Functionality accuracy and applicability information transmission

Abstract

Configuration information of at least one functionality and configuration of the assistance information message is sent. The configuration includes accuracy information, or at least one applicability

Description

[0002] In some communication systems such as the next cellular systems, artificial intelligence (AI) and / or machine learning (ML) technology is proposed to be used in order to improve the communication performance. An AI / ML model may be applied in the new radio (NR) radio interface to assist model functionalities or communication-related functions, such as, channel state information (CSI) overhead reduction, beam management (BM), positioning, and the like. For example, the AI / ML-based beam management targets spatial and / or time beam prediction for overhead and latency reduction. The AI / ML based functions such as air-interface functions need to be enhanced. SUMMARY

[0003] In a first aspect of the present disclosure, there is provided a first apparatus. The first apparatus comprises at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the first apparatus to: receive, from a second apparatus, configuration information comprising a configuration of at least one functionality and a further configuration enabling a transmission of an assistance information message, the further configuration indicating to include in the assistance information message at least one of: at least one accuracy information of the at least one functionality, or at least one applicability indication of the at least one functionality based on the at least one accuracy information; determine whether at least one event triggering a transmission of the assistance information message happens and at least one condition for transmitting the assistance information message is satisfied; and in accordance with a determination that the at least one event happens and the at least one condition is satisfied, transmit, to the second apparatus, the assistance information message based on the configuration information, the assistance information message comprising at least one of the at least one accuracy information, or the at least one applicability indication based on the at least one accuracy information.

[0004] In a second aspect of the present disclosure, there is provided a second apparatus. The second apparatus comprises at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the second apparatus to: transmit, to a first apparatus, configuration information comprising a configuration of at least one functionality and a further configuration enabling a transmission of an assistance information message, the further configuration indicating to include in the assistance information message at least one of: at least one accuracy information of the at least one functionality, or at least one applicability indication of the at least one functionality based on the at least one accuracy information; and receive, from the first apparatus, the assistance information message comprising at least one of: the at least one accuracy information, or the at least one applicability indication based on the at least one accuracy information.

[0005] In a third aspect of the present disclosure, there is provided a method. The method comprises: receiving, from a second apparatus, configuration information comprising a configuration of at least one functionality and a further configuration enabling a transmission of an assistance information message, the further configuration indicating to include in the assistance information message at least one of: at least one accuracy information of the at least one functionality, or at least one applicability indication of the at least one functionality based on the at least one accuracy information; determining whether at least one event triggering a transmission of the assistance information message happens and at least one condition for transmitting the assistance information message is satisfied; and in accordance with a determination that the at least one event happens and the at least one condition is satisfied, transmitting to the second apparatus, the assistance information message based on the configuration information, the assistance information message comprising at least one of: the at least one accuracy information, or the at least one applicability indication based on the at least one accuracy information.

[0006] In a fourth aspect of the present disclosure, there is provided a method. The method comprises: transmitting, to a first apparatus, configuration information comprising a configuration of at least one functionality and a further configuration enabling a transmission of an assistance information message, the further configuration indicating to include in the assistance information message at least one of: at least one accuracy information of the at least one functionality, or at least one applicability indication of the at least one functionality based on the at least one accuracy information; and receiving, from the first apparatus, the assistance information message comprising at least one of: the at least one accuracy information, or the at least one applicability indication based on the at least one accuracy information.

[0007] In a fifth aspect of the present disclosure, there is provided a first apparatus. The first apparatus comprises means for receiving, from a second apparatus, configuration information comprising a configuration of at least one functionality and a further configuration enabling a transmission of an assistance information message, the further configuration indicating to include in the assistance information message at least one of: at least one accuracy information of the at least one functionality, or at least one applicability indication of the at least one functionality based on the at least one accuracy information; means for determining whether at least one event triggering a transmission of the assistance information message happens and at least one condition for transmitting the assistance information message is satisfied; and means for in accordance with a determination that the at least one event happens and the at least one condition is satisfied, transmitting to the second apparatus, the assistance information message based on the configuration information, the assistance information message comprising at least one of: the at least one accuracy information, or the at least one applicability indication based on the at least one accuracy information.

[0008] In a sixth aspect of the present disclosure, there is provided a second apparatus. The second apparatus comprises means for transmitting, to a first apparatus, configuration information comprising a configuration of at least one functionality and a further configuration enabling a transmission of an assistance information message, the further configuration indicating to include in the assistance information message at least one of: at least one accuracy information of the at least one functionality, or at least one applicability indication of the at least one functionality based on the at least one accuracy information; and means for receiving, from the first apparatus, the assistance information message comprising at least one of: the at least one accuracy information, or the at least one applicability indication based on the at least one accuracy information.

[0009] In a seventh aspect of the present disclosure, there is provided a computer readable medium. The computer readable medium comprises instructions stored thereon for causing an apparatus to perform the method according to the third or fourth aspect.

[0010] It is to be understood that the Summary section is not intended to identify key or essential features of embodiments of the present disclosure, nor is it intended to be used to limit the scope of the present disclosure. Other features of the present disclosure will become easily comprehensible through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Some example embodiments will now be described with reference to the accompanying drawings, where:

[0012] FIG. 1 illustrates an example communication environment in which example embodiments of the present disclosure can be implemented;

[0013] FIG. 2A illustrates a signaling flow for accuracy information and applicability indication transmission according to some example embodiments of the present disclosure;

[0014] FIG. 2B illustrates a signaling flow for applicability indication transmission according to some example embodiments of the present disclosure;

[0015] FIG. 3 illustrates a signaling flow for assistance information message transmission according to some example embodiments of the present disclosure;

[0016] FIG. 4 illustrates a flowchart of a process for accuracy information and applicability indication transmission according to some example embodiments of the present disclosure;

[0017] FIG. 5 illustrates a timeline of determination and transmission of accuracy of a model for beam prediction according to some example embodiments of the present disclosure;

[0018] FIG. 6 illustrates another signaling flow for accuracy information transmission according to some example embodiments of the present disclosure;

[0019] FIG. 7 illustrates another signaling flow for accuracy information transmission according to some example embodiments of the present disclosure;

[0020] FIG. 8 illustrates another signaling flow for accuracy information transmission according to some example embodiments of the present disclosure;

[0021] FIG. 9 illustrates another signaling flow for accuracy information transmission according to some example embodiments of the present disclosure;

[0022] FIG. 10 illustrates a flowchart of a method implemented at a first apparatus according to some example embodiments of the present disclosure;

[0023] FIG. 11 illustrates a flowchart of a method implemented at a second apparatus according to some example embodiments of the present disclosure;

[0024] FIG. 12 illustrates a flowchart of a method implemented at a first apparatus according to some example embodiments of the present disclosure;

[0025] FIG. 13 illustrates a flowchart of a method implemented at a second apparatus according to some example embodiments of the present disclosure;

[0026] FIG. 14 illustrates a flowchart of a method implemented at a first apparatus according to some example embodiments of the present disclosure;

[0027] FIG. 15 illustrates a flowchart of a method implemented at a second apparatus according to some example embodiments of the present disclosure;

[0028] FIG. 16 illustrates a simplified block diagram of a device that is suitable for implementing example embodiments of the present disclosure; and

[0029] FIG. 17 illustrates a block diagram of an example computer readable medium in accordance with some example embodiments of the present disclosure.

[0030] Throughout the drawings, the same or similar reference numerals represent the same or similar element. DETAILED DESCRIPTION

[0031] Principle of the present disclosure will now be described with reference to some example embodiments. It is to be understood that these embodiments are described only for the purpose of illustration and help those skilled in the art to understand and implement the present disclosure, without suggesting any limitation as to the scope of the disclosure. Embodiments described herein can be implemented in various manners other than the ones described below.

[0032] In the following description and claims, unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skills in the art to which this disclosure belongs.

[0033] References in the present disclosure to “one embodiment,” “an embodiment,” “an example embodiment,” and the like indicate that the embodiment described may include a particular feature, structure, or characteristic, but it is not necessary that every embodiment includes the particular feature, structure, or characteristic. Moreover, such phrases are not necessarily referring to the same embodiment. Further, when a particular feature, structure, or characteristic is described in connection with an embodiment, it is submitted that it is within the knowledge of one skilled in the art to affect such feature, structure, or characteristic in connection with other embodiments whether or not explicitly described.

[0034] It shall be understood that although the terms “first,” “second” and the like may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first element could be termed a second element, and similarly, a second element could be termed a first element, without departing from the scope of example embodiments. As used herein, the term “and / or” includes any and all combinations of one or more of the listed terms.

[0035] As used herein, “at least one of the following: ” and “at least one of ” and similar wording, where the list of two or more elements are joined by “and” or “or”, mean at least any one of the elements, or at least any two or more of the elements, or at least all the elements.

[0036] As used herein, unless stated explicitly, performing a step “in response to A” does not indicate that the step is performed immediately after “A” occurs and one or more intervening steps may be included.

[0037] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments. As used herein, the singular forms “a”, “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises”, “comprising”, “has”, “having”, “includes” and / or “including”, when used herein, specify the presence of stated features, elements, and / or components etc., but do not preclude the presence or addition of one or more other features, elements, components and / or combinations thereof.

[0038] As used in this application, the term “circuitry” may refer to one or more or all of the following: (a) hardware-only circuit implementations (such as implementations in only analog and / or digital circuitry) and (b) combinations of hardware circuits and software, such as (as applicable): (i) a combination of analog and / or digital hardware circuit(s) with software / firmware and (ii) any portions of hardware processor(s) with software (including digital signal processor(s)), software, and memory(ies) that work together to cause an apparatus, such as a mobile phone or server, to perform various functions) and (c) hardware circuit(s) and or processor(s), such as a microprocessor(s) or a portion of a microprocessors), that requires software (e.g., firmware) for operation, but the software may not be present when it is not needed for operation.

[0039] This definition of circuitry applies to all uses of this term in this application, including in any claims. As a further example, as used in this application, the term 5 circuitry also covers an implementation of merely a hardware circuit or processor (or multiple processors) or portion of a hardware circuit or processor and its (or their) accompanying software and / or firmware. The term circuitry also covers, for example and if applicable to the particular claim element, a baseband integrated circuit or processor integrated circuit for a mobile device or a similar integrated circuit in server, a cellular 10 network device, or other computing or network device.

[0040] As used herein, the term “communication network” refers to a network following any suitable communication standards, such as New Radio (NR), Long Term Evolution (LTE), LTE-Advanced (LTE-A), Wideband Code Division Multiple Access (WCDMA), High-Speed Packet Access (HSPA), Narrow Band Internet of Things (NB-IoT) and so on. 15 Furthermore, the communications between a terminal device and a network device in the communication network may be performed according to any suitable generation communication protocols, including, but not limited to, the first generation (1G), the second generation (2G), 2.5G, 2.75G, the third generation (3G), the fourth generation (4G), 4.5G, the fifth generation (5G) communication protocols, and / or any other protocols either currently known or to be developed in the future. Embodiments of the present disclosure may be applied in various communication systems. Given the rapid development in communications, there will of course also be future type communication technologies and systems with which the present disclosure may be embodied. It should not be seen as limiting the scope of the present disclosure to only the aforementioned system.

[0041] As used herein, the term “network device” or “network access device” refers to a node in a communication network via which a terminal device accesses the network and receives services therefrom. The network device may refer to a base station (BS) or an access point (AP), for example, a node B (NodeB or NB), an evolved NodeB (eNodeB or eNB), an NR NB (also referred to as a gNB), a Remote Radio Unit (RRU), a radio header (RH), a remote radio head (RRH), a relay, an Integrated Access and Backhaul (IAB) node, a low power node such as a femto, a pico, a non-terrestrial network (NTN) or non-ground network device such as a satellite network device, a low earth orbit (LEO) satellite and a geosynchronous earth orbit (GEO) satellite, an aircraft network device, and so forth, depending on the applied terminology and technology. In some example embodiments, radio access network (RAN) split architecture comprises a Centralized Unit (CU) and a Distributed Unit (DU) at an IAB donor node. An IAB node comprises a Mobile Terminal (IAB-MT) part that behaves like a UE toward the parent node, and a DU part of an IAB node behaves like a base station toward the next-hop IAB node.

[0042] The term “terminal device” refers to any end device that may be capable of wireless communication. By way of example rather than limitation, a terminal device may also be referred to as a communication device, user equipment (UE), a Subscriber Station (SS), a Portable Subscriber Station, a Mobile Station (MS), or an Access Terminal (AT). The terminal device may include, but not limited to, a mobile phone, a cellular phone, a smart phone, voice over IP (VoIP) phones, wireless local loop phones, a tablet, a wearable terminal device, a personal digital assistant (PDA), portable computers, desktop computer, image capture terminal devices such as digital cameras, gaming terminal devices, music storage and playback appliances, vehicle-mounted wireless terminal devices, wireless endpoints, mobile stations, laptop-embedded equipment (LEE), laptop-mounted equipment (LME), USB dongles, smart devices, wireless customerpremises equipment (CPE), an Internet of Things (loT) device, a watch or other wearable, a head-mounted display (HMD), a vehicle, a drone, a medical device and applications (e.g., remote surgery), an industrial device and applications (e.g., a robot and / or other wireless devices operating in an industrial and / or an automated processing chain contexts), a consumer electronics device, a device operating on commercial and / or industrial wireless networks, and the like. The terminal device may also correspond to a Mobile Termination (MT) part of an IAB node (e.g., a relay node). In the following description, the terms “terminal device”, “communication device”, “terminal”, “user equipment” and “UE” may be used interchangeably.

[0043] As used herein, the term “resource,” “transmission resource,” “resource block,” “physical resource block” (PRB), “uplink resource,” or “downlink resource” may refer to any resource for performing a communication, for example, a communication between a terminal device and a network device, such as a resource in time domain, a resource in frequency domain, a resource in space domain, a resource in code domain, or any other resource enabling a communication, and the like. In the following, unless explicitly stated, a resource in both frequency domain and time domain will be used as an example of a transmission resource for describing some example embodiments of the present disclosure. It is noted that example embodiments of the present disclosure are equally applicable to other resources in other domains.

[0044] As used herein, the term “model” is referred to as an association between an input and an output learned from training data, and thus a corresponding output may be generated for a given input after the training. The generation of the model may be based on an ML technique. The ML techniques may also be referred to as AI techniques. In general, an ML model may be built, which receives input information and makes predictions based on the input information. As used herein, a model is equivalent to an AI / ML model, an AI model, an ML model, or a data-driven / data processing algori thm / procedure.

[0045] As described above, an AI / ML model may be applied in the NR radio interface to assist model functionalities or communication-related functions, such as, CSI feedback overhead reduction, beam management, enhanced positioning, and the like. For example, the AI / ML-based beam management targets spatial and / or time beam prediction for overhead and latency reduction.

[0046] For AI / ML enhancements related to beam management, two sub-use cases have been identified, including beam prediction in the spatial domain (referred to as BM-Casel) and beam prediction in the time domain (referred to as BM-Case2).

[0047] The scope of spatial beam prediction (BM-Casel) is to predict the best DL transmitting (Tx) beam and / or DL Tx / receiving (Rx) beam pairs in different spatial locations. Conversely, time-domain beam predictions (BM-Case2) aim to predict the best DL Tx beam and / or DL Tx / Rx beam pairs beam to use for next time instants. The primary motivation is to support a reduced overhead and lower beam measurements and reporting latency. Based on the evaluation, the benefits and gains were verified based on given metrics, and they could be supported by single-sided AI / ML models and consider supporting the necessary / recommended life cycle management (LCM) components for selected sub use cases.

[0048] Radio access network (RAN) has some discussion regarding the progress of the release (Rel-18) air interface AI / ML study item (SI) and the potential plan for the Rel-19 work item (WI). Specification provides support for the following aspects: AI / ML general framework for one-sided AI / ML models within the realm of what has been studied in the FS^NR^AIML^Air project [RAN2]: Signalling and protocol aspects of Life Cycle Management (LCM) enabling functionality and model (if justified) selection, activation, deactivation, switching, fallback; Identification related signalling is part of the above objective; Necessary signalling / mechanism(s) for LCM to facilitate model training, inference, performance monitoring, data collection (except for the purpose of CN / OAM / OTT collection of UE-sided model training data) for both UE-sided and NW-sided models; and Signalling mechanism of applicable functionalities / models. Beam management - DL Tx beam prediction for both UE-sided model and NW-sided model, encompassing [RAN1 / RAN2]: Spatial-domain DL Tx beam prediction for Set A of beams based on measurement results of Set B of beams (“BM-Casel”); Temporal DL Tx beam prediction for Set A of beams based on the historic measurement results of Set B of beams (“BM-Case2”); Specify necessary signalling / mechanism(s) to facilitate LCM operations specific to the Beam Management use cases, if any; and Enabling method(s) to ensure consistency between training and inference regarding NW-side additional conditions (if identified) for inference at UE.

[0049] As specified in work item scope both for BM easel and BM-Case2 Set A of Beams are AI / ML model predicted beam whereas Set B beams are actual measured beams, gNB configures UE both Set A and Set B related configuration such as CSI resource and report configuration.

[0050] RAN2 discussed the following definition for functionality types and decided to have more discussion to identify the need of such definitions and whether further update is needed to clarify the definition. Supported / identified functionalities: this refers to functionalities that UE can indicate by using UE capabilities. Configured functionalities: this refers to functionalities that gNB can configure UE for model inference and performing measurements for training purposes. Depending on proactive / reactive approach, configured functionalities may or may not be applicable upon configuration. Applicable functionalities: this refers to functionalities that the UE is ready to apply for model inference. It can be considered as candidates for functionality activation.

[0051] RAN2 will continue discussing the functionality activation / deactivation. Several companies are assuming that switching and fallback are supported via activation / deactivation. Some companies, go even further, assuming that de-activation is fallback to legacy. While others have more conservative views indicating that it depends on what functionality is for what use case and it could refer to switching.

[0052] RAN2 will support functionality activation / deactivation after inference configuration. It will work offline on the definitions for functionality types and define what is availability. The UE will indicate the gNB / LMF whether the AI / ML functionality is available / applicable. For a functionality to be applicable at least there should at least one model available within it. For NW-side additional conditions, RAN2 assumes that RRC signaling from gNB to UE can be designed for consistency between inference and training. RAN2 will wait for RANI input for further details. For BM use case, As a baseline the UE determines whether a functionality is applicable. Existing UAI framework is used at least for proactive reporting of applicable functionality.

[0053] The present disclosure investigates how activation / deactivation of a functionality is facilitated after applicable functionality reporting. UE capabilities reporting may be used for reporting conditions that remain static and may not be time- dependent or specific to certain cells and / or NW conditions.

[0054] On the other hand, current solutions consider using cell specific AI / ML models, where each model is trained for specific NW configuration, UE speeds, etc, and that may not generalize to other cells or to different NW configuration. In addition, the UE may not be able to store all the AI / ML models for every cell. Therefore, it is preferable that UE has possibility to report whether an AI / ML functionality remains applicable after certain events or conditions that relates to the ML model used by the UE for executing the AI / ML functionality.

[0055] UAI is used to signal temporary reductions to UE capabilities in the form of “overheating assistance” and is used to signal updates such as an indication that a new flight path is available (for UAV operation). Given that UAI can be used to signal restrictions to previously signaled capabilities, it is a good starting point for the reporting of applicable functionalities and updates thereto. Enhancing current UAI framework is the preferred direction of 3GPP RAN2 WG that was also agreed in the RAN2#126 meeting (as mentioned in Section 3) for specific case of proactive reporting of applicable AI / ML functionalities, whereas it is still for further study for other types of reporting of applicable AI / ML functionalities.

[0056] A set of open points that need to be addressed next is listed below. What the exact content of the UAI message is. Following other features that use the UAI message for restricting UE capabilities, several types of information are possible to be included. Considering the usability of UAI for updating UE conditions or indicating UE restrictions, it is still not clear which type of information may be more relevant to be included in UAI message for AI / ML functionality applicability.

[0057] Current assumptions consider: 1) the UE could indicate to support an AI / ML functionality in the capability even if there is no model available at the UE device and 2) the AI / ML functionality should be applicable whenever an ML model is available at the UE device. However, the model's availability may not guarantee its successful use and may not be sufficient. Other context information may facilitate the NW decision for activating or not the indicated available functionality.

[0058] A further aspect considers that AI / ML model may be downloaded at the UE device on-demand, therefore the AI / ML functionality applicability and / or accuracy could be improved and in general may change over time because of the different ML model downloaded. It is therefore key to provide that information to NW, which can activate and configure the functionality for the ML model that performs better.

[0059] In particular, AI / ML techniques for BM prediction should be activated only when they perform better than other legacy solutions. Additionally, the time needed to retrain an AI / ML model, including the time to process new data points, limits the LCM procedure of AI / ML functionalities. For example, the use of BM prediction schemes based on reinforcement learning techniques would be limited only to network configuration where the UE processing time is shorter than the SS / PBCH Block Measurement Timing Configuration (SMTC) periodicity.

[0060] In order to solve at least part of the above problems or other potential problems, a solution on accuracy information and applicability indication transmission is proposed. According to example embodiments, a second apparatus (for example, a network device) transmits, to a first apparatus (such as a terminal device) configuration information comprising a configuration of at least one functionality and a further configuration enabling a transmission of an assistance information message, the further configuration indicating to include in the assistance information message at least one of at least one accuracy information of the at least one functionality, or at least one applicability indication of the at least one functionality based on the at least one accuracy information. If at least one event triggering a transmission of the assistance information message happens and at least one condition for transmitting the assistance information message is satisfied, the first apparatus transmits, to the second apparatus, the assistance information message based on the configuration information. The assistance information message includes the at least one accuracy information, and / or the at least one applicability indication based on the at least one accuracy information.

[0061] In this manner, the accuracy information and / or the applicability indication of the functionality may be transmitted to the second apparatus via the assistance information message such as UE assistance information (UAI) message.

[0062] In order to solve at least part of the above problems or other potential problems, another solution on applicability indication transmission is proposed. According to example embodiments, a second apparatus (for example, a network device) transmits, to a first apparatus (such as a terminal device) configuration information comprising a configuration of at least one functionality and a further configuration comprising at least one criterion for reporting at least one applicability indication of the at least one functionality. The at least one applicability indication is based on at least one accuracy information of the at least one functionality. If the at least one criterion is satisfied, the first apparatus determines the at least one applicability indication based on the at least one accuracy information of the at least one functionality and transmits, to the second apparatus, the assistance information message including the at least one applicability indication.

[0063] In this manner, the applicability indication of the functionality may be transmitted to the second apparatus via the assistance information message such as UE assistance information (UAI) message.

[0064] Principle and implementations of the present disclosure will be described in detail below with reference to FIGS. 1-17.

[0065] FIG. 1 illustrates an example communication environment 100 in which example embodiments of the present disclosure can be implemented. In the communication environment 100, a plurality of communication devices, including a first apparatus 110 and a second apparatus 120, can communicate with each other.

[0066] In the example of FIG. 1, the first apparatus 110 may include a terminal device and the second apparatus 120 may include a network device serving the terminal device. The serving area of the second apparatus 120 may be called as a cell 102.

[0067] In some example embodiments, a model functionality such as an AI / ML based functionality may be provided for the first apparatus 110. For example, the second apparatus 120 may provide a plurality of beams for the first apparatuses 110. The model functionality may be a beam prediction which predicts a beam for a corresponding first apparatus 110. In some example embodiments, a model may derive an outcome such as the predicted beam of the model functionality. The model may be implemented at the first apparatus 110, or the second apparatus 120, or both. For purpose of illustration, some example embodiments hereinafter will be described with the beam prediction as the model functionality. It is to be understood that the model functionality may also be any other suitable functions, including but not limited to CSI prediction, positioning prediction, or the like. Scope of the present disclosure is not limited in this regard.

[0068] It is to be understood that the number of devices and their connections shown in FIG. 1 are only for the purpose of illustration without suggesting any limitation. The communication environment 100 may include any suitable number of devices configured to implementing example embodiments of the present disclosure. Although not shown, it would be appreciated that one or more additional devices may be located in the cell 102, and one or more additional cells may be deployed in the communication environment 100. It is noted that although illustrated as a network device, the second apparatus 120 may be another device than a network device. Although illustrated as a terminal device, the first apparatus 110 may be a device other than a terminal device.

[0069] In the following, for the purpose of illustration, some example embodiments are described with the first apparatus 110 operating as a terminal device and the second apparatus 120 operating as a network device. However, in some example embodiments, operations described in connection with a terminal device may be implemented at a network device or other device, and operations described in connection with a network device may be implemented at a terminal device or other device.

[0070] In some example embodiments, if the first apparatus 110 is a terminal device and the second apparatus 120 is a network device, a link from the second apparatus 120 to the first apparatus 110 is referred to as a downlink (DL), while a link from the first apparatus 110 to the second apparatus 120 is referred to as an uplink (UL). In DL, the second apparatus 120 is a transmitting (TX) device (or a transmitter) and the first apparatus 110 is a receiving (RX) device (or a receiver). In UL, the first apparatus 110 is a TX device (or a transmitter) and the second apparatus 120 is a RX device (or a receiver).

[0071] Communications in the communication environment 100 may be implemented according to any proper communication protocol(s), comprising, but not limited to, cellular communication protocols of the first generation (1G), the second generation (2G), the third generation (3G), the fourth generation (4G), the fifth generation (5G), the sixth generation (6G), and the like, wireless local network communication protocols such as Institute for Electrical and Electronics Engineers (IEEE) 802.11 and the like, and / or any other protocols currently known or to be developed in the future. Moreover, the communication may utilize any proper wireless communication technology, comprising but not limited to: Code Division Multiple Access (CDMA), Frequency Division Multiple Access (FDMA), Time Division Multiple Access (TDMA), Frequency Division Duplex (FDD), Time Division Duplex (TDD), Multiple-Input Multiple-Output (MIMO), Orthogonal Frequency Division Multiple (OFDM), Discrete Fourier Transform spread OFDM (DFT-s-OFDM) and / or any other technologies currently known or to be developed in the future.

[0072] As briefly mentioned, before the NW decides to activate or deactivate a model functionality, accuracy information and / or applicability indication of a functionality is required to be reported from the UE. FIG. 2A illustrates a signaling flow 200 for accuracy information and applicability indication transmission according to some example embodiments. The signaling flow 200 involves the first apparatus 110 and the second apparatus 120 in FIG. 1. For purpose of illustration, the signaling flow 200 will be described with respect to FIG. 1.

[0073] In operation, the second apparatus 120 transmit (210), to the first apparatus 110, configuration information comprising a configuration of at least one functionality and a further configuration enabling a transmission of an assistance information message. The further configuration indicates to include in the assistance information message at least one of: at least one accuracy information of the at least one functionality, or at least one applicability indication of the at least one functionality based on the at least one accuracy information. The first apparatus 110 receives (215) the configuration information. The configuration information may be transmitted (210) via radio resource control (RRC) or any other suitable signaling or message.

[0074] The first apparatus 110 determines (220) whether at least one event triggering a transmission of the assistance information message happens and determines (225) whether at least one condition for transmitting the assistance information message is satisfied.

[0075] If the at least one event happens and the at least one condition is satisfied, the first apparatus 110 transmits (230), to the second apparatus 120, the assistance information message based on the configuration information. The assistance information message includes the at least one accuracy information, and / or the at least one applicability indication based on the accuracy information. In addition, in some embodiments, the assistance information message may include an indication of the at least one applicable functionality. The second apparatus 120 receives (235) the assistance information message.

[0076] By way of example, the assistance information message may be UAI message. For example, UAI signalling may be used for reporting AI / ML functionality accuracy information associated with AI / ML functionality applicability. In one variant, the applicability of AI / ML functionality may be derived by the accuracy level. For example, accuracy 0 indicates the functionality is non-applicable, and accuracy >0 indicates that functionality is applicable.

[0077] In some example embodiments, the at least one functionality is based on an ML model, and the accuracy information comprises at least one of: a prediction accuracy of the ML model, a difference between a predicted value of the at least one functionality and a ground truth value, or a value associated with an implementation of the ML model.

[0078] In some example embodiments, the at least one functionality comprises a beam prediction based on the ML model, and the prediction accuracy comprises at least one of: a percentage of instances in which at least one predicted beam is the same as at least one ground truth best beam, a percentage of instances in which at least one ground truth signal strength of the at least one predicted beam is larger than or equal to a threshold. In some example embodiments, the difference between the predicted value and the ground truth value comprises at least one of: a signal strength of a predicted beam and a signal strength of a ground truth best beam, or a difference between a predicted signal strength of the predicted beam and a measured signal strength of the ground truth best beam. As used herein, the term “signal strength” may be related to measurements defined in the standard such as reference signal received power (RSRP), interference plus noise ratio (SINR), Signal to Noise Ratio (SNR), received signal strength indication (RSSI), channel quality indicator (CQI), or the like.

[0079] In some example embodiments, the functionality accuracy information indicates the performance of AI / ML functionality and may be defined as follows (examples refer to AI / ML beam prediction functionality): prediction accuracy as the percentage of instances in which the Top-1 (“best”) predicted beam is the Top-1 ground-truth best beam; prediction accuracy as the percentage of instances in which the Top-N (“best”) predicted beams are the Top-N ground-truth best beams, in any order; prediction accuracy as the percentage of instances in which the ground truth RSRP of the Top-1 or Top-N (“best”) predicted beams exceed an RSRP threshold; reference signal received power (RSRP) difference: difference between RSRP of Top-1 predicted beam and RSRP of ground-truth best beam; predicted RSRP difference: difference between predicted RSRP of Top-1 predicted beam and measured RSRP of ground-truth best beam; and / or an implementation-specific value set by the second apparatus 120.

[0080] It is to be understood that the accuracy information may include a combination of two or more of the previously described accuracy measures. Scope of the present disclosure is not limited here.

[0081] In some example embodiments, the first apparatus 110 may determine the at least one applicability indication of the at least one functionality based on the at least one accuracy information of the at least one functionality.

[0082] In some example embodiments, the further configuration comprises at least one of an indication of including the at least one accuracy information in the assistance information message, an indication of including the at least one applicability indication in the assistance information message, an indication of including at least one conditionally applicable indication in the assistance information message, where the at least one conditionally applicable indication indicates an ongoing accuracy evaluation of the at least one functionality, the at least one event triggering a transmission of the assistance information message happens, the at least one condition for transmitting the assistance information message is satisfied, or a timer associated with the transmission of the assistance information message.

[0083] In some example embodiments, the further configuration comprises the at least one event triggering the transmission of the assistance information message. For example, the network may configure the UE to report with UAI the AI / ML functionality accuracy information and / or applicability information based on the following events (the events may be also part of the configuration).

[0084] A first event may be that an ML model associated with the at least one functionality is changed. For example, the first apparatus 110 performs training / updating / fme-tuning of an AI / ML model associated with AI / ML functionality such that functionality accuracy information has changed. For another example, the first apparatus 110 downloads an upgraded AI / ML model associated with applicable AI / ML functionality. The upgraded AI / ML model determines changes of the functionality accuracy information.

[0085] A second event may be that the first apparatus 110 moves from a first cell to a second cell. For example, the first apparatus 110 leaves the current cell and connects to a neighbor cell (e.g., due to UE mobility). The functionality accuracy information may have changed due to AI / ML model generalization issues.

[0086] A third event may be that an indication from the second apparatus 120 indicates a change of network-side associated identifier (ID) associated with the at least one functionality. For example, the first apparatus 110 receives a NW side additional condition, e.g. associated ID. In some example embodiments, the change of network-side associated identifier indicates a change of a transmitting (Tx) beam property of the second apparatus 120. By way of example, the Tx beam property may include but not limited to order, shape or direction of the transmitting beam(s). In one example, the change of associated ID relates to the changes of Tx beam proprieties adopted by the NW while transmitting Tx beams and may change the functionality accuracy information.

[0087] A fourth event may be that at least one of a measured signal strength of a serving cell or a measured signal strength of at least one neighboring cell meets a condition for neighboring cells. The signal strength of the serving cell and / or neighbor cells that UE measures meet the condition for neighboring cells. By way of example, the condition for neighboring cells comprises at least one of: a condition that the measured signal strength of a serving cell is smaller than a sum of the measured signal strength of at least one neighboring cell and a threshold on the signal strength, or a condition that a prediction accuracy of the ML model applied on the measured signal strength of a serving cell is smaller than the maximum of the prediction accuracy of the ML model applied to the measured signal strength of at least one neighboring cell and a threshold on the prediction accuracy.

[0088] A fifth event may be that the first apparatus 110 fails to use the ML model due to lack of processing resource. For example, the first apparatus 110 is not able to use the AI / ML model associated with AI / ML functionality due to lack of processing resources.

[0089] It is to be understood that these events are only for the purpose of illustration, without suggesting any limitations. Any suitable events may be applied. Embodiments of the present disclosure is not limited here.

[0090] In some example embodiments, if at least one accuracy evaluation of the at least one functionality is ongoing, the first apparatus 110 may include the at least one conditionally applicable indication in the assistance information message. By way of example, the second apparatus 120 may configure the first apparatus 110 to provide the AI / ML functionality conditionally-applicable in UAI message. As used herein, “conditionally-applicable” indicates that the AI / ML functionality is not yet applicable as the evaluation of accuracy is ongoing. In one example, “conditionally-applicable” covers a different UE behavior with respect to the non-applicability status, since when indicating “conditionally-applicable”, the UE implies that the evaluation of accuracy is ongoing, which differentiates from the non-applicability indication, where the UE may not evaluate the AI / ML functionality or the UE may not even have an applicable model to perform the AI / ML functionality.

[0091] In one case, the first apparatus 110 may use performance monitoring to evaluate the AI / ML functionality accuracy information. If performance monitoring is passed, the UE may indicate to the NW that the AI / ML functionality is applicable.

[0092] Monitoring may not be necessarily configured by the second apparatus 120. The first apparatus 110 may transparently run monitoring processes in the background while executing an AI / ML functionality or the legacy BM. Alternatively, the first apparatus 110 may request the transmission of monitoring RS, for evaluating accuracy of AI / ML functionalities.

[0093] In some example embodiments, the at least one functionality comprises a plurality of functionalities. In response to the at least one event associated with a first functionality of the plurality of functionalities, the first apparatus 110 may add at least one first accuracy information for first applicability indication of the first functionality in the assistance information message. The first apparatus 110 may start a timer associated with the transmission of the assistance information message. Based on the timer being running, the first apparatus 110 may update the assistance information message by detecting the at least one event for the plurality of functionalities. Based on the timer expiring, the first apparatus 110 may transmit the updated assistance information message to the second apparatus 120.

[0094] In some example embodiments, at least one condition for transmitting the assistance information message comprises a condition that a change of accuracy information of a machine learning (ML) model associated with the at least one functionality is larger than or equal to a threshold.

[0095] In some example embodiments, the first apparatus 110 may determine the at least one accuracy information based on a monitoring process for the at least one functionality. The monitoring process compares at least one measured reference signal resource and at least one predicted reference signal resource obtained by the at least one functionality. The first apparatus 110 may determine the at least one applicability indication based on the determined at least one accuracy information.

[0096] In some example embodiments, the second apparatusl20 may transmit, to the first apparatus 110, at least one activation or deactivation signal for the at least one functionality based on the assistance information message. The first apparatus 110 may receive, from the second apparatus 120, the activation or deactivation signal for the at least one functionality. The activation or deactivation signal may be determined based on at least one of: the at least one accuracy information included in the assistance information message, or the at least one applicability indication included in the assistance information message.

[0097] In some example embodiments, if the at least one accuracy information indicates an accuracy larger than or equal to a threshold or the at least one applicability indication indicates that the at least one functionality is applicable, the second apparatus 120 may transmit the at least one activation signal for the at least one functionality to the first apparatus 110. If the at least one accuracy information indicates an accuracy less than the threshold or the at least one applicability indication indicates that the at least one functionality is inapplicable, the second apparatus 120 may transmit the at least one deactivation signal for the at least one functionality to the first apparatus 110.

[0098] That is, activation or deactivation of the functionality may be decided by the second apparatus 120 based on the UAI functionality accuracy information included in UAI message. In one example, the second apparatus 120 may decide to activate the AI / ML functionality if the functionality accuracy information of applicable AI / ML functionality indicated is above a threshold considered for activation of AI / ML functionality. In a second example, the second apparatus 120 may decide to deactivate the AI / ML functionality if the functionality accuracy information of applicable AI / ML functionality is below a threshold considered for activation of AI / ML functionality.

[0099] With these embodiments, it allows the NW to evaluate the UAI-based applicability reporting of AI / ML functionality before proceeding activating the functionality.

[0100] FIG. 2B illustrates a signaling flow 250 for applicability indication transmission according to some example embodiments of the present disclosure. The signaling flow 250 involves the first apparatus 110 and the second apparatus 120 in FIG. 1. For purpose of illustration, the signaling flow 250 will be described with respect to FIG. 1.

[0101] In operation, the second apparatus 120 transmit (260), to the first apparatus 110, configuration information comprising a configuration of at least one functionality and a further configuration comprising at least one criterion for reporting at least one applicability indication of the at least one functionality. The at least one applicability indication is based on at least one accuracy information of the at least one functionality. The at least one applicability indication indicates whether the at least one functionality is applicable. The further configuration may enable reporting the at least one applicability indication of the at least one functionality in the assistance information message. The first apparatus 110 receives (265) the configuration information.

[0102] The first apparatus 110 determines (270) whether the at least one criterion is satisfied. If the at least one criterion is satisfied, the first apparatus 110 determines (272) the at least one applicability indication based on at least one accuracy information of the at least one functionality. The first apparatus 110 transmits (275), to the second apparatus 120, the assistance information message including the at least one applicability indication based on the at least one accuracy information. The second apparatus 120 receives (280) the assistance information message, such as UAI message.

[0103] In some example embodiments, the at least one functionality is based on an ML model. The at least one criterion may include a first criterion that a prediction accuracy of the ML model is larger than a first threshold for prediction accuracy. To indicate if the functionality is applicable, prediction accuracy may be above a given prediction accuracy threshold. Alternatively, to indicate if the functionality is non-applicable, prediction accuracy may be below a given prediction accuracy threshold.

[0104] The at least one criterion may include a second criterion that an error between measurements of a signal strength of a predicted beam of the ML model and a groundtruth best beam is less than or equal to a second threshold for signal strength error. To indicate if the functionality is applicable, RSRP error is below a given RSRP error threshold. Alternatively, to indicate if the functionality is non-applicable, RSRP error is above a given RSRP error threshold.

[0105] The at least one criterion may include a third criterion that a difference between a prediction of a signal strength of a predicted beam of the ML model and a measurement of a signal strength of a ground-truth best beam is less than or equal to a third threshold for predicted signal strength error. To indicate if the functionality is applicable, predicted RSRP error is below a given predicted RSRP error threshold. Alternatively, to indicate if the functionality is non-applicable, predicted RSRP error is above a given predicted RSRP error threshold.

[0106] The at least one criterion may include a fourth criterion that a timer associated with reporting the at least one applicability indication expires or is stopped. For example, the fourth criterion may be that prohibit timer has expired, where the prohibit timer is configured by the second apparatus 120.

[0107] In some example embodiments, the further configuration may include at least one of: a first threshold for prediction accuracy, a second threshold for signal strength error, a third threshold for predicted signal strength error, or a timer associated with reporting the at least one applicability indication.

[0108] It is to be understood that these criteria are only for the purpose of illustration, without suggesting any limitations. Any suitable criteria may be applied. Embodiments of the present disclosure is not limited here.

[0109] In this way, the NW configures the UE to report with UAI the AI / ML functionality applicability indication (functionality is applicable / non-applicable) only if AI / ML functionality accuracy fulfils one or more of the criteria described above (which criteria(s) and threshold(s) to use may also be provided by NW as part of the configuration).

[0110] In some example embodiments, in response to transmitting the assistance information message including the at least one applicability indication based on the at least one accuracy information, the first apparatus 110 may initiate the timer associated with the at least one functionality. The first apparatus 110 may stop the timer based on a change of at least one applicability of the at least one functionality. The change of the at least one applicability may be based on at least one of: a change of a network-side associated identifier associated with the at least one functionality, or a change of a radio condition. The change of network-side associated identifier may indicate a change of a transmitting beam property of the second apparatus 120. If radio link failure is detected, or alternatively a following beam failure recovery request is received, the radio condition is changed.

[0111] In some example embodiments, based on the timer being running, the first apparatus 110 may refrain from transmitting the assistance information message including the at least one applicability indication to the second apparatus 120.

[0112] In some example embodiments, the further configuration comprises the at least one event triggering the transmission of the assistance information message. For example, the network may configure the UE to report with UAI the AI / ML functionality accuracy information and / or applicability information based on the following events (the events may be also part of the configuration).

[0113] A first event may be that an ML model associated with the at least one functionality is changed. For example, the first apparatus 110 performs training / updating / fme-tuning of an AI / ML model associated with AI / ML functionality such that functionality accuracy information has changed. For another example, the first apparatus 110 downloads an upgraded AI / ML model associated with applicable AI / ML functionality. The upgraded AI / ML model determines changes of the functionality accuracy information.

[0114] A second event may be that the first apparatus 110 moves from a first cell to a second cell. For example, the first apparatus 110 leaves the current cell and connects to a neighbor cell (e.g., due to UE mobility). The functionality accuracy information may have changed due to AI / ML model generalization issues.

[0115] A third event may be that an indication from the second apparatus 120 indicates a change of network-side associated identifier (ID) associated with the at least one functionality. For example, the first apparatus 110 receives a NW side additional condition, e.g. associated ID. In some example embodiments, the change of network-side associated identifier indicates a change of a transmitting (Tx) beam property of the second apparatus 120. By way of example, the Tx beam property may include but not limited to order, shape or direction of the transmitting beam(s). In one example, the change of associated ID relates to the changes of Tx beam proprieties adopted by the NW while transmitting Tx beams and may change the functionality accuracy information.

[0116] A fourth event may be that at least one of a measured signal strength of a serving cell or a measured signal strength of at least one neighboring cell meets a condition for neighboring cells. The signal strength of the serving cell and / or neighbor cells that UE measures meet the condition for neighboring cells. By way of example, the condition for neighboring cells comprises at least one of: a condition that the measured signal strength of a serving cell is smaller than a sum of the measured signal strength of at least one neighboring cell and a threshold on the signal strength, or a condition that a prediction accuracy of the ML model applied on the measured signal strength of a serving cell is smaller than the maximum of the prediction accuracy of the ML model applied to the measured signal strength of at least one neighboring cell and a threshold on the prediction accuracy.

[0117] A fifth event may be that the first apparatus 110 fails to use the ML model due to lack of processing resource. For example, the first apparatus 110 is not able to use the AI / ML model associated with AI / ML functionality due to lack of processing resources.

[0118] It is to be understood that these events are only for the purpose of illustration, without suggesting any limitations. Any suitable events may be applied. Embodiments of the present disclosure is not limited here.

[0119] In some example embodiments, in response to a timer associated with reporting the at least one applicability indication expiring, the first apparatus 110 may transmit a further assistance information message to the second apparatus 120. The further assistance information may include at least one updated applicability indication of the at least one functionality based on at least one of the following conditions being satisfied: a first condition that at least one applicability of the at least one functionality is changed based on a change of a configuration or property of the first apparatus 110, or a second condition that the at least one event triggering the transmission of the assistance information message happens. By way of example, the propriety of the first apparatus 110 may include but not limited to UE speed, UE trajectory and UE position, UE receiver beam codebook and receiver panel.

[0120] In some example embodiments, in response to a timer associated with reporting the at least one applicability indication expiring, the first apparatus 110 may refrain from transmitting the assistance information message including the at least one applicability indication based on at least one of the following conditions being satisfied: a first condition that the at least one applicability indication of the at least one functionality is transmitted by a reconfiguration message response, a second condition that the at least one applicability indication is same with that included in a previous assistance information message, a third condition that the at least one functionality is not supported by a configuration of the second apparatus 120, or a fourth condition that the at least one functionality is not supported by capability of the first apparatus 110.

[0121] In some example embodiments, the at least one functionality comprises a plurality of functionalities. While a timer associated with reporting the at least one applicability indication is running, the first apparatus 110 may detect that a first applicability indication of a first functionality and a second applicability indication of a second functionality change. The first apparatus 110 may include the changed (or updated) first applicability indication and the changed second applicability indication in the assistance information message. In response to the timer expiring, the first apparatus 110 may transmit, to the second apparatus 120, the assistance information message including the changed first applicability indication and the changed second applicability indication. It is to be understood that the assistance information message may include a single updated applicability indication of a single functionality, or two or more updated applicability indications associated with two or more functionalities. Embodiments of the present disclosure is not limited here.

[0122] In some example embodiments, the first apparatus 110 may determine the at least one accuracy information of the at least one functionality based on a monitoring process for the at least one functionality. The monitoring process compares at least one measured reference signal resource and at least one predicted reference signal resource obtained by the at least one functionality. The first apparatus 110 may determine (272) the at least one applicability indication based on the at least one determined accuracy information.

[0123] In some example embodiments, the second apparatus 120 may transmit, to the first apparatus 110, an activation or deactivation signal for the at least one functionality based on the at least one applicability indication in the assistance information message. The first apparatus 110 may receive, from the second apparatus 120, an activation or deactivation signal for the at least one functionality. The activation or deactivation signal may be determined based on the at least one applicability indication in the assistance information message.

[0124] In some example embodiments, if the at least one applicability indication based on the at least one accuracy information indicates that the at least one functionality is applicable, the second apparatus 120 may transmit the activation signal for the at least one functionality to the first apparatusl 10. If the at least one applicability indication based on the at least one accuracy information indicates that the at least one functionality is inapplicable, the second apparatus 120 may transmit the deactivation signal for the at least one functionality to the first apparatus 110.

[0125] With these embodiments, it allows the NW to evaluate the UAI-based applicability reporting of AI / ML functionality before proceeding activating the functionality.

[0126] As mentioned, the accuracy information and / or the applicability indication may be transmitted in the assistance information message. FIG. 3 illustrates a signaling flow 300 for assistance information message transmission according to some example embodiments of the present disclosure. The signaling flow 300 involves the first apparatus 110 and the second apparatus 120 in FIG. 1. For purpose of illustration, the signaling flow 300 will be described with respect to FIG. I.

[0127] In operation, the second apparatus 120 may transmit (310), to the first apparatus 110 such as UE, UECapabilityEnqiry message to initiate the procedure to a UE reporting its AI / ML supported functionalities.

[0128] The first apparatus 110 may transmit (320), to the second apparatus 120, UECapablitylnformation message containing supported functionalities at the side of the first apparatus 110. Supported functionalities refer to functionalities that the first apparatus 110 may indicate by using UE capability signalling.

[0129] The second apparatus 120 may configures the first apparatus 110 that it is allowed to provide its applicable functionalities. For example, the second apparatus 120 may transmit (330), to the first apparatus 110, RRCReconfiguration (for example, OtherConfig) including the configuration information as described with respect to FIG. 2A and FIG. 2B.

[0130] The first apparatus 110 may transmit (340), to the second apparatus 120, UAI message including applicable functionalities upon change of applicable functionality / condition. Applicable functionalities refer to functionalities that the UE is ready to apply for model inference.

[0131] The second apparatus 120 may transmit (350) an inference configuration (such as RRCReconfiguration) for the applicable functionalities to the first apparatus 110.

[0132] An inference / monitoring may be performed (360) based on network / UE activation / deactivation. For example, the second apparatus 120 may transmit an activation or deactivation signal for a corresponding functionality to the first apparatus 110. Activated functionalities refer to functionalities already activated and performing inference.

[0133] The signaling flow 300 may be applied in combination with the signaling flow 200 or signaling flow 250. In this way, it allows the NW to evaluate the UAI-based applicability reporting of AI / ML functionality before proceeding activating the functionality

[0134] FIG. 4 illustrates a flowchart of a process 400 for accuracy information and applicability indication transmission according to some example embodiments of the present disclosure. The process 400 may be implemented by the first apparatus 110. The process 400 shows an example of the implementation involved in determining and transmitting accuracy information of i-th AI / ML functionality through UAI message.

[0135] In the process 400, the first apparatus 110 may be configured by the second apparatus 120 to measure for example SetA beams, SetB beams, or both. In one implementation, the configuration includes a plurality of conditions to make measurements, including for example a periodicity, a mobility status equivalent to high mobility, a signal strength (such as RSRP) smaller than a threshold. In another implementation, the configuration includes at least one AI / ML functionality and its configuration, which include the type of inputs, outputs and loss or reward function for training.

[0136] At block 410, the first apparatus 110 measures for example SetA or SetB beams and determine a new sample, observation, data sample, performance monitoring time sample for the AI / ML model performing beam prediction.

[0137] At block 420, the first apparatus 110 determines if any event detected to update the accuracy information of the model. These events may cause the first apparatus 110 to update its accuracy and add it to its applicable functionality report. If the event(s) is detected, at block 430, the first apparatus 110 determines the accuracy of the AI / ML model, e.g. a function of Prediction accuracy, RSRP difference, Predicted RSRP difference.

[0138] At block 440, the first apparatus 110 determines whether any changes of the prediction accuracy have occurred for the AI / ML model. In one example, if the prediction accuracy is above a given prediction accuracy threshold, the first apparatus 110 may indicate that the functionality is applicable. On the other hand, if the prediction accuracy is below a given prediction accuracy threshold, the first apparatus 110 may indicate that the functionality is not applicable. On the other hand, if there are no changes to the prediction accuracy, the first apparatus 110 may proceed with the operations described in block 410, e.g., measuring SetA / SetB beams.

[0139] If changes are determined for the model accuracy, at block 450, the first apparatus 110 determines whether the prohibit timer is enabled or disabled. If the prohibit timer is disabled, the first apparatus 110 proceeds with block 460. On the other hand, in the case the prohibited timer is enabled, the first apparatus 110 may continue with the operations described at block 410, measuring e.g. SetA / SetB beams.

[0140] At block 460, the first apparatus 110 prepares the UAI message such as RRC UAI message, including at least the accuracy information of the AI / ML functionality corresponding to the AI / ML model and updated accuracy information for any other AI / ML models for which the accuracy changed during the evaluation period for the at least one AI / ML functionality.

[0141] At block 470, the first apparatus 110 transmits the UAI message to the second apparatus 120. Several examples of metrics that may be used to report accuracy information in the UAI message will be described. To note that they may be applied for determining the accuracy of an AI / ML model associated with the AI / ML functionality when 1) the accuracy is calculated offline, for instance, by testing AI / ML model requirements related to accuracy and / or when 2) the accuracy is derived from a monitoring process that may either be configured by second apparatus 120 and / or performed in a transparent manner by the first apparatus 110.

[0142] Some examples of metrics are provided as follows: Top-K beam prediction accuracy corresponding to predicted Top-K beam IDs. This metric can be derived for instance for Top-1 beam ID as the percentage of the Top-1 genie-aided beam matches the Top-1 predicted beam, and for the Top-K beam IDs as the percentage of the Top-1 genie-aided beam is one of the Top-K predicted beams. Ll-RSRP difference. This metric can be derived determining the difference between the ideal Ll-RSRP of Top-1 predicted beam and the ideal Ll-RSRP of the Top-1 genie-aided beam. Ll-RSRP difference predicted. This metric can be derived for AI / ML models supporting predicted RSRP and can be computed by calculating the difference between measured Ll-RSRP of current beam and predicted RSRP of the predicted Top 1 beam.

[0143] The process 400 may be repeated to update accuracy information of the applicable AI / ML functionality in the UAI message.

[0144] FIG. 5 illustrates an example diagram 500 of a timeline of determination and transmission of accuracy of a model for beam prediction according to some example embodiments of the present disclosure. At 510, the second apparatus 120 configures the first apparatus 110. The configuration includes a periodicity for the measurement of SetA / SetB beams and a prohibit timer, which sets a periodicity of UAI reporting. In this example the UAI reporting periodicity is longer than the measurement periodicity.

[0145] After being configured by the second apparatus 120, the first apparatus 110 makes measurements for SetA / SetB at regular intervals according to the periodicity of the measurement configuration. After the first UAI message transmission, at 520, a prohibit timer is triggered. As new observation becomes available, the model can be updated or retrained using a new measurement. The first apparatus 110 is not allowed to transmit any other UAI message while the timer is running at 530 even if the model has been updated / retrained using a new measurement and its accuracy of the model has been improved.

[0146] At the expiration of the prohibit timer at 540, the first apparatus 110 may be allowed to transmit a second UAI message indicating the changes of the accuracy for the applicable AI / ML functionality. Once the UAI has been transmitted, the prohibited timer is restarted by the first apparatus 110.

[0147] In another embodiment, the model may not be updated as new observation becomes available. However, it is still important for the network to be assisted by the first apparatus 110 in the decision on whether to use an AI / ML functionality (or which AI / ML functionality shall be activated). For example, the system might have changed (i.e., channel or the first apparatus 110 status may have changed) and it might differ from the conditions when the AI / ML functionality was trained. In this case, the first apparatus 110 may still assist the network by providing the accuracy of the AI / ML functionality without re-training it. Similarly to the example before, the first apparatus 110 is not allowed to transmit any other UAI message while the timer is running at 530 and the accuracy of the model has been changed.

[0148] FIG. 6 illustrates another signaling flow 600 for accuracy information transmission according to some example embodiments of the present disclosure. The signaling flow 600 involves the first apparatus 110 and the second apparatus 120 in FIG. 1. For purpose of illustration, the signaling flow 600 will be described with respect to FIG. 1. The signaling flow 600 shows an example of configuration, acquisition of accuracy, value, update and storage of accuracy values. The signaling flow 600 shows operations required to update the functionality accuracy and Store functionality accuracy(ies) for each AI / ML model or logical AI / ML model(s). Some details of the inference and monitoring operations are added to provide the context.

[0149] In operation, the first apparatus 110 receives the RRCReconfiguration including one or more CSI-ReportConfig, accuracy calculation and event trigger configuration. The first apparatus 110 monitors (615) or measures RS of one or more Set A and / or Set B beam sets.

[0150] For each of the configured monitored functionality the first apparatus 110 proceeds by performing (622) inference based on the RS measurement(s) and computing (624) accuracy based on inference output(s) and the ground truth value(s). Moreover, for each of the activated functionality the first apparatus 110 proceeds to perform (632) inference based on the RS measurement s).

[0151] When the second apparatus 120 computes the accuracy, the second apparatus 120 may receive (634) the measurements report including prediction and receive (636) the CSI measurements report for monitoring. The second apparatus 120 may compute (638) the accuracy based-on inference output(s) and the ground truth value(s). In one variant, the second apparatus 120 may transmit (640) the accuracy value to the first apparatus 110. In another variant, when the first apparatus 110 computes the accuracy, the first apparatus 110 may compute (643) the accuracy based-on inference output(s) and the ground truth value(s).

[0152] Based on above operations, the first apparatus 110 may update (650) the functionality accuracy. Based on the updated functionality accuracy value, the first apparatus 110 may store (660) functionality accuracy(ies) for each AI / ML model or logical AI / ML model(s).

[0153] FIG. 7 illustrates another signaling flow 700 for accuracy information transmission according to some example embodiments of the present disclosure. The signaling flow 700 involves the first apparatus 110 and the second apparatus 120 in FIG. 1. For purpose of illustration, the signaling flow 700 will be described with respect to FIG. 1.

[0154] In some example embodiments, the first apparatus 110 may update (710) the accuracy of the functionality X. The first apparatus 110 may detect (720) or check any of the configured event triggers. The first apparatus 110 may generates a UAI message based on any of the configured event triggers. The UAI message contains the accuracy information of the functionality X. The first apparatus 110 may transmit (730) the UAI message to the second apparatus 120.

[0155] FIG. 8 illustrates another signaling flow 800 for accuracy information transmission according to some example embodiments of the present disclosure. The signaling flow 800 involves the first apparatus 110 and the second apparatus 120 in FIG. 1. For purpose of illustration, the signaling flow 800 will be described with respect to FIG. 1.

[0156] In some example embodiments, the first apparatus 110 may update (810) the accuracy of the functionality X. The first apparatus 110 may detect (820) or check any of the configured event triggers.

[0157] If a functionality reporting event was triggered, the first apparatus 110 may add (830) accuracy for functionality X into the report. The first apparatus 110 may start (840) a timer when the functionality accuracy is updated. While the timer is running, for each configured and monitored functionality, the first apparatus 110 may repeat the followings: i) update (850) accuracy of the functionality X+i , ii) detect or check (860) any of the configured event triggers, iii) if event triggered, add (870) the accuracy of the functionality X+i to the report and iv) increment (880) the counter (such as i) indexing all the functionalities. At the stop (890) of the functionality accuracy report timer, the first apparatus 110 may transmit (895) a UAI message including the accuracy of functionalities which triggered events.

[0158] In order to solve at least part of the above problems or other potential problems, another solution on accuracy information transmission is proposed. According to example embodiments, a second apparatus (for example, a network device) transmits, to a first apparatus (such as a terminal device), at least one of: an indication of supporting forwarding accuracy information of a functionality from a first cell to a second cell, or a configuration of enabling partial reporting of the accuracy information. The partial reporting allows for excluding a partial of the accuracy information from an assistance information message. A handover is performed by the first apparatus from the first cell to the second cell. If a difference between first accuracy information of the functionality before the handover and second accuracy information of the functionality after the handover is less than or equal to a threshold, the first apparatus excludes the second accuracy information from the assistance information message.

[0159] In this manner, if the accuracy information remains the same after the handover, the first apparatus may exclude the accuracy information from the assistance information message. The signaling overhead can thus be reduced.

[0160] FIG. 9 illustrates another signaling flow 900 for accuracy information transmission according to some example embodiments of the present disclosure. The signaling flow 900 involves the first apparatus 110 and the second apparatus 120 in FIG. 1. For purpose of illustration, the signaling flow 900 will be described with respect to FIG. 1.

[0161] In operation, the first apparatus 110 may perform (910) a handover from a first cell to a second cell. For example, the second cell may be associated with the second apparatus 120. The first cell and the second cell are neighbouring cells. As used herein, the first cell may be referred to as a source cell. The second cell may be referred to as a target cell.

[0162] The second apparatus 120 transmit (920), to the first apparatus 110, at least one of: an indication of supporting forwarding accuracy information of a functionality from a first cell to a second cell, or a configuration of enabling partial reporting of the accuracy information. The partial reporting allows for excluding a partial of the accuracy information from an assistance information message. For example, the whole accuracy information may include accuracies or accuracy information of a plurality of functionalities. A partial of the whole accuracy information such as at least one accuracy or accuracy information of at least one functionality of the plurality of functionalities may be excluded from the assistance information message. The first apparatus 110 receives (930) the at least one of the indication or the configuration. By way of example, the at least one of the indication or the configuration may be received from the second apparatus 120 via the second cell. The indication and / or the configuration may be transmitted via RRC or any other suitable signaling.

[0163] The first apparatus 110 may determine (940) whether a difference between first accuracy information of the functionality before the handover and second accuracy information of the functionality after the handover is less than or equal to a threshold. The threshold may be predefined, or configured by the second apparatus 120. If the difference is less than or equal to the threshold, the first apparatus 110 may exclude the second accuracy information from the assistance information message such as UAI message. Otherwise, if the difference is larger than the threshold, the first apparatus 110 may include the second accuracy information into the assistance information message. The first apparatus 110 may transmit (950) the assistance information message to the second apparatus 120. The second apparatus 120 receives (960) the assistance information message.

[0164] In some example embodiments, the first cell and the second cell have same configuration information. For example, the configuration information may include at least one of an associated identifier, a transmitting beam shape, or a transmitting beams order.

[0165] In some example embodiments, if the first cell and the second cell have same configuration information, the second apparatus 120 may transmit the indication and / or the configuration to the first apparatus 110. In other words, if the target cell and source cell have same configuration (e.g. associate ID, Tx beam shape, Tx beams order), the target cell may configure the first apparatus 110 with delta reporting of AI / ML functionality accuracy information in UAI message.

[0166] In some example embodiments, the first apparatus 110 may prioritize the transmission of the assistance information message over further data transmission after the handover.

[0167] In some example embodiments, the first apparatus 110 may receive, from the second apparatus 120, a further configuration indicating to prioritize the transmission of the assistance information message over further data transmission after the handover. That is, the first apparatus 110 may be configured to prioritize the transmission of AI / ML functionality applicability information (including accuracy information) after the handover (HO), e g., in HO Complete.

[0168] In some example embodiments, the functionality is based on an ML model, and the accuracy information comprises at least one of: a prediction accuracy of the ML model, a difference between a predicted value of the functionality and a ground truth value, or a value associated with an implementation of the ML model.

[0169] In some example embodiments, the second apparatus 120 may receive, at the second cell from the first cell, the first accuracy information of the functionality associated with the first cell. If the second accuracy information is excluded from the assistance information message, the second apparatus 120 may determine the second accuracy information based on the first accuracy information.

[0170] In some example embodiments, the second apparatus 120 may receive, at the second cell from the first apparatus, the assistance information message including the second accuracy information of the functionality. The second apparatus 120 may transmit, at the second cell to at least one neighboring cell of the second cell, the second accuracy information of the functionality.

[0171] In this way, the second apparatus 120 such as the network may coordinate configuration for transmitting accuracy information among neighboring cells in HO scenarios. The source cell may forward the accuracy information of AI / ML functionalities received from the first apparatus 120 with UAI message to target cells. With the delta accuracy information transmission, the signaling overhead can be reduced.

[0172] It is to be understood that although there is a single first apparatus 110 and a single second apparatus shown in FIG. 2A, FIG. 2B, FIG. 3 and FIG. 6-FIG. 9, in some example embodiments, there may be a plurality of first apparatuses 110 and / or a plurality of second apparatuses 120. For purpose of discussion, some example embodiments are described where the first apparatus 110 is implemented as a terminal device and the second apparatus 120 is implemented as a network device.

[0173] It would be appreciated that some example specifications and embodiments are provided above, and the detailed description may be varied. It is to be understood that these signaling flows 200, 250, 300, 600, 700, 800, 900, and / or the process 500, can be used in any suitable combinations. In this way, the accuracy or applicability of the AI / ML based functionality can be informed to the network via UAI message.

[0174] FIG. 10 shows a flowchart of an example method 1000 implemented at a first apparatus in accordance with some example embodiments of the present disclosure. For the purpose of discussion, the method 1000 will be described from the perspective of the first apparatus 110 in FIG. 1.

[0175] At block 1010, the first apparatus 110 receives, from a second apparatus, configuration information comprising a configuration of at least one functionality and a further configuration enabling a transmission of an assistance information message. The further configuration indicates to include in the assistance information message at least one of: at least one accuracy information of the at least one functionality, or at least one applicability indication of the at least one functionality based on the at least one accuracy information.

[0176] At block 1020, the first apparatus 110 determines whether at least one event triggering a transmission of the assistance information message happens and at least one condition for transmitting the assistance information message is satisfied.

[0177] At block 1030, in accordance with a determination that the at least one event happens and the at least one condition is satisfied, the first apparatus 110 transmits to the second apparatus, the assistance information message based on the configuration information, the assistance information message comprising at least one of: the at least one accuracy information, or the at least one applicability indication of the at least one functionality based on the at least one accuracy information.

[0178] In some example embodiments, the at least one functionality is based on a machine learning (ML) model, and the accuracy information comprises at least one of: a prediction accuracy of the ML model, a difference between a predicted value of the at least one functionality and a ground truth value, or a value associated with an implementation of the ML model.

[0179] In some example embodiments, the at least one functionality comprises a beam prediction based on the ML model, and the prediction accuracy comprises at least one of: a percentage of instances in which at least one predicted beam is the same as at least one ground truth best beam, a percentage of instances in which at least one ground truth signal strength of the at least one predicted beam is larger than or equal to a threshold, and wherein the difference between the predicted value and the ground truth value comprises at least one of: a signal strength of a predicted beam and a signal strength of a ground truth best beam, or a difference between a predicted signal strength of the predicted beam and a measured signal strength of the ground truth best beam.

[0180] In some example embodiments, the method 1000 further comprises: determining the at least one applicability indication of the at least one functionality based on the at least one accuracy information of the at least one functionality.

[0181] In some example embodiments, the further configuration comprises at least one of: an indication of including the at least one accuracy information in the assistance information message, an indication of including the at least one applicability indication in the assistance information message, an indication of including at least one conditionally applicable indication in the assistance information message, wherein the at least one conditionally applicable indication indicates an ongoing accuracy evaluation of the at least one functionality, the at least one event triggering a transmission of the assistance information message happens, the at least one condition for transmitting the assistance information message is satisfied, or a timer associated with the transmission of the assistance information message.

[0182] In some example embodiments, the further configuration comprises the at least one event triggering the transmission of the assistance information message, the at least one event comprising at least one of: a first event that a machine learning (ML) model associated with the at least one functionality is changed, a second event that the first apparatus moves from a first cell to a second cell, a third event that an indication from the second apparatus indicates a change of network-side associated identifier associated with the at least one functionality, a fourth event that at least one of a measured signal strength of a serving cell or a measured signal strength of at least one neighboring cell meets a condition for neighboring cells, or a fifth event that the first apparatus fails to use the ML model due to lack of processing resource.

[0183] In some example embodiments, the change of network-side associated identifier indicates a change of a transmitting beam property of the second apparatus.

[0184] In some example embodiments, the method 1000 further comprises: in accordance with a determination that at least one accuracy evaluation of the at least one functionality is ongoing, including the at least one conditionally applicable indication in the assistance information message.

[0185] In some example embodiments, the method 1000 further comprises: in response to the at least one event associated with a first functionality of the plurality of functionalities, adding at least one first accuracy information for first applicability indication of the first functionality in the assistance information message; and starting a timer associated with the transmission of the assistance information message; based on the timer being running, updating the assistance information message by detecting the at least one event for the plurality of functionalities; and based on the timer expiring, transmitting the updated assistance information message to the second apparatus.

[0186] In some example embodiments, at least one condition for transmitting the assistance information message comprises a condition that a change of accuracy information of a machine learning (ML) model associated with the at least one functionality is larger than or equal to a threshold.

[0187] In some example embodiments, the method 1000 further comprises: determining the at least one accuracy information based on a monitoring process for the at least one functionality. The monitoring process compares at least one measured reference signal resource and at least one predicted reference signal resource obtained by the at least one functionality.

[0188] In some example embodiments, the method 1000 further comprises: receiving, from the second apparatus, an activation or deactivation signal for the at least one functionality. The activation or deactivation signal is determined based on at least one of: the at least one accuracy information included in the assistance information message, or the at least one applicability indication based on the at least one accuracy information included in the assistance information message.

[0189] In some example embodiments, the assistance information message comprises a user equipment (UE) assistance information (UAI) message.

[0190] FIG. 11 shows a flowchart of an example method 1100 implemented at a second apparatus in accordance with some example embodiments of the present disclosure. For the purpose of discussion, the method 1100 will be described from the perspective of the second apparatus 120 in FIG. 1.

[0191] At block 1110, the second apparatus 120 transmits, to a first apparatus, configuration information comprising a configuration of at least one functionality and a further configuration enabling a transmission of an assistance information message, the further configuration indicating to include in the assistance information message at least one of: at least one accuracy information of the at least one functionality, or at least one applicability indication of the at least one functionality based on the at least one accuracy information.

[0192] At block 1120, the second apparatus 120 receives, from the first apparatus, the assistance information message comprising at least one of: the at least one accuracy information, or the at least one applicability indication of the at least one functionality based on the at least one accuracy information.

[0193] In some example embodiments, the at least one functionality is based on a machine learning (ML) model, and the accuracy information comprises at least one of: a prediction accuracy of the ML model, a difference between a predicted value of the at least one functionality and a ground truth value, or a value associated with an implementation of the ML model.

[0194] In some example embodiments, the at least one functionality comprises a beam prediction based on the ML model, and the prediction accuracy comprises at least one of: a percentage of instances in which at least one predicted beam is the same as at least one ground truth best beam, a percentage of instances in which at least one ground truth signal strength of the at least one predicted beam is larger than or equal to a threshold, and wherein the difference between the predicted value and the ground truth value comprises at least one of: a signal strength of a predicted beam and a signal strength of a ground truth best beam, or a difference between a predicted signal strength of the predicted beam and a measured signal strength of the ground truth best beam.

[0195] In some example embodiments, the further configuration comprises at least one of: an indication of including the at least one accuracy information in the assistance information message, an indication of including the at least one applicability indication in the assistance information message, an indication of including at least one conditionally applicable indication in the assistance information message, wherein the at least one conditionally applicable indication indicates an ongoing accuracy evaluation of the at least one functionality, the at least one event triggering a transmission of the assistance information message happens, the at least one condition for transmitting the assistance information message, or a timer associated with the transmission of the assistance information message.

[0196] In some example embodiments, the further configuration comprises the at least one event triggering the transmission of the assistance information message, the at least one event comprising at least one of: a first event that a machine learning (ML) model associated with the at least one functionality is changed, a second event that the first apparatus moves from a first cell to a second cell, a third event that an indication from the second apparatus indicates a change of network-side associated identifier associated with the at least one functionality, a fourth event that at least one of a measured signal strength of a serving cell or a measured signal strength of at least one neighboring cell meets a condition for neighboring cells, or a fifth event that the first apparatus fails to use the ML model due to lack of processing resource.

[0197] In some example embodiments, at least one condition for transmitting the assistance information message comprises a condition that a change of accuracy information of a machine learning (ML) model associated with the at least one functionality is larger than or equal to a threshold.

[0198] In some example embodiments, the method 1100 further comprises: transmitting, to the first apparatus, at least one activation or deactivation signal for the at least one functionality based on the assistance information message.

[0199] In some example embodiments, the method 1100 further comprises: in accordance with a determination that the at least one accuracy information indicates an accuracy larger than or equal to a threshold or the at least one applicability indication indicates that the at least one functionality is applicable, transmitting the at least one activation signal for the at least one functionality to the first apparatus; and in accordance with a determination that the at least one accuracy information indicates an accuracy less than the threshold or the at least one applicability indication indicates that the at least one functionality is inapplicable, transmitting the at least one deactivation signal for the at least one functionality to the first apparatus.

[0200] In some example embodiments, the assistance information message comprises a user equipment (UE) assistance information (UAI) message.

[0201] In some example embodiments, a first apparatus capable of performing any of the method 1000 (for example, the first apparatus 110 in FIG. 1) may comprise means for performing the respective operations of the method 1000. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module. The first apparatus may be implemented as or included in the first apparatus 110 in FIG. 1.

[0202] In some example embodiments, the first apparatus comprises means for receiving, from a second apparatus, configuration information comprising a configuration of at least one functionality and a further configuration enabling a transmission of an assistance information message, the further configuration indicating to include in the assistance information message at least one of: at least one accuracy information of the at least one functionality, or at least one applicability indication of the at least one functionality based on the at least one accuracy information; means for determining whether at least one event triggering a transmission of the assistance information message happens and at least one condition for transmitting the assistance information message is satisfied; and means for in accordance with a determination that the at least one event happens and the at least one condition is satisfied, transmitting to the second apparatus, the assistance information message based on the configuration information, the assistance information message comprising at least one of the at least one accuracy information, or the at least one applicability indication of the at least one functionality based on the at least one accuracy information.

[0203] In some example embodiments, the at least one functionality is based on a machine learning (ML) model, and the accuracy information comprises at least one of: a prediction accuracy of the ML model, a difference between a predicted value of the at least one functionality and a ground truth value, or a value associated with an implementation of the ML model.

[0204] In some example embodiments, the at least one functionality comprises a beam prediction based on the ML model, and the prediction accuracy comprises at least one of: a percentage of instances in which at least one predicted beam is the same as at least one ground truth best beam, a percentage of instances in which at least one ground truth signal strength of the at least one predicted beam is larger than or equal to a threshold, and wherein the difference between the predicted value and the ground truth value comprises at least one of: a signal strength of a predicted beam and a signal strength of a ground truth best beam, or a difference between a predicted signal strength of the predicted beam and a measured signal strength of the ground truth best beam.

[0205] In some example embodiments, the first apparatus further comprises: means for determining the at least one applicability indication of the at least one functionality based on the at least one accuracy information of the at least one functionality.

[0206] In some example embodiments, the further configuration comprises at least one of: an indication of including the at least one accuracy information in the assistance information message, an indication of including the at least one applicability indication in the assistance information message, an indication of including at least one conditionally applicable indication in the assistance information message, wherein the at least one conditionally applicable indication indicates an ongoing accuracy evaluation of the at least one functionality, the at least one event triggering a transmission of the assistance information message happens, the at least one condition for transmitting the assistance information message is satisfied, or a timer associated with the transmission of the assistance information message. |0207]In some example embodiments, the further configuration comprises the at least one event triggering the transmission of the assistance information message, the at least one event comprising at least one of: a first event that a machine learning (ML) model associated with the at least one functionality is changed, a second event that the first apparatus moves from a first cell to a second cell, a third event that an indication from the second apparatus indicates a change of network-side associated identifier associated with the at least one functionality, a fourth event that at least one of a measured signal strength of a serving cell or a measured signal strength of at least one neighboring cell meets a condition for neighboring cells, or a fifth event that the first apparatus fails to use the ML model due to lack of processing resource.

[0208] In some example embodiments, the change of network-side associated identifier indicates a change of a transmitting beam property of the second apparatus.

[0209] In some example embodiments, the first apparatus further comprises: means for in accordance with a determination that at least one accuracy evaluation of the at least one functionality is ongoing, including the at least one conditionally applicable indication in the assistance information message.

[0210] In some example embodiments, the first apparatus further comprises: in response to the at least one event associated with a first functionality of the plurality of functionalities, means for adding at least one first accuracy information for first applicability indication of the first functionality in the assistance information message; and means for starting a timer associated with the transmission of the assistance information message; means for based on the timer being running, updating the assistance information message by detecting the at least one event for the plurality of functionalities; and means for based on the timer expiring, transmitting the updated assistance information message to the second apparatus. [021 l]In some example embodiments, at least one condition for transmitting the assistance information message comprises a condition that a change of accuracy information of a machine learning (ML) model associated with the at least one functionality is larger than or equal to a threshold.

[0212] In some example embodiments, the first apparatus further comprises: means for determining the at least one accuracy information based on a monitoring process for the at least one functionality. The monitoring process compares at least one measured reference signal resource and at least one predicted reference signal resource obtained by the at least one functionality.

[0213] In some example embodiments, the first apparatus further comprises: means for receiving, from the second apparatus, an activation or deactivation signal for the at least one functionality, wherein the activation or deactivation signal is determined based on at least one of: the at least one accuracy information included in the assistance information message, or the at least one applicability indication included in the assistance information message.

[0214] In some example embodiments, the assistance information message comprises a user equipment (UE) assistance information (UAI) message.

[0215] In some example embodiments, a second apparatus capable of performing any of the method 1100 (for example, the second apparatus 120 in FIG. 1) may comprise means for performing the respective operations of the method 1100. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module. The second apparatus may be implemented as or included in the second apparatus 120 in FIG. 1.

[0216] In some example embodiments, the second apparatus comprises means for transmitting, to a first apparatus, configuration information comprising a configuration of at least one functionality and a further configuration enabling a transmission of an assistance information message, the further configuration indicating to include in the assistance information message at least one of: at least one accuracy information of the at least one functionality, or at least one applicability indication of the at least one functionality based on the at least one accuracy information; and means for receiving, from the first apparatus, the assistance information message comprising at least one of: the at least one accuracy information, or the at least one applicability indication of the at least one functionality based on the at least one accuracy information.

[0217] In some example embodiments, the at least one functionality is based on a machine learning (ML) model, and the accuracy information comprises at least one of: a prediction accuracy of the ML model, a difference between a predicted value of the at least one functionality and a ground truth value, or a value associated with an implementation of the ML model.

[0218] In some example embodiments, the at least one functionality comprises a beam prediction based on the ML model, and the prediction accuracy comprises at least one of: a percentage of instances in which at least one predicted beam is the same as at least one ground truth best beam, a percentage of instances in which at least one ground truth signal strength of the at least one predicted beam is larger than or equal to a threshold, and wherein the difference between the predicted value and the ground truth value comprises at least one of: a signal strength of a predicted beam and a signal strength of a ground truth best beam, or a difference between a predicted signal strength of the predicted beam and a measured signal strength of the ground truth best beam.

[0219] In some example embodiments, the further configuration comprises at least one of: an indication of including the at least one accuracy information in the assistance information message, an indication of including the at least one applicability indication in the assistance information message, an indication of including at least one conditionally applicable indication in the assistance information message, wherein the at least one conditionally applicable indication indicates an ongoing accuracy evaluation of the at least one functionality, the at least one event triggering a transmission of the assistance information message happens, the at least one condition for transmitting the assistance information message, or a timer associated with the transmission of the assistance information message.

[0220] In some example embodiments, the further configuration comprises the at least one event triggering the transmission of the assistance information message, the at least one event comprising at least one of: a first event that a machine learning (ML) model associated with the at least one functionality is changed, a second event that the first apparatus moves from a first cell to a second cell, a third event that an indication from the second apparatus indicates a change of network-side associated identifier associated with the at least one functionality, a fourth event that at least one of a measured signal strength of a serving cell or a measured signal strength of at least one neighboring cell meets a condition for neighboring cells, or a fifth event that the first apparatus fails to use the ML model due to lack of processing resource.

[0221] In some example embodiments, at least one condition for transmitting the assistance information message comprises a condition that a change of accuracy information of a machine learning (ML) model associated with the at least one functionality is larger than or equal to a threshold.

[0222] In some example embodiments, the second apparatus further comprises: means for transmitting, to the first apparatus, at least one activation or deactivation signal for the at least one functionality based on the assistance information message.

[0223] In some example embodiments, the second apparatus further comprises: means for in accordance with a determination that the at least one accuracy information indicates an accuracy larger than or equal to a threshold or the at least one applicability indication indicates that the at least one functionality is applicable, transmitting the at least one activation signal for the at least one functionality to the first apparatus; and means for in accordance with a determination that the at least one accuracy information indicates an accuracy less than the threshold or the at least one applicability indication indicates that the at least one functionality is inapplicable, transmitting the at least one deactivation signal for the at least one functionality to the first apparatus.

[0224] In some example embodiments, the assistance information message comprises a user equipment (UE) assistance information (UAI) message.

[0225] FIG. 12 shows a flowchart of an example method 1200 implemented at a first apparatus in accordance with some example embodiments of the present disclosure. For the purpose of discussion, the method 1200 will be described from the perspective of the first apparatus 110 in FIG. 1.

[0226] At block 1210, the first apparatus 110 receives, from a second apparatus, configuration information comprising a configuration of at least one functionality and a further configuration comprising at least one criterion for reporting at least one applicability indication of the at least one functionality, wherein the at least one applicability indication is based on at least one accuracy information of the at least one functionality.

[0227] At block 1220, in accordance with a determination that the at least one criterion is satisfied, the first apparatus 110 determines the at least one applicability indication based on the at least one accuracy information of the at least one functionality.

[0228] At block 1230, the first apparatus 110 transmits, to the second apparatus, the assistance information message including the at least one applicability indication based on the at least one accuracy information.

[0229] In some example embodiments, the at least one functionality is based on a machine learning (ML) model, and the at least one criterion comprises at least one of: a first criterion that a prediction accuracy of the ML model is larger than a first threshold for prediction accuracy, a second criterion that an error between measurements of a signal strength of a predicted beam of the ML model and a ground-truth best beam is less than or equal to a second threshold for signal strength error, a third criterion that a difference between a prediction of a signal strength of a predicted beam of the ML model and a measurement of a signal strength of a ground-truth best beam is less than or equal to a third threshold for predicted signal strength error, or a fourth criterion that a timer associated with reporting the at least one applicability indication expires or is stopped.

[0230] In some example embodiments, the further configuration comprises at least one of: a first threshold for prediction accuracy, a second threshold for signal strength error, a third threshold for predicted signal strength error, or a timer associated with reporting the at least one applicability indication.

[0231] In some example embodiments, the method 1200 further comprises: in response to transmitting the assistance information message including the at least one applicability indication based on the at least one accuracy information, initiating the timer associated with the at least one functionality; and stopping the timer based on a change of at least one applicability of the at least one functionality, wherein the change of the at least one applicability is based on at least one of: a change of a network-side associated identifier associated with the at least one functionality, or a change of a radio condition.

[0232] In some example embodiments, the method 1200 further comprises: based on the timer being running, refrain from transmitting the assistance information message including the at least one applicability indication based on the at least one accuracy information to the second apparatus.

[0233] In some example embodiments, the change of network-side associated identifier indicates a change of a transmitting beam property of the second apparatus.

[0234] In some example embodiments, the further configuration further comprises at least one event triggering the transmission of the assistance information message, the at least one event comprising at least one of: a first event that a machine learning (ML) model associated with the at least one functionality is changed, a second event that the first apparatus moves from a first cell to a second cell, a third event that at least one of a measured signal strength of a serving cell or a measured signal strength of at least one neighboring cell meets a condition for neighboring cells, or a fourth event that the first apparatus fails to use the ML model due to lack of processing resource.

[0235] In some example embodiments, the condition for neighboring cells comprises at least one of: a condition that the measured signal strength of a serving cell is smaller than a sum of the measured signal strength of at least one neighboring cell and a threshold on the signal strength, or a condition that a prediction accuracy of the ML model applied on the measured signal strength of a serving cell is smaller than the maximum of the prediction accuracy of the ML model applied to the measured signal strength of at least one neighboring cell and a threshold on the prediction accuracy.

[0236] In some example embodiments, the method 1200 further comprises: in response to a timer associated with reporting the at least one applicability indication based on the at least one accuracy information expiring, transmitting a further assistance information message to the second apparatus, the further assistance information comprising at least one updated applicability indication of the at least one functionality based on at least one of the following conditions being satisfied: a first condition that at least one applicability of the at least one functionality is changed based on a change of a configuration or property of the first apparatus, or a second condition that the at least one event triggering the transmission of the assistance information message happens.

[0237] In some example embodiments, the method 1200 further comprises: in response to a timer associated with reporting the at least one applicability indication based on the at least one accuracy information expiring, refraining from transmitting the assistance information message including the at least one applicability indication based on at least one of the following conditions being satisfied: a first condition that the at least one applicability indication of the at least one functionality is transmitted by a reconfiguration message response, a second condition that the at least one applicability indication is same with that included in a previous assistance information message, a third condition that the at least one functionality is not supported by a configuration of the second apparatus, or a fourth condition that the at least one functionality is not supported by capability of the first apparatus.

[0238] In some example embodiments, the method 1200 further comprises: whiling a timer associated with reporting the at least one applicability indication based on the at least one accuracy information is running, detecting that a first applicability indication of a first functionality and a second applicability indication of a second functionality change; and including the changed first applicability indication and the changed second applicability indication in the assistance information message; and in response to the timer expiring, transmitting to the second apparatus, the assistance information message including the changed first applicability indication and the changed second applicability indication.

[0239] In some example embodiments, the method 1200 further comprises: determining the at least one accuracy information based on a monitoring process for the at least one functionality, wherein the monitoring process compares at least one measured reference signal resource and at least one predicted reference signal resource obtained by the at least one functionality; and determining the at least one applicability indication based on the at least one accuracy information.

[0240] In some example embodiments, the method 1200 further comprises: receiving, from the second apparatus, an activation or deactivation signal for the at least one functionality, the activation or deactivation signal being determined based on the at least one applicability indication based on the at least one accuracy information in the assistance information message.

[0241] In some example embodiments, the assistance information message comprises a user equipment (UE) assistance information (UAI) message.

[0242] FIG. 13 shows a flowchart of an example method 1300 implemented at a second apparatus in accordance with some example embodiments of the present disclosure. For the purpose of discussion, the method 1300 will be described from the perspective of the second apparatus 120 in FIG. 1.

[0243] At block 1310, the second apparatus 120 transmits, to a first apparatus, configuration information comprising a configuration of at least one functionality and a further configuration comprising at least one criterion for reporting at least one applicability indication of the at least one functionality, wherein the at least one applicability indication is based on at least one accuracy information of the at least one functionality.

[0244] At block 1320, the second apparatus 120 receives, from the first apparatus, the assistance information message including the at least one applicability indication based on the at least one accuracy information.

[0245] In some example embodiments, the at least one functionality is based on a machine learning (ML) model, and the at least one criterion comprises at least one of: a first criterion that a prediction accuracy of the ML model is larger than a first threshold for prediction accuracy, a second criterion that an error between measurements of a signal strength of a predicted beam of the ML model and a ground-truth best beam is less than or equal to a second threshold for signal strength error, a third criterion that a difference between a prediction of a signal strength of a predicted beam of the ML model and a measurement of a signal strength of a ground-truth best beam is less than or equal to a third threshold for predicted signal strength error, or a fourth criterion that a timer associated with reporting the at least one applicability indication expires or is stopped.

[0246] In some example embodiments, the further configuration comprises at least one of: a first threshold for prediction accuracy, a second threshold for signal strength error, a third threshold for predicted signal strength error, or a tinier associated with reporting the at least one applicability indication.

[0247] In some example embodiments, the further configuration further comprises at least one event triggering the transmission of the assistance information message, the at least one event comprising at least one of: a first event that a machine learning (ML) model associated with the at least one functionality is changed, a second event that the first apparatus moves from a first cell to a second cell, a third event that at least one of a measured signal strength of a serving cell or a measured signal strength of at least one neighboring cell meets a condition for neighboring cells, or a fourth event that the first apparatus fails to use the ML model due to lack of processing resource.

[0248] In some example embodiments, the method 1300 further comprises: transmitting, to the first apparatus, an activation or deactivation signal for the at least one functionality based on the at least one applicability indication in the assistance information message.

[0249] In some example embodiments, the method 1300 further comprises: in accordance with a determination that the at least one applicability indication based on the at least one accuracy information indicates that the at least one functionality is applicable, transmitting the activation signal for the at least one functionality to the first apparatus; and in accordance with a determination that the at least one applicability indication based on the at least one accuracy information indicates that the at least one functionality is inapplicable, transmitting the deactivation signal for the at least one functionality to the first apparatus.

[0250] In some example embodiments, the assistance information message comprises a user equipment (UE) assistance information (UAI) message.

[0251] In some example embodiments, a first apparatus capable of performing any of the method 1200 (for example, the first apparatus 110 in FIG. 1) may comprise means for performing the respective operations of the method 1200. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module. The first apparatus may be implemented as or included in the first apparatus 110 in FIG. 1.

[0252] In some example embodiments, the first apparatus comprises means for receiving, from a second apparatus, configuration information comprising a configuration of at least one functionality and a further configuration comprising at least one criterion for reporting at least one applicability indication of the at least one functionality, wherein the at least one applicability indication is based on at least one accuracy information of the at least one functionality; and means for in accordance with a determination that the at least one criterion is satisfied, determining the at least one applicability indication based on the at least one accuracy information of the at least one functionality; and means for transmitting, to the second apparatus, the assistance information message including the at least one applicability indication based on the at least one accuracy information.

[0253] In some example embodiments, the at least one functionality is based on a machine learning (ML) model, and the at least one criterion comprises at least one of: a first criterion that a prediction accuracy of the ML model is larger than a first threshold for prediction accuracy, a second criterion that an error between measurements of a signal strength of a predicted beam of the ML model and a ground-truth best beam is less than or equal to a second threshold for signal strength error, a third criterion that a difference between a prediction of a signal strength of a predicted beam of the ML model and a measurement of a signal strength of a ground-truth best beam is less than or equal to a third threshold for predicted signal strength error, or a fourth criterion that a timer associated with reporting the at least one applicability indication expires or is stopped.

[0254] In some example embodiments, the further configuration comprises at least one of a first threshold for prediction accuracy, a second threshold for signal strength error, a third threshold for predicted signal strength error, or a timer associated with reporting the at least one applicability indication.

[0255] In some example embodiments, the first apparatus further comprises: means for in response to transmitting the assistance information message including the at least one applicability indication based on the at least one accuracy information, initiating the timer associated with the at least one functionality; and means for stopping the timer based on a change of at least one applicability of the at least one functionality, wherein the change of the at least one applicability is based on at least one of: a change of a network-side associated identifier associated with the at least one functionality, or a change of a radio condition.

[0256] In some example embodiments, the first apparatus further comprises: based on the timer being running, refrain from transmitting the assistance information message including the at least one applicability indication based on the at least one accuracy information to the second apparatus.

[0257] In some example embodiments, the change of network-side associated identifier indicates a change of a transmitting beam property of the second apparatus.

[0258] In some example embodiments, the further configuration further comprises at least one event triggering the transmission of the assistance information message, the at least one event comprising at least one of: a first event that a machine learning (ML) model associated with the at least one functionality is changed, a second event that the first apparatus moves from a first cell to a second cell, a third event that at least one of a measured signal strength of a serving cell or a measured signal strength of at least one neighboring cell meets a condition for neighboring cells, or a fourth event that the first apparatus fails to use the ML model due to lack of processing resource.

[0259] In some example embodiments, the condition for neighboring cells comprises at least one of: a condition that the measured signal strength of a serving cell is smaller than a sum of the measured signal strength of at least one neighboring cell and a threshold on the signal strength, or a condition that a prediction accuracy of the ML model applied on the measured signal strength of a serving cell is smaller than the maximum of the prediction accuracy of the ML model applied to the measured signal strength of at least one neighboring cell and a threshold on the prediction accuracy.

[0260] In some example embodiments, the first apparatus further comprises: means for in response to a timer associated with reporting the at least one applicability indication based on the at least one accuracy information expiring, transmitting a further assistance information message to the second apparatus, the further assistance information comprising at least one updated applicability indication of the at least one functionality based on at least one of the following conditions being satisfied: a first condition that at least one applicability of the at least one functionality is changed based on a change of a configuration or property of the first apparatus, or a second condition that the at least one event triggering the transmission of the assistance information message happens. [0261 ]In some example embodiments, the first apparatus further comprises: means for in response to a timer associated with reporting the at least one applicability indication based on the at least one accuracy information expiring, refraining from transmitting the assistance information message including the at least one applicability indication based on at least one of the following conditions being satisfied: a first condition that the at least one applicability indication of the at least one functionality is transmitted by a reconfiguration message response, a second condition that the at least one applicability indication is same with that included in a previous assistance information message, a third condition that the at least one functionality is not supported by a configuration of the second apparatus, or a fourth condition that the at least one functionality is not supported by capability of the first apparatus.

[0262] In some example embodiments, the first apparatus further comprises: means for whiling a timer associated with reporting the at least one applicability indication based on the at least one accuracy information is running, means for detecting that a first applicability indication of a first functionality and a second applicability indication of a second functionality change; and means for including the changed first applicability indication and the changed second applicability indication in the assistance information message; and means for in response to the timer expiring, transmitting to the second apparatus, the assistance information message including the changed first applicability indication and the changed second applicability indication.

[0263] In some example embodiments, the first apparatus further comprises: means for determining the at least one accuracy information based on a monitoring process for the at least one functionality, wherein the monitoring process compares at least one measured reference signal resource and at least one predicted reference signal resource obtained by the at least one functionality; and means for determining the at least one applicability indication based on the at least one accuracy information.

[0264] In some example embodiments, the first apparatus further comprises: means for receiving, from the second apparatus, an activation or deactivation signal for the at least one functionality, the activation or deactivation signal being determined based on the at least one applicability indication based on the at least one accuracy information in the assistance information message.

[0265] In some example embodiments, the assistance information message comprises a user equipment (UE) assistance information (UAI) message.

[0266] In some example embodiments, a second apparatus capable of performing any of the method 1300 (for example, the second apparatus 120 in FIG. 1) may comprise means for performing the respective operations of the method 1300. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module. The second apparatus may be implemented as or included in the second apparatus 120 in FIG. 1.

[0267] In some example embodiments, the second apparatus comprises means for transmitting, to a first apparatus, configuration information comprising a configuration of at least one functionality and a further configuration comprising at least one criterion for reporting at least one applicability indication of the at least one functionality, wherein the at least one applicability indication is based on at least one accuracy information of the at least one functionality; and means for receiving, from the first apparatus, the assistance information message including the at least one applicability indication based on the at least one accuracy information.

[0268] In some example embodiments, the at least one functionality is based on a machine learning (ML) model, and the at least one criterion comprises at least one of: a first criterion that a prediction accuracy of the ML model is larger than a first threshold for prediction accuracy, a second criterion that an error between measurements of a signal strength of a predicted beam of the ML model and a ground-truth best beam is less than or equal to a second threshold for signal strength error, a third criterion that a difference between a prediction of a signal strength of a predicted beam of the ML model and a measurement of a signal strength of a ground-truth best beam is less than or equal to a third threshold for predicted signal strength error, or a fourth criterion that a timer associated with reporting the at least one applicability indication expires or is stopped.

[0269] In some example embodiments, the further configuration comprises at least one of: a first threshold for prediction accuracy, a second threshold for signal strength error, a third threshold for predicted signal strength error, or a timer associated with reporting the at least one applicability indication.

[0270] In some example embodiments, the further configuration further comprises at least one event triggering the transmission of the assistance information message, the at least one event comprising at least one of: a first event that a machine learning (ML) model associated with the at least one functionality is changed, a second event that the first apparatus moves from a first cell to a second cell, a third event that at least one of a measured signal strength of a serving cell or a measured signal strength of at least one neighboring cell meets a condition for neighboring cells, or a fourth event that the first apparatus fails to use the ML model due to lack of processing resource.

[0271] In some example embodiments, the second apparatus further comprises: means for transmitting, to the first apparatus, an activation or deactivation signal for the at least one functionality based on the at least one applicability indication in the assistance information message.

[0272] In some example embodiments, the second apparatus further comprises: means for in accordance with a determination that the at least one applicability indication based on the at least one accuracy information indicates that the at least one functionality is applicable, transmitting the activation signal for the at least one functionality to the first apparatus; and means for in accordance with a determination that the at least one applicability indication based on the at least one accuracy information indicates that the at least one functionality is inapplicable, transmitting the deactivation signal for the at least one functionality to the first apparatus.

[0273] In some example embodiments, the assistance information message comprises a user equipment (UE) assistance information (UAI) message.

[0274] FIG. 14 shows a flowchart of an example method 1400 implemented at a first apparatus in accordance with some example embodiments of the present disclosure. For the purpose of discussion, the method 1400 will be described from the perspective of the first apparatus 110 in FIG. 1.

[0275] At block 1410, the first apparatus 110 receives, from a second apparatus, at least one of: an indication of supporting forwarding accuracy information of a functionality from a first cell to a second cell, or a configuration of enabling partial reporting of the accuracy information. The partial reporting allows for excluding a partial of the accuracy information from an assistance information message. A handover is performed by the first apparatus from the first cell to the second cell.

[0276] At block 1420, in accordance with a determination that a difference between first accuracy information of the functionality before the handover and second accuracy information of the functionality after the handover is less than or equal to a threshold, the first apparatus 110 excludes the second accuracy information from the assistance information message.

[0277] In some example embodiments, the method 1400 further comprises: in accordance with a determination that the difference between the first accuracy information and the second accuracy information is larger than the threshold, including the second accuracy information in the assistance information message; and transmitting the assistance information message to the second apparatus.

[0278] In some example embodiments, the method 1400 further comprises: prioritizing the transmission of the assistance information message over further data transmission after the handover.

[0279] In some example embodiments, the method 1400 further comprises: receiving, from the second apparatus, a further configuration indicating to prioritize the transmission of the assistance information message over further data transmission after the handover.

[0280] In some example embodiments, the first cell and the second cell have same configuration information, the configuration information comprising an associated identifier.

[0281] In some example embodiments, the associated identifier indicates a transmitting beam property of the second apparatus.

[0282] In some example embodiments, the functionality is based on a machine learning (ML) model, and the accuracy information comprises at least one of: a prediction accuracy of the ML model, a difference between a predicted value of the functionality and a ground truth value, or a value associated with an implementation of the ML model.

[0283] In some example embodiments, the at least one of the indication or the configuration is received from the second apparatus via the second cell.

[0284] In some example embodiments, the assistance information message comprises a user equipment (UE) assistance information (UAI) message.

[0285] FIG. 15 shows a flowchart of an example method 1500 implemented at a second apparatus in accordance with some example embodiments of the present disclosure. For the purpose of discussion, the method 1500 will be described from the perspective of the second apparatus 120 in FIG. 1.

[0286] At block 1510, the second apparatus 120 transmits, to a first apparatus, at least one of: an indication of supporting forwarding accuracy information of a functionality from a first cell to a second cell, or a configuration of enabling partial reporting of the accuracy information. The partial reporting allows for excluding a partial of the accuracy information from an assistance information message. A handover is performed by the first apparatus from the first cell to the second cell.

[0287] In some example embodiments, the method 1500 further comprises: transmitting, to the first apparatus, a further configuration indicating to prioritize the transmission of the assistance information message over further data transmission after the handover.

[0288] In some example embodiments, the method 1500 further comprises: in accordance with a determination that the first cell and the second cell have same configuration information, transmitting the at least one of the indication or the configuration to the first apparatus, wherein the configuration information comprises an associated identifier.

[0289] In some example embodiments, the associated identifier indicates a transmitting beam property of the second apparatus.

[0290] In some example embodiments, the method 1500 further comprises: receiving, at the second cell from the first cell, the first accuracy information of the functionality associated with the first cell; and in accordance with a determination that the second accuracy information is excluded from the assistance information message, determining the second accuracy information based on the first accuracy information.

[0291] In some example embodiments, the functionality is based on a machine learning (ML) model, and the accuracy information comprises at least one of: a prediction accuracy of the AI / ML model, a difference between a predicted value of the functionality and a ground truth value, or a value associated with an implementation of the ML model.

[0292] In some example embodiments, the at least one of the indication or the configuration is transmitted to the first apparatus via the second cell.

[0293] In some example embodiments, the method 1500 further comprises: receiving, at the second cell from the first apparatus, the assistance information message including the second accuracy information of the functionality; and transmitting, at the second cell to at least one neighboring cell of the second cell, the second accuracy information of the functionality.

[0294] In some example embodiments, the assistance information message comprises a user equipment (UE) assistance information (UAI) message.

[0295] In some example embodiments, a first apparatus capable of performing any of the method 1400 (for example, the first apparatus 110 in FIG. 1) may comprise means for performing the respective operations of the method 1400. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module. The first apparatus may be implemented as or included in the first apparatus 110 in FIG. 1.

[0296] In some example embodiments, the first apparatus comprises means for receiving, from a second apparatus, at least one of: an indication of supporting forwarding accuracy information of a functionality from a first cell to a second cell, or a configuration of enabling partial reporting of the accuracy information, wherein the partial reporting allows for excluding a partial of the accuracy information from an assistance information message, wherein a handover is performed by the first apparatus from the first cell to the second cell; and means for in accordance with a determination that a difference between first accuracy information of the functionality before the handover and second accuracy information of the functionality after the handover is less than or equal to a threshold, excluding the second accuracy information from the assistance information message.

[0297] In some example embodiments, the first apparatus further comprises: means for in accordance with a determination that the difference between the first accuracy information and the second accuracy information is larger than the threshold, including the second accuracy information in the assistance information message; and means for transmitting the assistance information message to the second apparatus.

[0298] In some example embodiments, the first apparatus further comprises: means for prioritizing the transmission of the assistance information message over further data transmission after the handover.

[0299] In some example embodiments, the first apparatus further comprises: means for receiving, from the second apparatus, a further configuration indicating to prioritize the transmission of the assistance information message over further data transmission after the handover.

[0300] In some example embodiments, the first cell and the second cell have same configuration information, the configuration information comprising an associated identifier.

[0301] In some example embodiments, the associated identifier indicates a transmitting beam property of the second apparatus.

[0302] In some example embodiments, the functionality is based on a machine learning (ML) model, and the accuracy information comprises at least one of a prediction accuracy of the ML model, a difference between a predicted value of the functionality and a ground truth value, or a value associated with an implementation of the ML model.

[0303] In some example embodiments, the at least one of the indication or the configuration is received from the second apparatus via the second cell.

[0304] In some example embodiments, the assistance information message comprises a user equipment (UE) assistance information (UAI) message.

[0305] In some example embodiments, a second apparatus capable of performing any of the method 1500 (for example, the second apparatus 120 in FIG. 1) may comprise means for performing the respective operations of the method 1500. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module. The second apparatus may be implemented as or included in the second apparatus 120 in FIG. 1.

[0306] In some example embodiments, the second apparatus comprises means for transmitting, to a first apparatus, at least one of: an indication of supporting forwarding accuracy information of a functionality from a first cell to a second cell, or a configuration of enabling partial reporting of the accuracy information, wherein the partial reporting allows for excluding a partial of the accuracy information from an assistance information message, wherein a handover is performed by the first apparatus from the first cell to the second cell.

[0307] In some example embodiments, the second apparatus further comprises: means for transmitting, to the first apparatus, a further configuration indicating to prioritize the transmission of the assistance information message over further data transmission after the handover.

[0308] In some example embodiments, the second apparatus further comprises: means for in accordance with a determination that the first cell and the second cell have same configuration information, transmitting the at least one of the indication or the configuration to the first apparatus, wherein the configuration information comprises an associated identifier.

[0309] In some example embodiments, the associated identifier indicates a transmitting beam property of the second apparatus.

[0310] In some example embodiments, the second apparatus further comprises: means for receiving, at the second cell from the first cell, the first accuracy information of the functionality associated with the first cell; and means for in accordance with a determination that the second accuracy information is excluded from the assistance information message, determining the second accuracy information based on the first accuracy information.

[0311] In some example embodiments, the functionality is based on a machine learning (ML) model, and the accuracy information comprises at least one of: a prediction accuracy of the AI / ML model, a difference between a predicted value of the functionality and a ground truth value, or a value associated with an implementation of the ML model. [ (»312 ] In some example embodiments, the at least one of the indication or the configuration is transmitted to the first apparatus via the second cell.

[0313] In some example embodiments, the second apparatus further comprises: means for receiving, at the second cell from the first apparatus, the assistance information message including the second accuracy information of the functionality; and means for transmitting, at the second cell to at least one neighboring cell of the second cell, the second accuracy information of the functionality.

[0314] In some example embodiments, the assistance information message comprises a user equipment (UE) assistance information (UAI) message.

[0315] FIG. 16 is a simplified block diagram of a device 1600 that is suitable for implementing example embodiments of the present disclosure. The device 1600 may be provided to implement a communication device, for example, the first apparatus 110 or the second apparatus 120 as shown in FIG. 1. As shown, the device 1600 includes one or more processors 1610, one or more memories 1620 coupled to the processor 1610, and one or more communication modules 1640 coupled to the processor 1610.

[0316] The communication module 1640 is for bidirectional communications. The communication module 1640 has one or more communication interfaces to facilitate communication with one or more other modules or devices. The communication interfaces may represent any interface that is necessary for communication with other network elements. In some example embodiments, the communication module 1640 may include at least one antenna.

[0317] The processor 1610 may be of any type suitable to the local technical network and may include one or more of the following: general purpose computers, special purpose computers, microprocessors, digital signal processors (DSPs) and processors based on multicore processor architecture, as non-limiting examples. The device 1600 may have multiple processors, such as an application specific integrated circuit chip that is slaved in time to a clock which synchronizes the main processor.

[0318] The memory 1620 may include one or more non-volatile memories and one or more volatile memories. Examples of the non-volatile memories include, but are not limited to, a Read Only Memory (ROM) 1624, an electrically programmable read only memory (EPROM), a flash memory, a hard disk, a compact disc (CD), a digital video disk (DVD), an optical disk, a laser disk, and other magnetic storage and / or optical storage. Examples of the volatile memories include, but are not limited to, a random-access memory (RAM) 1622 and other volatile memories that will not last in the power-down duration.

[0319] A computer program 1630 includes computer executable instructions that are executed by the associated processor 1610. The instructions of the program 1630 may include instructions for performing operations / acts of some example embodiments of the present disclosure. The program 1630 may be stored in the memory, e.g., the ROM 1624. The processor 1610 may perform any suitable actions and processing by loading the program 1630 into the RAM 1622.

[0320] The example embodiments of the present disclosure may be implemented by means of the program 1630 so that the device 1600 may perform any process of the disclosure as discussed with reference to FIG. 2A to FIG. 15. The example embodiments of the present disclosure may also be implemented by hardware or by a combination of software and hardware.

[0321] In some example embodiments, the program 1630 may be tangibly contained in a computer readable medium which may be included in the device 1600 (such as in the memory 1620) or other storage devices that are accessible by the device 1600. The device 1600 may load the program 1630 from the computer readable medium to the RAM 1622 for execution. In some example embodiments, the computer readable medium may include any types of non-transitory storage medium, such as ROM, EPROM, a flash memory, a hard disk, CD, DVD, and the like. The term “non-transitory,” as used herein, is a limitation of the medium itself (i.e., tangible, not a signal) as opposed to a limitation on data storage persistency (e g., RAM vs. ROM).

[0322] FIG. 17 shows an example of the computer readable medium 1700 which may be in form of CD, DVD or other optical storage disk. The computer readable medium 1700 has the program 1630 stored thereon.

[0323] Generally, various embodiments of the present disclosure may be implemented in hardware or special purpose circuits, software, logic or any combination thereof. Some aspects may be implemented in hardware, and other aspects may be implemented in firmware or software which may be executed by a controller, microprocessor or other computing device. Although various aspects of embodiments of the present disclosure are illustrated and described as block diagrams, flowcharts, or using some other pictorial representations, it is to be understood that the block, apparatus, system, technique or method described herein may be implemented in, as non-limiting examples, hardware, software, firmware, special purpose circuits or logic, general purpose hardware or controller or other computing devices, or some combination thereof.

[0324] Some example embodiments of the present disclosure also provide at least one computer program product tangibly stored on a computer readable medium, such as a non-transitory computer readable medium. The computer program product includes computerexecutable instructions, such as those included in program modules, being executed in a device on a target physical or virtual processor, to carry out any of the methods as described above. Generally, program modules include routines, programs, libraries, objects, classes, components, data structures, or the like that perform particular tasks or implement particular abstract data types. The functionality of the program modules may be combined or split between program modules as desired in various embodiments. Machine-executable instructions for program modules may be executed within a local or distributed device. In a distributed device, program modules may be located in both local and remote storage media.

[0325] Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. The program code may be provided to a processor or controller of a general-purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program code, when executed by the processor or controller, cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may execute entirely on a machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

[0326] In the context of the present disclosure, the computer program code or related data may be carried by any suitable carrier to enable the device, apparatus or processor to perform various processes and operations as described above. Examples of the carrier include a signal, computer readable medium, and the like.

[0327] The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable medium may include but not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the computer readable storage medium would include an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random-access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0328] Further, although operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. In certain circumstances, multitasking and parallel processing may be advantageous. Likewise, although several specific implementation details are contained in the above discussions, these should not be construed as limitations on the scope of the present disclosure, but rather as descriptions of features that may be specific to particular embodiments. Unless explicitly stated, certain features that are described in the context of separate embodiments may also be implemented in combination in a single embodiment. Conversely, unless explicitly stated, various features that are described in the context of a single embodiment may also be implemented in a plurality of embodiments separately or in any suitable sub-combination.

[0329] Although the present disclosure has been described in languages specific to structural features and / or methodological acts, it is to be understood that the present disclosure defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are 5 disclosed as example forms of implementing the claims.

Claims

1. A first apparatus comprising:at least one processor; andat least one memory storing instructions that, when executed by the at least one processor, cause the first apparatus to:receive, from a second apparatus, configuration information comprising a configuration of at least one functionality and a further configuration enabling a transmission of an assistance information message, the further configuration indicating to include in the assistance information message at least one of: at least one accuracy information of the at least one functionality, or at least one applicability indication of the at least one functionality based on the at least one accuracy information;determine whether at least one event triggering a transmission of the assistance information message happens and at least one condition for transmitting the assistance information message is satisfied; andin accordance with a determination that the at least one event happens and the at least one condition is satisfied, transmit, to the second apparatus, the assistance information message based on the configuration information, the assistance information message comprising at least one of: the at least one accuracy information, or the at least one applicability indication based on the at least one accuracy information.

2. The first apparatus of claim 1, wherein the at least one functionality is based on a machine learning (ML) model, and the accuracy information comprises at least one of: a prediction accuracy of the ML model, a difference between a predicted value of the at least one functionality and a ground truth value, or a value associated with an implementation of the ML model.

3. The first apparatus of claim 2, wherein the at least one functionality comprises a beam prediction based on the ML model, and the prediction accuracy comprises at least one of: a percentage of instances in which at least one predicted beam is the same as at least one ground truth best beam, a percentage of instances in which at least one ground truth signal strength of the at least one predicted beam is larger than or equal to a threshold, andwherein the difference between the predicted value and the ground truth value comprises at least one of: a signal strength of a predicted beam and a signal strength of a ground truth best beam, or a difference between a predicted signal strength of the predicted beam and a measured signal strength of the ground truth best beam.

4. The first apparatus of any of claims 1-3, wherein the further configuration comprises at least one of:an indication of including the at least one accuracy information in the assistance information message,an indication of including the at least one applicability indication based on the accuracy information in the assistance information message,an indication of including at least one conditionally applicable indication in the assistance information message, wherein the at least one conditionally applicable indication indicates an ongoing accuracy evaluation of the at least one functionality,the at least one event triggering a transmission of the assistance information message happens,the at least one condition for transmitting the assistance information message is satisfied, ora timer associated with the transmission of the assistance information message.

5. The first apparatus of any of claims 1-4, wherein the further configuration comprises the at least one event triggering the transmission of the assistance information message, the at least one event comprising at least one of:a first event that a machine learning (ML) model associated with the at least one functionality is changed,a second event that the first apparatus moves from a first cell to a second cell,a third event that an indication from the second apparatus indicates a change of networkside associated identifier associated with the at least one functionality,a fourth event that at least one of a measured signal strength of a serving cell or a measured signal strength of at least one neighboring cell meets a condition for neighboring cells, ora fifth event that the first apparatus fails to use the ML model due to lack of processing resource.

6. The first apparatus of claim 5, wherein the change of network-side associated identifier indicates a change of a transmitting beam property of the second apparatus.

7. The first apparatus of claim 4, wherein the first apparatus is caused to:in accordance with a determination that at least one accuracy evaluation of the at least one functionality is ongoing, include the at least one conditionally applicable indication in the assistance information message.

8. The first apparatus of any of claims 1-7, wherein the at least one functionality comprises a plurality of functionalities, and the first apparatus is caused to:in response to the at least one event associated with a first functionality of the plurality of functionalities,add at least one first accuracy information for first applicability indication of the first functionality in the assistance information message; andstart a timer associated with the transmission of the assistance information message;based on the timer being running, update the assistance information message by detecting the at least one event for the plurality of functionalities; andbased on the timer expiring, transmit the updated assistance information message to the second apparatus.

9. The first apparatus of any of claims 1-8, wherein at least one condition for transmitting the assistance information message comprises a condition that a change of accuracy information of a machine learning (ML) model associated with the at least one functionality is larger than or equal to a threshold.

10. The first apparatus of any of claims 1-9, wherein the first apparatus is caused to: determine the at least one accuracy information based on a monitoring process for the at least one functionality, wherein the monitoring process compares at least one measured reference signal resource and at least one predicted reference signal resource obtained by the at least one functionality.

11. The first apparatus of any of claims 1-10, wherein the first apparatus is caused to: receive, from the second apparatus, an activation or deactivation signal for the at least one functionality, wherein the activation or deactivation signal is determined based on at least one of the at least one accuracy information included in the assistance information message, or the at least one applicability indication based on the at least one accuracy information.

12. The first apparatus of any of claims 1-11, wherein the assistance information message comprises a user equipment (UE) assistance information (UAI) message.

13. A second apparatus comprising:at least one processor; andat least one memory storing instructions that, when executed by the at least one processor, cause the second apparatus to:transmit, to a first apparatus, configuration information comprising a configuration of at least one functionality and a further configuration enabling a transmission of an assistance information message, the further configuration indicating to include in the assistance information message at least one of: at least one accuracy information of the at least one functionality, or at least one applicability indication of the at least one functionality based on the at least one accuracy information; andreceive, from the first apparatus, the assistance information message comprising at least one of: the at least one accuracy information, or at least one applicability indication based on the at least one accuracy information.

14. The second apparatus of claim 13, wherein the at least one functionality is based on a machine learning (ML) model, and the accuracy information comprises at least one of: a prediction accuracy of the ML model, a difference between a predicted value of the at least one functionality and a ground truth value, or a value associated with an implementation of the ML model.

15. The second apparatus of claim 14, wherein the at least one functionality comprises a beam prediction based on the ML model, and the prediction accuracy comprises at least one of: a percentage of instances in which at least one predicted beam is the same as at least one ground truth best beam, a percentage of instances in which at least one ground truth signal strength of the at least one predicted beam is larger than or equal to a threshold, andwherein the difference between the predicted value and the ground truth value comprises at least one of: a signal strength of a predicted beam and a signal strength of a ground truth best beam, or a difference between a predicted signal strength of the predicted beam and a measured signal strength of the ground truth best beam.

16. The second apparatus of any of claims 13-15, wherein the further configuration comprises at least one of:an indication of including the at least one accuracy information in the assistance information message,an indication of including the at least one applicability indication based on the accuracy information in the assistance information message,an indication of including at least one conditionally applicable indication in the assistance information message, wherein the at least one conditionally applicable indication indicates an ongoing accuracy evaluation of the at least one functionality,the at least one event triggering a transmission of the assistance information message happens,the at least one condition for transmitting the assistance information message, ora timer associated with the transmission of the assistance information message.

17. The second apparatus of any of claims 13-16, wherein the further configuration comprises the at least one event triggering the transmission of the assistance information message, the at least one event comprising at least one of:a first event that a machine learning (ML) model associated with the at least one functionality is changed,a second event that the first apparatus moves from a first cell to a second cell,a third event that an indication from the second apparatus indicates a change of networkside associated identifier associated with the at least one functionality,a fourth event that at least one of a measured signal strength of a serving cell or a measured signal strength of at least one neighboring cell meets a condition for neighboring cells, ora fifth event that the first apparatus fails to use the ML model due to lack of processing resource.

18. The second apparatus of any of claims 13-17, wherein at least one condition for transmitting the assistance information message comprises a condition that a change of accuracy information of a machine learning (ML) model associated with the at least one functionality is larger than or equal to a threshold.

19. The second apparatus of any of claims 13-18, wherein the second apparatus is caused to:transmit, to the first apparatus, at least one activation or deactivation signal for the at least one functionality based on the assistance information message.

20. The second apparatus of claim 19, wherein the second apparatus is caused to:in accordance with a determination that the at least one accuracy information indicates an accuracy larger than or equal to a threshold or the at least one applicability indication based on the at least one accuracy information indicates that the at least one functionality is applicable, transmit the at least one activation signal for the at least one functionality to the first apparatus; andin accordance with a determination that the at least one accuracy information indicates an accuracy less than the threshold or the at least one applicability indication based on the at least one accuracy information indicates that the at least one functionality is inapplicable, transmit the at least one deactivation signal for the at least one functionality to the first apparatus.

21. The second apparatus of any of claims 13-20, wherein the assistance information message comprises a user equipment (UE) assistance information (UAI) message.

22. A method comprising:receiving, at a first apparatus from a second apparatus, configuration information comprising a configuration of at least one functionality and a further configuration enabling a transmission of an assistance information message, the further configuration indicating to include in the assistance information message at least one of: at least one accuracy information of the at least one functionality, or at least one applicability indication of the at least one functionality based on the at least one accuracy information;determining whether at least one event triggering a transmission of the assistance information message happens and at least one condition for transmitting the assistance information message is satisfied; andin accordance with a determination that the at least one event happens and the at least one condition is satisfied, transmitting to the second apparatus, the assistance information message based on the configuration information, the assistance information message comprising at least one of: the at least one accuracy information, or the at least one applicability indication based on the at least one accuracy information.

23. A method comprising:transmitting, at a second apparatus to a first apparatus, configuration information comprising a configuration of at least one functionality and a further configuration enabling a transmission of an assistance information message, the further configuration indicating to include in the assistance information message at least one of: at least one accuracy information of the at least one functionality, or at least one applicability indication of the at least one functionality based on the at least one accuracy information; andreceiving, from the first apparatus, the assistance information message comprising at least one of: the at least one accuracy information, or the at least one applicability indication based on the at least one accuracy information.

24. A first apparatus comprising:means for receiving, from a second apparatus, configuration information comprising a configuration of at least one functionality and a further configuration enabling a transmission of an assistance information message, the further configuration indicating to include in the assistance information message at least one of: at least one accuracy information of the at least one functionality, or at least one applicability indication of the at least one functionality based on the at least one accuracy information;means for determining whether at least one event triggering a transmission of the assistance information message happens and at least one condition for transmitting the assistance information message is satisfied; andmeans for in accordance with a determination that the at least one event happens and the at least one condition is satisfied, transmitting to the second apparatus, the assistance information message based on the configuration information, the assistance information message comprising at least one of: the at least one accuracy information, or the at least one applicability indication based on the at least one accuracy information.

25. A second apparatus comprising:means for transmitting, to a first apparatus, configuration information comprising a configuration of at least one functionality and a further configuration enabling a transmission of an assistance information message, the further configuration indicating to include in the5 assistance information message at least one of: at least one accuracy information of the at least one functionality, or at least one applicability indication of the at least one functionality based on the at least one accuracy information; andmeans for receiving, from the first apparatus, the assistance information message comprising at least one of: the at least one accuracy information, or the at least one10 applicability indication based on the at least one accuracy information.73

Images