Prevention of poor performance

Abstract

Example embodiments of the present disclosure are directed to prevention of poor performance A method comprises receiving, from the second apparatus, a configuration for at least one timer associated with applicability determination information for a machine learning configuration; in accordance with receiving from the second apparatus, information indicating at least one cause for releasing a function configured by the machine learning configuration, starting the at least one timer; and reporting, to the second apparatus, an indication of an applicability associated with the applicability determination information based on at least a value of the at least one timer.

Description

PREVENTION OF POOR PERFORMANCEFIELDS

[0001] Various example embodiments of the present disclosure generally relate to the field of telecommunication and in particular, to methods, devices, apparatuses and computer readable storage medium of a prevention of poorly performing Artificial Intelligence (AI) / Machine Learning (ML) features.BACKGROUND

[0002] Due to the great success of AI / ML technologies, the AI / ML study item, which may refer to UE-sided model and network (NW) sided model, has been discussed in 3rd generation partnership project (3GPP). For example, potential benefits and gains of AI / ML aided Channel State Information (CSI) prediction has been studied.SUMMARY

[0003] In a first aspect of the present disclosure, there is provided a first apparatus. The first apparatus comprises at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the first apparatus at least to: receive, from the second apparatus, a configuration for a counter associated with applicability determination information for a machine learning configuration; in accordance with receiving from the second apparatus, information indicating a poor performance of a function configured by the machine learning configuration, increment the counter; and report, to the second apparatus, an indication of an applicability associated with the applicability determination information based at least on a value of the counter.

[0004] In a second aspect of the present disclosure, there is provided a second apparatus. The second apparatus comprises at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the second apparatus at least to: provide, to the first apparatus, a configuration for a counter associated withapplicability determination information for a machine learning configuration; transmit, to the first apparatus, information indicating a poor performance of the machine learning configuration associated with the applicability determination information; and receive, from the first apparatus, an indication of the applicability of the machine learning configuration.

[0005] In a third aspect of the present disclosure, there is provided a first apparatus. The first apparatus comprises at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the first apparatus at least to: receive, from the second apparatus, a configuration for a counter associated with applicability determination information for a machine learning configuration; in accordance with receiving from the second apparatus, information indicating at least one cause for releasing a function configured by the machine learning configuration, increment the counter; and report, to the second apparatus, an indication of an applicability associated with the applicability determination information based at least on a value of the counter.

[0006] In a fourth aspect of the present disclosure, there is provided a second apparatus. The second apparatus comprises at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the second apparatus at least to: provide, to the first apparatus, a configuration for a counter associated with applicability determination information for a machine learning configuration; transmit, to the first apparatus, information indicating at least one cause for releasing the machine learning configuration associated with the applicability determination information, and receive, from the first apparatus, an indication of the applicability of the machine learning configuration.

[0007] In a fifth aspect of the present disclosure, there is provided a first apparatus. The first apparatus comprises at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the first apparatus at least to: receive, from the second apparatus, a configuration for at least one timer associated with applicability determination information for a machine learning configuration; in accordance with receiving from the second apparatus, information indicating a poor performance of a function configured by the machine learning configuration, start the at least one timer; and report, to the second apparatus, an indicationof an applicability associated with the applicability determination information based at least on a value of the at least one timer.

[0008] In a sixth aspect of the present disclosure, there is provided a second apparatus. The second apparatus comprises at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the second apparatus at least to: provide, to the first apparatus, a configuration for at least one timer associated with applicability determination information for a machine learning configuration; transmit, to the first apparatus, information indicating a poor performance of a function configured by the machine learning configuration, and receive, from the first apparatus, an indication of the applicability of the machine learning configuration.

[0009] In a seventh aspect of the present disclosure, there is provided a first apparatus. The first apparatus comprises at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the first apparatus at least to: receive, from the second apparatus, a configuration for at least one timer associated with applicability determination information for a machine learning configuration; in accordance with receiving from the second apparatus, information indicating at least one cause for releasing a function configured by the machine learning configuration, start the at least one timer; and report, to the second apparatus, an indication of an applicability associated with the applicability determination information based on at least a value of the at least one timer.

[0010] In an eighth aspect of the present disclosure, there is provided a second apparatus. The second apparatus comprises at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the second apparatus at least to: provide, to the first apparatus, a configuration for at least one timer associated with applicability determination information for a machine learning configuration; transmit, to the first apparatus, information indicating at least one cause for releasing a function configured by the machine learning configuration, and receive, from the first apparatus, an indication of the applicability of the machine learning configuration.

[0011] In a ninth aspect of the present disclosure, there is provided a method. The method comprises: receiving, at the first apparatus from the second apparatus, a configuration for a counter associated with applicability determination information for amachine learning configuration; in accordance with receiving from the second apparatus, information indicating a poor performance of a function configured by the machine learning configuration, increment the counter; and reporting, to the second apparatus, an indication of an applicability associated with the applicability determination information based at least on a value of the counter.

[0012] In a tenth aspect of the present disclosure, there is provided a method. The method comprises: providing, from the second apparatus to the first apparatus, a configuration for a counter associated with applicability determination information for a machine learning configuration; transmitting, to the first apparatus, information indicating a poor performance of the machine learning configuration associated with the applicability determination information; and receiving, from the first apparatus, an indication of the applicability of the machine learning configuration.

[0013] In an eleventh aspect of the present disclosure, there is provided a method. The method comprises: receiving, at the first apparatus from the second apparatus, a configuration for a counter associated with applicability determination information for a machine learning configuration; in accordance with receiving from the second apparatus, information indicating at least one cause for releasing a function configured by the machine learning configuration, incrementing the counter; and reporting, to the second apparatus , an indication of an applicability associated with the applicability determination information based at least on a value of the counter.

[0014] In a twelfth aspect of the present disclosure, there is provided a method. The method comprises: providing, from the second apparatus to the first apparatus, a configuration for a counter associated with applicability determination information for a machine learning configuration; transmitting, to the first apparatus, information indicating at least one cause for releasing a function configured by the machine learning configuration, and receiving, from the first apparatus, an indication of the applicability of the machine learning configuration.

[0015] In a thirteenth aspect of the present disclosure, there is provided a method. The method comprises: receiving, at the first apparatus from the second apparatus, a configuration for at least one timer associated with applicability determination information for a machine learning configuration; in accordance with receiving from the second apparatus, information indicating a poor performance of a function configured bythe machine learning configuration, starting the at least one timer; and reporting, to the second apparatus, an indication of an applicability associated with the applicability determination information based at least on a value of the at least one timer.

[0016] In a fourteenth aspect of the present disclosure, there is provided a method. The method comprises: providing, from the second apparatus to the first apparatus, a configuration for at least one timer associated with applicability determination information for a machine learning configuration; transmitting, to the first apparatus, information indicating a poor performance of a function configured by the machine learning configuration, and receiving, from the first apparatus, an indication of the applicability of the machine learning configuration.

[0017] In a fifteenth aspect of the present disclosure, there is provided a method. The method comprises: receiving, at the first apparatus from the second apparatus, a configuration for at least one timer associated with applicability determination information for a machine learning configuration; in accordance with receiving from the second apparatus, information indicating at least one cause for releasing a function configured by the machine learning configuration, start the at least one timer; and reporting, to the second apparatus, an indication of an applicability associated with the applicability determination information based on at least a value of the at least one timer.

[0018] In a sixteenth aspect of the present disclosure, there is provided a method. The method comprises: providing, from the second apparatus to the first apparatus, a configuration for at least one timer associated with applicability determination information for a machine learning configuration; transmitting, to the first apparatus, information indicating at least one cause for releasing a function configured by the machine learning configuration, and receiving, from the first apparatus, an indication of the applicability of the machine learning configuration.

[0019] In a seventeenth aspect of the present disclosure, there is provided a first apparatus. The first apparatus comprises means for receiving, from the second apparatus, a configuration for a counter associated with applicability determination information for a machine learning configuration; means for in accordance with receiving from the second apparatus, information indicating a poor performance of a function configured by the machine learning configuration, increment the counter; and means for reporting, to the second apparatus, an indication of an applicability associated with the applicabilitydetermination information based at least on a value of the counter.

[0020] In an eighteenth aspect of the present disclosure, there is provided a second apparatus. The second apparatus comprises means for providing, to the first apparatus, a configuration for a counter associated with applicability determination information for a machine learning configuration; means for transmitting, to the first apparatus, information indicating a poor performance of a function configured by the machine learning configuration; and means for receiving, from the first apparatus, an indication of the applicability of the machine learning configuration.

[0021] In a nineteenth aspect of the present disclosure, there is provided a first apparatus. The third apparatus comprises means for receiving, from the second apparatus, a configuration for a counter associated with applicability determination information for a machine learning configuration; means for in accordance with receiving from the second apparatus, information indicating at least one cause for releasing a function configured by the machine learning configuration, increment the counter; and means for reporting, to the second apparatus , an indication of an applicability associated with the applicability determination information based at least on a value of the counter.

[0022] In a twentieth aspect of the present disclosure, there is provided a second apparatus. The fourth apparatus comprises means for providing, to the first apparatus, a configuration for a counter associated with applicability determination information for a machine learning configuration; means for transmitting, to the first apparatus, information indicating at least one cause for releasing a function configured by the machine learning configuration, and means for receiving, from the first apparatus, an indication of the applicability of the machine learning configuration.

[0023] In a twenty-first aspect of the present disclosure, there is provided a first apparatus. The fifth apparatus comprises means for receiving, from the second apparatus, a configuration for at least one timer associated with applicability determination information for a machine learning configuration; means for in accordance with receiving from the second apparatus, information indicating a poor performance of a function configured by the machine learning configuration, start the at least one timer; and means for reporting, to the second apparatus, an indication of an applicability associated with the applicability determination information based at least on a value of the at least one timer.

[0024] In a twenty-second aspect of the present disclosure, there is provided a secondapparatus. The sixth apparatus comprises means for providing, to the first apparatus, a configuration for at least one timer associated with applicability determination information for a machine learning configuration; means for transmitting, to the first apparatus, information indicating a poor performance of a function configured by the machine learning configuration, and means for receiving, from the first apparatus, an indication of the applicability of the machine learning configuration.

[0025] In a twenty-third aspect of the present disclosure, there is provided a first apparatus. The seventh apparatus comprises means for receiving, from the second apparatus, a configuration for at least one timer associated with applicability determination information for a machine learning configuration; means for in accordance with receiving from the second apparatus, information indicating at least one cause for releasing a function configured by the machine learning configuration, start the at least one timer; and means for reporting, to the second apparatus, an indication of an applicability associated with the applicability determination information based on at least a value of the at least one timer.

[0026] In a twenty-fourth aspect of the present disclosure, there is provided a second apparatus. The eighth apparatus comprises means for providing, to the first apparatus, a configuration for at least one timer associated with applicability determination information for a machine learning configuration; means for transmitting, to the first apparatus, information indicating at least one cause for releasing a function configured by the machine learning configuration, and means for receiving, from the first apparatus, an indication of the applicability of the machine learning configuration.

[0027] In a twenty-fifth aspect of the present disclosure, there is provided a computer readable medium. The computer readable medium comprises instructions stored thereon for causing an apparatus to perform at least the method according to the ninth aspect.

[0028] In a twenty-sixth aspect of the present disclosure, there is provided a computer readable medium. The computer readable medium comprises instructions stored thereon for causing an apparatus to perform at least the method according to the tenth aspect.

[0029] In a twenty-seventh aspect of the present disclosure, there is provided a computer readable medium. The computer readable medium comprises instructions stored thereon for causing an apparatus to perform at least the method according to the eleventh aspect.

[0030] In a twenty-eighth aspect of the present disclosure, there is provided a computer readable medium. The computer readable medium comprises instructions stored thereon for causing an apparatus to perform at least the method according to the twelfth aspect.

[0031] In a twenty-ninth aspect of the present disclosure, there is provided a computer readable medium. The computer readable medium comprises instructions stored thereon for causing an apparatus to perform at least the method according to the thirteenth aspect.

[0032] In a thirtieth aspect of the present disclosure, there is provided a computer readable medium. The computer readable medium comprises instructions stored thereon for causing an apparatus to perform at least the method according to the fourteenth aspect.

[0033] In a thirty-first aspect of the present disclosure, there is provided a computer readable medium. The computer readable medium comprises instructions stored thereon for causing an apparatus to perform at least the method according to the fifteenth aspect.

[0034] In a thirty-second aspect of the present disclosure, there is provided a computer readable medium. The computer readable medium comprises instructions stored thereon for causing an apparatus to perform at least the method according to the sixteenth aspect.

[0035] 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

[0036] Some example embodiments will now be described with reference to the accompanying drawings, where:

[0037] FIG. 1 illustrates an example communication environment in which example embodiments of the present disclosure can be implemented;

[0038] FIG. 2A illustrates an example of AI / ML beam management applicability determination and configuration;

[0039] FIG. 2B illustrates an example of an activation of CSI reporting;

[0040] FIG. 2C illustrates an example of a deactivation of CSI reporting;

[0041] FIG. 2D illustrates an example of CSI reporting de-configuration procedure;

[0042] FIG. 3 A illustrates a repeated activation and deactivation of a poorly performing AI / ML configuration;

[0043] FIG. 3B illustrates an example process of determination of the configuration applicability at user equipment side

[0044] FIG. 3C illustrates a behavior of an AI / ML feature with applicability information barred

[0045] FIGS. 4A and 4B illustrate signaling charts of communication according to some example embodiments of the present disclosure;

[0046] FIG. 5 illustrates a signaling chart of communication according to some example embodiments of the present disclosure;

[0047] FIG. 6 illustrates a signaling chart of communication according to some example embodiments of the present disclosure;

[0048] FIG. 7 illustrates a signaling chart of communication according to some example embodiments of the present disclosure;

[0049] FIG. 8 illustrates a signaling chart of communication according to some example embodiments of the present disclosure;

[0050] FIG. 9 illustrates a flowchart of a method implemented at a first apparatus in accordance with some example embodiments of the present disclosure;

[0051] FIG. 10 illustrates a flowchart of a method implemented at a second apparatus in accordance with some example embodiments of the present disclosure;

[0052] FIG. 11 illustrates a flowchart of a method implemented at a first apparatus in accordance with some example embodiments of the present disclosure;

[0053] FIG. 12 illustrates a flowchart of a method implemented at a second apparatus in accordance with some example embodiments of the present disclosure;

[0054] FIG. 13 illustrates a flowchart of a method implemented at a first apparatus in accordance with some example embodiments of the present disclosure;

[0055] FIG. 14 illustrates a flowchart of a method implemented at a second apparatusin accordance with some example embodiments of the present disclosure;

[0056] FIG. 15 illustrates a flowchart of a method implemented at a first apparatus in accordance with some example embodiments of the present disclosure;

[0057] FIG. 16 illustrates a flowchart of a method implemented at a second apparatus in accordance with some example embodiments of the present disclosure;

[0058] FIG. 17 illustrates a simplified block diagram of a device that is suitable for implementing example embodiments of the present disclosure; and

[0059] FIG. 18 illustrates a block diagram of an example computer readable medium in accordance with some example embodiments of the present disclosure.

[0060] Throughout the drawings, the same or similar reference numerals represent the same or similar element.DETAILED DESCRIPTION

[0061] Principle of the present disclosure will now be described with reference to some example embodiments. It is to be understood that these embodiments are described only for the purpose of illustration and help those skilled in the art to understand and implement the present disclosure, without suggesting any limitation as to the scope of the disclosure. Embodiments described herein can be implemented in various manners other than the ones described below.

[0062] 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.

[0063] 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 explicitlydescribed.

[0064] It shall be understood that although the terms “first,” “second,”..., etc. in front of noun(s) and the like may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another and they do not limit the order of the noun(s). 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.

[0065] 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.

[0066] As used herein, unless stated explicitly, performing a step “in response to A” does not necessarily indicate that the step is performed immediately after “A” occurs and one or more intervening steps may be included.

[0067] 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.

[0068] As used in this application, the term “circuitry” may refer to one or more or all of the following:(a) hardware-only circuit implementations (such as implementations in only analog and / or digital circuitry) and(b) combinations of hardware circuits and software, such as (as applicable):(i) a combination of analog and / or digital hardware circuit(s) with software / firmware and(ii) any portions of hardware processor(s) with software (including digital signal processor(s)), software, and memory(ies) that work together to cause an apparatus, such as a mobile phone or server, to perform various functions) and(c) hardware circuit(s) and or processor(s), such as a microprocessor(s) or a portion of a microprocessor(s), that requires software (e.g., firmware) for operation, but the software may not be present when it is not needed for operation.

[0069] 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 if applicable to the particular claim element, a baseband integrated circuit or processor integrated circuit for a mobile device or a similar integrated circuit in server, a cellular network device, or other computing or network device.

[0070] As used herein, the term “communication network” refers to a network following any suitable communication standards, such as New Radio (NR), Long Term Evolution (LTE), LTE-Advanced (LTE-A), Wideband Code Division Multiple Access (WCDMA), High-Speed Packet Access (HSPA), Narrow Band Internet of Things (NB-IoT) and so on. Furthermore, the communications between a terminal device and a network device in the communication network may be performed according to any suitable generation communication protocols, including, but not limited to, the first generation (1G), the second generation (2G), 2.5G, 2.75G, the third generation (3G), the fourth generation (4G), 4.5G, the fifth generation (5G), 5.5G, the sixth generation (6G) communication protocols, and / or any other protocols either currently known or to be developed in the future. Embodiments of the present disclosure may be applied in various communication systems. Given the rapid development in communications, there will of course also be future type communication technologies and systems with which the present disclosure may be embodied. It should not be seen as limiting the scope of the present disclosure to only the aforementioned system.

[0071] As used herein, the term “network device” refers to a node in a communicationnetwork via which a terminal device accesses the network and receives services therefrom. The network device may refer to a base station (BS) or an access point (AP), for example, a node B (NodeB or NB), an evolved NodeB (eNodeB or eNB), an NR NB (also referred to as a gNB), a Remote Radio Unit (RRU), a radio header (RH), a remote radio head (RRH), a relay, an Integrated Access and Backhaul (IAB) node, a low power node such as a femto, a pico, a non-terrestrial network (NTN) or non-ground network device such as a satellite network device, a low earth orbit (LEO) satellite and a geosynchronous earth orbit (GEO) satellite, an aircraft network device, and so forth, depending on the applied terminology and technology. In some example embodiments, radio access network (RAN) split architecture comprises a Centralized Unit (CU) and a Distributed Unit (DU) at an IAB donor node. An IAB node comprises a Mobile Terminal (IAB-MT) part that behaves like a UE toward the parent node, and a DU part of an IAB node behaves like a base station toward the next-hop IAB node.

[0072] The term “terminal device” refers to any end device that may be capable of wireless communication. By way of example rather than limitation, a terminal device may also be referred to as a communication device, user equipment (UE), a Subscriber Station (SS), a Portable Subscriber Station, a Mobile Station (MS), or an Access Terminal (AT). The terminal device may include, but not limited to, a mobile phone, a cellular phone, a smart phone, voice over IP (VoIP) phones, wireless local loop phones, a tablet, a wearable terminal device, a personal digital assistant (PDA), portable computers, desktop computer, image capture terminal devices such as digital cameras, gaming terminal devices, music storage and playback appliances, vehicle-mounted wireless terminal devices, wireless endpoints, mobile stations, laptop-embedded equipment (LEE), laptop-mounted equipment (LME), USB dongles, smart devices, wireless customer-premises equipment (CPE), an Internet of Things (loT) device, a watch or other wearable, a head-mounted display (HMD), a vehicle, a drone, a medical device and applications (e.g., remote surgery), an industrial device and applications (e.g., a robot and / or other wireless devices operating in an industrial and / or an automated processing chain contexts), a consumer electronics device, a device operating on commercial and / or industrial wireless networks, and the like. The terminal device may also correspond to a Mobile Termination (MT) part of an IAB node (e.g., a relay node). In the following description, the terms “terminal device”, “communication device”, “terminal”, “user equipment” and “UE” may be used interchangeably.

[0073] As used herein, the term “resource,” “transmission resource,” “resource block,” “physical resource block” (PRB), “uplink resource,” or “downlink resource” may refer to any resource for performing a communication, for example, a communication between a terminal device and a network device, such as a resource in time domain, a resource in frequency domain, a resource in space domain, a resource in code domain, or any other combination of the time, frequency, space and / or code domain resource enabling a communication, and the like. In the following, unless explicitly stated, a resource in both frequency domain and time domain will be used as an example of a transmission resource for describing some example embodiments of the present disclosure. It is noted that example embodiments of the present disclosure are equally applicable to other resources in other domains.

[0074] Example embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0075] FIG. 1 illustrates an example communication network 100 in which example embodiments of the present disclosure can be implemented. As shown in FIG. 1, the communication network 100 may comprise a first apparatus 110 which may be, for example, a terminal device. In some example embodiments, the terminal device may also be discussed as a UE.

[0076] The communication network 100 may further comprise a second apparatus 120, which may be, for example, a network device. In some example embodiments, the network device may be discussed as a BS, a gNB, or an eNB.

[0077] A serving area provided by the second apparatus 120 is called a cell. The first apparatus 110 may communicate with the second apparatus 120 within the cell 102. The cell currently serving the first apparatus 110 may be considered as a serving cell 102.

[0078] In the following, for the purpose of illustration, some example embodiments are described with the first apparatus 110 operating as a terminal device and the second apparatus 120 operating as a network device. However, in some example embodiments, operations described in connection with a terminal device may be implemented at a network device or other device, and operations described in connection with a network device may be implemented at a terminal device or other device.

[0079] In some example embodiments, if the first apparatus 110 is a terminal deviceand second apparatus 120 is a network device, a link from the second apparatus 120 to first apparatus 110 is referred to as a downlink (DL), while a link from the first apparatus 110 to second apparatus 120 is referred to as an uplink (UL). In DL, the second apparatus 120 is a transmitting (TX) apparatus (or a transmitter) and the first apparatus 110 is a receiving (RX) apparatus (or a receiver). In UL, the first apparatus 110 is a TX apparatus (or a transmitter) and the second apparatus 120 is a RX apparatus (or a receiver).

[0080] It is to be understood that the number of network devices and terminal devices shown in FIG. 1 is given for the purpose of illustration without suggesting any limitations. The communication environment 100 may include any suitable number of network devices and terminal devices.

[0081] Communications in the communication environment 100 may be implemented according to any proper communication protocol(s), comprising, but not limited to, cellular communication protocols of the first generation (1G), the second generation (2G), the third generation (3G), the fourth generation (4G), the fifth generation (5G), the sixth generation (6G), and the like, wireless local network communication protocols such as Institute for Electrical and Electronics Engineers (IEEE) 802.11 and the like, and / or any other protocols currently known or to be developed in the future. Moreover, the communication may utilize any proper wireless communication technology, comprising but not limited to: Code Division Multiple Access (CDMA), Frequency Division Multiple Access (FDMA), Time Division Multiple Access (TDMA), Frequency Division Duplex (FDD), Time Division Duplex (TDD), Multiple-Input Multiple-Output (MIMO), Orthogonal Frequency Division Multiple (OFDM), Discrete Fourier Transform spread OFDM (DFT-s-OFDM) and / or any other technologies currently known or to be developed in the future.

[0082] A basic procedure for determining applicability of an AI / ML configuration, reporting the applicability, and being configured with an AI / ML configuration has been agreed in some discussed schemes.

[0083] To better describe the above procedure, reference is now made to FIG. 2A, which shows a signaling chart 200A of the beam management (BM) or beam prediction, which involves a UE 210 and a gNB 220. The signaling chart 200 A shows the procedure of AI / ML beam management applicability determination and configuration

[0084] As shown in FIG. 2A, at Step3 the gNB 220 may transmit theRRCReconfiguration csi-ReportConfigToAddModList(CSI-ReportConfig(s)) or the applicability determination information to the UE 210. It should be noted that the contents of Step 3 or Step 5 as not agreed in some discussed schemes, but what is important is that the some new agreements and designs will mostly pertain to Step 3, wherein the applicability determination information, which could be a partial or full configuration, one or more associated IDs, or a combination thereof, is used by the UE 210 to determine whether it has an AI / ML model or a set of AI / ML models to support a configuration that would be provided by the network considering the applicability determination information. In Step 4, the UE 210 reports applicability of each applicability determination information to the network (NW) (i.e. gNB 219). At step 5, the UE 210 and the gNB 220 perform the RRC reconfiguration procedure which may be a full configuration procedure.

[0085] To activate channel state information (CSI) reporting for non-ML beam management, a different procedure is used for each of the reporting options, which will be described with reference to FIG. 2B. FIG. 2B shows a signaling chart 200B for the process of activation of the CSI reporting between the UE 210 and the gNB 220.

[0086] As shown in FIG. 2B, at Step 1A, the UE 210 activates the periodic reporting immediately after the configuration, i.e., the reception of a CSI-ReportConfig with a periodic reporting type. At Step IB, the gNB 220 transmits an aperiodic reporting upon the reception of a DCI. At Step 1C, the gNB 220 transmits a semipersistent reporting over physical uplink control channel (PUCCH) upon the reception of a medium access control (MAC) control element (CE). At Step ID, the gNB 220 transmits a semipersistent reporting over physical uplink shared channel (PUSCH) upon the reception of a downlink control information (DCI) message scrambled with a semi -persistent (SP) random network temporary identifier (RNTI).

[0087] To deactivate CSI reporting for non-ML beam management, the same messages are used except for in the case of aperiodic reporting, since it only reports once. Reference is now made to FIG. 2C, which shows a signaling chart 200C for the process of the activation of the process of the deactivation of CSI reporting between the UE 210 and the gNB 220.

[0088] As shown in FIG. 2C, at Step 1A, the RRCReconfiguration with the csi-ReportToReleaseList(CSI-Report Configld) is transmitted to the UE 210 in a periodic manner. At Step IB, the UE 210 ceases the reporting after sending a report. At Step 1C,the gNB 220 transmits a DIC on the PUCCH in a semi-persistent manner. At Step ID, the gNB 220 transmits a MAC-CE on the PUSCH in a semipersistent manner.

[0089] Regarding the above process, there is a lack of feedback from the NW (i.e., from the gNB 220) or a storage facility in the UE 210 to remember previously de-configured AI / ML configurations. The configuration procedure for CSI measurement reporting, and for beam management uses an RRCReconfiguration message, which carries a CSI-ReportConfigToAddModList containing CSI-ReportConfigs. To de-configure a beam management configuration, RRCReconfiguration carries a CSI-ReportConfigToRemoveList. The list only contains CSI-ReportConfiglds to remove, and no further feedback information is provided.

[0090] The de-configuration procedure for a non-ML beam management, which is enhanced by some schemes, is shown in FIG. 2D. Reference is now made to FIG. 2D, which shows a signaling chart 200D for the CSI reporting de-configuration procedure between the UE 210 and the gNB 220.

[0091] At Step 1, the gNB 220 simply provides a list of CSI-ReportConfiglds to de-configure. For example, the gNB 220 transmits the RRCReconfiguration with the csi-ReportToReleaseList(CSI-Report Configld) to the UE 210. At Step 2, the UE 210 performs the deconfiguraton. At Step 3, the UE 210 transmits the RRCReconfigurationComplete to the gNB 220.

[0092] Because AI / ML models have been determined not to generalize well across all scenarios, geographic locations, and network configurations, a feedback mechanism is required to align between user equipment (UE) and base stations (gNBs in 5G). Until now, it has been agreed that a UE can determine and report the applicability of a configuration, that is provide an indication that one or more models supporting the AI / ML configuration have been trained under certain conditions and should perform well in an area, specific NW conditions (conveyed by the NW via the Associated ID), or at a particular gNB, set of gNBs, a NW function, or set of NW functions. However, circumstances change, and uncaptured variables during model training could expose an AI / ML configuration to poor performance even when it was previously determined that the AI / ML configuration would perform well under the previous inference conditions.

[0093] An example is provided below, which shows a poorly performing AI / ML configuration being activated due to the UE reporting that the AI / ML configuration isapplicable, being deactivated a short time after in response to a monitoring procedure determining poor performance, and then being activated again in the future since no state was stored in the UE or the NW to capture past poor performance.

[0094] Reference is now made to FIG. 3A, which shows a diagram of the repeated activation and deactivation of a poorly performing AI / ML and AI / ML configuration.

[0095] At the time point 1, the UE in this example starts out with a legacy, i.e., a non-ML BM configuration. During the time duration 2, after being configured with an ML BM configuration, the performance monitoring begins.

[0096] At the time point 3, the performance of the ML BM configuration shows bad performance, and after the duration of a monitoring window (time duration 2), the NW deactivates the ML configuration.

[0097] At the time point 4, the UE transitions into IDLE mode. At the time point 5, upon returning from the IDLE mode to the same cell, the UE is configured with the ML BM again, and the cycle repeats. In this process, the ML BM configuration is applicable forever.

[0098] There is no mechanism to prevent the UE from repeatedly reporting the AI / ML feature, AI / ML configuration, model, or related configuration as applicable, and since the NW may not have the ability to store information about the performance of previously provided configurations, the NW would have no basis by which to avoid configuring the same AI / ML feature, AI / ML configuration, model, or related configuration. This can lead to situations where the network totally switches off the use of AI / ML for a feature due to repeatedly activated poor performing model.

[0099] This present disclosure enables the UE to store a barring indication in association with applicability information used to determine the applicability of an AI / ML feature, AI / ML configuration, model, or related configuration. The UE would set the barring indication based on one or more poor performance indications from the NW. The nature of the poor performance indication is such that the performance was unacceptable to the degree that required that the AI / ML configuration had to be de-configured in order to preserve NW performance. The barring indication would be used as part of the applicability determination by the UE by not signaling applicability for barred applicability information or by explicitly signaling inapplicability.

[0100] In accordance with some example embodiments of the present disclosure, there is provided a solution for a prevention of poor performance of AI / ML features. In this solution, the first apparatus 110 receives a configuration for a counter or at least one timer associated with applicability determination information for a machine learning configuration. Upon receiving information indicating a poor performance of a function configured by the machine learning configuration or indicating at least one cause for releasing the function configured by the machine learning configuration, the first apparatus 110 change the value of the counter and / or the at least one timer and report, to the second apparatus, an indication of an applicability associated with the applicability determination information based at least on a value of the counter.

[0101] Reference is now made to FIG. 3B, which shows a flowchart 300B of the specified UE-side steps to determine the configuration applicability. The flowchart 300B may also be referred to as a high-level view of the solution proposed in the present disclosure.

[0102] There are 3 conditions in the flowchart 300B, namely Condition 1: The UE receives from NW information to be used to determine the applicability of the final / full configuration; Condition 2: The UE evaluates the UE internal conditions to be used to determine the applicability of the final / full configuration; Condition 3: The UE evaluates the bar status for the applicability information, based on the barring counter and timers.

[0103] Regarding the above-mentioned counter and timers, to enable the UE to determine when to bar the applicability, a counter and at least one timer (e.g., two timers) are defined.

[0104] As an example, a barring counter would be incremented at each poor performance indication until it reached a configured maximum value, at which point the applicability determination information would be considered to be barred, i.e., the poorly performing AI / ML configuration is barred and cannot be used / activated.

[0105] As another example, the first timer, if configured, would automatically reset the barring counter if it never reached the maximum value, and the second timer, if configured, would reset the barring counter and the barring state of the barred applicability upon expiration.

[0106] For the UE, if the Condition 1 and Condition 2 are met, but the Condition 3 isnot met, then the UE may determine that the configuration is applicable. While in other cases, the UE may determine that the configuration is non-applicable.

[0107] After determining whether the configuration is applicable or not, the UE may report the configuration applicability status to the NW. The applicability used here may be related to what would eventually be a full configuration. It is important that the applicability is tied to the applicability determination information.

[0108] Reference is now made to FIG. 3C, which shows a diagram 300C of the behavior of an AI / ML feature with applicability information barred.

[0109] As shown in FIG. 3C, after time point 1 and time point 2, it is determined that the AI / ML configuration performed poorly over the course of a monitoring window and is thus deactivated at time point 3 with a cause of poor performance.

[0110] At time point 4, the barring counter reaches its maximum value, which in this example is set to 1, and the UE stores the barring state of the applicability information related to the configuration.

[0111] At time point 5, the UE goes to IDLE mode and when it reenters CONNECTED mode, any time after time point 6, it reports the configuration as inapplicable, so the NW configures a non-ML method instead, ensuring the acceptable performance. Time point 7 in FIG. 3C may be used as a reference in the part where the NW configures a non-ML method.

[0112] It should be noted that while the descriptions above refer to beam management, these are used as examples as to be able to refer to legacy signaling procedures. The present disclosure herein can be applied to, but is not limited to, AI / ML CSI prediction, AI / ML CSI compression, AI / ML beam management / prediction, AI / ML positioning, and AI / ML mobility.

[0113] In the following, embodiments of the present disclosure will be described with reference to signaling charts FIGS. 4A-8. In some embodiments, the UE may be configured to store a barring counter and / or at least one timer related to the applicability of one or more AI / ML configuration. The UE checks the counter and / or at least one timer as a part of determining the applicability and report applicability based in part on the barring information.

[0114] The reference now is made to FIG. 4A, which illustrates a signaling chart 400A for communication according to some example embodiments of the present disclosure. As shown in FIG. 4 A, the signaling chart 400 A involves a first apparatus 110 and a second apparatus 120. For the purpose of discussion, reference is made to FIG. 1 to describe the signaling chart 400A.

[0115] As shown in FIG. 4A, the second apparatus 120 may provide (402) a configuration of a counter to the first apparatus 110. The counter may be associated with applicability determination information for machine learning configuration. The machine learning configuration may be configured for the first apparatus 110 on which one or more AI / ML models are deployed for, e.g., a CSI prediction.

[0116] As an option, the configuration of the counter may be included or provided along with a CSI report configuration or a CSI measurement configuration. As another example, the configuration of the counter may be included or provided along with the applicability determination information.

[0117] The configuration may include a threshold (e.g., a maximum) value of the counter. In addition to the counter, the configuration may also include at least one timer and respective threshold (e.g., a maximum) value of the at least one timer. The principle for operating the counter and / or the at least one timer may be further described later.

[0118] The term applicability determination information used hereinafter may include any information transmitted to the first apparatus 110 by the second apparatus 120 which the first apparatus 110 uses to evaluate whether it can support an AI / ML configuration.

[0119] The applicability determination information may include, for example, an associated ID, which indicates a value that associates transmissions by the NW with a prior training data collection configuration. The applicability determination information may also include a cell global identity, i.e., a unique identifier which identifies a cell and gNB ID, which is a unique identifier which identifies a gNB.

[0120] In addition, applicability determination information may include the partial configuration or the full configuration. The partial configuration may include, e.g., essential parameters of a CSI-ReportConfig which may be used to determine applicability, while the full configuration may include, e.g., a complete CSI-ReportConfig, which may be used to configure the first apparatus 110 for beam prediction.

[0121] Other NW-side additional conditions may be included in the applicability determination information, which are NW configuration parameters, explicit, implicit, or mapped, which can be used by the first apparatus 110 to determine applicability.

[0122] The applicability determination information is necessary to align potential configurations from the NW with AI / ML models in the first apparatus 110 such that the first apparatus 110 is able to determine that a model is applicable under the circumstances under which the first apparatus 110 is operating. When indicated to the NW that given applicability determination information is applicable, the NW is able to determine configurations that will be applicable to the first apparatus 110 and its AI / ML models at that time.

[0123] In all cases, applicability ultimately means that the first apparatus 110 has at least one AI / ML model, or combination of AI / ML models, capable of supporting an AI / ML configuration provided by the NW.

[0124] As an option, upon receiving (404), from the second apparatus 120, information indicating a poor performance of a function configured by the machine learning configuration, the first apparatus 110 may increment (406) the configured counter. This counter may be incremented at each poor performance indication until it reaches a configured maximum value (i.e., a threshold). If the counter value reaches the configured maximum value, the first apparatus 110 may determine (408) the applicability determination information related to the machine learning configuration to be barred.

[0125] As another option, upon receiving (404), from the second apparatus 120, information indicating at least one cause for releasing a function configured by the machine learning configuration, the first apparatus 110 may increment (406) the configured counter. This counter may be incremented at each poor performance indication until it reaches a configured maximum value (i.e., a threshold). If the counter value reaches the configured maximum value, the first apparatus 110 may determine (408) the applicability determination information related to the machine learning configuration to be barred. More details of the release cause information will be further described in FIG.6.

[0126] That is, this counter may count instances of poor performance indications / release causes, received from the NW. If the counter’s maximum value is configured to 1, once a poor performance indication is received, the applicability determinationinformation may be considered as being barred.

[0127] As mentioned above, at least one timer may be configured. As an example, a first timer may start at the time point when the counter value reaches the configured maximum value. When the first timer expires, e.g. the timer value reaches a maximum timer value, the counter may be reset, and the applicability determination information may be considered as being unbarred.

[0128] It is also possible that there is a second timer. The second timer may start or may be reset when the counter is first incremented. When the second timer expires, e.g. the timer value reaches a maximum timer value, the counter may be decremented. If the value of the counter is not equal to zero, the second timer may be reset or restart.

[0129] During this process, the first apparatus 110 may evaluate the applicability associated with the applicability determination information. If the barring state associated with the applicability determination information is set to be barred, the first apparatus 110 may consider the applicability as inapplicable.

[0130] After determining the applicability associated with the applicability determination information, the first apparatus 110 may report, to the second apparatus 120, an indication of an applicability associated with the applicability determination information.

[0131] That is, if the first apparatus determines that a barring state of the applicability determination information to be barred, the first apparatus 110 may report (410) the applicability is inapplicable. If the first apparatus determines that a barring state of the applicability determination information to be unbarred, the first apparatus 110 may report the applicability is applicable. It is to be understood that in addition to the barring state, any other factor may also be used to determine the applicability, which has been described above.

[0132] For example, inapplicable applicability may be implicitly indicated in the report through an absence of the corresponding applicability determination information.

[0133] As another example, the report may also indicate a cause of inapplicability as barred for the corresponding applicability determination information.

[0134] The reference now is made to FIG. 4B, which illustrates a signaling chart 400Bfor communication according to some example embodiments of the present disclosure. As shown in FIG. 4B, the signaling chart 400B involves a first apparatus 110 and a second apparatus 120. For the purpose of discussion, reference is made to FIG. 1 to describe the signaling chart 400B.

[0135] As shown in FIG. 4B, the second apparatus 120 may provide (412) a configuration of at least one timer to the first apparatus 110. The at least one timer may be associated with applicability determination information for machine learning configuration. The machine learning configuration may be configured for the first apparatus 110 on which one or more AI / ML models are deployed for, e.g., a CSI prediction.

[0136] As an option, the configuration of the at least one timer may be included or provided along with a CSI report configuration or a CSI measurement configuration. As another example, the configuration of the at least one timer may be included or provided along with the applicability determination information.

[0137] It is to be understood that the configuration may also include parameters / information associated with the applicability determination of an AI / ML feature, which has been described with reference to FIG. 4A and will be omitted here.

[0138] The configuration may include respective threshold (e.g., a maximum) values of the at least one timer. In addition to the at least one timer, the configuration may also include a counter and a threshold (e.g., a maximum) value of the counter. The principle for operating the counter and / or the at least one timer may be further described later.

[0139] The term applicability determination information used hereinafter may include any information transmitted to the first apparatus 110 by the second apparatus 120 which the first apparatus 110 uses to evaluate whether it can support an AI / ML configuration. The parameters included in the applicability determination information have been described with reference to FIG. 4A, which will be omitted here.

[0140] As an option, upon receiving (414), from the second apparatus 120, information indicating a poor performance of a function configured by the machine learning configuration, the first apparatus 110 may start (416) a timer (e.g., a first timer) and consider (418) that a barring state of the applicability determination information to be barred. If the first timer expires, e.g. the timer value reaches a maximum timer value, theapplicability determination information may be considered as being unbarred. That is, the barring state may be considered as barred or unbarred based on the value of the first timer.

[0141] If the counter, as mentioned above, is configured, this counter may be incremented at each poor performance indication until it reaches a configured maximum value (i.e., a threshold). If the counter value reaches the configured maximum value, the first apparatus 110 may start the first timer and determine the applicability determination information related to the machine learning configuration to be barred.

[0142] As another option, upon receiving (414), from the second apparatus 120, information indicating at least one cause for releasing a function configured by the machine learning configuration, the first apparatus 110 may start (416) a timer (e.g., a first timer) and consider (418) that a barring state of the applicability determination information to be barred. If the first timer expires, e.g. the timer value reaches a maximum timer value, the applicability determination information may be considered as being unbarred. More details of the release cause information will be further described in FIG.6.

[0143] It is also possible that there is a second timer. The second timer may start or may be reset when the counter is first incremented. When the second timer expires, e.g. the timer value reaches a maximum timer value, the counter may be decremented. If the value of the counter is not equal to zero, the second timer may be reset or restart.

[0144] During this process, the first apparatus 110 may evaluate the applicability associated with the applicability determination information. If the barring state associated with the applicability determination information is set to be barred, the first apparatus 110 may consider the applicability as inapplicable.

[0145] After determining the applicability associated with the applicability determination information, the first apparatus 110 may report (420), to the second apparatus 120, an indication of an applicability associated with the applicability determination information.

[0146] That is, if the first apparatus determines that a barring state of the applicability determination information to be barred, the first apparatus 110 may report the applicability is inapplicable. If the first apparatus determines that a barring state of the applicabilitydetermination information to be unbarred, the first apparatus 110 may report the applicability as applicable. It is to be understood that in addition to the barring state, any other factor may also be used to determine the applicability which has been described above.

[0147] For example, inapplicable applicability may be implicitly indicated in the report through an absence of the corresponding applicability determination information.

[0148] As another example, the report may also indicate a cause of inapplicability as barred for the corresponding applicability determination information.

[0149] In addition to an indication of poor performance from NW, as mentioned above, the first apparatus may also transmit a poor performance indication on its own. In this case, the behavior of the first apparatus 110 may be similar with the process described with reference to FIG. 4 A and FIG. 4B.

[0150] The reference is now made to FIG. 5, which illustrates a signaling chart 500 for communication according to some example embodiments of the present disclosure. As shown in FIG. 5, the signaling chart 500 involves a first apparatus 110 and a second apparatus 120. For the purpose of discussion, reference is made to FIG. 1 to describe the signaling chart 500.

[0151] As mentioned above, a configuration of the counter and at least one timer may be configured via a CSI configuration, radio resource management (RRM) configuration,LTE Positioning Protocol (LPP) configuration or via applicability determination information. For example, this configuration may be of different types other than CSI such as ReportConfig, ReportConfigNR (for radio resource management / AI / ML mobility), LPP RequestLocationlnformation (for AI / ML positioning) or any other generic type of configuration for an AI / ML feature.

[0152] For example, if the configuration is included in a CSI configuration, a new information element (IE) called CSI-ReportConfigBarringConfig may be provided to configure values the counter and the at least one timer by introducing new IES called csi-BarringTimerMaxValue and csi-BarringCounterResetTimerMaxValue, which may be time in seconds (or, e.g., minutes, or hours). An example of the configuration is listed according to the new IEs.CSI-ReportConfigBarringConfig ::= SEQUENCE {csi-BarringCounterMaxValue INTEGER(0.,maxBarringCounterMaxValue), csi-BarringTimerMax Value INTEGER(O..maxCSI-BarringTimerMax Value), csi-BarringCounterResetTimerMaxValueINTEGER (0..maxCSI-BarringCounterResetTimerMax Value),csi-BarringScope CSI-BarringScope Alt. 1csi-BarringScopeList SEQUENCE (SIZE (O..max)) of CSI-BarringScope Alt. 2}

[0153] In this situation, in addition to the provision of a partial configuration or full configuration (CSI-ReportConfig(s) applicability determination information, Radio Resource Management (RRM) measurement configuration or LTE Positioning Protocol (LPP) configuration, the first apparatus 110 may be configured (505), on a per-applicability determination information basis, one or more parameters in the following:

[0154] A: Maximum value for the barring counter, e.g., csi-BarringCounterMax - when this counter reaches its maximum value (at the first apparatus 110 or UE), the applicability determination information is considered to be barred.

[0155] B: Maximum value for the barring timer, e.g., csi-BarringTimerMax - this timer is started by the first apparatus 110 when the barring counter reaches its maximum value or when a poor performance indication or a release cause associated with a poor performance, and when this timer reaches its maximum value, the barring counter is reset, and the applicability determination information is considered to be unbarred. It is to be understood that the timer may start regardless of whether a counter is configured.

[0156] C: Maximum value for the barring counter reset timer or decrement, e.g., csi-BarringCounterResetTimerMax - this timer is started by the first apparatus 110 when the barring counter is first incremented. When this timer reaches its maximum value, the barring counter decrements by 1, if configured to do so, or resets to 0, if configured to do so. If the barring counter value is 0, then this timer does not run.

[0157] In addition to the previously described parameters in the configuration, a barring scope may also be provided, csi-BarringScope and / or csi-BarringScopeList, to expand the z / scope of barring to beyond the first apparatus’s circumstances or connected cell, etc., at the time of barring.

[0158] For example, the barring could apply to similar gNBs or cells, or to wider areas by providing by the NW to the UE one or more of, but not limited to, one or more of the following pieces of information associated with the barring configuration:• Cell Global Identity (CGI)• Tracking Area Code (TAC)• Physical Cell ID (PCI)• Area - polygon representing a geographic area• gNB ID

[0159] An example of a barring scope configuration is listed below:CSI-BarringScope CHOICE {nr-CGI Cellldentity — includes gNBId and NCI trackingAreaCode TrackingAreaCodephysicalCellld PhysicalCellld,polygon Polygon — as defined in 37.355 (and below)Polygon ::= SEQUENCE (SIZE (3..15)) OF PolygonPointsPolygonPoints ::= SEQUENCE {latitudeSign ENUMERATED {north, south},degreesLatitude INTEGER (0..8388607), - 23 bit field degreesLongitude INTEGER (-8388608..8388607) - 24 bit field

[0160] Upon receiving the configuration and applicability determination information, the first apparatus 110 may check (510) whether the configuration which would be associated with the applicability determination information is barred, and if it is, considers it inapplicable. The process of determining whether the applicability determinationinformation is barred or not based on the counter value and / or the at least one timer value has been described with reference to FIG. 4A and 4B, which will be omitted here.

[0161] Then, the first apparatus 110 may report (515) the applicability, and optionally inapplicability, of the applicability determination information. The first apparatus 110 may be configured to explicitly report inapplicable applicability determination information or to implicitly report it by excluding the inapplicable applicability determination information from the report.

[0162] Based on the applicability determination and reporting thereof, and considering the barring state of applicability associated with the applicability determination information, the first apparatus is configured with an AI / ML or non-AI / ML feature. The first apparatus 110 and the second apparatus 120 may perform (520) the RRC reconfiguration procedure or the full configuration procedure.

[0163] The reference is now made to FIG. 6, which illustrates a signaling chart 600 for communication according to some example embodiments of the present disclosure. As shown in FIG. 6, the signaling chart 600 involves a first apparatus 110 and a second apparatus 120. For the purpose of discussion, reference is made to FIG. 1 to describe the signaling chart 600.

[0164] As described above, the second apparatus 120 may send at least one cause for releasing a function configured by the machine learning configuration. In this case, through the inclusion of one or more poorly performing AI / ML configurations identified by CSI-ReportConfigld(s) in the CSI-ReportConfigToReleaseList, a ReleaseCause is provided.

[0165] As an option, the second apparatus 120 may signal (605A) a CSI-ReportConfigToReleaseList simultaneously with a new list called CSI-ReportConfigToReleaseCauseList. The new list includes the release cause, which could for example indicate “poor performance”.

[0166] As another option, the second apparatus 120 may signal (605B) only a new list called CSI-ReportConfigToReleaseCauseList, which simultaneously de-configures the poorly performing CSI-ReportConfigld(s) and provides the cause of their de-configuration.

[0167] For example, an example showing the new IE “CSI-ReportConfigToReleaseCauseList” is listed below:CSI-ReportConfigToReleaseWithCauseListSEQUENCE( SIZE( O..max)) OF CSI-ReportConfigToReleaseWithCause CSI-ReportConfigToReleaseWithCause ::= SEQUENCE {csi-ReportConfigld CSI-ReportConfigld,csi-ReportConfigReleaseCause CSI-ReportConfigReleaseCause}CSI-ReportConfigReleaseCause ENUMERATION { poorPerformance, ... }

[0168] After receiving the signaling sent by the second apparatus 120, if the counter is configured, the first apparatus 110 may (610) increment the counter related to the applicability determination information. As an example, if the counter, after being incremented, equals the maximum value of the counter, the first apparatus 110 may set (615) the configuration barred for that applicability determination information.

[0169] Alternatively, if configured, the first apparatus 110 may start (620) the first timer, e.g., a barring timer. In addition, if the counter, after being incremented, does not equal the maximum value of the counter, the first apparatus 110 may start (625) the second timer, e.g., a barring counter reset timer, if configured.

[0170] The reference is now made to FIG. 7, which illustrates a signaling chart 700 for communication according to some example embodiments of the present disclosure. As shown in FIG. 7, the signaling chart 700 involves a first apparatus 110 and a second apparatus 120. For the purpose of discussion, reference is made to FIG. 1 to describe the signaling chart 700.

[0171] FIG. 7 illustrates the procedure to unbar a barred applicability determination information. The process of checking the timer(s) associated with each barred configuration / applicability determination information may check whether any timer(s) has expired. If they have, then the barred configuration(s) / applicability determination information is unbarred. The counter, barring timer (i.e., the first timer as described above), and barring counter reset timer (i.e., the second timer as described above) do not reset upon transition into IDLE and INACTIVE states. It is also possible that the timersand counter are allowed to be reset when the first apparatus 110 is going into IDLE or INACTIVE mode.

[0172] As shown in FIG. 7, the first apparatus 110 may set (705) a configuration to barred for applicability determination information. Upon an expiry of the barring timer (i.e., the first timer), the first apparatus 110 may determine (710) that the applicability determination information as being unbarred.

[0173] In some example embodiments, the applicability determination information may be considered as being unbarred when the machine learning capability has been updated. More detail will be further described with reference to FIG. 8.

[0174] The reference is now made to FIG. 8, which illustrates a signaling chart 800 for communication according to some example embodiments of the present disclosure. As shown in FIG. 8, the signaling chart 800 involves a first apparatus 110 and a second apparatus 120. For the purpose of discussion, reference is made to FIG. 1 to describe the signaling chart 800.

[0175] FIG. 8 shows a situation where the applicability determination information may be unbarred, if configured, based on events related to the AI / ML models, internal to the first apparatus 110. It is to be understood that it is up to configuration whether the first apparatus can unbar applicability determination information based on these events.

[0176] After setting (805) a machine learning configuration to be barred associated with the applicability determination information, the first apparatus 110 may update the AI / ML context related to a barred applicability determination information.

[0177] For example, the first apparatus 110 may download (810A) a new AI / ML model.

[0178] As another example, the first apparatus 110 may update (810B) the existing AI / ML model.

[0179] It is also possible that the first apparatus 110 may update (810C) the rules for switching between AI / ML models (first apparatus 110 implementation specific). For example, the applicable velocity range or signal strength range is updated for at least one model.

[0180] In addition, the first apparatus 110 may delete (810D) an AI / ML model, which was previously used among other models to enable a barred applicability determinationinformation.

[0181] Optionally, the first apparatus 110 may delete (810E) an AI / ML, AI / ML configuration, which could be one AI / ML model, or a collection of AI / ML models, thereby eliminating the need for storing the barring counter and timers.

[0182] After updating the AI / ML context, the first apparatus 110 may unbar (815) the machine learning configuration of barred applicability information due to the AI / ML environment update event.

[0183] That is, in relation to applicability determination information, the first apparatus 110 may update a machine learning capability by performing downloading one or more machine learning model, adjusting one or more parameters of one or more machine learning model, adjusting one or more model switching rules, deleting one or more machine learning model; or resetting respective barring states of one or more applicability determination information according to the update.

[0184] In addition, embodiments related to updating other affected UEs will be further described.

[0185] In response to having a configuration barred, related to applicability determination information, the affected UE could report the barring to a server used for training UE-side models such that the barring state could be propagated to other UEs running the same AI / ML environment, or those which contain the same AI / ML models, sets of models, model switching rules, etc., to avoid reporting as applicable, configurations likely to be barred after performing poorly.

[0186] Additionally, all affected UEs could be updated with model download, model deletion, model update, model switching rules, etc., as a response to the indication to the server used for training UE-side models that a model or group of models isn’t performing well given certain applicability determination information.

[0187] FIG. 9 shows a flowchart of an example method 900 implemented at a first apparatus 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 first apparatus 110 in FIG. 1.

[0188] At block 910, the first apparatus receives, from the second apparatus, aconfiguration for a counter associated with applicability determination information for a machine learning configuration.

[0189] At block 920, in accordance with receiving from the second apparatus, information indicating a poor performance of a function configured by the machine learning configuration, the first apparatus increments the counter.

[0190] At block 930, if the first apparatus reports, to the second apparatus, an indication of an applicability associated with the applicability determination information based at least on a value of the counter.

[0191] In some example embodiments, the configuration comprises at least one of the following: a counter threshold value; or at least one timer threshold value.

[0192] In some example embodiments, the method 900 further comprises: in accordance with a determination that a value of the counter reaches the counter threshold value, considering a barring state of the applicability determination information to be barred.

[0193] In some example embodiments, the method 900 further comprises: receiving, from the second apparatus, a timer threshold value of a first timer; in accordance with a determination that a value of the counter reaches a counter threshold value, starting the first timer; in accordance with a determination that a value of the first timer reaches the timer threshold value, resetting the counter; and considering a barring state of the applicability determination information to be unbarred.

[0194] In some example embodiments, the method 900 further comprises: receiving, from the second apparatus, a timer threshold value of a second timer; in accordance with a determination of an incrementing of the counter, resetting and start the second timer.

[0195] In some example embodiments, the method 900 further comprises: in accordance with a determination that a value of the second timer reaches the timer threshold value, decrementing the counter.

[0196] In some example embodiments, the method 900 further comprises: resetting and start the second timer upon a determination that a value of the counter is not equal to zero.

[0197] In some example embodiments, the method 900 further comprises: in accordance with a determination that a value of the second timer reaches the timer threshold value, resetting the counter.

[0198] In some example embodiments, the method 900 further comprises: in relation to applicability determination information, update a machine learning capability by performing at least one of the following: downloading one or more machine learning model, adjusting one or more parameters of one or more machine learning model, adjusting one or more model switching rules, or deleting one or more machine learning model; and resetting respective barring states of one or more applicability determination information according to the update.

[0199] In some example embodiments, the resetting of the barring state of the one or more applicability determination information causes the first apparatus to perform at least one of the following: resetting one or more counters; resetting one or more first timers; resetting one or more second timers; or setting one or more barring states to be unbarred.

[0200] In some example embodiments, the configuration is obtained along with a channel state information, CSI, report configuration, CSI measurement configuration, applicability determination information, Radio Resource Management (RRM) measurement configuration or LTE Positioning Protocol (LPP) configuration.

[0201] In some example embodiments, the method 900 further comprises: evaluating the applicability based on the applicability determination information; and considering the applicability to be inapplicable based on a barring state associated with the applicability determination information being set to barred.

[0202] In some example embodiments, the method 900 further comprises: in accordance with a determination that respective applicability of one or more applicability determination information is considered to be inapplicable based on respective barring states associated with the one or more applicability determination information being set to be barred, reporting to the second apparatus, respective applicability of one or more applicability determination information as inapplicable.

[0203] In some example embodiments, the respective inapplicable applicability is implicitly indicated in the report through an absence of the one or more applicability determination information.

[0204] In some example embodiments, the method 900 further comprises: indicating respective causes of inapplicability as barred for the one or more applicability determination information in the report.

[0205] In some example embodiments, the first apparatus comprises a terminal device and the second apparatus comprises a network node.

[0206] FIG. 10 shows a flowchart of an example method 1000 implemented at a second apparatus in accordance with some example embodiments of the present disclosure. For the purpose of discussion, the method 1000 will be described from the perspective of the second apparatus 120 in FIG. 1.

[0207] At block 1010, the second apparatus provides, to the first apparatus, a configuration for a counter associated with applicability determination information for a machine learning configuration.

[0208] At block 1020, the second apparatus transmits, to the first apparatus, information indicating a poor performance of the machine learning configuration associated with the applicability determination information.

[0209] At block 1030, the second apparatus receives, from the first apparatus, an indication of the applicability of the machine learning configuration.

[0210] In some example embodiments, the configuration comprises at least one of the following: a counter threshold value; or at least one timer threshold value.

[0211] In some example embodiments, the method 1000 further comprises: providing, to the first apparatus, a timer threshold value of a first timer.

[0212] In some example embodiments, the method 1000 further comprises: providing, to the first apparatus, a timer threshold value of a second timer.

[0213] In some example embodiments, the method 1000 further comprises: transmitting, to the first apparatus, the configuration along with a channel state information, CSI, report configuration, a CSI measurement configuration, applicability determination information, Radio Resource Management (RRM) measurement configuration or LTE Positioning Protocol (LPP) configuration.

[0214] In some example embodiments, the first apparatus comprises a terminal device and the second apparatus comprises a network node.

[0215] FIG. 11 shows a flowchart of an example method 1100 implemented at a first apparatus in accordance with some example embodiments of the present disclosure. For the purpose of discussion, the method 1200 will be described from the perspective of thefirst apparatus 110 in FIG. 1.

[0216] At block 1110, the first apparatus receives, from the second apparatus, a configuration for a counter associated with applicability determination information for a machine learning configuration.

[0217] At block 1120, in accordance with receiving from the second apparatus, information indicating at least one cause for releasing a function configured by the machine learning configuration, the first apparatus increments the counter.

[0218] At block 1130, the first apparatus reports, to the second apparatus, an indication of an applicability associated with the applicability determination information based at least on a value of the counter.

[0219] In some example embodiments, the configuration comprises at least one of the following: a counter threshold value; or at least one timer threshold value.

[0220] In some example embodiments, the method 1100 further comprises: in accordance with a determination that a value of the counter reaches the counter threshold value, considering a barring state of the applicability determination information to be barred.

[0221] In some example embodiments, the method 1100 further comprises: receiving, from the second apparatus, a timer threshold value of a first timer; in accordance with a determination that a value of the counter reaches a counter threshold value, starting the first timer; in accordance with a determination that a value of the first timer reaches the timer threshold value, resetting the counter; and considering a barring state of the applicability determination information to be unbarred.

[0222] In some example embodiments, the method 1100 further comprises: receiving, from the second apparatus, a timer threshold value of a second timer; in accordance with a determination of an incrementing of the counter, resetting and start the second timer.

[0223] In some example embodiments, the method 1100 further comprises: in accordance with a determination that a value of the second timer reaches the timer threshold value, decrementing counter.

[0224] In some example embodiments, the method 1100 further comprises: resetting and start the second timer upon a determination that a value of the counter is not equal tozero.

[0225] In some example embodiments, the method 1100 further comprises: in accordance with a determination that a value of the second timer reaches the timer threshold value, resetting the counter.

[0226] In some example embodiments, the method 1100 further comprises: in relation to applicability determination information, update a machine learning capability by performing at least one of the following: downloading one or more machine learning model, adjusting one or more parameters of one or more machine learning model, adjusting one or more model switching rules, or deleting one or more machine learning model; and resetting respective barring states of one or more applicability determination information according to the update.

[0227] In some example embodiments, the resetting of the barring state of the one or more applicability determination information causes the first apparatus to perform at least one of the following: resetting one or more counters; resetting one or more first timers; resetting one or more second timers; or setting one or more barring states to be unbarred.

[0228] In some example embodiments, the configuration is obtained along with a channel state information, CSI, report configuration, CSI measurement configuration, applicability determination information, Radio Resource Management (RRM) measurement configuration or LTE Positioning Protocol (LPP) configuration.

[0229] In some example embodiments, the method 1100 further comprises: evaluating the applicability based on the applicability determination information; and considering the applicability to be inapplicable based on a barring state associated with the applicability determination information being set to barred.

[0230] In some example embodiments, the method 1100 further comprises: in accordance with a determination that respective applicability of one or more applicability determination information is considered to be inapplicable based on respective barring states associated with the one or more applicability determination information being set to be barred, reporting to the second apparatus, respective applicability of one or more applicability determination information as inapplicable.

[0231] In some example embodiments, the respective inapplicable applicability is implicitly indicated in the report through an absence of the one or more applicabilitydetermination information.

[0232] In some example embodiments, the method 1100 further comprises: indicating respective causes of inapplicability as barred for the one or more applicability determination information in the report.

[0233] In some example embodiments, the at least one cause is indicated by an information element in a CSI report configuration release list or by a CSI report configuration release cause list.

[0234] In some example embodiments, the first apparatus comprises a terminal device and the second apparatus comprises a network node.

[0235] FIG. 12 shows a flowchart of an example method 1200 implemented at a second apparatus in accordance with some example embodiments of the present disclosure. For the purpose of discussion, the method 1200 will be described from the perspective of the second apparatus 120 in FIG. 1.

[0236] At block 1210, the second apparatus provides, to the first apparatus, a configuration for a counter associated with applicability determination information for a machine learning configuration.

[0237] At block 1220, the second apparatus transmits, to the first apparatus, information indicating at least one cause for releasing a function configured by the machine learning configuration,

[0238] At block 1230, the second apparatus receives, from the first apparatus, an indication of the applicability of the machine learning configuration.

[0239] In some example embodiments, the configuration comprises at least one of the following: a counter threshold value; or at least one timer threshold value.

[0240] In some example embodiments, the method 1200 further comprises: providing, to the first apparatus, a timer threshold value of a first timer.

[0241] In some example embodiments, the method 1200 further comprises: providing, to the first apparatus, a timer threshold value of a second timer.

[0242] In some example embodiments, the method 1200 further comprises: transmitting, to the first apparatus, the configuration along with a channel state information, CSI, reportconfiguration, a CSI measurement configuration, applicability determination information, Radio Resource Management (RRM) measurement configuration or LTE Positioning Protocol (LPP) configuration.

[0243] In some example embodiments, the at least one cause is indicated by an information element in a CSI report configuration release list or by a CSI report configuration release cause list.

[0244] In some example embodiments, the first apparatus comprises a terminal device and the second apparatus comprises a network node.

[0245] FIG. 13 shows a flowchart of an example method 1300 implemented at a first apparatus in accordance with some example embodiments of the present disclosure. For the purpose of discussion, the method 1300 will be described from the perspective of the first apparatus 110 in FIG. 1.

[0246] At block 1310, the first apparatus receives, from the second apparatus, a configuration for at least one timer associated with applicability determination information for a machine learning configuration.

[0247] At block 1320, in accordance with receiving from the second apparatus, information indicating a poor performance of a function configured by the machine learning configuration, the first apparatus starts the at least one timer.

[0248] At block 1330, the first apparatus reports, to the second apparatus, an indication of an applicability associated with the applicability determination information based at least on a value of the at least one timer.

[0249] In some example embodiments, the configuration comprises at least one timer threshold value.

[0250] In some example embodiments, the method 1300 further comprises: in accordance with a determination, considering on a timer threshold value of the first timer, that the first timer is not expired, consider a barring state of the applicability determination information to be barred.

[0251] In some example embodiments, the method 1300 further comprises: in accordance with a determination, considering on a timer threshold value of the first timer, that the first timer is expired, consider a barring state of the applicability determinationinformation to be unbarred.

[0252] In some example embodiments, the method 1300 further comprises: obtaining a counter and a counter threshold value from the second apparatus; incrementing the counter based on the reception of the information indicating the poor performance; in accordance with a determination that a value of the counter reaches a counter threshold value, starting the first timer; and in accordance with a determination that a value of the first timer reaches the timer threshold value, resetting the counter.

[0253] In some example embodiments, the method 1300 further comprises: in accordance with a determination of an incrementing of the counter, resetting and start the second timer.

[0254] In some example embodiments, the method 1300 further comprises: in accordance with a determination that a value of the second timer reaches a timer threshold value, decrementing counter.

[0255] In some example embodiments, the method 1300 further comprises: resetting and start the second timer upon a determination that a value of the counter is not equal to zero.

[0256] In some example embodiments, the method 1300 further comprises: in accordance with a determination that a value of the second timer reaches the timer threshold value, resetting the counter.

[0257] In some example embodiments, the method 1300 further comprises: in relation to applicability determination information, update a machine learning capability by performing at least one of the following: downloading one or more machine learning model, adjusting one or more parameters of one or more machine learning model, adjusting one or more model switching rules, or deleting one or more machine learning model; and resetting respective barring states of one or more applicability determination information according to the update.

[0258] In some example embodiments, the resetting of the barring state of the one or more applicability determination information causes the first apparatus to perform at least one of the following: resetting one or more counters; resetting one or more first timers; resetting one or more second timers; or setting one or more barring states to be unbarred.

[0259] In some example embodiments, the configuration is obtained along with a channel state information, CSI, report configuration, CSI measurement configuration, applicability determination information, Radio Resource Management (RRM) measurement configuration or LTE Positioning Protocol (LPP) configuration.

[0260] In some example embodiments, the method 1300 further comprises: evaluating the applicability based on the applicability determination information; and considering the applicability to be inapplicable based on a barring state associated with the applicability determination information being set to barred.

[0261] In some example embodiments, the method 1300 further comprises: in accordance with a determination that respective applicability of one or more applicability determination information is considered to be inapplicable based on respective barring states associated with the one or more applicability determination information being set to be barred, reporting to the second apparatus, respective applicability of one or more applicability determination information as inapplicable.

[0262] In some example embodiments, the respective inapplicable applicability is implicitly indicated in the report through an absence of the one or more applicability determination information.

[0263] In some example embodiments, the method 1300 further comprises: indicating respective causes of inapplicability as barred for the one or more applicability determination information in the report.

[0264] In some example embodiments, the first apparatus comprises a terminal device and the second apparatus comprises a network node.

[0265] FIG. 14 shows a flowchart of an example method 1400 implemented at a second apparatus in accordance with some example embodiments of the present disclosure. For the purpose of discussion, the method 1400 will be described from the perspective of the second apparatus 120 in FIG. 1.

[0266] At block 1410, the second apparatus provides, to the first apparatus, a configuration for at least one timer associated with applicability determination information for a machine learning configuration.

[0267] At block 1420, the second apparatus transmits, to the first apparatus, informationindicating a poor performance of a function configured by the machine learning configuration,

[0268] At block 1430, the second apparatus receives, from the first apparatus, an indication of the applicability of the machine learning configuration.

[0269] In some example embodiments, the configuration comprises at least one timer threshold value.

[0270] In some example embodiments, the method 1400 further comprises: providing, to the first apparatus, a counter and a counter threshold value

[0271] In some example embodiments, the method 1400 further comprises: transmitting, to the first apparatus, the configuration along with a channel state information, CSI, report configuration, a CSI measurement configuration, applicability determination information, Radio Resource Management (RRM) measurement configuration or LTE Positioning Protocol (LPP) configuration.

[0272] In some example embodiments, the first apparatus comprises a terminal device and the second apparatus comprises a network node.

[0273] FIG. 15 shows a flowchart of an example method 1500 implemented at a first apparatus in accordance with some example embodiments of the present disclosure. For the purpose of discussion, the method 1500 will be described from the perspective of the first apparatus 110 in FIG. 1.

[0274] At block 1510, the first apparatus receives, from the second apparatus, a configuration for at least one timer associated with applicability determination information for a machine learning configuration.

[0275] At block 1520, in accordance with receiving from the second apparatus, information indicating at least one cause for releasing a function configured by the machine learning configuration, the first apparatus starts the at least one timer.

[0276] At block 1530, the first apparatus reports, to the second apparatus, an indication of an applicability associated with the applicability determination information based on at least a value of the at least one timer.

[0277] In some example embodiments, the configuration comprises at least one timer threshold value.

[0278] In some example embodiments, the method 1500 further comprises: in accordance with a determination, considering on a timer threshold value of the first timer, that the first timer is not expired, consider a barring state of the applicability determination information to be barred.

[0279] In some example embodiments, the method 1500 further comprises: in accordance with a determination, considering on a timer threshold value of the first timer, that the first timer is expired, consider a barring state of the applicability determination information to be unbarred.

[0280] In some example embodiments, the method 1500 further comprises: obtaining a counter and a counter threshold value from the second apparatus; incrementing the counter based on the information indicating at least one cause; in accordance with a determination that a value of the counter reaches a counter threshold value, starting the first timer; and in accordance with a determination that a value of the first timer reaches the timer threshold value, resetting the counter.

[0281] In some example embodiments, the method 1500 further comprises: in accordance with a determination of an incrementing of the counter, resetting and start the second timer.

[0282] In some example embodiments, the method 1500 further comprises: in accordance with a determination that a value of the second timer reaches a timer threshold value, decrementing counter.

[0283] In some example embodiments, the method 1500 further comprises: resetting and start the second timer upon a determination that a value of the counter is not equal to zero.

[0284] In some example embodiments, the method 1500 further comprises: in accordance with a determination that a value of the second timer reaches the timer threshold value, resetting the counter.

[0285] In some example embodiments, the method 1500 further comprises: in relation to applicability determination information, update a machine learning capability by performing at least one of the following: downloading one or more machine learning model, adjusting one or more parameters of one or more machine learning model, adjusting one or more model switching rules, or deleting one or more machine learningmodel; and resetting respective barring states of one or more applicability determination information according to the update.

[0286] In some example embodiments, the resetting of the barring state of the one or more applicability determination information causes the first apparatus to perform at least one of the following: resetting one or more counters; resetting one or more first timers; resetting one or more second timers; or setting one or more barring states to be unbarred.

[0287] In some example embodiments, the configuration is obtained along with a channel state information, CSI, report configuration, CSI measurement configuration, applicability determination information, Radio Resource Management (RRM) measurement configuration or LTE Positioning Protocol (LPP) configuration.

[0288] In some example embodiments, the method 1500 further comprises: evaluating the applicability based on the applicability determination information; and considering the applicability to be inapplicable based on a barring state associated with the applicability determination information being set to barred.

[0289] In some example embodiments, the method 1500 further comprises: in accordance with a determination that respective applicability of one or more applicability determination information is considered to be inapplicable based on respective barring states associated with the one or more applicability determination information being set to be barred, reporting to the second apparatus, respective applicability of one or more applicability determination information as inapplicable.

[0290] In some example embodiments, the respective inapplicable applicability is implicitly indicated in the report through an absence of the one or more applicability determination information.

[0291] In some example embodiments, the method 1500 further comprises: indicating respective causes of inapplicability as barred for the one or more applicability determination information in the report.

[0292] In some example embodiments, the at least one cause is indicated by an information element in a CSI report configuration release list or by a CSI report configuration release cause list.

[0293] In some example embodiments, the first apparatus comprises a terminal deviceand the second apparatus comprises a network node.

[0294] FIG. 16 shows a flowchart of an example method 1600 implemented at a second apparatus in accordance with some example embodiments of the present disclosure. For the purpose of discussion, the method 1600 will be described from the perspective of the second apparatus 120 in FIG. 1.

[0295] At block 1610, the second apparatus provides, to the first apparatus, a configuration for at least one timer associated with applicability determination information for a machine learning configuration.

[0296] At block 1620, the second apparatus transmits, to the first apparatus, information indicating at least one cause for releasing a function configured by the machine learning configuration,

[0297] At block 1630, the second apparatus receives, from the first apparatus, an indication of the applicability of the machine learning configuration.

[0298] In some example embodiments, the configuration comprises at least one timer threshold value.

[0299] In some example embodiments, the method 1600 further comprises: providing, to the first apparatus, a counter and a counter threshold value.

[0300] In some example embodiments, the method 1600 further comprises: transmitting, to the first apparatus, the configuration along with a channel state information, CSI, report configuration, a CSI measurement configuration, applicability determination information, Radio Resource Management (RRM) measurement configuration or LTE Positioning Protocol (LPP) configuration.

[0301] In some example embodiments, the at least one cause is indicated by an information element in a CSI report configuration release list or by a CSI report configuration release cause list.

[0302] In some example embodiments, the first apparatus comprises a terminal device and the second apparatus comprises a network node.

[0303] In some example embodiments, a first apparatus capable of performing any of the method 900 (for example, the first apparatus 110 in FIG. 1) may comprise means for performing the respective operations of the method 900. The means may be implementedin any suitable form. For example, the means may be implemented in a circuitry or software module. The first apparatus may be implemented as or included in the first apparatus 110 in FIG. 1.

[0304] In some example embodiments, the first apparatus comprises means for receiving, from the second apparatus, a configuration for a counter associated with applicability determination information for a machine learning configuration; means for in accordance with receiving from the second apparatus, information indicating a poor performance of a function configured by the machine learning configuration, increment the counter; and means for reporting, to the second apparatus, an indication of an applicability associated with the applicability determination information based at least on a value of the counter.

[0305] In some example embodiments, the configuration comprises at least one of the following: a counter threshold value; or at least one timer threshold value.

[0306] In some example embodiments, the first apparatus further comprises: means for in accordance with a determination that a value of the counter reaches the counter threshold value, considering a barring state of the applicability determination information to be barred.

[0307] In some example embodiments, the first apparatus further comprises: means for receiving, from the second apparatus, a timer threshold value of a first timer; means for in accordance with a determination that a value of the counter reaches a counter threshold value, starting the first timer; means for in accordance with a determination that a value of the first timer reaches the timer threshold value, resetting the counter; and means for considering a barring state of the applicability determination information to be unbarred.

[0308] In some example embodiments, the first apparatus further comprises: means for receiving, from the second apparatus, a timer threshold value of a second timer; means for in accordance with a determination of an incrementing of the counter, resetting and start the second timer.

[0309] In some example embodiments, the first apparatus further comprises: means for in accordance with a determination that a value of the second timer reaches the timer threshold value, decrementing the counter.

[0310] In some example embodiments, the first apparatus further comprises: means forresetting and starting the second timer upon a determination that a value of the counter is not equal to zero.

[0311] In some example embodiments, the first apparatus further comprises: means for in accordance with a determination that a value of the second timer reaches the timer threshold value, resetting the counter.

[0312] In some example embodiments, the first apparatus further comprises: means for in relation to applicability determination information, update a machine learning capability by performing at least one of the following: means for downloading one or more machine learning model, means for adjusting one or more parameters of one or more machine learning model, means for adjusting one or more model switching rules, or means for deleting one or more machine learning model; and means for resetting respective barring states of one or more applicability determination information according to the update.

[0313] In some example embodiments, the resetting of the barring state of the one or more applicability determination information causes the first apparatus to perform at least one of the following: resetting one or more counters; resetting one or more first timers; resetting one or more second timers; or setting one or more barring states to be unbarred.

[0314] In some example embodiments, the configuration is obtained along with a channel state information, CSI, report configuration, CSI measurement configuration, applicability determination information, Radio Resource Management (RRM) measurement configuration or LTE Positioning Protocol (LPP) configuration.

[0315] In some example embodiments, the first apparatus further comprises: means for evaluating the applicability based on the applicability determination information; and means for considering the applicability to be inapplicable based on a barring state associated with the applicability determination information being set to barred.

[0316] In some example embodiments, the first apparatus further comprises: means for in accordance with a determination that respective applicability of one or more applicability determination information is considered to be inapplicable based on respective barring states associated with the one or more applicability determination information being set to be barred, reporting to the second apparatus, respective applicability of one or more applicability determination information as inapplicable.

[0317] In some example embodiments, the respective inapplicable applicability is implicitly indicated in the report through an absence of the one or more applicability determination information.

[0318] In some example embodiments, the first apparatus further comprises: means for indicating respective causes of inapplicability as barred for the one or more applicability determination information in the report.

[0319] In some example embodiments, the first apparatus comprises a terminal device and the second apparatus comprises a network node.

[0320] In some example embodiments, a second apparatus capable of performing any of the method 1000 (for example, the second apparatus 120 in FIG. 1) may comprise means for performing the respective operations of the method 1000. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module. The second apparatus may be implemented as or included in the second apparatus 120 in FIG. 1.

[0321] In some example embodiments, the second apparatus comprises means for providing, to the first apparatus, a configuration for a counter associated with applicability determination information for a machine learning configuration; means for transmitting, to the first apparatus, information indicating a poor performance of the machine learning configuration associated with the applicability determination information; and means for receiving, from the first apparatus, an indication of the applicability of the machine learning configuration.

[0322] In some example embodiments, the configuration comprises at least one of the following: a counter threshold value; or at least one timer threshold value.

[0323] In some example embodiments, the second apparatus further comprises: means for providing, to the first apparatus, a timer threshold value of a first timer.

[0324] In some example embodiments, the second apparatus further comprises: means for providing, to the first apparatus, a timer threshold value of a second timer.

[0325] In some example embodiments, the second apparatus further comprises: means for transmitting, to the first apparatus, the configuration along with a channel state information, CSI, report configuration, a CSI measurement configuration, applicabilitydetermination information, Radio Resource Management (RRM) measurement configuration or LTE Positioning Protocol (LPP) configuration.

[0326] In some example embodiments, the first apparatus comprises a terminal device and the second apparatus comprises a network node.

[0327] In some example embodiments, a first apparatus capable of performing any of the method 1100 (for example, the first apparatus 110 in FIG. 1) may comprise means for performing the respective operations of the method 1100. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module. The first apparatus may be implemented as or included in the first apparatus 110 in FIG. 1.

[0328] In some example embodiments, the first apparatus comprises means for receiving, from the second apparatus, a configuration for a counter associated with applicability determination information for a machine learning configuration; means for in accordance with receiving from the second apparatus, information indicating at least one cause for releasing a function configured by the machine learning configuration, increment the counter; and means for reporting, to the second apparatus , an indication of an applicability associated with the applicability determination information based at least on a value of the counter.

[0329] In some example embodiments, the configuration comprises at least one of the following: a counter threshold value; or at least one timer threshold value.

[0330] In some example embodiments, the first apparatus further comprises: means for in accordance with a determination that a value of the counter reaches the counter threshold value, considering a barring state of the applicability determination information to be barred.

[0331] In some example embodiments, the first apparatus further comprises: means for receiving, from the second apparatus, a timer threshold value of a first timer; means for in accordance with a determination that a value of the counter reaches a counter threshold value, starting the first timer; means for in accordance with a determination that a value of the first timer reaches the timer threshold value, resetting the counter; and means for considering a barring state of the applicability determination information to be unbarred.

[0332] In some example embodiments, the first apparatus further comprises: means forreceiving, from the second apparatus, a timer threshold value of a second timer; means for in accordance with a determination of an incrementing of the counter, resetting and start the second timer.

[0333] In some example embodiments, the first apparatus further comprises: means for in accordance with a determination that a value of the second timer reaches the timer threshold value, decrementing counter.

[0334] In some example embodiments, the first apparatus further comprises: means for resetting and starting the second timer upon a determination that a value of the counter is not equal to zero.

[0335] In some example embodiments, the first apparatus further comprises: means for in accordance with a determination that a value of the second timer reaches the timer threshold value, resetting the counter.

[0336] In some example embodiments, the first apparatus further comprises: means for in relation to applicability determination information, update a machine learning capability by performing at least one of the following: means for downloading one or more machine learning model, means for adjusting one or more parameters of one or more machine learning model, means for adjusting one or more model switching rules, or means for deleting one or more machine learning model; and means for resetting respective barring states of one or more applicability determination information according to the update.

[0337] In some example embodiments, the resetting of the barring state of the one or more applicability determination information causes the first apparatus to perform at least one of the following: resetting one or more counters; resetting one or more first timers; resetting one or more second timers; or setting one or more barring states to be unbarred.

[0338] In some example embodiments, the configuration is obtained along with a channel state information, CSI, report configuration, CSI measurement configuration, applicability determination information, Radio Resource Management (RRM) measurement configuration or LTE Positioning Protocol (LPP) configuration.

[0339] In some example embodiments, the first apparatus further comprises: means for evaluating the applicability based on the applicability determination information; and means for considering the applicability to be inapplicable based on a barring stateassociated with the applicability determination information being set to barred.

[0340] In some example embodiments, the first apparatus further comprises: means for in accordance with a determination that respective applicability of one or more applicability determination information is considered to be inapplicable based on respective barring states associated with the one or more applicability determination information being set to be barred, reporting to the second apparatus, respective applicability of one or more applicability determination information as inapplicable.

[0341] In some example embodiments, the respective inapplicable applicability is implicitly indicated in the report through an absence of the one or more applicability determination information.

[0342] In some example embodiments, the first apparatus further comprises: means for indicating respective causes of inapplicability as barred for the one or more applicability determination information in the report.

[0343] In some example embodiments, the at least one cause is indicated by an information element in a CSI report configuration release list or by a CSI report configuration release cause list.

[0344] In some example embodiments, the first apparatus comprises a terminal device and the second apparatus comprises a network node.

[0345] In some example embodiments, a second apparatus capable of performing any of the method 1200 (for example, the second apparatus 120 in FIG. 1) may comprise means for performing the respective operations of the method 1200. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module. The second apparatus may be implemented as or included in the second apparatus 120 in FIG. 1.

[0346] In some example embodiments, the second apparatus comprises means for providing, to the first apparatus, a configuration for a counter associated with applicability determination information for a machine learning configuration; means for transmitting, to the first apparatus, information indicating at least one cause for releasing a function configured by the machine learning configuration, and means for receiving, from the first apparatus, an indication of the applicability of the machine learning configuration.

[0347] In some example embodiments, the configuration comprises at least one of the following: a counter threshold value; or at least one timer threshold value.

[0348] In some example embodiments, the second apparatus further comprises: means for providing, to the first apparatus, a timer threshold value of a first timer.

[0349] In some example embodiments, the second apparatus further comprises: means for providing, to the first apparatus, a timer threshold value of a second timer.

[0350] In some example embodiments, the second apparatus further comprises: means for transmitting, to the first apparatus, the configuration along with a channel state information, CSI, report configuration, a CSI measurement configuration, applicability determination information, Radio Resource Management (RRM) measurement configuration or LTE Positioning Protocol (LPP) configuration.

[0351] In some example embodiments, the at least one cause is indicated by an information element in a CSI report configuration release list or by a CSI report configuration release cause list.

[0352] In some example embodiments, the first apparatus comprises a terminal device and the second apparatus comprises a network node.

[0353] In some example embodiments, a first apparatus capable of performing any of the method 1300 (for example, the first apparatus 110 in FIG. 1) may comprise means for performing the respective operations of the method 1300. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module. The first apparatus may be implemented as or included in the first apparatus 110 in FIG. 1.

[0354] In some example embodiments, the first apparatus comprises means for receiving, from the second apparatus, a configuration for at least one timer associated with applicability determination information for a machine learning configuration; means for in accordance with receiving from the second apparatus, information indicating a poor performance of a function configured by the machine learning configuration, start the at least one timer; and means for reporting, to the second apparatus, an indication of an applicability associated with the applicability determination information based at least on a value of the at least one timer.

[0355] In some example embodiments, the configuration comprises at least one timer threshold value.

[0356] In some example embodiments, the first apparatus further comprises: means for in accordance with a determination, considering on a timer threshold value of the first timer, that the first timer is not expired, consider a barring state of the applicability determination information to be barred.

[0357] In some example embodiments, the first apparatus further comprises: means for in accordance with a determination, considering on a timer threshold value of the first timer, that the first timer is expired, consider a barring state of the applicability determination information to be unbarred.

[0358] In some example embodiments, the first apparatus further comprises: means for obtaining a counter and a counter threshold value from the second apparatus; means for incrementing the counter based on the reception of the information indicating the poor performance; means for in accordance with a determination that a value of the counter reaches a counter threshold value, starting the first timer; and means for in accordance with a determination that a value of the first timer reaches the timer threshold value, resetting the counter.

[0359] In some example embodiments, the first apparatus further comprises: means for in accordance with a determination of an incrementing of the counter, resetting and start the second timer.

[0360] In some example embodiments, the first apparatus further comprises: means for in accordance with a determination that a value of the second timer reaches a timer threshold value, decrementing counter.

[0361] In some example embodiments, the first apparatus further comprises: means for resetting and starting the second timer upon a determination that a value of the counter is not equal to zero.

[0362] In some example embodiments, the first apparatus further comprises: means for in accordance with a determination that a value of the second timer reaches the timer threshold value, resetting the counter.

[0363] In some example embodiments, the first apparatus further comprises: means forin relation to the applicability determination information, update a machine learning capability by performing at least one of the following: means for downloading one or more machine learning model, means for adjusting one or more parameters of one or more machine learning model, means for adjusting one or more model switching rules, or means for deleting one or more machine learning model; and means for resetting respective barring states of one or more applicability determination information according to the update.

[0364] In some example embodiments, the resetting of the barring state of the one or more applicability determination information causes the first apparatus to perform at least one of the following: resetting one or more counters; resetting one or more first timers; resetting one or more second timers; or setting one or more barring states to be unbarred.

[0365] In some example embodiments, the configuration is obtained along with a channel state information, CSI, report configuration, CSI measurement configuration, applicability determination information, Radio Resource Management (RRM) measurement configuration or LTE Positioning Protocol (LPP) configuration.

[0366] In some example embodiments, the first apparatus further comprises: means for evaluating the applicability based on the applicability determination information; and means for considering the applicability to be inapplicable based on a barring state associated with the applicability determination information being set to barred.

[0367] In some example embodiments, the first apparatus further comprises: means for in accordance with a determination that respective applicability of one or more applicability determination information is considered to be inapplicable based on respective barring states associated with the one or more applicability determination information being set to be barred, reporting to the second apparatus, respective applicability of one or more applicability determination information as inapplicable.

[0368] In some example embodiments, the respective inapplicable applicability is implicitly indicated in the report through an absence of the one or more applicability determination information.

[0369] In some example embodiments, the first apparatus further comprises: means for indicating respective causes of inapplicability as barred for the one or more applicability determination information in the report.

[0370] In some example embodiments, the first apparatus comprises a terminal device and the second apparatus comprises a network node.

[0371] In some example embodiments, a second apparatus capable of performing any of the method 1400 (for example, the second apparatus 120 in FIG. 1) may comprise means for performing the respective operations of the method 1400. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module. The second apparatus may be implemented as or included in the second apparatus 120 in FIG. 1.

[0372] In some example embodiments, the second apparatus comprises means for providing, to the first apparatus, a configuration for at least one timer associated with applicability determination information for a machine learning configuration; means for transmitting, to the first apparatus, information indicating a poor performance of a function configured by the machine learning configuration, and means for receiving, from the first apparatus, an indication of the applicability of the machine learning configuration.

[0373] In some example embodiments, the configuration comprises at least one timer threshold value.

[0374] In some example embodiments, the second apparatus further comprises: means for providing, to the first apparatus, a counter and a counter threshold value

[0375] In some example embodiments, the second apparatus further comprises: means for transmitting, to the first apparatus, the configuration along with a channel state information, CSI, report configuration, a CSI measurement configuration, applicability determination information, Radio Resource Management (RRM) measurement configuration or LTE Positioning Protocol (LPP) configuration.

[0376] In some example embodiments, the first apparatus comprises a terminal device and the second apparatus comprises a network node.

[0377] In some example embodiments, a first apparatus capable of performing any of the method 1500 (for example, the first apparatus 110 in FIG. 1) may comprise means for performing the respective operations of the method 1500. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module. The first apparatus may be implemented as or included in the first apparatus 110 in FIG. 1.

[0378] In some example embodiments, the first apparatus comprises means for receiving, from the second apparatus, a configuration for at least one timer associated with applicability determination information for a machine learning configuration; means for in accordance with receiving from the second apparatus, information indicating at least one cause for releasing a function configured by the machine learning configuration, start the at least one timer; and means for reporting, to the second apparatus, an indication of an applicability associated with the applicability determination information based on at least a value of the at least one timer.

[0379] In some example embodiments, the configuration comprises at least one timer threshold value.

[0380] In some example embodiments, the first apparatus further comprises: means for in accordance with a determination, considering on a timer threshold value of the first timer, that the first timer is not expired, consider a barring state of the applicability determination information to be barred.

[0381] In some example embodiments, the first apparatus further comprises: means for in accordance with a determination, considering on a timer threshold value of the first timer, that the first timer is expired, consider a barring state of the applicability determination information to be unbarred.

[0382] In some example embodiments, the first apparatus further comprises: means for obtaining a counter and a counter threshold value from the second apparatus; means for incrementing the counter based on the information indicating at least one cause; means for in accordance with a determination that a value of the counter reaches a counter threshold value, starting the first timer; and means for in accordance with a determination that a value of the first timer reaches the timer threshold value, resetting the counter.

[0383] In some example embodiments, the first apparatus further comprises: means for in accordance with a determination of an incrementing of the counter, resetting and start the second timer.

[0384] In some example embodiments, the first apparatus further comprises: means for in accordance with a determination that a value of the second timer reaches a timer threshold value, decrementing counter.

[0385] In some example embodiments, the first apparatus further comprises: means forresetting and starting the second timer upon a determination that a value of the counter is not equal to zero.

[0386] In some example embodiments, the first apparatus further comprises: means for in accordance with a determination that a value of the second timer reaches the timer threshold value, resetting the counter.

[0387] In some example embodiments, the first apparatus further comprises: means for in relation to the applicability determination information, update a machine learning capability by performing at least one of the following: means for downloading one or more machine learning model, means for adjusting one or more parameters of one or more machine learning model, means for adjusting one or more model switching rules, or means for deleting one or more machine learning model; and means for resetting respective barring states of one or more applicability determination information according to the update.

[0388] In some example embodiments, the resetting of the barring state of the one or more applicability determination information causes the first apparatus to perform at least one of the following: resetting one or more counters; resetting one or more first timers; resetting one or more second timers; or setting one or more barring states to be unbarred.

[0389] In some example embodiments, the configuration is obtained along with a channel state information, CSI, report configuration, CSI measurement configuration, applicability determination information, Radio Resource Management (RRM) measurement configuration or LTE Positioning Protocol (LPP) configuration.

[0390] In some example embodiments, the first apparatus further comprises: means for evaluating the applicability based on the applicability determination information; and means for considering the applicability to be inapplicable based on a barring state associated with the applicability determination information being set to barred.

[0391] In some example embodiments, the first apparatus further comprises: means for in accordance with a determination that respective applicability of one or more applicability determination information is considered to be inapplicable based on respective barring states associated with the one or more applicability determination information being set to be barred, reporting to the second apparatus, respective applicability of one or more applicability determination information as inapplicable.

[0392] In some example embodiments, the respective inapplicable applicability is implicitly indicated in the report through an absence of the one or more applicability determination information.

[0393] In some example embodiments, the first apparatus further comprises: means for indicating respective causes of inapplicability as barred for the one or more applicability determination information in the report.

[0394] In some example embodiments, the at least one cause is indicated by an information element in a CSI report configuration release list or by a CSI report configuration release cause list.

[0395] In some example embodiments, the first apparatus comprises a terminal device and the second apparatus comprises a network node.

[0396] In some example embodiments, a second apparatus capable of performing any of the method 1600 (for example, the second apparatus 120 in FIG. 1) may comprise means for performing the respective operations of the method 1600. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module. The second apparatus may be implemented as or included in the second apparatus 120 in FIG. 1.

[0397] In some example embodiments, the second apparatus comprises means for providing, to the first apparatus, a configuration for at least one timer associated with applicability determination information for a machine learning configuration; means for transmitting, to the first apparatus, information indicating at least one cause for releasing a function configured by the machine learning configuration, and means for receiving, from the first apparatus, an indication of the applicability of the machine learning configuration.

[0398] In some example embodiments, the configuration comprises at least one timer threshold value.

[0399] In some example embodiments, the second apparatus further comprises: means for providing, to the first apparatus, a counter and a counter threshold value.

[0400] In some example embodiments, the second apparatus further comprises: means for transmitting, to the first apparatus, the configuration along with a channel stateinformation, CSI, report configuration, a CSI measurement configuration, applicability determination information, Radio Resource Management (RRM) measurement configuration or LTE Positioning Protocol (LPP) configuration.

[0401] In some example embodiments, the at least one cause is indicated by an information element in a CSI report configuration release list or by a CSI report configuration release cause list.

[0402] In some example embodiments, the first apparatus comprises a terminal device and the second apparatus comprises a network node.

[0403] FIG. 17 is a simplified block diagram of a device 1700 that is suitable for implementing example embodiments of the present disclosure. The device 1700 may be provided to implement a communication device, for example, the first apparatus 110 or the second apparatus 120 as shown in FIG. 1. As shown, the device 1700 includes one or more processors 1710, one or more memories 1720 coupled to the processor 1710, and one or more communication modules 1740 coupled to the processor 1710.

[0404] The communication module 1740 is for bidirectional communications. The communication module 1740 has one or more communication interfaces to facilitate communication with one or more other modules or devices. The communication interfaces may represent any interface that is necessary for communication with other network elements. In some example embodiments, the communication module 1740 may include at least one antenna.

[0405] The processor 1710 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 1700 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.

[0406] The memory 1720 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) 1724, an electrically programmable read only memory (EPROM), a flash memory, a hard disk, a compact disc (CD), a digital video disk (DVD), an optical disk, a laser disk, and other magnetic storage and / or optical storage.Examples of the volatile memories include, but are not limited to, a random-access memory (RAM) 1722 and other volatile memories that will not last in the power-down duration.

[0407] A computer program 1730 includes computer executable instructions that are executed by the associated processor 1710. The instructions of the program 1730 may include instructions for performing operations / acts of some example embodiments of the present disclosure. The program 1730 may be stored in the memory, e.g., the ROM 1724. The processor 1710 may perform any suitable actions and processing by loading the program 1730 into the RAM 1722.

[0408] The example embodiments of the present disclosure may be implemented by means of the program 1730 so that the device 1700 may perform any process of the disclosure as discussed with reference to FIG. 2 to FIG. 16. The example embodiments of the present disclosure may also be implemented by hardware or by a combination of software and hardware.

[0409] In some example embodiments, the program 1730 may be tangibly contained in a computer readable medium which may be included in the device 1700 (such as in the memory 1720) or other storage devices that are accessible by the device 1700. The device 1700 may load the program 1730 from the computer readable medium to the RAM 1722 for execution. In some example embodiments, the computer readable medium may include any types of non-transitory storage medium, such as ROM, EPROM, a flash memory, a hard disk, CD, DVD, and the like. The term “non-transitory,” as used herein, is a limitation of the medium itself (i.e., tangible, not a signal) as opposed to a limitation on data storage persistency (e.g., RAM vs. ROM).

[0410] FIG. 18 shows an example of the computer readable medium 1800 which may be in form of CD, DVD or other optical storage disk. The computer readable medium 1800 has the program 1730 stored thereon.

[0411] Generally, various embodiments of the present disclosure may be implemented in hardware or special purpose circuits, software, logic or any combination thereof. Some aspects may be implemented in hardware, and other aspects may be implemented in firmware or software which may be executed by a controller, microprocessor or other computing device. Although various aspects of embodiments of the present disclosure are illustrated and described as block diagrams, flowcharts, or using some other pictorialOUrepresentations, 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.

[0412] Some example embodiments of the present disclosure also provide at least one computer program product tangibly stored on a computer readable medium, such as a non-transitory computer readable medium. The computer program product includes computerexecutable instructions, such as those included in program modules, being executed in a device on a target physical or virtual processor, to carry out any of the methods as described above. Generally, program modules include routines, programs, libraries, objects, classes, components, data structures, or the like that perform particular tasks or implement particular abstract data types. The functionality of the program modules may be combined or split between program modules as desired in various embodiments. Machine-executable instructions for program modules may be executed within a local or distributed device. In a distributed device, program modules may be located in both local and remote storage media.

[0413] Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. The program code may be provided to a processor or controller of a general-purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program code, when executed by the processor or controller, cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may execute entirely on a machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

[0414] In the context of the present disclosure, the computer program code or related data may be carried by any suitable carrier to enable the device, apparatus or processor to perform various processes and operations as described above. Examples of the carrier include a signal, computer readable medium, and the like.

[0415] 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 specificexamples 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.

[0416] Further, although operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. In certain circumstances, multitasking and parallel processing may be advantageous. Likewise, although several specific implementation details are contained in the above discussions, these should not be construed as limitations on the scope of the present disclosure, but rather as descriptions of features that may be specific to particular embodiments. Unless explicitly stated, certain features that are described in the context of separate embodiments may also be implemented in combination in a single embodiment. Conversely, unless explicitly stated, various features that are described in the context of a single embodiment may also be implemented in a plurality of embodiments separately or in any suitable sub-combination.

[0417] 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 first apparatus comprising:at least one processor; andat least one memory storing instructions that, when executed by the at least one processor, cause the first apparatus at least to:receive, from the second apparatus, a configuration for at least one timer associated with applicability determination information for a machine learning configuration;in accordance with receiving from the second apparatus, information indicating at least one cause for releasing a function configured by the machine learning configuration, start the at least one timer; andreport, to the second apparatus, an indication of an applicability associated with the applicability determination information based on at least a value of the at least one timer.

2. The apparatus of claim 1, wherein the configuration comprises at least one timer threshold value.

3. The first apparatus of claim 2, wherein the at least timer comprises a first timer, and wherein the first apparatus is caused to:in accordance with a determination, based on a timer threshold value of the first timer, that the first timer is not expired, consider a barring state of the applicability determination information to be barred.

4. The first apparatus of claim 3, wherein the first apparatus is caused to:in accordance with a determination, based on a timer threshold value of the first timer, that the first timer is expired, consider a barring state of the applicability determination information to be unbarred.

5. The first apparatus of claim 2, wherein the first apparatus is caused to:obtain a counter and a counter threshold value from the second apparatus; increment the counter based on the information indicating at least one cause;in accordance with a determination that a value of the counter reaches a counterthreshold value, start the first timer; andin accordance with a determination that a value of the first timer reaches the timer threshold value of the first timer, reset the counter.

6. The first apparatus of claim 5, wherein the at least one timer further comprises a second timer, and wherein the first apparatus is caused to:in accordance with a determination of an incrementing of the counter, reset and start the second timer.

7. The first apparatus of claim 6, wherein the first apparatus is caused to:in accordance with a determination that a value of the second timer reaches a timer threshold value of the second timer, decrement counter.

8. The first apparatus of claim 7, wherein the first apparatus is caused to:reset and start the second timer upon a determination that a value of the counter is not equal to zero.

9. The first apparatus of claim 5, wherein the first apparatus is caused to:in accordance with a determination that a value of the second timer reaches the timer threshold value of the second timer, reset the counter.

10. The first apparatus of claim 1, wherein the first apparatus is caused to:in relation to the applicability determination information, update a machine learning capability by performing at least one of the following:downloading one or more machine learning model;adjusting one or more parameters of one or more machine learning model; adjusting one or more model switching rules;deleting one or more machine learning model; orresetting respective barring states of one or more applicability determination information according to the update.

11. The first apparatus of claim 10, wherein the resetting of the barring state of the one or more applicability determination information causes the first apparatus to perform at least one of the following:64resetting one or more counters;resetting one or more first timers;resetting one or more second timers; orsetting one or more barring states to be unbarred.

12. The first apparatus of claim 1, wherein the configuration is obtained along with a channel state information, CSI, report configuration, CSI measurement configuration, applicability determination information, Radio Resource Management (RRM) measurement configuration or LTE Positioning Protocol (LPP) configuration.

13. The first apparatus of claim 1, wherein the first apparatus is caused to: evaluate the applicability based on the applicability determination information; and consider the applicability to be inapplicable based on a barring state associated with the applicability determination information being set to barred.

14. The first apparatus of claim 13, wherein the first apparatus is caused to:in accordance with a determination that respective applicability of one or more applicability determination information is considered to be inapplicable based on respective barring states associated with the one or more applicability determination information being set to be barred, report, to the second apparatus, respective applicability of one or more applicability determination information as inapplicable.

15. The first apparatus of claim 14, wherein the respective inapplicable applicability is implicitly indicated in the report through an absence of the one or more applicability determination information.

16. The first apparatus of claim 15, wherein the first apparatus is caused to: indicate respective causes of inapplicability as barred for the one or more applicability determination information in the report.

17. The first apparatus of any of claims 1-16, wherein the at least one cause is indicated by an information element in a CSI report configuration release list or by a CSI report configuration release cause list.6518. The first apparatus of any of claims 1-17, wherein the first apparatus comprises a terminal device and the second apparatus comprises a network node.

19. A second apparatus comprising:at least one processor; andat least one memory storing instructions that, when executed by the at least one processor, cause the second apparatus at least to:provide, to the first apparatus, a configuration for at least one timer associated with applicability determination information for a machine learning configuration;transmit, to the first apparatus, information indicating at least one cause for releasing a function configured by the machine learning configuration, andreceive, from the first apparatus, an indication of the applicability of the machine learning configuration.

20. The second apparatus of claim 19, wherein the configuration comprises at least one timer threshold value.

21. The second apparatus of claim 19, wherein the second apparatus is caused to: provide, to the first apparatus, a counter and a counter threshold value.

22. The second apparatus of claim 19, wherein the second apparatus is caused to: transmit, to the first apparatus, the configuration along with a channel state information, CSI, report configuration, a CSI measurement configuration, applicability determination information, Radio Resource Management (RRM) measurement configuration or LTE Positioning Protocol (LPP) configuration.

23. The second apparatus of claim 19, wherein the at least one cause is indicated by an information element in a CSI report configuration release list or by a CSI report configuration release cause list.

24. The second apparatus of any of claims 19-23, wherein the first apparatus comprises a terminal device and the second apparatus comprises a network node.

25. A method comprising:66receiving, from the second apparatus, a configuration for at least one timer associated with applicability determination information for a machine learning configuration;in accordance with receiving from the second apparatus, information indicating at least one cause for releasing a function configured by the machine learning configuration, starting the at least one timer; andreporting, to the second apparatus, an indication of an applicability associated with the applicability determination information based on at least a value of the at least one timer.

26. A method comprising:providing, to the first apparatus, a configuration for at least one timer associated with applicability determination information for a machine learning configuration;transmitting, to the first apparatus, information indicating at least one cause for releasing a function configured by the machine learning configuration, andreceiving, from the first apparatus, an indication of the applicability of the machine learning configuration.

27. A first apparatus comprising:means for receiving, from the second apparatus, a configuration for at least one timer associated with applicability determination information for a machine learning configuration;means for in accordance with receiving from the second apparatus, information indicating at least one cause for releasing a function configured by the machine learning configuration, starting the at least one timer; andmeans for reporting, to the second apparatus, an indication of an applicability associated with the applicability determination information based on at least a value of the at least one timer.

28. A second apparatus comprising:means for providing, to the first apparatus, a configuration for at least one timer associated with applicability determination information for a machine learning configuration;means for transmitting, to the first apparatus, information indicating at least one cause for releasing a function configured by the machine learning configuration, andmeans for receiving, from the first apparatus, an indication of the applicability of the machine learning configuration.6729 A computer readable medium comprising instructions stored thereon for causing an apparatus at least to perform the method of claim 25 or the method of claim 26.

Images