RRC process design for wireless ai / ml

Abstract

There is provided an apparatus of a user equipment (UE), the apparatus comprising: a processor; and a memory storing instructions that, when executed by the processor, configure the apparatus to: receive an artificial intelligence (AI) model from a base station; obtaining a trained AI model resulting from the training of the AI model; and transmitting the trained AI model to the base station via an uplink radio resource control (RRC) message.

Description

Technical Field

[0001] The present application generally relates to wireless communication systems, including providing a radio resource control (RRC) process design for wireless artificial intelligence (AI) or machine learning (ML), for example in a 5G communication system. Background Art

[0002] Wireless mobile communication technology uses various standards and protocols to send data between base stations and wireless communication devices. Wireless communication system standards and protocols may include, for example, the 3rd Generation Partnership Project (3GPP) Long Term Evolution (LTE) (e.g., 4G), 3GPP New Radio (NR) (e.g., 5G), and the IEEE 802.11 standard for wireless local area networks (WLANs) (commonly referred to within industry organizations as WLANs). ).

[0003] As envisioned by 3GPP, different wireless communication system standards and protocols may use various radio access networks (RANs) to communicate between base stations of the RAN (which may also sometimes be referred to as RAN nodes, network nodes, or simply nodes) and wireless communication devices referred to as user equipment (UE). 3GPP RANs may include, for example, Global System for Mobile Communications (GSM), Enhanced Data Rates for GSM Evolution (EDGE) RAN (GERAN), Universal Terrestrial Radio Access Network (UTRAN), Evolved Universal Terrestrial Radio Access Network (E-UTRAN), and / or Next Generation Radio Access Network (NG-RAN).

[0004] Each RAN may use one or more radio access technologies (RATs) to perform communications between base stations and UEs. For example, GERAN implements GSM and / or EDGE RAT, UTRAN implements Universal Mobile Telecommunications System (UMTS) RAT or other 3GPP RAT, E-UTRAN implements LTE RAT (sometimes referred to as LTE), and NG-RAN implements NR RAT (sometimes referred to as 5G RAT, 5G NR RAT, or NR in this document). In some deployments, E-UTRAN may also implement NR RAT. In some deployments, NG-RAN may also implement LTE RAT.

[0005] The base stations used by the RAN may correspond to the RAN. An example of an E-UTRAN base station is an Evolved Universal Terrestrial Radio Access Network (E-UTRAN) Node B (also commonly denoted as an evolved Node B, enhanced Node B, eNodeB, or eNB). An example of an NG-RAN base station is a Next Generation Node B (also sometimes referred to as a gNodeB or gNB).

[0006] The RAN provides communication services together with external entities through its connection with the Core Network (CN). For example, E-UTRAN may utilize the Evolved Packet Core (EPC) and NG-RAN may utilize the 5G Core Network (5GC). Summary of the invention

[0007] In one aspect, a device of a user equipment (UE) is provided, comprising: a processor; and a memory storing instructions that, when executed by the processor, configure the device to: receive an artificial intelligence (AI) model from a base station; obtain a trained AI model generated from training of the AI ​​model; and transmit the trained AI model to the base station via an uplink radio resource control (RRC) message.

[0008] On the other hand, a device in a base station is provided, comprising: a processor; and a memory storing instructions that, when executed by the processor, configure the device to: transmit an artificial intelligence (AI) model to a user equipment (UE); and receive a trained AI model generated from training of the AI ​​model from the UE via an uplink radio resource control (RRC) message.

[0009] On the other hand, a device of a user equipment (UE) is provided, comprising: a processor; and a memory storing instructions that, when executed by the processor, configure the device to: receive an artificial intelligence (AI) model trained by a base station via a downlink radio resource control (RRC) message; and perform inference using the trained AI model.

[0010] On the other hand, a device in a base station is provided, comprising: a processor; and a memory storing instructions that, when executed by the processor, configure the device to: train an artificial intelligence (AI) model; and configure the trained AI model to a user equipment (UE) via an uplink radio resource control (RRC) message.

[0011] This summary is intended to provide a brief overview of some of the topics described in this document. Therefore, it should be understood that the above features are only examples and should not be construed as narrowing the scope or essence of the topics described herein in any way. Other features, aspects, and advantages of the topics described herein will become apparent through the following detailed description, drawings, and claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] To easily identify the discussion of any particular element or action, the most significant digit(s) in a reference number refers to the drawing number that first introduces the element.

[0013] Figure 1An example architecture of a wireless communication system according to some embodiments of the present application is illustrated.

[0014] Figure 2 A system for performing signaling between a wireless device and a network device according to some embodiments of the present application is illustrated.

[0015] Figure 3 An example flow chart of wireless AI / ML according to some embodiments of the present application is illustrated.

[0016] Figure 4 Another example flow chart of wireless AI / ML according to some embodiments of the present application is illustrated.

[0017] Figure 5 Another example flow chart of wireless AI / ML according to some embodiments of the present application is illustrated.

[0018] Figure 6 Another example flow chart of wireless AI / ML according to some embodiments of the present application is illustrated.

[0019] Figure 7 is an example flowchart of an AI capability exchange process according to some embodiments of the present application.

[0020] Figure 8 is a flowchart illustrating an example method performed at a UE according to some embodiments of the present application.

[0021] Fig. 9 is a flow chart illustrating an example method performed at a base station according to some embodiments of the present application.

[0022] Fig.10 is a flowchart illustrating an example method performed at a UE according to some embodiments of the present application.

[0023] Fig.11 is a flow chart illustrating an example method performed at a base station according to some embodiments of the present application. DETAILED DESCRIPTION

[0024] Various exemplary embodiments of the present application will be described below with reference to the accompanying drawings. For the sake of clarity and brevity, not all features are described in the specification. However, it should be noted that when practicing the embodiments of the present application, many settings specific to the specific implementation can be made. In addition, it should be noted that, in order to avoid blurring the description, some of the accompanying drawings only illustrate the steps of the process and / or components of the device that are closely related to the technical solution of the present application, while in some other drawings, well-known process steps and / or device structures are illustrated only for a better understanding of the present application.

[0025] For ease of explanation, various aspects of the present application will be described below in the context of 5G NR. However, it should be noted that this is not a limitation on the scope of application of the present application, and one or more aspects of the present application may also be applied to wireless communication systems that are already commonly used (such as 4G LTE / LTE-A) or various wireless communication systems to be developed in the future. Equivalents of the architectures, entities, functions, processes, etc. described in the following description may be found in these communication systems.

[0026] Various embodiments are described with reference to UE. However, reference to UE is provided for illustrative purposes only. The example embodiments may be used with any electronic component that can establish a connection with a network and is configured with hardware, software and / or firmware for exchanging information and data with the network. Therefore, UE as described herein is used to represent any appropriate electronic component. Examples of UE may include mobile devices, personal digital assistants (PDAs), tablet computers, laptop computers, personal computers, Internet of Things (IoT) devices, or machine type communication (MTC) devices, etc., which may be implemented in various objects (such as electrical appliances or vehicles, meters, etc.).

[0027] In addition, various embodiments are described with reference to a "base station". However, reference to a base station is provided for illustrative purposes only. The term "base station" as used in this application is an example of a control device in a wireless communication system, which has the full breadth of its ordinary meaning. For example, in addition to the gNB specified in 5G NR, a "base station" may also be, for example, an ng-eNB compatible with an NR communication system, an eNB in ​​an LTE communication system, a remote radio head, a wireless access point, a relay node, a drone control tower, or any communication device or element thereof for performing similar control functions.

[0028] System Overview

[0029] Figure 1 An example architecture of a wireless communication system 100 according to an embodiment disclosed herein is illustrated. The description provided below is for an example wireless communication system 100 operating in conjunction with the LTE system standard and / or the 5G or NR system standard provided in the 3GPP technical specifications.

[0030] like Figure 1 As shown, wireless communication system 100 includes UE 102 and UE 104 (although any number of UEs may be used). In this example, UE 102 and UE 104 are illustrated as smartphones (e.g., handheld touch screen mobile computing devices capable of connecting to one or more cellular networks), but may also include any mobile or non-mobile computing device configured for wireless communication.

[0031] UE 102 and UE 104 may be configured to be communicatively coupled to RAN 106. In an embodiment, RAN 106 may be NG-RAN, E-UTRAN, etc. UE 102 and UE 104 utilize connections (or channels) (shown as connection 108 and connection 110, respectively) with RAN 106, where each connection (or channel) includes a physical communication interface. RAN 106 may include one or more base stations, such as base station 112 and base station 114, to implement connection 108 and connection 110.

[0032] In this example, connection 108 and connection 110 are air interfaces that enable such communicative coupling and may conform to the RAT used by RAN 106 , such as, for example, LTE and / or NR.

[0033] In some embodiments, UE 102 and UE 104 may also directly exchange communication data via side link interface 116. UE 104 is shown as being configured to access an access point (shown as AP 118) via connection 120. By way of example, connection 120 may include a local wireless connection, such as a connection conforming to any IEEE 802.11 protocol, wherein AP 118 may include In this example, AP 118 may be connected to another network (eg, the Internet) without going through CN 124.

[0034] In an embodiment, UE 102 and UE 104 may be configured to communicate with each other or with base station 112 and / or base station 114 over a multi-carrier communication channel using orthogonal frequency division multiplexing (OFDM) communication signals according to various communication techniques, such as but not limited to orthogonal frequency division multiple access (OFDMA) communication techniques (e.g., for downlink communication) or single carrier frequency division multiple access (SC-FDMA) communication techniques (e.g., for uplink and ProSe or sidelink communication), although the scope of the embodiment is not limited in this respect. The OFDM signal may include multiple orthogonal subcarriers.

[0035] In some embodiments, all or part of base station 112 or base station 114 may be implemented as one or more software entities running on a server computer as part of a virtual network. In addition, or in other embodiments, base station 112 or base station 114 may be configured to communicate with each other via interface 122. In an embodiment where wireless communication system 100 is an LTE system (e.g., when CN124 is EPC), interface 122 may be an X2 interface. The X2 interface may be defined between two or more base stations (e.g., two or more eNBs, etc.) connected to EPC and / or between two eNBs connected to EPC. In an embodiment where wireless communication system 100 is an NR system (e.g., when CN 124 is 5GC), interface 122 may be an Xn interface. The Xn interface is defined between two or more base stations (e.g., two or more gNBs, etc.) connected to 5GC, between base station 112 (e.g., gNB) and eNB connected to 5GC, and / or between two eNBs connected to 5GC (e.g., CN 124).

[0036] The RAN 106 is shown as being communicatively coupled to the CN 124. The CN 124 may include one or more network elements 126 configured to provide various data and telecommunication services to customers / subscribers (e.g., UE 102 and users of UE 104) connected to the CN 124 via the RAN 106. The components of the CN 124 may be implemented in one physical device or separate physical devices including components for reading and executing instructions from a machine-readable or computer-readable medium (e.g., a non-transitory machine-readable storage medium).

[0037] In an embodiment, CN 124 may be an EPC, and RAN 106 may be connected to CN 124 via an S1 interface 128. In an embodiment, S1 interface 128 may be divided into two parts: an S1 user plane (S1-U) interface that carries traffic data between base station 112 or base station 114 and a serving gateway (S-GW); and an S1-MME interface that is a signaling interface between base station 112 or base station 114 and a mobility management entity (MME).

[0038] In an embodiment, CN 124 may be a 5GC, and RAN 106 may be connected to CN 124 via an NG interface 128. In an embodiment, NG interface 128 may be divided into two parts: an NG user plane (NG-U) interface that carries service data between base station 112 or base station 114 and a user plane function (UPF); and an S1 control plane (NG-C) interface that is a signaling interface between base station 112 or base station 114 and an access and mobility management function (AMF).

[0039] Generally speaking, application server 130 may be an element that provides applications (e.g., packet-switched data services) that use Internet Protocol (IP) bearer resources with CN 124. Application server 130 may also be configured to support one or more communication services (e.g., VoIP sessions, group communication sessions, etc.) for UE 102 and UE 104 via CN 124. Application server 130 may communicate with CN 124 via IP communication interface 132.

[0040] Figure 2 A system 200 for performing signaling 234 between a wireless device 202 and a network device 218 according to an embodiment disclosed herein is illustrated. The system 200 may be part of a wireless communication system as described herein. The wireless device 202 may be, for example, a UE of a wireless communication system. The network device 218 may be, for example, a base station (e.g., an eNB or a gNB) of a wireless communication system.

[0041] The wireless device 202 may include one or more processors 204. The processor 204 may execute instructions to perform various operations of the wireless device 202, as described herein. The processor 204 may include one or more baseband processors implemented using, for example, a central processing unit (CPU), a digital signal processor (DSP), an application specific integrated circuit (ASIC), a controller, a field programmable gate array (FPGA) device, another hardware device, a firmware device, or any combination thereof configured to perform the operations described herein.

[0042] The wireless device 202 may include a memory 206. The memory 206 may be a non-transitory computer-readable storage medium that stores instructions 208 (which may include, for example, instructions executed by the processor 204). The instructions 208 may also be referred to as program code or a computer program. The memory 206 may also store data used by the processor 204 and results calculated by the processor.

[0043] The wireless device 202 may include one or more transceivers 210 that may use radio frequency (RF) transmitter and / or receiver circuitry that uses an antenna 212 of the wireless device 202 to facilitate signaling (e.g., signaling 234) to and / or from the wireless device 202 with other devices (e.g., network device 218) according to a corresponding RAT.

[0044] The wireless device 202 may include one or more (e.g., one, two, four, or more) antennas 212. For embodiments with multiple antennas 212, the wireless device 202 may utilize the spatial diversity of such multiple antennas 212 to transmit and / or receive multiple different data streams on the same time-frequency resources. This behavior may be referred to as, for example, multiple-input multiple-output (MIMO) behavior (referring to the multiple antennas used at each of the transmitting device and the receiving device to implement this aspect). MIMO transmission by the wireless device 202 may be implemented based on precoding (or digital beamforming) applied at the wireless device 202, which multiplexes the data streams across the antennas 212 based on known or assumed channel characteristics, so that each data stream is received at an appropriate signal strength relative to the other streams and at a desired location in the spatial domain (e.g., the location of the receiver associated with the data stream). Certain embodiments may use a single-user MIMO (SU-MIMO) approach (where the data streams are all directed to a single receiver) and / or a multi-user MIMO (MU-MIMO) approach (where the individual data streams may be directed to individual (different) receivers in different locations in the spatial domain).

[0045] In certain embodiments with multiple antennas, the wireless device 202 may implement analog beamforming techniques whereby the phases of signals transmitted by the antennas 212 are relatively adjusted so that the (joint) transmissions of the antennas 212 can be directed (this is sometimes referred to as beam steering).

[0046] The wireless device 202 may include one or more interfaces 214. The interface 214 may be used to provide input to the wireless device 202 or output from the wireless device. For example, a wireless device 202 that is a UE may include an interface 214, such as a microphone, a speaker, a touch screen, and buttons, etc., to allow a user of the UE to input and / or output to the UE. Other interfaces of such a UE may be composed of transmitters, receivers, and other circuits that allow the UE to communicate with other devices (e.g., in addition to the transceiver 210 / antenna 212 described above), and may communicate according to known protocols (e.g., and etc.) to perform the operation.

[0047] The network device 218 may include one or more processors 220. The processor 220 may execute instructions to perform various operations of the network device 218, as described herein. The processor 204 may include one or more baseband processors implemented using, for example, a CPU, a DSP, an ASIC, a controller, an FPGA device, another hardware device, a firmware device, or any combination thereof configured to perform the operations described herein.

[0048] The network device 218 may include a memory 222. The memory 222 may be a non-transitory computer-readable storage medium that stores instructions 224 (which may include, for example, instructions executed by the processor 220). The instructions 224 may also be referred to as program code or a computer program. The memory 222 may also store data used by the processor 220 and results calculated by the processor.

[0049] The network device 218 may include one or more transceivers 226, which may include RF transmitter and / or receiver circuits that use an antenna 228 of the network device 218 to facilitate signaling (e.g., signaling 234) to and / or from the network device 218 with other devices (e.g., wireless device 202) according to a corresponding RAT.

[0050] The network device 218 may include one or more (e.g., one, two, four, or more) antennas 228. In embodiments with multiple antennas 228, the network device 218 may perform MIMO, digital beamforming, analog beamforming, beamsteering, etc. as described.

[0051] The network device 218 may include one or more interfaces 230. The interface 230 may be used to provide input to or output from the network device 218. For example, the network device 218 as a base station may include an interface 230 composed of a transmitter, a receiver, and other circuits (e.g., in addition to the transceiver 226 / antenna 228 described above), which enables the base station to communicate with other equipment in the core network and / or enables the base station to communicate with external networks, computers, databases, etc., in order to achieve the purpose of performing operations, management, and maintenance of the base station or other equipment operably connected to the base station.

[0052] In recent years, the application of AI / ML in wireless communication systems has aroused great interest in academic and industrial research. AI provides a machine or system with the ability to simulate human intelligence and behavior. ML can be called a subfield of AI research. In some cases, the terms AI and ML are used interchangeably. A typical implementation of AI / ML is a neural network (NN), such as a conventional neural network (CNN), a recurrent / recursive neural network (RNN), or a generative adversarial network (GAN). The following description sometimes uses a neural network as an example of an AI / ML model, however, it should be understood that the AI / ML model discussed herein may not be limited thereto, and any other algorithm or model that performs inference on the UE side or the network side is possible.

[0053] The air interface design may be augmented with features that enable improved support for AI / ML based algorithms for enhanced performance and / or reduced complexity / overhead. The enhanced performance depends on the use case under consideration and may be, for example, improved throughput, robustness, accuracy, or reliability. For example, use cases may include:

[0054] - Channel state information (CSI) feedback enhancements, such as overhead reduction, accuracy improvement or prediction;

[0055] - beam management, e.g., beam prediction in the time and / or spatial domain for overhead and latency reduction or beam selection accuracy improvement, etc.; and

[0056] - Positioning accuracy enhancement for different scenarios, including, for example, those with heavy No-Site Line-Of-Site (NLOS) conditions.

[0057] Currently, use cases are explored in the base physical (PHY) layer, for example for improving processes in modems (modulator-demodulators). However, there is the potential to extend the use cases to processes in upper layers such as the medium access control (MAC) layer, the radio resource control (RRC) layer, etc.

[0058] It is expected that specific AI / ML models may be left to industry vendors (such as UE vendors, network equipment vendors, network operators, or 3rd party solution providers) for specific implementation. For specific use cases, there may be multiple vendors (e.g., UE vendors or network equipment vendors, etc.) that develop different AI / ML algorithms and models. The storage and management of AI / ML models may also be vendor-specific and may be outside the scope of 3GPP. For example, a vendor might create its own AI / ML model library server to store and manage AI / ML models, while another vendor might rent it from an OTT. However, it may be difficult or even impossible to coordinate the two vendors on their AI / ML model libraries.

[0059] The AI / ML model can be implemented as a one-sided model that performs inference on one side (e.g., UE side or gNB side), or as a two-sided model that performs inference on both the UE side and the gNB side. The gNB and UE may be reluctant to share their local data for training, for example, due to data privacy or business interests. In this case, federated learning can be used to allow AI / ML models to be trained locally without data migration. In addition, compared to gNB, UE is limited by its power consumption and complexity to run data training, and transfer learning can be used, that is, the AI / ML model is trained by the gNB and then run by the UE.

[0060] Depending on where the AI / ML model is trained and used, various levels of collaboration between the network and the UE may be defined. For example, the collaboration level may be defined as no collaboration (level x), signaling-based collaboration without model migration (level y), and signaling-based coloring with model migration (level z), etc.

[0061] However, it may be required that the UE align its understanding of the AI / ML model with the gNB. For example, in cases where the training and / or inference of the AI / ML model occurs across the air interface between the UE and the gNB, the UE and gNB must be synchronized on the AI / ML model used.

[0062] An embodiment of the present application is provided to support an RRC process for wireless AI / ML, and the embodiments of the present application are described below with reference to the accompanying drawings.

[0063] Figure 3 An example flow chart of wireless AI / ML according to some embodiments of the present application is illustrated. Figure 3 As shown, in step S11, the UE may download the AI / ML model from its model server, which may be created or rented by the UE supplier. Optionally, the download of the AI / ML may be initiated by a request from the UE (S10). Alternatively, the AI / ML may be pushed to the UE by a model server (not shown).

[0064] According to some embodiments of the present application, the downloaded AI / ML model may be included in a model file, which contains the model structure of the AI / ML model and optionally the initial model parameters. In the case where the AI / ML model is a deep neural network, the model file may include the layers and initial weights / biases of the neural network. The model file may have a format that depends on the machine learning framework used, such as .h5 format or .ONNX format, etc. Optionally, AI / ML may also include a unique model ID and metadata. The model ID is used to explicitly identify the AI / ML model, for example, within a public land mobile network (PLMN) or between several PLMNs, while generating metadata to describe various information about the corresponding AI / ML model. Optionally, the AI / ML model data may be compressed for storage and / or migration, for example, by using the standard compression method provided in ISO-IEC 15938-17 or any other possible compression method, which will not be described in detail here.

[0065] The downloaded AI / ML model may be a one-sided model, and in this case, the entire model is migrated from the model server to the UE. Alternatively, the AI / ML model may be part of a two-sided model. In the context of this application, an AI / ML model may refer to a one-sided model or a two-sided model.

[0066] In one example, the download of AI / ML models can adopt a traditional over-the-top (OTT) solution. AI / ML model data is sent as application layer data via the user plane (UP) of the operator network, which provides a tunnel transparent to the network (e.g., to the gNB). The UE receives and decapsulates the protocol data unit (PDU) carrying the model data and forwards the model data to its application layer.

[0067] In another example, the AI / ML model may be encapsulated in a transparent container, and the gNB may migrate the transparent container including the AI / ML model to the UE via a downlink RRC message (i.e., via the control plane). Segmentation of the RRC message may be supported to include the AI / ML model data with a high payload size. The access stratum (AS) of the UE may receive the transparent container in the RRC message and forward it to the application layer.

[0068] Then, in step S12, the UE may train the AI / ML model using its local data information by using various methods, such as a back-propagation method. After performing the training, in step S13, the UE may transmit the trained model to the gNB via an uplink RRC message. For example, the trained AI / ML model may be sent as UE Assistance Information (UAI). For the transmission of the RRC message, the signaling radio bearer 4 (SRB4) may be configured by the network after AS security activation. Segmentation of the RRC message may be supported to include trained AI / ML model data with a high payload size. Preferably, the trained AI / ML model may have its model ID (e.g., the same as the untrained AI / ML model) and related metadata.

[0069] In step S14, the gNB extracts the trained AI / ML model from the received RRC message. The trained AI / ML model can be used for various purposes. For example, the gNB may store the trained AI / ML model in the memory of its modem (modulator-demodulator) and configure the modem for inferring corresponding use cases such as CSI feedback enhancement, beam management, or positioning accuracy enhancement. For example, the gNB may train its AI / ML model part with reference to the trained part from the UE. For example, the gNB may perform model fusion based on its training results and the UE's training results (e.g., the trained AI / ML model from the UE).

[0070] pass Figure 3 The RRC procedure shown allows the UE and gNB to maintain a consistent understanding of the AI / ML model used.

[0071] Figure 4 Another example flow chart of wireless AI / ML according to some embodiments of the present application is illustrated. Figure 4 As shown, in step S21, the gNB may download the AI / ML model from its model server, which may be created or rented by the gNB supplier. The download of AI / ML (S20) may be initiated by a request from the gNB, or the AI / ML may be pushed to the gNB by the model server (not shown).

[0072] According to some embodiments of the present application, the downloaded AI / ML model may be included in a model file, which includes the model structure of the AI / ML model and optionally initial model parameters. Optionally, the AI / ML may also include a unique model ID for identifying the AI / ML model and related metadata.

[0073] In one example, the download of the AI / ML model may adopt an OTT solution, that is, the AI / ML model data is sent to the gNB via the user plane as application layer data. In another example, the AI / ML model may be encapsulated in a container and sent to the gNB via the control plane.

[0074] Then in step S22, the gNB may train the AI / ML model using its local data using various methods. After performing the training, in step S23, the gNB may configure the trained model to the UE via a downlink RRC message. In the context of the present application, if the gNB "configures" the AI / ML model, the gNB knows the model. For example, the trained AI / ML model may be sent as an RRC reconfiguration (Reconfig). For the sending of RRC messages, SRB4 may be configured. Segmentation of RRC messages may be supported to include trained AI / ML model data with a high payload size. Preferably, the trained AI / ML model may have its model ID (e.g., the same as an untrained AI / ML model) and related metadata.

[0075] In step S24, the UE extracts the trained AI / ML model from the received RRC message. The trained AI / ML model can be used for various purposes. For example, the UE can store the trained AI / ML model in the memory of its modem (modulator-demodulator) and configure the modem to infer the corresponding use case.

[0076] pass Figure 4 With the configuration of the AI / ML model shown, the UE and gNB can maintain consistent understanding of the AI / ML model used.

[0077] Figure 5 Another example flow chart of wireless AI / ML according to some embodiments of the present application is illustrated. Figure 5As shown in steps S31 and S32 in FIG. 1 , the gNB may download the AI / ML model from the AI / ML model library of the network server. The AI / ML model may include a model structure and optionally initial parameters / weights and a model ID. The download of the AI / ML model may be performed through the operator network's operations management and maintenance (OAM) or core network (CN), which may encapsulate the AI / ML model in a transparent container and transmit it to the gNB.

[0078] In step S33, the gNB transmits the transparent container including the AI / ML model to the UE via a downlink RRC message. As described above, RRC message segmentation may be supported to migrate AI / ML model data with a high payload size. The access stratum (AS) of the UE receives the RRC message and may forward the transparent container to the upper layers of the UE (such as a UE APP, a VAL client, or another application layer client), for example, via an AT command that may provide communication between the AS and the upper layers of the UE.

[0079] In step S34, the received AI / ML model may be checked for compatibility. For example, the UE (e.g., UE APP) may transmit the AI / ML model to a UE model server that may be operated by a UE vendor. The UE model server may verify the compatibility of the model with the UE. When the AI / ML model is verified to be compatible with the UE, the UE model server may further train the model on UE-side data. As a result of the check and training, a status indication may be generated. For example, the status indication may indicate any of "success", meaning that the model is compatible with the UE and the training of the model is successful, "failure", meaning that the model is compatible with the UE but the training of the model fails, or "model incompatibility", meaning that the model is incompatible with the UE. However, it should be understood that the status indication may take other values.

[0080] The UE model server may feed back the results of the compatibility check to the UE (e.g., UE APP). For example, in the case of successful training, the status indication "success" and the training result of the AI / ML model (i.e., the trained AI / ML model) are transmitted to the UE, and in the case of failed training or incompatibility, the status indication "failure" or "model incompatible" is transmitted to the UE. The UE APP may forward the status indication to the AS of the UE via an AT command and optionally forward the training result of the AI / ML model. In one case, the UE may store the trained AI / ML model in the memory of its modem and configure the modem for inferring whether the model is activated.

[0081] In step S35, the UE may transmit the status indication and the training result of the AI / ML model to the gNB via an uplink RRC message. If the status indication is "success", the gNB may perform inference using the trained model. Alternatively, as shown in step S36, the gNB may perform model fusion based on the local training result of the AI / ML model and the training result received from the UE.

[0082] Optionally, the gNB may report the status indication to the network model server. For example, if the status indication is "model incompatible" or "failed", the gNB may transmit an error report to the network model server.

[0083] pass Figure 5 With the compatibility check and RRC procedures shown, the gNB can keep its understanding of the AI / ML model consistent with the UE, even though the model is transmitted to the UE transparently to the gNB.

[0084] Figure 6 Another example flow chart of wireless AI / ML according to some embodiments of the present application is illustrated. Figure 6 In the example above, the operator network manages the AI / ML library so that the UE and gNB can download the same AI / ML models.

[0085] like Figure 6 As shown, the AI / ML model may be stored in an operator model server operated by an operator. In steps S41 and S42, the gNB may download the AI / ML model from the AI / ML model library of the operator model server via OAM or CN. The AI / ML model may include a model structure and optionally initial parameters / weights and a model ID. Figure 5 Different from this, downloading the AI / ML model to the gNB is opaque, so the gNB has access to the AI / ML model.

[0086] In step S43, the gNB configures the AI / ML model to the UE via a downlink RRC message. For example, the AI / ML model may be included in the RRC configuration as an information element (IE). In addition, RRC message segmentation may be supported to migrate AI / ML model data with a high payload size. The AS of the UE receives the RRC message and may extract the AI / ML model and forward it to the application layer of the UE (such as a UE APP, a VAL client, or another application layer client), for example, via an AT command.

[0087] In step S44, the received AI / ML model may be trained offline. For example, the UE (e.g., UE APP) may transmit the AI / ML model to the UE model server. After training the AI / ML model, the UE model server may transmit the training result to the UE (e.g., UE APP). The UE APP may forward the training result of the AI / ML model to the AS of the UE via an AT command. In one case, the UE may store the trained AI / ML model in the memory of its modem and configure the modem to infer whether the model is activated.

[0088] In step S45, the UE may transmit the training result of the AI / ML model (i.e., the trained AI / ML model) to the gNB via an uplink RRC message, for example, as UE assistance information. The trained AI / ML model may be used for various purposes. For example, as shown in step S46, the gNB may perform model fusion based on the local training result of the AI / ML model and the training result received from the UE.

[0089] pass Figure 6 Through the RRC process shown, the gNB can keep its understanding of the AI / ML model consistent with that of the UE.

[0090] According to some embodiments of the present application, the gNB may check the AI ​​capabilities and / or preferences of the UE. Figure 7 An example flow chart of an AI capability exchange process that can be performed in the RRC layer is illustrated.

[0091] like Figure 7 As shown, in step S51, the gNB may transmit a query (UECapabilityEquiry) for the UE's AI capability to the UE. In response, in step S61, the UE may report the UE's capability information (UECapabilityInformation) to the gNB. For example, the capability information may include a single bit to indicate whether the UE supports AI / ML (training or inference). Alternatively, the capability information may include a set of bits to indicate the coloring level (e.g., level x, y, z) supported by the UE or the supported use cases (e.g., CSI feedback enhancement, beam management, positioning accuracy enhancement), etc.

[0092] The UE may also report its AI preference information (UEPreferenceInformation) to the gNB. The preference information may include one or more bits to indicate whether the UE is willing to run AI / ML or how long it can perform AI / ML, etc. For example, the UE may be able to perform AI / ML training or inference, but due to battery status, it is unwilling to do so, and the preference information may indicate such information. The preference information may be reported as UE assistance information via a dedicated RRC message, or may be reported together with the capability information.

[0093] Based on the AI ​​capability and / or preference information reported by the UE, the gNB may configure the UE via an RRC configuration message (e.g., RRCReconfiguration). The RRC configuration message may indicate the level of cooperation or whether to stop or continue AI / ML at the UE.

[0094] Available in Figures 3 to 6 The flowchart uses Figure 7 For example, before step S11, S23, S33, or S43, the gNB may check the capabilities and / or preferences of the UE, and transmit the model to the UE only if the UE is able and / or willing to run the corresponding AI / ML model. For example, after checking the capabilities and preferences of the UE, the gNB may indicate the cooperation level z in the downlink RRC message used to transmit the AI ​​model, as shown in step S11, S23, S33, or S43.

[0095] Figure 8 1 is a flowchart illustrating an example method for supporting wireless AI / ML according to some embodiments of the present application. The method can be performed at a UE.

[0096] At S101, the UE receives an AI model from a base station. The AI ​​model may be transparently transmitted to the base station via a user plane or a control plane, or may be configured by the base station in a non-transparent manner.

[0097] At S102 , the UE obtains a trained AI model by training the received AI model or by receiving a training result from a server.

[0098] At S103 , the UE transmits the trained AI model to the base station via an uplink RRC message.

[0099] Fig. 9 1 is a flowchart illustrating an example method for supporting wireless AI / ML according to some embodiments of the present application. The method can be performed by a base station such as a gNB.

[0100] At S201, the base station transmits the AI ​​model to the UE. The AI ​​model may be transparently transmitted to the base station via the user plane or the control plane, or may be configured by the base station in a non-transparent manner.

[0101] At S202, the base station receives a trained AI model from the UE via an uplink RRC message. The trained AI model may be generated by training of the UE or a UE model server.

[0102] Fig.10 1 is a flowchart illustrating an example method for supporting wireless AI / ML according to some embodiments of the present application. The method can be performed at a UE.

[0103] At S301, the UE receives an AI model trained by a base station via a downlink RRC message. The AI ​​model may be configured by the base station in a non-transparent manner.

[0104] At S302 , the UE may utilize the trained AI model to perform inference.

[0105] Fig.11 1 is a flowchart illustrating an example method for supporting wireless AI / ML according to some embodiments of the present application. The method can be performed by a base station such as a gNB.

[0106] At S401, the base station trains the AI ​​model.

[0107] At S402, the base station configures the trained AI model to the UE via an uplink RRC message.

[0108] Embodiments contemplated herein include an apparatus comprising a method for performing Figure 8 or Fig.10 The apparatus may be, for example, an apparatus of a UE (such as the wireless device 202 as a UE, as described herein).

[0109] Embodiments contemplated herein include one or more non-transitory computer-readable media including instructions that, when executed by one or more processors of an electronic device, cause the electronic device to perform the following operations: Figure 8 or Fig.10 One or more elements of the method shown. The non-transitory computer-readable medium may be, for example, a memory of a UE (such as the memory 206 of the wireless device 202 as a UE, as described herein).

[0110] Embodiments contemplated herein include an apparatus comprising a device for performing Figure 8 or Fig.10 Logic, modules, or circuits of one or more elements of the illustrated method. The apparatus may be, for example, an apparatus of a UE (such as the wireless device 202 as a UE, as described herein).

[0111] Embodiments contemplated herein include an apparatus comprising: one or more processors and one or more computer-readable media comprising instructions that, when executed by the one or more processors, cause the one or more processors to perform the following steps: Figure 8 or Fig.10 One or more elements of the method shown. The apparatus may be, for example, an apparatus of a UE (such as the wireless device 202 as a UE, as described herein).

[0112] Embodiments contemplated herein include a signal such as Figure 8 or Fig.10 The invention may be described in or relating to one or more elements of the method shown.

[0113] Embodiments contemplated herein include a computer program or computer program product comprising instructions, wherein execution of the program by a processor causes the processor to perform the following: Figure 8 or Fig.10 One or more elements of the method shown. The processor may be a processor of a UE (such as the processor 204 of the wireless device 202 as a UE, as described herein). These instructions may be located, for example, in the processor and / or on a memory of the UE (such as the memory 206 of the wireless device 202 as a UE, as described herein).

[0114] Embodiments contemplated herein include an apparatus comprising a device for performing Fig. 9 or Fig.11 The apparatus may be, for example, an apparatus of a base station (such as network device 218 as a base station, as described herein).

[0115] Embodiments contemplated herein include one or more non-transitory computer-readable media including instructions that, when executed by one or more processors of an electronic device, cause the electronic device to perform the following operations: Fig. 9 or Fig.11 One or more elements of the method shown. The non-transitory computer-readable medium may be, for example, a memory of a base station (such as the memory 222 of the network device 218 as a base station, as described herein).

[0116] Embodiments contemplated herein include an apparatus comprising a device for performing Fig. 9 or Fig.11 Logic, modules or circuits of one or more elements of the illustrated method. The apparatus may be, for example, an apparatus of a base station (such as the network device 218 as a base station, as described herein).

[0117] Embodiments contemplated herein include an apparatus comprising: one or more processors and one or more computer-readable media comprising instructions that, when executed by the one or more processors, cause the one or more processors to perform the following steps: Fig. 9 or Fig.11 One or more elements of the method shown. The apparatus may be, for example, an apparatus of a base station (such as network device 218 as a base station, as described herein).

[0118] Embodiments contemplated herein include a signal such as Fig. 9 or Fig.11 The invention may be described in or relating to one or more elements of the method shown.

[0119] Embodiments contemplated herein include a computer program or computer program product comprising instructions, wherein execution of the program by a processing element causes the processing element to perform the following steps: Fig. 9 or Fig.11 One or more elements of the method shown. The processor may be a processor of a base station (such as processor 220 of network device 218 as a base station, as described herein). These instructions may, for example, be located in the processor and / or in a memory of the UE (such as memory 222 of network device 218 as a base station, as described herein).

[0120] For one or more embodiments, at least one of the components set forth in one or more of the foregoing figures may be configured to perform one or more operations, techniques, processes, and / or methods as described herein. For example, a baseband processor as described herein in conjunction with one or more of the foregoing figures may be configured to operate according to one or more of the examples set forth herein. For another example, a circuit system associated with a UE, a base station, a network element, etc. as described above in conjunction with one or more of the foregoing figures may be configured to operate according to one or more of the examples set forth herein.

[0121] Examples

[0122] The following examples relate to additional embodiments.

[0123] Embodiment 1 may include a device of a user equipment (UE), the device comprising: a processor; and a memory, the memory storing instructions, the instructions, when executed by the processor, configuring the device to: receive an artificial intelligence (AI) model from a base station; obtain a trained AI model generated from training of the AI ​​model; and transmit the trained AI model to the base station via an uplink radio resource control (RRC) message.

[0124] Embodiment 2 may include the apparatus of embodiment 1, wherein the AI ​​model is received in a transparent container via a downlink RRC message.

[0125] Embodiment 3 may include the apparatus of embodiment 1, wherein the AI ​​model is received via a user plane.

[0126] Embodiment 4 may include the apparatus of embodiment 1, wherein the AI ​​model is received from the base station as an RRC configuration.

[0127] Embodiment 5 may include an apparatus according to embodiment 1, wherein the instructions, when executed by the processor, further configure the apparatus to: obtain the trained AI model by training the AI ​​model at the UE.

[0128] Embodiment 6 may include a device according to embodiment 1, wherein the instructions, when executed by the processor, further configure the device to: send the AI ​​model to a server; and obtain the trained AI model by receiving the training results of the AI ​​model from the server.

[0129] Embodiment 7 may include a device according to embodiment 6, wherein the instructions, when executed by the processor, further configure the device to: receive a status indication for the AI ​​model from the server, wherein the status indication indicates at least one of a result of checking the compatibility of the AI ​​model with the UE or a result of the training of the AI ​​model.

[0130] Embodiment 8 may include an apparatus according to embodiment 1, wherein the instructions, when executed by the processor, further configure the apparatus to report to the base station one or more of: capability information indicating the AI ​​capability of the UE or preference information indicating the AI ​​preference of the UE.

[0131] Embodiment 9 may include the apparatus of embodiment 8, wherein the preference information includes one or more of: whether the UE prefers to use AI or how long the UE prefers to use AI.

[0132] Embodiment 10 may include the apparatus of embodiment 1, wherein the instructions, when executed by the processor, further configure the apparatus to: receive an RRC configuration based on the capability information and / or the preference information from the base station.

[0133] Embodiment 11 may include the apparatus of embodiment 10, wherein the RRC configuration includes one or more of: a level of cooperation between the UE and the base station or when to stop using AI.

[0134] Embodiment 12 may include a device in a base station, the device comprising: a processor; and a memory storing instructions that, when executed by the processor, configure the device to: transmit an artificial intelligence (AI) model to a user equipment (UE); and receive a trained AI model generated from training of the AI ​​model from the UE via an uplink radio resource control (RRC) message.

[0135] Embodiment 13 may include the apparatus of embodiment 12, wherein the AI ​​model is transmitted in a transparent container of an RRC message.

[0136] Embodiment 14 may include the apparatus of embodiment 12, wherein the AI ​​model is transmitted as an RRC configuration.

[0137] Embodiment 15 may include the apparatus of embodiment 12, wherein the AI ​​model is transmitted via a user plane.

[0138] Embodiment 16 may include a device according to embodiment 12, wherein the instructions, when executed by the processor, further configure the device to: perform inference using the trained AI model; or perform model fusion based on the training results of the AI ​​model at the base station and the trained AI model from the UE.

[0139] Embodiment 17 may include an apparatus according to embodiment 12, wherein the instructions, when executed by the processor, further configure the apparatus to: check the AI ​​capabilities and / or AI preferences of the UE before transmitting the AI ​​model to the UE.

[0140] Embodiment 18 may include an apparatus according to embodiment 12, wherein the instructions, when executed by the processor, further configure the apparatus to: receive capability information indicating the AI ​​capability of the UE and / or preference information indicating the AI ​​preference of the UE from the UE; determine an RRC configuration based on the capability information and / or the preference information; and transmit the RRC configuration to the UE.

[0141] Embodiment 19 may include the apparatus of embodiment 18, wherein the RRC configuration includes one or more of: a level of cooperation between the UE and the base station or when to stop using AI.

[0142] Embodiment 20 may include a device of a user equipment (UE), the device comprising: a processor; and a memory storing instructions that, when executed by the processor, configure the device to: receive an artificial intelligence (AI) model trained by a base station via a downlink radio resource control (RRC) message; and perform inference using the trained AI model.

[0143] Embodiment 21 may include an apparatus according to embodiment 20, wherein the RRC message supports segmentation to include data of the AI ​​model with a high payload size.

[0144] Embodiment 22 may include an apparatus according to Embodiment 20, wherein the trained AI model is identified by a model ID.

[0145] Embodiment 23 may include an apparatus according to embodiment 20, wherein the instructions, when executed by the processor, further configure the apparatus to report to the base station one or more of: capability information indicating the AI ​​capability of the UE or preference information indicating the AI ​​preference of the UE.

[0146] Embodiment 24 may include the apparatus of embodiment 23, wherein the preference information includes one or more of: whether the UE prefers to use AI or how long the UE prefers to use AI.

[0147] Embodiment 25 may include an apparatus according to embodiment 23, wherein the instructions, when executed by the processor, further configure the apparatus to: receive an RRC configuration based on the capability information and / or the preference information from the base station.

[0148] Embodiment 26 may include the apparatus of embodiment 25, wherein the RRC configuration includes one or more of: a level of cooperation between the UE and the base station or when to stop using AI.

[0149] Embodiment 27 may include a device in a base station, the device comprising: a processor; and a memory, the memory storing instructions that, when executed by the processor, configure the device to: train an artificial intelligence (AI) model; and configure the trained AI model to a user equipment (UE) via an uplink radio resource control (RRC) message.

[0150] Embodiment 28 may include an apparatus according to embodiment 27, wherein the RRC message supports segmentation to include data of the trained AI model with a high payload size.

[0151] Embodiment 29 may include an apparatus according to embodiment 27, wherein the instructions, when executed by the processor, further configure the apparatus to: check the AI ​​capabilities and / or AI preferences of the UE before transmitting the AI ​​model to the UE.

[0152] Embodiment 30 may include an apparatus according to embodiment 29, wherein the instructions, when executed by the processor, further configure the apparatus to: receive capability information indicating the AI ​​capability of the UE and / or preference information indicating the AI ​​preference of the UE from the UE; determine an RRC configuration based on the capability information and / or the preference information; and transmit the RRC configuration to the UE.

[0153] Embodiment 31 may include the apparatus of embodiment 30, wherein the RRC configuration includes one or more of: a level of cooperation between the UE and the base station or when to stop using AI.

[0154] Unless otherwise expressly stated, any of the above embodiments may be combined with any other embodiment (or combination of embodiments). The foregoing description of one or more specific implementations provides illustration and description, but is not intended to be exhaustive or to limit the scope of the embodiments to the precise form disclosed. In view of the above teachings, modifications and variations are possible or can be obtained from the practice of various embodiments.

[0155] Embodiments and implementations of the systems and methods described herein may include various operations that may be embodied in machine executable instructions to be executed by a computer system. A computer system may include one or more general or special purpose computers (or other electronic devices). A computer system may include hardware components that include specific logic components for performing operations; or may include a combination of hardware, software, and / or firmware.

[0156] It should be appreciated that the systems described herein include descriptions of specific embodiments. These embodiments may be combined into a single system, partially combined into other systems, separated into multiple systems, or otherwise divided or combined. In addition, it is contemplated that parameters, attributes, aspects, etc. of another embodiment may be used in one embodiment. For clarity, these parameters, attributes, aspects, etc. are described only in one or more embodiments, and it should be appreciated that these parameters, attributes, aspects, etc. may be combined with or substituted for parameters, attributes, aspects, etc. of another embodiment unless expressly stated herein.

[0157] It is well known that the use of personally identifiable information should be subject to privacy policies and practices that are generally recognized to meet or exceed industry or government requirements for maintaining user privacy. Specifically, personally identifiable information data should be managed and processed to minimize the risk of unintentional or unauthorized access or use, and the nature of the authorized use should be clearly stated to users.

[0158] Although the foregoing has been described in considerable detail for the sake of clarity, it will be apparent that certain changes and modifications may be made without departing from the principles of the invention. It should be noted that there are many alternative ways to implement both the processes and the apparatus described herein. Therefore, the embodiments of the present invention should be regarded as illustrative rather than restrictive, and the specification is not limited to the details given herein, but may be modified within the scope and equivalents of the appended claims.

Claims

1. A device of a user equipment (UE), the device comprising: processor; and a memory storing instructions that, when executed by the processor, configure the apparatus to: receiving an artificial intelligence (AI) model from a base station; Obtaining a trained AI model generated by training the AI ​​model; and The trained AI model is transmitted to the base station via an uplink radio resource control (RRC) message.

2. The apparatus of claim 1, wherein the AI ​​model is received in a transparent container via a downlink RRC message.

3. The apparatus of claim 1, wherein the AI ​​model is received via a user plane.

4. The apparatus of claim 1, wherein the AI ​​model is received from the base station as an RRC configuration.

5. The apparatus of claim 1 , wherein the instructions, when executed by the processor, further configure the apparatus to: The trained AI model is obtained by training the AI ​​model at the UE.

6. The apparatus of claim 1, wherein the instructions, when executed by the processor, further configure the apparatus to: Sending the AI ​​model to a server; and The trained AI model is obtained by receiving the training result of the AI ​​model from the server.

7. The apparatus of claim 6, wherein the instructions, when executed by the processor, further configure the apparatus to: A status indication for the AI ​​model is received from the server, wherein the status indication indicates at least one of a result of checking compatibility of the AI ​​model with the UE or a result of the training of the AI ​​model.

8. The apparatus of claim 1, wherein the instructions, when executed by the processor, further configure the apparatus to: One or more of the following is reported to the base station: capability information indicating an AI capability of the UE or preference information indicating an AI preference of the UE. 9 . The apparatus according to claim 8 , wherein the preference information comprises one or more of the following: whether the UE prefers to use AI or how long the UE prefers to use AI.

10. The apparatus of claim 8, wherein the instructions, when executed by the processor, further configure the apparatus to: An RRC configuration based on the capability information and / or the preference information is received from the base station.

11. The apparatus of claim 10, wherein the RRC configuration comprises one or more of: a level of cooperation between the UE and the base station or when to stop using AI.

12. A device in a base station, the device comprising: processor; and a memory storing instructions that, when executed by the processor, configure the apparatus to: transmitting an artificial intelligence (AI) model to a user equipment (UE); and A trained AI model generated by the training of the AI ​​model is received from the UE via an uplink radio resource control (RRC) message.

13. The apparatus of claim 12, wherein the AI ​​model is transmitted in a transparent container of an RRC message.

14. The apparatus of claim 12, wherein the AI ​​model is transmitted as an RRC configuration.

15. The apparatus of claim 12, wherein the AI ​​model is transmitted via a user plane.

16. The apparatus of claim 12, wherein the instructions, when executed by the processor, further configure the apparatus to: utilizing the trained AI model to perform inference; or Model fusion is performed based on the training results of the AI ​​model at the base station and the trained AI model from the UE.

17. The apparatus of claim 12, wherein the instructions, when executed by the processor, further configure the apparatus to: Before transmitting the AI ​​model to the UE, the AI ​​capability and / or AI preference of the UE is checked.

18. The apparatus of claim 17, wherein the instructions, when executed by the processor, further configure the apparatus to: receiving, from the UE, capability information indicating an AI capability of the UE and / or preference information indicating an AI preference of the UE; determining an RRC configuration based on the capability information and / or the preference information; as well as The RRC configuration is transmitted to the UE.

19. The apparatus of claim 18, wherein the RRC configuration comprises one or more of: a level of cooperation between the UE and the base station or when to stop using AI.

20. A device of a user equipment (UE), the device comprising: processor; and a memory storing instructions that, when executed by the processor, configure the apparatus to: receiving an artificial intelligence (AI) model trained by a base station via a downlink radio resource control (RRC) message; and Inference is performed using the trained AI model.

21. The apparatus of claim 20, wherein the RRC message supports segmentation to include data of the AI ​​model with a high payload size.

22. The apparatus of claim 20, wherein the trained AI model is identified by a model ID.

23. The apparatus of claim 20, wherein the instructions, when executed by the processor, further configure the apparatus to: One or more of the following is reported to the base station: capability information indicating an AI capability of the UE or preference information indicating an AI preference of the UE.

24. The apparatus of claim 23, wherein the preference information comprises one or more of: whether the UE prefers to use AI or how long the UE prefers to use AI.

25. The apparatus of claim 23, wherein the instructions, when executed by the processor, further configure the apparatus to: An RRC configuration based on the capability information and / or the preference information is received from the base station.

26. The apparatus of claim 25, wherein the RRC configuration comprises one or more of: a level of cooperation between the UE and the base station or when to stop using AI.

27. A device in a base station, the device comprising: processor; and a memory storing instructions that, when executed by the processor, configure the apparatus to: Training artificial intelligence (AI) models; and The trained AI model is configured to a user equipment (UE) via an uplink radio resource control (RRC) message.

28. The device of claim 27, wherein the RRC message supports segmentation to include data of the trained AI model with a high payload size.

29. The apparatus of claim 27, wherein the instructions, when executed by the processor, further configure the apparatus to: Before transmitting the AI ​​model to the UE, the AI ​​capability and / or AI preference of the UE is checked.

30. The apparatus of claim 29, wherein the instructions, when executed by the processor, further configure the apparatus to: receiving, from the UE, capability information indicating an AI capability of the UE and / or preference information indicating an AI preference of the UE; determining an RRC configuration based on the capability information and / or the preference information; as well as The RRC configuration is transmitted to the UE.

31. The apparatus of claim 30, wherein the RRC configuration comprises one or more of: a level of cooperation between the UE and the base station or when to stop using AI.

Images