a model identifier that can be used for each model of the UE 120.

[0132] As shown by reference numeral 925 in the attached figure, UE 120 can send model information, and the first network node 110-1 can receive the model information. The model information can be sent to the first network node 110-1 via RRC signaling, MAC-CE signaling, and / or combinations thereof.

[0133] As shown by reference numeral 930 in the attached figure, the first network node 110-1 can send a handover request, and the second network node 110-2 can receive the handover request. In some aspects, the handover request may include the UE AI / ML context. Therefore, using the handover request, the second network node 110-2 can know which models are available for UE 120.

[0134] As shown by reference numeral 935 in the attached figure, the second network node 110-2 can send a handover response, and the first network node 110-1 can receive a handover response. The handover response may include or identify one or more models that are not available at UE 120.

[0135] As shown by reference numeral 940 in the attached figure, the first network node 110-1 can send an RRC reconfiguration signal, and the UE 120 can receive the RRC reconfiguration signal. The RRC reconfiguration signal may include configurations for the UE 120 to initiate communication on the target NG-RAN via the second network node 110-2.

[0136] As shown by reference numeral 945 in the attached figure, the first network node 110-1 or the second network node 110-2 can send model transmissions via RRC signaling, and the UE 120 can receive model transmissions via RRC signaling. Model transmissions may include one or more AI / ML models for use by the UE 120 when communicating via the target NG-RAN through the second network node 110-2. In some aspects, model transmissions occur only when the UE 120 does not have one or more available AI / ML models.

[0137] As mentioned above, Figure 9 This is provided as an example. Other examples may be provided in conjunction with [the relevant information]. Figure 9 The descriptions are different.

[0138] Figure 10 This is a diagram illustrating example 1000 associated with the delivery of an AI / ML model via RRC signaling according to this disclosure. Figure 10 As shown, the second network node 110-2 and the UE 120 can communicate with each other. For example, as a result of the UE 120 returning from an idle / inactive state to an active state, the second network node 110-2 can be part of the target NG-RAN that communicates with the UE 120.

[0139] As shown by reference numeral 1005 in the attached figure, UE 120 may store a list of available models. In some aspects, the list of available models is stored in an RRC variable.

[0140] As shown by reference numeral 1010 in the attached figure, UE 120 can send an RRC recovery request, an RRC establishment request, or an RRC reconstruction request, and the second network node 110-2 can receive the RRC recovery request, RRC establishment request, or RRC reconstruction request. The RRC recovery request, RRC establishment request, or RRC reconstruction request can indicate to the second network node 110-2 the transition of UE 120 from an idle / inactive state to an active state.

[0141] As shown by reference numeral 1015 in the attached figure, the second network node 110-2 can send an RRC recovery or RRC establishment signal, and the UE 120 can receive the RRC recovery or RRC establishment signal. The RRC recovery or RRC establishment signal may include a request for available model information stored by the UE 120.

[0142] As shown by reference numeral 1020 in the attached figure, UE 120 can send an RRC recovery complete, RRC establishment complete, or RRC reconstruction complete signal, and the second network node 110-2 can receive the RRC recovery complete, RRC establishment complete, or RRC reconstruction complete signal. The RRC recovery complete, RRC establishment complete, or RRC reconstruction complete signal may include a response from the second network node 110-2 to a request for model information stored by UE 120.

[0143] As shown by reference numeral 1025 in the attached figure, the second network node 110-2 can send model transmissions via RRC signaling, and the UE 120 can receive model transmissions via RRC signaling. Model transmissions may include one or more AI / ML models for use by the UE 120 when communicating via the target NG-RAN through the second network node 110-2. In some aspects, model transmissions occur only when the UE 120 does not have one or more available AI / ML models.

[0144] As mentioned above, Figure 10 This is provided as an example. Other examples may be provided in conjunction with [the relevant information]. Figure 10 The descriptions are different.

[0145] Figure 11 This is a diagram illustrating example 1100 associated with the delivery of an AI / ML model via RRC signaling according to this disclosure. Figure 11 As shown, the first network node 110-1, the second network node 110-2, and the UE 120 can communicate with each other. The first network node 110-1 may be a portion of the previous NG-RAN that communicates with the UE 120 before the UE 120 enters an idle / inactive state. In some aspects, the first network node 110-1 is an Access and Mobility Function (AMF). As a result, for example, when the UE 120 returns from an idle / inactive state to an active state, the second network node 110-2 may be a portion of the target NG-RAN that communicates with the UE 120.

[0146] As shown by reference numeral 1105 in the attached figure, UE 120 can send an RRC recovery request, an RRC establishment request, or an RRC reconstruction request, and the second network node 110-2 can receive the RRC recovery request, RRC establishment request, or RRC reconstruction request. The RRC recovery request, RRC establishment request, or RRC reconstruction request can indicate to the second network node 110-2 the transition of UE 120 from an idle / inactive state to an active state.

[0147] As shown by reference numeral 1110 in the attached figure, the second network node 110-2 can send a UE context retrieval request, and the first network node 110-1 can receive the UE context retrieval request. The UE context retrieval request may include a request for the first network node 110-1 to retrieve a list of AI / ML models or other identifiers that can be used by the UE 120.

[0148] As shown by reference numeral 1115 in the attached figure, the first network node 110-1 can send a UE context retrieval request response, and the second network node 110-2 can receive the UE context retrieval request response. The UE context retrieval request response may include a list of AI / ML models available for UE 120 or other identifiers.

[0149] As shown by reference numeral 1120 in the attached figure, the second network node 110-2 can send an RRC recovery or RRC establishment signal, and the UE 120 can receive the RRC recovery or RRC establishment signal. The RRC recovery or RRC establishment signal can transmit one or more AI / ML models from the second network node 110-2 to the UE 120.

[0150] As shown by reference numeral 1125 in the attached figure, UE 120 can send an RRC recovery complete, RRC establishment complete, or RRC reconstruction complete signal, and the second network node 110-2 can receive the RRC recovery complete, RRC establishment complete, or RRC reconstruction complete signal. The RRC recovery complete, RRC establishment complete, or RRC reconstruction complete signal can indicate to the second network node 110-2 that UE 120 has received the AI / ML model transmission.

[0151] As shown by reference numeral 1130, the second network node 110-2 can send additional model transmissions via RRC signaling, and the UE 120 can receive additional model transmissions via RRC signaling. The additional model transmissions may include one or more AI / ML models for the UE 120 to use when communicating via the target NG-RAN through the second network node 110-2. In some aspects, additional model transmissions occur only when the UE 120 does not have one or more available AI / ML models. For example, additional model transmissions may occur if more AI / ML models are needed or if the model transmission shown by reference numeral 1130 is incomplete.

[0152] As mentioned above, Figure 11 This is provided as an example. Other examples may be provided in conjunction with [the relevant information]. Figure 11 The descriptions are different.

[0153] Figure 12 This is a diagram illustrating example 1200 associated with the delivery of an AI / ML model via RRC signaling according to this disclosure. Figure 12As shown, the first network node 110-1, the second network node 110-2, and the UE 120 can communicate with each other. The first network node 110-1 may be a portion of a supported NG-RAN that communicates with the UE 120 before the handover is performed. The second network node 110-2 may be a portion of a non-supported NG-RAN (e.g., an NG-RAN that does not support one or more AI / ML models used by the UE 120) that communicates with the UE 120 after the handover process. The handover process may include the handover of the UE 120 during its movement from a supported NG-RAN to a non-supported NG-RAN.

[0154] As shown in the attached figure 1205, the first network node 110-1 can initiate a handover from UE 120 to the second network node 110-2.

[0155] As shown by reference numeral 1210 in the attached figure, a first network node 110-1 can send a handover request, and a second network node 110-2 can receive the handover request. In some aspects, the handover request may include a transparent container with the UE AI / ML context. Therefore, using the handover request, the second network node 110-2 can know which models are available for UE 120.

[0156] As shown by reference numeral 1215 in the attached figure, the second network node 110-2 can store a transparent container containing the UE AI / ML context. In some aspects, the second network node 110-2 can update the transparent container to include one or more AI / ML models.

[0157] As shown by reference numeral 1220 in the attached figure, the second network node 110-2 can send a handover response, and the first network node 110-1 can receive the handover response. The handover response may include a transparent container having one or more AI / ML models for use by the UE 120.

[0158] As shown by reference numeral 1225 in the accompanying drawings, the first network node 110-1 can send an RRC reconfiguration signal, and the UE 120 can receive the RRC reconfiguration signal. The RRC reconfiguration signal may include configuration for the UE 120 to initiate communication on a non-supported NG-RAN via the second network node 110-2. In some aspects, the RRC reconfiguration signal may include a transparent container.

[0159] As mentioned above, Figure 12 This is provided as an example. Other examples may be provided in conjunction with [the relevant information]. Figure 12 The descriptions are different.

[0160] Figure 13 This is a diagram illustrating example 1300 associated with the delivery of an AI / ML model via RRC signaling according to this disclosure. Figure 13 As shown, the first network node 110-1, the second network node 110-2, and the UE 120 can communicate with each other. The first network node 110-1 may be a portion of a supported NG-RAN that communicates with the UE 120 after the handover is performed. The second network node 110-2 may be a portion of a non-supported NG-RAN that communicates with the UE 120 before the handover process. The handover process may include the handover of the UE 120 during its movement from a non-supported NG-RAN to a supported NG-RAN.

[0161] As shown in the attached figure 1305, the second network node 110-2 can initiate a handover of UE 120 to the first network node 110-1.

[0162] As shown by reference numeral 1310 in the attached figure, the second network node 110-2 can send a handover request, and the first network node 110-1 can receive the handover request. In some aspects, the handover request may include a transparent container with UE AI / ML context. As described above, the UE AI / ML context may include available model information communicated by UE 120 to the second network node 110-2. Therefore, using the handover request, the first network node 110-1 can know which models are available to UE 120.

[0163] As shown by reference numeral 1315 in the attached figure, the first network node 110-1 can store the UE AI / ML context.

[0164] As shown by reference numeral 1320 in the attached figure, the first network node 110-1 can send a handover response, and the second network node 110-2 can receive the handover response. The handover response can include the UE AI / ML context within a transparent container.

[0165] As shown by reference numeral 1325 in the attached figure, the second network node 110-2 can send an RRC reconfiguration signal, and the UE 120 can receive the RRC reconfiguration signal. The RRC reconfiguration signal may include configuration for the UE 120 to initiate communication on a supported NG-RAN via the first network node 110-1. In some aspects, the RRC reconfiguration signal may include one or more AI / ML models.

[0166] As shown by reference numeral 1330 in the attached figure, UE 120 can send an RRC reconfiguration complete signal, and the first network node 110-1 can receive the RRC reconfiguration complete signal. The RRC reconfiguration complete signal can indicate that UE 120 is configured to communicate on a supported NG-RAN via the first network node 110-1.

[0167] As shown by reference numeral 1335 in the attached figure, the first network node 110-1 can send one or more additional AI / ML models, and the UE 120 can receive one or more additional AI / ML models.

[0168] As mentioned above, Figure 13 This is provided as an example. Other examples may be provided in conjunction with [the relevant information]. Figure 13 The descriptions are different.

[0169] Figure 14 This is a diagram illustrating example 1400 associated with the delivery of an AI / ML model via RRC signaling according to this disclosure. Figure 14 As shown, the first network node 110-1, the second network node 110-2, and the UE 120 can communicate with each other. The first network node 110-1 may be a portion of a supported NG-RAN that communicates with the UE 120 after handover is performed (e.g., the handover process is completed). The second network node 110-2 may be a portion of a non-supported NG-RAN that communicates with the UE 120 before handover is performed. The handover process may include the handover of the UE 120 during movement from a non-supported NG-RAN to a supported NG-RAN.

[0170] As shown by reference numeral 1405 in the accompanying drawings, a first network node 110-1, a second network node 110-2, and a UE 120 can participate in a handover process to, for example, transition the UE 120 from unsupported NG-RAN via the second network node 110-2 to supported NG-RAN via the first network node 110-1. The handover process may include either the first network node 110-1 or the second network node 110-2 sending an RRC reconfiguration signal, and the UE 120 receiving the RRC reconfiguration signal having a configuration for the UE 120 to initiate communication via the second network node 110-2 on the unsupported NG-RAN. In some aspects, the RRC reconfiguration signal may include one or more AI / ML models.

[0171] As shown by reference numeral 1410 in the attached figure, UE 120 may send an RRC reconfiguration complete signal, and the first network node 110-1 may receive the RRC reconfiguration complete signal. The RRC reconfiguration complete signal may indicate that UE 120 is configured to communicate on a supported NG-RAN via the first network node 110-1. In some aspects, the RRC reconfiguration complete signal may indicate one or more AI / ML models available to UE 120.

[0172] Alternatively or additionally, as indicated by reference numeral 1415, the first network node 110-1 may send a UE information request, and the UE 120 may receive the UE information request. The UE information request may request from the UE 120 the identification of one or more AI / ML models that can be used by the UE 120.

[0173] As shown by reference numeral 1420, UE 120 may send an RRC reconfiguration complete signal or a UE information response signal, and the first network node 110-1 may receive the RRC reconfiguration complete signal or the UE information response signal. The RRC reconfiguration complete signal or the UE information response signal shown by reference numeral 1420 may include information about one or more AI / ML models that can be used by UE 120.

[0174] As shown by reference numeral 1425 in the attached figure, the first network node 110-1 can send model transmissions via RRC signaling, and the UE 120 can receive model transmissions via RRC signaling. Model transmissions may include one or more AI / ML models. In some aspects, one or more AI / ML models included in the model transmission may differ from one or more AI / ML models indicated in the RRC reconfiguration completion signal or the UE information response signal.

[0175] As mentioned above, Figure 14 This is provided as an example. Other examples may be provided in conjunction with [the relevant information]. Figure 14 The descriptions are different.

[0176] Figure 15 This is a diagram illustrating example 1500 associated with configuration and model delivery according to this disclosure. Figure 15 As shown, Example 1500 includes communication between a first network node 110-1 and a UE (not shown) and between a second network node 110-2 and the UE. In some examples, such a UE may be UE 120 as described herein. In some aspects, the first network node 110-1 is a source NG-RAN (e.g., as...). Figure 15 The source cell shown is part of the target NG-RAN (e.g., as shown in the image), and the second network node 110-2 is part of the target NG-RAN (e.g., as shown in the image). Figure 15 (The target cell shown) is part of it.

[0177] As indicated by reference numeral 1505, in one example, a first network node 110-1 may provide the UE with configuration 1535, additional configuration 1540 (sometimes referred to as fallback configuration), and AI / ML model 1545 via the same signaling radio bearer (SRB) 1550. Upon successful delivery of AI / ML model 1545 to the UE, the first network node 110-1 may send an indication to the second network node. Alternatively, the UE may indicate to the second network node 110-2 that the UE has received all configured AI / ML models and / or a list of received or available AI / ML models. In some aspects, the second network node 110-2 may send an LCM control signal 1555 to the UE after a handover from the first network node 110-1 to the second network node 110-2. The LCM control signal 1555 may include control signals for managing the lifecycle of one or more network functions or services, such as the creation, modification, and termination of network functions. In some aspects, such as during the handover process, the LCM control signal 1555 can be used to allocate resources that facilitate handover to the target cell without degrading the quality of service.

[0178] As indicated by reference numeral 1510, in one example, a first network node 110-1 may provide configuration 1535 and additional configuration 1540 to the UE in a first SRB 1550, and may provide AI / ML model 1545 to the UE via a second SRB 1565. In the example shown by reference numeral 1510, the first SRB 1550 may have a higher priority than the second SRB 1565. Upon successful delivery of model 1545, the first network node 110-1 may send an indication to the second network node 110-2. Alternatively, the UE may indicate to the second network node 110-2 that the UE has received all configured AI / ML models and / or a list of received or available AI / ML models. In some aspects, the second network node 110-2 may send an LCM control signal 1555 to the UE after a handover from the first network node 110-1 to the second network node 110-2.

[0179] As shown by reference numeral 1515, in one example, a first network node 110-1 may provide configuration 1535 and additional configuration 1540 to the UE in a first SRB 1550, and may provide AI / ML model 1545 to the UE via a second SRB 1565. In the example shown by reference numeral 1515, the first SRB 1550 may have a higher priority than the second SRB 1565. If the first network node 110-1 determines that it cannot send the AI / ML model within a predetermined time, the first network node 110-1 may send a portion of configuration 1535 and / or a portion of additional configuration 1540 before sending the AI / ML model 1545. After sending a portion of configuration 1535 or additional configuration 1540, the first network node 110-1 may send the remainder of configuration 1535 or additional configuration 1540. Upon successful delivery of model 1545, the first network node 110-1 may send an indication to the second network node 110-2. Alternatively, the UE may indicate to the second network node 110-2 that the UE has received all configured AI / ML models and / or a list of received or available AI / ML models. In some aspects, the second network node 110-2 may send an LCM control signal 1555 to the UE after a handover from the first network node 110-1 to the second network node 110-2.

[0180] As shown by reference numeral 1520 in the attached figure, in one example, the first network node 110-1 may provide the UE with configuration 1535 and AI / ML model 1545 via the same or different SRB as the handover configuration and model delivery. For example, as Figure 15As shown, configuration 1535 can be sent in the second SRB 1565, AI / ML model 1545 can be sent in the first SRB 1545, and LCM control signal 1555 can be sent in the third SRB 1570. Alternatively, similar to the example shown by reference numeral 1515, configuration 1535 and additional configuration 1540 can be sent in the first SRB 1550, and AI / ML model 1545 can be sent in the second SRB 1565. In another alternative (discussed below with respect to reference numeral 1525), configuration 1535, additional configuration 1540, and AI / ML model 1545 can be sent in a single SRB (e.g., the first SRB 1550). The first network node 110-1 can send AI / ML model 1545 and switch configurations after model delivery is complete. Upon successful delivery of AI / ML model 1545, the first network node 110-1 can send an indication to the second network node 110-2. Alternatively, the UE may indicate to the second network node 110-2 that the UE has received all configured AI / ML models and / or a list of received or available AI / ML models. In some aspects, the second network node 110-2 may send an LCM control signal 1555 to the UE after a handover from the first network node 110-1 to the second network node 110-2.

[0181] As shown by reference numeral 1525, in one example, a first network node 110-1 may begin providing the UE with configuration 1535, additional configuration 1540, and AI / ML model 1545 via the same SRB (e.g., first SRB 1550). In an instance where the first network node 110-1 fails to complete model delivery, the first network node 110-1 may send an indication of delivery failure of the AI / ML model 1545 to the second network node 110-2, and the UE may apply additional configuration 1560 while the second network node 110-2 is sending the AI / ML model 1545 to the UE. Upon successful delivery of the AI / ML model 1545, the UE may indicate to the second network node 110-2 that the UE has received all configured AI / ML models and / or a list of received or available AI / ML models. In some aspects, the UE may indicate to the second network node 110-2 that additional AI / ML models need to be delivered. In some aspects, the indication from the UE to the second network node 110-2 is made via RRC signaling. In some respects, the second network node 110-2 may send an LCM control signal 1555 to the UE after a handover from the first network node 110-1 to the second network node 110-2.

[0182] As shown by reference numeral 1530, in one example, a first network node 110-1 may begin providing configuration 1535 and additional configuration 1540 to the UE via a first SRB 1550, and may begin providing AI / ML model 1545 to the UE via a second SRB 1565. In an instance where the first network node 110-1 fails to complete the delivery of AI / ML model 1545 to the UE, the first network node 110-1 may send an indication of delivery failure of AI / ML model 1545 to the second network node 110-2, and the UE may apply the additional configuration while the second network node 110-2 is sending AI / ML model 1545 to the UE. Upon successful delivery of AI / ML model 1545, the UE may indicate to the second network node 110-2 that the UE has received all configured AI / ML models and / or a list of received or available AI / ML models. In some aspects, the UE may indicate to the second network node 110-2 that additional AI / ML models need to be delivered. In some aspects, instructions from the UE to the second network node 110-2 are made via RRC signaling. In some aspects, the second network node 110-2 may send an LCM control signal 1555 to the UE after a handover from the first network node 110-1 to the second network node 110-2.

[0183] Regarding the examples above, in some aspects, the AI / ML model may be considered "active" by default, in which case the second network node 110-2 may not need to send the LCM control signal 1555 for model activation. In some instances, such as in the event of model delivery failure, the second network node 110-2 may send a temporary configuration to the UE. In some instances, the temporary configuration may include a low-complexity, lightweight reference model to be used until one or more of the desired AI / ML models are delivered to the UE. In some instances, such as when the model is successfully delivered before configuration, a temporary configuration from the first network node 110-1 may not be needed. The first network node 110-1 may release the temporary configuration upon successful delivery of the AI / ML model.

[0184] As mentioned above, Figure 15 This is provided as an example. Other examples may be provided in conjunction with [the relevant information]. Figure 15 The descriptions are different.

[0185] Figure 16 This is a diagram illustrating Example 1600 associated with the delivery of an AI / ML model via RRC signaling according to this disclosure. Figure 16As shown, the first network node 110-1, the second network node 110-2, and the UE 120 can communicate with each other. The first network node 110-1 may be a portion of the source NG-RAN that communicates with the UE before the handover is performed. The second network node 110-2 may be a portion of the target NG-RAN that communicates with the UE after the handover process. The handover process may include the UE 120's handover from the source NG-RAN to the target NG-RAN. As shown by reference numeral 1605, the second network node 110-2 may send model transmissions (e.g., transmissions of AI / ML models), and the first network node 110-1 may receive model transmissions. Model transmissions may occur during an Xn-based handover process between the first network node 110-1 and the second network node 110-2. As shown by reference numeral 1610, the first network node 110-1 attempts to send an AI / ML model to the UE 120 via RRC signaling, but the model transmission fails. In some aspects, as indicated by reference numeral 1615, the second network node 110-2 can restart model delivery to UE 120 via RRC signaling (e.g., to implement model transfer). As described above, Figure 16 This is provided as an example. Other examples may be provided in conjunction with [the relevant information]. Figure 16 The descriptions are different.

[0186] Figure 17 This is a diagram illustrating Example 1700 associated with the delivery of an AI / ML model via RRC signaling according to this disclosure. Figure 17As shown, the first network node 110-1, the second network node 110-2, and the UE 120 can communicate with each other. The first network node 110-1 may be a portion of the source NG-RAN communicating with the UE 120 before the handover is performed. The second network node 110-2 may be a portion of the target NG-RAN communicating with the UE 120 after the handover process. The handover process may include the UE's handover from the source NG-RAN to the target NG-RAN. As shown by reference numeral 1705, the second network node 110-2 may send model transmissions (e.g., transmissions of AI / ML models), and the first network node 110-1 may receive model transmissions. Model transmissions may occur during an Xn-based handover process between the first network node 110-1 and the second network node 110-2. As shown by reference numeral 1710, the first network node 110-1 sends at least a portion of the AI / ML model to the UE 120 via RRC signaling. As shown by reference numeral 1715, at least a portion of the model transmission between the first network node 110-1 and the UE 120 fails. As shown by reference numeral 1720, the first network node 110-1 can instruct the second network node 110-2 to specify the bytes, segments, or sequence numbers associated with a partial (e.g., incomplete) transmission of the AI / ML model. Therefore, the instruction shown by reference numeral 1720 can indicate to the second network node 110-2 how much of the AI / ML model UE 120 has received. As shown by reference numeral 1725, the second network node 110-2 can send the remaining bytes, segments, or sequences of the AI / ML model to the UE 120 via RRC signaling, thereby resulting in lossless model transmission during Xn-based handover. As described above, Figure 17 This is provided as an example. Other examples may be provided in conjunction with [the relevant information]. Figure 17 The descriptions are different.

[0187] Figure 18 This is a diagram illustrating Example 1800 associated with the delivery of an AI / ML model via RRC signaling according to this disclosure. Figure 18As shown, the first network node 110-1, the second network node 110-2, and the UE 120 can communicate with each other. The first network node 110-1 may be a portion of the source NG-RAN that communicates with the UE 120 before the handover is performed. The second network node 110-2 may be a portion of the target NG-RAN that communicates with the UE 120 after the handover process. The handover process may include the UE 120's handover from the source NG-RAN to the target NG-RAN. As shown by reference numeral 1805, the second network node 110-2 may send an AI / ML model to the AMF 1825 via the NG Application Protocol (AP). As shown by reference numeral 1810, the AMF 1825 may send model transmissions (e.g., AI / ML model transmissions) via the NG-AP, and the first network node 110-1 may receive model transmissions (e.g., AI / ML model transmissions) via the NG-AP. As shown by reference numeral 1815, the first network node 110-1 attempts to send an AI / ML model to the UE 120 via RRC signaling, but the model transmission fails. In some aspects, as indicated by reference numeral 1820, the second network node 110-2 can restart model transmission to UE 120 via RRC signaling (e.g., to implement model transmission). As described above, Figure 18 This is provided as an example. Other examples may be provided in conjunction with [the relevant information]. Figure 18 The descriptions are different.

[0188] Figure 19 This is a diagram illustrating Example 1900 associated with the delivery of an AI / ML model via RRC signaling according to this disclosure. Figure 19As shown, the first network node 110-1, the second network node 110-2, and the UE 120 can communicate with each other. The first network node 110-1 may be a portion of the source NG-RAN communicating with the UE 120 before the handover is performed. The second network node 110-2 may be a portion of the target NG-RAN communicating with the UE 120 after the handover process. The handover process may include the UE 120's handover from the source NG-RAN to the target NG-RAN. As shown by reference numeral 1905, the second network node 110-2 may send an AI / ML model to the AMF 1935 via the NG-AP. As shown by reference numeral 1910, the AMF 1935 may send model transmissions (e.g., AI / ML model transmissions) via the NG-AP, and the first network node 110-1 may receive model transmissions (e.g., AI / ML model transmissions) via the NG-AP. As shown by reference numeral 1915, the first network node 110-1 attempts to send an AI / ML model to the UE 120 via RRC signaling, but the model transmission fails at least partially. As shown by reference numeral 1920, the first network node 110-1 can indicate to the AMF 1935 the bytes, segments, or sequence numbers associated with a portion of the AI / ML model transmission. Therefore, the indication sent to the AMF 1935 via NG-AP (as shown by reference numeral 1920) can indicate to the AMF 1935 how much AI / ML model the UE has received. As shown by reference numeral 1925, the AMF 1935 can send the remaining bytes, segments, or sequences of the AI / ML model to the second network node 110-2 via NG-AP. As shown by reference numeral 1930, the second network node 110-2 can send the remaining bytes, segments, or sequences of the AI / ML model to the UE 120 via RRC signaling, resulting in lossless model transmission during NG-AP handover. As described above, Figure 19 This is provided as an example. Other examples may be provided in conjunction with [the relevant information]. Figure 19 The descriptions are different.

[0189] Figure 20 This is a diagram illustrating an example process 2000 performed by a UE, for example, according to this disclosure. Example process 2000 is an example in which a UE (e.g., UE 120) performs operations associated with the RRC delivery of an AI / ML model.

[0190] like Figure 20 As shown, in some aspects, process 2000 may include communication with one of the first network node or the second network node to update available model information in the UE context at one or more of the first or second network nodes (box 2010). For example, the UE (e.g., using...) Figure 22The receiving component 2202, the transmitting component 2204, and / or the communication manager 2206 depicted herein can communicate with one of the first network node or the second network node to update the available model information in the UE context at one or more of the first network node or the second network node, as described above.

[0191] like Figure 20 As further shown, in some aspects, process 2000 may include receiving a model transmission from one of the first or second network nodes via RRC signaling (box 2020). For example, the UE (e.g., using...) Figure 22 The receiving component 2202 and / or communication manager 2206 described herein can receive model transmissions from one of the first or second network nodes via RRC signaling, as described above.

[0192] Process 2000 may include additional aspects, such as those described below and / or any single aspect or any combination of aspects described in conjunction with one or more other process descriptions elsewhere herein.

[0193] In the first aspect, process 2000 includes sending available model information to a first network node.

[0194] In the second aspect, alone or in combination with the first aspect, process 2000 includes receiving a model release instruction from the first network node.

[0195] In the third aspect, alone or in combination with one or more of the first and second aspects, process 2000 includes releasing one or more models indicated in the release instruction.

[0196] In the fourth aspect, alone or in combination with one or more of the first to third aspects, process 2000 includes sending a model release request to the first network node.

[0197] In the fifth aspect, the receiving of the model release instruction, either alone or in combination with one or more of the first to fourth aspects, occurs after a model release request is sent to the first network node.

[0198] In the sixth aspect, alone or in combination with one or more of the first to fifth aspects, process 2000 includes releasing one or more models without instruction from the first network node.

[0199] In the seventh aspect, alone or in combination with one or more of the first to sixth aspects, process 2000 includes sending available model information to a first network node, the model information indicating that one or more models are available or have been released.

[0200] In the eighth aspect, alone or in combination with one or more of the first to seventh aspects, process 2000 includes receiving a request for model information from the first network node.

[0201] In the ninth aspect, alone or in combination with one or more of the first to eighth aspects, process 2000 includes sending model information to a first network node in response to a request for model information.

[0202] In the tenth aspect, alone or in combination with one or more of the first to ninth aspects, process 2000 includes sending an RRC establishment request, an RRC reconstruction request, or an RRC recovery request to the second network node.

[0203] In the eleventh aspect, alone or in combination with one or more of the first to tenth aspects, receiving a model transmission includes receiving a model transmission from a second network node based at least in part on sending an RRC establishment request, an RRC reconstruction request, or an RRC recovery request to the second network node.

[0204] In the twelfth aspect, alone or in combination with one or more of the first to eleventh aspects, process 2000 includes receiving model transmissions from the second network node after completing the RRC establishment process, RRC reconstruction process, or RRC recovery process.

[0205] In the thirteenth aspect, alone or in combination with one or more of the first to twelfth aspects, process 2000 includes sending an indication to update available model information in an RRC establishment completion message, RRC reconstruction completion message, or RRC recovery completion message before receiving the model transmission from the second network node.

[0206] In the fourteenth aspect, communicating with one of the first or second network nodes, either alone or in combination with one or more of the first to thirteenth aspects, includes communicating with the first network node before the handover is performed and communicating with the second network node after the handover process is completed.

[0207] In the fifteenth aspect, receiving a model transmission from one of the first or second network nodes, alone or in combination with one or more of the first to fourteenth aspects, includes receiving a model transmission from the first network node prior to the handover process.

[0208] In the sixteenth aspect, alone or in combination with one or more of the first to fifteenth aspects, process 2000 includes receiving an RRC reconfiguration signal from the first network node after the model transmission process is completed.

[0209] In the seventeenth aspect, receiving a model transmission from one of the first or second network nodes, alone or in combination with one or more of the first to sixteenth aspects, includes receiving a model transmission from the second network node after the handover process is completed.

[0210] In the eighteenth aspect, alone or in combination with one or more of the first to seventeenth aspects, process 2000 includes sending an RRC reconfiguration completion signal to a second network node to update available model information, wherein, after sending the RRC reconfiguration completion signal, model transmission is received from the second network node.

[0211] In the nineteenth aspect, alone or in combination with one or more of the first to eighteenth aspects, process 2000 includes receiving a request for model information from a second network node after the switching process.

[0212] In the twentieth aspect, alone or in combination with one or more of the first to nineteenth aspects, process 2000 includes sending model information to the second network node based at least in part on receiving a request for model information from the second network node.

[0213] In the twenty-first aspect, alone or in combination with one or more of the first to twentieth aspects, process 2000 includes receiving a first configuration and message via a first SRB.

[0214] In the twenty-second aspect, receiving a model transmission from one of the first or second network nodes via RRC signaling, either alone or in combination with one or more of the first to twenty-first aspects, includes receiving a first configuration, a second configuration, and a model transmission from the first network node via a first SRB.

[0215] In the twentieth aspect, alone or in combination with one or more of the first to twenty-second aspects, process 2000 includes receiving a second configuration from a first network node via a first SRB.

[0216] In the 24th aspect, receiving model transmission from one of the first or second network nodes via RRC signaling, either alone or in combination with one or more of the first to 23rd aspects, includes receiving a first configuration and a second configuration from the first network node via a first SRB, and receiving model transmission via a second SRB.

[0217] In aspect 25, either alone or in combination with one or more of aspects 1 to 24, the first SRB has a higher priority than the second SRB.

[0218] In the twenty-sixth aspect, receiving model transmissions from one of the first or second network nodes via RRC signaling, either alone or in combination with one or more of the first to twenty-fifth aspects, includes receiving model transmissions via a second SRB.

[0219] In the twentieth aspect, alone or in combination with one or more of the first to twenty-sixth aspects, process 2000 includes receiving a second configuration via a first SRB when model transmission cannot be completed before the completion of the switching process.

[0220] In the twenty-eighth aspect, alone or in combination with one or more of the first to twenty-seventh aspects, process 2000 includes receiving at least a portion of the second configuration after receiving the model transmission.

[0221] In aspect 29, either alone or in combination with one or more of aspects 1 to 28, the first SRB has a higher priority than the second SRB.

[0222] In the thirtieth aspect, alone or in combination with one or more of the first to twenty-ninth aspects, process 2000 includes receiving the model before receiving the first configuration.

[0223] In the thirty-first aspect, alone or in combination with one or more of the first to thirtieth aspects, process 2000 includes receiving LCM control signals from the second network node.

[0224] In the thirty-second aspect, receiving a model transmission from one of the first or second network nodes via RRC signaling, either alone or in combination with one or more of the first to thirty-first aspects, includes receiving at least a portion of the model transmission from the first network node and at least a portion of the model transmission from the second network node when the model transmission cannot be completed before the handover process is completed.

[0225] In the thirty-third aspect, alone or in combination with one or more of the first to thirty-two aspects, process 2000 includes receiving a second configuration from a first network node or from a second network node.

[0226] In the thirty-fourth aspect, alone or in combination with one or more of the first to thirty-third aspects, process 2000 includes applying a second configuration from the first network node until all model transmissions are received.

[0227] although Figure 20 An example box of process 2000 is shown, but in some aspects, process 2000 may include... Figure 20 The boxes depicted in the diagram are compared to additional boxes, fewer boxes, different boxes, or boxes with different arrangements. Alternatively, two or more boxes in the process 2000 can be executed in parallel.

[0228] Figure 21 This is a diagram illustrating an example process 2100 performed, for example, by a network node according to this disclosure. Example process 2100 is an example in which a network node (e.g., network node 110) performs operations associated with the RRC delivery of an AI / ML model.

[0229] like Figure 21 As shown, in some aspects, process 2100 may include communication with the UE (block 2110). For example, a network node (e.g., using...) Figure 23 The receiving component 2302, the transmitting component 2304, and / or the communication manager 2306 depicted herein can communicate with the UE, as described above.

[0230] like Figure 21 As further shown, in some aspects, process 2100 may include transmitting an AI / ML model to the UE via RRC signaling (box 2120). For example, a network node (e.g., using...) Figure 23 The transmission component 2304 and / or communication manager 2306 described herein can output AI / ML models to the UE via RRC signaling, as described above.

[0231] Process 2100 may include additional aspects, such as any single aspect or any combination of aspects described below and / or in conjunction with one or more other process descriptions described elsewhere herein.

[0232] In the first aspect, process 2100 includes receiving AI / ML model information output by the UE.

[0233] In the second aspect, alone or in combination with the first aspect, process 2100 includes outputting an AI / ML model release instruction to the UE.

[0234] In the third aspect, either alone or in combination with one or more of the first and second aspects, the AI / ML model release instruction configures the UE to release one or more AI / ML models.

[0235] In the fourth aspect, alone or in combination with one or more of the first to third aspects, process 2100 includes receiving an AI / ML model release request from the UE.

[0236] In the fifth aspect, the output of the AI / ML model release instruction occurs, either alone or in combination with one or more of the first to fourth aspects, at least in part based on the receipt of the AI / ML model release request.

[0237] In the sixth aspect, alone or in combination with one or more of the first to fifth aspects, process 2100 includes receiving AI / ML model information from the UE, the model information identifying one or more AI / ML models released by the UE.

[0238] In the seventh aspect, alone or in combination with one or more of the first to sixth aspects, process 2100 includes outputting a request for AI / ML model information to the UE.

[0239] In the eighth aspect, alone or in combination with one or more of the first to seventh aspects, process 2100 includes receiving AI / ML model information based at least in part on a request for AI / ML model information from the output.

[0240] In the ninth aspect, alone or in combination with one or more of the first to eighth aspects, process 2100 includes receiving an RRC recovery request from the UE.

[0241] In the tenth aspect, alone or in combination with one or more of the first to ninth aspects, the output model delivery includes at least in part based on receiving an RRC recovery request to output an AI / ML model delivery.

[0242] In the eleventh aspect, alone or in combination with one or more of the first to tenth aspects, process 2100 includes outputting an RRC recovery signal or an RRC establishment signal to the UE after receiving the RRC recovery request and before outputting the AI / ML model.

[0243] In the twelfth aspect, alone or in combination with one or more of the first to eleventh aspects, process 2100 includes receiving a UE context response.

[0244] In the thirteenth aspect, alone or in combination with one or more of the first to twelfth aspects, the output RRC recovery signal or RRC establishment signal is based at least in part on the received UE context response.

[0245] In the fourteenth aspect, alone or in combination with one or more of the first to thirteenth aspects, process 2100 includes outputting an RRC recovery completion signal or an RRC establishment completion signal to the UE before outputting the AI / ML model.

[0246] In the fifteenth aspect, communication with the UE occurs, either alone or in combination with one or more of the first to fourteenth aspects, at least in part based on the handover process.

[0247] In the sixteenth aspect, alone or in combination with one or more of the first to fifteenth aspects, process 2100 includes outputting an RRC reconfiguration signal to the UE after the handover process is completed.

[0248] In the seventeenth aspect, alone or in combination with one or more of the first to sixteenth aspects, output model transmission includes output model transmission after the switching process is completed.

[0249] In the eighteenth aspect, alone or in combination with one or more of the first to seventeenth aspects, process 2100 includes receiving an RRC reconfiguration completion signal, wherein the AI / ML model transmission to the UE is based at least in part on receiving the RRC reconfiguration completion signal.

[0250] In the nineteenth aspect, alone or in combination with one or more of the first to eighteenth aspects, process 2100 includes outputting a request for AI / ML model information to the UE after the handover process is completed.

[0251] In the twentieth aspect, alone or in combination with one or more of the first to nineteenth aspects, process 2100 includes receiving AI / ML model information based at least in part on a request for AI / ML model information from the output.

[0252] In the twenty-first aspect, alone or in combination with one or more of the first to twentieth aspects, process 2100 includes outputting a first configuration to the UE via a first SRB.

[0253] In the twentieth aspect, the transmission of AI / ML models to the UE via RRC signaling, either alone or in combination with one or more of the first to twenty-first aspects, includes the transmission of AI / ML models to the UE via the first SRB.

[0254] In the twenty-third aspect, alone or in combination with one or more of the first to twenty-second aspects, process 2100 includes outputting a second configuration to the UE via the first SRB.

[0255] In the 24th aspect, the transmission of AI / ML model to the UE via RRC signaling, either alone or in combination with one or more of the first to 23rd aspects, includes the transmission of the second configuration via the first SRB and the transmission of AI / ML model via the second SRB.

[0256] In aspect 25, either alone or in combination with one or more of aspects 1 to 24, the first SRB has a higher priority than the second SRB.

[0257] In the twenty-sixth aspect, the AI / ML model transmission to the UE via RRC signaling, either alone or in combination with one or more of the first to twenty-fifth aspects, includes the transmission of the AI / ML model via the second SRB.

[0258] In the twenty-seventh aspect, alone or in combination with one or more of the first to twenty-sixth aspects, outputting the first configuration includes outputting at least a portion of the first configuration via the first SRB.

[0259] In the twenty-eighth aspect, alone or in combination with one or more of the first to twenty-seventh aspects, process 2100 includes outputting at least a portion of the second configuration after the output model is transmitted.

[0260] In aspect 29, either alone or in combination with one or more of aspects 1 to 28, the first SRB has a higher priority than the second SRB.

[0261] In the thirtieth aspect, either alone or in combination with one or more of the first to twenty-ninth aspects, the delivery of the output AI / ML model occurs before the output of the first configuration.

[0262] In the thirty-first aspect, either alone or in combination with one or more of the first to thirtieth aspects, the output AI / ML model transmission to the UE via RRC signaling includes at least a portion of the output AI / ML model transmission.

[0263] In aspect thirty-two, alone or in combination with one or more of aspects one through thirty-one, process 2100 includes outputting an LCM control signal.

[0264] In aspect 33, alone or in combination with one or more of aspects 1 to 32, process 2100 includes determining the transmission of an incomplete AI / ML model to the UE.

[0265] In the thirty-fourth aspect, alone or in combination with one or more of the first to thirty-third aspects, process 2100 includes outputting an incomplete model transmission indication to a target network node based at least in part on determining the incomplete AI / ML model transmission to the UE.

[0266] In aspect thirty-five, alone or in combination with one or more of aspects one through thirty-four, process 2100 includes at least in part outputting an incomplete AI / ML model transmission instruction to the AMF based on determining the incomplete AI / ML model transmission to the UE.

[0267] In the thirty-sixth aspect, alone or in combination with one or more of the first to thirty-fifth aspects, process 2100 includes updating the available AI / ML model information in the UE context at one or more locations in the UE or network node.

[0268] although Figure 21 An example box of process 2100 is shown, but in some aspects, process 2100 may include... Figure 21The boxes depicted in the diagram are compared to additional boxes, fewer boxes, different boxes, or boxes with different arrangements. Alternatively, two or more boxes in the process 2100 can be executed in parallel.

[0269] Figure 22 This is a diagram of an example device 2200 for wireless communication according to this disclosure. Device 2200 may be a UE, or a UE may include device 2200. In some aspects, device 2200 includes a receiving component 2202, a transmitting component 2204, and / or a communication manager 2206, which may communicate with each other (e.g., via one or more buses and / or one or more other components). In some aspects, communication manager 2206 is combined with... Figure 1 The communication manager 140 is described. As shown, the device 2200 can communicate with other devices 2208 (such as UEs or network nodes (such as CUs, DUs, RUs or base stations)) using the receiving component 2202 and the transmitting component 2204.

[0270] In some respects, device 2200 can be configured to perform the functions described herein. Figures 4-19 One or more operations described herein. Alternatively or concurrently, device 2200 may be configured to perform one or more processes described herein, such as Figure 20 The process 2000. In some respects, Figure 22 The device 2200 and / or one or more components shown may include a combination Figure 2 One or more components of the UE as described. Alternatively or in addition, Figure 22 One or more components shown can be combined Figure 2 Implementation within one or more components described. Alternatively or additionally, one or more components in the set of components may be implemented at least partially as software stored in memory. For example, a component (or a portion thereof) may be implemented as instructions or code stored in a non-transitory computer-readable medium and executable by a controller or processor to perform the function or operation of the component.

[0271] Receiver 2202 may receive communications from device 2208, such as reference signals, control information, data communications, or combinations thereof. Receiver 2202 may provide the received communications to one or more other components of device 2200. In some aspects, receiver 2202 may perform signal processing (such as filtering, amplification, demodulation, analog-to-digital conversion, demultiplexing, deinterleaving, demapping, equalization, interference cancellation, or decoding) on ​​the received communications, and may provide the processed signals to one or more other components of device 2200. In some aspects, receiver 2202 may include combinations of... Figure 2The described UE includes one or more antennas, modems, demodulators, MIMO detectors, receiver processors, controllers / processors, memory, or combinations thereof.

[0272] The transmission component 2204 can send communications, such as reference signals, control information, data communications, or combinations thereof, to the device 2208. In some aspects, one or more other components of the device 2200 can generate communications and provide the generated communications to the transmission component 2204 for transmission to the device 2208. In some aspects, the transmission component 2204 can perform signal processing (e.g., filtering, amplification, modulation, digital-to-analog conversion, multiplexing, interleaving, mapping, or encoding, etc.) on the generated communications and can send the processed signals to the device 2208. In some aspects, the transmission component 2204 can include combinations of... Figure 2 The described UE includes one or more antennas, modems, modulators, transmit MIMO processors, transmit processors, controllers / processors, memory, or combinations thereof. In some aspects, the transmit component 2204 may be co-located with the receive component 2202 in a transceiver.

[0273] The communication manager 2206 can support the operation of the receiving component 2202 and / or the transmitting component 2204. For example, the communication manager 2206 can receive information associated with configuring the receiving component 2202 to receive communication and / or the transmitting component 2204 to transmit communication. Additionally or alternatively, the communication manager 2206 can generate and / or provide control information to the receiving component 2202 and / or the transmitting component 2204 to control the reception and / or transmission of communication.

[0274] The receiving component 2202 and / or the transmitting component 2204 can communicate with one of the first or second network nodes to update the available model information in the UE context at one or more of the first or second network nodes. The receiving component 2202 can receive model transmissions from one of the first or second network nodes via RRC signaling.

[0275] Transmission component 2204 can send model information to a first network node. Receiving component 2202 can receive a model release command from the first network node. Communication manager 2206 can release one or more models indicated in the model release command. Communication manager 2206 can release one or more models without an instruction from the first network node. Transmission component 2204 can send updated model information to the first network node, indicating that one or more models are available or have been released. Receiving component 2202 can receive a request for available model information from the first network node. Transmission component 2204 can send model information to the first network node in response to the request for model information. Transmission component 2204 can send an RRC recovery request to a second network node. Receiving component 2202 can receive an RRC recovery signal or an RRC establishment signal from the second network node after sending the RRC recovery request and before receiving model transmission from the second network node. Transmission component 2204 can send an indication of updated available model information in an RRC establishment completion message, RRC reconstruction completion message, or RRC recovery completion message before receiving model transmission from the second network node. The receiving component 2202 can receive an RRC reconfiguration signal from the first network node after completing the model transmission process. The transmitting component 2204 can send an RRC reconfiguration completion signal to the second network node to update the available model information, wherein the model transmission is received from the second network node after sending the RRC reconfiguration completion signal. The receiving component 2202 can receive a request for model information from the second network node after the handover process. The transmitting component 2204 can send model information to the second network node based at least in part on the request for model information received from the second network node. The receiving component 2202 can receive a first configuration via a first SRB. The receiving component 2202 can receive a second configuration from the first network node via the first SRB. The receiving component 2202 can receive at least a portion of the second configuration after receiving the model transmission. The receiving component 2202 can receive LCM control signals from the second network node. The receiving component 2202 can receive the second configuration from either the first network node or the second network node. The communication manager 2206 can apply the second configuration from the first network node until all model transmissions have been received.

[0276] Figure 22 The number and arrangement of components shown are provided as an example. In practice, different arrangements may exist. Figure 22 The components shown are compared to additional components, fewer components, different components, or components with different arrangements. Furthermore, Figure 22 The two or more components shown can be implemented within a single component, or Figure 22 The single component shown can be implemented as multiple, distributed components. Additionally or alternatively, Figure 22 The collection of (one or more) components shown can perform actions described as being performed by Figure 22 The other set of components shown performs one or more functions.

[0277] Figure 23 This is a diagram of an example device 2300 for wireless communication according to the present disclosure. Device 2300 may be a network node, or a network node may include device 2300. In some aspects, device 2300 includes a receiving component 2302, a transmitting component 2304, and / or a communication manager 2306, which can communicate with each other (e.g., via one or more buses and / or one or more other components). In some aspects, communication manager 2306 is combined with... Figure 1 The communication manager 150 is described. As shown, the device 2300 can communicate with other devices 2308 (such as UEs or network nodes (such as CUs, DUs, RUs or base stations)) using the receiving component 2302 and the transmitting component 2304.

[0278] In some respects, device 2300 can be configured to perform the functions described herein. Figures 4-19 One or more operations described herein. Alternatively or concurrently, device 2300 may be configured to perform one or more processes described herein, such as Figure 21 The process 2100. In some respects, Figure 23 The device 2300 and / or one or more components shown may include a combination Figure 2 One or more components of the described network node. Alternatively, Figure 23 One or more components shown can be combined Figure 2 Implementation within one or more components described. Alternatively or additionally, one or more components in the set of components may be implemented at least partially as software stored in memory. For example, a component (or a portion thereof) may be implemented as instructions or code stored in a non-transitory computer-readable medium and executable by a controller or processor to perform the function or operation of the component.

[0279] Receiver 2302 may receive communications from device 2308, such as reference signals, control information, data communications, or combinations thereof. Receiver 2302 may provide the received communications to one or more other components of device 2300. In some aspects, receiver 2302 may perform signal processing (such as filtering, amplification, demodulation, analog-to-digital conversion, demultiplexing, deinterleaving, demapping, equalization, interference cancellation, or decoding) on ​​the received communications, and may provide the processed signals to one or more other components of device 2300. In some aspects, receiver 2302 may include combinations of... Figure 2The described network node includes one or more antennas, modems, demodulators, MIMO detectors, receiver processors, controllers / processors, memory, or combinations thereof. In some aspects, receiver component 2302 and / or transmitter component 2304 may include or be included in a network interface. The network interface may be configured to acquire and / or output signals for device 2300 via one or more communication links, such as backhaul links, midhaul links, and / or fronthaul links.

[0280] The transmission component 2304 can send communications, such as reference signals, control information, data communications, or combinations thereof, to the device 2308. In some aspects, one or more other components of the device 2300 can generate communications and provide the generated communications to the transmission component 2304 for transmission to the device 2308. In some aspects, the transmission component 2304 can perform signal processing (e.g., filtering, amplification, modulation, digital-to-analog conversion, multiplexing, interleaving, mapping, or encoding, etc.) on the generated communications and can send the processed signals to the device 2308. In some aspects, the transmission component 2304 can include combinations of... Figure 2 The described network node includes one or more antennas, modems, modulators, transmit MIMO processors, transmit processors, controllers / processors, memory, or combinations thereof. In some aspects, the transmit component 2304 may be co-located with the receive component 2302 in a transceiver.

[0281] The communication manager 2306 can support the operation of the receiving component 2302 and / or the transmitting component 2304. For example, the communication manager 2306 can receive information associated with configuring the receiving component 2302 to receive communication and / or the transmitting component 2304 to transmit communication. Additionally or alternatively, the communication manager 2306 can generate and / or provide control information to the receiving component 2302 and / or the transmitting component 2304 to control the reception and / or transmission of communication.

[0282] The receiving component 2302 and / or the transmitting component 2304 can communicate with the UE. The transmitting component 2304 can output model transmission to the UE via RRC signaling. The receiving component 2302 can receive model information output by the UE. The transmitting component 2304 can output a model release command to the UE. The receiving component 2302 can receive a model release request from the UE. The receiving component 2302 can receive model information from the UE, which identifies one or more models released by the UE. The transmitting component 2304 can output a request for model information to the UE. The receiving component 2302 can receive model information at least in part based on the output request for model information. The receiving component 2302 can receive an RRC recovery request from the UE. The transmitting component 2304 can output an RRC recovery signal or an RRC establishment signal to the UE after receiving the RRC recovery request and before outputting the model. The receiving component 2302 can receive a UE context response. The transmitting component 2304 can output an RRC recovery complete signal or an RRC establishment complete signal to the UE before outputting the model. The transmission component 2304 may output an RRC reconfiguration signal to the UE after the handover process is completed. The receiving component 2302 may receive an RRC reconfiguration completion signal, wherein model transmission is output to the UE at least in part based on the receipt of the RRC reconfiguration completion signal. The transmission component 2304 may output a request for model information to the UE after the handover process is completed.

[0283] The receiving component 2302 can receive model information at least partially based on an output request for model information. The transmitting component 2304 can output a first configuration to the UE via a first SRB. The transmitting component 2304 can output a second configuration to the UE via the first SRB. The transmitting component 2304 can output at least a portion of the second configuration after outputting the model. The transmitting component 2304 can output an LCM control signal. The communication manager 2306 can determine the incomplete model transmission to the UE. The transmitting component 2304 can output an incomplete model transmission instruction to the target network node at least partially based on the determination of the incomplete model transmission to the UE. The transmitting component 2304 can output an incomplete model transmission instruction to the AMF at least partially based on the determination of the incomplete model transmission to the UE. The communication manager 2306 can update the available model information in the UE context at one or more locations in the UE or network node.

[0284] Figure 23 The number and arrangement of components shown are provided as an example. In practice, different arrangements may exist. Figure 23 The components shown are compared to additional components, fewer components, different components, or components with different arrangements. Furthermore, Figure 23 The two or more components shown can be implemented within a single component, or Figure 23The single component shown can be implemented as multiple, distributed components. Additionally or alternatively, Figure 23 The collection of (one or more) components shown can perform actions described as being performed by Figure 23 The other set of components shown performs one or more functions.

[0285] The following provides an overview of some aspects of this disclosure:

[0286] Aspect 1: A method of wireless communication performed by a UE, comprising: communicating with one of a first network node or a second network node to update available model information in the UE context at one or more of the first network node or the second network node; and receiving a model transmission from one of the first network node or the second network node via RRC signaling.

[0287] Aspect 2: The method described in aspect 1 further includes sending model information to the first network node.

[0288] Aspect 3: The method according to aspect 2 further includes receiving a model release instruction from the first network node.

[0289] Aspect 4: The method according to aspect 3 further includes one or more models indicated in the release model release instruction.

[0290] Aspect 5: The method described in aspect 3 further includes sending a model release request to the first network node.

[0291] Aspect 6: According to the method of aspect 5, the receiving of the model release instruction occurs after sending the model release request to the first network node.

[0292] Aspect 7: The method according to any one of Aspects 1-6 further includes releasing one or more models without instruction from the first network node.

[0293] Aspect 8: The method according to aspect 7 further includes sending available model information to a first network node, the model information indicating that one or more models are available or have been released.

[0294] Aspect 9: The method according to any one of aspects 1-8 further includes receiving a request for model information from the first network node.

[0295] Aspect 10: The method according to aspect 9 further includes sending model information to the first network node in response to a request for model information.

[0296] Aspect 11: The method according to any one of Aspects 1-10 further includes sending an RRC recovery request to the second network node.

[0297] Aspect 12: According to the method of aspect 11, receiving the model transmission includes receiving the model transmission from the second network node based at least in part on sending an RRC recovery request to the second network node.

[0298] Aspect 13: The method according to aspect 12 further includes receiving the model transmission from the second network node after the completion of the RRC establishment process, RRC reconstruction process or RRC recovery process.

[0299] Aspect 14: The method according to aspect 12 further includes sending an instruction to the second network node in an RRC establishment completion message, RRC reconstruction completion message, or RRC recovery completion message to update the available model information before receiving the model transmission from the second network node.

[0300] Aspect 15: The method according to any one of Aspects 1-14, wherein communicating with one of the first network node or the second network node includes communicating with the first network node before the handover is performed and communicating with the second network node after the handover process is completed.

[0301] Aspect 16: According to the method of aspect 15, receiving a model transmission from one of the first network node or the second network node includes receiving a model transmission from the first network node before the handover process.

[0302] Aspect 17: The method according to aspect 15 further includes receiving an RRC reconfiguration signal from the first network node after the model transmission process is completed.

[0303] Aspect 18: According to the method of aspect 15, receiving a model transmission from one of the first network node or the second network node includes receiving a model transmission from the second network node after the handover process.

[0304] Aspect 19: The method according to aspect 18 further includes: sending an RRC reconfiguration completion signal to a second network node to update available model information, wherein the model transfer is received from the second network node after the RRC reconfiguration completion signal is sent.

[0305] Aspect 20: The method according to aspect 15 further includes receiving a request for model information from a second network node after the switching process.

[0306] Aspect 21: The method according to aspect 20 further includes sending model information to the second network node at least in part based on a request for model information received from the second network node.

[0307] Aspect 22: The method according to any one of aspects 1-21 further includes receiving a first configuration via a first SRB.

[0308] Aspect 23: According to the method of aspect 22, receiving a model transmission from one of the first network node or the second network node via RRC signaling includes receiving a first configuration, a second configuration, and a model transmission from the first network node via a first SRB.

[0309] Aspect 24: The method according to aspect 23 further includes receiving a second configuration from a first network node via a first SRB.

[0310] Aspect 25: According to the method of aspect 22, receiving model transmission from one of the first network node or the second network node via RRC signaling includes receiving a first configuration and a second configuration from the first network node via a first SRB, and receiving model transmission via a second SRB.

[0311] Aspect 26: According to the method described in aspect 25, the first SRB has a higher priority than the second SRB.

[0312] Aspect 27: According to the method of aspect 22, receiving model transmission from one of the first network node or the second network node via RRC signaling includes receiving model transmission via a second SRB.

[0313] Aspect 28: According to the method of aspect 27, receiving the first configuration includes receiving the second configuration via the first SRB when the model transfer cannot be completed before the handover process is completed.

[0314] Aspect 29: The method according to aspect 28 further includes receiving at least a portion of the second configuration after receiving the model transmission.

[0315] Aspect 30: The method according to aspect 28, wherein the first SRB has a higher priority than the second SRB.

[0316] Aspect 31: According to the method of aspect 22, the receiving model occurs before the first configuration is received.

[0317] Aspect 32: The method according to aspect 24 further includes receiving an LCM control signal from a second network node.

[0318] Aspect 33: According to the method of aspect 22, receiving a model transmission from one of the first network node or the second network node via RRC signaling includes receiving at least a portion of the model transmission from the first network node and at least a portion of the model transmission from the second network node when the model transmission cannot be completed before the handover process is completed.

[0319] Aspect 34: The method according to aspect 33 further includes receiving a second configuration from a first network node or from a second network node.

[0320] Aspect 35: The method according to aspect 34 further includes applying a second configuration from the first network node until all model transmissions are received.

[0321] Aspect 36: A method for wireless communication performed by a network node, comprising: communicating with a UE; and transmitting an AI / ML model to the UE via RRC signaling.

[0322] Aspect 37: The method according to aspect 36 further includes receiving AI / ML model information output by the UE.

[0323] Aspect 38: The method described in aspect 37 further includes outputting an AI / ML model release command to the UE.

[0324] Aspect 39: According to the method described in aspect 38, wherein the AI / ML model release instruction configures the UE to release one or more AI / ML models.

[0325] Aspect 40: The method according to aspect 38 further includes receiving an AI / ML model release request from the UE.

[0326] Aspect 41: According to the method of aspect 40, the output of the AI / ML model release instruction occurs at least in part based on the receipt of the AI / ML model release request.

[0327] Aspect 42: The method according to any one of Aspects 36-41 further includes receiving model information from the UE, wherein the AI / ML model information identifies one or more AI / ML models released by the UE.

[0328] Aspect 43: The method according to any one of aspects 36-42 further includes outputting a request for AI / ML model information to the UE.

[0329] Aspect 44: The method according to aspect 43 further includes receiving AI / ML model information at least in part based on a request for AI / ML model information output.

[0330] Aspect 45: The method according to any one of aspects 36-44 further includes receiving an RRC recovery request from the UE.

[0331] Aspect 46: The method according to aspect 45, wherein the output AI / ML model transmission includes at least in part based on receiving an RRC recovery request to output the AI / ML model transmission.

[0332] Aspect 47: The method according to aspect 46 further includes outputting an RRC recovery signal or an RRC establishment signal to the UE after receiving the RRC recovery request and before outputting the AI / ML model.

[0333] Aspect 48: The method according to aspect 47 further includes receiving a UE context response.

[0334] Aspect 49: The method according to aspect 48, wherein the output RRC recovery signal or RRC establishment signal is based at least in part on the received UE context response.

[0335] Aspect 50: The method according to aspect 46 further includes outputting an RRC recovery completion signal or an RRC establishment completion signal to the UE before transmitting the output AI / ML model.

[0336] Aspect 51: The method according to any one of aspects 36-50, wherein communication with the UE occurs at least in part based on the handover process.

[0337] Aspect 52: The method according to aspect 51 further includes outputting an RRC reconfiguration signal to the UE after the handover process is completed.

[0338] Aspect 53: According to the method of aspect 51, wherein the output AI / ML model transmission includes outputting the AI / ML model transmission after the switching process is completed.

[0339] Aspect 54: The method according to aspect 53 further includes receiving an RRC reconfiguration completion signal, wherein the AI / ML model transmission is output to the UE at least in part based on receiving the RRC reconfiguration completion signal.

[0340] Aspect 55: The method according to aspect 51 further includes outputting a request for AI / ML model information to the UE after the handover process is completed.

[0341] Aspect 56: The method according to aspect 55 further includes receiving AI / ML model information based at least in part on the output of a request for AI / ML model information.

[0342] Aspect 57: The method according to any one of aspects 36-56 further includes outputting a first configuration to the UE via a first SRB.

[0343] Aspect 58: According to the method of aspect 57, the transmission of AI / ML model to UE via RRC signaling includes the transmission of AI / ML model to UE via a first SRB.

[0344] Aspect 59: The method according to aspect 58 further includes outputting a second configuration to the UE via a first SRB.

[0345] Aspect 60: According to the method of aspect 57, the transmission of AI / ML model to UE via RRC signaling includes the transmission of first configuration and second configuration via first SRB and the transmission of AI / ML model via second SRB.

[0346] Aspect 61: According to the method of aspect 60, the first SRB has a higher priority than the second SRB.

[0347] Aspect 62: According to the method of aspect 57, wherein the transmission of AI / ML model to the UE via RRC signaling includes transmission of model via a second SRB.

[0348] Aspect 63: The method according to aspect 62, wherein outputting the first configuration includes outputting at least a portion of the first configuration via the first SRB.

[0349] Aspect 64: The method according to aspect 63 further includes outputting at least a portion of the second configuration after the output AI / ML model is transmitted.

[0350] Aspect 65: According to the method of aspect 63, wherein the first SRB has a higher priority than the second SRB.

[0351] Aspect 66: According to the method described in aspect 57, the output model transmission occurs before the output of the first configuration.

[0352] Aspect 67: The method according to any one of Aspects 36-66, wherein the output AI / ML model transmission to the UE via RRC signaling includes at least a portion of the output AI / ML model transmission.

[0353] Aspect 68: The method according to any one of aspects 36-67 further includes outputting an LCM control signal.

[0354] Aspect 69: The method according to aspect 38 further includes determining the transmission of an incomplete AI / ML model to the UE.

[0355] Aspect 70: The method according to aspect 69 further includes, at least in part, outputting an incomplete AI / ML model transmission indication to a target network node based on determining the incomplete AI / ML model transmission to the UE.

[0356] Aspect 71: The method according to aspect 69 further includes, at least in part, outputting an incomplete AI / ML model transmission indication to the Access and Mobility Management Function (AMF) based on determining the incomplete AI / ML model transmission to the UE.

[0357] Aspect 72: The method according to any one of aspects 36-71 further includes updating the available model information in the UE context at one or more locations in the UE or network node.

[0358] Aspect 73: An apparatus for wireless communication at a device, comprising a processor; a memory coupled to the processor; and instructions stored in the memory and executable by the processor to cause the apparatus to perform the method according to one or more of aspects 1-72.

[0359] Aspect 74: An apparatus for wireless communication, comprising a memory and one or more processors coupled to the memory, the one or more processors being configured to perform the method described in one or more of aspects 1-72.

[0360] Aspect 75: An apparatus for wireless communication, comprising at least one component for performing the method according to one or more of aspects 1-72.

[0361] Aspect 76: A non-transitory computer-readable medium storing code for wireless communication, the code including instructions executable by a processor to perform the methods described in one or more of aspects 1-72.

[0362] Aspect 77: A non-transitory computer-readable medium storing a set of instructions for wireless communication, the set of instructions including one or more instructions which, when executed by one or more processors of a device, cause the device to perform the method described in one or more of aspects 1-72.

[0363] The foregoing disclosure provides illustrations and descriptions, but is not intended to be exhaustive or to limit the aspects to the precise forms disclosed. Modifications and variations can be made based on the foregoing disclosure, or from practice of the aspects.

[0364] As used herein, the term "component" is intended to be interpreted broadly as hardware and / or a combination of hardware and software. Whether referred to as software, firmware, middleware, microcode, hardware description language, or other terms, "software" should be interpreted broadly as instructions, instruction sets, code, code segments, program code, programs, subroutines, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, and / or functions. As used herein, a "processor" is implemented in hardware and / or a combination of hardware and software. It will be apparent that the systems and / or methods described herein can be implemented in various forms of hardware and / or combinations of hardware and software. The actual dedicated control hardware or software code used to implement these systems and / or methods does not limit these aspects. Therefore, this document describes the operation and behavior of systems and / or methods without reference to any specific software code, as those skilled in the art will understand that software and hardware can be designed to implement systems and / or methods, at least in part, based on the descriptions herein.

[0365] As used in this article, depending on the context, "meeting the threshold" can mean a value greater than the threshold, greater than or equal to the threshold, less than the threshold, less than or equal to the threshold, equal to the threshold, not equal to the threshold, etc.

[0366] Even if a specific combination of features is described in the claims and / or disclosed in the specification, such combinations are not intended to limit the disclosure of the aspects. Many of these features can be combined in ways not specifically described in the claims and / or not specifically disclosed in the specification. The disclosure of aspects includes combinations of each dependent claim with each other claim in the claim set. As used herein, the phrase “at least one” in the list of items refers to any combination of these items, including a single member. As an example, “at least one of a, b, or c” is intended to cover a, b, c, a+b, a+c, b+c, and a+b+c, as well as any combination with multiple identical elements (e.g., a+a, a+a+a, a+a+b, a+a+c, a+b+b, a+c+c, b+b, b+b+b, b+b+c, c+c, and c+c+c, or any other ordering of a, b, and c).

[0367] Unless explicitly stated otherwise, the elements, actions, or instructions used herein should not be construed as critical or necessary. Furthermore, as used herein, the articles “a” and “one” are intended to include one or more items and may be used interchangeably with “one or more.” Furthermore, as used herein, the article “the” is intended to include one or more items referenced in combination with the article “the” and may be used interchangeably with “one or more.” Furthermore, as used herein, the terms “set” and “group” are intended to include one or more items and may be used interchangeably with “one or more.” Where only one item is referred to, the phrase “only one” or similar language is used. Furthermore, as used herein, the terms “have,” “possess,” “own,” etc., are intended to be open-ended terms that do not limit the elements they modify (e.g., an element “having” A may also have B). Furthermore, unless explicitly stated otherwise, the phrase “based on” is intended to mean “at least partially based on.” Furthermore, as used herein, the term “or” when used in series is intended to be inclusive and may be used interchangeably with “and / or” unless explicitly stated otherwise (e.g., if used in combination with “either” or “only one of”).

Claims

1. A user equipment (UE) for wireless communication, comprising: Memory; as well as One or more processors are coupled to the memory, said one or more processors being configured to: Communicate with one of the first network nodes or the second network nodes to update the available model information in the UE context at one or more of the first network nodes or the second network nodes; as well as The model transmission is received from one of the first or second network nodes via Radio Resource Control (RRC) signaling.

2. The UE according to claim 1, wherein, The one or more processors are also configured to send available model information to the first network node.

3. The UE according to claim 1, wherein, The one or more processors are also configured to receive a model release instruction from the first network node.

4. The UE according to claim 3, wherein, The one or more processors are also configured to release one or more models indicated in the model release instruction.

5. The UE according to claim 3, wherein, The one or more processors are further configured to: Send a model release request to the first network node. The receipt of the model release instruction occurs after the model release request is sent to the first network node.

6. The UE according to claim 1, wherein, The one or more processors are further configured to: Release one or more models without instruction from the first network node; and The updated model information is sent to the first network node, indicating that the one or more models are available or have been released.

7. The UE according to claim 1, wherein, The RRC signaling includes one or more of an RRC establishment message, an RRC reconstruction message, or an RRC recovery message, and wherein, in order to receive the model transmission via the RRC signaling, the one or more processors are configured to receive the model transmission from the second network node as a result of sending an RRC establishment request, an RRC reconstruction request, or an RRC recovery request to the second network node.

8. The UE according to claim 7, wherein, The one or more processors are further configured to receive the model transmission from the second network node after completing the RRC establishment process, RRC reconstruction process, or RRC recovery process.

9. The UE according to claim 7, wherein, The one or more processors are further configured to send an indication of updated available model information in an RRC establishment complete message, RRC reconstruction complete message, or RRC recovery complete message before receiving the model transmission from the second network node.

10. The UE according to claim 1, wherein, In order to communicate with one of the first network node or the second network node, the one or more processors are configured to communicate with the first network node before the handover is executed and with the second network node after the handover is executed. Communication with the first network node and communication with the second network node include model transmission information.

11. The UE according to claim 10, wherein, In order to receive the model transmission from one of the first network node or the second network node, the one or more processors are configured to receive the model from the first network node before the switching is performed.

12. The UE according to claim 10, wherein, The one or more processors are also configured to receive an RRC reconfiguration signal from the first network node after the model transfer process is completed.

13. The UE according to claim 10, wherein, To receive the model transmission from one of the first network node or the second network node, the one or more processors are configured to: The model is received from the second network node after the switch is executed; and Send an RRC reconfiguration complete signal to the second network node to update the available model information. The model is received from the second network node after the RRC reconfiguration completion signal is sent.

14. The UE according to claim 10, wherein, The one or more processors are further configured to: After the switch is executed, a request for available model information is received from the second network node; and The available model information is sent to the second network node, at least in part, based on the request for model information received from the second network node.

15. The UE according to claim 10, wherein, The one or more processors are configured to receive lifecycle management control signals from the second network node after a handover from the first network node to the second network node is executed.

16. The UE according to claim 1, wherein, The one or more processors are also configured to receive a first configuration and message via a first signaling radio bearer (SRB).

17. The UE according to claim 16, wherein, To receive the model transmission from one of the first or second network nodes via RRC signaling, the one or more processors are configured to: Receive the second configuration from the first network node; as well as The second configuration from the first network node is applied until all of the model transmissions are received.

18. The UE according to claim 16, wherein, In order to receive the model transmission from one of the first network node or the second network node via RRC signaling, the one or more processors are configured to receive the first configuration, the second configuration, and the model transmission from the first network node via the first SRB.

19. The UE according to claim 16, wherein, In order to receive the model transmission from one of the first network node or the second network node via RRC signaling, the one or more processors are configured to receive a first configuration and a second configuration from the first network node via the first SRB, and to receive the model transmission via the second SRB.

20. The UE according to claim 16, wherein, The one or more processors are configured to receive a second configuration via the first SRB when the model transfer cannot be completed before the switching process is executed.

21. The UE according to claim 16, wherein, In order to receive the model transmission from one of the first network node or the second network node via RRC signaling, the one or more processors are configured to receive at least a portion of the model transmission from the first network node and at least a portion of the model transmission from the second network node when the model transmission cannot be completed before a handover process is performed.

22. The UE according to claim 16, wherein, The one or more processors are configured to receive the model before receiving the first configuration.

23. A network node for wireless communication, comprising: Memory; as well as One or more processors are coupled to the memory, said one or more processors being configured to: Communicating with user equipment (UE); The artificial intelligence or machine learning (AI / ML) model is transmitted to the UE via radio resource control (RRC) signaling; Receive an AI / ML model release request from the UE; as well as Output an AI / ML model release command to the UE to configure the UE to release one or more AI / ML models.

24. The network node according to claim 23, wherein, The one or more processors are also configured to output a first configuration and message to the UE via a first signaling radio bearer (SRB). Specifically, in order to transmit the AI / ML model to the UE via RRC signaling, the one or more processors are configured to transmit the AI / ML model to the UE via the first SRB.

25. The network node according to claim 23, wherein, In order to output the AI / ML model transmission to the UE via RRC signaling, the one or more processors are configured to output at least a portion of the model transmission.

26. A method for wireless communication performed by a user equipment (UE), comprising: Communicate with one of the first network nodes or the second network nodes to update the available artificial intelligence or machine learning (AI / ML) model information in the UE context at one or more of the first network nodes or the second network nodes; as well as AI / ML model transmissions are received from one of the first or second network nodes via Radio Resource Control (RRC) signaling.

27. The method of claim 26, further comprising: Send an AI / ML model release request to the first network node; as well as After sending the AI / ML model release request to the first network node, the AI / ML model release instruction is received.

28. The method according to claim 26, wherein, Receiving the AI / ML model transmission from one of the first network node or the second network node includes: Receive configuration from the first network node; and The configuration from the first network node is applied until all of the AI / ML model transmitted is received.

29. A method for wireless communication performed by a network node, comprising: Communicating with user equipment (UE); The artificial intelligence or machine learning (AI / ML) model is transmitted to the UE via radio resource control (RRC) signaling; Receive an AI / ML model release request from the UE; and Output an AI / ML model release command to the UE. The AI / ML model release instruction configures the UE to release one or more AI / ML models.

30. The method of claim 29, further comprising configuring the UE to: Receive configuration; and Apply the configuration until the UE receives all of the AI / ML model transmitted.

Images