Mechanism for function-based lifecycle management

Abstract

The invention provides a function-based lifecycle management method, equipment, a device and a computer readable storage medium. Specifically, a solution is proposed to enable function-based performance monitoring via sending updates on configured / identified functions using an applicable condition framework. In this way, the performance of the AI / ML entity may be improved.

Description

Technical Field

[0001] Various example embodiments of the present disclosure relate generally to the field of telecommunications, and more particularly to methods, devices, apparatuses, and computer-readable storage media for capability-based lifecycle management (LCM). Background Art

[0002] Artificial intelligence (AI) and machine learning (ML) technologies are increasingly used in 5G systems (5GS) and are considered key enablers for the 5G advanced and 6G mobile network era. In the telecommunication industry, AI / ML models have been adopted in telecommunication systems to improve the performance of telecommunication systems. AI / ML technologies can be applied in a variety of scenarios. Therefore, it is worthwhile to further study AI / ML technologies. Summary of the invention

[0003] In a first aspect of the present disclosure, a device is provided. The device includes: at least one processor; and at least one memory, the at least one memory storing instructions, which, when executed by the at least one processor, cause the device to: send first information to a network device, the first information indicating at least one artificial intelligence and machine learning (AI / ML) entity supported by the device and a delay associated with the at least one AI / ML entity, wherein the delay includes at least one of the following: an activation delay of the at least one AI / ML entity, or a switching delay between another AI / ML entity and the at least one AI / ML entity; determine an updated delay associated with the at least one AI / ML entity, wherein the updated delay includes at least one of the following: an updated activation delay of the at least one AI / ML entity, or an updated switching delay between another AI / ML entity and the at least one AI / ML entity; and send second information associated with the updated delay to the network device.

[0004] In a second aspect of the present disclosure, a device is provided. The device includes: at least one processor; and at least one memory, wherein the at least one memory stores instructions, which, when executed by the at least one processor, cause the device to: receive first information from a terminal device, the first information indicating a condition associated with configuring at least one AI / ML entity and a delay associated with at least one AI / ML entity, wherein the delay includes at least one of the following: an activation delay of at least one AI / ML entity, or a switching delay between another AI / ML entity and at least one AI / ML entity; and receive second information associated with an updated delay from the terminal device, the updated delay being associated with at least one AI / ML entity, wherein the updated delay includes at least one of the following: an updated activation delay of at least one AI / ML entity, or an updated switching delay between another AI / ML entity and at least one AI / ML entity.

[0005] In a third aspect of the present disclosure, a method is provided. The method includes: sending first information to a network device, the first information indicating at least one artificial intelligence and machine learning (AI / ML) entity supported by the device and a delay associated with the at least one AI / ML entity, wherein the delay includes at least one of the following: an activation delay of the at least one AI / ML entity, or a switching delay between another AI / ML entity and the at least one AI / ML entity; determining an updated delay associated with the at least one AI / ML entity, wherein the updated delay includes at least one of the following: an updated activation delay of the at least one AI / ML entity, or an updated switching delay between another AI / ML entity and the at least one AI / ML entity; and sending second information associated with the updated delay to the network device.

[0006] In a fourth aspect of the present disclosure, a method is provided. The method includes: receiving first information from a terminal device, the first information indicating a condition associated with configuring at least one AI / ML entity and a delay associated with the at least one AI / ML entity, wherein the delay includes at least one of the following: an activation delay of the at least one AI / ML entity, or a switching delay between another AI / ML entity and the at least one AI / ML entity; and receiving second information associated with an updated delay from the terminal device, the updated delay being associated with the at least one AI / ML entity, wherein the updated delay includes at least one of the following: an updated activation delay of the at least one AI / ML entity, an updated switching delay between another AI / ML entity and the at least one AI / ML entity.

[0007] In a fifth aspect of the present disclosure, a first device is provided. The first device includes: a component for sending first information to a network device, the first information indicating at least one artificial intelligence and machine learning (AI / ML) entity supported by the device and a delay associated with the at least one AI / ML entity, wherein the delay is at least one of: an activation delay of the at least one AI / ML entity, or a switching delay between another AI / ML entity and the at least one AI / ML entity; a component for determining an updated delay associated with the at least one AI / ML entity, wherein the updated delay includes at least one of: an updated activation delay of the at least one AI / ML entity, or an updated switching delay between another AI / ML entity and the at least one AI / ML entity; and a component for sending second information associated with the updated delay to the network device.

[0008] In a sixth aspect of the present disclosure, a second device is provided. The second device includes: a component for receiving first information from a terminal device, the first information indicating a condition associated with configuring at least one AI / ML entity and a delay associated with at least one AI / ML entity, wherein the delay includes at least one of the following: an activation delay of at least one AI / ML entity, or a switching delay between another AI / ML entity and at least one AI / ML entity; and a component for receiving second information associated with an updated delay from the terminal device, the updated delay being associated with at least one AI / ML entity, wherein the updated delay includes at least one of the following: an updated activation delay of at least one AI / ML entity, or an updated switching delay between another AI / ML entity and at least one AI / ML entity.

[0009] In a seventh aspect of the present disclosure, a computer-readable medium is provided, wherein the computer-readable medium includes instructions stored thereon, and the instructions are used to cause a device to at least execute the method according to the third aspect.

[0010] In an eighth aspect of the present disclosure, a computer-readable medium is provided, wherein the computer-readable medium includes instructions stored thereon, and the instructions are used to cause a device to at least execute the method according to the fourth aspect.

[0011] It should be understood that the invention summary is not intended to identify the key or essential features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Some example embodiments will now be described with reference to the accompanying drawings, in which:

[0013] Figure 1 An example communication environment is shown in which example embodiments of the present disclosure may be implemented;

[0014] Figure 2 shows a signaling diagram for performance monitoring of a function according to an example embodiment of the present disclosure;

[0015] Figure 3 A schematic diagram showing function switching according to an exemplary embodiment of the present disclosure is shown;

[0016] Figure 4 A flowchart showing a method implemented at a first device according to some example embodiments of the present disclosure is shown;

[0017] Figure 5 A flowchart showing a method implemented at a second device according to some example embodiments of the present disclosure is shown;

[0018] Figure 6shows a simplified block diagram of a device suitable for implementing an example embodiment of the present disclosure; and

[0019] Figure 7 A block diagram of an example computer-readable medium is shown according to some example embodiments of the present disclosure.

[0020] Throughout the drawings, the same or similar reference numerals refer to the same or similar elements. DETAILED DESCRIPTION

[0021] The principles of the present disclosure will now be described with reference to some example embodiments. It should be understood that these embodiments are described only for illustrative purposes and to help those skilled in the art understand and implement the present disclosure, without implying any limitation on the scope of the present disclosure. The embodiments described herein can be implemented in various ways except for the way described below.

[0022] 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 skill in the art to which this disclosure belongs.

[0023] References in this disclosure to "one embodiment," "an embodiment," "an example embodiment," etc. indicate that the described embodiment may include a particular feature, structure, or characteristic, but not every embodiment necessarily includes the particular feature, structure, or characteristic. Furthermore, such phrases do not necessarily refer to the same embodiment. Furthermore, when a particular feature, structure, or characteristic is described in conjunction with an embodiment, whether or not explicitly described, it is considered within the knowledge of those skilled in the art to affect such feature, structure, or characteristic in conjunction with other embodiments.

[0024] It should be understood that, although the terms "first", "second", etc., preceding nouns, etc., may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another, and they do not limit the order of the nouns. For example, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element without departing from the scope of the exemplary embodiments. As used herein, the term "and / or" includes any and all combinations of one or more of the listed terms.

[0025] As used herein, “at least one of: ” and “at least one of ” and similar expressions, where a list of two or more elements is combined 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 of the elements.

[0026] As used herein, unless explicitly stated, performing a step "in response to A" does not indicate that the step is performed immediately after "A" occurs, and may include one or more intermediate steps.

[0027] The terms used herein are used only for the purpose of describing specific embodiments and are not intended to limit the exemplary embodiments. As used herein, the singular forms "a", "an", and "the" are also intended to include the plural forms unless the context clearly indicates otherwise. It will be further understood that the terms "comprises", "has", "has", "includes", and / or" when used herein specify the presence of stated features, elements, and / or components, etc., but do not exclude the presence or addition of one or more other features, elements, components, and / or combinations thereof.

[0028] As used in this application, the term "circuitry" may refer to one or more or all of the following: (a) hardware circuit implementation only (such as implementation only in analog and / or digital circuits) and (b) a combination of hardware circuitry and software such as (where applicable): (i) a combination of analog and / or digital hardware circuits and software / firmware and (ii) any portion of a hardware processor and software (including a digital signal processor), software and memory that work together to enable a device, such as a mobile phone or server, to perform various functions and (c) Hardware circuits and / or processors, such as a microprocessor or portion of a microprocessor, that require software (e.g., firmware) to operate, but which software may not be present when not needed for operation.

[0029] This definition of circuitry applies to all uses of the 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 only a hardware circuit or processor (or multiple processors) or a 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 a server, cellular network device, or other computing or network device.

[0030] As used herein, the term "communication network" refers to a network that follows any suitable communication standard, such as New Radio (NR), Long Term Evolution (LTE), Advanced LTE (LTE-A), Wideband Code Division Multiple Access (WCDMA), High Speed ​​Packet Access (HSPA), Narrowband Internet of Things (NB-IoT), etc. In addition, the communication between the terminal equipment and the network equipment in the communication network can be performed according to any suitable generation of communication protocols, including but not limited to the first generation (1G), second generation (2G), 2.5G, 2.75G, third generation (3G), fourth generation (4G), 4.5G, fifth generation (5G), sixth generation (6G) communication protocols and / or any other protocols currently known or developed in the future. The embodiments of the present disclosure can be applied to various communication systems. In view of the rapid development of communication, there will certainly be communication technologies and systems that can embody future types of the present disclosure. It should not be considered that the scope of the present disclosure is limited to the aforementioned system.

[0031] As used herein, the term "network device" refers to a node in a communication network, via which a terminal device accesses the network and receives services from it. A network device may refer to a base station (BS) or an access point (AP), for example, a NodeB (NodeB or NB), an evolved NodeB (eNodeB or eNB), a NR NB (also known as a gNB), a remote radio unit (RRU), a radio head (RH), a remote radio head (RRH), a relay, an integrated access and backhaul (IAB) node, a low-power node, such as a femto, a micro, a non-terrestrial network (NTN) or non-terrestrial network equipment, such as satellite network equipment, a low earth orbit (LEO) satellite and a geosynchronous orbit (GEO) satellite, an aircraft network equipment, etc., depending on the terminology and technology applied. In some example embodiments, a radio access network (RAN) split architecture includes a centralized unit (CU) and a distributed unit (DU) at an IAB donor node. An IAB node includes a mobile terminal (IAB-MT) portion, which behaves similarly to a UE to a parent node, and the DU portion of the IAB node behaves similarly to a base station to a next-hop IAB node.

[0032] The term "terminal device" refers to any terminal device capable of wireless communication. As an example and not limitation, the terminal device may also be referred to as a communication device, a 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 is not limited to, a mobile phone, a cellular phone, a smart phone, a voice over IP (VoIP) phone, a wireless local ring phone, a tablet computer, a wearable terminal device, a personal digital assistant (PDA), a portable computer, a desktop computer, an image capture terminal device such as a digital camera, a game terminal device, a music storage and playback device, a vehicle-mounted wireless terminal device, a wireless endpoint, a mobile station, a laptop embedded equipment (LEE), a laptop mounted equipment (LME), a USB dongle, a smart device, a wireless customer premises equipment (CPE), an Internet of Things (IoT) device, a watch or other wearable device, a head mounted display (HMD), a vehicle, a drone, medical equipment and applications (e.g., remote surgery), industrial equipment and applications (e.g., robots and / or other wireless devices operating in industrial and / or automatic processing chain scenarios), consumer electronic devices, equipment operating on commercial and / or industrial wireless networks, etc. The terminal device may also correspond to the mobile terminal (MT) part of an IAB node (eg, a relay node).In the following description, the terms "terminal device", "communication device", "terminal", "user equipment" and "UE" may be used interchangeably.

[0033] As used herein, the terms "resource", "transmission resource", "resource block", "physical resource block" (PRB), "uplink resource" or "downlink resource" may refer to any resource used to perform communication, for example, communication between a terminal device and a network device, such as time domain resources, frequency domain resources, space domain resources, code domain resources, or any other combination of time domain, frequency domain, space domain and / or code domain resources that enable communication. In the following, unless explicitly stated, resources in the frequency domain and time domain will be used as examples of transmission resources for describing some example embodiments of the present disclosure. It should be noted that the example embodiments of the present disclosure are equally applicable to other resources in other domains.

[0034] The term "AI / ML model" as used herein may refer to a data-driven algorithm that applies AI / ML techniques to generate a set of outputs based on a set of inputs. The terms "AI / ML model" and "model" may be used interchangeably. The term "function" as used herein may refer to an AI / ML-enabled feature / FG enabled by a configuration, where the configuration is supported based on conditions indicated by UE capabilities. The term "AI / ML entity" as used herein may refer to an AI / ML model or function.

[0035] The term "UE-side (AI / ML) model" used herein may refer to an AI / ML model that performs inference entirely at the UE. The term "network-side (AI / ML) model" used herein may refer to an AI / ML model that performs inference entirely at the network. The term "one-side (AI / ML) model" used herein may refer to a UE-side (AI / ML) model or a network-side (AI / ML) model. The term "double-sided (AI / ML) model" used herein may refer to a paired AI / ML model on which joint inference is performed, wherein the joint inference includes AI / ML inference that performs inference jointly across the UE and the network, i.e., the first part of the inference is first performed by the UE, and then the remaining part is performed by the gNB, or vice versa.

[0036] The term "activation" as used herein may refer to enabling an AI / ML entity for a particular function. The term "deactivation" as used herein may refer to disabling an AI / ML entity for a particular function. The term "switching" as used herein may refer to deactivating a currently active AI / ML entity and activating a different AI / ML entity for a particular function. The term "model management" as used herein may refer to a more general term including one or more of the following functions / processes: model activation, deactivation, selection, switching, fallback, and update (including retraining).

[0037] As mentioned above, AI / ML technology can be applied in multiple scenarios. For example, the use case set of AI / ML technology can include channel state information (CSI) feedback enhancement, beam management, and positioning accuracy enhancement.

[0038] In some solutions, there is a set of operations for supporting beamforming transmissions, including beam scanning, beam measurement and reporting, beam maintenance and recovery. All of these aspects are detailed in the standards under the broad topic of beam management procedures. Beam management has evolved to support more advanced configurations, such as multi-beam reporting, to enable multiple transmit receive points (TRPs) and multi-panel configurations. However, the fundamental problem with the beam management process is that with the larger number of beams supported by high-dimensional multiple-input multiple-output (MIMO) arrays, the CSI reference signal (RS) measurement and feedback overhead increases dramatically to enable beam selection. In addition, the time required for the gNB and UE to complete beam scanning and establish the best beam increases accordingly. Therefore, support for low-latency communications is limited. This is mainly due to the frequency of synchronization signal blocks (SSBs) / CSI-RS transmissions during processes P1, P2, P3, which are described in 3GPP TR 38.802 and summarized as follows: -P1 provides beam scanning, which is implemented for the gNB to scan the coverage area to periodically transmit SSBs using wide-angle beams. Conversely, the UE scans different SSBs to identify the best beam and corresponding time / frequency resources for requesting access. -During P2, after the gNB establishes the wide beam in P1, it performs beam refinement to send CSI-RS with a narrow beam to identify a more precise direction towards the UE. - During P3, beam refinement is implemented on the UE side to scan the Rx narrow beam set, while The gNB transmits CSI-RS using the best beam identified in P2.

[0039] Processes P1, P2, and P3 are performed sequentially to establish data transmission between the gNB and the UE, and are completely repeated in case of beam failure and recovery. In addition, P2 and P3 are also repeated periodically for beam maintenance.

[0040] Supporting AI / ML based beam management can save overhead and reduce latency. It has been shown that ML algorithms enable prediction of serving beams for different UE locations and time instances, thereby avoiding measuring actual beam quality and saving those resources to be used for data transmission. On the other hand, beam scanning operations like those performed in P1, P2 and P3 are time-inefficient and non-scalable when the size of the antenna array increases. Therefore, the ML algorithm can replace the sequential beam scanning by recommending a reduced set of beams that may include the best beam index of the full scan.

[0041] In addition, for AI / ML function identification and function-based lifecycle management (LCM) of the UE-side model and / or the UE part of the model on both sides, the function-based LCM operates based on at least one configuration of the AI / ML-enabled feature / FG or a specific configuration of the AI / ML-enabled feature / FG. For AI / ML model identification and model ID-based LCM of the UE-side model and / or the UE part of the model on both sides, the model ID-based LCM operates based on the identified model, wherein the model and the function-based LCM can be associated with a specific configuration / condition associated with the UE capabilities of the AI / ML-enabled feature / FG and additional conditions (e.g., scenarios, sites, and data sets) as determined / identified between the UE side and the NW side. It can be seen that the function definition, configuration, and AI / ML function identification and function-based LCM of the UE-side model have been studied. A major aspect is to define the conditions and content on activating / switching / deactivating / falling back the AI / ML function.

[0042] Function-based LCM operations have been identified as one of the potential solutions to identify and study the conditions to enable development of one or more functions for support of ML-enabled features for a given use case. In function identification and function-based LCM, knowing the UE conditions (including parameters / configurations) required at the network as a first step before anything else as this will reveal the contextual conditions when using the ML model for supporting a given ML-enabled feature.

[0043] In a solution, the UE may report the worst case handover / activation delay for all functions, since the UE may not know the exact function configuration from the network, and the UE may report the same delay for all possible functions (configurations), since it may sound like a feasible approach with legal-like UE capability reporting. However, this solution may not reveal the actual delay in handover / activation of functions and may result in large delays when switching between functions.

[0044] In another solution, the UE may still report to the NW via capability reporting different switching / activation delays that may correspond to different functions. However, the UE capability signaling may need to change significantly, as the UE must refer to some "identified function" (configurable function based on the reporting conditions of the UE capabilities) before receiving any functional configuration. With this approach, the UE can define some association of different delay values ​​with the identified functions. This will be a challenging task due to significant changes to the traditional capability signaling framework to support this capability signaling framework. Assuming this can be done, it is still difficult to report the actual delay for function activation / switching, as the delay of switching / activating functions may vary over time.

[0045] Although UE capability reporting is known for reporting switching delays between functions, it has not been studied to identify dynamic switching / activation between multiple functions, where an indication of LCM operation for performance monitoring of multiple functions with different activation / switching delays can be studied. In addition, update reporting of applicable functions (with different applicable conditions, such as activation delay) has not been studied in function-based LCM operations.

[0046] Figure 1 An example communication environment 100 in which an example embodiment of the present disclosure may be implemented is shown. In the communication environment 100, a plurality of communication devices including a first device 110 and a second device 120 may communicate with each other. It should be understood that Figure 1The number of devices and their connections shown in FIG. 1 is for illustrative purposes only and does not imply any limitation. The communication environment 100 may include any suitable number of devices configured to implement the example embodiments of the present disclosure. Although not shown, it should be understood that one or more additional devices may be located in the cell 102 and one or more additional cells may be deployed in the communication environment 100. The first device 110 may support one or more AI / ML entities, such as the AI / ML entity F 1 ,F 2 ,F 3 ,....F N , where N is an integer. The one or more AI / ML entities may include one or more AI / ML models. Alternatively, the one or more AI / ML entities may include one or more functions. The AI / ML entity may be applied to channel state information feedback. Alternatively or additionally, the AI / ML entity may be applied in beam management. In some other example embodiments, the AI / ML entity may be applied to positioning.

[0047] In the following, for the purpose of illustration, some example embodiments are described in which the first device 110 operates as a terminal device and the second device 120 operates as a network device. However, in some example embodiments, the operations described in conjunction with the terminal device may be implemented at a network device or other device, and the operations described in conjunction with the network device may be implemented at a terminal device or other device.

[0048] In some example embodiments, if first device 110 is a terminal device and second device 120 is a network device, a link from second device 120 to first device 110 is referred to as a downlink (DL), and a link from first device 110 to second device 120 is referred to as an uplink (UL). In DL, second device 120 is a transmitting (TX) device (or transmitter), and first device 110 is a receiving (RX) device (or receiver). In UL, first device 110 is a TX device (or transmitter), and second device 120 is an RX device (or receiver).

[0049] The communication in the communication environment 100 can be implemented according to any appropriate communication protocol, including 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), etc., wireless local area network communication protocols such as the Institute of Electrical and Electronics Engineers (IEEE) 802.11, and / or any other protocol currently known or developed in the future. In addition, the communication can utilize any appropriate wireless communication technology, including 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 access (OFDM), discrete Fourier transform spread OFDM (DFT-s-OFDM) and / or any other technology currently known or developed in the future.

[0050] According to some example embodiments of the present disclosure, a solution for function-based performance monitoring is provided. In particular, a solution is proposed to enable function-based performance monitoring by sending updates on configured / identified functions using an applicable conditional framework. In this way, the performance of AI / ML entities can be improved.

[0051] Hereinafter, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. Figure 2 , which shows a signaling flow 200 for reference signal transmission alignment according to some example embodiments of the present disclosure. For the purpose of discussion, reference will be made to Figure 1 The signaling flow 200 is discussed by using the first device 110 and the second device 120, for example.

[0052] The first device 110 transmits (2010) the first information to the second device 120. In other words, the second device 120 receives the first information from the first device 110. The first information may be transmitted using UE capability signaling.

[0053] The first information indicates the AI / ML entities supported by the device (eg, one or more AI / ML entities F 1 ,F 2 ,F 3 ,....FN). In an example embodiment, the first information may include the number of supported AI / ML entities. For example, if the first device 110 supports AI / ML entity F 1 ,F 2 ,F 3 ,....F N , the number of supported AI / ML entities included in the first information may be “N”.

[0054] The first information also includes a delay associated with the AI / ML entity. The delay may include an activation delay of the AI / ML entity. In an example embodiment, the activation delay may be common to all AI / ML entities. For example, if the first device 110 supports the AI / ML entity F 1 ,F 2 ,F 3 , the first information may include the AI / ML entity F 1 ,F 2 ,F 3 In another example, the first information may include an activation delay for each AI / ML entity. For example, if the first device 110 supports the AI / ML entity F 1 ,F 2 ,F 3 , then the first information may include the AI / ML entity F 1 Activation delay of AI / ML entities 2 and activation delay of AI / ML entities F 3 .

[0055] Alternatively or additionally, the delay may include a switching delay between another AI / ML entity and the AI / ML entity. In an example embodiment, the switching delay may be common to all AI / ML entities. For example, if the first device 110 supports the AI / ML entity F 1 ,F 2 ,F 3 , the first information may be included in the AI / ML entity F 1 ,F 2 ,F 3 In another example, the first information may include a switching delay between each two AI / ML entities. As an example, the first information may include a maximum switching delay between each two AI / ML entities. For example, if the first device 110 supports the AI / ML entity F 1 ,F 2 ,F 3 , then the first information may include the AI / ML entity F 1 and F 2 Switching delay between AI / ML entities F 2 and F 3 Switching delay between AI / ML entities F 1 and F 3 Switching delay between .

[0056] Figure 3 FIG. 3 is a schematic diagram showing a function switch 300 according to an exemplary embodiment of the present disclosure. As an example, the first information may include Figure 3The configuration shown in {F 1 ,F 2 ,F 3 ,....F N} associated conditions and the corresponding maximum switching delay (e.g., d max Fij , where F ij Represents the AI / ML entity F i Switch to AI / ML Entity F j ). In an example, the first information may include the supported BM use case AI / ML entities shown in Table 1 {F 1 ,F 2 ,F 3 ,....F N} corresponding maximum switching or activation delay. Note that Table 1 is only an example and not a limitation. Table 1

[0057] In some example embodiments, the AI / ML entity {F 1 ,F 2 ,F 3 ,....F N} can be shown in the following Table 2. Note that Table 2 is only an example and not a limitation. Table 2 Function describe <![CDATA[F 1 ]]> DLTx Beam Prediction F2 Tx-RX beam pair prediction .... ..... <![CDATA[F N ]]> Rx beam prediction

[0058] In some example embodiments, the first information may also include applicable conditions of the AI / ML entity associated with beam management (BM) - Case 1 assumes DL TX beam prediction, which is listed in Table 3 below. Table 3

[0059] In some example embodiments, the first information may also include applicable conditions of the AI / ML entity associated with the BM - Case 2 assumes DL Tx beam prediction, supports Top-K DL Tx beam prediction, which is listed in Table 4 below. Table 4

[0060] The second device 120 may configure (2020) one or more AI / ML entities based on the first information. For example, the second device 120 may configure the AI / ML entity {F1 ,F 2 ,F 3 ,....F N The second device 120 may also obtain a delay from the first information. For example, the second device 120 may determine a switching delay (eg, d max Fij ).

[0061] The second device 120 may send (2030) an instruction to activate another AI / ML entity to the first device 110. In other words, the first device 110 may receive an instruction to activate another AI / ML entity from the second device 120. For example, the second device 120 may instruct the first device 110 to activate the AI / ML entity F via the LCM operation. i The first device 110 may activate (2040) other functions, such as the AI / ML entity F i In some embodiments, contributing factors to activation delay for an AI / ML entity or switching delay between two AI / ML entities may relate to corresponding model inference delay, setting up or downloading the model, pre-processing delays due to measurements, or logical model complexity (e.g., in terms of differences in parameter updates or structure updates) that may affect periodic measurement and reporting.

[0062] The first device 110 may send (2050) to the second device 120 the metric obtained by the first device 110. In other words, the second device 120 may receive the metric from the first device 110. For example, the first device 110 may perform a measurement and send the measurement to the second device 120. For example, the metric may be a measured reference signal received power (L1-RSRP).

[0063] The second device 120 may send (2060) an instruction to activate the AI / ML entity to the first device 110. In other words, the first device 110 may receive an instruction to activate the AI / ML entity from the second device 120. For example, the second device 120 may instruct the first device 110 to activate the AI / ML entity via the LCM operation F j .

[0064] The second device 120 may expect the corresponding delay to be the delay indicated in the first information. For example, the second device 120 may expect the corresponding delay to be the delay indicated in the first information. i To AI / ML entity F j The switching delay is d max Fij .

[0065] The first device 110 determines (2070) a delay for an update associated with the AI / ML entity. The delay for the update may include an activation delay for the update of the AI / ML entity. Alternatively or additionally, the delay for the update may include a switching delay for the update between other AI / ML entities and the AI / ML entity. For example, if the indication is received (2060) from the second device 120, the first device 110 may determine the delay for the update. For example, after reporting the first information to the second device 120, the first device 110 may determine the delay for future reporting instances from the AI / ML entity F. i To AI / ML entity F j F j The first device 110 may activate (2080) the AI / ML entity. For example, the first device 110 may activate (2080) the AI / ML entity F i Switch to AI / ML Entity F j .

[0066] First device 110 sends (2090) second information associated with the updated delay to second device 120. In other words, second device 120 receives second information associated with the updated delay from first device 110. For example, the second information may include an indication of a change in the previously reported (2010) delay. In some example embodiments, the transmission of the second information may be applied based on a reporting mechanism triggered by a UE event. In this way, the actual delay may be reported to the network, thereby improving the performance of the AI / ML entity.

[0067] In an example embodiment, the first device 110 may determine whether there is a change between the delay and the updated delay based on a predefined criterion. For example, the predefined criterion may be predefined or preconfigured at the first device 110. In this case, the first device 110 may send second information associated with the updated delay based on the change.

[0068] In an example embodiment, if the updated activation delay is less than or equal to the first threshold delay, the first device 110 may determine that there is a change between the delay and the updated delay based on a predefined criterion. In this case, the second information may indicate the first threshold or updated activation delay. The first threshold delay may be the activation delay multiplied by the first scaling factor. In an example embodiment, the first scaling factor may be configured by the second device 120. In another example embodiment, if the updated activation delay is greater than the first threshold delay but less than or equal to the activation delay, the first device 110 may determine that there is no change between the delay and the updated delay based on a predefined criterion. In this case, the second information may indicate that there is no change between the delay and the updated delay.

[0069] In yet another example embodiment, if the updated activation delay is greater than the activation delay but less than or equal to a second threshold delay, the first device 110 may determine, based on predefined criteria, that there is a change between the delay and the updated delay. In such a case, the second information may indicate the second threshold delay or the updated activation delay. The second threshold delay may be the activation delay multiplied by a second scaling factor configurable by the second device 120. In another example embodiment, if the updated activation delay is greater than the second threshold delay, the first device 110 determines, based on predefined criteria, that the updated activation delay is out of range. In such a case, the second information may indicate the lack of support of an AI / ML entity.

[0070] In an example embodiment, if the updated handover delay is less than or equal to a third threshold delay, the first device 110 may determine, based on predefined criteria, that there is a change between the delay and the updated delay. In such a case, the second information may indicate the third threshold delay or the updated handover delay. The third threshold delay may be the handover delay multiplied by a third scaling factor. In an example embodiment, the third scaling factor may be configurable by the second device 120. For example, assuming represents the updated delay corresponding to the activation / handover from AI / ML entity F i to AI / ML entity F j and d maxFij represents the reported (2010) delay corresponding to the activation / handover from AI / ML entity F i to AI / ML entity F j and L1 and L2 (0 < L1 (indicating a lower delay) <= 1 and / or 1 < L2 (indicating a higher delay)), then the predefined criteria may include: if then the first device 110 may report the change in d maxFij (a drop to L1). For future reference, the second device 120 and / or the first device 110 may assume that d max Fij = L1 * d max Fij . In such a case, if then it means that the first device 110 is able to activate / handover from AI / ML entity F i to AI / ML entity F j (faster than the L1 portion of the initially configured d max Fij ). This may be due to the previously experienced model corresponding to F i when transitioning from F j during inference to F j .

[0071] In another example embodiment, if the updated switching delay is greater than the third threshold delay but less than or equal to the switching delay, the first device 110 may determine that there is no change between the delay and the updated delay based on the predefined criteria. In this case, the second information may indicate that there is no change between the delay and the updated delay. For example, the predefined criteria may include: The first device 110 may not report d max Fij In the future, the second device 120 and / or the first device 110 may assume that d max Fij =d max Fij In this way, greater flexibility is achieved.

[0072] In another example embodiment, if the updated switching delay is greater than the switching delay but less than or equal to the fourth threshold delay, the first device 110 may determine that there is a change between the delay and the updated delay based on the predefined criteria. In this case, the second information may indicate the fourth threshold delay or the updated switching delay. In an example, the fourth threshold delay may be the switching delay multiplied by a fourth scaling factor that may be configured by the second device 120. For example, the predefined criteria may include: if Then the first device 110 may report d max Fij For the future, the second device 120 and / or the first device 110 may assume that d max Fij =L2*d max Fij In this case, if This means that the first device 110 can be fast enough (higher than d max Fij and is less than the initial configuration d max Fij L2 score) from AI / ML entity F i Switch to AI / ML Entity F j This may be due to the fact that during inference, the AI / ML entity F i Transform to AI / ML Entity F j When the first experience model corresponds to F j .

[0073] In yet another example embodiment, if the updated switching delay is greater than the fourth threshold delay, the first device 110 may determine that the updated switching delay is out of range based on a predefined criterion. In this case, the second information may indicate that there is no support for the AI / ML entity. For example, the second information may indicate that there is no AI / ML entity F j support.

[0074] In some other example embodiments, the second information may also include a measurement result obtained by the first device 110. For example, the second information may include an L1-RSRP measurement. Alternatively or additionally, the second information may also include a confirmation message of activation or switching of the AI / ML entity. For example, the updated delayed reporting may be completed using a confirmation message.

[0075] The second device 120 may configure (2095) a delay for updating based on the second information. For example, the second device 120 may configure (2095) a delay for updating based on the second information. i To AI / ML entity F j Future Switch Example Updates (instead of d max Fij In an example embodiment, if the second information indicates an updated activation delay, the second device 120 may delay activation of the at least one AI / ML entity (eg, by d max Fij ) changes to an updated activation delay (e.g., ). In another example embodiment, if the second information indicates an updated switching delay, the second device 120 may change the switching delay of at least one AI / ML entity to the updated switching delay. In yet another example embodiment, if the second information indicates a first threshold delay, the second device 120 may change the activation delay of at least one AI / ML entity to the first threshold delay. In another example embodiment, if the second information indicates a second threshold delay, the second device 120 may change the activation delay of at least one AI / ML entity to the second threshold delay. If the second information indicates a third threshold delay, the second device 120 may change the activation delay of at least one AI / ML entity to the third threshold delay. In some other example embodiments, if the second information indicates a fourth threshold delay, the second device 120 may change the switching delay of at least one AI / ML entity to the fourth threshold delay.

[0076] Figure 4 FIG. 4 is a flowchart of an example method 400 implemented at a first device according to some example embodiments of the present disclosure. For discussion purposes, Figure 1 The method 400 is described from the perspective of the first device 110.

[0077] At block 410, the apparatus sends first information to a network device, the first information indicating at least one artificial intelligence and machine learning (AI / ML) entity supported by the apparatus and a delay associated with the at least one AI / ML entity. The delay includes at least one of: an activation delay of the at least one AI / ML entity, or a switching delay between another AI / ML entity and the at least one AI / ML entity.

[0078] At block 420, the device determines an updated delay associated with the at least one AI / ML entity. The updated delay includes at least one of: an updated activation delay of the at least one AI / ML entity, or an updated switching delay between other AI / ML entities and the at least one AI / ML entity.

[0079] At block 430 , the apparatus sends second information associated with the updated delay to the network device.

[0080] In some example embodiments, method 400 further includes: determining a delay in updating associated with at least one AI / ML entity based on determining that an indication to activate or switch to the at least one AI / ML entity is received from a network device; and switching to the at least one AI / ML entity from other AI / ML entities.

[0081] In some example embodiments, method 400 further includes: determining whether there is a change between the delay and the updated delay based on a predefined criterion; and based on the change, sending second information associated with the updated delay to the network device.

[0082] In some example embodiments, method 400 further includes: determining, based on a predefined criterion, that a change exists between the delay and the updated delay in accordance with determining that the updated activation delay is less than or equal to a first threshold delay, wherein the first threshold delay is the activation delay multiplied by a first scaling factor; and sending second information to the network device, the second information indicating the first threshold delay or the updated activation delay.

[0083] In some example embodiments, method 400 further includes: determining, based on a predefined criterion, that there is no change between the delay and the updated delay in response to determining that the updated activation delay is greater than a first threshold delay but less than or equal to the activation delay, wherein the first threshold delay is the activation delay multiplied by a first scaling factor; and sending second information to the network device, the second information indicating that there is no change between the delay and the updated delay.

[0084] In some example embodiments, method 400 further includes: determining that a change exists between the delay and the updated delay based on a predefined criterion in accordance with determining that the updated activation delay is greater than the activation delay but less than or equal to a second threshold delay, wherein the second threshold delay is the activation delay multiplied by a second scaling factor; and sending second information to the network device, the second information indicating the second threshold delay or the updated activation delay.

[0085] In some example embodiments, method 400 further includes: determining that activation of the update is out of range based on a predefined criterion in accordance with determining that activation delay of the update is greater than a second threshold delay, wherein the second threshold delay is the activation delay multiplied by a second scaling factor; and sending second information to the network device, the second information indicating a lack of support for at least one AI / ML entity.

[0086] In some example embodiments, method 400 further includes: determining, based on a predefined criterion, that a change exists between the delay and the updated delay in accordance with determining that the updated switching delay is less than or equal to a third threshold delay, wherein the third threshold delay is the switching delay multiplied by a third scaling factor; and sending second information to the network device, the second information indicating the third threshold delay or the updated switching delay.

[0087] In some example embodiments, method 400 further includes: determining, based on a predefined criterion, that there is no change between the delay and the updated delay, in accordance with determining that the updated switching delay is greater than a third threshold delay but less than or equal to the switching delay, wherein the third threshold delay is the activation delay multiplied by a scaling factor of three; and sending second information to the network device, the second information indicating that there is no change between the delay and the updated delay.

[0088] In some example embodiments, method 400 further includes: determining, based on a predefined criterion, that a change exists between the delay and the updated delay in accordance with determining that the updated switching delay is greater than the switching delay but less than or equal to a fourth threshold delay, wherein the fourth threshold delay is the switching delay multiplied by a fourth scaling factor; and sending second information to the network device, the second information indicating the fourth threshold delay or the updated switching delay.

[0089] In some example embodiments, method 400 further includes: determining, based on a predefined criterion, that the updated switching delay is out of range in accordance with determining that the updated switching delay is greater than a fourth threshold delay, wherein the fourth threshold delay is the switching delay multiplied by a fourth scaling factor; and sending second information to the network device, the second information indicating a lack of support for at least one AI / ML entity.

[0090] In some example embodiments, the second information further includes measurement results obtained by the device.

[0091] In some example embodiments, at least one AI / ML entity is related to one of: channel state information feedback of the device, beam management of the device, or positioning of the device.

[0092] Figure 5 FIG. 5 is a flowchart of an example method 500 implemented at a second device according to some example embodiments of the present disclosure. For discussion purposes, Figure 1 The method 500 is described from the perspective of the second device 120.

[0093] At block 510, the apparatus receives first information from a terminal device, the first information indicating a condition associated with configuring at least one AI / ML entity and a delay associated with the at least one AI / ML entity. The delay includes at least one of: an activation delay of the at least one AI / ML entity, or a switching delay between another AI / ML entity and the at least one AI / ML entity.

[0094] At block 520, the apparatus receives second information associated with an updated delay from the terminal device, the updated delay associated with the at least one AI / ML entity. The updated delay includes at least one of: an updated activation delay of the at least one AI / ML entity, or an updated switching delay between other AI / ML entities and the at least one AI / ML entity.

[0095] In some example embodiments, the method 500 further includes: changing the activation delay of the at least one AI / ML entity to the updated activation delay based on determining that the second information indicates an updated activation delay.

[0096] In some example embodiments, the method 500 further includes: changing the switching delay of the at least one AI / ML entity to the updated switching delay in response to determining that the second information indicates an updated switching delay.

[0097] In some example embodiments, method 500 further includes: based on determining that the second information indicates a first threshold delay, the first threshold delay being the activation delay multiplied by the first scaling factor, changing the activation delay of the at least one AI / ML entity to the first threshold delay.

[0098] In some example embodiments, method 500 further includes: based on determining that the second information indicates a second threshold delay, the second threshold delay is the activation delay multiplied by the second scaling factor, changing the activation delay of the at least one AI / ML entity to the second threshold delay.

[0099] In some example embodiments, the method 500 further includes: based on determining that the second information indicates a third threshold delay, the third threshold delay being the switching delay multiplied by a third scaling factor, changing the switching delay of the at least one AI / ML entity to the third threshold delay.

[0100] In some example embodiments, the method 500 further includes: based on determining that the second information indicates a fourth threshold delay, the fourth threshold delay being the switching delay multiplied by a fourth scaling factor, changing the switching delay of the at least one AI / ML entity to the fourth threshold delay.

[0101] In some example embodiments, the second information indicates an absence of support of the at least one AI / ML entity.

[0102] In some example embodiments, the second information further comprises metrics acquired by the terminal device / ML entity.

[0103] In some example embodiments, at least one AI / ML entity is related to one of: channel state information feedback of a terminal device, beam management of a terminal device, or positioning of a terminal device.

[0104] In some example embodiments, any of the methods 400 can be performed (e.g., Figure 1 The first device of the first device 110 in the embodiment may include a device for performing the corresponding operation of the method 400. The device may be implemented in any suitable form. For example, the device may be implemented in a circuit or a software module. The first device may be implemented as or included in Figure 1 In the first device 110.

[0105] In some example embodiments, a first apparatus includes components for sending first information indicating at least one artificial intelligence and machine learning (AI / ML) entity supported by the apparatus and a delay associated with the at least one AI / ML entity to a network device, wherein the delay comprises at least one of: an activation delay of the at least one AI / ML entity, or a switching delay between another AI / ML entity and the at least one AI / ML entity; components for determining an updated delay associated with the at least one AI / ML entity, wherein the updated delay comprises at least one of: an updated activation delay of the at least one AI / ML entity, or an updated switching delay between another AI / ML entity and the at least one AI / ML entity; and components for sending second information associated with the updated delay to the network device.

[0106] In some example embodiments, the first apparatus further comprises: a component for determining a delay in updating associated with at least one AI / ML entity based on determining that an indication to activate or switch to the at least one AI / ML entity is received from a network device; and a component for switching from other AI / ML entities to the at least one AI / ML entity.

[0107] In some example embodiments, the first apparatus further comprises: means for determining whether there is a change between the delay and the updated delay based on a predefined criterion; and means for sending second information associated with the updated delay to the network device based on the change.

[0108] In some example embodiments, the first apparatus further comprises: a component for determining, based on a predefined criterion, that a change exists between the delay and the updated delay in accordance with determining that the updated activation delay is less than or equal to a first threshold delay, wherein the first threshold delay is the activation delay multiplied by a first scaling factor; and a component for sending second information to the network device, the second information indicating the first threshold delay or the updated activation delay.

[0109] In some example embodiments, the first apparatus further comprises: means for determining, based on a predefined criterion, that there is no change between the delay and the updated delay in response to determining that the updated activation delay is greater than a first threshold delay but less than or equal to the activation delay, wherein the first threshold delay is the activation delay multiplied by a first scaling factor; and means for sending second information to the network device, the second information indicating that there is no change between the delay and the updated delay.

[0110] In some example embodiments, the first apparatus further comprises: means for determining, based on a predefined criterion, that a change exists between the delay and the updated delay in accordance with determining that the updated activation delay is greater than the activation delay but less than or equal to a second threshold delay, wherein the second threshold delay is the activation delay multiplied by a second scaling factor; and means for sending second information to the network device, the second information indicating the second threshold delay or the updated activation delay.

[0111] In some example embodiments, the first apparatus further comprises: means for determining that an activation delay for an update is out of range based on a predefined criterion in accordance with determining that the activation delay for the update is greater than a second threshold delay, wherein the second threshold delay is the activation delay multiplied by a second scaling factor; and means for sending second information to the network device, the second information indicating a lack of support for at least one AI / ML entity.

[0112] In some example embodiments, the first apparatus further comprises: a component for determining, based on a predefined criterion, that a change exists between the delay and the updated delay in accordance with determining that the updated switching delay is less than or equal to a third threshold delay, wherein the third threshold delay is the switching delay multiplied by a third scaling factor; and a component for sending second information to the network device, the second information indicating the third threshold delay or the updated switching delay.

[0113] In some example embodiments, the first apparatus further comprises: a component for determining, based on a predefined criterion, that there is no change between the delay and the updated delay in response to determining that the updated switching delay is greater than a third threshold delay but less than or equal to the switching delay, wherein the third threshold delay is the activation delay multiplied by a third scaling factor; and a component for sending second information to the network device, the second information indicating that there is no change between the delay and the updated delay.

[0114] In some example embodiments, the first apparatus further comprises: a component for determining, based on a predefined criterion, that a change exists between the delay and the updated delay in accordance with determining that the updated switching delay is greater than the switching delay but less than or equal to a fourth threshold delay, wherein the fourth threshold delay is the switching delay multiplied by a fourth scaling factor; and a component for sending second information to the network device, the second information indicating the fourth threshold delay or the updated switching delay.

[0115] In some example embodiments, the first apparatus further comprises: means for determining that the updated switching delay is out of range based on a predefined criterion in accordance with determining that the updated switching delay is greater than a fourth threshold delay, wherein the fourth threshold delay is the switching delay multiplied by a fourth scaling factor; and means for sending second information to the network device, the second information indicating a lack of support for at least one AI / ML entity.

[0116] In some example embodiments, the second information further includes measurement results obtained by the device.

[0117] In some example embodiments, at least one AI / ML entity is related to one of: channel state information feedback of the device, beam management of the device, or positioning of the device.

[0118] In some example embodiments, the apparatus comprises a terminal device.

[0119] In some example embodiments, the first apparatus further comprises means for performing the method 400 or other operations in some example embodiments of the first device 110. In some example embodiments, the apparatus comprises: at least one processor; and at least one memory storing instructions that, when executed by the at least one processor, cause the execution of the first apparatus.

[0120] In some example embodiments, any of the methods 500 can be performed (e.g., Figure 1 The second device of the second device 120 in the embodiment may include components for performing the corresponding operations of the method 500. The device may be implemented in any suitable form. For example, the device may be implemented in a circuit or a software module. The second device may be implemented as or included in Figure 1 In the second device 120 in.

[0121] In some example embodiments, the second apparatus includes a component for receiving first information from a terminal device, the first information indicating a condition associated with configuring at least one AI / ML entity and a delay associated with the at least one AI / ML entity, wherein the delay is at least one of: an activation delay of the at least one AI / ML entity, or a switching delay between another AI / ML entity to the at least one AI / ML entity; and a component for receiving second information associated with an updated delay from the terminal device, the updated delay being associated with the at least one AI / ML entity, wherein the updated delay includes at least one of: an updated activation delay of the at least one AI / ML entity, or an updated switching delay between the other AI / ML entity and the at least one AI / ML entity.

[0122] In some example embodiments, the second apparatus further comprises means for changing the activation delay of the at least one AI / ML entity to the updated activation delay based on determining that the second information indicates the updated activation delay.

[0123] In some example embodiments, the second apparatus further comprises means for changing the handover delay of the at least one AI / ML entity to the updated handover delay in accordance with determining that the second information indicates an updated handover delay.

[0124] In some example embodiments, the second device further comprises: a component for converting an activation delay of at least one AI / ML entity to the first threshold delay based on determining that the second information indicates a first threshold delay, the first threshold delay being an activation delay multiplied by a first scaling factor.

[0125] In some example embodiments, the second device further comprises: a component for changing the activation delay of at least one AI / ML entity to the second threshold delay based on determining that the second information indicates a second threshold delay, the second threshold delay being the activation delay multiplied by a second scaling factor.

[0126] In some example embodiments, the second device further comprises: a component for converting a switching delay of at least one AI / ML entity to the third threshold delay based on determining that the second information indicates a third threshold delay, the third threshold delay being the switching delay multiplied by a third scaling factor.

[0127] In some example embodiments, the second device further comprises: a component for converting a switching delay of at least one AI / ML entity to the fourth threshold delay based on determining that the second information indicates a fourth threshold delay, the fourth threshold delay being the switching delay multiplied by a fourth scaling factor.

[0128] In some example embodiments, the second information indicates that an activation delay of the update is out of range, or wherein the second information indicates an absence of support by the at least one AI / ML entity.

[0129] In some example embodiments, the second information further comprises metrics acquired by the terminal device / ML entity.

[0130] In some exemplary embodiments, at least one AI / ML entity is related to one of: channel state information feedback of a terminal device, beam management of a terminal device, or positioning of a terminal device.

[0131] In some example embodiments, the apparatus comprises a network device.

[0132] In some example embodiments, the second apparatus further comprises means for performing some example embodiments of the method 500 or other operations in the second device 120. In some example embodiments, the apparatus comprises: at least one processor; and at least one memory storing instructions which, when executed by the at least one processor, cause the execution of the second apparatus.

[0133] Figure 6 is a simplified block diagram of a device 600 suitable for implementing an example embodiment of the present disclosure. The device 600 may be provided to implement a communication device, such as Figure 1 The first device 110 or the second device 120 is shown. As shown in the figure, the device 600 includes one or more processors 610, one or more memories 620 coupled to the processor 610, and one or more communication modules 640 coupled to the processor 610.

[0134] The communication module 640 is used for two-way communication. The communication module 640 has one or more communication interfaces to facilitate communication with one or more other modules or devices. The communication interface may represent any interface required to communicate with other network elements. In some example embodiments, the communication module 640 may include at least one antenna.

[0135] As non-limiting examples, processor 610 may be of any type suitable for a local technology network, and may include one or more of: a general purpose computer, a special purpose computer, a microprocessor, a digital signal processor (DSP), and a processor based on a multi-core processor architecture. Device 600 may have multiple processors, such as application specific integrated circuit chips, which are time-slaved to a clock synchronized with a main processor.

[0136] The memory 620 may include one or more non-volatile memories and one or more volatile memories. Examples of non-volatile memories include, but are not limited to, read-only memory (ROM) 624, electrically programmable read-only memory (EPROM), flash memory, hard disk, compact disk (CD), digital video disk (DVD), optical disk, laser disk, and other magnetic storage and / or optical storage. Examples of volatile memories include, but are not limited to, random access memory (RAM) 622 and other volatile memories that do not continue to operate for the duration of a power outage.

[0137] The computer program 630 includes computer executable instructions executed by the associated processor 610. The instructions of the program 630 may include instructions for performing the operations / actions of some example embodiments of the present disclosure. The program 630 may be stored in a memory, such as ROM 624. The processor 610 may perform any suitable operations and processes by loading the program 630 into the RAM 622.

[0138] The exemplary embodiments of the present disclosure may be implemented by a program 630 so that the device 600 may execute a program according to the present disclosure. Figures 2 to 5 Any process of the present disclosure discussed. The exemplary embodiments of the present disclosure may also be implemented by hardware or by a combination of software and hardware.

[0139] In some example embodiments, the program 630 may be tangibly embodied in a computer-readable medium that may be included in the device 600 (such as in the memory 620) or in other storage devices accessible by the device 600. The device 600 may load the program 630 from the computer-readable medium into the RAM 622 for execution. In some example embodiments, the computer-readable medium may include any type of non-transitory storage medium, such as ROM, EPROM, flash memory, hard disk, CD, DVD, etc. The term "non-transitory" as used herein is a limitation on the medium itself (i.e., tangible, not a signal), not a limitation on the persistence of data storage (e.g., RAM vs. ROM).

[0140] Figure 7 An example of a computer readable medium 700 is shown, which may be in the form of a CD, DVD, or other optical storage disk. Computer readable medium 700 has program 630 stored thereon.

[0141] In general, various embodiments of the present disclosure may be implemented in hardware or dedicated 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 the embodiments of the present disclosure are illustrated and described in block diagrams, flow charts, or using some other graphical representations, it should be understood that, as non-limiting examples, the boxes, devices, systems, techniques, or methods described herein may be implemented in hardware, software, firmware, dedicated circuits or logic, general hardware or controllers or other computing devices, or some combination thereof.

[0142] Some example embodiments of the present disclosure also provide at least one computer program product that is tangibly stored on a computer-readable medium, such as a non-transitory computer-readable medium. The computer program product includes computer-executable instructions, such as instructions contained in program modules, which are executed in a device on a target physical or virtual processor to perform any of the above methods. In general, program modules include routines, programs, libraries, objects, classes, components, data structures, etc. that perform specific tasks or implement specific abstract data types. In various embodiments, the functions of program modules can be combined or split between program modules as needed. Machine executable instructions for program modules can be executed in local or distributed devices. In distributed devices, program modules can be located in local and remote storage media at the same time.

[0143] The program code for executing the method 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, a special-purpose computer, or other programmable data processing device, so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code may be executed entirely on the machine, partially on the machine as a stand-alone software package, partially on the machine, partially on a remote machine, or entirely on a remote machine or server.

[0144] In the context of the present disclosure, computer program codes or related data may be carried by any suitable carrier to enable a device, apparatus or processor to perform the above-mentioned various processes and operations. Examples of carriers include signals, computer-readable media, etc.

[0145] The computer readable medium may be a computer readable signal medium or a computer readable storage medium. The computer readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or apparatuses, or any suitable combination of the above mediums. More specific examples of computer readable storage media would include an electronic connection with one or more wires, a portable computer floppy disk, 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above devices.

[0146] In addition, although operations are described in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in a sequential order, or that all illustrated operations be performed to achieve the desired result. In some cases, multitasking and parallel processing may be advantageous. Similarly, although several specific implementation details are included in the above discussion, these details should not be understood as limitations on the scope of the present disclosure, but rather as descriptions of features that may be unique to a particular embodiment. Unless expressly stated, certain features described in the context of separate embodiments may also be implemented in combination in a single embodiment. Conversely, unless expressly stated, various features described in the context of a single embodiment may also be implemented separately in multiple embodiments or in any suitable sub-combination.

[0147] Although the present disclosure has been described in language specific to structural features and / or methodological acts, it should be understood that the present disclosure defined in the appended claims is not necessarily limited to the specific features or acts described above. Instead, the specific features and acts described above are disclosed as example forms of implementing the claims.

Claims

1. A device comprising: at least one processor; as well as at least one memory storing instructions that, when executed by the at least one processor, cause the apparatus to: sending, to a network device, the first information indicating at least one artificial intelligence and machine learning (AI / ML) entity supported by the apparatus and a delay associated with the at least one AI / ML entity, wherein the delay comprises at least one of: an activation delay of the at least one AI / ML entity, or a switching delay between another AI / ML entity and the at least one AI / ML entity; determining an updated delay associated with the at least one AI / ML entity, wherein the updated delay comprises at least one of: an updated activation delay for the at least one AI / ML entity, or an updated switching delay between the another AI / ML entity and the at least one AI / ML entity; and Second information associated with the updated delay is sent to the network device.

2. The device according to claim 1, wherein the device: determining a delay of the update associated with the at least one AI / ML entity based on determining that an indication to activate or switch to the at least one AI / ML entity is received from the network device; and Switch from the other AI / ML entity to the at least one AI / ML entity.

3. The device according to claim 1, wherein the device: determining, based on predefined criteria, whether there is a change between the delay and the updated delay; and Based on the change, the second information associated with the updated delay is sent to the network device.

4. The device according to claim 3, wherein the device: determining, based on the predefined criteria, that the change exists between the delay and the updated delay in accordance with determining that the updated activation delay is less than or equal to a first threshold delay, wherein the first threshold delay is the activation delay multiplied by a first scaling factor; and The second information is sent to the network device, the second information indicating the first threshold delay or the updated activation delay.

5. The device according to claim 3, wherein the device: in response to determining that the updated activation delay is greater than a first threshold delay but less than or equal to the activation delay, determining, based on the predefined criteria, that there is no change between the delay and the updated delay, wherein the first threshold delay is the activation delay multiplied by a first scaling factor; and The second information is sent to the network device, the second information indicating no change between the delay and the updated delay.

6. The device according to claim 3, wherein the device: determining, based on the predefined criteria, that the change exists between the delay and the updated delay in accordance with determining that the updated activation delay is greater than the activation delay but less than or equal to a second threshold delay, wherein the second threshold delay is the activation delay multiplied by a second scaling factor; and The second information is sent to the network device, the second information indicating the second threshold delay or the updated activation delay.

7. The device according to claim 3, wherein the device: determining that the updated activation delay is out of range based on the predefined criteria in response to determining that the updated activation delay is greater than a second threshold delay, wherein the second threshold delay is the activation delay multiplied by a second scaling factor; and The second information is sent to the network device, the second information indicating the absence of support of the at least one AI / ML entity.

8. The device according to claim 3, wherein the device: determining, based on the predefined criteria, that the change exists between the delay and the updated delay in accordance with determining that the updated switching delay is less than or equal to a third threshold delay, wherein the third threshold delay is the switching delay multiplied by a third scaling factor; and Second information is sent to the network device, the second information indicating the third threshold delay or the updated switching delay.

9. The device according to claim 3, wherein the device: In response to determining that the updated handover delay is greater than a third threshold delay but less than or equal to the handover delay, determining, based on the predefined criteria, that there is no change between the delay and the updated delay, wherein the third threshold delay is the handover delay multiplied by a third scaling factor; and The second information is sent to the network device, the second information indicating that there is no change between the delay and the updated delay.

10. The device according to claim 3, wherein the device: determining, based on the predefined criteria, that the change exists between the delay and the updated delay in response to determining that the updated handover delay is greater than the handover delay but less than or equal to a fourth threshold delay, wherein the fourth threshold delay is the handover delay multiplied by a fourth scaling factor; and The second information is sent to a network device, the second information indicating the fourth threshold delay or the updated switching delay.

Images