Artificial intelligence functionality activation and switching
By enabling UE to transmit activation or switch indications for AI functionalities and configuring network options for switching, the solution addresses the lack of flexibility in existing AI life cycle management systems, enhancing switching efficiency and reducing overhead.
Patent Information
- Application Number
- PCT/CN2024/105302
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-07-12
- Publication Date
- 2025-05-22
AI Technical Summary
Existing mechanisms for artificial intelligence (AI) life cycle management in wireless communications systems lack flexibility, making it difficult for user equipment (UE) to autonomously or semi-autonomously switch between different AI functionalities or configurations.
The implementation of a method that allows UE to transmit indications for activating or switching between available AI functionalities, with network-configured options for switching, including UE semi-autonomous, network-assisted, and network-controlled switching, to reduce signaling overhead and enhance flexibility.
This solution simplifies AI functionality switching, reduces signaling overhead, and enables efficient inference outcomes while allowing UE to make autonomous decisions regarding functionality switching.
Smart Images

Figure CN2024105302_22052025_PF_FP_ABST
Abstract
Description
ARTIFICIAL INTELLIGENCE FUNCTIONALITY ACTIVATION AND SWITCHINGTECHNICAL FIELD
[0001] The present disclosure relates to wireless communications, and more specifically to artificial intelligence and machine learning (AI / ML) in wireless communications.BACKGROUND
[0002] A wireless communications system may include one or multiple network communication devices, such as base stations, which may support wireless communications for one or multiple user communication devices, which may be otherwise known as user equipment (UE) , or other suitable terminology. The wireless communications system may support wireless communications with one or multiple user communication devices by utilizing resources of the wireless communication system (e.g., time resources (e.g., symbols, slots, subframes, frames, or the like) or frequency resources (e.g., subcarriers, carriers, or the like) . Additionally, the wireless communications system may support wireless communications across various radio access technologies including third generation (3G) radio access technology, fourth generation (4G) radio access technology, fifth generation (5G) radio access technology, among other suitable radio access technologies beyond 5G (e.g., sixth generation (6G)) .
[0003] The wireless communications system may support wireless communications, and may include one or more devices, such as UEs, base stations (e.g., gNBs) , network entities, satellites, and / or network equipment (NE) , among other devices, that transmit and / or receive signaling.SUMMARY
[0004] An article “a” before an element is unrestricted and understood to refer to “at least one” of those elements or “one or more” of those elements. The terms “a, ” “at least one, ” “one or more, ” and “at least one of one or more” may be interchangeable. As used herein, including in the claims, “or” as used in a list of items (e.g., a list of items prefaced by a phrase such as “at least one of” or “one or more of” or “one or both of” ) indicates an inclusive list such that, for example, a list of at least one of A, B, or C means A or B or C or AB or AC or BC or ABC (i.e., A and B and C) . Also, as used herein, the phrase “based on” shall not be construed as a reference to a closed set of conditions. For example, an example step that is described as “based on condition A” may be based on both a condition A and a condition B without departing from the scope of the present disclosure. In other words, as used herein, the phrase “based on” shall be construed in the same manner as the phrase “based at least in part on” . Further, as used herein, including in the claims, a “set” may include one or more elements.
[0005] Some implementations of the method and apparatuses described herein may include a UE for wireless communication to transmit a first indication including information of one or more available artificial intelligence functionalities; receive one or more configurations for the one or more available artificial intelligence functionalities; and transmit, for the one or more available artificial intelligence functionalities, at least one of an activation indication or a switch indication.
[0006] In some implementations of the method and apparatuses described herein, the first indication further includes one or more configurations for one or more supported artificial intelligence functionalities; at least one of: the activation indication includes one or more of an activation report or an activation request; or the switch indication includes one or more of a switch report or a switch request; one or more of the activation request or the switch request includes at least one of an indication of a new artificial intelligence functionality or an indication of a configuration for UE switching; the one or more configurations include one or more parameters for at least one of the one or more available artificial intelligence functionalities or an initial artificial intelligence functionality to be activated; the one or more configurations for the one or more available artificial intelligence functionalities include one or more switching rules for the one or more available artificial intelligence functionalities.
[0007] In some implementations of the method and apparatuses described herein, the one or more configurations include switch timer configuration for artificial intelligence functionality switching, the switch timer configuration including one or more of: switch timer activation based at least in part on occurrence of one or more functionality switching criteria or upon receiving an indication; switch timer expiry is to trigger one or more of artificial intelligence functionality fallback or artificial intelligence functionality switching; switch timer to be configured to be UE specific; switch timer configuration signaled via radio resource control (RRC) configuration; or switch timer configuration signaled via one or more of medium access control (MAC) control element (CE) or downlink control information (DCI) ; the at least one processor is configured to cause the UE to transmit one or more of an acknowledgement (ACK) or a negative acknowledgement (NACK) for a functionality switch command; the at least one processor is configured to cause the UE to receive a confirmation message based at least in part on the activation indication or the switch indication; the at least one processor is configured to cause the UE to transmit the first indication via UE assistance information (UAI) ; the at least one processor is configured to cause the UE to receive the one or more configurations via RRC signaling; the at least one processor is configured to cause the UE to transmit the at least one of the activation indication or the switch indication via a MAC CE.
[0008] Some implementations of the method and apparatuses described herein may further include a processor for wireless communication transmit a first indication including information of one or more available artificial intelligence functionalities; receive one or more configurations for the one or more available artificial intelligence functionalities; and transmit, for the one or more available artificial intelligence functionalities, at least one of an activation indication or a switch indication.
[0009] Some implementations of the method and apparatuses described herein may further include a method performed by a UE, the method including transmitting a first indication including information of one or more available artificial intelligence functionalities; receiving one or more configurations for the one or more available artificial intelligence functionalities; and transmitting, for the one or more available artificial intelligence functionalities, at least one of an activation indication or a switch indication.
[0010] In some implementations of the method and apparatuses for a UE described herein, the first indication further includes one or more configurations for one or more supported artificial intelligence functionalities; at least one of: the activation indication includes one or more of an activation report or an activation request; or the switch indication includes one or more of a switch report or a switch request; one or more of the activation request or the switch request includes at least one of an indication of a new artificial intelligence functionality or an indication of a configuration for UE switching; the one or more configurations include one or more parameters for at least one of the one or more available artificial intelligence functionalities or an initial artificial intelligence functionality to be activated; the one or more configurations for the one or more available artificial intelligence functionalities include one or more switching rules for the one or more available artificial intelligence functionalities.
[0011] In some implementations of the method and apparatuses for a UE described herein, the one or more configurations include switch timer configuration for artificial intelligence functionality switching, the switch timer configuration including one or more of: switch timer activation based at least in part on occurrence of one or more functionality switching criteria or upon receiving an indication; switch timer expiry is to trigger one or more of artificial intelligence functionality fallback or artificial intelligence functionality switching; switch timer to be configured to be UE specific; switch timer configuration signaled via RRC configuration; or switch timer configuration signaled via one or more of MAC CE or DCI; further including transmitting one or more of an ACK or a NACK for a functionality switch command; receiving a confirmation message based at least in part on the activation indication or switch indication; transmitting the first indication via UAI; receiving the one or more configurations via RRC signaling; transmitting the at least one of the activation indication or the switch indication via a MAC CE.
[0012] Some implementations of the method and apparatuses described herein may further include a NE for wireless communication to receive a first indication including information of one or more available artificial intelligence functionalities of a UE; transmit one or more configurations for at least one of the one or more available artificial intelligence functionalities or one or more other artificial intelligence functionalities ; and receive, for the one or more available artificial intelligence functionalities, at least one of an activation indication or a switch indication.
[0013] In some implementations of the method and apparatuses described herein, the at least one processor is configured to cause the NE to transmit one or more of an artificial intelligence functionality activation command or an artificial intelligence functionality switch command; at least one of the activation indication includes an activation request or the switch indication includes a switch request or a switch report, and wherein the at least one processor is configured to cause the NE to transmit one or more of an activation confirmation or a switch confirmation via a MAC CE or a DCI; the one or more configurations include one or more parameters for at least one of the one or more available artificial intelligence functionalities, the one or more other artificial intelligence functionalities, or an initial artificial intelligence functionality to be activated; the one or more configurations for the at least one of the one or more available artificial intelligence functionalities or the one or more other artificial intelligence functionalities include one or more switching rules for the at least one of the one or more available artificial intelligence functionalities or the one or more other artificial intelligence functionalities; the one or more configurations include switch timer configuration for artificial intelligence functionality switching, the switch timer configuration including one or more of: switch timer activation based at least in part on occurrence of one or more functionality switching criteria or upon receiving an indication; switch timer expiry is to trigger one or more of artificial intelligence functionality fallback or artificial intelligence functionality switching; switch timer to be configured to be UE specific; switch timer configuration signaled via RRC configuration; or switch timer configuration signaled via one or more of MAC CE or DCI.
[0014] Some implementations of the method and apparatuses described herein may further include a method performed by a NE, the method including receiving a first indication including information of one or more available artificial intelligence functionalities of a UE; transmitting one or more configurations for at least one of the one or more available artificial intelligence functionalities or one or more other artificial intelligence functionalities ; and receiving, for the one or more available artificial intelligence functionalities, at least one of an activation indication or a switch indication.
[0015] In some implementations of the method and apparatuses for a NE described herein, the method further includes transmitting one or more of an artificial intelligence functionality activation command or an artificial intelligence functionality switch command; at least one of the activation indication includes an activation request or the switch indication includes a switch request or a switch report, and wherein the at least one processor is configured to cause the NE to transmit one or more of an activation confirmation or a switch confirmation via a MAC CE or a DCI; the one or more configurations include one or more parameters for at least one of the one or more available artificial intelligence functionalities, the one or more other artificial intelligence functionalities, or an initial artificial intelligence functionality to be activated; the one or more configurations for the at least one of the one or more available artificial intelligence functionalities or the one or more other artificial intelligence functionalities include one or more switching rules for the at least one of the one or more available artificial intelligence functionalities or the one or more other artificial intelligence functionalities; the one or more configurations include switch timer configuration for artificial intelligence functionality switching, the switch timer configuration including one or more of: switch timer activation based at least in part on occurrence of one or more functionality switching criteria or upon receiving an indication; switch timer expiry is to trigger one or more of artificial intelligence functionality fallback or artificial intelligence functionality switching; switch timer to be configured to be UE specific; switch timer configuration signaled via RRC configuration; or switch timer configuration signaled via one or more of MAC CE or DCI.BRIEF DESCRIPTION OF THE DRAWINGS
[0016] Figure 1 illustrates an example of a wireless communications system in accordance with aspects of the present disclosure.
[0017] Figure 2 illustrates an example AI framework 200.
[0018] Figure 3 illustrates an example block diagram 300 for a node A one sided model.
[0019] Figure 4 illustrates an example block diagram 400 for a node B one sided model.
[0020] Figure 5 illustrates an example block diagram 500 for a two sided model.
[0021] Figure 6 illustrates a signaling diagram 600 according to aspects of the present disclosure.
[0022] Figure 7 illustrates a signaling diagram 700 according to aspects of the present disclosure.
[0023] Figure 8 illustrates a signaling diagram 800 according to aspects of the present disclosure.
[0024] Figure 9 illustrates a signaling diagram 900 according to aspects of the present disclosure.
[0025] Figure 10 illustrates a signaling diagram 1000 according to aspects of the present disclosure.
[0026] Figure 11 illustrates an example of a UE 1100 in accordance with aspects of the present disclosure.
[0027] Figure 12 illustrates an example of a processor 1200 in accordance with aspects of the present disclosure.
[0028] Figure 13 illustrates an example of a NE 1300 in accordance with aspects of the present disclosure.
[0029] Figure 14 illustrates a flowchart of a method 1400 in accordance with aspects of the present disclosure.
[0030] Figure 15 illustrates a flowchart of a method 1500 in accordance with aspects of the present disclosure.DETAILED DESCRIPTION
[0031] In a wireless communications system, a UE and a NE (e.g., a base station, gNB) may support wireless communication (e.g., reception and / or transmission of wireless communication) using time-frequency resources. Wireless communications systems can utilize artificial intelligence (AI) and machine learning (ML) (AI / ML, hereinafter referred to as “AI” ) for a variety of different purposes, such as for network operation, network optimization, automated processing (e.g., self-driving cars in vehicle to everything (V2X) scenarios) , network planning, security information and event management (SIEM) ) , etc. AI can leverage AI models (referred to herein as “models” ) which represent programs and / or algorithms trained on a set of data to provide outputs, such as to recognize patterns, make decisions, generate content, etc. AI models, for instance, can apply different algorithms to data inputs to provide output for performing different tasks.
[0032] When an AI functionality (hereinafter may be referred to as “functionality” ) is active at a node (e.g., UE) , the node may need to switch a current functionality to another functionality and / or switch from one AI configuration (hereinafter may be referred to as “configuration” ) to another configuration for the same functionality when enabled and reconfigured by the network. However, existing mechanisms of AI life cycle management (LCM) may not provide the flexibility to a UE to switch between different functionalities or configurations autonomously or semi-autonomously. Although switching from one functionality or configuration to another may require some coordination from the network, in some scenarios the UE can independently decide to switch to another functionality without impacting the network configuration.
[0033] One possible scenario is that the network may reconfigure a functionality for another configuration and / or context. However, such scenarios can introduce limitations on the switching from one functionality / configuration to another from the UE perspective. For instance, for each change in conditions / context, the network may need to reconfigure the UE with a new RRC reconfiguration. This can introduce high signaling overhead and reduce the flexibility for a UE to trigger and switch from one functionality / configuration to another. Thus, such procedures may limit the functioning of the AI functionality when UE and / or network conditions and / or configurations change.
[0034] Aspects of the present disclosure are described in the context of a wireless communications system, and include implementations that provide for functionality switching, which can be configured by the network. The described implementations can simplify functionality switching with a UE to reduce signaling overhead while ensuring efficient inference outcomes and UE autonomous decisions to switch among functionality. The present disclosure includes options for switching from one functionality to another including UE semi-autonomous switching, UE autonomous switching (e.g., network-assisted) , NW-controlled switching (e.g., NW-triggered, UE-triggered) , etc.
[0035] For instance, in implementations the network can configure the UE to apply one of the different options (introduced in this disclosure) for switching between different functionalities depending on particular use cases. The available functionality on the configuration level can be reported by the UE separately after reporting the supported functionalities in UE capability. Alternatively or additionally, supported functionalities can be defined at the configuration level, which can be reported in the UE capability directly. In implementations multiple RRC configurations from the network can facilitate the functionality switching. Further, switching rules and switching timers are provided to support the activation of new functionalities and configurations. By performing the described techniques, a device in a wireless communications system can flexibly utilize AI functionalities and configurations for different tasks, such as channel estimation (e.g., CSI processing) , beam management, device positioning, etc.
[0036] Reference is made herein to communicating data or information, such as signaling communication resources and / or communications that are transmitted or received between devices. It is to be appreciated that other terms may be used interchangeably with communicating, such as signaling, transmitting, receiving, outputting, forwarding, retrieving, obtaining, and so forth.
[0037] Aspects of the present disclosure are described in the context of a wireless communications system.
[0038] Figure 1 illustrates an example of a wireless communications system 100 in accordance with aspects of the present disclosure. The wireless communications system 100 may include one or more NEs 102, one or more UEs 104, and a core network (CN) 106. The wireless communications system 100 may support various radio access technologies. In some implementations, the wireless communications system 100 may be a 4G network, such as an LTE network or an LTE-Advanced (LTE-A) network. In some other implementations, the wireless communications system 100 may be a NR network, such as a 5G network, a 5G-Advanced (5G-A) network, or a 5G ultrawideband (5G-UWB) network. In other implementations, the wireless communications system 100 may be a combination of a 4G network and a 5G network, or other suitable radio access technology including Institute of Electrical and Electronics Engineers (IEEE) 802.11 (Wi-Fi) , IEEE 802.16 (WiMAX) , IEEE 802.20. The wireless communications system 100 may support radio access technologies beyond 5G, for example, 6G. Additionally, the wireless communications system 100 may support technologies, such as time division multiple access (TDMA) , frequency division multiple access (FDMA) , or code division multiple access (CDMA) , etc.
[0039] The one or more NEs 102 may be dispersed throughout a geographic region to form the wireless communications system 100. One or more of the NEs 102 described herein may be or include or may be referred to as a network node, a base station, a network element, a network function, a network entity, a radio access network (RAN) , a NodeB, an eNodeB (eNB) , a next-generation NodeB (gNB) , or other suitable terminology. An NE 102 and a UE 104 may communicate via a communication link, which may be a wireless or wired connection. For example, an NE 102 and a UE 104 may perform wireless communication (e.g., receive signaling, transmit signaling) over a Uu interface.
[0040] An NE 102 may provide a geographic coverage area for which the NE 102 may support services for one or more UEs 104 within the geographic coverage area. For example, an NE 102 and a UE 104 may support wireless communication of signals related to services (e.g., voice, video, packet data, messaging, broadcast, etc. ) according to one or multiple radio access technologies. In some implementations, an NE 102 may be moveable, for example, a satellite associated with a non-terrestrial network (NTN) . In some implementations, different geographic coverage areas associated with the same or different radio access technologies may overlap, but the different geographic coverage areas may be associated with different NE 102.
[0041] The one or more UEs 104 may be dispersed throughout a geographic region of the wireless communications system 100. A UE 104 may include or may be referred to as a remote unit, a mobile device, a wireless device, a remote device, a subscriber device, a transmitter device, a receiver device, or some other suitable terminology. In some implementations, the UE 104 may be referred to as a unit, a station, a terminal, or a client, among other examples. Additionally, or alternatively, the UE 104 may be referred to as an Internet-of-Things (IoT) device, an Internet-of-Everything (IoE) device, or machine-type communication (MTC) device, among other examples.
[0042] A UE 104 may be able to support wireless communication directly with other UEs 104 over a communication link. For example, a UE 104 may support wireless communication directly with another UE 104 over a device-to-device (D2D) communication link. In some implementations, such as vehicle-to-vehicle (V2V) deployments, vehicle-to-everything (V2X) deployments, or cellular-V2X deployments, the communication link may be referred to as a sidelink. For example, a UE 104 may support wireless communication directly with another UE 104 over a PC5 interface.
[0043] An NE 102 may support communications with the CN 106, or with another NE 102, or both. For example, an NE 102 may interface with other NE 102 or the CN 106 through one or more backhaul links (e.g., S1, N2, N6, or other network interface) . In some implementations, the NE 102 may communicate with each other directly. In some other implementations, the NE 102 may communicate with each other indirectly (e.g., via the CN 106) . In some implementations, one or more NEs 102 may include subcomponents, such as an access network entity, which may be an example of an access node controller (ANC) . An ANC may communicate with the one or more UEs 104 through one or more other access network transmission entities, which may be referred to as a radio heads, smart radio heads, or transmission-reception points (TRPs) .
[0044] The CN 106 may support user authentication, access authorization, tracking, connectivity, and other access, routing, or mobility functions. The CN 106 may be an evolved packet core (EPC) , or a 5G core (5GC) , which may include a control plane entity that manages access and mobility (e.g., a mobility management entity (MME) , an access and mobility management functions (AMF) ) and a user plane entity that routes packets or interconnects to external networks (e.g., a serving gateway (S-GW) , a packet data network (PDN) gateway (P-GW), or a user plane function (UPF) ) . In some implementations, the control plane entity may manage non-access stratum (NAS) functions, such as mobility, authentication, and bearer management (e.g., data bearers, signal bearers, etc. ) for the one or more UEs 104 served by the one or more NEs 102 associated with the CN 106.
[0045] The CN 106 may communicate with a packet data network over one or more backhaul links (e.g., via an S1, N2, N6, or other network interface) . The packet data network may include an application server. In some implementations, one or more UEs 104 may communicate with the application server. A UE 104 may establish a session (e.g., a protocol data unit (PDU) session, or the like) with the CN 106 via an NE 102. The CN 106 may route traffic (e.g., control information, data, and the like) between the UE 104 and the application server using the established session (e.g., the established PDU session) . The PDU session may be an example of a logical connection between the UE 104 and the CN 106 (e.g., one or more network functions of the CN 106) .
[0046] In the wireless communications system 100, the NEs 102 and the UEs 104 may use resources of the wireless communications system 100 (e.g., time resources (e.g., symbols, slots, subframes, frames, or the like) or frequency resources (e.g., subcarriers, carriers) ) to perform various operations (e.g., wireless communications) . In some implementations, the NEs 102 and the UEs 104 may support different resource structures. For example, the NEs 102 and the UEs 104 may support different frame structures. In some implementations, such as in 4G, the NEs 102 and the UEs 104 may support a single frame structure. In some other implementations, such as in 5G and among other suitable radio access technologies, the NEs 102 and the UEs 104 may support various frame structures (i.e., multiple frame structures) . The NEs 102 and the UEs 104 may support various frame structures based on one or more numerologies.
[0047] One or more numerologies may be supported in the wireless communications system 100, and a numerology may include a subcarrier spacing and a cyclic prefix. A first numerology (e.g., μ=0) may be associated with a first subcarrier spacing (e.g., 15 kHz) and a normal cyclic prefix. In some implementations, the first numerology (e.g., μ=0) associated with the first subcarrier spacing (e.g., 15 kHz) may utilize one slot per subframe. A second numerology (e.g., μ=1) may be associated with a second subcarrier spacing (e.g., 30 kHz) and a normal cyclic prefix. A third numerology (e.g., μ=2) may be associated with a third subcarrier spacing (e.g., 60 kHz) and a normal cyclic prefix or an extended cyclic prefix. A fourth numerology (e.g., μ=3) may be associated with a fourth subcarrier spacing (e.g., 120 kHz) and a normal cyclic prefix. A fifth numerology (e.g., μ=4) may be associated with a fifth subcarrier spacing (e.g., 240 kHz) and a normal cyclic prefix.
[0048] A time interval of a resource (e.g., a communication resource) may be organized according to frames (also referred to as radio frames) . Each frame may have a duration, for example, a 10 millisecond (ms) duration. In some implementations, each frame may include multiple subframes. For example, each frame may include 10 subframes, and each subframe may have a duration, for example, a 1 ms duration. In some implementations, each frame may have the same duration. In some implementations, each subframe of a frame may have the same duration.
[0049] Additionally or alternatively, a time interval of a resource (e.g., a communication resource) may be organized according to slots. For example, a subframe may include a number (e.g., quantity) of slots. The number of slots in each subframe may also depend on the one or more numerologies supported in the wireless communications system 100. For instance, the first, second, third, fourth, and fifth numerologies (i.e., μ=0, μ=1, μ=2, μ=3, μ=4) associated with respective subcarrier spacings of 15 kHz, 30 kHz, 60 kHz, 120 kHz, and 240 kHz may utilize a single slot per subframe, two slots per subframe, four slots per subframe, eight slots per subframe, and 16 slots per subframe, respectively. Each slot may include a number (e.g., quantity) of symbols (e.g., OFDM symbols) . In some implementations, the number (e.g., quantity) of slots for a subframe may depend on a numerology. For a normal cyclic prefix, a slot may include 14 symbols. For an extended cyclic prefix (e.g., applicable for 60 kHz subcarrier spacing) , a slot may include 12 symbols. The relationship between the number of symbols per slot, the number of slots per subframe, and the number of slots per frame for a normal cyclic prefix and an extended cyclic prefix may depend on a numerology. It should be understood that reference to a first numerology (e.g., μ=0) associated with a first subcarrier spacing (e.g., 15 kHz) may be used interchangeably between subframes and slots.
[0050] In the wireless communications system 100, an electromagnetic (EM) spectrum may be split, based on frequency or wavelength, into various classes, frequency bands, frequency channels, etc. By way of example, the wireless communications system 100 may support one or multiple operating frequency bands, such as frequency range designations FR1 (410 MHz –7.125 GHz) , FR2 (24.25 GHz –52.6 GHz) , FR3 (7.125 GHz –24.25 GHz) , FR4 (52.6 GHz –114.25 GHz) , FR4a or FR4-1 (52.6 GHz –71 GHz) , and FR5 (114.25 GHz –300 GHz) . In some implementations, the NEs 102 and the UEs 104 may perform wireless communications over one or more of the operating frequency bands. In some implementations, FR1 may be used by the NEs 102 and the UEs 104, among other equipment or devices for cellular communications traffic (e.g., control information, data) . In some implementations, FR2 may be used by the NEs 102 and the UEs 104, among other equipment or devices for short-range, high data rate capabilities.
[0051] FR1 may be associated with one or multiple numerologies (e.g., at least three numerologies) . For example, FR1 may be associated with a first numerology (e.g., μ=0) , which includes 15 kHz subcarrier spacing; a second numerology (e.g., μ=1) , which includes 30 kHz subcarrier spacing; and a third numerology (e.g., μ=2) , which includes 60 kHz subcarrier spacing. FR2 may be associated with one or multiple numerologies (e.g., at least 2 numerologies) . For example, FR2 may be associated with a third numerology (e.g., μ=2) , which includes 60 kHz subcarrier spacing; and a fourth numerology (e.g., μ=3) , which includes 120 kHz subcarrier spacing.
[0052] According to implementations, one or more of the NEs 102 and the UEs 104 are operable to implement various aspects of the techniques described with reference to the present disclosure. For example, a UE 104 can transmit to a NE 102 a first indication including information of one or more available artificial intelligence functionalities. The NE 102 can transmit to the UE 104 one or more configurations for the one or more available artificial intelligence functionalities, and the UE 104 can transmit to the NE 102, for the one or more available artificial intelligence functionalities, at least one of an activation indication or a switch indication.
[0053] Reference is made herein to communicating data or information, such as signaling communication resources and / or communications that are transmitted or received between devices. It is to be appreciated that other terms may be used interchangeably with communicating, such as signaling, transmitting, receiving, outputting, forwarding, retrieving, obtaining, and so forth.
[0054] With reference to the utilization of AI in wireless communications systems, the following represent some examples of features and / or terminology that are relevant.
[0055] AI-enabled Feature: refers to a feature where AI may be used.
[0056] AI Functionality: Functionality refers to an AI-enabled feature / feature group enabled by configurations, where configurations can be supported based on conditions indicated by a UE.
[0057] AI Model: A data driven algorithm that applies AI techniques to generate a set of outputs based on a set of inputs.
[0058] AI model Inference: A process of using a trained model to produce a set of outputs based on a set of inputs.
[0059] AI model training: A process to train a model (e.g., by learning an input / output relationship) in a data driven manner and obtain a trained model for inference.
[0060] Applicable functionalities: Applicable functionalities can be a subset of supported functionalities.
[0061] Additional conditions: Conditions that may vary for different scenarios, sites, or datasets are defined as additional conditions. Examples of additional conditions include UE internal conditions such as battery, memory, hardware attributes, etc. There may be UE side conditions and network side conditions.
[0062] Associated IDs: Identifiers referring to additional conditions, e.g., UE side additional conditions and / or network side additional conditions may be represented by associated IDs.
[0063] Data collection: A process of collecting data by network nodes, management entities, and / or UE for the purpose of model training, data analytics, and inference.
[0064] Dataset: A related set of information can be collectively called a dataset, which can be used for the purpose of training and is thus referred to as a training dataset.
[0065] Functionality identification: A process and / or method of identifying an AI functionality for a common understanding between the network and the UE. Where AI functionality resides can depend on specific use cases and sub-use cases.
[0066] Management instruction: Information that can be used to ensure proper inference operation. This information may include selection, activation, deactivation, and / or switching of models and / or AI functionalities, fallback to non-AI operation, etc.
[0067] Model activation: Enabling a model for a specific AI-enabled feature.
[0068] Model deactivation: Disabling a model for a specific AI-enabled feature.
[0069] Model identification: A process and / or method of identifying a model for a common understanding between the network and the UE. A process and / or method of model identification may or may not be applicable, and information regarding a model may be shared during model identification.
[0070] Model monitoring: A procedure that monitors the inference performance of a model.
[0071] Model selection: The process of selecting a model for activation among multiple models for the same AI enabled feature. Model selection may or may not be carried out simultaneously with model activation.
[0072] Model switching: Deactivating a currently active model and activating a different model for a specific AI-enabled feature.
[0073] Network-side model: A model whose inference is performed at the network.
[0074] Supported functionalities: As a result of functionality identification, the common understanding of functionalities supported can be developed between the network and the UE. The functionalities can be said to be identified and / or supported.
[0075] Two-sided model: A paired model over which joint inference is performed, where joint inference includes AI inference performed jointly across the UE and the network. For instance, a first part of inference is firstly performed by UE and then the remaining part is performed by NE, or vice versa.
[0076] UE side model: A model whose inference is performed at the UE.
[0077] UE state: A state of the UE can be defined as the UE state based on specific UE side conditions such as settings of a UE including internal conditions, additional conditions, a scenario, etc.
[0078] NE state: A state of a NE (e.g., gNB) can be defined as a network state based on specific network side conditions such as settings of a NE including additional conditions, a scenario, a configuration, etc.
[0079] Scenario: A scenario can be defined as a deployment scenario categorized based on different factors such as channel models (e.g., heavy line of sight / non-line of sight (LOS / NLOS) conditions, urban microcellular (UMi) , urban macrocellular (UMa) , indoor hotspot (InH)) , outdoor / indoor UE distributions, carrier frequencies, UE speeds, antenna spacings, etc. For example, network defined scenarios can be scenarios with network defined dataset categorization. UE defined scenarios can be scenarios with UE defined dataset categorization.
[0080] Examples of scenarios include: (a) Various deployment scenarios, e.g. : UMa, UMi and others; 200m inter-site distance (ISD) or 500m ISD and others; same deployment, different cells with different configuration / assumption; gNB height and UE height; (b) Various outdoor / indoor UE distributions, e.g., 100% / 0%, 20% / 80%, and others; (c) Various UE mobility, e.g., 3km / h, 30km / h, 60km / h, and others.
[0081] Configuration: A set of parameters constitutes a configuration which are considered to focus on aspects relevant to a use case, such as bandwidth, UE speed, antenna port layouts, numerology etc. A set of configurations can include one or more of the following aspects: bandwidth, UE speed, antenna port layouts, numerology etc. Examples of configurations (e.g., parameters and settings) include: (a) Various UE parameters, e.g., number of UE Rx beams (including number of panels and UE antenna array dimensions) , UE codebook; (b) Various NE settings, e.g., downlink Tx beam codebook (including various Set A of beam (pairs) and NE antenna array dimensions) ; (c) Various Set A of beam and various Set B of beam.
[0082] Figure 2 illustrates an example AI framework 200. The AI framework 200 includes data collection functions 202, model training functions 204, management functions 206, inference functions 208, and model storage functions 210. The data collection function 202 can provide input data to the model training functions 204, management functions 206, and inference functions 208. The training data can represent data used as input for the model training function 204. The monitoring data can represent data used as input for the management functions 206, e.g., for AI models and / or AI functionalities.
[0083] In the AI framework 200 inference data can be used as input for the inference functions 208. Further, the model training functions 204 can perform model training, validation, and testing which may generate model performance metrics that can be used as part of the model testing procedure. The model training functions 204 can also perform data preparation (e.g., data pre-processing and cleaning, formatting, and transformation) based on training data delivered by the data collection function 202. The management function 206 can oversee the operation (e.g., selection, (de) activation, switching, fallback, etc. ) and monitoring (e.g., performance) of models and / or AI functionalities. The management function 206 can also make decisions to ensure the proper inference operation based on data received from the data collection function 202 and the inference function 208. Management instruction can represent information for input to manage the inference function 208, such as information for selection, (de) activation, switching of models and / or AI-based functionalities, fallback to non-AI operation (e.g., not relying on inference processes) , etc. A model transfer / delivery request can be used to request model (s) to the model storage function 210.
[0084] Further to the AI framework 200 performance feedback / retraining request can represent information for input for the model training function 204, e.g., for model (re) training and / or model updating purposes. The inference function 208 can provide outputs from processes of applying AI models and / or AI functionalities using the data that is provided by the data collection function 202 (e.g., inference data) as input. The inference function 208 can also perform data preparation (e.g., data pre-processing and cleaning, data formatting, data transformation, etc. ) based on inference data delivered by the data collection function 202. Inference output can represent data used by the management function 206 to monitor the performance of models and / or AI functionalities. The model storage functions 210 can store trained models and / or updated models that can be used to perform the inference functions 208.
[0085] LCM of models and / or AI functionality can include functionality-based LCM and model-ID-based LCM. In functionality-based LCM, the network can indicate activation, deactivation, fallback, and / or switching of AI functionality via 3GPP signaling (e.g., RRC, MAC CE, DCI) . Models may not be identified at the network, and the UE may perform model-level LCM. For functionality identification, there may be one or more functionalities defined within an AI-enabled feature, whereby an AI-enabled feature can refer to a feature where AI may be used. The UE may have one model for the functionality, or the UE may have multiple models for the functionality.
[0086] For AI functionality identification and functionality-based LCM of UE-side models and / or UE-part of two sided models, functionality can refer to an AI-enabled feature / feature group enabled by configuration (s) , where configuration (s) can be supported based on conditions indicated by UE capability. Correspondingly, functionality-based LCM can operate based on, at least, one configuration of AI-enabled feature / feature group or specific configurations of an AI-enabled feature / feature group. After functionality identification, necessity information, and / or mechanisms for the UE to report updates on applicable functionality can be considered, where the applicable functionalities may be a subset of all functionalities. Applicable functionalities can be reported by the UE. Different use cases can be supported, such as channel state information (CSI) feedback enhancement, beam management, positioning accuracy, etc.
[0087] Data collection may be performed for different purposes in LCM, e.g., for model training, model management, and inference functions, etc. For instance, training data represents data used as input for the AI model training function. Monitoring data represents data used as input for the management of AI models and / or AI / functionalities. Inference Data represents data used as input for the AI inference function.
[0088] For AI-enabled features / feature group, additional conditions can refer to aspects that are assumed for the training of a model but are not a part of UE capability for the AI-enabled feature / feature group and may not imply that additional conditions are necessarily specified. Additional conditions can be divided into two categories: network side additional conditions and UE side additional conditions. For inference for UE side models, to ensure consistency between training and inference regarding network side additional conditions, the following options can apply: Model identification to achieve alignment on the network side additional condition between network side and UE side; model training at network and transfer to UE, where the model has been trained under the additional condition; information and / or indication on network side additional conditions can be provided to UE; consistency assisted by monitoring by UE and / or network, the performance of UE side candidate models and / or AI functionalities to select a model and / or functionality; other approaches are not precluded.
[0089] The present disclosure pertains to models including one sided models and two sided models. In one sided models, the model is located either at a node A (e.g., UE) or a node B (e.g., NE) referred to here as MA (model located at node A) and MB (model located at node B) , respectively. This is for purpose of illustration only, and node A and / or node B can be either a NE or a UE.
[0090] Figure 3 illustrates an example block diagram 300 for a node A one sided model, and Figure 4 illustrates an example block diagram 400 for a node B one sided model. The one sided models in the block diagrams 300, 400, for instance, can be implemented for use cases such as beam management, CSI prediction, radio resource management (RRM) measurement prediction, radio link failure prediction, handover failure prediction, positioning, etc. Depending on where the inference takes place, a model can be called a UE-side model when the UE performs the inference whereas for a NW-side model, the inference can be performed by the NW. In the block diagram 300 node A can implement a model MA and the node B may not implement a model, e.g., may not include AI capability. In the block diagram 400 node A may not implement a model (e.g., may not include AI capability) and node B can implement a model MB. Regarding inference, a model can be a UE side model when the UE performs the inference (e.g., the block diagram 300) and in a network side model inference can be performed by the network, e.g., the block diagram 400.
[0091] Figure 5 illustrates an example block diagram 500 for a two sided model. In two sided models, one part of the model can be located at a first node and another part of the model can be located at a second node. In the block diagram 500 node A (e.g., UE) can include Me (encoding model) and node B (e.g., NE) can include Md (decoding model) . Note that this is one example, the location of the encoder and decoder can be alternated. A two sided model can represent a scheme to reduce the required feedback information where an encoding part (e.g., at the UE) can compute a quantized latent representation of the input data, and the decoding part (e.g., at the NE) can receive the latent representation and use the latent representation to reconstruct an output. The input data, for instance, can be a dataset which is based on the channel measurements. For example, the input data be the raw channel inputs of Hk or and / or the precoders that are computed from the channel matrix, e.g., the eigenvector associated with the largest eigen-vector of Hk for each subband.
[0092] Models may be tailored toward and applicable to specific scenarios, configurations, locations, and deployments, among other factors. In this regard, models may undergo updates (e.g., model changes) as part of their development. After training the models, there may be multiple models (at node A side) associated with different node Bs, and multiple models (at node B side) associated with different node As. Given multiple models for a single functionality, some of which may be scenario or cell-specific, there can be a mechanism for node A and / or node B to select the appropriate model during the inference phase. For models at the UE (e.g., UE side models and / or UE side of a model) , the network may have a certain level of control to ensure efficient management (e.g., selection, activation, deactivation, switching, etc. ) of models and / or AI functionality.
[0093] Aspects of the present disclosure include solutions for AI functionality switching and activation. In the discussion herein a node can be a UE (Node A) or a NE (e.g., gNB / LMF, Node B) . An AI model can be trained for at least one or more specific datasets, scenarios, and configurations and more than one model can exist for a single AI functionality supported by a node. A model for an AI functionality supported by a node (e.g., UE) may be trained with a dataset subject to specific conditions of the node (e.g., UE / gNB) and specific conditions of the other node (e.g., gNB or LMF) . An ideal AI model would be a model which can be generalized for different datasets subject to different scenarios, configurations, and conditions of node A and node B and which can be applicable to any other node. However, this is practically a major challenge to create a model that is completely generalizable for a functionality. Therefore, it is highly likely that a node may contain multiple functionalities per use-case / sub-use-case and there may exist multiple trained models for each functionality.
[0094] For an AI functionality, a model has higher probability of providing a high precision inference outcome if it is trained with the same condition, additional conditions, scenarios, and / or configurations that are observed at the time of inference. Therefore it becomes important that the model training is associated with identifiers that represent the conditions, additional conditions, scenarios, and configuration under which the model is trained. This can allow to maintain consistency in training and inference. For the sake of simplicity in explanation, we call conditions, scenarios, configuration, additional conditions, or a combination of these as a “context” .
[0095] An AI functionality can be defined based on the parameter settings (e.g., configuration / context) of a use-case / sub-use-case. For example, if spatial domain beam management is the sub-use-case (Functionality A) , the following can be the available functionalities or sub-functionalities of A: Functionality A1: One option of spatial domain beam management with a specific parameter setting X (set A, set B) . Functionality A1 contains one or more models trained with this specific parameter setting X. Functionality A2: Another option of spatial domain beam management with a specific parameter setting Y (set A, set B) . Functionality A2 contains one or more models trained with this specific parameter setting Y. A1 and A2 can be called as functionalities that belong to the family of functionality A which can be represented by a single sub-use-case or in some cases a use-case, or they can be interpreted as sub-functionalities of functionality A. In this disclosure, for simplicity in illustration, the term functionality can be used for the functionalities such as A1 and A2. These available functionalities may contain one or more applicable functionalities.
[0096] The present disclosure discusses mechanisms and signaling for switching from one AI functionality and / or configuration to another. A node (e.g., UE, NE) may switch a current functionality to another functionality when enabled and reconfigured by the network. However, some existing implementations do not provide the flexibility for a node to switch between different functionalities (semi) -autonomously. Although switching from one functionality to another may involve a certain level of coordination from the network, in some scenarios the UE can independently decide to switch to another functionality without impacting the network configuration.
[0097] Accordingly, the present disclosure provides implementations for functionality switching which can be configured by the network. Such implementations can simplify functionality switching with the target to reduce the signaling overhead while ensuring efficient inference outcomes and UE autonomous decisions to switch among functionality. Additionally, the solutions presented in this disclosure can also be applied to configuration / context switching for a single functionality. For instance, if functionality A1 and A2 represent configuration / context C1 and C2, respectively, then switching between functionality A1 and A2 can imply switching between different configurations / context C1 and C2. For ease of explanation, we will discuss functionality switching which can be adapted to other implementations depending on the granularity of a functionality.
[0098] Implementations described in the present disclosure include the following options for switching from one functionality to another: UE semi-autonomous switching; UE autonomous switching including NW-assisted; and NW-controlled switching including NW-triggered and UE-triggered switching.
[0099] In implementations the network can configure the UE to apply one of above-stated options for switching between different functionalities depending on the particular use case. The available functionality on the configuration level can be reported by the UE separately after reporting the supported functionalities in UE capability. Alternatively or additionally, the supported functionalities can be defined at the configuration level, which can be reported in the UE capability directly. Associated signaling may be based at least in part on factors such as the type of applicability reporting (e.g., reactive or proactive) and the entity determining the applicability of functionality (e.g., network or the UE) . The solutions discussed in this disclosure can be adapted as per these factors. Additionally, the functionality switching and the signaling mechanisms can be applicable to other management functions / management instructions including selection, activation, deactivation, switching of AI models and / or AI functionalities, fallback to non-AI operation, etc. Discussed herein are a few illustration examples for functionality switching and the solutions are not limited to these example implementations.
[0100] Implementations include UE semi-autonomous functionality switching. For instance, solutions are provided to enable the UE to switch from one functionality to another. Further, multiple RRC and / or LPP configurations by the network are provided to facilitate the functionality switching. As the UE reports its supported functionalities in the capability report message (e.g., UE capability report or LPP ProvideCapabilities message) , the UE may further report its available functionalities (e.g., in the form of available configurations for the supported functionalities) in the applicability report (e.g. via RRC UEAssitanceInformation message or similar LPP message from UE to LMF) . For instance, available functionalities = {A1, A2, A3, A4, A5, A6} . The network may filter the received available functionalities based on its NW-side conditions such as functionalities {A1, A3, A4, A5} . Further, the network may provide multiple RRC or LPP configurations for the selected available functionalities. Here, the indicators A1, A2, A3, etc., may represent different available functionalities in the form of an identifier, alternatively, they may represent a structure that contains one or more parameters relevant to the corresponding functionality.
[0101] In implementations, the network may allocate each available functionality with an individual configuration. Alternatively or additionally, a particular configuration may be allocated to more than one available functionality. In one example, a RRC configuration configuring a particular functionality may contain an identifier which can assist in identifying the multiple different functionalities, e.g., for the purpose of activating and / or deactivating a particular functionality respectively switching among configured functionalities.
[0102] Figure 6 illustrates a signaling diagram 600 according to aspects of the present disclosure. The signaling diagram 600 represents implementations for semi-autonomous functionality switching and may include a UE 104 and a NE 102. The signaling diagram 600 includes sections for initial functionality activation process and functionality switching illustrated in the respective dashed boxes. At 602 the UE 104 can communicate to the NE 102 a capability report that includes supported AI functionalities and at 604 the UE 104 can communicate to the NE 104 an AI applicability report that includes information of available AI functionalities at the UE 104.
[0103] At 606 the UE 104 can receive from the NE 102 multiple RRC configurations for the available functionalities and at 608 the UE 104 can determine the applicability. As a result, the UE 104 can determine the initial functionality that is applicable and which can be activated. At 610 the UE 104 can send a functionality activation / switch report which indicates the applicable functionality and its configuration. In at least one example this report can be signaled via MAC CE to the network. In one example the new MAC CE may contain an identifier (ID) identifying the applicable functionality. The ID can be one of the IDs assigned by the network within the multiple RRC configurations. In response to the report at 610, at 612 the NE 102 can communicate to the UE 104 a confirmation of activation / switch report and at 614 can apply the configuration indicated in the MAC CE received from the UE. Upon receiving the confirmation, at 616 the UE 104 may activate functionality and apply the configuration related to the activated functionality. In one example the functionality may be activated upon transmission of a HARQ ACK on PUCCH indicating the successful reception of the confirmation MAC CE. According to one exemplary implementation, the UE 104 considers a successful reception of the functionality activation / switch report MAC CE upon reception of a PDCCH addressed to the UE (C-RNTI) indicating uplink grant for a new transmission for the HARQ process used for the transmission of the functionality activation / switch report MAC CE.
[0104] At 618 if a change in UE-side / NW-side conditions occurs, the currently active functionality may not be applicable anymore. In such scenarios the UE 104 may determine to switch to other functionality suitable to the current UE and network conditions. The nature of UE-side / NW-side conditions may be decisive for the need to switch functionality, which can be use-case specific and may depend on the conditions considered while training the model. At 620 when UE 104 detects that the applicability of the functionality has changed, at 622 the UE 104 can send to the NE 102 a functionality activation / switch report via MAC CE indicating the newly applicable functionality that the UE 104 determines to switch to. At 624 the NE 104 can communicate (e.g., via a MAC CE) a confirmation of functionality activation / switch and at 626 the NE 102 can apply a new configuration based on the functionality activation / switch.
[0105] In implementations the UE 104 contains RRC configurations for its available functionalities, and at 628 the UE may activate the new functionality directly after receiving the confirmation at 624, e.g., confirmation MAC CE sent from the NE 102 to the UE 104 in response to the functionality activation report MAC CE. If a confirmation is not received by the UE 104 from the NE 102, the UE 104 may drop to fallback (e.g., default AI or non-AI) if the UE cannot continue with the current active functionality. In one example, the UE 104 may start a timer after sending at 622 the functionality activation / switch report via MAC CE. If the configuration from NE 102 is not received upon the timer expiry, the UE 104 can fall back to a default AI or non-AI method. In one example, the UE 104 may start another prohibit timer after sending a functionality activation / switch report via MAC CE. Further, the UE 104 may be prohibited from sending another functionality activation / switch report if the prohibit timer is running. A value of the prohibit timer can be configured by the network (e.g., NE 102) in order to prevent too frequent AI functionality switching.
[0106] Figure 7 illustrates a signaling diagram 700 according to aspects of the present disclosure. The signaling diagram 700 represents implementations for semi-autonomous functionality switching and may include a UE 104 and a NE 102. The signaling diagram 700 includes sections for initial functionality activation process and functionality switching illustrated in the respective dashed boxes. The signaling diagram 700, for instance, represents an implementation variation on the implementation described in the signaling diagram 600. The signaling diagram 700 includes sections for initial functionality activation process and functionality switching illustrated in the respective dashed boxes. At 702 the UE 104 can communicate to the NE 102 a capability report that includes supported AI functionalities and at 704 the UE 104 can communicate to the NE 104 an AI applicability report that includes information of available AI functionalities at the UE 104.
[0107] At 706 the NE 102 can determine applicability of available AI functionalities and at 708 the UE 104 can receive from the NE 102 multiple RRC configurations for the available functionalities. At 710 the NE 102 can apply AI functionality configuration and at 712 the UE 104 may activate functionality and apply the configuration related to the activated functionality. At 714 AI functionality applicability can be determined by either or both the NE 102 or the UE 104, and thus respective applicability information can be exchanged between the UE 104 and the NE 102.
[0108] At 716 if a change in UE-side / NW-side conditions occurs, the currently active functionality may cease to be applicable. In such scenarios the UE 104 may determine to switch to other functionality suitable to the current UE and network conditions. The nature of UE-side / NW-side conditions may be decisive for the need to switch functionality, which can be use-case specific and may depend on the conditions considered while training the model. When UE 104 detects that the change in conditions, at 718 the UE 104 can send to the NE 102 a functionality activation / switch report via MAC CE indicating the newly applicable functionality that the UE 104 determines to switch to. At 720 the NE 104 can communicate (e.g., via a MAC CE) a confirmation of functionality activation / switch and at 722 the NE 102 can apply a new configuration based on the functionality activation / switch. At 724 the UE may activate the new functionality after receiving the confirmation at 720.
[0109] Thus, in implementations the NE 102 may configure the UE 104 with multiple RRC configurations which contain one RRC configuration for the currently applicable functionality (indication of the currently applicable functionality) along with configurations for other available functionalities. The UE 104 may report the available functionalities such that they are applicable from the UE perspective and thus the NE 102 can determine the final applicability of the initial functionality and configure the UE 104 accordingly for activation. The UE 104 may activate an applicable functionality directly upon receiving the RRC configuration.
[0110] Figure 8 illustrates a signaling diagram 800 according to aspects of the present disclosure. The signaling diagram 800 represents implementations for autonomous functionality switching and may include a UE 104 and a NE 102. For instance, the signaling diagram 800 illustrates implementations that provide techniques to enable a UE to switch from one functionality to another with network assistance is introduced. The signaling diagram 800 includes sections for initial functionality activation process and functionality switching illustrated in the respective dashed boxes. At 802 the UE 104 can communicate to the NE 102 a capability report that includes supported AI functionalities and at 804 the UE 104 can communicate to the NE 104 an AI applicability report that includes information of available AI functionalities at the UE 104.
[0111] At 806 along with the multiple RRC configurations provided by the network (as discussed in the above implementations) , the NE 102 configures the UE 104 with functionality-switching rules and switch timers. For instance, a UE autonomous functionality-switching can be enabled by facilitating switching criteria and the UE 102 may provide one or more functionality-switching criteria to the UE 104. The switching rules can be associated with a functionality, a use case, and / or a sub-use-case. At 808 the UE 104 can determine the applicability and the UE 104 can determine the initial functionality that is applicable and which can be activated. At 810 the UE 104 can send a functionality activation / switch report which indicates the applicable functionality and its configuration. In at least one example this report can be signaled via MAC CE to the network. At 812 the NE 102 communicates a confirmation of activation message to the UE 104 and at 814 the NE 102 can apply the configuration (e.g., indicated in the MAC CE) received from the UE
[0112] At 816 the initial functionality activation process can be performed by one of the procedures described in the previous implementations. For instance, the UE 104 may be configured directly by the NE 102 to activate an applicable functionality upon configuration or the UE 104 may determine the functionality applicability after receiving configuration. If the latter is applied, then the UE 104 may wait for a confirmation (e.g., from 812) from the NE 102 to activate the functionality.
[0113] The process of functionality switching can be performed based on the switching rules provided by the NE 102, e.g., at 806. At 818 if the pre-configured switching conditions for a functionality are fulfilled, at 820 the UE 104 can trigger the functionality switching process by starting the switch timer. The UE 104 can send a functionality activation / switch report via MAC CE which may include the switch timer information. At 822 the duration of the timer can provide a time window for the network to intervene in the functionality switching process. In cases where the pre-configured switching conditions are no longer valid, the NE 102 may reconfigure the UE with updated switching rules. Alternatively, at 824 the NE 102 may force the UE 104 to go to fallback (default non-AI or default AI scheme) in response to the switching report at 820 from the UE 104. If the switch timer expires at 826 without any response from the NE 102, the UE 104 can send a fallback report (e.g., via MAC CE) to the NE 102 and at 828 the UE 104 may opt for a fallback. Otherwise, a new functionality can be activated directly upon receiving reconfiguration or acknowledgment from the NE 102.
[0114] In implementations, the switch timer can be configured by the NE 102. When the timer is configured by the NE 102, the UE 104 may send an indication of the start of the timer (e.g., at 820) and the timer expiry can be derived by the NE 102 based on the timer duration. Alternatively, the switch timer may be UE-specific. In such cases, the UE 104 may send its switch timer configuration (e.g., duration of the timer) when the UE 104 determines to trigger the timer. The NE 102 can expect a start of the timer upon receiving the switch timer duration, based on which the NE 102 may derive the timer expiry. If no switching rules are configured, the UE 104 may determine the applicability of the functionality / configuration and evaluate autonomously when to switch.
[0115] In another implementation, a UE 104 may switch to another functionality upon timer expiry if the switching does not impact the network configuration. Additionally, the UE 104 may report to the NE 102 about the functionality switch. In one example, the UE 104 may start another prohibit timer after sending to the NE 102 a functionality activation / switch report via MAC CE. In implementations the UE 104 is prohibited from sending another functionality activation / switch report if the prohibit timer is running. The value prohibit timer can be configured by the NE 102 in order to prevent frequent AI functionality switching.
[0116] In an alternative or additional implementation, the RRC configuration provided by the NE 102 may be an umbrella configuration that applies to more than one available functionality. In such cases, the UE 104 may not require reconfiguration from the network and the network configuration may not change, thus the UE 104 may independently switch between such functionalities (under the same configuration) if configured by the NE 102. Additionally, the UE 104 may report the functionality switch to the NE 102.
[0117] Implementations are also provided for functionality switching in cases where multiple functionalities are not preconfigured by a network. Different options for such network controlled functionality switching schemes are discussed below.
[0118] Figure 9 illustrates a signaling diagram 900 according to aspects of the present disclosure. The signaling diagram 900 represents implementations for network-controlled functionality switching and may include a UE 104 and a NE 102. The signaling diagram 900 includes sections for initial functionality activation process and functionality switching illustrated in the respective dashed boxes. At 902 the UE 104 can communicate to the NE 102 a capability report that includes supported AI functionalities and at 904 the UE 104 can communicate to the NE 104 an AI applicability report that includes information of available AI functionalities at the UE 104.
[0119] At 906 the NE 102 can communicate to the UE 104 configuration information for an applicable functionality, at 908 the NE 102 can apply the configuration for the functionality, and at 910 the UE 104 can activate the functionality. The initial functionality activation, for instance, is performed upon receiving the RRC configuration from the NE 102 at 906. The applicability of the functionality is either determined by the NE 102 after receiving the applicability report at 904 or by the UE 104 before the applicability report.
[0120] At 912 a change in conditions occurs at the NE 102 and / or the UE 104 and at 914, upon the change in conditions, for example, if the NE 102 determines at 914 the applicability status of the existing active functionality has changed, the NE 102 may trigger to change to another functionality from available functionalities (if determined applicable) . Thus, at 916 a functionality switch command containing the RRC configuration for this newly applicable functionality can be sent to the UE 104 using RRC signaling. At 918 The UE 104 may further determine the applicability from the UE perspective and at 920 provide an acknowledgment report (functionality activation / switch) to the NE 102 via MAC CE. In cases where the functionality is not applicable from the UE perspective, the UE 104 may report a NACK in a functionality activation / switch report indicating a switch to fallback. At 922 the NE 102 can communicate a confirmation of activation / switch message to the UE 104, and at 924 the NE 102 can apply configuration for the functionality activation / switch. Upon receiving a confirmation of MAC CE, at 926 the UE 104 may either activate the newly applicable functionality or fallback.
[0121] Figure 10 illustrates a signaling diagram 1000 according to aspects of the present disclosure. The signaling diagram 1000 represents implementations for network-controlled functionality switching and may include a UE 104 and a NE 102. The signaling diagram 1000 includes sections for initial functionality activation process and functionality switching illustrated in the respective dashed boxes. At 1002 the UE 104 can communicate to the NE 102 a capability report that includes supported AI functionalities and at 1004 the UE 104 can communicate to the NE 104 an AI applicability report that includes information of available AI functionalities at the UE 104.
[0122] At 1006 the NE 102 can communicate to the UE 104 configuration information for an applicable functionality, at 1008 the NE 102 can apply the configuration for the functionality, and at 1010 the UE 104 can activate the functionality. The initial functionality activation, for instance, is performed upon receiving the RRC configuration from the NE 102 at 1006. The applicability of the functionality is either determined by the NE 102 after receiving the applicability report at 1004 or by the UE 104 before the applicability report.
[0123] At 1012 a change in conditions occurs at the NE 102 and / or the UE 104 and at 1014 the UE 104 can determine that applicability the applicability status of the existing active functionality has changed. At 1016 the UE 104 triggers a change in functionality by sending a functionality switch request (MAC CE) to the NE 102. The request can include a newly applicable functionality, in response to which at 1018 the NE 102 may provide to the UE 102 an RRC configuration for the newly applicable functionality and at 1020 the NE 102 may apply configuration for the new functionality. Upon receiving the configuration, at 1022 the UE 104 may activate the functionality. If a response to the request at 1016 is not received by the UE 104, at 1024 the UE 104 can communicate a fallback report to the NE 102 and at 1026 the UE 104 can go to a fallback AI functionality and / or non-AI functionality. In at least one example implementation, the UE 104 may send to the NE 102 its conditions / additional conditions in the functionality activation / switch request message. Thus, the NE 102 may determine the applicability of the functionality and provide the functionality switch configuration.
[0124] In implementations, the UE 104 may discard the previously received configurations of any previously active functionality upon receiving a new RRC configuration. Whereas, in another implementation, the UE 104 may store these configurations unless configured to discard them. In this case, the NE 102 may provide a one-bit indication in the functionality switch command and not provide a complete RRC configuration. In yet another implementation, the NE 102 may configure the UE to switch (semi-) autonomously if certain RRC configurations for a functionality are already present at the UE 104.
[0125] Figure 11 illustrates an example of a UE 1100 in accordance with aspects of the present disclosure. The UE 1100 may include a processor 1102, a memory 1104, a controller 1106, and a transceiver 1108. The processor 1102, the memory 1104, the controller 1106, or the transceiver 1108, or various combinations thereof or various components thereof may be examples of means for performing various aspects of the present disclosure as described herein. These components may be coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more interfaces.
[0126] The processor 1102, the memory 1104, the controller 1106, or the transceiver 1108, or various combinations or components thereof may be implemented in hardware (e.g., circuitry) . The hardware may include a processor, a digital signal processor (DSP) , an application-specific integrated circuit (ASIC) , or other programmable logic device, or any combination thereof configured as or otherwise supporting a means for performing the functions described in the present disclosure.
[0127] The processor 1102 may include an intelligent hardware device (e.g., a general-purpose processor, a DSP, a CPU, an ASIC, an FPGA, or any combination thereof) . In some implementations, the processor 1102 may be configured to operate the memory 1104. In some other implementations, the memory 1104 may be integrated into the processor 1102. The processor 1102 may be configured to execute computer-readable instructions stored in the memory 1104 to cause the UE 1100 to perform various functions of the present disclosure.
[0128] The memory 1104 may include volatile or non-volatile memory. The memory 1104 may store computer-readable, computer-executable code including instructions when executed by the processor 1102 cause the UE 1100 to perform various functions described herein. The code may be stored in a non-transitory computer-readable medium such as the memory 1104 or another type of memory. Computer-readable media includes both non-transitory computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A non-transitory storage medium may be any available medium that may be accessed by a general-purpose or special-purpose computer.
[0129] In some implementations, the processor 1102 and the memory 1104 coupled with the processor 1102 may be configured to cause the UE 1100 to perform one or more of the functions described herein (e.g., executing, by the processor 1102, instructions stored in the memory 1104) . For example, the processor 1102 may support wireless communication at the UE 1100 in accordance with examples as disclosed herein. The UE 1100 may be configured to or operable to support a means for transmitting a first indication including information of one or more available artificial intelligence functionalities; receiving one or more configurations for the one or more available artificial intelligence functionalities; and transmitting, for the one or more available artificial intelligence functionalities, at least one of an activation indication or a switch indication.
[0130] Additionally, the UE 1100 may be configured to support any one or combination of the first indication further includes one or more configurations for one or more supported artificial intelligence functionalities; at least one of: the activation indication includes one or more of an activation report or an activation request; or the switch indication includes one or more of a switch report or a switch request; one or more of the activation request or the switch request includes at least one of an indication of a new artificial intelligence functionality or an indication of a configuration for UE switching; the one or more configurations include one or more parameters for at least one of the one or more available artificial intelligence functionalities or an initial artificial intelligence functionality to be activated; the one or more configurations for the one or more available artificial intelligence functionalities include one or more switching rules for the one or more available artificial intelligence functionalities.
[0131] Additionally, the UE 1100 may be configured to support any one or combination of the one or more configurations include switch timer configuration for artificial intelligence functionality switching, the switch timer configuration including one or more of: switch timer activation based at least in part on occurrence of one or more functionality switching criteria or upon receiving an indication; switch timer expiry is to trigger one or more of artificial intelligence functionality fallback or artificial intelligence functionality switching; switch timer to be configured to be UE specific; switch timer configuration signaled via RRC configuration; or switch timer configuration signaled via one or more of MAC CE or DCI; further including transmitting one or more of an ACK or a NACK for a functionality switch command; receiving a confirmation message based at least in part on the activation indication or the switch indication; transmitting the first indication via UAI; receiving the one or more configurations via RRC signaling; transmitting the at least one of the activation indication or the switch indication via a MAC CE.
[0132] Additionally, or alternatively, the UE 1100 may support at least one memory (e.g., the memory 1104) and at least one processor (e.g., the processor 1102) coupled with the at least one memory and configured to cause the UE to transmit a first indication including information of one or more available artificial intelligence functionalities; receive one or more configurations for the one or more available artificial intelligence functionalities; and transmit, for the one or more available artificial intelligence functionalities, at least one of an activation indication or a switch indication.
[0133] Additionally, the UE 1100 may be configured to support any one or combination of where the first indication further includes one or more configurations for one or more supported artificial intelligence functionalities; at least one of: the activation indication includes one or more of an activation report or an activation request; or the switch indication includes one or more of a switch report or a switch request; one or more of the activation request or the switch request includes at least one of an indication of a new artificial intelligence functionality or an indication of a configuration for UE switching; the one or more configurations include one or more parameters for at least one of the one or more available artificial intelligence functionalities or an initial artificial intelligence functionality to be activated; the one or more configurations for the one or more available artificial intelligence functionalities include one or more switching rules for the one or more available artificial intelligence functionalities.
[0134] Additionally, the UE 1100 may be configured to support any one or combination of where the one or more configurations include switch timer configuration for artificial intelligence functionality switching, the switch timer configuration including one or more of: switch timer activation based at least in part on occurrence of one or more functionality switching criteria or upon receiving an indication; switch timer expiry is to trigger one or more of artificial intelligence functionality fallback or artificial intelligence functionality switching; switch timer to be configured to be UE specific; switch timer configuration signaled via RRC configuration; or switch timer configuration signaled via one or more of MAC CE or DCI; the at least one processor is configured to cause the UE to transmit one or more of an ACK or a NACK for a functionality switch command; the at least one processor is configured to cause the UE to receive a confirmation message based at least in part on the activation indication or the switch indication; the at least one processor is configured to cause the UE to transmit the first indication via UAI; the at least one processor is configured to cause the UE to receive the one or more configurations via RRC signaling; the at least one processor is configured to cause the UE to transmit the at least one of the activation indication or the switch indication via a MAC CE.
[0135] The controller 1106 may manage input and output signals for the UE 1100. The controller 1106 may also manage peripherals not integrated into the UE 1100. In some implementations, the controller 1106 may utilize an operating system such as or other operating systems. In some implementations, the controller 1106 may be implemented as part of the processor 1102.
[0136] In some implementations, the UE 1100 may include at least one transceiver 1108. In some other implementations, the UE 1100 may have more than one transceiver 1108. The transceiver 1108 may represent a wireless transceiver. The transceiver 1108 may include one or more receiver chains 1110, one or more transmitter chains 1112, or a combination thereof.
[0137] A receiver chain 1110 may be configured to receive signals (e.g., control information, data, packets) over a wireless medium. For example, the receiver chain 1110 may include one or more antennas to receive a signal over the air or wireless medium. The receiver chain 1110 may include at least one amplifier (e.g., a low-noise amplifier (LNA) ) configured to amplify the received signal. The receiver chain 1110 may include at least one demodulator configured to demodulate the receive signal and obtain the transmitted data by reversing the modulation technique applied during transmission of the signal. The receiver chain 1110 may include at least one decoder for decoding the demodulated signal to receive the transmitted data.
[0138] A transmitter chain 1112 may be configured to generate and transmit signals (e.g., control information, data, packets) . The transmitter chain 1112 may include at least one modulator for modulating data onto a carrier signal, preparing the signal for transmission over a wireless medium. The at least one modulator may be configured to support one or more techniques such as amplitude modulation (AM) , frequency modulation (FM) , or digital modulation schemes like phase-shift keying (PSK) or quadrature amplitude modulation (QAM) . The transmitter chain 1112 may also include at least one power amplifier configured to amplify the modulated signal to an appropriate power level suitable for transmission over the wireless medium. The transmitter chain 1112 may also include one or more antennas for transmitting the amplified signal into the air or wireless medium.
[0139] Figure 12 illustrates an example of a processor 1200 in accordance with aspects of the present disclosure. The processor 1200 may be an example of a processor configured to perform various operations in accordance with examples as described herein. The processor 1200 may include a controller 1202 configured to perform various operations in accordance with examples as described herein. The processor 1200 may optionally include at least one memory 1204, which may be, for example, an L1 / L2 / L3 cache. Additionally, or alternatively, the processor 1200 may optionally include one or more arithmetic-logic units (ALUs) 1206. One or more of these components may be in electronic communication or otherwise coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more interfaces (e.g., buses) .
[0140] The processor 1200 may be a processor chipset and include a protocol stack (e.g., a software stack) executed by the processor chipset to perform various operations (e.g., receiving, obtaining, retrieving, transmitting, outputting, forwarding, storing, determining, identifying, accessing, writing, reading) in accordance with examples as described herein. The processor chipset may include one or more cores, one or more caches (e.g., memory local to or included in the processor chipset (e.g., the processor 1200) or other memory (e.g., random access memory (RAM) , read-only memory (ROM) , dynamic RAM (DRAM) , synchronous dynamic RAM (SDRAM) , static RAM (SRAM) , ferroelectric RAM (FeRAM) , magnetic RAM (MRAM) , resistive RAM (RRAM) , flash memory, phase change memory (PCM) , and others) .
[0141] The controller 1202 may be configured to manage and coordinate various operations (e.g., signaling, receiving, obtaining, retrieving, transmitting, outputting, forwarding, storing, determining, identifying, accessing, writing, reading) of the processor 1200 to cause the processor 1200 to support various operations in accordance with examples as described herein. For example, the controller 1202 may operate as a control unit of the processor 1200, generating control signals that manage the operation of various components of the processor 1200. These control signals include enabling or disabling functional units, selecting data paths, initiating memory access, and coordinating timing of operations.
[0142] The controller 1202 may be configured to fetch (e.g., obtain, retrieve, receive) instructions from the memory 1204 and determine subsequent instruction (s) to be executed to cause the processor 1200 to support various operations in accordance with examples as described herein. The controller 1202 may be configured to track memory addresses of instructions associated with the memory 1204. The controller 1202 may be configured to decode instructions to determine the operation to be performed and the operands involved. For example, the controller 1202 may be configured to interpret the instruction and determine control signals to be output to other components of the processor 1200 to cause the processor 1200 to support various operations in accordance with examples as described herein. Additionally, or alternatively, the controller 1202 may be configured to manage flow of data within the processor 1200. The controller 1202 may be configured to control transfer of data between registers, ALUs 1206, and other functional units of the processor 1200.
[0143] The memory 1204 may include one or more caches (e.g., memory local to or included in the processor 1200 or other memory, such as RAM, ROM, DRAM, SDRAM, SRAM, MRAM, flash memory, etc. In some implementations, the memory 1204 may reside within or on a processor chipset (e.g., local to the processor 1200) . In some other implementations, the memory 1204 may reside external to the processor chipset (e.g., remote to the processor 1200) .
[0144] The memory 1204 may store computer-readable, computer-executable code including instructions that, when executed by the processor 1200, cause the processor 1200 to perform various functions described herein. The code may be stored in a non-transitory computer-readable medium such as system memory or another type of memory. The controller 1202 and / or the processor 1200 may be configured to execute computer-readable instructions stored in the memory 1204 to cause the processor 1200 to perform various functions. For example, the processor 1200 and / or the controller 1202 may be coupled with or to the memory 1204, the processor 1200, and the controller 1202, and may be configured to perform various functions described herein. In some examples, the processor 1200 may include multiple processors and the memory 1204 may include multiple memories. One or more of the multiple processors may be coupled with one or more of the multiple memories, which may, individually or collectively, be configured to perform various functions herein.
[0145] The one or more ALUs 1206 may be configured to support various operations in accordance with examples as described herein. In some implementations, the one or more ALUs 1206 may reside within or on a processor chipset (e.g., the processor 1200) . In some other implementations, the one or more ALUs 1206 may reside external to the processor chipset (e.g., the processor 1200) . One or more ALUs 1206 may perform one or more computations such as addition, subtraction, multiplication, and division on data. For example, one or more ALUs 1206 may receive input operands and an operation code, which determines an operation to be executed. One or more ALUs 1206 may be configured with a variety of logical and arithmetic circuits, including adders, subtractors, shifters, and logic gates, to process and manipulate the data according to the operation. Additionally, or alternatively, the one or more ALUs 1206 may support logical operations such as AND, OR, exclusive-OR (XOR) , not-OR (NOR) , and not-AND (NAND) , enabling the one or more ALUs 1206 to handle conditional operations, comparisons, and bitwise operations.
[0146] The processor 1200 may support wireless communication in accordance with examples as disclosed herein. The processor 1200 may be configured to or operable to support at least one controller (e.g., the controller 1202) coupled with at least one memory (e.g., the memory 1204) and configured to cause the processor to transmit a first indication including information of one or more available artificial intelligence functionalities; receive one or more configurations for the one or more available artificial intelligence functionalities; and transmit, for the one or more available artificial intelligence functionalities, at least one of an activation indication or a switch indication.
[0147] Additionally, the processor 1200 may be configured to or operable to support any one or combination of where the first indication further includes one or more configurations for one or more supported artificial intelligence functionalities; at least one of: the activation indication includes one or more of an activation report or an activation request; or the switch indication includes one or more of a switch report or a switch request; one or more of the activation request or the switch request includes at least one of an indication of a new artificial intelligence functionality or an indication of a configuration for UE switching; the one or more configurations include one or more parameters for at least one of the one or more available artificial intelligence functionalities or an initial artificial intelligence functionality to be activated; the one or more configurations for the one or more available artificial intelligence functionalities include one or more switching rules for the one or more available artificial intelligence functionalities.
[0148] Additionally, the processor 1200 may be configured to or operable to support any one or combination of where the one or more configurations include switch timer configuration for artificial intelligence functionality switching, the switch timer configuration including one or more of: switch timer activation based at least in part on occurrence of one or more functionality switching criteria or upon receiving an indication; switch timer expiry is to trigger one or more of artificial intelligence functionality fallback or artificial intelligence functionality switching; switch timer to be configured to be UE specific; switch timer configuration signaled via RRC configuration; or switch timer configuration signaled via one or more of MAC CE or DCI; the at least one controller is configured to cause the processor to transmit one or more of an ACK or a NACK for a functionality switch command; the at least one controller is configured to cause the processor to receive a confirmation message based at least in part on the activation indication or the switch indication; In some aspects, the techniques described herein relate to a processor, wherein the at least one controller is configured to cause the processor to transmit the first indication via UAI; the at least one controller is configured to cause the processor to receive the one or more configurations via RRC signaling; the at least one controller is configured to cause the processor to transmit the at least one of the activation indication or the switch indication via a MAC CE.
[0149] Figure 13 illustrates an example of a NE 1300 in accordance with aspects of the present disclosure. The NE 1300 may include a processor 1302, a memory 1304, a controller 1306, and a transceiver 1308. The processor 1302, the memory 1304, the controller 1306, or the transceiver 1308, or various combinations thereof or various components thereof may be examples of means for performing various aspects of the present disclosure as described herein. These components may be coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more interfaces.
[0150] The processor 1302, the memory 1304, the controller 1306, or the transceiver 1308, or various combinations or components thereof may be implemented in hardware (e.g., circuitry) . The hardware may include a processor, a digital signal processor (DSP) , an application-specific integrated circuit (ASIC) , or other programmable logic device, or any combination thereof configured as or otherwise supporting a means for performing the functions described in the present disclosure.
[0151] The processor 1302 may include an intelligent hardware device (e.g., a general-purpose processor, a DSP, a CPU, an ASIC, an FPGA, or any combination thereof) . In some implementations, the processor 1302 may be configured to operate the memory 1304. In some other implementations, the memory 1304 may be integrated into the processor 1302. The processor 1302 may be configured to execute computer-readable instructions stored in the memory 1304 to cause the NE 1300 to perform various functions of the present disclosure.
[0152] The memory 1304 may include volatile or non-volatile memory. The memory 1304 may store computer-readable, computer-executable code including instructions when executed by the processor 1302 cause the NE 1300 to perform various functions described herein. The code may be stored in a non-transitory computer-readable medium such as the memory 1304 or another type of memory. Computer-readable media includes both non-transitory computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A non-transitory storage medium may be any available medium that may be accessed by a general-purpose or special-purpose computer.
[0153] In some implementations, the processor 1302 and the memory 1304 coupled with the processor 1302 may be configured to cause the NE 1300 to perform one or more of the functions described herein (e.g., executing, by the processor 1302, instructions stored in the memory 1304) . For example, the processor 1302 may support wireless communication at the NE 1300 in accordance with examples as disclosed herein. The NE 1300 may be configured to or operable to support a means for receiving a first indication including information of one or more available artificial intelligence functionalities of a UE; transmitting one or more configurations for at least one of the one or more available artificial intelligence functionalities or one or more other artificial intelligence functionalities ; and receiving, for the one or more available artificial intelligence functionalities, at least one of an activation indication or a switch indication.
[0154] Additionally, the NE 1300 may be configured to or operable to support any one or combination of transmitting one or more of an artificial intelligence functionality activation command or an artificial intelligence functionality switch command; at least one of the activation indication includes an activation request or the switch indication includes a switch request or a switch report, and wherein the at least one processor is configured to cause the NE to transmit one or more of an activation confirmation or a switch confirmation via a MAC CE or a DCI; the one or more configurations include one or more parameters for at least one of the one or more available artificial intelligence functionalities, the one or more other artificial intelligence functionalities, or an initial artificial intelligence functionality to be activated; the one or more configurations for the at least one of the one or more available artificial intelligence functionalities or the one or more other artificial intelligence functionalities include one or more switching rules for the at least one of the one or more available artificial intelligence functionalities or the one or more other artificial intelligence functionalities; the one or more configurations include switch timer configuration for artificial intelligence functionality switching, the switch timer configuration including one or more of: switch timer activation based at least in part on occurrence of one or more functionality switching criteria or upon receiving an indication; switch timer expiry is to trigger one or more of artificial intelligence functionality fallback or artificial intelligence functionality switching; switch timer to be configured to be UE specific; switch timer configuration signaled via RRC configuration; or switch timer configuration signaled via one or more of MAC CE or DCI.
[0155] Additionally, or alternatively, the NE 1300 may support at least one memory (e.g., the memory 1304) and at least one processor (e.g., the processor 1302) coupled with the at least one memory and configured to cause the NE receive a first indication including information of one or more available artificial intelligence functionalities of a UE; transmit one or more configurations for at least one of the one or more available artificial intelligence functionalities or one or more other artificial intelligence functionalities ; and receive, for the one or more available artificial intelligence functionalities, at least one of an activation indication or a switch indication.
[0156] Additionally, the NE 1300 may be configured to support any one or combination of where the at least one processor is configured to cause the NE to transmit one or more of an artificial intelligence functionality activation command or an artificial intelligence functionality switch command; wherein at least one of the activation indication includes an activation request or the switch indication includes a switch request or a switch report, and wherein the at least one processor is configured to cause the NE to transmit one or more of an activation confirmation or a switch confirmation via a MAC CE or a DCI; wherein the one or more configurations include one or more parameters for at least one of the one or more available artificial intelligence functionalities, the one or more other artificial intelligence functionalities, or an initial artificial intelligence functionality to be activated; wherein the one or more configurations for the at least one of the one or more available artificial intelligence functionalities or the one or more other artificial intelligence functionalities include one or more switching rules for the at least one of the one or more available artificial intelligence functionalities or the one or more other artificial intelligence functionalities; wherein the one or more configurations include switch timer configuration for artificial intelligence functionality switching, the switch timer configuration including one or more of: switch timer activation based at least in part on occurrence of one or more functionality switching criteria or upon receiving an indication; switch timer expiry is to trigger one or more of artificial intelligence functionality fallback or artificial intelligence functionality switching; switch timer to be configured to be UE specific; switch timer configuration signaled via RRC configuration; or switch timer configuration signaled via one or more of MAC CE or DCI.
[0157] The controller 1306 may manage input and output signals for the NE 1300. The controller 1306 may also manage peripherals not integrated into the NE 1300. In some implementations, the controller 1306 may utilize an operating system such as or other operating systems. In some implementations, the controller 1306 may be implemented as part of the processor 1302.
[0158] In some implementations, the NE 1300 may include at least one transceiver 1308. In some other implementations, the NE 1300 may have more than one transceiver 1308. The transceiver 1308 may represent a wireless transceiver. The transceiver 1308 may include one or more receiver chains 1310, one or more transmitter chains 1312, or a combination thereof.
[0159] A receiver chain 1310 may be configured to receive signals (e.g., control information, data, packets) over a wireless medium. For example, the receiver chain 1310 may include one or more antennas to receive a signal over the air or wireless medium. The receiver chain 1310 may include at least one amplifier (e.g., a low-noise amplifier (LNA) ) configured to amplify the received signal. The receiver chain 1310 may include at least one demodulator configured to demodulate the receive signal and obtain the transmitted data by reversing the modulation technique applied during transmission of the signal. The receiver chain 1310 may include at least one decoder for decoding the demodulated signal to receive the transmitted data.
[0160] A transmitter chain 1312 may be configured to generate and transmit signals (e.g., control information, data, packets) . The transmitter chain 1312 may include at least one modulator for modulating data onto a carrier signal, preparing the signal for transmission over a wireless medium. The at least one modulator may be configured to support one or more techniques such as amplitude modulation (AM) , frequency modulation (FM) , or digital modulation schemes like phase-shift keying (PSK) or quadrature amplitude modulation (QAM) . The transmitter chain 1312 may also include at least one power amplifier configured to amplify the modulated signal to an appropriate power level suitable for transmission over the wireless medium. The transmitter chain 1312 may also include one or more antennas for transmitting the amplified signal into the air or wireless medium.
[0161] Figure 14 illustrates a flowchart of a method 1400 in accordance with aspects of the present disclosure. The operations of the method may be implemented by a UE as described herein. In some implementations, the UE may execute a set of instructions to control the function elements of the UE to perform the described functions. It should be noted that the method described herein describes a possible implementation, and that the operations and the steps may be rearranged or otherwise modified and that other implementations are possible.
[0162] At 1402, the method may include transmitting a first indication comprising information of one or more available artificial intelligence functionalities. The operations of 1402 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 1402 may be performed by a UE as described with reference to Figure 11.
[0163] At 1404, the method may include receiving one or more configurations for the one or more available artificial intelligence functionalities. The operations of 1404 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 1404 may be performed by a UE as described with reference to Figure 11.
[0164] At 1406, the method may include transmitting, for the one or more available artificial intelligence functionalities, at least one of an activation indication or a switch indication. The operations of 1406 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 1406 may be performed a UE as described with reference to Figure 11.
[0165] Figure 15 illustrates a flowchart of a method 1500 in accordance with aspects of the present disclosure. The operations of the method may be implemented by a NE as described herein. In some implementations, the NE may execute a set of instructions to control the function elements of the NE to perform the described functions. It should be noted that the method described herein describes a possible implementation, and that the operations and the steps may be rearranged or otherwise modified and that other implementations are possible.
[0166] At 1502, the method may include receiving a first indication including information of one or more available artificial intelligence functionalities of a UE. The operations of 1502 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 1502 may be performed by a NE as described with reference to Figure 13.
[0167] At 1504, the method may include transmitting one or more configurations for at least one of the one or more available artificial intelligence functionalities or one or more other artificial intelligence functionalities. The operations of 1504 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 1504 may be performed by a NE as described with reference to Figure 13.
[0168] At 1506, the method may include receiving, for the one or more available artificial intelligence functionalities, at least one of an activation indication or a switch indication. The operations of 1506 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 1506 may be performed a NE as described with reference to Figure 13.
[0169] The description herein is provided to enable a person having ordinary skill in the art to make or use the disclosure. Various modifications to the disclosure will be apparent to a person having ordinary skill in the art, and the generic principles defined herein may be applied to other variations without departing from the scope of the disclosure. Thus, the disclosure is not limited to the examples and designs described herein but is to be accorded the broadest scope consistent with the principles and novel features disclosed herein.
Claims
1.A user equipment (UE) for wireless communication, comprising:at least one memory; andat least one processor coupled with the at least one memory and configured to cause the UE to:transmit a first indication comprising information of one or more available artificial intelligence functionalities;receive one or more configurations for the one or more available artificial intelligence functionalities; andtransmit, for the one or more available artificial intelligence functionalities, at least one of an activation indication or a switch indication.2.The UE of claim 1, wherein the first indication further comprises one or more configurations for one or more supported artificial intelligence functionalities.3.The UE of claim 1, wherein at least one of:the activation indication comprises one or more of an activation report or an activation request; orthe switch indication comprises one or more of a switch report or a switch request.4.The UE of claim 3, wherein one or more of the activation request or the switch request comprises at least one of an indication of a new artificial intelligence functionality or an indication of a configuration for UE switching.5.The UE of claim 1, wherein the one or more configurations comprise one or more parameters for at least one of the one or more available artificial intelligence functionalities or an initial artificial intelligence functionality to be activated.6.The UE of claim 1, wherein the one or more configurations for the one or more available artificial intelligence functionalities comprise one or more switching rules for the one or more available artificial intelligence functionalities.7.The UE of claim 1, wherein the one or more configurations comprise switch timer configuration for artificial intelligence functionality switching, the switch timer configuration comprising one or more of:switch timer activation based at least in part on occurrence of one or more functionality switching criteria or upon receiving an indication;switch timer expiry is to trigger one or more of artificial intelligence functionality fallback or artificial intelligence functionality switching;switch timer to be configured to be UE specific;switch timer configuration signaled via radio resource control (RRC) configuration; orswitch timer configuration signaled via one or more of medium access control (MAC) control element (CE) or downlink control information (DCI) .8.The UE of claim 1, wherein the at least one processor is configured to cause the UE to transmit one or more of an acknowledgement (ACK) or a negative acknowledgement (NACK) for a functionality switch command.9.The UE of claim 1, wherein the at least one processor is configured to cause the UE to receive a confirmation message based at least in part on the activation indication or the switch indication.10.The UE of claim 1, wherein the at least one processor is configured to cause the UE to transmit the first indication via UE assistance information (UAI) .11.The UE of claim 1, wherein the at least one processor is configured to cause the UE to receive the one or more configurations via radio resource control (RRC) signaling.12.The UE of claim 1, wherein the at least one processor is configured to cause the UE to transmit the at least one of the activation indication or the switch indication via a medium access control (MAC) control element (CE) .13.A processor for wireless communication, comprising:at least one controller coupled with at least one memory and configured to cause the processor to:transmit a first indication comprising information of one or more available artificial intelligence functionalities;receive one or more configurations for the one or more available artificial intelligence functionalities; andtransmit, for the one or more available artificial intelligence functionalities, at least one of an activation indication or a switch indication.14.A method performed by a user equipment (UE) , the method comprising:transmitting a first indication comprising information of one or more available artificial intelligence functionalities;receiving one or more configurations for the one or more available artificial intelligence functionalities; andtransmitting, for the one or more available artificial intelligence functionalities, at least one of an activation indication or a switch indication.15.A network equipment for wireless communication, comprising:at least one memory; andat least one processor coupled with the at least one memory and configured to cause the network equipment to:receive a first indication comprising information of one or more available artificial intelligence functionalities of a user equipment (UE) ;transmit one or more configurations for at least one of the one or more available artificial intelligence functionalities or one or more other artificial intelligence functionalities ; andreceive, for the one or more available artificial intelligence functionalities, at least one of an activation indication or a switch indication.16.The network equipment of claim 15, wherein the at least one processor is configured to cause the network equipment to transmit one or more of an artificial intelligence functionality activation command or an artificial intelligence functionality switch command.17.The network equipment of claim 15, wherein at least one of the activation indication comprises an activation request or the switch indication comprises a switch request or a switch report, and wherein the at least one processor is configured to cause the network equipment to transmit one or more of an activation confirmation or a switch confirmation via a medium access control (MAC) control element (CE) or a DCI.18.The network equipment of claim 15, wherein the one or more configurations comprise one or more parameters for at least one of the one or more available artificial intelligence functionalities, the one or more other artificial intelligence functionalities, or an initial artificial intelligence functionality to be activated.19.The network equipment of claim 15, wherein the one or more configurations for the at least one of the one or more available artificial intelligence functionalities or the one or more other artificial intelligence functionalities comprise one or more switching rules for the at least one of the one or more available artificial intelligence functionalities or the one or more other artificial intelligence functionalities.20.The network equipment of claim 15, wherein the one or more configurations comprise switch timer configuration for artificial intelligence functionality switching, the switch timer configuration comprising one or more of:switch timer activation based at least in part on occurrence of one or more functionality switching criteria or upon receiving an indication;switch timer expiry is to trigger one or more of artificial intelligence functionality fallback or artificial intelligence functionality switching;switch timer to be configured to be UE specific;switch timer configuration signaled via radio resource control (RRC) configuration; orswitch timer configuration signaled via one or more of medium access control (MAC) control element (CE) or downlink control information (DCI) .
Citation Information
Patent Citations
Providing machine learning-based assistance to producer nodes
CN114762367A
Artificial intelligence model configuration method and device, terminal and network equipment
CN117135650A
Artificial intelligence radio function model management in a communication network
US20240187877A1
Enhanced collaboration between user equpiment and network to facilitate machine learning
WO2022235525A1