Inference configuration management for artificial intelligence model
By employing content/definition and filtering schemes, signaling-based, and timer-based management, the overhead associated with managing AI/ML model inference configurations in wireless networks is reduced, improving network efficiency.
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-10-02
- Publication Date
- 2026-04-09
AI Technical Summary
The management of inference configurations for artificial intelligence (AI)/machine learning (ML) models in wireless networks is associated with high signaling overhead, particularly when multiple configurations are involved.
Implementing a content/definition and filtering scheme, signaling-based management, and timer-based management of inference configurations to reduce overhead, including UE and network entity interactions for supported functionality and model availability information.
Reduces signaling overhead by optimizing the transmission and management of inference configurations, enhancing network efficiency and reducing operational costs.
Smart Images

Figure CN2024123174_09042026_PF_FP_ABST
Abstract
Description
INFERENCE CONFIGURATION MANAGEMENT FOR ARTIFICIAL INTELLIGENCE MODELTECHNICAL FIELD
[0001] The present disclosure relates generally to wireless communication, and more particularly, to management of inference configurations for artificial intelligence (AI) / machine learning (ML) models in wireless networks.BACKGROUND
[0002] The Third Generation Partnership Project (3GPP) specifies a radio interface referred to as fifth generation (5G) new radio (NR) (5G NR) . An architecture for a 5G NR wireless communication system includes a 5G core (5GC) network, a 5G radio access network (5G-RAN) , a user equipment (5G UE) , etc. The 5G NR architecture seeks to provide increased data rates, decreased latency, and / or increased capacity compared to prior generation cellular communication systems.
[0003] Wireless communication systems, in general, provide various telecommunication services (e.g., telephony, video, data, messaging, etc. ) based on multiple-access technologies, such as orthogonal frequency division multiple access (OFDMA) technologies, that support communication with multiple UEs. Improvements in mobile broadband continue the progression of such wireless communication technologies. For example, AI may be utilized in a radio access network (RAN) to implement network intelligence and provide an efficient RAN.
[0004] BRIEF SUMMARY
[0005] The following presents a simplified summary of one or more aspects in order to provide a basic understanding of such aspects. This summary is not an extensive overview of all contemplated aspects. This summary neither identifies key or critical elements of all aspects nor delineates the scope of any or all aspects. Its sole purpose is to present some concepts of one or more aspects in a simplified form as a prelude to the more detailed description that is presented later.
[0006] A network entity, such as a radio access network (RAN) entity (e.g., a base station or a unit of a base station) or a core network (CN) entity (e.g., location management function (LMF) ) , or operation, administration and maintenance (OAM) entity, may communicate with a user equipment (UE) in a radio access network (RAN) , where artificial intelligence (AI) / machine learning (ML) may be utilized between the UE and the network entity to implement network intelligence and provide an efficient RAN. The application of AI / ML is considered with respect to wireless communications, such that AI / ML may be utilized to examine the air-interface, Xn connectivity, or other interfaces corresponding to each target use case. Use cases that may correspond to air interface include channel state information (CSI) feedback enhancement, beam management, positioning accuracy enhancement, Layer1 (L1) or Layer3 (L3) mobility management, or the like.
[0007] A model may be deployed at a UE side and / or at the network side (e.g., network entity) of a communication link. When the model is deployed, the related entity performs the inference accordingly. A UE-side model is an instance where the model inference is performed entirely at the UE. A network-side model is an instance where the model inference is performed entirely at the network. In some instances, both a UE-side model and a network-side model can be considered as a one-sided model. In some instances, a two-sided model may be considered as the paired AI / ML model over which joint inference is performed across the UE and network (e.g., a first part of the inference is performed by UE, and a second part of the inference is performed by network, or vice versa) . In some instances, such as a functionality-based control, the network performs at least one functionality operation, such as, functionality identification, functionality selection, functionality activation, functionality deactivation, functionality switching, fallback to non-AI operation or other possible operations. In some instances, such as a model-based control / life control management (LCM) , the network is aware of the model information to be controlled.
[0008] To enable inference for a UE-side model for functionality / model-based control, the network may provide an inference configuration to the UE. The inference configuration can be provided to the UE before or after the applicable functionality is reported. The transmission of the inference configuration may include high signaling overhead. When performing management for different inference configurations, it is desirable to reduce the overhead associated with the inference configurations.
[0009] Aspects of the present disclosure address the above-noted and other deficiencies by managing inference configuration for AI in wireless networks, such as a content / definition and filtering scheme for inference configuration, a signaling based management of multiple inference configurations, or timer based management of multiple inference configurations.
[0010] According to some aspects, a UE transmits, to a network entity, at least one of: supported functionality information, model availability information, or first inference configuration information. The UE receives, from the network entity, second inference configuration information based on the first inference configuration information. The UE transmits, to the network entity, applicable functionality information based on the second inference configuration information.
[0011] According to some aspects, a network entity obtains first inference configuration information. The network entity transmits, to a UE, second inference configuration information based on the first inference configuration information. The network entity receives, from the UE, applicable functionality information based on the second inference configuration.BRIEF DESCRIPTION OF THE DRAWINGS
[0012] FIG. 1 illustrates a diagram of a wireless communications system that includes a plurality of UEs and network entities in communication over one or more cells according to an embodiment.
[0013] FIGs. 2A-2B illustrate diagrams of AI / ML models associated with one or more functionalities.
[0014] FIG. 3 is a signaling diagram that illustrates an applicable functionality reporting procedure.
[0015] FIG. 4A illustrates a signaling diagram of an inference configuration reporting procedure where the UE reports first inference configuration information to the network entity 104.
[0016] FIG. 4B illustrates a signaling diagram of an inference configuration reporting procedure where the network entity acquires the first inference configuration information from an additional entity.
[0017] FIG. 5 illustrates a signaling diagram for signaling-based activation of inference configuration management.
[0018] FIG. 6 illustrates a flow diagram of an example timer-based management of multiple inference configurations.
[0019] FIG. 7 is a flowchart of a method of wireless communication at a UE according to an embodiment.
[0020] FIG. 8 is a flowchart of a method of wireless communication at a network entity according to an embodiment.
[0021] FIG. 9 is a diagram illustrating a hardware implementation for an example UE apparatus according to some embodiments.
[0022] FIG. 10 is a diagram illustrating a hardware implementation for one or more example network entities according to some embodiments.DETAILED DESCRIPTION
[0023] FIG. 1 illustrates a diagram 100 of a wireless communications system associated with a plurality of cells 190. The wireless communications system includes user equipments (UEs) 102 and base stations / network entities 104. Some base stations may include an aggregated base station architecture and other base stations may include a disaggregated base station architecture. The aggregated base station architecture utilizes a radio protocol stack that is physically or logically integrated within a single radio access network (RAN) node. A disaggregated base station architecture utilizes a protocol stack that is physically or logically distributed among two or more units (e.g., radio unit (RU) 106, distributed unit (DU) 108, central unit (CU) 110) . For example, a CU 110 is implemented within a RAN node, and one or more DUs 108 may be co-located with the CU 110, or alternatively, may be geographically or virtually distributed throughout one or multiple other RAN nodes. The DUs 108 may be implemented to communicate with one or more RUs 106. Any of the RU 106, the DU 108 and the CU 110 can be implemented as virtual units, such as a virtual radio unit (VRU) , a virtual distributed unit (VDU) , or a virtual central unit (VCU) . The base station / network entity 104 (e.g., an aggregated base station or disaggregated units of the base station, such as the RU 106 or the DU 108) , may be referred to as a transmission reception point (TRP) .
[0024] Operations of the base station 104 and / or network designs may be based on aggregation characteristics of base station functionality. For example, disaggregated base station architectures are utilized in an integrated access backhaul (IAB) network, an open-radio access network (O-RAN) network, or a virtualized radio access network (vRAN) , which may also be referred to a cloud radio access network (C-RAN) . Disaggregation may include distributing functionality across the two or more units at various physical locations, as well as distributing functionality for at least one unit virtually, which can enable flexibility in network designs. The various units of the disaggregated base station architecture, or the disaggregated RAN architecture, can be configured for wired or wireless communication with at least one other unit. For example, the base stations 104d, 104e and / or the RUs 106a, 106b, 106c, 106d may communicate with the UEs 102a, 102b, 102c, 102d, and / or 102s via one or more radio frequency (RF) access links based on a Uu interface. In examples, multiple RUs 106 and / or base stations 104 may simultaneously serve the UEs 102, such as by intra-cell and / or inter-cell access links between the UEs 102 and the RUs 106 / base stations 104.
[0025] The RU 106, the DU 108, and the CU 110 may include (or may be coupled to) one or more interfaces configured to transmit or receive information / signals via a wired or wireless transmission medium. For example, a wired interface can be configured to transmit or receive the information / signals over a wired transmission medium, such as via the fronthaul link 160 between the RU 106d and the baseband unit (BBU) 112 of the base station 104d associated with the cell 190d. The BBU 112 includes a DU 108 and a CU 110, which may also have a wired interface (e.g., midhaul link) configured between the DU 108 and the CU 110 to transmit or receive the information / signals between the DU 108 and the CU 110. In further examples, a wireless interface, which may include a receiver, a transmitter, or a transceiver, such as an RF transceiver, configured to transmit and / or receive the information / signals via the wireless transmission medium, such as for information communicated between the RU 106a of the cell 190a and the base station 104e of the cell 190e via cross-cell communication beams 136-138 of the RU 106a and the base station 104e.
[0026] The RUs 106 may be configured to implement lower layer functionality. For example, the RU 106 is controlled by the DU 108 and may correspond to a logical node that hosts RF processing functions, or lower layer PHY functionality, such as execution of fast Fourier transform (FFT) , inverse FFT (iFFT) , digital beamforming, physical random access channel (PRACH) extraction and filtering, etc. The functionality of the RU 106 may be based on the functional split, such as a functional split of lower layers.
[0027] The RUs 106 may transmit or receive over-the-air (OTA) communication with one or more UEs 102. For example, the RU 106b of the cell 190b communicates with the UE 102b of the cell 190b via a first set of communication beams 132 of the RU 106b and a second set of communication beams 134b of the UE 102b, which may correspond to inter-cell communication beams or, in some examples, cross-cell communication beams. For instance, the UE 102b of the cell 190b may communicate with the RU 106a of the cell 190a via a third set of communication beams 134a of the UE 102b and a fourth set of communication beams 136 of the RU 106a. DUs 108 can control both real-time and non-real-time features of control plane and user plane communications of the RUs 106.
[0028] Any combination of the RU 106, the DU 108, and the CU 110, or reference thereto individually, may correspond to a base station 104. Thus, the base station 104 may include at least one of the RU 106, the DU 108, or the CU 110. The base stations 104 provide the UEs 102 with access to a core network. The base stations 104 may relay communications between the UEs 102 and the core network (not shown) . The base stations 104 may be associated with macrocells for higher-power cellular base stations and / or small cells for lower-power cellular base stations. For example, the cell 190e may correspond to a macrocell, whereas the cells 190a-190d may correspond to small cells. Small cells include femtocells, picocells, microcells, etc. A network that includes at least one macrocell and at least one small cell may be referred to as a “heterogeneous network. ”
[0029] Transmissions from a UE 102 to a base station / network entity 104 / RU 106 are referred to as uplink (UL) transmissions, whereas transmissions from the base station 104 / RU 106 to the UE 102 are referred to as downlink (DL) transmissions. Uplink transmissions may also be referred to as reverse link transmissions and downlink transmissions may also be referred to as forward link transmissions. For example, the RU 106d utilizes antennas of the base station 104d of cell 190d to transmit a downlink / forward link communication to the UE 102d or receive an uplink / reverse link communication from the UE 102d based on the Uu interface associated with the access link between the UE 102d and the base station 104d / RU 106d.
[0030] Communication links between the UEs 102 and the base stations 104 / RUs 106 may be based on multiple-input and multiple-output (MIMO) antenna technology, including spatial multiplexing, beamforming, and / or transmit diversity. The communication links may be associated with one or more carriers. The UEs 102 and the base stations 104 / RUs 106 may utilize a spectrum bandwidth of Y MHz (e.g., 5, 10, 15, 20, 100, 400, 800, 1600, 2000, etc. MHz) per carrier allocated in a carrier aggregation of up to a total of Yx MHz, where x component carriers (CCs) are used for communication in each of the uplink and downlink directions. The carriers may or may not be adjacent to each other along a frequency spectrum. In examples, uplink and downlink carriers may be allocated in an asymmetric manner, with more or fewer carriers allocated to either the uplink or the downlink. A primary component carrier and one or more secondary component carriers may be included in the component carriers. The primary component carrier may be associated with a primary cell (PCell) and a secondary component carrier may be associated with a secondary cell (SCell) .
[0031] The UEs 102 and the base stations 104 / RUs 106 may each include a plurality of antennas. The plurality of antennas may correspond to antenna elements, antenna panels, and / or antenna arrays that may facilitate beamforming operations. For example, the RU 106b transmits a downlink beamformed signal based on a first set of communication beams 132 to the UE 102b in one or more transmit directions of the RU 106b. The UE 102b may receive the downlink beamformed signal based on a second set of communication beams 134b from the RU 106b in one or more receive directions of the UE 102b. In a further example, the UE 102b may also transmit an uplink beamformed signal (e.g., sounding reference signal (SRS) ) to the RU 106b based on the second set of communication beams 134b in one or more transmit directions of the UE 102b. The RU 106b may receive the uplink beamformed signal from the UE 102b in one or more receive directions of the RU 106b. The UE 102b may perform beam training to determine the best receive and transmit directions for the beamformed signals. The transmit and receive directions for the UEs 102 and the base stations 104 / RUs 106 may or may not be the same.
[0032] In further examples, beamformed signals may be communicated between a first base station / RU 106a and a second base station 104e. For instance, the base station 104e of the cell 190e may transmit a beamformed signal to the RU 106a based on the communication beams 138 in one or more transmit directions of the base station 104e. The RU 106a may receive the beamformed signal from the base station 104e of the cell 190e based on the RU communication beams 136 in one or more receive directions of the RU 106a. In further examples, the base station 104e transmits a downlink beamformed signal to the UE 102e based on the communication beams 138 in one or more transmit directions of the base station 104e. The UE 102e receives the downlink beamformed signal from the base station 104e based on UE communication beams 130 in one or more receive directions of the UE 102e. The UE 102e may also transmit an uplink beamformed signal to the base station 104e based on the UE communication beams 130 in one or more transmit directions of the UE 102e, such that the base station 104e may receive the uplink beamformed signal from the UE 102e in one or more receive directions of the base station 104e.
[0033] The base station 104 may include and / or be referred to as a network entity. That is, “network entity” may refer to the base station 104 or at least one unit of the base station 104, such as the RU 106, the DU 108, and / or the CU 110. The base station 104 may also include and / or be referred to as a next generation evolved Node B (ng-eNB) , a next generation NB (gNB) , an evolved NB (eNB) , an access point, a base transceiver station, a radio base station, a radio transceiver, a transceiver function, a basic service set (BSS) , an extended service set (ESS) , a TRP, a network node, network equipment, or other related terminology. The base station 104 or an entity at the base station 104 can be implemented as an IAB node, a relay node, a sidelink node, an aggregated (monolithic) base station, or a disaggregated base station including one or more RUs 106, DUs 108, and / or CUs 110. A set of aggregated or disaggregated base stations may be referred to as a next generation-radio access network (NG-RAN) . In some examples, the UE 102a operates in dual connectivity (DC) with the base station 104e and the base station / RU 106a. In such cases, the base station 104e can be a master node and the base station / RU 160a can be a secondary node.
[0034] Uplink / downlink signaling may also be communicated via a satellite positioning system (SPS) 114. In an example, the SPS 114 associated with the cell 190c may be in communication with one or more UEs 102, such as the UE 102c, and one or more base stations 104 / RUs 106, such as the RU 106c. The SPS 114 may correspond to one or more of a Global Navigation Satellite System (GNSS) , a global position system (GPS) , a non-terrestrial network (NTN) , or other satellite position / location system. The SPS 114 may be associated with long term evolution (LTE) signals, NR signals (e.g., based on round trip time (RTT) and / or multi-RTT) , wireless local area network (WLAN) signals, a terrestrial beacon system (TBS) , sensor-based information, NR enhanced cell ID (NR E-CID) techniques, downlink angle-of-departure (DL-AoD) , downlink time difference of arrival (DL-TDOA) , uplink time difference of arrival (UL-TDOA) , uplink angle-of-arrival (UL-AoA) , and / or other systems, signals, or sensors.
[0035] Still referring to FIG. 1, any of the UEs 102 may include an applicable functionality component 140 configured to transmit, to a network entity, at least one of:supported functionality information, model availability information, or first inference configuration information; receive, from the network entity, second inference configuration information based on the first inference configuration information; and transmit, to the network entity, applicable functionality information based on the second inference configuration information.
[0036] The network entity 104 may include an inference configuration component 150 configured to obtain first inference configuration information; transmit, to a UE, second inference configuration information based on the first inference configuration information; and receiving, from the UE, applicable functionality information based on the second inference configuration. As discussed herein, “base station (s) ” may be illustrated as a network entity but this is not intended to place any limitations on the other possible implementation, e.g., the CN entity or OAM entity.
[0037] Accordingly, FIG. 1 describes a wireless communication system that may be implemented in connection with aspects of one or more other figures described herein. Further, although the following description may be focused on 5G NR, the concepts described herein may be applicable to other similar areas, such as 5G-Advanced and future versions, LTE, LTE-advanced (LTE-A) , and other wireless technologies, such as 6G.
[0038] FIGs. 2A-2B illustrate diagrams 200A-200B of artificial intelligence (AI) / machine learning (ML) models 252 associated with one or more functionalities 250. In particular, the diagram 200A illustrates one or more models (e.g., Model 1 to Model N, collectively model group 252a) associated with one functionality (i.e., functionality k 250a) , whereas the diagram 200B illustrates the one or more models (e.g., Model n included in each of model groups 252b and 252c) being associated with multiple functionalities (e.g., functionality i 250b and functionality j 250c) .
[0039] Embodiments described herein include communication methods that introduce AI / ML techniques at a radio access network (RAN) . The AI / ML models 252 provide improved network intelligence and increased RAN efficiency. AI / ML models 252 may be used in association with an air-interface, Xn connectivity, and / or other related interfaces. For example, AI / ML models 252 used in association with air interface may be provided for channel state information (CSI) feedback enhancements, beam management, positioning accuracy enhancements, etc.
[0040] AI / ML models 252 may be deployed at the UE-side and / or the network-side of a communication link. When the AI / ML model 252 is deployed, the corresponding entity may perform an inferencing operation. If the inference performed for the AI / ML model 252 occurs entirely at the UE, the AI / ML model may be referred to as a UE-side model. If the inference performed for the AI / ML model 252 occurs entirely at the network, the AI / ML model may be referred to as a network-side model. In some examples, UE-side models and network-side models are considered one-sided AI / ML model. In other examples, there are two-sided AI / ML models where the UE-side model and the network-side model are paired with each other to perform a joint inference across the UE and the network. That is, a first part of the inference is performed by the UE and a second (remaining) part of the inference is performed by the network, or vice versa.
[0041] To implement the AI / ML models 252 for various use cases or sub-use cases, one or more functionalities 250 are defined for the AI / ML models 252. One functionality 250 may be performed by one or more AI / ML models 252. For example, in the diagram 200A, Model 1 (and optionally up to Model N) , collectively 252a, may perform the functionality k 250a. In other implementations, multiple different functionalities 250 may be performed / shared by a same AI / ML model. For example, in the diagram 200B, Model n may perform each of functionality i 250b and functionality j 250c. FIGs. 2A-2B illustrate one or more AI / ML models 252 that perform one or more functionalities 250, whereas FIG. 3 illustrates a procedure to enable inferencing by the AI / ML models 252.
[0042] FIG. 3 is a signaling diagram that illustrates a functionality reporting procedure 300 (e.g., applicable functionality reporting) . In an example where an inference of the UE-side model is enabled for functionality / model-based control, a network entity 104 may provide the inference configuration to the UE 102. The inference configuration can be transmitted 306a / 306b, to the UE 102, before or after communication 308 of an applicable functionality report, such as through either of the illustrated radio resource control (RRC) reconfiguration messages 306a / 306b. In some implementations, information associated with the applicable functionality reporting is indicated in the configuration message transmitted 306 from the network entity 104 to the UE 102.
[0043] In the diagram 300, the network entity 104 may initiate the procedure by transmitting 302, to the UE 102, a UECapabilityEnqiry message. For example, the UECapabilityEnqiry message triggers the UE 102 to report supported AI / ML functionalities to the network entity 104. In response to receiving 302 the UECapabilityEnqiry message, the UE 102 transmits 304 a UECapablityInformation message to the network entity 104. The UECapablityInformation message indicates supported AI / ML functionalit (ies) at the UE 102 / UE-side model.
[0044] Based on one or more supported AI / ML functionalities at the UE 102, the network entity 104 transmits 306a, to the UE 102, a configuration message (e.g., an RRCReconfiguration message) that enables the inference operation of the UE-side model. The configuration message may include other configuration information, such as network-side additional condition information, where the other configuration information is different from the inference configuration information. In some examples, the network entity 104 includes a network-side additional condition in the configuration message. When the UE 102 receives 306a the inference configuration from the network entity 104 based on the indicated UE-supported functionalities, the UE 102 may determine one or more applicable functionalities from the supported functionalities. The determination of the one or more applicable functionalities may be based on the network-side additional condition (s) , if provided, UE-side additional conditions (e.g., determined internally at the UE 102) , and / or AI / ML model availability at the UE 102. In some implementations, the UE 102 determines the one or more applicable functionalities even when the network entity 104 does not provide the network-side additional condition (s) to the UE 102.
[0045] The UE 102 transmits 308, to the network entity 104, an applicable functionality report based on the inference configuration, where one or more applicable functionalities is selected from the UE-supported functionalities. For example, upon being configured to indicate applicable functionality and / or upon a change of applicable functionality, the UE 102 indicates 308 the applicable functionality to the network entity 104. In some examples, the applicable functionality is included in an RRCReconfigurationComplete message or UEAssistanceInformation (UAI) message. The UE 102 may transmit 308 the applicable functionality report to the network entity 104 based on the network-side additional condition requesting the applicable functionality report.
[0046] In other implementations, the network entity 104 provides an inference configuration to the UE 102 (or activates an inference configuration) after the network entity 104 receives 308 the applicable functionality reporting message from the UE 102. For example, the network entity 104 transmits 306b, to the UE 102, an RRCReconfiguration message including the inference configuration (e.g., such as when the inference configuration has not already been provided to the UE 102 or when an already-provided inference configuration is to be changed / updated) in response to receiving 308 the applicable functionality reporting message from the UE 102. In examples where the inference configuration has already been transmitted 306a to the UE 102 based on the one or more supported functionalities, it is up to network implementation regarding whether to provide an updated / different inference configuration to the UE 102.
[0047] The UE 102 and the network entity 104 may activate 310 one or more applicable functionalities (e.g., to an initial activation state) after communication 306a-306b of the inference configuration to the UE 102. In some examples, activation information is included with the inference configuration message. In other examples, the activation information is transmitted to the UE 102 in a separate message from the configuration message. The UE 102 and the network entity 104 may perform 310 any of activation, deactivation, inferencing, or monitoring of the one or more applicable functionalities. For example, activation / deactivation of an applicable functionality may occur based on communication (s) 310 between the UE 102 and the network entity 104. The activation / deactivation may be based on additional layer 1 (L1) / layer 2 (L2) signaling.
[0048] Transmission of the inference configuration to the UE 102 may be associated with additional signaling overhead. Thus, overhead reduction techniques may be implemented for inference configuration management, such as when multiple different inference configurations are being managed. The content of the inference configuration message and / or the management of the inference configuration (s) may be leveraged to reduce the signaling overhead, such as through a content / definition and filtering scheme for an inference configuration, as described in FIGs. 4A-4B, signaling-based management of multiple inference configurations, as described in FIG. 5, and / or timer-based management of multiple inference configurations, as described in FIG. 6.
[0049] FIGs. 4A-4B illustrate signaling diagrams of inference configuration reporting procedures 400A-400B. More specifically, FIG. 4A illustrates a signaling diagram of an inference configuration reporting procedure 400A where the UE 120 reports 404a first inference configuration information to the network entity 104. FIG. 4B illustrates a signaling diagram of an inference configuration reporting procedure 400B where the network entity 104 acquires 414 the first inference configuration information from an additional entity 103. The additional entity 103 may be a second network entity, a second UE, a core network entity, an OAM entity, a model management entity, etc.
[0050] In both procedures 400A-400B, the network entity 104 transmits 406, to the UE 102, inference configuration information to filter the applicable functionality information reported 408 by the UE 102 from the supported functionality information. In other examples, the UE 102 can send information to the network entity 104 to filter the inference configuration received 406 from the network entity 104.
[0051] Referring to the procedure 400A, the UE 102 transmits 404a, to the network entity 104, a functionality reporting message. The functionality reporting message may include functionality information used to indicate one or more supported functionalities of the UE. Supported functionalities refers to functionalities that the UE 102 supports, e.g., based on its UE capability. The UE 102 may transmit 404a the functionality information (e.g., UE capability information) to the network entity 104 via RRC signaling or LTE positioning protocol (LPP) signaling. In some implementations, the UE 102 indicates, to the network entity 104, a first subset of the supported functionalities, e.g., functionality other than positioning related functionality, via one or more RRC messages (e.g., one or more UE capability information messages) and a second subset of the functionality information, e.g., positioning-related functionality, via the LPP signaling. In some examples, the network entity 104 corresponds to a location management function (LMF) entity.
[0052] The functionality reporting message may indicate model availability information associated with the supported functionality of the UE 102. The model availability information indicates whether there is at least one AI / ML model available at the UE 102 that can be used for the supported functionality.
[0053] The first functionality reporting message may indicate first inference configuration information. The first inference configuration information indicates at least one required and / or supported inference configuration for a related functionality, such as in examples where a granularity of the inference configuration is associated with the functionality. Alternatively, the first inference configuration information may be based on other alternative granularity of a different type (e.g., model-specific, use case-specific, AI / ML-based feature-specific, AI / ML-based feature group-specific, or other granularity-specific type) . In the embodiment, the granularity of the inference configuration is regarded as functionality specific. It is understood that this is one illustration and does not place any limitation on other possible implementation on the granularity of the inference configuration.
[0054] The first inference configuration information can include at least one of: beam measurement resources configuration information (e.g., beam measurement resources configuration information of set A and / or set B) , an x beams-to-y beams prediction for spatial domain prediction configuration information, an m samples-to-n samples prediction for temporal domain prediction configuration information, positioning reference signal configuration information, other configuration information, channel state information-reference signal (CSI-RS) resources for CSI prediction configuration, or an m1 samples-to-n1 samples CSI prediction. The beam type may correspond to a synchronization signal block (SSB) (also referred to as SS / physical broadcast channel (PBCH) block) , CSI, CSI-RS, or other beam type. For example, the first inference configuration information may indicate the CSI-RS measurement resource. In some implementations, the first inference configuration information may include at least one of: measurement resource configuration information for mobility prediction, m2 samples-to-n2 samples, a layer 3 (L3) measurement results prediction configuration such as an L3-reference signal received power (L3-RSRP) prediction configuration, or a radio link failure (RLF) prediction configuration.
[0055] Based on the contents of the functionality reporting message, the network entity 104 determines 405 adjustments (if any) to the first inference configuration information, e.g., the second inference configuration information. For example, the network entity 104 may determine the second inference configuration information based on the supported functionality (or other granularity) and, based on AI / ML model availability. The second inference configuration information is decided for the supported functionality / functionalities for which there is at least one AI / ML model available at the UE 102. The inference configuration information determined 405, at the network entity 104, may include adjusted inference configuration information (e.g., third inference configuration information) to provide second inference configuration information to the UE 102.
[0056] The second inference configuration information can include same or different information from the first inference configuration information. For example, the second inference configuration information may include at least one of: beam measurement resources configuration information (e.g., beam measurement resources configuration information of set A and / or set B) , an x beams-to-y beams prediction for spatial domain prediction configuration information, an m samples-to-n samples prediction for temporal domain prediction configuration information, positioning reference signal configuration information, other configuration information, CSI-RS resources for CSI prediction configuration, or an m1 samples-to-n1 samples CSI prediction. The beam type may correspond to an SSB (also referred to as SS / PBCH block) , CSI, CSI-RS, or other beam type. For example, the second inference configuration information may indicate the CSI-RS measurement resource. In some implementations, the second inference configuration information may include at least one of: measurement resource configuration information for mobility prediction, m2 samples-to-n2 samples, an L3 measurement results prediction configuration such as an L3-RSRP prediction configuration, or an RLF prediction configuration.
[0057] In some implementations, the second inference configuration information includes completely different information from the first inference configuration information, such that the first inference configuration information is replaced with the second inference configuration information. In other implementations, the second inference configuration information includes at least a portion of the information included in the first inference configuration information. For instance, the first inference configuration information indicates a first portion of the second inference configuration information, and the adjusted inference configuration information (e.g., third inference configuration information) determined 405 by the network entity 104 indicates a remaining portion of the second inference configuration information. Alternatively, the second inference configuration information includes a subset of information from the first inference configuration information but does not include a remaining portion of the information from the first inference configuration information. In still other implementations, the second inference configuration information is the same as the first inference configuration information and can be referred to interchangeably.
[0058] The network entity 104 transmits 406, to the UE 102, the second inference configuration information. The second inference configuration information may be included in an inference configuration message. The second inference configuration information indicates an inference configuration that can be configured or supported at the network entity 104. In some implementations, the network entity 104 transmits 406 the second inference configuration information to modify or augment the first inference configuration information, e.g., provide a delta of information for the first inference configuration information. In other implementations, the network entity 104 transmits 406 the second inference configuration to replace the first inference configuration information.
[0059] Based on the second inference configuration information, the UE 102 determines 407 applicable functionality information. That is, the UE 102 may determine 407 one or more applicable functionalities from the UE-supported functionalities based on the second inference configuration information. In some implementations, if the second inference configuration information only augments or modifies a portion of the first inference configuration information, the UE 102 determines 407 the applicable functionality information based on the second inference configuration information and the unchanged portion of the first inference configuration information. In other implementations, if the second inference configuration information replaces the first inference configuration information, the UE 102 determines 407 the applicable functionality information based on the second inference configuration information.
[0060] The UE 102 transmits 408, to the network entity 104, an indication of the applicable functionality / functionalities at the UE-side (e.g., based on the second inference configuration information indicating at least one of applicable functionality at the network-side) . The UE 102 can include the second inference configuration information in an applicable functionality report to indicate, to the network entity 104, inference configuration-specific second applicable functionality information. For example, if the UE 102 receives 406 in the inference configuration message: >inference configuration information 1 and >inference configuration information 2, the UE 102 can report 408 the functionality information as: >inference configuration information 1 >> applicable functionality information 1; and >inference configuration information 2 >> applicable functionality information 2. In other implementations, the UE 102 can first determine 407 and report 408 the applicable functionality information to the network entity 104 before the UE 102 receives the second inference configuration information from the network entity 104. The network entity 104 can determine the second inference configuration information based on the applicable functionality information.
[0061] Referring to the procedure 400B, elements 405, 406, 407, and 408 have already been similarly described with respect to the procedure 400A and for brevity of description will not be redescribed with respect to the procedure 400B. The functionality reporting message transmitted 404b in the procedure 400B is similar to the functionality reporting message transmitted 404a in the procedure 400A, except that the functionality reporting message transmitted 404b in the procedure 400B does not include (e.g., omits) the first inference configuration information.
[0062] Since the functionality reporting message received 404b from the UE 102 does not include the first inference configuration information, the network entity 104 may acquire the first inference configuration information of the supported functionality / functionalities of the UE 102 from an additional entity 103, such as a second network entity or a second UE. In some examples, the additional entity 103 is in communication with the UE 102. The additional entity 103 may also be a core network entity, an OAM entity, a model management entity, etc. The network entity 104 may acquire the first inference configuration information of the supported functionality / functionalities for which there is at least one model available at the UE 102.
[0063] The network entity 104 transmits 412, to the additional entity 103, an inference configuration information request message for the first inference configuration (e.g., not included in / omitted from the functionality reporting message received 404b from the UE 102) . In some implementations, the network entity 104 may include, in the request message, second functionality information identifying / corresponding to first inference configuration information excluded from the functionality reporting message 404b. The second functionality information may be the same, different, or a subset of the information includes in functionality request messages 404a / 404b. For example, the second functionality information may indicate at least one functionality for which there is at least one AI / ML model available at the UE 102.
[0064] Based on the inference configuration request message, the network entity 104 receives 414, from the additional entity 103, an inference configuration response message including the first inference configuration information. The response message may include the second functionality information and / or related first inference configuration information. The network entity 104 may use the information included in the response message to perform elements 405, 406, 407, and 408, as similarly described with respect to the procedure 400A.
[0065] Accordingly, FIGs. 4A-4B describe how the UE 102 can send 404 filtering information (e.g., model availability information, first inference configuration, supported functionality information, CSI processing unit information, etc. ) to the network entity 104 to reduce the signaling overhead for the second inference configuration information from the network entity 104. The network entity 104 can also send other filtering information (e.g., the second inference configuration information) to the UE 102 to reduce the signaling overhead of the functionality information (e.g., applicable functionality information) from UE 102.
[0066] FIG. 5 illustrates a signaling diagram 500 for signaling-based activation of inference configuration management. In an example, the network entity 104 configures 506 a plurality of second inference configuration information (e.g., based on granularity) to the UE 102. The description of granularity of inference configuration may be similar to the aspects disclosed herein.
[0067] The network entity 104 may perform the management of the inference configuration information via signaling. For example, the signaling includes an RRC message, LTE Positioning Protocol (LPP) , L1 (e.g., DCI) / L2 (e.g., MAC CE) related signaling, or the like.
[0068] In some aspects, the network entity 104 configures a plurality of second inference configuration information via signaling. The network entity 104 indicates the first signaling indication information to indicate the inference configuration which can be the current one or the one to be applied between UE 102 and the network entity 104 for the first time. Additionally, the network entity 104 can update the inference configuration, where the inference configuration to be applied and / or indicate the switching from the first inference configuration to the second one to be applied. The first or second signaling indication information can be sent via RRC, LPP, L1 or L2 signaling.
[0069] The network entity 104 transmits 506, to the UE 102, a first configuration message including a plurality of second inference configuration information or a first activation inference configuration. The first inference configuration message can be constructed via RRC, or LPP signaling. The determination of the first configuration message may be similar as discussed in diagram 400A of FIG. 4A or diagram 400B of FIG. 4B. In some aspects, the first configuration message indicates identification (ID) information of corresponding second inference configuration information from the plurality of second inference configuration information. The identification information may be an index, an ID, or other information. The first configuration message may include the identification information for each of the plurality of second inference configuration. In some aspects, the first configuration message indicates the identification information for each of the plurality of second inference configuration based on an ordering of each the plurality of second inference configuration in a list. The UE 102 derives the identification information of each second inference configuration based on the order of entry in the list.
[0070] In some aspects, the first configuration message includes a first activation inference configuration which indicates information of the first activation inference configuration. The first activation inference configuration corresponds to a current inference configuration at the network entity 104 side or the inference configuration to be applied between UE 102 and network entity 104. In some aspects, the first activation inference configuration may comprise one bit within the first configuration message that correlates to the first activation inference configuration. In some aspects, the first configuration message indicates the identification information of the first activation inference configuration.
[0071] In some aspects, the UE determines a default activation inference configuration as the first activation inference configuration. The default activation inference configuration may be pre-defined in the specification, such as in instances where the first configuration message includes the plurality of second inference configuration information. In such instances, for each of the plurality of the second inference configurations in the first configuration message, a first of the second inference configurations is configured such that the first one in the list is activated first by default. For example, if the network entity configures more than one second inference configuration information for functionality, according to the default information or predefinition in specification, the first inference configuration in the list will be considered as the first one to be activated.
[0072] In some aspects, the first activation inference configuration is the activation information of the functionality to be activated. For example, one functionality may be activated with one inference configuration. When the UE 102 receives the activation information of the functionality to be activated, the UE 102 is aware of the functionality to be activated based on the activation inference configuration information.
[0073] In some aspects, if the first configuration message to send the first indication information is the same one to send more than one inference configuration information, the message may comprise RRC signaling, or LPP signaling. In some aspects, the first configuration message may comprise RRC, LPP, L1 or L2 signaling.
[0074] The network entity 104 transmits 510, to the UE 102, a L1 or L2 signaling including a second activation inference configuration or deactivation of an inference corresponding to the first activation inference configuration. In some aspects, the L1 or L2 signaling indicates the second activation inference configuration information to be applied between UE 102 and the network entity 104. The description of the second indication information may refer to the description for the first activation inference configuration. The UE 102 determines the second activation inference configuration based on the L1 or L2 signaling. The UE 102 considers the second activation inference configuration to be a new inference configuration at the network entity 104 side or the new inference configuration to be applied between UE 102 and the network entity 104. The UE 102 will apply the second activation inference configuration and stop the inference associated with the first activation inference configuration. In some aspects, the L1 or L2 signaling may include a stop indication, which is used to indicate the UE 102 to stop the inference based on the first activation inference configuration. In such instances, the UE 102 may revert or switch to a non-AI operation state.
[0075] In some aspects, the network entity 104 may send the activation / deactivation of the inference configuration (s) via DCI based on a radio network temporary identifier (RNTI) pre-defined or configured by the network entity 104 or based on cell RNTI (C-RNTI) . The network entity 104 may send the DCI in a unicast or a group-cast manner. For a groupcast based DCI, the network entity 104 may configure the location of the DCI field (s) for each UE 104. The UE 102 determines the activation / deactivation status for the inference configuration (s) based on the corresponding DCI field (s) . The network entity 104 sends the DCI to indicate the activation / deactivation of inference configuration for the same serving cell as the DCI or another serving cell, where the serving cell index may be indicated by the DCI or configured by the network entity 104 (e.g., via RRC signaling) . In some aspects, the network entity 104 may send the activation / deactivation of the inference configuration (s) via MAC CE. The network entity 104 may send the MAC CE to indicate the activation / deactivation of inference configuration for the same serving cell as the MAC CE or another serving cell, where the serving cell index may be indicated by the MAC CE or configured by the network entity 104 (e.g., via RRC signaling) .
[0076] In some aspects, the UE 102 may apply the updated activation / deactivation of the inference configuration (s) X symbols / slots after receiving the last symbol / slot of the PDCCH carrying the DCI or the PDSCH carrying the MAC CE, where X > 0 and may be pre-defined or reported by the UE 102 (e.g., via UE capability) , or configured by the network entity 104 (e.g., via RRC signaling, MAC CE or DCI) . In some aspects, the UE 102 may apply the updated activation / deactivation of the inference configuration (s) Y symbols / slots after transmitting the last symbol / slot of the PUCCH or PUSCH carrying the acknowledgement (ACK) of the PDCCH carrying the DCI or the PDSCH carrying the MAC CE, where Y > 0 and may be pre-defined or reported by the UE 102 (e.g., via UE capability) , or configured by the network entity 104 (e.g., via RRC signaling, MAC CE or DCI) . In some aspects, the network entity 104 and UE 102 may determine value of X and / or Y based on the subcarrier spacing of the downlink bandwidth part or uplink bandwidth part of the serving cell for the DCI or MAC CE or the target serving cell for the activated / deactivated inference configuration.
[0077] At least one advantage of the disclosure is that the network entity 104 provides more than one inference configuration supported by the network entity 104 and can dynamically inform UE 102 of the one to be applied between UE 102 and network entity 104, which will reduce the signaling overhead of inference configuration management. In addition, the L1 or L2 signaling reduces the latency to manage the inference configuration between UE 102 and network entity 104.
[0078] FIG. 6 illustrates a flow diagram 600 of an example timer-based management of multiple inference configurations. In an example, the network entity 104 configures a plurality of second inference configuration information based on the granularity. The network entity 104 configures a timer-based inference configuration for the UE 102 to manage the inference configuration to be applied between UE 102 and network entity 104. The timer information may be configured via RRC, or LPP signaling. The description of the granularity of the inference configuration may be similar to the aspects discussed herein.
[0079] The UE 102 receives 606, from the network entity 104, a configuration message including timer information. The timer information may be associated with the first activation inference configuration. The configuration message may include a plurality of second inference configuration information and / or first indication information of the first configuration message as discussed in FIG. 5. The configuration message includes the timer information that indicates the maximum activation time of the first activation inference configuration. The timer information may be a time value (e.g., in terms of milliseconds, seconds, minutes, hours, etc. ) . The determination of the first activation inference configuration is configured similarly as discussed in FIG. 5. In some aspects, the timer information is configured for the first activation inference configuration, or is common for all activation inference configurations. In some aspects, the configuration message may be used for the determination of a second activation inference configuration from the plurality of second activation inference configuration. In some aspects, the configuration message includes the plurality of second indication information. The description of the plurality of second indication information is configured similarly as discussed in FIG. 5. The first and second activation inference configurations can be for the same functionality or different functionalities. For example, if both are for the same functionality, the activation inference configuration changes, but the activated functionality is not changed. In some aspects, the configuration message includes a second activation functionality information that indicates the functionality to be activated after an expiration of a timer.
[0080] The UE 102 starts 616 a timer for a first activation inference configuration. A maximum value of the time may be indicated or based on the timer information of the configuration message. In some aspects, the UE 102 starts the related timer when UE 102 starts the inference based on the first activation inference configuration. In some aspects, the UE 102 starts the related timer when the UE 102 determines the activated first functionality. For example, the UE 102 starts the related timer when the UE 102 receives the activation information of the first functionality. In some aspects, the UE 102 starts the related timer when the UE 102 receives the timer information.
[0081] The UE 102 determines 626 whether the timer has expired or has stopped. In some aspects, the UE 102 may stop the timer based on an occurrence of an event. For example, the UE 102 may stop the timer if at least one of the following occurs: the UE 102 deactivates the first activated functionality automatically, the UE 102 resets a MAC entity of a current serving cell, the UE 102 detects failure between the UE 102 and the current serving cell (e.g., beam recovery failure, radio link failure, integrity check failure, RRC connection reconfiguration failure, etc. ) , the UE 102 determines the timer (e.g., timeAlignmentTimer) for a timing advance group (e.g., primary timing advance group (PTAG) ) expires, or the UE 102 detects the failure of a corresponding functionality. In some aspects, when the timer expires or the UE stops the timer, without any configuration from the network, (e.g., the Yes branch) , the UE 102 executes 610a.
[0082] The UE 102 deactivates 610a inference corresponding to the first activation inference configuration. In some aspects, the timer expires or the UE 102 stops the timer autonomously without any configuration from the network entity 104. The UE 102 stops the inference for the first activated functionality based on the first activation inference configuration. In some aspects, the UE 102 determines the second activation inference configuration. In some aspects, the UE 102 considers the second activation inference configuration as being applied between UE 102 and the network entity 104. In some aspects, the UE 102 starts the inference for the first activated functionality based on the second activation inference configuration. The UE 102 determines the second activation inference configuration based on the second activation inference configuration included in the configuration message or based on the default configuration. In some aspects, if the timer information is common for all the activation inference configuration, the UE 102 starts the timer for the second activation inference configuration.
[0083] In some aspects, the UE 102 determines the second functionality to be activated after expiration of the timer. In some aspects, when the timer expires, the UE 102 starts the inference for the second activated functionality based on the second activation inference configuration. The UE 102 determines the second functionality information as being activated based on the second activation functionality information included in the configuration message or based on the default or predefined functionality information as discussed previously herein. In some aspects, if the timer information is common for all the activation inference configuration, the UE 102 starts the timer for the second activation inference configuration.
[0084] In instances where the UE 102 determines 626 that the timer is running, or the timer has not expired or has not stopped (e.g., the No branch) , the UE 102 executes 611a.
[0085] The UE 102 receives 611a management information. The UE 102 receives 611a the management information in response to determining 626 that the timer is running, or the timer has not expired or has not stopped. In some aspects, the management information includes the L1 or L2 signaling as described in FIG. 5. In some aspects, the management information includes at least one of a deactivation of the first activated functionality, a connection release with the current serving cell, a configuration for the UE to enter to switch to an idle or an inactive state, a handover command, or the like.
[0086] The UE 102 acts 611b based on the management information. The UE 102 may act based on the management information upon receipt of the management information. For example, the UE 102 may stop the timer. In some aspects, the management information includes the second activation inference configuration information. In some aspects, the UE 102 stops the timer and considers the second activation inference configuration as being applied between UE 102 and network entity 104. In some aspects, the UE 102 stops the timer and starts the inference for the first activated functionality based on the second activation inference configuration. In some aspects, the management information includes the deactivation of the first activation inference configuration, or the release of the current serving cell, or the UE state configuration to configure UE 102 to the idle or the inactive state. In such instances, the UE 102 stops the timer. The UE 102 deactivates the first activation inference configuration, or release the current serving cell, or enters idle or inactive state based on management information.
[0087] At least one advantage of the disclosure is that the timer-based solution for inference configuration management allows for switching of the inference configuration to be applied between UE 102 and network entity 104 which improves the efficiency of the inference configuration management. FIGs. 2-6 illustrate examples of management of inference configurations for AI in wireless networks. FIGs. 7-8 show methods for implementing one or more aspects of FIGs. 2-6. In particular, FIG. 7 shows an implementation by the UE 102 of the one or more aspects of FIGs. 2-6. FIG. 8 shows an implementation by the network entity 104 of the one or more aspects of FIGs. 2-6.
[0088] FIG. 7 illustrates a flowchart 700 of a method of wireless communication at a UE. With reference to FIGs. 1-6, the method may be performed by the UE 102. In embodiments, the UE 102 transmits 704, to a network entity 104, at least one of: supported functionality information, model availability information, or first inference configuration information. For example, FIG. 4A shows that the UE transmits 404a / 404b at least one of: supported functionality information, model availability information, or first inference configuration information.
[0089] The UE 102 receives 706a, from the network entity 104, second inference configuration information based on the first inference configuration information. For example, FIG. 4A shows that the UE receives 406 the second inference configuration information based on the first inference configuration information.
[0090] The UE 102 optionally determines 707, applicable functionality information based on second inference configuration information. For example, FIG. 4A shows that the UE optionally determines 407 applicable functionality information based on second inference configuration information.
[0091] The UE 102 transmits 708, to the network entity 104, applicable functionality information based on the second inference configuration information. For example, FIG. 4A shows that the UE transmits 408 applicable functionality information based on the second inference configuration information.
[0092] The UE 102 optionally receives 706b, from the network entity 104, a configuration message. For example, FIGs. 5 and 6 shows that the UE optionally receives 506, 606 a configuration message. The configuration message indicates at least one of the second inference configuration information, a plurality of second inference configuration information, a first activation of one or more inference configurations, or timer information associated with an activation time of one or more inference configurations.
[0093] The UE 102 optionally receives 710b, from the network entity 104, control signaling. For example, FIG. 5 shows that the UE optionally receives 510 control signaling. The control signaling indicates at least one of a second activation of the one or more other inference configurations or a deactivation of one or more activated inference configurations. In some aspects, the UE activates one or more other inference configurations associated with the second activation, and resets the timer for the second activation based on the timer information.
[0094] The UE 102 optionally initiates 716 a timer for an activation time associated with the first activation based on the timer information. For example, FIG. 6 shows that the UE optionally initiates 616 a timer for an activation time associated with the first activation based on the timer information.
[0095] The UE 102 optionally determines 726 whether the timer has expired or stopped. For example, FIG. 6 shows that the UE may optionally determine 626 whether the timer has expired or stopped.
[0096] The UE 102 optionally deactivates 710a the one or more inference configurations associated with the first activation upon expiration of the timer. For example, FIG. 6 shows that the UE optionally deactivate 610a the one or more inference configurations associated with the first activation upon expiration of the timer.
[0097] The UE 102 optionally processes 711 inference configuration management information when the timer has not expired. For example, FIG. 6 shows that the UE optionally processes 611a / 611b inference configuration management information when the timer has not expired.
[0098] FIG. 7 describes a method from a UE-side of a wireless communication link, whereas FIG. 8 describes a method from a network-side of the wireless communication link.
[0099] FIG. 8 is a flowchart 800 of a method of wireless communication at a network entity. With reference to FIGs. 1-6, the method may be performed by one or more network entities 104, which may correspond to a base station or a unit of the base station, such as the RU 106, the DU 108, and / or the CU 110. In embodiments, the network entity 104 obtains 804 first inference configuration information. For example, FIGs. 4A and 4B show that the network entity obtains 404a, 414 first inference configuration information.
[0100] In one embodiment, the network entity 104 optionally transmits 812, to another entity 103, a request for the first inference configuration information. For example, FIG. 4B shows that the network entity may transmit 412, to another entity, a request for the first inference configuration information.
[0101] The network entity 104 optionally receives 814, from the another entity 103, a response message indicating the first inference configuration information. For example, FIG. 4B shows that the network entity may receive 414, from the another entity, the response message indicating the first inference configuration information.
[0102] In another embodiment, the network entity 102 may receive 804a the first inference configuration information for the UE. For example, FIG. 4A shows that the network entity may receive 404a a functionality reporting message including supported functionality information, model availability, and the first inference configuration information.
[0103] The network entity 104 optionally determines 805 third inference configuration information based on supported functionality information, the model availability information, and the first inference configuration information. For example, FIGs. 4A / 4B show that the network entity optionally determines 405 adjustments to the first inference configuration information to determine the third inference configuration information. The UE may determine the third inference configuration information based on supported functionality information, the model availability information, and the first inference configuration information.
[0104] The network entity 104 transmits 806a, to the UE, second inference configuration information based on the first inference configuration information. For example, FIGs. 4A / 4B show that the network entity transmits 406, to the UE, the second inference configuration information based on the first inference configuration information.
[0105] The network entity 104 receives 808, from the UE, applicable functionality information based on the second inference configuration. For example, FIGs. 4A / 4B show that the network entity receives 408 applicable functionality information. The applicable functionality information being based on the second inference configuration.
[0106] The network entity 104 optionally transmits 806b, to the UE, a configuration message. For example, FIG. 5 that the network entity optionally transmits 506 a configuration message. The configuration message indicates at least one of the second inference configuration information, a plurality of second inference configuration information, a first activation of one or more inference configurations, or timer information associated with an activation time of one or more inference configurations.
[0107] The network entity 104 optionally transmits 810, to the UE, control signaling. For example, FIG. 5 shows that the network entity optionally transmits 510 control signaling. The control signaling indicates at least one of a second activation of the one or more other inference configurations or a deactivation of one or more activated inference configurations. A UE apparatus 902, as described in FIG. 9, may perform the method of flowchart 700. The one or more network entities 104, as described in FIG. 10, may perform the method of flowchart 800.
[0108] FIG. 9 is a diagram 900 illustrating an example of a hardware implementation for a UE apparatus 902. The UE apparatus 902 may be the UE 102, a component of the UE 102, or may implement UE functionality. The UE apparatus 902 may include an application processor 906, which may have on-chip memory 906’. In examples, the application processor 906 may be coupled to a secure digital (SD) card 908 and / or a display 910. The application processor 906 may also be coupled to a sensor (s) module 912, a power supply 914, an additional module of memory 916, a camera 918, and / or other related components.
[0109] The UE apparatus 902 may further include a wireless baseband processor 926, which may be referred to as a modem. The wireless baseband processor 926 may have on-chip memory 926'. Along with, and similar to, the application processor 906, the wireless baseband processor 926 may also be coupled to the sensor (s) module 912, the power supply 914, the additional module of memory 916, the camera 918, and / or other related components. The wireless baseband processor 926 may be additionally coupled to one or more subscriber identity module (SIM) card (s) 920 and / or one or more transceivers 930 (e.g., wireless RF transceivers) .
[0110] Within the one or more transceivers 930, the UE apparatus 902 may include a Bluetooth module 932, a WLAN module 934, an SPS module 936 (e.g., GNSS module) , and / or a cellular module 938. The Bluetooth module 932, the WLAN module 934, the SPS module 936, and the cellular module 938 may each include an on-chip transceiver (TRX) , or in some cases, just a transmitter (TX) or just a receiver (RX) . The Bluetooth module 932, the WLAN module 934, the SPS module 936, and the cellular module 938 may each include dedicated antennas and / or utilize antennas 940 for communication with one or more other nodes. For example, the UE apparatus 902 can communicate through the transceiver (s) 930 via the antennas 940 with another UE (e.g., sidelink communication) and / or with a network entity 104 (e.g., uplink / downlink communication) , where the network entity 104 may correspond to a base station or a unit of the base station, such as the RU 106, the DU 108, or the CU 110.
[0111] The wireless baseband processor 926 and the application processor 906 may each include a computer-readable medium / memory 926', 906', respectively. The additional module of memory 916 may also be considered a computer-readable medium / memory. Each computer-readable medium / memory 926', 906', 916 may be non-transitory. The wireless baseband processor 926 and the application processor 906 may each be responsible for general processing, including execution of software stored on the computer-readable medium / memory 926', 906', 916. The software, when executed by the wireless baseband processor 926 / application processor 906, causes the wireless baseband processor 926 / application processor 906 to perform the various functions described herein. The computer-readable medium / memory may also be used for storing data that is manipulated by the wireless baseband processor 926 / application processor 906 when executing the software. The wireless baseband processor 926 / application processor 906 may be a component of the UE 102. The UE apparatus 902 may be a processor chip (e.g., modem and / or application) and include just the wireless baseband processor 926 and / or the application processor 906. In other examples, the UE apparatus 902 may be the entire UE 102 and include the additional modules of the apparatus 902.
[0112] As discussed in FIG. 1 and implemented with respect to FIG. 7, the applicable functionality component 140 is configured to transmit, to a network entity, at least one of: supported functionality information, model availability information, or first inference configuration information; receive, from the network entity, second inference configuration information based on the first inference configuration information; and transmit, to the network entity, applicable functionality information based on the second inference configuration information. The applicable functionality component 140 may be within the application processor 906 (e.g., at 140a) , the wireless baseband processor 926 (e.g., at 140b) , or both the application processor 906 and the wireless baseband processor 926. The applicable functionality component 140a-140b may be one or more hardware components specifically configured to carry out the stated processes / algorithm, implemented by one or more processors configured to perform the stated processes / algorithm, stored within a computer-readable medium for implementation by the one or more processors, or a combination thereof.
[0113] FIG. 10 is a diagram 1000 illustrating an example of a hardware implementation for one or more network entities 104. The one or more network entities 104 may be a base station, a component of a base station, or may implement base station functionality. The one or more network entities 104 may include, or may correspond to, at least one of the RU 106, the DU, 108, or the CU 110. The CU 110 may include a CU processor 1046, which may have on-chip memory 1046'. In some aspects, the CU 110 may further include an additional module of memory 1056 and / or a communications interface 1048, both of which may be coupled to the CU processor 1046. The CU 110 can communicate with the DU 108 through a midhaul link 162, such as an F1 interface between the communications interface 1048 of the CU 110 and a communications interface 1028 of the DU 108.
[0114] The DU 108 may include a DU processor 1026, which may have on-chip memory 1026'. In some aspects, the DU 108 may further include an additional module of memory 1036 and / or the communications interface 1028, both of which may be coupled to the DU processor 1026. The DU 108 can communicate with the RU 106 through a fronthaul link 160 between the communications interface 1028 of the DU 108 and a communications interface 1008 of the RU 106.
[0115] The RU 106 may include an RU processor 1006, which may have on-chip memory 1006'. In some aspects, the RU 106 may further include an additional module of memory 1016, the communications interface 1008, and one or more transceivers 1030, all of which may be coupled to the RU processor 1006. The RU 106 may further include antennas 1040, which may be coupled to the one or more transceivers 1030, such that the RU 106 can communicate through the one or more transceivers 1030 via the antennas 1040 with the UE 102.
[0116] The on-chip memory 1006', 1026', 1046' and the additional modules of memory 1016, 1036, 1056 may each be considered a computer-readable medium / memory. Each computer-readable medium / memory may be non-transitory. Each of the processors 1006, 1026, 1046 is responsible for general processing, including execution of software stored on the computer-readable medium / memory. The software, when executed by the corresponding processor (s) 1006, 1026, 1046 causes the processor (s) 1006, 1026, 1046 to perform the various functions described herein. The computer-readable medium / memory may also be used for storing data that is manipulated by the processor (s) 1006, 1026, 1046 when executing the software. In examples, the inference configuration component 150 may sit at any of the one or more network entities 104, such as at the CU 110; both the CU 110 and the DU 108; each of the CU 110, the DU 108, and the RU 106; the DU 108; both the DU 108 and the RU 106; or the RU 106.
[0117] As discussed in FIG. 1 and implemented with respect to FIG. 8, the inference configuration component 150 is configured to obtain first inference configuration information; transmit, to a UE, second inference configuration information based on the first inference configuration information; and receiving, from the UE, applicable functionality information based on the second inference configuration. The inference configuration component 150 may be within one or more processors of the one or more network entities 104, such as the RU processor 1006 (e.g., at 150a) , the DU processor 1026 (e.g., at 150b) , and / or the CU processor 1046 (e.g., at 150c) . The inference configuration component 150a-150c may be one or more hardware components specifically configured to carry out the stated processes / algorithm, implemented by one or more processors 1006, 1026, 1046 configured to perform the stated processes / algorithm, stored within a computer-readable medium for implementation by the one or more processors 1006, 1026, 1046, or a combination thereof.
[0118] The specific order or hierarchy of blocks in the processes and flowcharts disclosed herein is an illustration of example approaches. Hence, the specific order or hierarchy of blocks in the processes and flowcharts may be rearranged. Some blocks may also be combined or deleted. Dashed lines may indicate optional elements of the diagrams. The accompanying method claims present elements of the various blocks in an example order, and are not limited to the specific order or hierarchy presented in the claims, processes, and flowcharts.
[0119] The detailed description set forth herein describes various configurations in connection with the drawings and does not represent the only configurations in which the concepts described herein may be practiced. The detailed description includes specific details for the purpose of providing a thorough explanation of various concepts. However, these concepts may be practiced without these specific details. In some instances, well known structures and components are shown in block diagram form in order to avoid obscuring such concepts.
[0120] Aspects of wireless communication systems, such as telecommunication systems, are presented with reference to various apparatuses and methods. These apparatuses and methods are described in the following detailed description and are illustrated in the accompanying drawings by various blocks, components, circuits, processes, call flows, systems, algorithms, etc. (collectively referred to as “elements” ) . These elements may be implemented using electronic hardware, computer software, or combinations thereof. Whether such elements are implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system.
[0121] An element, or any portion of an element, or any combination of elements may be implemented as a “processing system” that includes one or more processors. Examples of processors include microprocessors, microcontrollers, graphics processing units (GPUs) , central processing units (CPUs) , application processors, digital signal processors (DSPs) , reduced instruction set computing (RISC) processors, systems-on-chip (SoC) , baseband processors, field programmable gate arrays (FPGAs) , programmable logic devices (PLDs) , state machines, gated logic, discrete hardware circuits, and other similar hardware configured to perform the various functionality described throughout this disclosure. One or more processors in the processing system may execute software, which may be referred to as software, firmware, middleware, microcode, hardware description language, or otherwise. Software shall be construed broadly to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software components, applications, software applications, software packages, routines, subroutines, objects, executables, threads of execution, procedures, functions, or any combination thereof.
[0122] If the functionality described herein is implemented in software, the functions may be stored on, or encoded as, one or more instructions or code on a computer-readable medium, such as a non-transitory computer-readable storage medium. Computer-readable media includes computer storage media and can include a random-access memory (RAM) , a read-only memory (ROM) , an electrically erasable programmable ROM (EEPROM) , optical disk storage, magnetic disk storage, other magnetic storage devices, combinations of these types of computer-readable media, or any other medium that can be used to store computer executable code in the form of instructions or data structures that can be accessed by a computer. Storage media may be any available media that can be accessed by a computer.
[0123] Aspects, implementations, and / or use cases described herein may be implemented across many differing platform types, devices, systems, shapes, sizes, and packaging arrangements. For example, the aspects, implementations, and / or use cases may come about via integrated chip implementations and other non-module-component based devices, such as end-user devices, vehicles, communication devices, computing devices, industrial equipment, retail / purchasing devices, medical devices, artificial intelligence (AI) -enabled devices, machine learning (ML) -enabled devices, etc. The aspects, implementations, and / or use cases may range from chip-level or modular components to non-modular or non-chip-level implementations, and further to aggregate, distributed, or original equipment manufacturer (OEM) devices or systems incorporating one or more techniques described herein.
[0124] Devices incorporating the aspects and features described herein may also include additional components and features for the implementation and practice of the claimed and described aspects and features. For example, transmission and reception of wireless signals necessarily includes a number of components for analog and digital purposes, such as hardware components, antennas, RF-chains, power amplifiers, modulators, buffers, processor (s) , interleavers, adders / summers, etc. Techniques described herein may be practiced in a wide variety of devices, chip-level components, systems, distributed arrangements, aggregated or disaggregated components, end-user devices, etc., of varying configurations.
[0125] The description herein is provided to enable a person skilled in the art to practice the various aspects described herein. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects. Thus, the claims are not limited to the aspects described herein, but are to be interpreted in view of the full scope of the present disclosure consistent with the language of the claims.
[0126] Reference to an element in the singular does not mean “one and only one” unless specifically stated, but rather “one or more. ” Terms such as “if, ” “when, ” and “while” do not imply an immediate temporal relationship or reaction. That is, these phrases, e.g., “when, ” do not imply an immediate action in response to or during the occurrence of an action, but simply imply that if a condition is met then an action will occur, but without requiring a specific or immediate time constraint for the action to occur. The terms “may” , “might” , and “can” , as used in this disclosure, often carry certain connotations. For example, “may” refers to a permissible feature that may or may not occur, “might” refers to a feature that probably occurs, and “can” refers to a capability (e.g., capable of) . The phrase “For example” often carries a similar connotation to “may” and, therefore, “may” is sometimes excluded from sentences that include “for example” or other similar phrases.
[0127] Unless specifically stated otherwise, the term “some” refers to one or more. Combinations such as “at least one of A, B, or C” or “one or more of A, B, or C”include any combination of A, B, and / or C, such as A and B, A and C, B and C, or A and B and C, and may include multiples of A, multiples of B, and / or multiples of C, or may include A only, B only, or C only. Sets should be interpreted as a set of elements where the elements number one or more. Terms or articles such as “a” , “an” , and / or “the” may refer to one of an item, feature, element, etc., that the term or article precedes, or may refer to more than one of said item, feature, element, etc. that the term or article precedes. For example, the recitation “awidget” does not preclude reference to multiples of said widget, as “multiple widgets” necessarily includes “awidget” . Hence, the recitation “awidget” may be interpreted as “at least one widget” or, similarly, interpreted as “one or more widgets” .
[0128] Unless otherwise specifically indicated, ordinal terms such as “first” and “second” do not necessarily imply an order in time, sequence, numerical value, etc., but are used to distinguish between different instances of a term or phrase that follows each ordinal term.
[0129] Reference numbers, as used in the specification and figures, are sometimes cross-referenced among drawings to denote same or similar features. A feature that is exactly the same in multiple drawings may be labeled with the same reference number in the multiple drawings. A feature that is similar among the multiple drawings, but not exactly the same, may be labeled with reference numbers that have different leading numbers but have one or more of the same trailing numbers (e.g., 206, 306, 406, etc., may refer to similar features in the drawings) . Hence, like numbers may refer to like actions.
[0130] Structural and functional equivalents to elements of the various aspects described throughout this disclosure that are known or later come to be known to those of ordinary skill in the art are expressly incorporated herein by reference and are encompassed by the claims. The words “module, ” “mechanism, ” “element, ” “device, ” and the like may not be a substitute for the word “means. ” As such, no claim element is to be construed as a means plus function unless the element is expressly recited using the phrase “means for. ” As used herein, the phrase “based on” shall not be construed as a reference to a closed set of information, one or more conditions, one or more factors, or the like. In other words, the phrase “based on A” , where “A” may be information, a condition, a factor, or the like, shall be construed as “based at least on A” unless specifically recited differently.
[0131] The following examples are illustrative only and may be combined with other examples or teachings described herein, without limitation.
[0132] Example 1 is a method of wireless communication at a UE, including: transmitting, to a network entity, at least one of: supported functionality information, model availability information, or first inference configuration information; receiving, from the network entity, second inference configuration information based on the first inference configuration information; and transmitting, to the network entity, applicable functionality information based on the second inference configuration information.
[0133] Example 2 may be combined with Example 1 and includes that the first inference configuration information indicates a supported inference configuration associated with the supported functionality information or the model availability information.
[0134] Example 3 may be combined with any of Examples 1-2 and includes that the transmitting includes: transmitting the first inference configuration information.
[0135] Example 4 may be combined with any of Examples 1-2 and includes that the transmitting includes: transmitting the supported functionality information and the model availability information; and omitting the first inference configuration information.
[0136] Example 5 may be combined with any of Examples 1-4 and includes that at least one of the first inference configuration information or the second inference configuration information corresponds to at least one of: beam measurement resources configuration information, beam prediction for spatial domain configuration information, sample prediction for time domain configuration information, positioning reference signal configuration information, CSI-RS resources, CSI samples prediction, measurement resources configuration information for mobility prediction, L3 measurement result prediction, or RLF prediction.
[0137] Example 6 may be combined with any of Examples 1-5 and includes that the transmitting the applicable functionality information further includes: transmitting one or more inference configurations associated with the applicable functionality information.
[0138] Example 7 may be combined with any of Examples 1-6 and further includes receiving, from the network entity, a configuration message indicating at least one of: the second inference configuration information, a plurality of second inference configuration information, a first activation of one or more inference configurations, or timer information associated with an activation time of one or more inference configurations.
[0139] Example 8 may be combined with Example 7 and further includes receiving, from the network entity, control signaling indicating that at least one of: a second activation of the one or more other inference configurations, or a deactivation of one or more activated inference configurations.
[0140] Example 9 may be combined with any of Examples 7-8 and further includes initiating a timer for an activation time associated with the first activation based on the timer information.
[0141] Example 10 may be combined with Example 9 and further includes deactivating the one or more inference configurations associated with the first activation upon expiration of the timer.
[0142] Example 11 may be combined with Example 10 and further includes activating one or more other inference configurations associated with the second activation; and resetting the timer for the second activation based on the timer information.
[0143] Example 12 may be combined with Example 9 and further includes processing inference configuration management information when the timer has not expired.
[0144] Example 13 is a method of wireless communication at a network entity including: obtaining first inference configuration information; transmitting, to a UE, second inference configuration information based on the first inference configuration information; and receiving, from the UE, applicable functionality information based on the second inference configuration.
[0145] Example 14 may be combined with Example 13 and further includes determining third inference configuration information based on supported functionality information, the model availability information, and the first inference configuration information, and includes that the second inference configuration information is based on the third inference configuration information.
[0146] Example 15 may be combined with Example 14 and includes that the second inference configuration is the same as the third inference configuration information.
[0147] Example 16 may be combined with any of Examples 13-15 and includes that the obtaining the first inference configuration information includes: receiving, from the UE, supported functionality information, model availability information, and the first inference configuration information.
[0148] Example 17 may be combined with any of Examples 13-16 and includes that the obtaining the first inference configuration information includes: transmitting, to another entity, a request for the first inference configuration information; and receiving, from the another entity, a response message indicating the first inference configuration information.
[0149] Example 18 may be combined with any of Examples 13-17 and includes that at least one of the first inference configuration information or the second inference configuration information corresponds to at least one of: beam measurement resources configuration information, beam prediction for spatial domain configuration information, sample prediction for time domain configuration information, positioning reference signal configuration information, CSI-RS resources, CSI samples prediction, measurement resources configuration information for mobility prediction, L3 measurement result prediction, or RLF prediction.
[0150] Example 19 may be combined with any of Examples 13-18 and further includes transmitting, to the UE, a configuration message indicating at least one of: the second inference configuration information, a plurality of second inference configuration information, a first activation of one or more inference configurations, or timer information associated with an activation time of one or more inference configurations.
[0151] Example 20 may be combined with any of Examples 13-19 and further includes transmitting, to the UE, control signaling indicating that at least one of: a second activation of the one or more other inference configurations, or a deactivation of one or more activated inference configurations.
[0152] Example 21 is an apparatus for wireless communication for implementing a method as in any of Examples 1-20.
[0153] Example 22 is an apparatus for wireless communication including means for implementing a method as in any of Examples 1-20.
[0154] Example 23 is a non-transitory computer-readable medium storing computer executable code, the code when executed by a processor causes the processor to implement a method as in any of Examples 1-20.
Claims
A method of wireless communication at a user equipment, UE, (102) comprising:transmitting (404) , to a network entity (104) , at least one of: supported functionality information, model availability information, or first inference configuration information;receiving (406) , from the network entity (104) , second inference configuration information based on the first inference configuration information; andtransmitting (408) , to the network entity (104) , applicable functionality information based on the second inference configuration information.The method of claim 1, wherein the first inference configuration information indicates at least one supported inference configuration associated with the supported functionality information or the model availability information.The method of any of claims 1-2, wherein the transmitting (404) comprises:transmitting (404a) the first inference configuration information.The method of any of claims 1-2, wherein the transmitting (404) comprises:transmitting (404b) the supported functionality information and the model availability information; andomitting the first inference configuration information.The method of any of claims 1-4, wherein the transmitting (408) the applicable functionality information further comprises:transmitting one or more inference configurations associated with the applicable functionality information.The method of any of claims 1-5, further comprising:receiving (506, 606) , from the network entity (104) , a configuration message indicating at least one of:the second inference configuration information,a plurality of second inference configuration information,a first activation of one or more inference configurations, ortimer information associated with an activation time of one or more inference configurations.The method of claim 6, further comprising:receiving (510) , from the network entity (104) , control signaling indicating that at least one of:a second activation of the one or more other inference configurations, ora deactivation of one or more activated inference configurations.The method of any of claims 6-7, further comprising:initiating (616) a timer for an activation time associated with the first activation based on the timer information.The method of claim 8, further comprising:deactivating (610a) the one or more inference configurations associated with the first activation upon expiration of the timer.The method of claim 9, further comprising:activating one or more other inference configurations associated with the second activation; andresetting the timer for the second activation based on the timer information.The method of claim 8, further comprising:processing (611) inference configuration management information when the timer has not expired.A method of wireless communication at a network entity (104) comprising:obtaining first inference configuration information;transmitting (406) , to a user equipment, UE, (102) , second inference configuration information based on the first inference configuration information; andreceiving (408) , from the UE (102) , applicable functionality information based on the second inference configuration.The method of claim 12, further comprising:determining (405) third inference configuration information based on supported functionality information, the model availability information, and the first inference configuration information, wherein the second inference configuration information is based on the third inference configuration information.The method of claim 13, wherein the second inference configuration is the same as the third inference configuration information.The method of any of claims 12-14, wherein the obtaining the first inference configuration information comprises:receiving (404a) , from the UE (102) , supported functionality information, model availability information, and the first inference configuration information.The method of any of claims 12-14, wherein the obtaining the first inference configuration information comprises:transmitting (412) , to another entity (103) , a request for the first inference configuration information; andreceiving (414) , from the another entity (103) , a response message indicating the first inference configuration information.The method of any of claims 12-16, further comprising:transmitting (506, 606) , to the UE (102) , a configuration message indicating at least one of:the second inference configuration information,a plurality of second inference configuration information,a first activation of one or more inference configurations, ortimer information associated with an activation time of one or more inference configurations.The method of claim 17, further comprising:transmitting (510) , to the UE (102) , control signaling indicating that at least one of:a second activation of the one or more other inference configurations, ora deactivation of one or more activated inference configurations.An apparatus for wireless communication comprising a memory, a transceiver, and a processor coupled to the memory and the transceiver, the apparatus being configured to implement a method as in any of claims 1-18.
Citation Information
Patent Citations
Method for support of artificial intelligence or machine learning techniques for channel estimation and mobility enhancements
US20220294666A1
User equipment machine learning functionality monitoring
WO2023211356A1
Operation configuration method and device
WO2023245586A1