AI / ML model management and activation / deactivation

Abstract

Apparatus, systems, and methods for AI / ML model management and activation / deactivation. A wireless device including at least one antenna and a processor is configured to: receive a configuration message from a network device, the configuration message including indication information of a list of artificial intelligence (AI) models, where the configuration message further includes an activation field indicating a first AI model to be activated in the list of AI models; and activating the first AI model indicated by the activation field.

Description

Technical Field

[0001] The present application as a whole relates to wireless communication systems, including devices, systems and methods for AI / ML model management and activation / deactivation in wireless communication systems. Background Art

[0002] Wireless mobile communication technologies use 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 its communication services with external entities through its connection to the Core Network (CN). For example, E-UTRAN may utilize the Evolved Packet Core (EPC) while NG-RAN may utilize the 5G Core Network (5GC).

[0007] Artificial intelligence (AI) is the simulation of human intelligence processes by machines, usually computer systems. Machine learning (ML) is a subset of AI that creates algorithms and statistical models to perform specific tasks without explicit instructions, but instead relies on patterns and reasoning. ML algorithms build mathematical models based on sample data, called training data, to make predictions or decisions without being specifically programmed for the task. Learned signal processing algorithms can support next-generation wireless systems with significantly reduced power consumption and improved density, throughput, and accuracy when compared to today's fragile, manually designed systems. Summary of the invention

[0008] The present disclosure provides apparatus, systems, and methods for AI / ML model management and activation / deactivation in wireless communication systems.

[0009] The embodiments disclosed herein include a wireless device comprising: at least one antenna; and a processor configured to: receive a configuration message from a network device, the configuration message comprising indication information of an artificial intelligence (AI) model list, wherein the configuration message also comprises an activation field, the activation field indicating a first AI model to be activated in the AI ​​model list; and activate the first AI model indicated by the activation field.

[0010] The embodiments disclosed herein include a network device comprising: at least one antenna; and a processor configured to: receive capability information indicating AI capabilities from a wireless device; and send a configuration message to the wireless device, the configuration message including indication information of an artificial intelligence (AI) model list, wherein the configuration message also includes an activation field indicating a first AI model to be activated in the AI ​​model list.

[0011] The embodiments disclosed herein include a method performed by a wireless device, the method comprising: receiving a configuration message from a network device, the configuration message including indication information of an artificial intelligence (AI) model list, wherein the configuration message also includes an activation field, the activation field indicating a first AI model to be activated in the AI ​​model list; and activating the first AI model indicated by the activation field.

[0012] The embodiments disclosed herein include a method performed by a network device, the method comprising: receiving capability information indicating AI capabilities from a wireless device; and sending a configuration message to the wireless device, the configuration message including indication information of an artificial intelligence (AI) model list, wherein the configuration message also includes an activation field indicating a first AI model to be activated in the AI ​​model list.

[0013] The embodiments disclosed herein include a non-transitory computer-readable storage medium having instructions stored thereon, which, when executed by a processor of a wireless device, causes the processor to: receive a configuration message from a network device, the configuration message including indication information of an artificial intelligence (AI) model list, wherein the configuration message also includes an activation field, the activation field indicating a first AI model to be activated in the AI ​​model list; and activate the first AI model indicated by the activation field.

[0014] The embodiments disclosed herein include a non-transitory computer-readable storage medium having instructions stored thereon, which, when executed by a processor of a network device, causes the processor to: receive capability information indicating AI capabilities from a wireless device; and send a configuration message to the wireless device, the configuration message including indication information of an artificial intelligence (AI) model list, wherein the configuration message also includes an activation field indicating a first AI model to be activated in the AI ​​model list. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] 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.

[0016] Figure 1 An example architecture of a wireless communication system according to embodiments disclosed herein is illustrated.

[0017] Figure 2 A system for performing signaling between a wireless device and a network device according to embodiments disclosed herein is illustrated.

[0018] Figure 3 An example functional framework of AI / ML in a wireless communication system according to the embodiments disclosed herein is illustrated.

[0019] Figure 4 An example communication process between a UE and a gNB for model configuration and activation according to an embodiment disclosed herein is illustrated.

[0020] Figure 5 An example communication process between a UE and a gNB for model switching according to an embodiment disclosed herein is illustrated.

[0021] Fig. 6A An example communication process between a UE and a gNB for conditional model deactivation according to an embodiment disclosed herein is illustrated.

[0022] Figure 6B Another example communication process between a UE and a gNB for conditional model deactivation according to an embodiment disclosed herein is illustrated.

[0023] Figure 7 An example communication process between a UE and a gNB for model management according to an embodiment disclosed herein is illustrated.

[0024] Figure 8 An example method performed by a wireless device according to embodiments disclosed herein is illustrated.

[0025] Fig. 9 An example method performed by a network device according to embodiments disclosed herein is illustrated. DETAILED DESCRIPTION

[0026] Various embodiments are described with respect to UE. However, reference to UE is provided for illustrative purposes only. The example embodiments may be used with any wireless device 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 described herein is used to represent any suitable network-wired device.

[0027] Various embodiments are described with respect to gNBs. However, references to gNBs are provided for illustrative purposes only. The example embodiments may be used with any network device in a network and configured with hardware, software, and / or firmware to implement any functionality of the network. Thus, gNB as described herein is used to represent any suitable network device.

[0028] Figure 1 An example architecture of a wireless communication system 100 according to embodiments 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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).

[0035] 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).

[0036] 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).

[0037] 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).

[0038] 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.

[0039] Figure 2 A system 200 for performing signaling 234 between a wireless device 202 and a network device 218 according to embodiments 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.

[0040] 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.

[0041] 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.

[0042] 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.

[0043] The wireless device 202 may include one or more antennas 212 (e.g., one, two, four, or more). 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 separate data streams may be directed to separate (different) receivers in different locations in the spatial domain).

[0044] 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).

[0045] The wireless device 202 may include one or more interfaces 214. The interfaces 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, 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 communication between the UE and other devices (e.g., in addition to the transceiver 210 / antenna 212 described above), and may be based on known protocols (e.g., etc.) to perform the operation.

[0046] 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.

[0047] 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.

[0048] 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.

[0049] The network device 218 may include one or more antennas 228 (eg, one, two, four, or more). In embodiments with multiple antennas 228, the network device 218 may perform MIMO, digital beamforming, analog beamforming, beamsteering, etc. as described.

[0050] 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.

[0051] AI / ML can be applied to wireless communication systems. Use cases include channel state information (CSI) feedback enhancement (e.g., overhead reduction, improved accuracy and prediction), beam management (BM) (e.g., beam prediction in time, spatial domain for overhead and latency reduction, and beam selection accuracy improvement), and positioning accuracy enhancement for different scenarios (including, for example, those with severe NLOS conditions).

[0052] Implementations contemplated herein provide AI / ML model management and activation / deactivation in wireless communication systems.

[0053] Figure 3 An example functional framework of AI / ML in a wireless communication system according to the embodiments disclosed herein is illustrated.

[0054] Data collection 302 is a function that provides input data to the model training and model reasoning functions. No AI / ML algorithm specific data preparation (e.g., data preprocessing and cleaning, formatting, and transformation) is performed in the data collection function. Examples of input data may include measurements from UEs or different network entities, feedback from actors, outputs from AI / ML models. Training data is data required as input to the AI / ML model training function. Reasoning data is data required as input to the AI / ML model reasoning function.

[0055] Model training 304 is a function that performs AI / ML model training, validation, and testing, which can generate model performance metrics as part of the model testing process. The model training function is also responsible for data preparation (e.g., data preprocessing and cleaning, formatting, and transformation) based on the training data delivered by the data collection function, if necessary. Model deployment / update is the initial deployment of the trained, validated, and tested AI / ML model to the model reasoning function or the delivery of an updated model to the model reasoning function.

[0056] Model reasoning 306 is a function that provides AI / ML model reasoning output (e.g., prediction or decision). When applicable, the model reasoning function can provide model performance feedback to the model training function. If necessary, the model reasoning function is also responsible for data preparation (e.g., data preprocessing and cleaning, formatting, and transformation) based on the reasoning data delivered by the data collection function. The output is the reasoning output of the AI / ML model produced by the model reasoning function. The details of the reasoning output are use case specific. When available, model performance feedback can be used to monitor the performance of the AI / ML model.

[0057] The actor 308 is a function that receives output from the model reasoning function and triggers or executes the corresponding action. The actor can trigger actions for other entities or for itself. Feedback is the information needed to derive training data, reasoning data, or monitor the performance of the AI / ML model and its impact on the network by updating KPIs and performance counters.

[0058] An example communication process will be described below to illustrate various aspects of the present disclosure. The example communication process is described with respect to AI. However, reference to AI is provided for illustrative purposes only and may be replaced with ML.

[0059] Figure 4 An example communication process between a UE and a gNB for model configuration and activation according to an embodiment disclosed herein is illustrated.

[0060] Before model configuration, the UE and the gNB may perform UE capability exchange regarding AI to determine which AI models can be applied to the UE. In step 402, when the gNB needs to know the UE's capabilities regarding AI, the gNB sends a capability query to the UE. In step S404, in response to the received capability query, the UE sends capability information to the gNB. The capability information may indicate the UE's capabilities regarding AI. Using the capability information, the gNB may determine which AI models can be applied to the UE.

[0061] In step S406, the gNB sends a configuration message to the UE to configure the AI ​​model list to the UE. The configuration message may include indication information of the AI ​​model list that can be used by the UE and may be in the form of a radio resource control (RRC) reconfiguration message. The indication information of the AI ​​model list may include a model ID of each AI model in the AI ​​model list. In step S408, in response to the received configuration message, the UE sends a configuration completion message to the gNB.

[0062] Only one configured AI model may be activated for a UE at a time. The initial state of the configured AI model may be deactivated. The gNB may notify the UE of the AI ​​model to be activated in various ways.

[0063] In some embodiments disclosed herein, the configuration message may include an activation field indicating an AI model to be activated (e.g., model A) in the AI ​​model list. For example, the activation field may include an index of the AI ​​model to be activated (e.g., model A). Therefore, when the configuration message is received in step S412, the UE directly activates the AI ​​model (e.g., model A). In the case where only one AI model is configured in the configuration message, the AI ​​model may be considered to be activated by default.

[0064] In some embodiments disclosed herein, at step S410, the gNB may send a model activation command to the UE to indicate the AI ​​model to be activated in the AI ​​model list (e.g., model A). Therefore, at step S412, upon receiving the model activation command, the UE activates the AI ​​model (e.g., model A).

[0065] The model activation command may be in the form of a medium access control (MAC) control element (CE) or downlink control information (DCI). A mapping of at least a subset of the AI ​​model list to code points of the MAC CE / DCI may be included in a configuration message. Thus, the gNB may notify the UE via MAC CE / DCI to activate any AI model in the subset. For AI models not in the subset, the model activation command may be in the form of an additional configuration message. The additional configuration message may include indication information of the AI ​​model to be activated.

[0066] In addition, one or more of the AI ​​models may be configured with a slice range. For example, the configuration message may include applicable slice information indicating applicable slices for the AI ​​model. The AI ​​model will only apply to operations / data related to the indicated applicable slices.

[0067] Figure 5 An example communication process between a UE and a gNB for model switching according to an embodiment disclosed herein is illustrated. Initially, it is assumed that model A is activated at the UE in step S502. In the event that a decision is made to switch to a new AI model (e.g., model B) configured in a configuration message in the AI ​​model list (e.g., in response to performance degradation), then in step S504, the gNB sends a model activation command indicating the new AI model to the UE. In the event that the new model has been mapped to a code point of a MAC CE or DCI in the configuration message, the model activation command may be in the form of a MAC CE / DCI. In the event that the new model has not been mapped to a code point of a MAC CE or DCI in the configuration message, the model activation command may be in the form of an additional configuration message. The additional configuration message may include indication information of the new AI model to be activated. In step S506, the UE activates the new AI model (e.g., model B) upon receiving the model activation command.

[0068] The AI ​​model activated at the UE may be associated with one or more deactivation conditions configured by the gNB via a configuration message. If one of the deactivation conditions for the AI ​​model is met, the AI ​​model may be deactivated at the UE. Table 1 lists some examples of deactivation conditions.

[0069] Table 1

[0070] Deactivation conditions UE battery < threshold Radio quality (RSRP / RSRQ / SINR) < threshold UE moving speed > threshold Indoor->Outdoor or Outdoor->Indoor Height > Threshold or Height < Threshold Outside of geographic location Inference accuracy < threshold Inference completeness < threshold Inference wait time > threshold Verify duration > threshold

[0071] Fig. 6AAn example communication process between a UE and a gNB for conditional model deactivation according to an embodiment disclosed herein is illustrated. Initially, assume that model A is activated at the UE in step S602. In step S604, the UE determines that the deactivation condition for model A is met. In step S606a, the UE deactivates model A, selects and activates a new AI model (e.g., model C) in the AI ​​model list configured by the gNB via a configuration message. When the UE selects a new AI model, it may consider the deactivation condition (if any) associated with the new AI model. The UE may select a new AI model that does not meet the deactivation condition so that the new AI model can match the current communication condition of the UE. In step S608a, the UE sends a model activation notification to the gNB to indicate that the new AI model (e.g., model C) is activated. The model activation notification may include indication information of the new AI model and may be in the form of user assistance information (UAI).

[0072] Figure 6B Another example communication process between a UE and a gNB for conditional model deactivation according to an embodiment disclosed herein is illustrated. Initially, it is assumed that model A is activated at the UE in step S602. In step S604, the UE determines that the deactivation condition for model A is met. In step S606b, the UE deactivates model A and selects another AI model (e.g., model C). When the UE selects a new AI model, it may consider the deactivation condition (if any) associated with the new AI model. The UE may select a new AI model that does not meet the deactivation condition so that the new AI model can match the current communication condition of the UE.

[0073] However, with Fig. 6A Unlike the process in step S608b, the UE does not immediately activate the selected AI model. Instead, in step S608b, the UE sends a model activation request to the gNB requesting switching to the selected AI model. The model activation request may include indication information of the selected AI model and may be in the form of user assistance information (UAI).

[0074] In step S610b, the gNB sends a model activation command indicating a new AI model to the UE. The new AI model may be the AI ​​model selected by the UE, or it may be a different AI model selected by the gNB. In the case where the new AI model has been mapped to a code point of the MAC CE / DCI in the configuration message, the model activation command may be in the form of a MAC CE / DCI. In the case where the new model has not been mapped to a code point of the MAC CE / DCI in the configuration message, the model activation command may be in the form of an additional configuration message. The additional configuration message may include indication information of the new AI model to be activated.

[0075] In step S612b, the UE activates the new AI model upon receiving the model activation command. Figure 6B , the gNB instructs the UE to switch to an AI model selected by the UE. However, the gNB may instruct the UE to switch to a different AI model selected by the gNB.

[0076] In the event that all AI models in the existing AI model list have been disabled, the UE may stop using AI and may return to a conventional method without using AI for certain functionalities (e.g., CSI feedback, beam management, positioning, etc.).

[0077] In addition, the gNB can perform management on AI models in the existing AI model list. Figure 7 An example communication process between a UE and a gNB for model management according to an embodiment disclosed herein is illustrated.

[0078] The model management can be initiated by the UE or the gNB. In the case of being initiated by the UE, in step S702, the UE may send a model change request to the gNB. The model change request may include a preferred change to the existing AI model list and may be in the form of user assistance information (UAI). In response to the received model change request, in step S704, the gNB may send a model change command to the UE to indicate the change to the existing AI model list. The indicated changes included in the model change command may be different from the requested changes included in the model change request. That is, in the case where the gNB believes that different changes may be more appropriate, it may include different changes in the model change command.

[0079] In the case of initiation by gNB, in step S704, gNB may actively send a model change command to UE. In response to the model change command, in step S708, UE sends a change completion message to gNB.

[0080] Changes to the AI ​​model list may include one or more of model addition, model release, or model modification. Model addition is to add at least one new AI model to the existing AI model list. Model release is to release at least one model from the existing AI model list. Model modification is to modify at least one model in the existing AI model list (for example, changes in some parameters of some layers of a deep learning model, or re-moving / adding some inputs to the model).

[0081] In the case that all AI models have been released from the list, the UE may stop using AI and may fall back to the legacy method without using AI for certain functions (e.g., CSI feedback, beam management, positioning, etc.). In addition, the UE may send user assistance information (UAI) including its preference for AI to the gNB. The preference may include whether the UE prefers to use AI or the legacy method.

[0082] Various embodiments are described above with respect to UE and gNB. However, as previously indicated, UE as described herein is used to represent any suitable wireless device, and gNB as described herein is used to represent any suitable network device.

[0083] Figure 8 An example method performed by a wireless device according to an embodiment disclosed herein is illustrated. In step S802, the wireless device sends capability information indicating AI capabilities to a network device. The network device may use the capability information to determine which AI models can be applied to the wireless device. In step S804, the wireless device receives a configuration message from the network device, the configuration message including indication information of an artificial intelligence (AI) model list, wherein the configuration message also includes an activation field, the activation field indicating a first AI model to be activated in the AI ​​model list. In step S806, the wireless device activates the first AI model indicated by the activation field. In the case of deciding to deactivate the first AI model and switch to a second AI model, steps S808 and S810 may be performed. In step S808, the wireless device receives a model activation command from the network device, the model activation command indicating a second AI model to be activated in the AI ​​model list. In step S810, the wireless device switches to the second AI model upon receiving the model activation command. That is, the wireless device deactivates the first AI model and activates the second AI model.

[0084] Any of the steps described above with reference to the UE may be performed by the wireless device and are not repeated here for the sake of brevity. Figure 8 All steps shown in are required, and the wireless device may perform only one or more of these steps.

[0085] Fig. 9An example method performed by a network device according to an embodiment disclosed herein is illustrated. In step S902, the network device receives capability information indicating AI capabilities from a wireless device. The network device can use the capability information to determine which AI models can be applied to the wireless device. In step S904, the network device sends a configuration message to the wireless device, the configuration message including indication information of an artificial intelligence (AI) model list, wherein the configuration message also includes an activation field, the activation field indicating the first AI model to be activated in the AI ​​model list. In the event that a decision is made to deactivate the first AI model and switch to the second AI model, step S906 can be performed. In step S906, the network device sends a model activation command to the wireless device, and the model activation command indicates the second AI model to be activated in the AI ​​model list.

[0086] Any of the steps described above with reference to the gNB may be performed by the network device and are not repeated here for the sake of brevity. Fig. 9 All steps shown in are required, and a network device may perform only one or more of these steps.

[0087] The embodiments contemplated herein include a wireless device comprising: at least one antenna; and a processor configured to: receive a configuration message from a network device, the configuration message comprising indication information of a list of artificial intelligence (AI) models, wherein the configuration message also comprises an activation field, the activation field indicating a first AI model to be activated in the list of AI models; and activate the first AI model indicated by the activation field.

[0088] In some embodiments of the present disclosure, the indication information of the AI ​​model list includes the model ID of the AI ​​model list.

[0089] In some embodiments of the present disclosure, the configuration message is an RRC reconfiguration message.

[0090] In some embodiments of the present disclosure, the processor is further configured to send capability information indicating AI capabilities to the network device.

[0091] In some embodiments of the present disclosure, the processor is further configured to: receive a model activation command from the network device, the model activation command indicating a second AI model to be activated in the AI ​​model list; and switch to the second AI model upon receiving the model activation command.

[0092] In some embodiments of the present disclosure, the model activation command is a MAC CE or a DCI, and the configuration message includes a mapping of at least a subset of the AI ​​model list to code points of the MAC CE or the DCI, and the subset includes the second AI model.

[0093] In some embodiments of the present disclosure, the model activation command is an additional configuration message, and the additional configuration message includes indication information of the second AI model.

[0094] In some embodiments of the present disclosure, the configuration message also includes a deactivation condition associated with the AI ​​model in the AI ​​model list.

[0095] In some embodiments of the present disclosure, the deactivation condition includes one or more of the following: the battery of the wireless device is below a threshold; the radio quality of the wireless device is below a threshold; the moving speed of the wireless device is above a threshold; the wireless device moves from indoors to outdoors or from outdoors to indoors; the height of the wireless device is above a threshold or below a threshold; the wireless device is outside the geographic location range; the inference accuracy of the wireless device is below a threshold; the inference completeness of the wireless device is below a threshold; the inference waiting time of the wireless device is above a threshold; or the verification duration of the wireless device is above a threshold.

[0096] In some embodiments of the present disclosure, the processor is further configured to: deactivate the currently activated AI model if a deactivation condition associated with the currently activated AI model is met.

[0097] In some embodiments of the present disclosure, the processor is further configured to: select a third AI model to be activated from the AI ​​model list; and send indication information of the selected third AI model to the network device.

[0098] In some embodiments of the present disclosure, the processor is further configured to stop using the AI ​​if all AI models in the AI ​​model list have been deactivated.

[0099] In some embodiments of the present disclosure, the processor is also configured to receive a model change command from the network device, the model change command comprising a change to the AI ​​model list, and the change to the AI ​​model list comprises one or more of model addition, model release, or model modification.

[0100] In some embodiments of the present disclosure, the processor is further configured to send the preferred changes to the AI ​​model list to the network device.

[0101] In some embodiments of the present disclosure, the processor is further configured to send user assistance information (UAI) including its preference for AI to the network device.

[0102] In some embodiments of the present disclosure, the configuration message also includes applicable slice information associated with the AI ​​model in the AI ​​model list.

[0103] Embodiments contemplated herein include an apparatus including means for performing one or more elements of a method including: receiving a configuration message from a network device, the configuration message including indication information of an artificial intelligence (AI) model list, wherein the configuration message also includes an activation field, the activation field indicating a first AI model to be activated in the AI ​​model list; and activating the first AI model indicated by the activation field. The apparatus may be, for example, an apparatus of a UE (such as a wireless device 202 as a UE, as described herein).

[0104] Embodiments contemplated herein include one or more non-transitory computer-readable media including instructions to cause an electronic device, when executed by one or more processors of the electronic device, to perform one or more elements of a method including: receiving a configuration message from a network device, the configuration message including an indication of an artificial intelligence (AI) model list, wherein the configuration message also includes an activation field indicating a first AI model to be activated in the AI ​​model list; and activating the first AI model indicated by the activation field. 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).

[0105] Embodiments contemplated herein include an apparatus including logic, modules, or circuits for performing one or more elements of a method including: receiving a configuration message from a network device, the configuration message including an indication of an artificial intelligence (AI) model list, wherein the configuration message also includes an activation field, the activation field indicating a first AI model to be activated in the AI ​​model list; and activating the first AI model indicated by the activation field. The apparatus may be, for example, an apparatus of a UE (such as a wireless device 202 as a UE, as described herein).

[0106] Embodiments contemplated herein include an apparatus comprising: one or more processors and one or more computer-readable media, the 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 one or more elements of a method comprising: receiving a configuration message from a network device, the configuration message comprising an indication of an artificial intelligence (AI) model list, wherein the configuration message further comprises an activation field, the activation field indicating a first AI model in the AI ​​model list to be activated; and activating the first AI model indicated by the activation field. The apparatus may be, for example, an apparatus of a UE (such as a wireless device 202 as a UE, as described herein).

[0107] Embodiments contemplated herein include a signal as described in or relating to one or more elements of a method comprising the following items: receiving a configuration message from a network device, the configuration message including indication information of a list of artificial intelligence (AI) models, wherein the configuration message also includes an activation field, the activation field indicating a first AI model to be activated in the list of AI models; and activating the first AI model indicated by the activation field.

[0108] Embodiments contemplated herein include a computer program or computer program product including instructions, wherein the program is executed by a processor so that the processor performs one or more elements of a method including the following items: receiving a configuration message from a network device, the configuration message including an indication of an artificial intelligence (AI) model list, wherein the configuration message also includes an activation field, the activation field indicating the first AI model to be activated in the AI ​​model list; and activating the first AI model indicated by the activation field. The processor can be a processor of a UE (such as processor 204 of wireless device 202 as a UE, as described herein). These instructions can be located, for example, in a processor and / or on a memory of a UE (such as memory 206 of wireless device 202 as a UE, as described herein).

[0109] The embodiments contemplated herein include a network device, the wireless device comprising: at least one antenna; and a processor configured to: receive capability information indicating AI capabilities from the wireless device; and send a configuration message to the wireless device, the configuration message including indication information of an artificial intelligence (AI) model list, wherein the configuration message also includes an activation field indicating a first AI model to be activated in the AI ​​model list.

[0110] In some embodiments of the present disclosure, the indication information of the AI ​​model list includes the model ID of the AI ​​model list.

[0111] In some embodiments of the present disclosure, the configuration message is an RRC reconfiguration message.

[0112] In some embodiments of the present disclosure, the processor is further configured to receive capability information indicating AI capabilities from the wireless device.

[0113] In some embodiments of the present disclosure, the processor is further configured to send a model activation command to the wireless device, and the model activation command indicates a second AI model in the AI ​​model list to be activated.

[0114] In some embodiments of the present disclosure, the model activation command is a MAC CE or a DCI, and the configuration message further includes a mapping of at least a subset of the AI ​​model list to code points of the MAC CE or the DCI, the subset including a second AI model, or the model activation command is an additional configuration message including indication information of the second AI model.

[0115] In some embodiments of the present disclosure, the configuration message also includes a deactivation condition associated with the AI ​​model in the AI ​​model list.

[0116] In some embodiments of the present disclosure, the deactivation condition includes one or more of the following: the battery of the wireless device is below a threshold; the radio quality of the wireless device is below a threshold; the moving speed of the wireless device is above a threshold; the wireless device moves from indoors to outdoors or from outdoors to indoors; the height of the wireless device is above a threshold or below a threshold; the wireless device is outside the geographic location range; the inference accuracy of the wireless device is below a threshold; the inference completeness of the wireless device is below a threshold; the inference waiting time of the wireless device is above a threshold; or the verification duration of the wireless device is above a threshold.

[0117] In some embodiments of the present disclosure, the processor is further configured to receive indication information of the selected third AI model from the wireless device.

[0118] In some embodiments of the present disclosure, the processor is also configured to send a model change command to the wireless device, the model change command including a change in the AI ​​model list, and the change in the AI ​​model list includes one or more of model addition, model release, or model modification.

[0119] In some embodiments of the present disclosure, the processor is further configured to receive user assistance information (UAI) including a preference for AI from the wireless device.

[0120] In some embodiments of the present disclosure, the configuration message also includes applicable slice information associated with the AI ​​model in the AI ​​model list.

[0121] Embodiments contemplated herein include an apparatus including means for performing one or more elements of a method including: receiving capability information indicating AI capabilities from a wireless device; and sending a configuration message to the wireless device, the configuration message including information indicating an artificial intelligence (AI) model list, wherein the configuration message also includes an activation field indicating a first AI model in the AI ​​model list to be activated. The apparatus may be, for example, an apparatus of a base station (such as network device 218 as a base station, as described herein).

[0122] Embodiments contemplated herein include one or more non-transitory computer-readable media including instructions to cause an electronic device, when executed by one or more processors of the electronic device, to perform one or more elements of a method including: receiving capability information indicating AI capabilities from a wireless device; and sending a configuration message to the wireless device, the configuration message including information indicating an artificial intelligence (AI) model list, wherein the configuration message also includes an activation field indicating a first AI model in the AI ​​model list to be activated. The non-transitory computer-readable medium may be, for example, a memory of a base station (such as memory 222 of network device 218 as a base station, as described herein).

[0123] Embodiments contemplated herein include an apparatus including logic, modules, or circuits for performing one or more elements of a method including: receiving capability information indicating AI capabilities from a wireless device; and sending a configuration message to the wireless device, the configuration message including information indicating an artificial intelligence (AI) model list, wherein the configuration message also includes an activation field indicating a first AI model in the AI ​​model list to be activated. The apparatus may be, for example, an apparatus of a base station (such as a network device 218 as a base station, as described herein).

[0124] Embodiments contemplated herein include an apparatus comprising: one or more processors and one or more computer-readable media, the 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 one or more elements of a method comprising: receiving capability information indicating AI capabilities from a wireless device; and sending a configuration message to the wireless device, the configuration message including an indication of an artificial intelligence (AI) model list, wherein the configuration message also includes an activation field indicating a first AI model in the AI ​​model list to be activated. The apparatus may be, for example, an apparatus of a base station (such as network device 218 as a base station, as described herein).

[0125] Embodiments contemplated herein include a signal as described in or relating to one or more elements of a method comprising: receiving capability information indicating AI capabilities from a wireless device; and sending a configuration message to the wireless device, the configuration message including indicative information of a list of artificial intelligence (AI) models, wherein the configuration message also includes an activation field indicating a first AI model in the list of AI models to be activated.

[0126] Embodiments contemplated herein include a computer program or computer program product including instructions, wherein execution of the program by a processing element causes the processing element to perform one or more elements of a method including: receiving capability information indicating AI capabilities from a wireless device; and sending a configuration message to the wireless device, the configuration message including information indicating a list of artificial intelligence (AI) models, wherein the configuration message also includes an activation field indicating a first AI model in the list of AI models to be activated. 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). For example, the instructions may be located in a processor and / or on a memory of a base station (such as memory 222 of network device 218 as a base station, as described herein).

[0127] 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, circuits 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.

[0128] 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.

[0129] 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 for performing operations; or may include a combination of hardware, software, and / or firmware.

[0130] 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.

[0131] It is understood 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.

[0132] 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 wireless device, comprising: at least one antenna; and A processor, the processor being configured to: receiving a configuration message from a network device, the configuration message including indication information of an artificial intelligence (AI) model list, wherein the configuration message further includes an activation field, the activation field indicating a first AI model to be activated in the AI ​​model list; and The first AI model indicated by the activation field is activated. 2 . The wireless device according to claim 1 , wherein the indication information of the AI ​​model list includes a model ID of the AI ​​model list.

3. The wireless device of claim 1, wherein the configuration message is a radio resource control (RRC) reconfiguration message. 4 . The wireless device of claim 1 , wherein the processor is further configured to send capability information indicating AI capability to the network device.

5. The wireless device of claim 1 , wherein the processor is further configured to: receiving a model activation command from the network device, the model activation command indicating a second AI model in the AI ​​model list to be activated, and Switch to the second AI model upon receiving the model activation command.

6. The wireless device of claim 5, wherein the model activation command is a medium access control (MAC) control element (CE) or downlink control information (DCI), and the configuration message includes a mapping of at least a subset of the AI ​​model list to code points of the MAC CE or the DCI, the subset including the second AI model. 7 . The wireless device according to claim 5 , wherein the model activation command is an additional configuration message, and the additional configuration message includes indication information of the second AI model.

8. The wireless device of claim 1, wherein the configuration message further comprises a deactivation condition associated with an AI model in the AI ​​model list.

9. The wireless device of claim 8, wherein the deactivation condition comprises one or more of the following: the battery of the wireless device is below a threshold; The radio quality of the wireless device is below a threshold; The moving speed of the wireless device is higher than a threshold; The wireless device moves from indoors to outdoors or from outdoors to indoors; The height of the wireless device is above a threshold or below a threshold; The wireless device is out of range of a geographic location; The inference accuracy of the wireless device is below a threshold; the inference integrity of the wireless device is below a threshold; The inferred latency of the wireless device is above a threshold; or The wireless device is authenticated for a duration greater than a threshold.

10. The wireless device of claim 8, wherein the processor is further configured to deactivate the currently activated AI model if the deactivation condition associated with the currently activated AI model is satisfied.

11. The wireless device of claim 10, wherein the processor is further configured to: selecting a third AI model to be activated in the AI ​​model list; and Sending indication information of the selected third AI model to the network device. 12 . The wireless device of claim 1 , wherein the processor is further configured to stop using AI if all AI models in the AI ​​model list have been deactivated.

13. The wireless device of claim 1 , wherein the processor is further configured to receive a model change command from the network device, the model change command comprising a change to the AI ​​model list, and the change to the AI ​​model list comprising one or more of a model addition, a model release, or a model modification.

14. The wireless device of claim 1, wherein the processor is further configured to send a preferred change of the AI ​​model list to the network device.

15. The wireless device of claim 1, wherein the processor is further configured to send user assistance information (UAI) including its preference for AI to the network device.

16. The network device of claim 1, wherein the configuration message further includes applicable slice information associated with the AI ​​model in the AI ​​model list.

17. A network device, comprising: at least one antenna; and A processor, the processor being configured to: receiving capability information indicating AI capabilities from the wireless device; as well as A configuration message is sent to the wireless device, the configuration message including indication information of an artificial intelligence (AI) model list, wherein the configuration message also includes an activation field, the activation field indicating a first AI model to be activated in the AI ​​model list. 18 . The network device according to claim 17 , wherein the indication information of the AI ​​model list comprises a model ID of the AI ​​model list.

19. The network device of claim 17, wherein the configuration message is a radio resource control (RRC) reconfiguration message.

20. The network device of claim 17, wherein the processor is further configured to send a model activation command to the wireless device, and the model activation command indicates a second AI model in the AI ​​model list to be activated.

21. The network device according to claim 20, wherein: The model activation command is a medium access control (MAC) control element (CE) or downlink control information (DCI), and the configuration message also includes a mapping of at least a subset of the AI ​​model list to code points of the MAC CE or the DCI, the subset including the second AI model, or The model activation command is an additional configuration message, and the additional configuration message includes indication information of the second AI model.

22. The network device of claim 17, wherein the configuration message further comprises a deactivation condition associated with an AI model in the AI ​​model list.

23. The network device according to claim 22, wherein the deactivation condition comprises one or more of the following: the battery of the wireless device is below a threshold; The radio quality of the wireless device is below a threshold; The moving speed of the wireless device is higher than a threshold; The wireless device moves from indoors to outdoors or from outdoors to indoors; The height of the wireless device is above a threshold or below a threshold; The wireless device is out of range of a geographic location; The inference accuracy of the wireless device is below a threshold; the inference integrity of the wireless device is below a threshold; The inferred latency of the wireless device is above a threshold; or The wireless device is authenticated for a duration greater than a threshold.

24. The network device of claim 17, wherein the processor is further configured to receive an indication of the selected third AI model from the wireless device.

25. The network device of claim 17, wherein the processor is further configured to send a model change command to the wireless device, the model change command comprising a change to the AI ​​model list, and the change to the AI ​​model list comprising one or more of a model addition, a model release, or a model modification.

26. The network device of claim 17, wherein the processor is further configured to receive user assistance information (UAI) including a preference for AI from the wireless device.

27. The network device of claim 17, wherein the configuration message further includes applicable slice information associated with the AI ​​model in the AI ​​model list.

28. A method performed by a wireless device, the method comprising: receiving a configuration message from a network device, the configuration message including indication information of an artificial intelligence (AI) model list, wherein the configuration message further includes an activation field, the activation field indicating a first AI model to be activated in the AI ​​model list; and The first AI model indicated by the activation field is activated.

29. A method performed by a network device, the method comprising: receiving capability information indicating AI capabilities from the wireless device; as well as A configuration message is sent to the wireless device, the configuration message including indication information of an artificial intelligence (AI) model list, wherein the configuration message also includes an activation field, the activation field indicating a first AI model to be activated in the AI ​​model list.

30. A non-transitory computer-readable storage medium having stored thereon instructions that, when executed by a processor of a wireless device, cause the processor to: receiving a configuration message from a network device, the configuration message including indication information of an artificial intelligence (AI) model list, wherein the configuration message further includes an activation field, the activation field indicating a first AI model to be activated in the AI ​​model list; and The first AI model indicated by the activation field is activated.

31. A non-transitory computer-readable storage medium having stored thereon instructions that, when executed by a processor of a network device, cause the processor to: receiving capability information indicating AI capabilities from the wireless device; and A configuration message is sent to the wireless device, the configuration message including indication information of an artificial intelligence (AI) model list, wherein the configuration message also includes an activation field, the activation field indicating a first AI model to be activated in the AI ​​model list.

Images