Ai / ML functionality reporting

Abstract

Example embodiments of the present disclosure relate to applicable artificial intelligence (AI) / machine learning (ML) functionality reporting In an aspect, a terminal device detects an update in at least one functionality for artificial intelligence (AI) / machine learning (ML). Based on detecting the update in the at least one functionality for AI / ML, the terminal device transmits, to a network device, information indicating the update.

Description

AI / ML FUNCTIONALITY REPORTINGCROSS-REFERENCE TO RELATED APPLICATION

[0001] This application claims priority from, and the benefit of, India Provisional Application No. 202441075270, filed October 4, 2024, which is hereby incorporated by reference in its entirety.FIELD

[0002] Example embodiments of the present disclosure generally relate to the field of communications, and in particular, to devices, methods, apparatuses, and a computer readable storage medium for artificial intelligence (Al) / machine learning (ML) functionality reporting.BACKGROUND

[0003] A communication network can be seen as a facility that enables communications between two or more communication devices, or provides communication devices access to a data network. A mobile or wireless communication network is one example of a communication network. A communication device may be provided with a service by an application server.

[0004] Such communication networks operate in according with standards such as those provided by 3GPP (Third Generation Partnership Project) or ETSI (European Telecommunications Standards Institute). Examples of standards are the so-called 5G (5th Generation) standards, 6G (6th Generation) standards or other standards within the scope of 3GPP.SUMMARY

[0005] In general, example embodiments of the present disclosure provide a solution for Al / ML functionality reporting.

[0006] In a first aspect, there is provided a terminal device. The terminal device may include at least one processor and at least one memory storing instructions that, when executed by the at least one processor, cause the terminal device at least to receive, from a network device, first configuration information for configuring applicable functionality reporting for artificial intelligence (Al) / machine learning (ML) for at least one associated identity (ID). The terminal device is further caused to transmit, to the network device, based on the first configuration information, first functionality-related information comprising at least one entry corresponding to functionality information for AI / ML. An entry corresponds to functionality information and comprises an associated ID and at least one relaxation or reduced parameter for a corresponding applicable functionality reported for AI / ML.

[0007] In a second aspect, there is provided a network device. The network device may include at least one processor and at least one memory storing instructions that, when executed by the at least one processor, cause the network device at least to transmit, to a terminal device, first configuration information for configuring applicable functionality reporting for artificial intelligence (Al) / machine learning (ML) for at leastone associated identity (ID). The network device is further caused to receive, from the terminal device, based on the first configuration information, first functionality-related information comprising at least one entry corresponding to functionality information for AI / ML. An entry corresponds to functionality information and comprises an associated ID and at least one relaxation or reduced parameter for a corresponding applicable functionality reported for AI / ML.

[0008] In a third aspect, there is provided method. The method may include: receiving, from a network device, first configuration information for configuring applicable functionality reporting for artificial intelligence (Al) / machine learning (ML) for at least one associated identity (ID); and transmitting, to the network device, based on the first configuration information, first functionality-related information comprising at least one entry corresponding to functionality information for AI / ML, wherein an entry corresponds to functionality information and comprises an associated ID and at least one relaxation or reduced parameter for a corresponding applicable functionality reported for AI / ML.

[0009] In a fourth aspect, there is provided method. The method may include: transmitting, to a terminal device, first configuration information for configuring applicable functionality reporting for artificial intelligence (Al) / machine learning (ML) for at least one associated identity (ID); and receiving, from the terminal device, based on the first configuration information, first functionality-related information comprising at least one entry corresponding to functionality information for AI / ML, wherein an entry corresponds to functionality information and comprises an associated ID and at least one relaxation or reduced parameter for a corresponding applicable functionality reported for AI / ML.

[0010] In a fifth aspect, there is provided an apparatus. The apparatus may include: means for receiving, from a network device, first configuration information for configuring applicable functionality reporting for artificial intelligence (Al) / machine learning (ML) for at least one associated identity (ID); and means for transmitting, to the network device, based on the first configuration information, first functionality-related information comprising at least one entry corresponding to functionality information for AI / ML, wherein an entry corresponds to functionality information and comprises an associated ID and at least one relaxation or reduced parameter for a corresponding applicable functionality reported for AI / ML.

[0011] In a sixth aspect, there is provided an apparatus. The apparatus may include: means for transmitting, to a terminal device, first configuration information for configuring applicable functionality reporting for artificial intelligence (Al) / machine learning (ML) for at least one associated identity (ID); and means for receiving, from the terminal device, based on the first configuration information, first functionality- related information comprising at least one entry corresponding to functionality information for AI / ML, wherein an entry corresponds to functionality information and comprises an associated ID and at least one relaxation or reduced parameter for a corresponding applicable functionality reported for AI / ML.

[0012] In a seventh aspect, there is provided a non-transitory computer readable medium including program instructions for causing an apparatus to perform at least the method according to any one of thethird aspect or fourth aspect.

[0013] In an eighth aspect, there is provided a computer program including instructions, which, when executed by an apparatus, cause the apparatus at least to perform at least the method according to according to any one of the third aspect or fourth aspect.

[0014] In a ninth aspect, there is provided a terminal device. The terminal device may include: receiving circuitry configured to receive, from a network device, first configuration information for configuring applicable functionality reporting for artificial intelligence (Al) / machine learning (ML) for at least one associated identity (ID); and transmit, to the network device, based on the first configuration information, first functionality-related information comprising at least one entry corresponding to functionality information for AI / ML, wherein an entry corresponds to functionality information and comprises an associated ID and at least one relaxation or reduced parameter for a corresponding applicable functionality reported for AI / ML.

[0015] In a tenth aspect, there is provided a network device. The network device may include: transmitting circuitry configured to transmit, to a terminal device, first configuration information for configuring applicable functionality reporting for artificial intelligence (Al) / machine learning (ML) for at least one associated identity (ID); and receiving circuitry, configured to receive, from the terminal device, based on the first configuration information, first functionality-related information comprising at least one entry corresponding to functionality information for AI / ML, wherein an entry corresponds to functionality information and comprises an associated ID and at least one relaxation or reduced parameter for a corresponding applicable functionality reported for AI / ML.

[0016] In an eleventh aspect, there is provided a terminal device. The terminal device may include at least one processor and at least one memory storing instructions that, when executed by the at least one processor, cause the terminal device at least to: detect an update in at least one functionality for artificial intelligence (Al) / machine learning (ML); and based on detecting the update in the at least one functionality for AI / ML, transmit, to a network device, information indicating the update.

[0017] In a twelfth aspect, there is provided a network device. The network device may include at least one processor and at least one memory storing instructions that, when executed by the at least one processor, cause the network device at least to receive, from a terminal device, information indicating an update in at least one functionality for artificial intelligence (Al) / machine learning (ML).

[0018] In a thirteenth aspect, there is provided method. The method may include: detecting an update in at least one functionality for artificial intelligence (Al) / machine learning (ML); and based on detecting the update in the at least one functionality for AI / ML, transmit, to a network device, information indicating the update.

[0019] In a fourteenth aspect, there is provided method. The method may include: receiving, from a terminal device, information indicating an update in at least one functionality for artificial intelligence (Al) / machine learning (ML).

[0020] In a fifteenth aspect, there is provided an apparatus. The apparatus may include: means for detecting an update in at least one functionality for artificial intelligence (Al) / machine learning (ML); and means for based on detecting the update in the at least one functionality for AI / ML, transmit, to a network device, information indicating the update.

[0021] In a sixteenth aspect, there is provided an apparatus. The apparatus may include: means for receiving, from a terminal device, information indicating an update in at least one functionality for artificial intelligence (Al) / machine learning (ML).

[0022] In a seventeenth aspect, there is provided a non-transitory computer readable medium including program instructions for causing an apparatus to perform at least the method according to any one of the thirteenth aspect or fourteenth aspect.

[0023] In an eighth aspect, there is provided a computer program comprising instructions, which, when executed by an apparatus, cause the apparatus at least to perform at least the method according to according to any one of the thirteenth aspect or fourteenth aspect.

[0024] In a nineteenth aspect, there is provided a terminal device. The terminal device may include: detecting circuitry configured to detect an update in at least one functionality for artificial intelligence (Al) / machine learning (ML); and transmitting circuitry, configured to transmit, to a network device, information indicating the update based on detecting the update in the at least one functionality for AI / ML.

[0025] In a twentieth aspect, there is provided a network device. The network device may include: receiving circuitry configured to receive, from a terminal device, information indicating an update in at least one functionality for artificial intelligence (Al) / machine learning (ML).

[0026] 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

[0027] Some example embodiments will now be described with reference to the accompanying drawings, in which:

[0028] FIG. 1A illustrates an example of a network environment in which example embodiments of the present disclosure can be implemented;

[0029] FIG. 1 B illustrates two beam management (BM) cases related to some embodiments of the present disclosure;

[0030] FIG. 10 illustrates an example of proactive reporting for applicable functionality related to some embodiments of the present disclosure;

[0031] FIG. 1 D illustrates an example of reactive reporting for applicable functionality related to some embodiments of the present disclosure;

[0032] FIG. 2 illustrates a flow chart of method according to some embodiments of the present disclosure;

[0033] FIG. 3 illustrates a process for a signaling process for configuring functionality-related information according to some embodiments of the present disclosure;

[0034] FIG. 4 illustrates a flowchart of method according to some embodiments of the present disclosure;

[0035] FIG. 5 illustrates a process for an updated applicable functionality report according to some embodiments of the present disclosure.;

[0036] FIG. 6 illustrates a process for an updated applicable functionality report using UElnformation Procedure according to some embodiments of the present disclosure;

[0037] FIG. 7 illustrates a process for an updated applicable functionality report using UElnformation Procedure according to some embodiments of the present disclosure;

[0038] FIG. 8 illustrates a flowchart of a method implemented at a terminal device in accordance with some example embodiments of the present disclosure;

[0039] FIG. 9 illustrates a flowchart of a method implemented at a network device in accordance with some example embodiments of the present disclosure;

[0040] FIG. 10 illustrates a flowchart of a method implemented at a terminal device in accordance with some example embodiments of the present disclosure;

[0041] FIG. 11 illustrates a flowchart of a method implemented at a network device in accordance with some example embodiments of the present disclosure;

[0042] FIG. 12 illustrates simplified block diagram of a device that is suitable for implementing some example embodiments of the present disclosure; and

[0043] FIG. 13 illustrates a block diagram of an example of a computer readable medium in accordance with some example embodiments of the present disclosure.

[0044] Throughout the drawings, the same or similar reference numerals represent the same or similar elements.DETAILED DESCRIPTION

[0045] Principles 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. The disclosure described herein can be implemented in various manners other than the ones described below.

[0046] 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.

[0047] 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.

[0048] It shall be understood that although the terms “first” and “second” etc. 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.

[0049] 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. 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.

[0050] As used in this application, the term “circuitry” may refer to one or more or all of the following:(a) hardware-only circuits (such as in analog and / or digital circuits) 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 (e.g., 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 microprocessor(s), that requires software (for example, firmware) for operation, but the software may not be present when it is not needed for operation.

[0051] 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 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 ifapplicable 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 network device, or other computing or network device.

[0052] As used herein, the term “cellular network” refers to a network operating in accordance with any suitable radio access technology defined by standards, such as Long Term Evolution (LTE), LTE-Advanced (LTE-A), new radio Wideband Code Division Multiple Access (WCDMA), High-Speed Packet Access (HSPA), Narrow Band Internet of Things (NB-loT) and so on. Furthermore, the communications between a terminal device and a network device of a cellular network may be performed according to any suitable communication protocols, including, but not limited to, the fourth generation (4G), 4.5G, the future 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 cellular networks. 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.

[0053] As used herein, the term “network device” refers to any device in a cellular network via which a terminal device accesses a data network and receives services exposed by other network devices of the cellular network. In some examples, a network device may comprise or implement a network function of a 5thgeneration communication system (5GS) (e.g., a core network) of a cellular network. In some examples, the network devices may be located at the RAN of the 5GS. The network device may be part of a satellite, a base station (BS) or an access point (AP), for example, a node B (NodeB or NB), an evolved NodeB (eNodeB or eNB), a NR NB (also referred to as a gNB), a Remote Radio Unit (RRU), a radio header (RH), a remote radio head (RRH), a relay, a low power node such as a femto, a pico node, and so forth, depending on the applied terminology and technology. A gNB may include a centralized unit CU and one or more distributed DUs. Femto and Pico nodes are small base stations with a small coverage area.

[0054] The term “terminal device” refers to a device of a communication system of a cellular network, such as a 5thgeneration communication system (5GS) that may be capable of wireless (e.g., radio) communication with a NR-RAN of the 5GS). By way of example rather than limitation, a terminal device may also be referred to as a wireless communication device, user equipment (UE), a Subscriber Station (SS), a Portable Subscriber Station, a Mobile Station (MS), or an Access Terminal (AT). Examples of a terminal device 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 customer-premises equipment (CPE), an Internet of Things (loT) device, awatch or other wearable, a head-mounted display (HMD), a vehicle, a drone, a medical device and applications (for example, remote surgery), an industrial device and applications (for example, 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. In the following description, the terms “terminal device”, “communication device”, “terminal”, “user equipment” and “UE” may be used interchangeably.

[0055] Currently, an associated identity (ID) is used or defined for enabling consistency between an inference operation at the terminal device and a configuration by a network device (e.g., in a channel state information (CSI) framework for BM use case, an inference operation is matched to a configuration used during data collection). Although an associated ID is supported as being one part of applicable functionality determination, there has been no agreement yet regarding what extra / additional information may be available for a terminal device to fully determine an applicable functionality such that it will be guaranteed that the reported applicable functionality may be reliably activated by a network device. In other words, an associated ID may only provide applicability based on supported functionalities that the terminal device has indicated via capability reporting. However, relying only on supported functionalities may have following drawbacks:

[0056] (1) Inappropriate configuration may be resulted at the terminal device due to restrictions on model availability and additional conditions at the terminal device side.

[0057] (2) Supported functionalities indicated in capability reporting provided by the terminal device represent only the maximum range of AI / ML enabled features-related capability. The terminal device may not be capable of running inference with a maximum range as indicted in the terminal device capability reporting, since what is indicated in the UE capability reporting is not dependent on available terminal device models at time the terminal device receives configuration from the network device.

[0058] For a given applicable functionality, current solutions rely only on an associated ID and on a configuration provided based on the supported functionality determined from a terminal device capability exchange. The deficiency in current solutions is that the capability exchange signals maximum capability, e.g., maximum number of beams to measure for a BM case, while an AI / ML model might not have the capability or necessity to support the maximum for inference, which may lead to the network device configuring the terminal device with a functionality that is inapplicable or partly applicable.

[0059] In view of the above, example embodiments of the present disclosure provide a solution to determine an applicable functionality reporting for AI / ML for at least one associated identity (ID). The terminal device receive, from a network device, first configuration information for configuring applicable functionality reporting for artificial intelligence (Al) / machine learning (ML) for at least one associated identity (ID). The terminal device transmits, to the network device, based on the first configuration information, first functionality-related information comprising at least one entry corresponding to functionality information forAI / ML. An entry corresponds to functionality information and comprises an associated ID and at least one relaxation or reduced parameter for a corresponding applicable functionality reported for AI / ML.

[0060] A potential solution may be the terminal device detects an update in at least one functionality for artificial intelligence (Al) / machine learning (ML), and based on detecting the update in the at least one functionality for AI / ML, transmits, to a network device, information indicating the update.

[0061] Example embodiments of the present disclosure provide a solution to report an update in a functionality for AI / ML. The terminal device may detect a plurality of functionalities for AI / ML. The terminal device may, based on detecting an update in a functionality for AI / ML among the plurality of functionalities for AI / ML, transmit, to a network device, information indicating the update.

[0062] Embodiments of the present disclosure propose enhancements to applicability reporting mechanism and configurations of AI / ML functionalities, such that a signaling exchange between a network device and a terminal device before inference activation can be significantly improved.

[0063] FIG. 1A illustrates an example of a network environment 100a in which example embodiments of the present disclosure can be implemented. The environment 100a may be a part of a communication network and may include multiple terminal devices and network devices, such as a terminal device 110, a network device 120, etc. As an example, the terminal device 110 may be implemented as a User Equipment (UE) or an Access Terminal (AT), and the network device 120 may be implemented as a gNB, or a base station (BS). The network device 120 may transmit various data to the terminal device 110 via network environment 100a.

[0064] To transmit data and / or control information, the terminal device 110 may perform communications with the network device 120. A link from the network device 120 to the terminal device 110 is referred to as a downlink (DL), while a link from the terminal device 110 to the network device 120 is referred to as an uplink (UL).

[0065] Although the terminal device 110 and the network device 120 are described in the communication environment 100a of FIG. 1A, embodiments of the present disclosure may apply to any other suitable communication devices in communication with one another. That is, embodiments of the present disclosure are not limited to the exemplary scenarios of FIG. 1 A. In this regard, it is noted that although the terminal device is schematically depicted as a mobile phone and the network device 120 is schematically depicted as a base station in FIG. 1 A, it is understood that these depictions are exemplary in nature without suggesting any limitation. In another embodiment, the terminal device 110 and the network device 120 may be any other communication devices, for example, any other wireless communication devices.

[0066] It is to be understood that the particular number of various communication devices and the particular number of various communication links as shown in FIG. 1 A is for illustration purpose only without suggesting any limitations. The communication environment 100a may include any suitable number of communication devices and any suitable number of communication links for implementing embodiments ofthe present disclosure. In addition, it should be appreciated that there may be various wireless as well as wireline communications (if needed) among all of the communication devices.

[0067] FIG. 1 B illustrates two beam management (BM) cases 100b related to some embodiments of the present disclosure. For AI / ML enhancements related to beam management, two sub-use cases have been identified: beam prediction in the spatial domain (BM-Case1) and beam prediction in the time domain (BM- Case2).

[0068] The scope of spatial beam prediction (BM-Case1 ) is to predict the best DL transmission (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 have been verified based on given metrics, and they can be supported by single-sided models and consider supporting the necessary / recommended LCM components for selected sub-use cases.

[0069] FIG. 1 C illustrates an example 100c of proactive reporting for applicable functionality related to some embodiments of the present disclosure. I n this example embodiment, at 113, the network device 120 may send UECapabilityEnquiry message to initiate a procedure to a UE 110 for reporting its AI / ML supported functionalities. At 115, the UE may send UECapablitylnformation message to the network device 120, containing supported functionalities at the UE side.

[0070] At 117, the network device 120 may configure the UE 110 with functionality configurations for evaluation. The network device 120 may configure UE 110 that it is allowed to provide its applicable functionalities.

[0071] At 119, the UE 110 may send applicable functionalities to network device 120 upon functionality configuration and upon a change of applicable functionality / condition. At 121 , the network device 120 may send an inference activation configuration for one or more of the applicable functionalities to the UE 110. At 123, inference or monitoring may be started based on network / UE activation / deactivation.

[0072] FIG. 1 D illustrates an example 10Od of reactive reporting for applicable functionality related to some embodiments of the present disclosure. In this example embodiment, at 125, the network device 120 may send UECapabilityEnquiry message to initiate the procedure to a UE 110 for reporting its AI / ML supported functionalities. At 127, UE 110 may send UECapablitylnformation message to the network device 120, containing supported functionalities at the UE 110 side.

[0073] At 129, the network device 120 may provide network configurations and initiates UE 110 to report its applicable functionalities. At 131 , the UE 110 may send applicable functionalities to the network device 120.

[0074] At 133, the network device 120 may send updated inference configuration for applicable functionalities reported at 131 to the UE 110. At 135, inference or monitoring may be started based onnetwork / UE activation / deactivation.

[0075] FIG. 2 illustrates a flowchart of method according to some embodiments of the present disclosure. For the purpose of discussion, the method 200 will be described with reference to FIG. 1 A.

[0076] In the process flow 200, a network device 120 may transmit (202) first configuration information for configuring applicable functionality reporting for artificial intelligence (Al) / machine learning (ML) for one or more associated identities (IDs).

[0077] In some embodiment, the first configuration information may include one or more pairs, in which a pair of the one or more pairs may include an associated ID and one or more functionalities for AI / ML. In some embodiments, one associated ID may be associated with multiple functionalities. In some embodiments, the first configuration information may include a parameter to configure the terminal device 110 with a priority of the applicable functionality reporting. For example, the parameter may be configured to be as “urgent,” indicating the terminal device 110 to transmit functionalities reported for AI / ML with a priority in an urgent reporting message (e.g., a UE assistance information (UAI) message). In some embodiment, the first configuration information may include a radio resource control (RRC) reconfiguration information that is transmitted to the terminal device 110 from the network device 120.

[0078] In some embodiments, the first configuration information may include a functionality configuration ready for inference when it is applicable, and in some embodiments, the functionality configuration, as a part of the first configuration information, may include at least one critical parameter to which at least one relaxation or reduced parameter is able to be applied.

[0079] Alternatively, the first configuration information may include a partial functionality configuration comprising at least one critical parameter to which at least one relaxation or reduced parameters is able to be applied.

[0080] The terminal device 110 transmits (204), to the network device 120, based on the first configuration information, first functionality-related information comprising at least one entry corresponding to functionality information for AI / ML. In some embodiments, an entry may correspond to functionality information and may include an associated ID and at least one relaxation or reduced parameter for a corresponding applicable functionality reported for AI / ML. In some embodiments, a configuration for the at least one relaxation or reduced parameter is reduced relative to a maximum configuration of a corresponding parameter supported for the corresponding applicable functionality indicated to the network device via capability reporting. In some embodiments, a configuration for a relaxation or reduced parameter may include a value for the relaxation or reduced parameter.

[0081] In some embodiments, upon receiving the first configuration information from the network device 120, the terminal device 110 may determine applicability of each functionality for AI / ML in the first configuration information. For example, the terminal device 110 may evaluate applicability of a functionality for AI / ML among the one or more functionalities for AI / ML indicated by the first configuration information.The terminal device 110 may propose one or more relaxation or reduced parameters for the applicable functionality reported for AI / ML based on the evaluation. The terminal device 110 may generate the first functionality-related information based on the proposed one or more relaxation or reduced parameters.

[0082] In some embodiments, a relaxation or reduced parameter may include a configuration parameter recommended by the terminal device 110 to the network device 120 for activating an applicable functionality for AI / ML inference. When proposing a relaxation or reduced parameter for a functionality reported for AI / ML (e.g., functionality F1), the terminal device 110 may determine a configuration for the relaxation or reduced parameter based on one or more of followings: a characteristic of an AI / ML model at the terminal device side for the functionality (e.g., functionality F1), a maximum configuration of a parameter associated with the relaxation or reduced parameter, or a configuration for another relaxation or reduced parameter. Specifically, when determining a configuration for a relaxation or reduced parameter P1, a relationship of the relaxation or reduced parameter to another relaxation or reduced parameter may also be considered. In other words, the maximum value of relaxation or reduced parameter P1 and another relaxation or reduced parameter(s) may also be considered. For example, in a capabilities report, maximum values of A=8 and B=4 are reported. A situation may occur that when A=8, the maximum value for B is effectively 2 based on some conditions in the capabilities.

[0083] In some embodiments, a configuration for a relaxation or reduced parameter is reduced or relaxed relative to a maximum value of corresponding parameter supported for the corresponding applicable functionality. In some embodiment, the maximum value of corresponding parameter may be indicated in a capability report or indicated via capability reporting by the terminal device 110.

[0084] Taking a relaxation or reduced parameter for a beam management use case as an example. The relaxation or reduced parameter may include a “predicted Set A DL RS dimension” indicative an updated number of non-zero power channel state information reference signal (NZP-CSI-RS) resources to be configured as prediction NZP-CSI-RS resource sets. The maximum value for the parameter “predicted Set A DL RS dimension” may be 128 for example, and a configuration for the relaxation or reduced parameter “predicted Set A DL RS dimension” may be reduced or relaxed relative to 128. For example, the configuration for the relaxation or reduced parameter “predicted Set A DL RS dimension” may be 64, 32, or any value less than the maximum value for the parameter “predicted Set A DL RS dimension.”

[0085] In some embodiment, the first functionality-related information may include one or more entries. An entry may correspond to functionality information for AI / ML and may include an associated ID (for example, referring to the network side additional conditions) and one or more relaxation or reduced parameters for a corresponding applicable functionality reported for AI / ML. An entry may include a functionality ID indicative of an identity of a configured functionality and to define an index in an ApplicableFunctionality list. For example, a field of “applicableFunctionalityld” may be used to indicate a functionality ID. An entry may include a field of “applicability” indicating if a given functionality referred by applicableFunctionalityld isapplicable for inference purposes or not. An entry may further include a field with a configuration to indicate the reason for indicating inapplicability of a configured or activated functionality. In some embodiment, the first functionality-related information may be a part of RRCReconfigurationComplete message.

[0086] In some embodiments, the first functionality-related information may be, for example, a report of ApplicableFunctionalityReport. The structure of the first functionality-related information may be defined in terms of a list of (e.g., ApplicableFunctionality) information elements (lEs) using an AddMod / Remove structure. Alternatively, a SEQUENCE data structure may also be used for the first functionality-related information. By employing the structure of the AddMod / Remove structure, an update may be provided without providing an entire list of first functionality-related information (e.g., ApplicableFunctionality) for each update.

[0087] For an AddMod / Remove structure, an entry may further include a field indicative of a list of applicable functionalities to modify. For example, a field “applicableFunctionalityToAddModLis" may be used to indicate a list of applicable functionalities to modify. In addition, an entry may further include a field indicative of a list of applicable functionalities to release. For example, a field “applicableFunctionalityToRemoveLisf’ may be used to indicate a list of applicable functionalities to release.

[0088] In some embodiments, first functionality-related information, e.g. report of ApplicableFunctionality, may include one or more of a functionality ID, a field of ApplicableFunctionalityld (to define an index in the ApplicableFunctionality list), a field of Associatedld (to indicate associated ID), a field of InapplicabilityCause (indicating a reason for indicating inapplicability of a configured or activated functionality), or a field of ConfigRelaxation (e.g., including one or more relaxation or reduced parameters).

[0089] Table 1 shows an example of first functionality-related information provided for a beam management feature, including example parameters that may be signaled to aid the network device 120 in providing configurations aligned with the terminal network’s available models.

[0090] Table 1 An example of first functionality-related information provided for a beam management feature

[0091] Table 2 illustrates descriptions for some fields shown in Table 1 .Table 2 ApplicableFunctionalityReport -lEs field descriptions

[0092] Based on the associated ID in an entry is related to a beam management use case, as shown in Table 1 , a relaxation or reduced parameter in the entry may include one or more of following parameter: a number of predicted beams in Set A, represented by “nrofPredictedBeams" for example; an observation window indicating a minimum time duration for measuring non-zero power channel state information reference signal (NZP-CSI-RS) resources, for example, represented by “observationWindov ,- a prediction window indicating a maximum time duration that the NZP-CSI-RS resources is predicted based on Set B, forexample, represented by “prediction Window a measured downlink (DL) resource signal (RS) indicating a support of using synchronized signal block (SSB) and / or CSI-RS-based reference signal received power (RSRP) measurements, for example, represented by “MeasuredSetbDLRS" a measured Set B DL RS dimension indicating an updated number of NZP-CSI-RS resources to be measured and used for predicting a best K-NZP CSI-RS resource, for example, represented by “MeasuredSetbRSDiemension": a measured DL RS Set B pattern indicating a restriction on the updated number of NZP-CSI-RS resources to be measured and used for predicting a best K-NZP CSI-RS resource, for example, represented by “MeasuredSetbPattern",- a predicted Set A DL RS dimension indicating an updated number of NZP-CSI-RS resources to be configured as prediction NZP CSI-RS resource sets, represented by “PredictedSetaRSDiemension",- performance monitoring indicating an updated / preferred performance monitoring type, represented by “PerformanceMonitoring": or measured DL RS performance monitoring indicative of supported measurement for a predicted DL RS set, represented by “MeasuredDLRSPerformanceMonitoring."

[0093] Although the relaxation or reduced parameter and associated ID are illustrated in combination with Table 1 using a beam management use case, it should be understood that, the principle of the present disclosure can be applied to other use cases besides the beam management. An entry of associated ID and a relaxation or reduced parameter included in the first functionality-related information may be adjusted based on the AI / ML use case. Moreover, the term “first” before the “functionality-related information” does not mean to limit functionality-related information. It should be understood that, the description with respect to the first functionality-related information should also be applied to other functionality-related information transmitted by the terminal device to the network device.

[0094] In some embodiments, upon receiving the first functionality-related information from the terminal device 110, the network device 120 may evaluate an applicable functionality reported for AI / ML in the functionality-related information based on a configuration for a relaxation or reduced parameter for the applicable functionality reported for AI / ML. The network device 120 may select the applicable functionality for AI / ML inference based on the evaluation. The network device 120 may generate second configuration information for configuring the applicable functionality for AI / ML inference at the terminal device 110 side. Then the network device 120 may transmit, to the terminal device 110, the second configuration information, such that the terminal device 110 may configure the applicable functionality for AI / ML inference based on the second configuration information. In other words, the terminal device 110 may receive the second configuration information for configuring an applicable functionality for AI / ML inference from the network device 120, and the second configuration information is generated at least based on a configuration for a relaxation or reduced parameter of the applicable functionality reported for AI / ML inference in the reporting information. The terminal device 110 may configure the applicable functionality for AI / ML inference. The network device 120 may activate the applicable functionality for AI / ML inference.

[0095] According to embodiments shown in Fig. 2, the network device 120 may configure the terminaldevice 110 to indicate an applicable functionality report for an ML-enabled use-case (e.g., beam prediction) based first on an AI / ML-enabled feature and an associated ID. The applicable functionality report includes a list of relaxation or reduced parameter(s) which may increase the specificity of parameters initially signaled as part of supported functionalities with respect to a specific applicable functionality for inference. The network device 120 may configure the terminal device 110 with an applicable functionality after considering the relaxation or reduced parameter(s).

[0096] Adventurously, embodiments of the present disclosure propose enhancements to applicability reporting mechanism and configurations of AI / ML functionalities, such that a signaling exchange between a network device and a terminal device before inference activation can be significantly improved.

[0097] Fig. 3 illustrates a process 300 for a signaling process for configuring functionality-related information according to some embodiments of the present disclosure. It is noted that FIG. 3 may be deemed as a further example of the signaling process 200. For example, the UE 310 may be example devices of the terminal device 110, the gNB / NW 320 may be the example devices of the network device 120. It is to be understood that these devices are described only for the purpose of illustration without suggesting any limitation as to the scope of the disclosure. This process will be described in detail as follows.

[0098] At 301 and 302, UE 310 may perform an attach procedure and UE’s exchange capabilities with gNB / NW 320. By exchanging capabilities, a maximum value for a parameter of a functionality for AI / ML may be obtained by the gNB / NW 320.

[0099] At 303, gNB / NW 320 may provide a list of one or more pair of associated ID and a functionality for AI / ML, for example, in the first configuration information. In some embodiments, one associated ID may be listed in the first configuration information for multiple times if the associated ID may apply to multiple functionalities.

[0100] At 304, the terminal device 110 may evaluate an applicability of each pair of associated ID and an AI / ML functionality included in the first configuration information. For example, the applicability may indicate if a functionality is applicable for inference purposes or inapplicable for inference purposes.

[0101] At 305, the UE 310 may send functionality-related information to the gNB / NW 320. The functionality-related information may include an applicable functionality report as a part of RRCReconfigurationComplete. The report may include one or more entries. Each entry is corresponding to functionality information. Each entry is for each pair of associated ID and functionality for AI / ML which is applicable, considering a provided relaxation or reduced parameter, e.g., a relaxation or reduced parameter included in a field of ConfigRelaxation in the report.

[0102] At 306, gNB / NW 320 may evaluate the applicable functionalities as received in the functionality information (e.g., the report) from the UE 310, considering a relaxation or reduced parameter, e.g., a relaxation or reduced parameter included in a field of ConfigRelaxation in the report included in a field of ConfigRelaxation in the report.

[0103] At 307, based on one or more applicable functionalities, considering the relaxation or reduced parameter(s) e.g., in the field of ConfigRelaxation, being acceptable to the gNB / NW 320, the gNB / NW 320 may select a functionality to configure the UE 310. The configuration may be complete to support inference operation at the UE 320, i.e., including not only a subset of relaxation or reduced parameters, e.g., in the field of ConfigRelaxation, but also the full configuration.

[0104] At 308, the gNB / NW 320 may configure the UE 310 for inference by configuring an applicable functionality. In some embodiments, the gNB / NW 320 may transmit a second configuration information (e.g., RRCReconfiguration) including inference configuration considering a relaxation or reduced parameter, e.g., a relaxation or reduced parameter included in a field of ConfigRelaxation.

[0105] At 309, the UE 310 may acknowledge the configuration. The UE 310 may transmit RRCReconfigurationComplete to gNB / NW 320. At 310, the gNB / NW 320 may active the functionality selected at 307 for AI / ML inference.

[0106] In some embodiments, the terminal device 110 may detect an update or a change in a functionality for AI / ML. In some embodiments, the update may be detected based on one or more of: first configuration information for configuring applicable functionality reporting for AI / ML for at least one associated ID that is received from the network device, or first functionality-related information.

[0107] In some embodiments, the update may include an update on one or more of: an applicability of a functionality or at least one relaxation or reduced parameter of an applicable functionality. The change may include one or more of the following: one or more functionalities are no longer applicable, irrespective of configuration relaxation or reduced parameters; one or more functionalities which was already applicable has an update to is configured relaxation or reduced parameters; or a previously unreported, non-applicable functionality is reported as applicable with a corresponding relaxation or reduced parameter, for example, a parameter configured in the field of ConfigRelaxation.

[0108] In some embodiments, the terminal device 110 may transmit, to the network device 120, second functionality-related information based on detecting an update or a change in a functionality for AI / ML. In some embodiments, the second functionality-related information may include updated information based on the update or the change. For example, the second functionality-related information may be updated functionality-related information relative to previous functionality-related information (e.g., the first functionality-related information).

[0109] In some embodiments, the second functionality-related information or the updated functionality- related information has similar structure with that of the functionality-related information. For example, the second functionality-related information or the updated functionality-related information may correspond to functionality information and include an associated ID and at least one relaxation or reduced parameter for a corresponding applicable functionality reported for AI / ML. The second functionality-related information or the updated functionality-related information may include one or more updated entries relative to the firstfunctionality-related information. An updated entry may include one or more of following: at least one relaxation or reduced parameter for a corresponding applicable functionality reported for AI / ML or a removal of at least one previously proposed relaxation or reduced parameter.

[0110] In some embodiments, the terminal device 110 may detect a change or update in a functionality, considering a configuration for one or more relaxation or reduced parameter, e.g., in a field of ConfigRelaxation. The change may be related to an active functionality, an inactive previously reported applicable functionality, or to a previously reported non-applicable functionality. In some embodiments, the terminal device 110 may provide in a UE assistance information (UAI) message an indicator or an indication of characteristic of the update.

[0111] In some embodiments, the characteristic of the update may include one or more of following: an applicability update, e.g., updated ConfigRelaxation, which may increase the functionality’s performance, is available for the active functionality (e.g., an applicability update for an active functionality for AI / ML inference, wherein the applicability update may include an updated configuration for a relaxation or reduced parameter that increases the active functionality’s capability; an applicability update, e.g., updated ConfigRelaxation, which may decrease the functionality’s performance, is available for the active functionality (e.g., an applicability update for an active functionality for AI / ML inference, wherein the applicability update may include an updated configuration for a relaxation or reduced parameter that decreases the active functionality’s capability); or an applicability update to an inactive functionality, e.g., an update from applicable to non-applicable or from non-applicable to applicable, or an updated ConfigRelaxation, is available for a previously reported applicable or non-applicable functionality (for example, an applicability update for an inactive functionality for AI / ML, wherein the applicability update may include one or more of following: the inactive functionality is updated from applicable to be non-applicable, the inactive functionality is update from non-applicable to be applicable, or a configuration for at least one relaxation or reduced parameter for the inactive functionality is updated).

[0112] In some embodiments, an inactive functionality is a functionality that has been provided in an applicable functionality report, which the network device 120 has not enabled for inference.

[0113] The network device 120 may transmit a request for information related to applicable functionality update if the network device 120 is interested in the update. For example, the request may include a UElnformationRequest, and the terminal device 110 may respond with updated functionality-related information (e.g. second functionality-related information) and transmit the second functionality-related information or the updated functionality-related information to the network device 120. In some embodiments, the second or the updated functionality-related information may include information of UElnformationResponse, including the report of ApplicableFunctionalityReport.

[0114] That is, the terminal device 110 may receive a request for information related to applicable functionality update from the network device 120, and transmit second or updated functionality-relatedinformation based on the received request to the network device 110. The structure of the second functionality-related information has been described above, and repetitive descriptions are omitted here for purposes of clarity and brevity.

[0115] In some embodiments, for the second or the updated functionality-related information transmitted by the terminal device 110 based on detecting an update on a functionality for AI / ML or based on a request for information related to applicable functionality update from the network device 120, the second or the updated functionality-related information is different from the first functionality-related information (e.g., previous functionality-related information transmitted by the terminal device 110 at 204), and in some embodiments, a difference between the updated functionality-related information and the functionality-related information may include one or more of following: a first entry in the first functionality-related information is updated in the second functionality-related information to indicate a previously applicable functionality for AI / ML associated with the first entry is inapplicable, in which the first entry may include a field (e.g., “ inapplicabilityCause") indicating a cause for an inapplicability of the previously applicable functionality for AI / ML associated with the first entry; a second entry in the first functionality-related information is updated in the second functionality-related information to indicate a previously inapplicable functionality for AI / ML associated with the second entry is applicable; a third entry not in the first functionality-related information is added into the second functionality-related information, in which the third entry is corresponding to a new applicable functionality for AI / ML, and the third entry may include an associated ID and at least one relaxation or reduced parameter for the new applicable functionality for AI / ML; a configuration for a relaxation or reduced parameter in a fourth entry in the first functionality-related information is updated in the second functionality- related information; or a fifth entry in the first functionality-related information is removed from the second functionality-related information.

[0116] In some embodiments, an update on a functionality for AI / ML may include an update on one or more of an applicability of a functionality or a configuration for one or more relaxation or reduced parameters of an applicable functionality, and may include one or more of following: the functionality for AI / ML becomes inapplicable from a previously applicable state; the functionality for AI / ML becomes an applicable from a previously inapplicable state; the functionality for AI / ML is newly indicated in the first configuration information (e.g., the first configuration information transmitted by the network device 120 at 202); a configuration for a relaxation or reduced parameter for the applicable functionality for AI / ML has been updated; or the functionality for AI / ML has been released.

[0117] In some embodiments, the first configuration information may be an initial configuration for configuring applicable functionality reporting for AI / ML for at least one associated identity (ID) during a communication. Alternatively, the first configuration information may be an intermediate configuration for AI / ML for at least one associated identity (ID) during the communication process. In a situation that the first configuration information is an intermediate configuration, an entry in the first functionality-related informationcorresponds to functionality information and may include one or more of: at least one relaxation or reduced parameter for a corresponding applicable functionality reported for AI / ML or a removal of at least one previously proposed relaxation or reduced parameter.

[0118] In some embodiments, the network device 120, when receives the second functionality-related information from the terminal device 110, may evaluate the second or the updated functionality-related information. The network device 120 may generate a third configuration information based on the evaluation and transmit the third configuration information to the terminal device. The terminal device 110, based on the received third configuration information, may perform one or more of following: update a configuration of a currently activated applicable functionality for AI / ML inference; switch to a newly activated applicable functionality for AI / ML inference; or fallback to a non-AI / ML mechanism.

[0119] In some embodiments, if an updated relaxation or reduced parameter in a field e.g. ConfigRelaxation is provided for an active functionality, the network device 120 may evaluate the updated relaxation or reduced parameter to determine whether the updated relaxation or reduced parameter is acceptable. If the ConfigRelaxation update for the active functionality is acceptable, the network device 120 may reconfigure the terminal device 110 with a new inference configuration compatible with the update. Then the terminal device 110 may update a configuration of a currently activated applicable functionality for AI / ML inference.

[0120] If another reported applicable functionality is found (or evaluated) to be acceptable, the network device 110 may decide to switch functionalities, e.g., irrespective of whether the active functionality remained applicable after the update to a relaxation or reduced parameter in a field e.g., ConfigRelaxation. Then the terminal device 110 may switch to a newly activated applicable functionality for AI / ML inference.

[0121] If no applicable functionalities remain or if the network device 110 does not find any of the applicable functionalities acceptable considering the relaxation or reduced parameter(s) for example, in the field of ConfigRelaxation, the network device 120 may configure the terminal device 110 to fallback to a non-ML mechanism.

[0122] FIG. 4 illustrates a flowchart of method according to some embodiments of the present disclosure. For the purpose of discussion, the method 400 will be described with reference to FIG. 1 A.

[0123] At 402, the terminal device 110 may detect an update in one or more functionalities for AI / ML among the plurality of functionalities. At 404, the terminal device may transmit to the network device 110 information indicating the update based on detecting the update in the one or more functionalities for AI / ML.

[0124] In some embodiments, the update is detected based on one or more of: first configuration information for configuring applicable functionality reporting for AI / ML for at least one associated ID that is received from the network device 120, or first functionality-related information.

[0125] In some embodiments, the terminal device 110 may receive, from the network device 120, the first configuration information for configuring applicable functionality reporting for AI / ML for one or moreassociated IDs (for example, at 202 in Fig. 2). The terminal device 110 may transmit, to the network device 120, based on the first configuration information, first functionality-related information including at least one entry corresponding to functionality information for AI / ML. An entry may correspond to functionality information and may include an associated ID and at least one relaxation or reduced parameter for a corresponding applicable functionality reported for AI / ML.

[0126] In some embodiments, the first configuration information may be an initial configuration for configuring applicable functionality reporting for AI / ML for at least one associated identity (ID) during a communication. Alternatively, the first configuration information may be an intermediate configuration for AI / ML for at least one associated identity (ID) during the communication process. In a situation that the first configuration information is an intermediate configuration, an entry in the first functionality-related information corresponds to functionality information and may include one or more of: at least one relaxation or reduced parameter for a corresponding applicable functionality reported for AI / ML or a removal of at least one previously proposed relaxation or reduced parameter.

[0127] In some embodiments, the first configuration information may include a functionality configuration ready for inference when it is applicable, and wherein the functionality configuration, as a part of the first configuration information, comprises at least one critical parameter to which at least one relaxation or reduced parameter is able to be applied. Alternatively, the first configuration information may include a partial functionality configuration comprising at least one critical parameter to which at least one relaxation or reduced parameters is able to be applied.

[0128] In some embodiments, the relaxation or reduced parameter is reduced relative to a maximum configuration of a corresponding parameter supported for the corresponding applicable functionality indicated to the network device via capability reporting.

[0129] In some embodiments, the terminal device 110 may propose at least one relaxation or reduced parameter for the functionality for AI / ML. The terminal device may generate the functionality-related information at least based on the proposal.

[0130] In some embodiments, when proposing a relaxation or reduced parameter for a functionality for AI / ML, the terminal device 110 may determine a configuration for the relaxation or reduced parameter based on one or more of followings: a characteristic of an AI / ML model at the terminal device side for the functionality, a maximum configuration of a parameter associated with the relaxation or reduced parameter, or a configuration for another relaxation or reduced parameter. A detailed description for determining a relaxation or reduced parameter may be understood in combination with reference to the description of Fig. 2, and for the purposes of clarity and brevity, the repetition is omitted herein.

[0131] The description for the first configuration information and the first functionality-related information may be understood in combination with reference to description for FIG. 2. Repetitive descriptions are omitted here for purposes of clarity and brevity.

[0132] In some embodiments, the information transmitted by the terminal device 110 at 404 may include second or updated functionality-related information indicating an update in a functionality for AI / ML, and the functionality-related information may include updated information relative to a previous functionality-related information based on the update. In other words, the first functionality-related information may be a previous functionality-related information of the second functionality-related information transmitted by the terminal device 110 at 404. In some embodiments, the first functionality-related information transmitted by the terminal device 110 may include an entry including an associated ID and one or more relaxation or reduced parameters for a corresponding applicable functionality reported for AI / ML. The second functionality-related information may include at least one updated entry relative to the first functionality- related information, and an updated entry of the at least one updated entry may include one or more of: at least one relaxation or reduced parameter for a corresponding applicable functionality reported for AI / ML or a removal of at least one previously proposed relaxation or reduced parameter.

[0133] In some embodiments, the update occurring in at least one functionality may include an update on one or more of an applicability of a functionality or a configuration for one or more relaxation or reduced parameters of an applicable functionality, and may include one or more of following: the functionality for AI / ML becomes inapplicable from a previously applicable state; the functionality for AI / ML becomes an applicable from a previously inapplicable state; the functionality for AI / ML is indicated as a new functionality in the first configuration information; a configuration for a relaxation or reduced parameter for the functionality reported for AI / ML has been updated; or the functionality for AI / ML has been released.

[0134] In some embodiments, the information transmitted at 404 by the terminal device 110 may include second or updated functionality-related information based on detecting an updated in a functionality. For example, the terminal device 110 may detect an update or a change in a functionality for AI / ML. In some embodiments, the update may include an update on one or more of: an applicability of a functionality or one or more relaxation or reduced parameters of an applicable functionality. The update may include one or more of the following: one or more functionalities are no longer applicable, irrespective of configuration relaxation or reduced parameters; one or more functionalities which was already applicable has an update to is configuration relaxation or reduced parameters; or a previously unreported, non-applicable functionality is reported as applicable with one or more corresponding relaxation or reduced parameters, for example, one or more parameters configured in a field e.g., ConfigRelaxation.

[0135] In some embodiments, the information transmitted by the terminal device 110 at 404 may include an indication of characteristic of the update in a functionality for AI / ML. The detailed information on characteristic of the update has been described above and the will be omitted herein for purposes of clarity and brevity.

[0136] In some embodiments, the network device 120, may transmit a request for information related to applicable functionality update if the network device 120 is interested in the update. For example, therequest may include a message such as UElnformationRequest, and the terminal device may respond with second or updated functionality-related information and transmit the second or updated functionality-related information to the network device 120. In some embodiments, the second or updated functionality-related information may include information of UElnformationResponse, including the ApplicableFunctionalityReport.

[0137] In some embodiments, the second functionality-related information transmitted by the terminal device 110 in response to the request may include one or more updated entries relative to the first functionality-related information, and in some embodiments, an updated entry of the one or more updated entries may include one or more: at least one relaxation or reduced parameter for a corresponding applicable functionality reported for AI / ML or a removal of at least one previously proposed relaxation or reduced parameter.

[0138] That is, the terminal device 110 may receive a request for information related to applicable functionality update from the network device 120, and transmit updated functionality-related information based on the received request to the network device 110.

[0139] In some embodiments, the second or updated functionality-related information may be different from a previous functionality-related information (e.g., first functionality-related information), and a difference between the second functionality-related information and the first functionality-related information may include one or more of following: a first entry in the first functionality-related information is updated in the second functionality-related information to indicate a previously applicable functionality for AI / ML associated with the first entry is inapplicable, wherein the first entry may include a field indicating a cause for an inapplicability of the previously applicable functionality for AI / ML associated with the first entry; a second entry in the first functionality-related information is updated in the second functionality-related information to indicate a previously inapplicable functionality for AI / ML associated with the second entry is applicable; a third entry not in the first functionality-related information is added into the second functionality-related information, in which the third entry is corresponding to a new applicable functionality for AI / ML, and the third entry may include an associated ID and at least one relaxation or reduced parameter for the new applicable functionality for AI / ML; a configuration for a relaxation or reduced parameter in a fourth entry in the first functionality-related information is updated based on the update in the second functionality-related information; or a fifth entry in the second functionality-related information is removed from the first functionality-related information.

[0140] In some embodiments, the network device 120, when receives the second or the updated functionality-related information from the terminal device 110, may evaluate the second or the updated functionality-related information. The network device 120 may generate a third configuration information based on the evaluation and transmit the third configuration information to the terminal device 110. The terminal device 110, based on the received third configuration information, may perform one or more of following: update a configuration of a currently activated applicable functionality for AI / ML inference; switchto a newly activated applicable functionality for AI / ML inference; or fallback to a non-AI / ML mechanism. A detailed description may be understood by referring to the above descriptions, and repetitive description is omitted for purposes of clarity and brevity.

[0141] FIG. 5 illustrates a process 500 for an updated applicable functionality report according to some embodiments of the present disclosure. It is noted that FIG. 5 can be deemed as a further example of the process flow 400. For example, the UE 510 may be example devices of the terminal device 110, the gNB 520 may be the example devices of the network device 120. It is to be understood that these devices are described only for the purpose of illustration without suggesting any limitation as to the scope of the disclosure. This process will be described in detail as follows.

[0142] At 501 , the UE 510 may periodically, or based on internal monitoring, evaluate applicable functionalities in a loop. At 502, the terminal device 110 may detect a change or an update in applicable functionalities. The change or update may be characterized as one of the following: one or more functionalities are no longer applicable, irrespective of configuration relaxation or reduced parameters; one or more functionalities which was already applicable has an update to is configuration relaxation or reduced parameters; a previously unreported, non-applicable functionality is reported as applicable with a corresponding configuration in a field, e.g., ConfigRelaxation, e.g., with one or more relaxation or reduced parameters.

[0143] At 503, UE 510 may transmit a functionality-related information. The functionality-related information may be an applicable functionality report, which may be included as a part of UE Assistance Information (UAI) or a UE Information Response (the UE Information Response may be transmitted in response to a request from gNB 520 for requesting updated information related to applicable functionality update if a UE 510 transmits an indication of a characteristic of the update). The report may indicate the change in a functionality for AI / ML that has been detected at 502. In some embodiments, the report may include entries at least for each pair of associated ID and a functionality for AI / ML which is applicable, considering any provided relaxation or reduced parameters, i.e., those parameters included in a field, e.g., ConfigRelaxation. In some embodiments, the report may include one or more updated entries relative to previous functionality-related information, and an updated entry may include one or more of: at least one relaxation or reduced parameter for a corresponding applicable functionality reported for AI / ML or a removal of at least one previously proposed relaxation or reduced parameter. Detailed information of relaxation or reduced parameters e.g., included in the field of ConfigRelaxation may be understood with reference to the above descriptions, and repetitive descriptions are omitted herein for purposes of clarity and brevity.

[0144] At 504, if an updated relaxation or reduced parameter (e.g., in a field of ConfigRelaxation) is provided for an active functionality, the network device 120 may evaluate the updated relaxation or reduced parameter to determine whether the updated relaxation or reduced parameter is acceptable. At 505, if the ConfigRelaxation update for the active functionality is acceptable, the network device 120 may reconfigurethe terminal device 110 with a new inference configuration compatible with the update. Then the terminal device 110 may update a configuration of a currently activated applicable functionality for AI / ML inference.

[0145] At 506, if another reported applicable functionality is found (or evaluated) to be acceptable, the network device 110 may decide to switch functionalities, e.g., irrespective of whether the active functionality remained applicable after the update to a relaxation or reduced parameter in a field of ConfigRelaxation. Then the terminal device 110 may switch to a newly activated applicable functionality for AI / ML inference.

[0146] At 507, if no applicable functionalities remain or if the network device 110 does not find any of the applicable functionalities acceptable considering the relaxation or reduced parameter(s) in the field of ConfigRelaxation, the network device 120 may configure the terminal device 110 to fallback to a non-ML mechanism.

[0147] At 508, the UE may acknowledge the updated configuration. For example, the UE 510 may transmit RRCReconfiguraitonComplete to the gNB 520. At 509, the gNB 520 may activate the functionality.

[0148] In some embodiments, the network 120 may configure the terminal device 110 with a new ML- enabled CSI-ReportConfig considering the terminal device’s reported applicability compatible with current terminal deice-side additional conditions (referred to as applicability relaxation determination). The new ML-enabled CS-ReportConfig may carry the same associatedJD to that provided in step 203 in FIG. 2 or step 503 in FIG. 5. In some embodiments, a new ML-enabled CS-ReportConfig may not carry the same associatedJD to that provided in step 203 in FIG. 2 or step 503 in FIG. 5.

[0149] In some embodiments, based on none of the terminal devices reported applicable functionalities, considering applicability relaxations by the network device, the network device 120 may fallback to non-ML functionality (e.g., CSI-ReportConfig) and release associated ID of a configured functionality as provided in step 203 in FIG. 2 or step 503 in FIG. 5.

[0150] FIG. 6 illustrates a process 600 for an updated applicable functionality report using UElnformation procedure according to some embodiments of the present disclosure. It is noted that FIG. 6 can be deemed as a further example of the process flow 400. For example, the UE 610 may be example devices of the terminal device 110, the gNB 620 may be the example devices of the network device 120. It is to be understood that these devices are described only for the purpose of illustration without suggesting any limitation as to the scope of the disclosure. This process will be described in detail as follows.

[0151] In some embodiments, the UE 620 may detect a change in applicable functionalities, considering a possible ConfigRelaxation, as shown in 601 and 602. The change may be related to an active functionality, an inactive previously reported applicable functionality, or to a previously reported non- applicable functionality, as described above in detail.

[0152] At 603, the UE 610 may transmit an indication indicating applicable functionality change, e.g., in a UAI message, to the gNB 620. The indication may be indicative of a characteristic of the update to a functionality for AI / ML. In some embodiments, the UE 620 may provide in a UAI message a simple indicatoror flag indicating one or more of following: an applicability update, e.g., updated ConfigRelaxation, which may increase the active functionality’s capability, is available for the active functionality; an applicability update, e.g., updated ConfigRelaxation, which may decrease the active functionality’s capability, is available for the active functionality; or an applicability update to an inactive functionality, e.g., an update from applicable to non-applicable or from non-applicable to applicable, or an updated ConfigRelaxation (e.g., a configuration for a relaxation or reduced parameter in the field of ConfigRelaxation ), is available for a previously reported applicable or non-applicable functionality. An inactive functionality may include a functionality that has been provided in an applicable functionality report, which the gNB 620 has not enabled for inference.

[0153] Due to the urgency of each case differs, the gNB 620 may suppress an update which it doesn’t need. At 604, the gNB 620 may determine if the update is relevant or needed. The gNB 620, if interested in the update, may transmit to the UE a request for updated information, e.g., UElnformationRequest for applicable functionality report update, at 605. The UE, at 606, may respond with UElnformationResponse including the applicable functionality report update, e.g., ApplicableFunctionalityReport.

[0154] FIG. 7 illustrates a process 700 for an updated applicable functionality report using UElnformation procedure according to some embodiments of the present disclosure. It is noted that FIG. 7 can be deemed as a further example of the process flow 400. For example, the UE 710 may be example devices of the terminal device 110, the gNB 720 may be the example devices of the network device 120. It is to be understood that these devices are described only for the purpose of illustration without suggesting any limitation as to the scope of the disclosure. This process will be described in detail as follows.

[0155] At 701 and 702, UE 710 may perform an attach procedure and UE’s exchange capabilities with gNB 720. By exchanging capabilities, a maximum value for a parameter of a functionality for AI / ML may be obtained by the gNB 720.

[0156] At 703, gNB 720 may provide functionality information. The functionality information may include multiple pairs, with each pair including a functionality for AI / ML with an associated IDs. At 704, the UE 710 may determine an applicability of each pair of associated ID and an AI / ML functionality included in the functionality information transmitted by gNB 720 at 703. For example, the applicability may indicate if a functionality is applicable for inference purposes or inapplicable for inference purposes.

[0157] At 705, the UE 710 may send functionality-related information. In some embodiments, the functionality-related information may include an applicable functionality report (the report may be an initial applicable functionality report in a situation that the functionality information at 703 is for an initial configuration for applicable functionality reporting). The applicable functionality report may be a part of RRCReconfigurationComplete. The report may include one or more entries, with each entry corresponding to functionality information for AI / ML being and being for each pair of associated ID and functionality for AI / ML which is applicable, considering a provided relaxation or reduced parameter, i.e., a relaxation or reduced parameter included in a field e.g., ConfigRelaxation in the applicable functionality report. An entrycorresponds to functionality information and may include an associated ID and one ore more relaxation or reduced parameter for a corresponding applicable functionality reported for AI / ML.

[0158] In some embodiments, the functionality information provided at step 703 may be an initial configuration for configuring applicable functionality reporting for AI / ML for at least one associated identity (ID) during a communication. Alternatively, the functionality information provided at step 703 may be an intermediate configuration for AI / ML for at least one associated identity (ID). In a situation that the functionality information provided at step 703 is an intermediate configuration, an entry in the applicable functionality report may include one or more of: at least one relaxation or reduced parameter for a corresponding applicable functionality reported for AI / ML or a removal of at least one previously proposed relaxation or reduced parameter.

[0159] At 706, gNB 720 may evaluate the applicable functionalities as received in the report from the UE 710, considering a relaxation or reduced parameter included in a field e.g., ConfigRelaxation in the applicable functionality report.

[0160] At 707, the gNB 720 may provide functionality configuration to UE 710. The detailed process for 707 may be understood in combination with reference to step 308 at FIG. 3, and repetitive descriptions are omitted herein for purposes of clarity and brevity.

[0161] As shown in Fig. 7, steps 701 -707 may be related to a process of report after reception of functionality information, e.g., referred as a “first stage”. The first stage may be an initial configuration for application functionality reporting or an intermediate configuration for application functionality reporting. That is, the process may include an initial process for configuring applicable functionality reporting for AI / ML for at least one associated ID. Alternatively, the process may also include an intermediate process for configuring applicable functionality reporting for AI / ML for at least one associated ID, for example. In an intermediate process, the gNB 720 may configure an unreported functionality.

[0162] At 708, the UE 710 may periodically, or based on internal monitoring, evaluate applicable functionalities in a loop, e.g., to detect an update in a functionality for AI / ML. The UE 710 may monitor function information from gNB 720 to detect an update in a functionality for AI / ML. In some embodiments, the update may be determined based on one or more of: functionality information at 703 or (initial) applicable functionality report at 705. The change or update has been described above, repetitive descriptions are omitted herein. If a change or an update in an applicable functionality has been detected, as shown in the block 740, the UE 710 may transmit a (updated) applicable functionality report, which may be included as a part of UE Assistance Information (UAI) or a UE Information Response (the UE Information Response may be transmitted in response to a request from gNB 720 for requesting updated information related to applicable functionality update if a UE 710 transmits an indication of a characteristic of the update). Detailed information be understood with reference to FIG. 5, and repetitive descriptions are omitted herein for purposes of clarity and brevity.

[0163] At 711 , the gNB 720 may evaluate the (updated) applicable functionality report and transmit functionality configuration at 712 to the UE 710. Detailed description for 711 and 712 may be referred to descriptions for steps 504-507 in FIG. 5, and repetitive descriptions are omitted herein for purposes of clarity and brevity. Steps 708-712 in FIG. 7 may be related to a process associated with an updated report after a change in an applicable functionality, e.g., referred as a “second stage”.

[0164] In some embodiments, step 703 in FIG. 7 may be applied for both procedures of the first stage and the second stage. In some embodiments, previously provided Functionality Information at 703 may be reused for an applicable functionality report updates. When new or updated Functionality Information is provided at 703, the steps described in the first stage are applicable. Otherwise, the steps described in the second stage are applicable.

[0165] FIG. 8 illustrates a flowchart of a method 800 implemented at a terminal device in accordance with some example embodiments of the present disclosure. For the purpose of discussion, the method 800 will be described from the perspective of the terminal device 110 with reference to FIG. 1A.

[0166] At block 810, the terminal device 110 may receive, from a network device 120, first configuration information for configuring applicable functionality reporting for artificial intelligence (Al) / machine learning (ML) for at least one associated identity (ID). At block 820, the terminal device 110 may transmit, to the network device 210, based on the first configuration information, first functionality-related information comprising at least one entry corresponding to functionality information for AI / ML. In some embodiments, an entry may correspond to functionality information and may include an associated ID and at least one relaxation or reduced parameter for a corresponding applicable functionality reported for AI / ML.

[0167] In some embodiments, the first configuration information may include a functionality configuration ready for inference when it is applicable, and wherein the functionality configuration, as a part of the first configuration information, may include at least one critical parameter to which at least one relaxation or reduced parameter is able to be applied.

[0168] In some embodiments, the first configuration information may include a partial functionality configuration including at least one critical parameter to which at least one relaxation or reduced parameters is able to be applied.

[0169] In some embodiments, the relaxation or reduced parameter is reduced relative to a maximum configuration of a corresponding parameter supported for the corresponding applicable functionality indicated to the network device via capability reporting.

[0170] In some embodiments, the terminal device 110 may propose at least one relaxation or reduced parameter for an applicable functionality reported for AI / ML.

[0171] In some embodiments, the terminal device 110 may propose at least one relaxation or reduced parameter for an applicable functionality reported for AI / ML by determining a configuration for the at least one relaxation or reduced parameter based on at least one of following: a characteristic of an AI / ML modelat the terminal device side for the applicable functionality, a maximum configuration of a parameter associated with the at least one relaxation or reduced parameter, or a configuration for another relaxation or reduced parameter.

[0172] In some embodiments, the terminal device 110 may receive, from the network device 120, second configuration information for configuring an applicable functionality for AI / ML inference, wherein the second configuration information is generated based on a configuration for a relaxation or reduced parameter of the applicable functionality reported for AI / ML inference in the reporting information. The terminal device 110 may configure the applicable functionality for AI / ML inference according to the second configuration information.

[0173] In some embodiments, the terminal device 110 may transmit, to the network device 120, second functionality-related information based on detecting an update in at least one functionality for AI / ML, wherein the second functionality-related information may include updated information based on the update.

[0174] In some embodiments, the terminal device 110 may transmit, to the network device, an indication of a characteristic of an update in at least one functionality based on detecting the update.

[0175] In some embodiments, the characteristic of the update indicating at least one of following: an applicability update for an active functionality for AI / ML inference, wherein the applicability update may include an updated configuration for a relaxation or reduced parameter that increases the active functionality’s capability; an applicability update for an active functionality for AI / ML inference, wherein the applicability update comprises an updated configuration for a relaxation or reduced parameter that decreases the active functionality’s capability; or an applicability update for an inactive functionality for AI / ML, wherein the applicability update comprises at least one of following: the inactive functionality is updated from applicable to be non-applicable, the inactive functionality is updated from non-applicable to be applicable, or a configuration for at least one relaxation or reduced parameter for the inactive functionality is updated.

[0176] In some embodiments, the terminal device 110 may receive, from the network device 120, a request for information related to applicable functionality update. The terminal device 110 may transmit, to the network device 120, second functionality-related information based on the received request.

[0177] In some embodiments, the second functionality-related information is different from the first functionality-related information, and wherein a difference between the second functionality-related information and the first functionality-related information may include at least one of following: a first entry in the first functionality-related information is updated in the second functionality-related information to indicate a previously applicable functionality for AI / ML associated with the first entry is inapplicable, wherein the first entry comprises a field indicating a cause for an inapplicability of the previously applicable functionality for AI / ML associated with the first entry; a second entry in the first functionality-related information is updated in the second functionality-related information to indicate a previously inapplicable functionality for AI / ML associated with the second entry is applicable; a third entry not in the first functionality-related information isadded into the second functionality-related information, wherein the third entry is corresponding to a new applicable functionality for AI / ML, wherein the third entry comprises an associated ID and at least one relaxation or reduced parameter for the new applicable functionality for AI / ML; a configuration for a relaxation or reduced parameter in a fourth entry in the first functionality-related information is updated in the second updated functionality-related information; or a fifth entry in the functionality-related information is removed from the updated functionality-related information.

[0178] In some embodiments, the terminal device 110 may receive, from the network device 120, third configuration information that is generated based on the updated functionality-related information, and may perform at least one of following based on the received third configuration information: update a configuration of a currently activated functionality for AI / ML inference; switch to a newly activated applicable functionality for AI / ML inference from a previously activated functionality for AI / ML inference; and fallback to a non-AI / ML mechanism.

[0179] In some embodiments, based on the associated ID in an entry being related to a beam management use case, a relaxation or reduced parameter in the entry may include at least one of following: a number of predicted beams in Set A; an observation window indicating a minimum time duration for measuring nonzero power channel state information reference signal (NZP-CSI-RS) resources; a prediction window indicating a maximum time duration that the NZP-CSI-RS resources is predicted based on Set B; a measured downlink (DL) resource signal (RS) indicating a support of using synchronized signal block (SSB) and / or CS I - RS-based reference signal received power (RSRP) measurements; a measured Set B DL RS dimension indicating an updated number of NZP-CSI-RS resources to be measured and used for predicting a best K- NZP CSI-RS resource; a measured DL RS Set B pattern indicating a restriction on the updated number of NZP-CSI-RS resources to be measured and used for predicting a best K-NZP CSI-RS resource; a predicted Set A DL RS dimension indicating an updated number of NZP-CSI-RS resources to be configured as prediction NZP CSI-RS resource sets; performance monitoring indicating an updated / preferred performance monitoring type; or measured DL RS performance monitoring indicative of supported measurement for a predicted DL RS set.

[0180] FIG. 9 illustrates a flowchart of a method 900 implemented at a network device in accordance with some example embodiments of the present disclosure. For the purpose of discussion, the method 900 will be described from the perspective of the network device 120 with reference to FIG. 1A.

[0181] At block 910, the network device 120 may transmit, to a terminal device 110, first configuration information for configuring applicable functionality reporting for artificial intelligence (Al) / machine learning (ML) for at least one associated identity (ID). The network device 120 may receive, from the terminal device 110, based on the first configuration information, first functionality-related information comprising at least one entry corresponding to functionality information for AI / ML. In some embodiments, an entry may correspond to functionality information and may include an associated ID and at least one relaxation or reducedparameter for a corresponding applicable functionality reported for AI / ML.

[0182] In some embodiments, the first configuration information may include a functionality configuration ready for inference when it is applicable, and wherein the functionality configuration, as a part of the first configuration information, comprises at least one critical parameter to which at least one relaxation or reduced parameter is able to be applied.

[0183] In some embodiments, the first configuration information may include a partial functionality configuration comprising at least one critical parameter to which at least one relaxation or reduced parameters is able to be applied.

[0184] In some embodiments, the relaxation or reduced parameter is reduced relative to a maximum configuration of a corresponding parameter supported for the corresponding applicable functionality indicated to the network device via capability reporting.

[0185] In some embodiments, a configuration for the at least one relaxation or reduced parameter is determined based on at least one of following: a characteristic of an AI / ML model at the terminal device side for the corresponding applicable functionality, a maximum configuration of a parameter associated with the at least one relaxation or reduced parameter, or a configuration for another relaxation or reduced parameter.

[0186] In some embodiments, the network device 120 may evaluate an applicable functionality for AI / ML in the functionality-related information based on a configuration for a relaxation or reduced parameter for the applicable functionality reported for AI / ML. The network device 120 may select the applicable functionality for AI / ML inference based on the evaluation. The network device 120 may generate second configuration information for configuring the applicable functionality for AI / ML inference. The network device 120 may transmit, to the terminal device 110, the second configuration information.

[0187] In some embodiments, the network device 120 may activate the applicable functionality for AI / ML inference.

[0188] In some embodiments, the network device 120 may receive, from the terminal device 110, second functionality-related information, wherein the second information is transmitted by the terminal device based on detecting an update in at least one functionality for AI / ML, and wherein the second functionality-related information comprises updated information based on the update.

[0189] In some embodiments, the network device 120 may receive, from the terminal device 110, an indication of a characteristic of an update occurring in at least one applicable functionality for AI / ML.

[0190] In some embodiments, the characteristic of the update indicating at least one of following: an applicability update for an active functionality for AI / ML inference, wherein the applicability update may include an updated configuration for a relaxation or reduced parameter that increases the active functionality’s capability; an applicability update for an active functionality for AI / ML inference, wherein the applicability update may include an updated configuration for a relaxation or reduced parameter that decreases the active functionality’s capability; or an applicability update for an inactive functionality for AI / ML,wherein the applicability update may include at least one of following: the inactive functionality is updated from applicable to be non-applicable, the inactive functionality is updated from non-applicable to be applicable, or a configuration for at least one relaxation or reduced parameter for the inactive functionality is updated.

[0191] In some embodiments, the network device 120 may transmit, to the terminal device 110, a request for information related to applicable functionality update, and may receive, from the terminal device 110, second functionality-related information that is transmitted based on the request.

[0192] In some embodiments, the second functionality-related information is different from the first functionality-related information, and wherein a difference between the second functionality-related information and the first functionality-related information may include at least one of following: a first entry in the first functionality-related information is updated in the second functionality-related information to indicate a previously applicable functionality for AI / ML associated with the first entry is inapplicable, wherein the first entry may include a field indicating a cause for an inapplicability of the previously applicable functionality for AI / ML associated with the first entry; a second entry in the first functionality-related information is updated in the second functionality-related information to indicate a previously inapplicable functionality for AI / ML associated with the second entry is applicable; a third entry not in the first functionality-related information is added into the second functionality-related information, wherein the third entry is corresponding to a new applicable functionality for AI / ML, wherein the third entry may include an associated ID and at least one relaxation or reduced parameter for the new applicable functionality for AI / ML; a configuration for a relaxation or reduced parameter in a fourth entry in the first functionality-related information is updated in the second updated functionality-related information; or a fifth entry in the functionality-related information is removed from the updated functionality-related information.

[0193] In some embodiments, the network device 120 may evaluate the second functionality-related information, may generate third configuration information based on the evaluation, and may transmit the third configuration information to the terminal device.

[0194] In some embodiments, the third configuration may be used to configure the terminal device 110 to perform at least one of following: updating a configuration of a currently activated functionality for AI / ML inference; switching to a newly activated applicable functionality for AI / ML inference from a previously activated functionality for AI / ML inference; or fallbacking to a non-AI / ML mechanism.

[0195] In some embodiments, based on the associated ID in an entry being related to a beam management use case, a relaxation or reduced parameter in the entry may include at least one of following: a number of predicted beams in Set A; an observation window indicating a minimum time duration for measuring nonzero power channel state information reference signal (NZP-CSI-RS) resources; a prediction window indicating a maximum time duration that the NZP-CSI-RS resources is predicted based on Set B; a measured downlink (DL) resource signal (RS) indicating a support of using synchronized signal block (SSB) and / or CS I - RS-based reference signal received power (RSRP) measurements; a measured Set B DL RS dimensionindicating an updated number of NZP-CSI-RS resources to be measured and used for predicting a best K- NZP CSI-RS resource; a measured DL RS Set B pattern indicating a restriction on the updated number of NZP-CSI-RS resources to be measured and used for predicting a best K-NZP CSI-RS resource; a predicted Set A DL RS dimension indicating an updated number of NZP-CSI-RS resources to be configured as prediction NZP CSI-RS resource sets; performance monitoring indicating an updated / preferred performance monitoring type; or measured DL RS performance monitoring indicative of supported measurement for a predicted DL RS set.

[0196] In some embodiments, an apparatus capable of performing any of the method 800 (for example, the terminal device 110) may include means for performing the respective steps of the method 800. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module.

[0197] In some embodiments, the apparatus may include means for receiving, from a network device 120, first configuration information for configuring applicable functionality reporting for artificial intelligence (Al) / machine learning (ML) for at least one associated identity (ID). The apparatus may include means for transmitting, to the network device 120, based on the first configuration information, first functionality-related information comprising at least one entry corresponding to functionality information for AI / ML. In some embodiments, an entry may correspond to functionality information and may include an associated ID and at least one relaxation or reduced parameter for a corresponding applicable functionality reported for AI / ML.

[0198] In some embodiments, the first configuration information may include a functionality configuration ready for inference when it is applicable, and wherein the functionality configuration, as a part of the first configuration information, may include at least one critical parameter to which at least one relaxation or reduced parameter is able to be applied.

[0199] In some embodiments, the first configuration information may include a partial functionality configuration including at least one critical parameter to which at least one relaxation or reduced parameters is able to be applied.

[0200] In some embodiments, the relaxation or reduced parameter is reduced relative to a maximum configuration of a corresponding parameter supported for the corresponding applicable functionality indicated to the network device via capability reporting.

[0201] In some embodiments, the apparatus may include means for proposing at least one relaxation or reduced parameter for an applicable functionality reported for AI / ML.

[0202] In some embodiments, the means for proposing at least one relaxation or reduced parameter for an applicable functionality reported for AI / ML may include means for determining a configuration for the at least one relaxation or reduced parameter based on at least one of following: a characteristic of an AI / ML model at the terminal device side for the applicable functionality, a maximum configuration of a parameter associated with the at least one relaxation or reduced parameter, or a configuration for another relaxation orreduced parameter.

[0203] In some embodiments, the apparatus may include means for receiving, from the network device 120, second configuration information for configuring an applicable functionality for AI / ML inference, wherein the second configuration information is generated based on a configuration for a relaxation or reduced parameter of the applicable functionality reported for AI / ML inference in the reporting information. The apparatus may include means for configuring the applicable functionality for AI / ML inference according to the second configuration information.

[0204] In some embodiments, the apparatus may include means for transmitting, to the network device 120, second functionality-related information based on detecting an update in at least one functionality for AI / ML, wherein the second functionality-related information may include updated information based on the update.

[0205] In some embodiments, the apparatus may include means for transmitting, to the network device, an indication of a characteristic of an update in at least one functionality based on detecting the update.

[0206] In some embodiments, the characteristic of the update indicating at least one of following: an applicability update for an active functionality for AI / ML inference, wherein the applicability update may include an updated configuration for a relaxation or reduced parameter that increases the active functionality’s capability; an applicability update for an active functionality for AI / ML inference, wherein the applicability update comprises an updated configuration for a relaxation or reduced parameter that decreases the active functionality’s capability; or an applicability update for an inactive functionality for AI / ML, wherein the applicability update comprises at least one of following: the inactive functionality is updated from applicable to be non-applicable, the inactive functionality is updated from non-applicable to be applicable, or a configuration for at least one relaxation or reduced parameter for the inactive functionality is updated.

[0207] In some embodiments, the apparatus may include means for receiving, from the network device 120, a request for information related to applicable functionality update. The apparatus may include means for transmitting, to the network device 120, second functionality-related information based on the received request.

[0208] In some embodiments, the second functionality-related information is different from the first functionality-related information, and wherein a difference between the second functionality-related information and the first functionality-related information may include at least one of following: a first entry in the first functionality-related information is updated in the second functionality-related information to indicate a previously applicable functionality for AI / ML associated with the first entry is inapplicable, wherein the first entry comprises a field indicating a cause for an inapplicability of the previously applicable functionality for AI / ML associated with the first entry; a second entry in the first functionality-related information is updated in the second functionality-related information to indicate a previously inapplicable functionality for AI / ML associated with the second entry is applicable; a third entry not in the first functionality-related information isadded into the second functionality-related information, wherein the third entry is corresponding to a new applicable functionality for AI / ML, wherein the third entry comprises an associated ID and at least one relaxation or reduced parameter for the new applicable functionality for AI / ML; a configuration for a relaxation or reduced parameter in a fourth entry in the first functionality-related information is updated in the second updated functionality-related information; or a fifth entry in the functionality-related information is removed from the updated functionality-related information.

[0209] In some embodiments, the apparatus may include means for receiving, from the network device 120, third configuration information that is generated based on the updated functionality-related information, and may include means for performing at least one of following based on the received third configuration information: update a configuration of a currently activated functionality for AI / ML inference; switch to a newly activated applicable functionality for AI / ML inference from a previously activated functionality for AI / ML inference; and fallback to a non-AI / ML mechanism.

[0210] In some embodiments, based on the associated ID in an entry being related to a beam management use case, a relaxation or reduced parameter in the entry may include at least one of following: a number of predicted beams in Set A; an observation window indicating a minimum time duration for measuring nonzero power channel state information reference signal (NZP-CSI-RS) resources; a prediction window indicating a maximum time duration that the NZP-CSI-RS resources is predicted based on Set B; a measured downlink (DL) resource signal (RS) indicating a support of using synchronized signal block (SSB) and / or CS I - RS-based reference signal received power (RSRP) measurements; a measured Set B DL RS dimension indicating an updated number of NZP-CSI-RS resources to be measured and used for predicting a best K- NZP CSI-RS resource; a measured DL RS Set B pattern indicating a restriction on the updated number of NZP-CSI-RS resources to be measured and used for predicting a best K-NZP CSI-RS resource; a predicted Set A DL RS dimension indicating an updated number of NZP-CSI-RS resources to be configured as prediction NZP CSI-RS resource sets; performance monitoring indicating an updated / preferred performance monitoring type; or measured DL RS performance monitoring indicative of supported measurement for a predicted DL RS set.

[0211] In some embodiments, an apparatus capable of performing any of the method 900 (for example, the network device 120) may include means for performing the respective steps of the method 900. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module.

[0212] In some embodiments, the apparatus may include means for transmitting, to a terminal device 110, first configuration information for configuring applicable functionality reporting for artificial intelligence (Al) / machine learning (ML) for at least one associated identity (ID). The apparatus may include means for receiving, from the terminal device 110, based on the first configuration information, first functionality-related information comprising at least one entry corresponding to functionality information for AI / ML. In someembodiments, an entry may correspond to functionality information and may include an associated ID and at least one relaxation or reduced parameter for a corresponding applicable functionality reported for AI / ML.

[0213] In some embodiments, the first configuration information may include a functionality configuration ready for inference when it is applicable, and wherein the functionality configuration, as a part of the first configuration information, comprises at least one critical parameter to which at least one relaxation or reduced parameter is able to be applied.

[0214] In some embodiments, the first configuration information may include a partial functionality configuration comprising at least one critical parameter to which at least one relaxation or reduced parameters is able to be applied.

[0215] In some embodiments, the relaxation or reduced parameter is reduced relative to a maximum configuration of a corresponding parameter supported for the corresponding applicable functionality indicated to the network device via capability reporting.

[0216] In some embodiments, a configuration for the at least one relaxation or reduced parameter is determined based on at least one of following: a characteristic of an AI / ML model at the terminal device side for the corresponding applicable functionality, a maximum configuration of a parameter associated with the at least one relaxation or reduced parameter, or a configuration for another relaxation or reduced parameter.

[0217] In some embodiments, the apparatus may include means for evaluating an applicable functionality for AI / ML in the functionality-related information based on a configuration for a relaxation or reduced parameter for the applicable functionality reported for AI / ML. The apparatus may include means for selecting the applicable functionality for AI / ML inference based on the evaluation. The apparatus may include means for generating second configuration information for configuring the applicable functionality for AI / ML inference. The apparatus may include means for transmitting, to the terminal device 110, the second configuration information.

[0218] In some embodiments, the apparatus may include means activating the applicable functionality for AI / ML inference.

[0219] In some embodiments, the apparatus may include means for receiving, from the terminal device 110, second functionality-related information, wherein the second information is transmitted by the terminal device based on detecting an update in at least one functionality for AI / ML, and wherein the second functionality-related information comprises updated information based on the update.

[0220] In some embodiments, the apparatus may include means for receiving, from the terminal device 110, an indication of a characteristic of an update occurring in at least one applicable functionality for AI / ML.

[0221] In some embodiments, the characteristic of the update indicating at least one of following: an applicability update for an active functionality for AI / ML inference, wherein the applicability update may include an updated configuration for a relaxation or reduced parameter that increases the active functionality’s capability; an applicability update for an active functionality for AI / ML inference, wherein theapplicability update may include an updated configuration for a relaxation or reduced parameter that decreases the active functionality’s capability; or an applicability update for an inactive functionality for AI / ML, wherein the applicability update may include at least one of following: the inactive functionality is updated from applicable to be non-applicable, the inactive functionality is updated from non-applicable to be applicable, or a configuration for at least one relaxation or reduced parameter for the inactive functionality is updated.

[0222] In some embodiments, the apparatus may include means for transmitting, to the terminal device 110, a request for information related to applicable functionality update, and the apparatus may include means for receiving, from the terminal device 110, second functionality-related information that is transmitted based on the request.

[0223] In some embodiments, the second functionality-related information is different from the first functionality-related information, and wherein a difference between the second functionality-related information and the first functionality-related information may include at least one of following: a first entry in the first functionality-related information is updated in the second functionality-related information to indicate a previously applicable functionality for AI / ML associated with the first entry is inapplicable, wherein the first entry may include a field indicating a cause for an inapplicability of the previously applicable functionality for AI / ML associated with the first entry; a second entry in the first functionality-related information is updated in the second functionality-related information to indicate a previously inapplicable functionality for AI / ML associated with the second entry is applicable; a third entry not in the first functionality-related information is added into the second functionality-related information, wherein the third entry is corresponding to a new applicable functionality for AI / ML, wherein the third entry may include an associated ID and at least one relaxation or reduced parameter for the new applicable functionality for AI / ML; a configuration for a relaxation or reduced parameter in a fourth entry in the first functionality-related information is updated in the second updated functionality-related information; or a fifth entry in the functionality-related information is removed from the updated functionality-related information.

[0224] In some embodiments, the apparatus may include means for evaluating the second functionality- related information, may include means for generating third configuration information based on the evaluation, and may include means for transmitting the third configuration information to the terminal device.

[0225] In some embodiments, the third configuration may be used to configure the terminal device 110 to perform at least one of following: updating a configuration of a currently activated functionality for AI / ML inference; switching to a newly activated applicable functionality for AI / ML inference from a previously activated functionality for AI / ML inference; or fallbacking to a non-AI / ML mechanism.

[0226] In some embodiments, based on the associated ID in an entry being related to a beam management use case, a relaxation or reduced parameter in the entry may include at least one of following: a number of predicted beams in Set A; an observation window indicating a minimum time duration for measuring nonzero power channel state information reference signal (NZP-CSI-RS) resources; a prediction windowindicating a maximum time duration that the NZP-CSI-RS resources is predicted based on Set B; a measured downlink (DL) resource signal (RS) indicating a support of using synchronized signal block (SSB) and / or CS I - RS-based reference signal received power (RSRP) measurements; a measured Set B DL RS dimension indicating an updated number of NZP-CSI-RS resources to be measured and used for predicting a best K- NZP CSI-RS resource; a measured DL RS Set B pattern indicating a restriction on the updated number of NZP-CSI-RS resources to be measured and used for predicting a best K-NZP CSI-RS resource; a predicted Set A DL RS dimension indicating an updated number of NZP-CSI-RS resources to be configured as prediction NZP CSI-RS resource sets; performance monitoring indicating an updated / preferred performance monitoring type; or measured DL RS performance monitoring indicative of supported measurement for a predicted DL RS set.

[0227] FIG. 10 illustrates a flowchart of a method 1000 implemented at a terminal device 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 terminal device 110 with reference to FIG. 1 A.

[0228] At block 1010, the terminal device 120 may detect an update in at least one functionality for artificial intelligence (Al) / machine learning (ML). At block 1020, the terminal device 110, based on detecting the update in the at least one functionality for AI / ML, may transmit, to a network device, information indicating the update.

[0229] In some example embodiments, the update is detected based on at least one of: first configuration information for configuring applicable functionality reporting for AI / ML for at least one associated ID that is received from the network device, or first functionality-related information.

[0230] In some example embodiments, the terminal device 110 may receive, from the network device 120, the first configuration information for configuring the applicable functionality reporting for AI / ML for the at least one associated ID. The terminal device 110 may receive, from the network device 120, the first configuration information for configuring the applicable functionality reporting for AI / ML for the at least one associated ID. In some embodiments, an entry may correspond to functionality information and may include at least one of: at least one relaxation or reduced parameter for a corresponding applicable functionality reported for AI / ML or a removal of at least one previously proposed relaxation or reduced parameter.

[0231] In some example embodiments, the relaxation or reduced parameter is reduced relative to a maximum configuration of a corresponding parameter supported for the corresponding applicable functionality indicated to the network device via capability reporting.

[0232] In some example embodiments, the terminal device 110 may propose at least one relaxation or reduced parameter for an applicable functionality reported for AI / ML.

[0233] In some example embodiments, the terminal device 110 may propose at least one relaxation or reduced parameter by determining a configuration for the at least one relaxation or reduced parameter basedon at least one of following: a characteristic of an AI / ML model at the terminal device side for the applicable functionality, a maximum configuration of a parameter associated with the at least one relaxation or reduced parameter, or a configuration for another relaxation or reduced parameter.

[0234] In some example embodiments, the terminal device 110 may receive, from the network device 120, second configuration information for configuring an applicable functionality for AI / ML inference, wherein the second configuration information is generated based on a configuration of a relaxation or reduced parameter of the applicable functionality for AI / ML inference in the first reporting information. The terminal device 110 may configure the applicable functionality for AI / ML inference based on the second configuration information.

[0235] In some example embodiments, the information may include second functionality-related information indicating the update in a functionality for AI / ML, wherein the second functionality-related information may include at least one updated entry relative to the first functionality-related information, and wherein an updated entry of the at least one updated entry may include at least one of: at least one relaxation or reduced parameter for a corresponding applicable functionality reported for AI / ML or a removal of at least one previously proposed relaxation or reduced parameter.

[0236] In some example embodiments, the information may include an indication of a characteristic of the update in a functionality for AI / ML.

[0237] In some example embodiments, the characteristic of the update indicating at least one of following: an applicability update for an active functionality for AI / ML inference, wherein the applicability update may include an updated configuration for a relaxation or reduced parameter that increases the active functionality’s capability; an applicability update for an active functionality for AI / ML inference, wherein the applicability update may include an updated configuration for a relaxation or reduced parameter that decreases the active functionality’s capability; or an applicability update for an inactive functionality for AI / ML, wherein the applicability update may include at least one of following: the inactive functionality is updated from applicable to be non-applicable, the inactive functionality is updated from non-applicable to be applicable, or a configuration for at least one relaxation or reduced parameter for the inactive functionality is updated.

[0238] In some example embodiments, the terminal device 110 may receive, from the network device 120, a request for information related to applicable functionality update. The terminal device 110 may transmit, to the network device 120, second functionality-related information based on the received request, wherein the second functionality-related information may include at least one updated entry relative to the first functionality-related information, and wherein an updated entry of the at least one updated entry may include at least one of: at least one relaxation or reduced parameter for a corresponding applicable functionality reported for AI / ML or a removal of at least one previously proposed relaxation or reduced parameter.

[0239] In some embodiments, the second functionality-related information is different from the first functionality-related information, and wherein a difference between the second functionality-related information and the first functionality-related information may include at least one of following: a first entry inthe first functionality-related information is updated in the second functionality-related information to indicate a previously applicable functionality for AI / ML associated with the first entry is inapplicable, wherein the first entry may include a field indicating a cause for an inapplicability of the previously applicable functionality for AI / ML associated with the first entry; a second entry in the first functionality-related information is updated in the second functionality-related information to indicate a previously inapplicable functionality for AI / ML associated with the second entry is applicable; a third entry not in the first functionality-related information is added into the second functionality-related information, wherein the third entry is corresponding to a new applicable functionality for AI / ML, wherein the third entry may include an associated ID and at least one relaxation or reduced parameter for the new applicable functionality for AI / ML; a configuration for a relaxation or reduced parameter in a fourth entry in the first functionality-related information is updated in the second updated functionality-related information; or a fifth entry in the functionality-related information is removed from the updated functionality-related information.

[0240] In some embodiments, the terminal device 110 may receive, from the network device 120, a third configuration information that is generated based on the second functionality-related information. The terminal device 110 may perform at least one of following based on the received third configuration information: update a configuration of a currently activated functionality for AI / ML inference; switch to a newly activated applicable functionality for AI / ML inference from a previous activated functionality for AI / ML inference; or fallback to a non-AI / ML mechanism.

[0241] In some embodiments, based on the associated ID in an entry being related to a beam management use case, a relaxation or reduced parameter in the entry may include at least one of following: a number of predicted beams in Set A; an observation window indicating a minimum time duration for measuring nonzero power channel state information reference signal (NZP-CSI-RS) resources; a prediction window indicating a maximum time duration that the NZP-CSI-RS resources is predicted based on Set B; a measured downlink (DL) resource signal (RS) indicating a support of using synchronized signal block (SSB) and / or CS I - RS-based reference signal received power (RSRP) measurements; a measured Set B DL RS dimension indicating an updated number of NZP-CSI-RS resources to be measured and used for predicting a best K- NZP CSI-RS resource; a measured DL RS Set B pattern indicating a restriction on the updated number of NZP-CSI-RS resources to be measured and used for predicting a best K-NZP CSI-RS resource; a predicted Set A DL RS dimension indicating an updated number of NZP-CSI-RS resources to be configured as prediction NZP CSI-RS resource sets; performance monitoring indicating an updated / preferred performance monitoring type; or measured DL RS performance monitoring indicative of supported measurement for a predicted DL RS set.

[0242] FIG. 11 illustrates a flowchart of a method 1100 implemented at a network device 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 network device 120 with reference to FIG. 1A.

[0243] At block 1110, the network device 120 may receive, from a terminal device 110, information indicating an update in at least one functionality for artificial intelligence (Al) / machine learning (ML).

[0244] In some embodiments, the update is detected by the terminal device based on at least one of: first configuration information for configuring applicable functionality reporting for AI / ML for at least one associated ID that is transmitted to the terminal device, or first functionality-related information.

[0245] In some embodiments, the network device 120 may transmit, to the terminal device 110, the first configuration information for configuring the applicable functionality reporting for AI / ML for the at least one associated ID. The network device 120 may receive, from the terminal device 110, based on the first configuration information, the first functionality-related information comprising at least one entry corresponding functionality information. In some embodiments, an entry may correspond to functionality information and may include at least one of: at least one relaxation or reduced parameter for a corresponding applicable functionality reported for AI / ML or a removal of at least one previously proposed relaxation or reduced parameter.

[0246] In some embodiments, the relaxation or reduced parameter is reduced relative to a maximum configuration of a corresponding parameter supported for the corresponding applicable functionality indicated via capability reporting.

[0247] In some embodiments, a configuration for the at least one relaxation or reduced parameter is determined based on at least one of following: a characteristic of an AI / ML model at the terminal device side for the corresponding applicable functionality, a maximum configuration of the corresponding parameter allowed for the corresponding applicable functionality, or a configuration for another relaxation or reduced parameter.

[0248] In some embodiments, the network device 120 may evaluate an applicable functionality for AI / ML in the first functionality-related information based on a configuration for a relaxation or reduced parameter for the applicable functionality reported for AI / ML. The network device 120 may select the applicable functionality for AI / ML inference based on the evaluation. The network device 120 may generate second configuration information for configuring the applicable functionality for AI / ML inference. The network device 120 may transmit, to the terminal device 110, the second configuration information.

[0249] In some embodiments, the network device 120 may activate the applicable functionality for AI / ML inference.

[0250] In some embodiments, the information may include second functionality-related information indicating the update in a functionality for AI / ML, and wherein the second functionality-related information may include at least one updated entry relative to the first functionality-related information, and wherein an updated entry of the at least one updated entry may include at least one of: at least one relaxation or reduced parameter for a corresponding applicable functionality reported for AI / ML or a removal of at least one previously proposed relaxation or reduced parameter.

[0251] In some embodiments, the information may include an indication of a characteristic of the update in a functionality for AI / ML.

[0252] In some embodiments, the characteristic of the update indicating at least one of following: an applicability update for an active functionality for AI / ML inference, wherein the applicability update may include an updated configuration for a relaxation or reduced parameter that increases the active functionality’s capability; an applicability update for an active functionality for AI / ML inference, wherein the applicability update may include an updated configuration for a relaxation or reduced parameter that decreases the active functionality’s capability; or an applicability update for an inactive functionality for AI / ML, wherein the applicability update may include at least one of following: the inactive functionality is updated from applicable to be non-applicable, the inactive functionality is updated from non-applicable to be applicable, or a configuration for at least one relaxation or reduced parameter for the inactive functionality is updated.

[0253] In some embodiments, the network device 120 may transmit, to the terminal device 110, a request for information related to applicable functionality update. The network device 120 may receive, from the terminal device 110, second functionality-related information transmitted based on the received request, wherein the second functionality-related information may include at least one updated entry relative to the first functionality-related information, and wherein an updated entry may include at least one of: at least one relaxation or reduced parameter for a corresponding applicable functionality reported for AI / ML or a removal of at least one previously proposed relaxation or reduced parameter.

[0254] In some embodiments, the second functionality-related information is different from the first functionality-related information, and wherein a difference between the second functionality-related information and the first functionality-related information may include at least one of following: a first entry in the first functionality-related information is updated in the second functionality-related information to indicate a previously applicable functionality for AI / ML associated with the first entry is inapplicable, wherein the first entry may include a field indicating a cause for an inapplicability of the previously applicable functionality for AI / ML associated with the first entry; a second entry in the first functionality-related information is updated in the second functionality-related information to indicate a previously inapplicable functionality for AI / ML associated with the second entry is applicable; a third entry not in the first functionality-related information is added into the second functionality-related information, wherein the third entry is corresponding to a new applicable functionality for AI / ML, wherein the third entry may include an associated ID and at least one relaxation or reduced parameter for the new applicable functionality for AI / ML; a configuration for a relaxation or reduced parameter in a fourth entry in the first functionality-related information is updated in the second updated functionality-related information; or a fifth entry in the functionality-related information is removed from the updated functionality-related information.

[0255] In some embodiments, the network device 120 may evaluate the second functionality-related information. The network device 120 may generate third configuration information based on the evaluation.The network device 120 may transmit the third configuration information to the terminal device.

[0256] In some embodiments, the third configuration is used to configure the terminal device to perform at least one of following: update a configuration of a currently activated functionality for AI / ML inference; switch to a newly activated applicable functionality for AI / ML inference from a previous activated functionality for AI / ML inference; or fallback to a non-AI / ML mechanism.

[0257] In some embodiments, based on the associated ID in an entry being related to a beam management use case, a relaxation or reduced parameter in the entry may include at least one of following: a number of predicted beams in Set A; an observation window indicating a minimum time duration for measuring nonzero power channel state information reference signal (NZP-CSI-RS) resources; a prediction window indicating a maximum time duration that the NZP-CSI-RS resources is predicted based on Set B; a measured downlink (DL) resource signal (RS) indicating a support of using synchronized signal block (SSB) and / or CS I - RS-based reference signal received power (RSRP) measurements; a measured Set B DL RS dimension indicating an updated number of NZP-CSI-RS resources to be measured and used for predicting a best K- NZP CSI-RS resource; a measured DL RS Set B pattern indicating a restriction on the updated number of NZP-CSI-RS resources to be measured and used for predicting a best K-NZP CSI-RS resource; a predicted Set A DL RS dimension indicating an updated number of NZP-CSI-RS resources to be configured as prediction NZP CSI-RS resource sets; performance monitoring indicating an updated / preferred performance monitoring type; or measured DL RS performance monitoring indicative of supported measurement for a predicted DL RS set.

[0258] In some embodiments, an apparatus capable of performing any of the method 1000 (for example, the terminal device 110) may include means for performing the respective steps 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.

[0259] In some embodiments, the apparatus may include means for detecting an update in at least one functionality for artificial intelligence (Al) / machine learning (ML). The apparatus may include means for, based on detecting the update in the at least one functionality for AI / ML, transmitting, to a network device, information indicating the update.

[0260] In some example embodiments, the update is detected based on at least one of: first configuration information for configuring applicable functionality reporting for AI / ML for at least one associated ID that is received from the network device, or first functionality-related information.

[0261] In some example embodiments, the apparatus may include means for receiving, from the network device 120, the first configuration information for configuring the applicable functionality reporting for AI / ML for the at least one associated ID. The apparatus may include means for receiving, from the network device 120, the first configuration information for configuring the applicable functionality reporting for AI / ML for the at least one associated ID. In some embodiments, an entry may correspond to functionality informationand may include at least one of: at least one relaxation or reduced parameter for a corresponding applicable functionality reported for AI / ML or a removal of at least one previously proposed relaxation or reduced parameter.

[0262] In some example embodiments, the relaxation or reduced parameter is reduced relative to a maximum configuration of a corresponding parameter supported for the corresponding applicable functionality indicated to the network device via capability reporting.

[0263] In some example embodiments, the apparatus may include means for proposing at least one relaxation or reduced parameter for an applicable functionality reported for AI / ML.

[0264] In some example embodiments, the means for proposing at least one relaxation or reduced parameter may include means for determining a configuration for the at least one relaxation or reduced parameter based on at least one of following: a characteristic of an AI / ML model at the terminal device side for the applicable functionality, a maximum configuration of a parameter associated with the at least one relaxation or reduced parameter, or a configuration for another relaxation or reduced parameter.

[0265] In some example embodiments, the apparatus may include means for receiving, from the network device 120, second configuration information for configuring an applicable functionality for AI / ML inference, wherein the second configuration information is generated based on a configuration of a relaxation or reduced parameter of the applicable functionality for AI / ML inference in the first reporting information. The apparatus may include means for configuring the applicable functionality for AI / ML inference based on the second configuration information.

[0266] In some example embodiments, the information may include second functionality-related information indicating the update in a functionality for AI / ML, wherein the second functionality-related information may include at least one updated entry relative to the first functionality-related information, and wherein an updated entry of the at least one updated entry may include at least one of: at least one relaxation or reduced parameter for a corresponding applicable functionality reported for AI / ML or a removal of at least one previously proposed relaxation or reduced parameter.

[0267] In some example embodiments, the information may include an indication of a characteristic of the update in a functionality for AI / ML.

[0268] In some example embodiments, the characteristic of the update indicating at least one of following: an applicability update for an active functionality for AI / ML inference, wherein the applicability update may include an updated configuration for a relaxation or reduced parameter that increases the active functionality’s capability; an applicability update for an active functionality for AI / ML inference, wherein the applicability update may include an updated configuration for a relaxation or reduced parameter that decreases the active functionality’s capability; or an applicability update for an inactive functionality for AI / ML, wherein the applicability update may include at least one of following: the inactive functionality is updated from applicable to be non-applicable, the inactive functionality is updated from non-applicable to be applicable,or a configuration for at least one relaxation or reduced parameter for the inactive functionality is updated.

[0269] In some example embodiments, the apparatus may include means for receiving, from the network device 120, a request for information related to applicable functionality update. The apparatus may include means for transmitting, to the network device 120, second functionality-related information based on the received request, wherein the second functionality-related information may include at least one updated entry relative to the first functionality-related information, and wherein an updated entry of the at least one updated entry may include at least one of: at least one relaxation or reduced parameter for a corresponding applicable functionality reported for AI / ML or a removal of at least one previously proposed relaxation or reduced parameter.

[0270] In some embodiments, the second functionality-related information is different from the first functionality-related information, and wherein a difference between the second functionality-related information and the first functionality-related information may include at least one of following: a first entry in the first functionality-related information is updated in the second functionality-related information to indicate a previously applicable functionality for AI / ML associated with the first entry is inapplicable, wherein the first entry may include a field indicating a cause for an inapplicability of the previously applicable functionality for AI / ML associated with the first entry; a second entry in the first functionality-related information is updated in the second functionality-related information to indicate a previously inapplicable functionality for AI / ML associated with the second entry is applicable; a third entry not in the first functionality-related information is added into the second functionality-related information, wherein the third entry is corresponding to a new applicable functionality for AI / ML, wherein the third entry may include an associated ID and at least one relaxation or reduced parameter for the new applicable functionality for AI / ML; a configuration for a relaxation or reduced parameter in a fourth entry in the first functionality-related information is updated in the second updated functionality-related information; or a fifth entry in the functionality-related information is removed from the updated functionality-related information.

[0271] In some embodiments, the apparatus may include means for receiving, from the network device 120, a third configuration information that is generated based on the second functionality-related information, the apparatus may include means performing at least one of following based on the received third configuration information: update a configuration of a currently activated functionality for AI / ML inference; switch to a newly activated applicable functionality for AI / ML inference from a previous activated functionality for AI / ML inference; or fallback to a non-AI / ML mechanism.

[0272] In some embodiments, based on the associated ID in an entry being related to a beam management use case, a relaxation or reduced parameter in the entry may include at least one of following: a number of predicted beams in Set A; an observation window indicating a minimum time duration for measuring nonzero power channel state information reference signal (NZP-CSI-RS) resources; a prediction window indicating a maximum time duration that the NZP-CSI-RS resources is predicted based on Set B; a measureddownlink (DL) resource signal (RS) indicating a support of using synchronized signal block (SSB) and / or CS I - RS-based reference signal received power (RSRP) measurements; a measured Set B DL RS dimension indicating an updated number of NZP-CSI-RS resources to be measured and used for predicting a best K- NZP CSI-RS resource; a measured DL RS Set B pattern indicating a restriction on the updated number of NZP-CSI-RS resources to be measured and used for predicting a best K-NZP CSI-RS resource; a predicted Set A DL RS dimension indicating an updated number of NZP-CSI-RS resources to be configured as prediction NZP CSI-RS resource sets; performance monitoring indicating an updated / preferred performance monitoring type; or measured DL RS performance monitoring indicative of supported measurement for a predicted DL RS set.

[0273] In some embodiments, an apparatus capable of performing any of the method 1100 (for example, the network device 120) may include means for performing the respective steps 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.

[0274] In some embodiments, the apparatus may include means for receiving, from a terminal device 110, information indicating an update in at least one functionality for artificial intelligence (Al) / machine learning (ML).

[0275] In some embodiments, the update is detected by the terminal device based on at least one of: first configuration information for configuring applicable functionality reporting for AI / ML for at least one associated ID that is transmitted to the terminal device, or first functionality-related information.

[0276] In some embodiments, the apparatus may include means for transmitting, to the terminal device 110, the first configuration information for configuring the applicable functionality reporting for AI / ML for the at least one associated ID. The apparatus may include means for receiving, from the terminal device 110, based on the first configuration information, the first functionality-related information comprising at least one entry corresponding functionality information. In some embodiments, an entry may correspond to functionality information and may include at least one of: at least one relaxation or reduced parameter for a corresponding applicable functionality reported for AI / ML or a removal of at least one previously proposed relaxation or reduced parameter.

[0277] In some embodiments, the relaxation or reduced parameter is reduced relative to a maximum configuration of a corresponding parameter supported for the corresponding applicable functionality indicated via capability reporting.

[0278] In some embodiments, a configuration for the at least one relaxation or reduced parameter is determined based on at least one of following: a characteristic of an AI / ML model at the terminal device side for the corresponding applicable functionality, a maximum configuration of the corresponding parameter allowed for the corresponding applicable functionality, or a configuration for another relaxation or reduced parameter.

[0279] In some embodiments, the apparatus may include means for evaluating an applicable functionality for AI / ML in the first functionality-related information based on a configuration for a relaxation or reduced parameter for the applicable functionality reported for AI / ML. The apparatus may include means for selecting the applicable functionality for AI / ML inference based on the evaluation. The apparatus may include means for generating second configuration information for configuring the applicable functionality for AI / ML inference. The apparatus may include means for transmitting, to the terminal device 110, the second configuration information.

[0280] In some embodiments, the apparatus may include means for activating the applicable functionality for AI / ML inference.

[0281] In some embodiments, the information may include second functionality-related information indicating the update in a functionality for AI / ML, and wherein the second functionality-related information may include at least one updated entry relative to the first functionality-related information, and wherein an updated entry of the at least one updated entry may include at least one of: at least one relaxation or reduced parameter for a corresponding applicable functionality reported for AI / ML or a removal of at least one previously proposed relaxation or reduced parameter.

[0282] In some embodiments, the information may include an indication of a characteristic of the update in a functionality for AI / ML.

[0283] In some embodiments, the characteristic of the update indicating at least one of following: an applicability update for an active functionality for AI / ML inference, wherein the applicability update may include an updated configuration for a relaxation or reduced parameter that increases the active functionality’s capability; an applicability update for an active functionality for AI / ML inference, wherein the applicability update may include an updated configuration for a relaxation or reduced parameter that decreases the active functionality’s capability; or an applicability update for an inactive functionality for AI / ML, wherein the applicability update may include at least one of following: the inactive functionality is updated from applicable to be non-applicable, the inactive functionality is updated from non-applicable to be applicable, or a configuration for at least one relaxation or reduced parameter for the inactive functionality is updated.

[0284] In some embodiments, the apparatus may include means for transmitting, to the terminal device 110, a request for information related to applicable functionality update. The apparatus may include means for receiving, from the terminal device 110, second functionality-related information transmitted based on the received request, wherein the second functionality-related information may include at least one updated entry relative to the first functionality-related information, and wherein an updated entry may include at least one of: at least one relaxation or reduced parameter for a corresponding applicable functionality reported for AI / ML or a removal of at least one previously proposed relaxation or reduced parameter.

[0285] In some embodiments, the second functionality-related information is different from the first functionality-related information, and wherein a difference between the second functionality-relatedinformation and the first functionality-related information may include at least one of following: a first entry in the first functionality-related information is updated in the second functionality-related information to indicate a previously applicable functionality for AI / ML associated with the first entry is inapplicable, wherein the first entry may include a field indicating a cause for an inapplicability of the previously applicable functionality for AI / ML associated with the first entry; a second entry in the first functionality-related information is updated in the second functionality-related information to indicate a previously inapplicable functionality for AI / ML associated with the second entry is applicable; a third entry not in the first functionality-related information is added into the second functionality-related information, wherein the third entry is corresponding to a new applicable functionality for AI / ML, wherein the third entry may include an associated ID and at least one relaxation or reduced parameter for the new applicable functionality for AI / ML; a configuration for a relaxation or reduced parameter in a fourth entry in the first functionality-related information is updated in the second updated functionality-related information; or a fifth entry in the functionality-related information is removed from the updated functionality-related information.

[0286] In some embodiments, the apparatus may include means for evaluating the second functionality- related information. The apparatus may include means for generating third configuration information based on the evaluation. The apparatus may include means for transmitting the third configuration information to the terminal device.

[0287] In some embodiments, the third configuration is used to configure the terminal device to perform at least one of following: update a configuration of a currently activated functionality for AI / ML inference; switch to a newly activated applicable functionality for AI / ML inference from a previous activated functionality for AI / ML inference; or fallback to a non-AI / ML mechanism.

[0288] In some embodiments, based on the associated ID in an entry being related to a beam management use case, a relaxation or reduced parameter in the entry may include at least one of following: a number of predicted beams in Set A; an observation window indicating a minimum time duration for measuring nonzero power channel state information reference signal (NZP-CSI-RS) resources; a prediction window indicating a maximum time duration that the NZP-CSI-RS resources is predicted based on Set B; a measured downlink (DL) resource signal (RS) indicating a support of using synchronized signal block (SSB) and / or CS I - RS-based reference signal received power (RSRP) measurements; a measured Set B DL RS dimension indicating an updated number of NZP-CSI-RS resources to be measured and used for predicting a best K- NZP CSI-RS resource; a measured DL RS Set B pattern indicating a restriction on the updated number of NZP-CSI-RS resources to be measured and used for predicting a best K-NZP CSI-RS resource; a predicted Set A DL RS dimension indicating an updated number of NZP-CSI-RS resources to be configured as prediction NZP CSI-RS resource sets; performance monitoring indicating an updated / preferred performance monitoring type; or measured DL RS performance monitoring indicative of supported measurement for a predicted DL RS set.

[0289] FIG. 12 illustrates simplified block diagram of a device 1200 that is suitable for implementing some example embodiments of the present disclosure. The device 1200 may be provided to implement a communication device, for example, the terminal device 110 and the network device 120 as shown in FIG. 1A. As shown, the device 1200 may include one or more processors 1210, one or more memories 1220 coupled to the processor 1210, and one or more communication modules 1240 coupled to the processor 1210.

[0290] The communication module 1240 is for bidirectional communications. The communication module 1240 has at least one antenna to facilitate communication. The communication interface may represent any interface that is necessary for communication with other network elements.

[0291] The processor 1210 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 1200 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.

[0292] The memory 1220 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) 1224, an electrically programmable read only memory (EPROM), a flash memory, a hard disk, a compact disc (CD), a digital video disk (DVD), and other magnetic storage and / or optical storage. Examples of the volatile memories include, but are not limited to, a random access memory (RAM) 1222 and other volatile memories that will not last in the power-down duration.

[0293] A computer program 1230 includes computer executable instructions that are executed by the associated processor 1210. The program 1230 may be stored in the ROM 1224. The processor 1210 may perform any suitable actions and processing by loading the program 1230 into the RAM 1222.

[0294] The embodiments of the present disclosure may be implemented by means of the program 1230 so that the device 1200 may perform any process of the disclosure as discussed with reference to FIGS. 2- 11 . The embodiments of the present disclosure may also be implemented by hardware or by a combination of software and hardware.

[0295] In some example embodiments, the program 1230 may be tangibly contained in a computer readable medium which may be included in the device 1200 (such as in the memory 1220) or other storage devices that are accessible by the device 1200. The device 1200 may load the program 1230 from the computer readable medium to the RAM 1222 for execution. The computer readable medium may include any types of tangible non-volatile storage, such as ROM, EPROM, a flash memory, a hard disk, CD, DVD, and the like.

[0296] FIG. 13 illustrates a block diagram of an example of a computer readable medium 1200 in accordance with some example embodiments of the present disclosure. The computer readable medium1300 has the program 1330 stored thereon. It is noted that although the computer readable medium 1300 is depicted in form of CD or DVD in FIG. 13, the computer readable medium 1300 may be in any other form suitable for carry or hold the program 1230.

[0297] 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, while other aspects may be implemented in firmware or software which may be executed by a controller, microprocessor or other computing device. While 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.

[0298] The present disclosure also provides at least one computer program product tangibly stored on a non-transitory computer readable storage medium. The computer program product includes computerexecutable instructions, such as those included in program modules, being executed in a device on a target real or virtual processor, to carry out the method 800, 900, 1000 or 1100 as described above with reference to FIGS. 8-11. 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.

[0299] Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program codes 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 codes, 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.

[0300] In the context of the present disclosure, the computer program codes 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.

[0301] 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. 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).

[0302] Further, while 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, while 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. Certain features that are described in the context of separate embodiments may also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment may also be implemented in multiple embodiments separately or in any suitable subcombination.

[0303] 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 disclosed as example forms of implementing the claims.

Claims

WHAT IS CLAIMED IS:1 . A terminal device comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the terminal device at least to: detect an update in at least one functionality for artificial intelligence (Al) / machine learning (ML); and based on detecting the update in the at least one functionality for AI / ML, transmit, to a network device, information indicating the update.

2. The terminal device of claim 1 , wherein the update is detected based on at least one of: first configuration information for configuring applicable functionality reporting for AI / ML for at least one associated ID that is received from the network device, or first functionality-related information.

3. The terminal device of claim 2, wherein the terminal device is further caused to: receive, from the network device, the first configuration information for configuring the applicable functionality reporting for AI / ML for the at least one associated ID; and transmit, to the network device, based on the first configuration information, the first functionality- related information comprising at least one entry corresponding to functionality information for AI / ML, wherein an entry corresponds to functionality information and comprises at least one of: at least one relaxation or reduced parameter for a corresponding applicable functionality reported for AI / ML or a removal of at least one previously proposed relaxation or reduced parameter.

4. The terminal device of claim 3, wherein the relaxation or reduced parameter is reduced relative to a maximum configuration of a corresponding parameter supported for the corresponding applicable functionality indicated to the network device via capability reporting.

5. The terminal device of any of claims 3-4, wherein the terminal device is further caused to: propose at least one relaxation or reduced parameter for an applicable functionality reported forAI / ML.

6. The terminal device of claim 5, wherein the terminal device is caused to propose at least one relaxation or reduced parameter by: determining a configuration for the at least one relaxation or reduced parameter based on at least one of following: a characteristic of an AI / ML model at the terminal device side for the applicable functionality,a maximum configuration of a parameter associated with the at least one relaxation or reduced parameter, or a configuration for another relaxation or reduced parameter.

7. The terminal device of any of claims 2-6, wherein the terminal device is further caused to: receive, from the network device, second configuration information for configuring an applicable functionality for AI / ML inference, wherein the second configuration information is generated based on a configuration of a relaxation or reduced parameter of the applicable functionality for AI / ML inference in the first reporting information; and configure the applicable functionality for AI / ML inference based on the second configuration information.

8. The terminal device of any of claims 2-7, wherein the information comprises second functionality- related information indicating the update in a functionality for AI / ML, wherein the second functionality-related information comprises at least one updated entry relative to the first functionality-related information, and wherein an updated entry of the at least one updated entry comprises at least one of: at least one relaxation or reduced parameter for a corresponding applicable functionality reported for AI / ML or a removal of at least one previously proposed relaxation or reduced parameter.

9. The terminal device of any of claims 2-7, wherein the information comprises an indication of a characteristic of the update in a functionality for AI / ML.

10. The terminal device of claim 9, wherein the characteristic of the update comprises at least one of following: an applicability update for an active functionality for AI / ML inference, wherein the applicability update comprises an updated configuration for a relaxation or reduced parameter that increases the active functionality’s capability, an applicability update for an active functionality for AI / ML inference, wherein the applicability update comprises an updated configuration for a relaxation or reduced parameter that decreases the active functionality’s capability, or an applicability update for an inactive functionality for AI / ML, wherein the applicability update comprises at least one of following: the inactive functionality is updated from applicable to be non-applicable, the inactive functionality is update from non-applicable to be applicable, or a configuration for at least one relaxation or reduced parameter for the inactive functionality is updated.11 . The terminal device of any of claim 9 or 10, wherein the terminal device is further caused to:receive, from the network device, a request for information related to applicable functionality update; and transmit, to the network device, second functionality-related information based on the received request, wherein the second functionality-related information comprises at least one updated entry relative to the first functionality-related information, and wherein an updated entry of the at least one updated entry comprises at least one of: at least one relaxation or reduced parameter for a corresponding applicable functionality reported for AI / ML or a removal of at least one previously proposed relaxation or reduced parameter.

12. The terminal device of any of claims 8-11 , wherein the second functionality-related information is different from the first functionality-related information, and wherein a difference between the second functionality-related information and the first functionality-related information comprises at least one of following: a first entry in the first functionality-related information is updated in the second functionality-related information to indicate a previously applicable functionality for AI / ML associated with the first entry is inapplicable, wherein the first entry comprises a field indicating a cause for an inapplicability of the previously applicable functionality for AI / ML associated with the first entry; a second entry in the first functionality-related information is updated in the second functionality- related information to indicate a previously inapplicable functionality for AI / ML associated with the second entry is applicable; a third entry not in the first functionality-related information is added into the second functionality- related information, wherein the third entry is corresponding to a new applicable functionality for AI / ML, wherein the third entry comprises an associated ID and at least one relaxation or reduced parameter for the new applicable functionality for AI / ML; a configuration for a relaxation or reduced parameter in a fourth entry in the first functionality-related information is updated in the second functionality-related information; or a fifth entry in the functionality-related information is removed from the second functionality-related information.

13. The terminal device of any of claims 8-12, wherein the terminal device is further caused to: receive, from the network device, a third configuration information that is generated based on the second functionality-related information; and perform at least one of following based on the received third configuration information: update a configuration of a currently activated functionality for AI / ML inference;switch to a newly activated applicable functionality for AI / ML inference from a previous activated functionality for AI / ML inference; or fallback to a non-AI / ML mechanism.

14. The terminal device of any of claims 2-13, wherein based on the associated ID in an entry being related to a beam management use case, a relaxation or reduced parameter in the entry comprises at least one of following: a number of predicted beams in Set A; an observation window indicating a minimum time duration for measuring non-zero power channel state information reference signal (NZP-CSI-RS) resources; a prediction window indicating a maximum time duration that the NZP-CSI-RS resources is predicted based on Set B; a measured downlink (DL) resource signal (RS) indicating a support of using synchronized signal block (SSB) and / or CSI-RS-based reference signal received power (RSRP) measurements; a measured Set B DL RS dimension indicating an updated number of NZP-CSI-RS resources to be measured and used for predicting a best K-NZP CSI-RS resource; a measured DL RS Set B pattern indicating a restriction on the updated number of NZP-CSI-RS resources to be measured and used for predicting a best K-NZP CSI-RS resource; a predicted Set A DL RS dimension indicating an updated number of NZP-CSI-RS resources to be configured as prediction NZP CSI-RS resource sets; performance monitoring indicating an updated / preferred performance monitoring type; or measured DL RS performance monitoring indicative of supported measurement for a predicted DL RS set.

15. A network device comprising: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the network device at least to: receive, from a terminal device, information indicating an update in at least one functionality for artificial intelligence (Al) / machine learning (ML).

16. The network device of claim 15, wherein the update is detected by the terminal device based on at least one of: first configuration information for configuring applicable functionality reporting for AI / ML for at least one associated ID that is transmitted to the terminal device, or first functionality-related information.

17. The network device of claim 16, wherein the network device is further caused to: transmit, to the terminal device, the first configuration information for configuring the applicable functionality reporting for AI / ML for the at least one associated ID; and receive, from the terminal device, based on the first configuration information, the first functionality- related information comprising at least one entry corresponding functionality information, wherein an entry corresponds to functionality information and comprises at least one of: at least one relaxation or reduced parameter for a corresponding applicable functionality reported for AI / ML or a removal of at least one previously proposed relaxation or reduced parameter.

18. The network device of claim 17, wherein the relaxation or reduced parameter is reduced relative to a maximum configuration of a corresponding parameter supported for the corresponding applicable functionality indicated via capability reporting.

19. The network device of claim 17 or 18, wherein a configuration for the at least one relaxation or reduced parameter is determined based on at least one of following: a characteristic of an AI / ML model at the terminal device side for the corresponding applicable functionality, a maximum configuration of the corresponding parameter allowed for the corresponding applicable functionality, or a configuration for another relaxation or reduced parameter.

20. The network device of any of claims 16-19, wherein the network device is further caused to: evaluate an applicable functionality for AI / ML in the first functionality-related information based on a configuration for a relaxation or reduced parameter for the applicable functionality reported for AI / ML; select the applicable functionality for AI / ML inference based on the evaluation; generate second configuration information for configuring the applicable functionality for AI / ML inference; and transmit, to the terminal device, the second configuration information.21 . The network device of claim 20, wherein the network device is further caused to: activate the applicable functionality for AI / ML inference.

22. The network device of any of claims 16-21 , wherein the information comprises second functionality-related information indicating the update in a functionality for AI / ML, and wherein the second functionality-related information comprises at least one updated entry relative to the first functionality-related information, and wherein an updated entry of the at least one updated entry comprises at least one of: atleast one relaxation or reduced parameter for a corresponding applicable functionality reported for AI / ML or a removal of at least one previously proposed relaxation or reduced parameter.

23. The network device of any of claims 16-21 , wherein the information comprises an indication of a characteristic of the update in a functionality for AI / ML.

24. The network device of claim 23, wherein the characteristic of the update indicating at least one of following: an applicability update for an active functionality for AI / ML inference, wherein the applicability update comprises an updated configuration for a relaxation or reduced parameter that increases the active functionality’s capability, an applicability update for an active functionality for AI / ML inference, wherein the applicability update comprises an updated configuration for a relaxation or reduced parameter that decreases the active functionality’s capability, or an applicability update for an inactive functionality for AI / ML, wherein the applicability update comprises at least one of following: the inactive functionality is updated from applicable to be non-applicable, the inactive functionality is update from non-applicable to be applicable, or a configuration for at least one relaxation or reduced parameter for the inactive functionality is updated.

25. The network device of any of claims 23 or 24, wherein the network device is further caused to: transmit, to the terminal device, a request for information related to applicable functionality update; and receive, from the terminal device, second functionality-related information transmitted based on the received request, wherein the second functionality-related information comprises at least one updated entry relative to the first functionality-related information, and wherein an updated entry comprises at least one of: at least one relaxation or reduced parameter for a corresponding applicable functionality reported for AI / ML or a removal of at least one previously proposed relaxation or reduced parameter.

26. The network device of any of claims 16-25, wherein the second functionality-related information is different from the first functionality-related information, and wherein a difference between the second functionality-related information and the first functionality-related information comprises at least one of following: a first entry in the first functionality-related information is updated in the second functionality-related information to indicate a previously applicable functionality for AI / ML associated with the first entry isinapplicable, wherein the first entry comprises a field indicating a cause for an inapplicability of the previously applicable functionality for AI / ML associated with the first entry; a second entry in the first functionality-related information is updated in the second functionality- related information to indicate a previously inapplicable functionality for AI / ML associated with the second entry is applicable; a third entry not in the first functionality-related information is added into the second functionality- related information, wherein the third entry is corresponding to a new applicable functionality for AI / ML, wherein the third entry comprises an associated ID and at least one relaxation or reduced parameter for the new applicable functionality reported for AI / ML indicated via UE capability reporting; a configuration for a relaxation or reduced parameter in a fourth entry in the first functionality-related information is updated based on the update in the second functionality-related information; or a fifth entry in the functionality-related information is removed from the functionality-related information.

27. The network device of any of claims 22-26, wherein the network device is further caused to: evaluate the second functionality-related information; generate third configuration information based on the evaluation; and transmit the third configuration information to the terminal device.

28. The network device of claim 27, wherein the third configuration is used to configure the terminal device to perform at least one of following: update a configuration of a currently activated functionality for AI / ML inference; switch to a newly activated applicable functionality for AI / ML inference from a previous activated functionality for AI / ML inference; or fallback to a non-AI / ML mechanism.

29. The network device of any of claims 16-28, wherein based on the associated ID in an entry being related to a beam management use case, a relaxation or reduced parameter in the entry comprises at least one of following: a number of predicted beams in Set A; an observation window indicating a minimum time duration for measuring non-zero power channel state information reference signal (NZP-CSI-RS) resources; a prediction window indicating a maximum time duration that the NZP-CSI-RS resources is predicted based on Set B; a measured downlink (DL) resource signal (RS) indicating a support of using synchronized signal block (SSB) and / or CSI-RS-based reference signal received power (RSRP) measurements;a measured Set B DL RS dimension indicating an updated number of NZP-CSI-RS resources to be measured and used for predicting a best K-NZP CSI-RS resource; a measured DL RS Set B pattern indicating a restriction on the updated number of NZP-CSI-RS resources to be measured and used for predicting a best K-NZP CSI-RS resource; a predicted Set A DL RS dimension indicating an updated number of NZP-CSI-RS resources to be configured as prediction NZP CSI-RS resource sets; performance monitoring indicating an updated / preferred performance monitoring type; or measured DL RS performance monitoring indicative of supported measurement for a predicted DL RS set.

30. A method, comprising: detecting an update in at least one functionality for artificial intelligence (Al) / machine learning (ML); and based on detecting the update in the at least one functionality for AI / ML, transmit, to a network device, information indicating the update.

31. A method, comprising: receiving, from a terminal device, information indicating an update in at least one functionality for artificial intelligence (Al) / machine learning (ML).

32. An apparatus comprising: means for detecting an update in at least one functionality for artificial intelligence (Al) / machine learning (ML); and means for based on detecting the update in the at least one functionality for AI / ML, transmit, to a network device, information indicating the update.

33. An apparatus comprising: means for receiving, from a terminal device, information indicating an update in at least one functionality for artificial intelligence (Al) / machine learning (ML).

34. A computer readable medium comprising program instructions for causing an apparatus to perform at least the method of claim 30 or 31 .

Images