Capability information transmission

Abstract

The embodiment of the invention relates to a method, equipment and device for capacity information transmission and a computer readable storage medium. In one method, a first device receives a capability query from a second device, the capability query including a machine learning ML capability having one or more application conditions and an indication requesting the first device to indicate support for at least one activation condition for the application conditions. The first device transmits capability information to the second device, the capability information including an application condition and at least one activation condition for the application condition. The at least one activation condition indicates whether the corresponding application condition is currently supported.

Description

Technical Field

[0001] Various example embodiments of the present disclosure relate generally to the field of telecommunications, and in particular, to methods, devices, apparatuses, and computer-readable storage media for capability information transmission. Background Art

[0002] In certain communication systems, such as next cellular systems, artificial intelligence (AI) and / or machine learning (ML) techniques are proposed to improve communication performance. AI / ML models can be applied in the new radio (NR) radio interface to assist model functions or communication-related functions, such as channel state information (CSI) overhead reduction, beam management (BM), positioning, etc. For example, AI / ML-based beam management targets spatial and / or temporal beam prediction to reduce overhead and latency. AI / ML-based functions (e.g., air interface functions) need to enhance / expand the air interface with features that can improve support for AI / ML-based algorithms to enhance performance and / or reduce complexity / overhead, where the enhanced performance depends on the use case considered and can be, for example, improved throughput, robustness, accuracy or reliability, etc. Summary of the invention

[0003] In a first aspect of the present disclosure, a first device is provided. The first device includes at least one processor; and at least one memory storing instructions. The instructions, when executed by the at least one processor, cause the first device to at least: receive a capability query from a second device, the capability query including a machine learning (ML) capability with one or more applicable conditions and an indication requesting the first device to indicate support for at least one activation condition for the applicable condition; and transmit capability information to the second device, the capability information including the applicable condition and at least one activation condition for the applicable condition, the at least one activation condition indicating whether the corresponding applicable condition is currently supported.

[0004] In a second aspect of the present disclosure, a second device is provided. The second device includes: at least one processor; and at least one memory storing instructions. When the instructions are executed by the at least one processor, the second device at least: transmits a capability query to the first device, the capability query includes a machine learning (ML) capability with one or more applicable conditions and an indication requesting the first device to indicate support for at least one activation condition for the applicable condition; and receives capability information from the first device, the capability information includes an applicable condition and at least one activation condition for the applicable condition, and the at least one activation condition indicates whether the corresponding applicable condition is currently supported.

[0005] In a third aspect of the present disclosure, a method is provided. The method includes: receiving a capability query at a first device from a second device, the capability query including a machine learning (ML) capability having one or more applicable conditions and an indication requesting the first device to indicate support for at least one activation condition for the applicable condition; and transmitting capability information to the second device, the capability information including the applicable condition and at least one activation condition for the applicable condition, the at least one activation condition indicating whether the corresponding applicable condition is currently supported.

[0006] In a fourth aspect of the present disclosure, a method is provided. The method includes: at a second device, transmitting a capability query to a first device, the capability query including a machine learning (ML) capability having one or more applicable conditions and requesting the first device to indicate an indication of support for at least one activation condition for the applicable condition; and receiving capability information from the first device, the capability information including the applicable condition and at least one activation condition for the applicable condition, the at least one activation condition indicating whether the corresponding applicable condition is currently supported.

[0007] In a fifth aspect of the present disclosure, a first device is provided. The first device includes: a component for receiving a capability query from a second device, the capability query including a machine learning (ML) capability having one or more applicable conditions and an indication requesting the first device to indicate support of at least one activation condition for the applicable condition; and a component for transmitting capability information to the second device, the capability information including the applicable condition and at least one activation condition for the applicable condition, the at least one activation condition indicating whether the corresponding applicable condition is currently supported.

[0008] In a sixth aspect of the present disclosure, a second device is provided. The second device includes: a device for transmitting a capability query to a first device, the capability query including a machine learning (ML) capability having one or more applicable conditions and an indication requesting the first device to indicate support for at least one activation condition for the applicable condition; and a component for receiving capability information from the first device, the capability information including the applicable condition and at least one activation condition for the applicable condition, the at least one activation condition indicating whether the corresponding applicable condition is currently supported.

[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 or fourth aspect.

[0010] It should be understood that the invention summary is not intended to identify the key features 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 invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0012] Figures 1A to 1C shows example communication environments in which example embodiments of the present disclosure may be respectively implemented;

[0013] Figure 2 An example configuration for AI / ML-based beam management is shown;

[0014] Figure 3 shows a signaling flow for capability information transmission according to some example embodiments of the present disclosure;

[0015] Figure 4A and Figure 4B respectively show example signaling flows between a first device and a second device according to some example embodiments of the present disclosure;

[0016] Figure 5 An example diagram showing features supporting ML according to some example embodiments of the present disclosure;

[0017] Figure 6 shows an example mapping of a logical to physical model based on applicable conditions according to some example embodiments of the present disclosure;

[0018] Figure 7 A flowchart showing a method implemented at a first device according to some example embodiments of the present disclosure is shown;

[0019] Figure 8 A flowchart showing a method implemented at a second device according to some example embodiments of the present disclosure is shown;

[0020] Fig. 9 shows a simplified block diagram of a device suitable for implementing an example embodiment of the present disclosure; and

[0021] Fig.10 A block diagram of an example computer-readable medium is shown according to some example embodiments of the present disclosure.

[0022] Throughout the drawings, the same or similar reference numerals refer to the same or similar elements. Specific embodiments

[0023] The principle of the present invention will now be described with reference to some exemplary embodiments. It should 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 implying any limitation to the scope of the present disclosure. In addition to the embodiments described below, the embodiments described herein can be implemented in various ways.

[0024] 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.

[0025] 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, these phrases do not necessarily refer to the same embodiment. Furthermore, when a particular feature, structure, or characteristic is described in conjunction with an embodiment, it is within the knowledge of those skilled in the art to affect such feature, structure, or characteristic in other embodiments, whether or not explicitly described.

[0026] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another element. For example, without departing from the scope of the exemplary embodiment, the first element may be referred to as the second element, and similarly, the second element may be referred to as the first element. As used herein, the term "and / or" includes any and all combinations of one or more of the listed terms.

[0027] As used herein, “at least one of: ,” “at least one of ,” and similar descriptions, a list of two or more elements connected by “and” or “or,” means at least any one element, or at least any two or more elements, or at least all the elements.

[0028] As used herein, unless explicitly stated, performing a step “in response to A” does not mean performing the step immediately after “A” occurs, and may include one or more intermediate steps.

[0029] The terms used herein are used only for the purpose of describing specific embodiments and are not intended to limit the example 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 should also be understood that when used herein, the terms "comprise", "comprising", "having", "having", "includes", and / or "including", when used herein, specify the presence of the described 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.

[0030] As used in this application, the term "circuitry" may refer to one or more or all of the following: (a) implemented only in hardware circuits (e.g. implemented 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 (such as firmware) to operate, but the software may not be present when not required for operation.

[0031] 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 only a hardware circuit or a processor (or multiple processors) or a portion of a hardware circuit or a processor and its (or its) accompanying software and / or firmware. For example and if applicable to the particular claim element, the term circuitry also covers 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.

[0032] As used herein, the term "communication network" refers to a network that complies with any suitable communication standard, for example, 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 device and the network device in the communication network can be performed according to any suitable generation communication protocol, 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 protocol and / or any other protocol 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 are of course future types of communication technologies and systems that can implement the present disclosure. It should not be considered that the scope of the present disclosure is limited to the above-mentioned system.

[0033] As used herein, the term "network device" refers to a node in a communication network via which a terminal device accesses a network and receives services from it. A network device may refer to a base station (BS) or an access point (AP), such as a NodeB (NodeB or NB), an evolved NodeB (eNodeB or eNB), an NRNB (also known as a gNB), a remote radio unit (RRU), a radio head (RH), a remote radio head (RRH), a repeater, an integrated access and backhaul (IAB) node, a low power node (e.g., a femto), a micro-network, 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 user equipment (UE) to a parent node, and a distributed unit (DU) portion of the IAB node behaves similarly to a base station to a next-hop IAB node.

[0034] 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 loop 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 device (LEE), a laptop mounted device (LME), a USB dongle, a smart device, a wireless customer premises equipment (CPE), an Internet of Things (IoT) device, a watch or other wearable, a head mounted display (HMD), a vehicle, a drone, a medical device and an application (e.g., remote surgery), an industrial device and an application (e.g., a robot and / or other wireless devices operating in an industrial and / or automatic processing chain environment), a consumer electronic device, a device operating on a commercial and / or industrial wireless network, 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.

[0035] 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 (e.g., communication between a terminal device and a network device), such as a resource in the time domain, a resource in the frequency domain, a resource in the spatial domain, a resource in the code domain, or any other combination of time, frequency, space and / or code domain resources to achieve communication. In the following, unless explicitly stated, resources in the frequency domain and the 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 also applicable to other resources in other domains.

[0036] As used herein, the term "model" refers to the association between input and output learned from training data, so that after training, a corresponding output can be generated for a given input. The generation of the model can be based on machine learning (ML) technology. ML technology can also be referred to as artificial intelligence (AI) technology. Typically, an ML model can be established that receives input information and makes predictions based on the input information. As used herein, a model is equivalent to an AI / ML model or an ML model, or a data-driven / data processing algorithm / program.

[0037] As used herein, the term “data collection” refers to the process by which a network node, a management entity, or a UE collects data for the purpose of AI / ML model training, data analysis, and inference.

[0038] As used herein, the term “AI / ML model” refers to a data-driven algorithm that applies AI / ML techniques to produce a set of outputs based on a set of inputs.

[0039] As used herein, the term “AI / ML model training” refers to the process of training an AI / ML model by learning input / output relationships in a data-driven manner and obtaining the trained AI / ML model for reasoning.

[0040] As used herein, the term “AI / ML model inference” refers to the process of using a trained AI / ML model to produce a set of outputs based on a set of inputs.

[0041] As used herein, the term “AI / ML model validation” refers to a subprocess of training to evaluate the quality of an AI / ML model using a dataset different from the one used for model training, facilitating the selection of model parameters that are generalizable beyond the dataset used for model training.

[0042] As used herein, the term "AI / ML model testing" refers to a sub-process of training to evaluate the performance of the final AI / ML model using a dataset different from the one used for model training and validation. Unlike AI / ML model validation, testing does not assume subsequent adjustments to the model.

[0043] As used herein, the term “UE-side (AI / ML) model” refers to an AI / ML model whose reasoning is performed entirely at the UE.

[0044] As used herein, the term “network-side (AI / ML) model” refers to an AI / ML model whose reasoning is performed entirely at the network.

[0045] As used herein, the term “one-sided (AI / ML) model” is referred to as a UE-side (AI / ML) model or a network-side (AI / ML) model.

[0046] As used herein, the term "two-sided (AI / ML) model" refers to a paired AI / ML model by which joint reasoning is performed, wherein the joint reasoning includes AI / ML reasoning, which is performed jointly on the UE and the network, i.e., the first part of the reasoning is first performed by the UE and then the remaining part is performed by the gNB, or vice versa.

[0047] As used herein, the term "AI / ML model transfer" refers to the delivery of an AI / ML model over an air interface, either with parameters of a model structure known at the receiving end or a new model with parameters. The delivery may include a complete model or a partial model.

[0048] As used herein, the term "model download" refers to the transfer of a model from a network to a UE.

[0049] As used herein, the term "model upload" refers to the transmission of a model from a UE to a network.

[0050] As used herein, the term "federated learning / federated training" refers to a machine learning technique that trains AI / ML models across multiple distributed edge nodes (e.g., UE, gNB), where each node performs local model training using local data samples. This technique requires multiple interactions of the model, but does not exchange local data samples.

[0051] As used herein, the term “offline field data” refers to data collected from the field and used for offline training of AI / ML models.

[0052] As used herein, the term “online field data” refers to data collected from the field and used for online training of AI / ML models.

[0053] As used herein, the term “model monitoring” refers to the process of monitoring the inference performance of an AI / ML model.

[0054] As used herein, the term “supervised learning” refers to the process of training a model based on inputs and their corresponding labels.

[0055] As used herein, the term “unsupervised learning” refers to the process of training a model without labeled data.

[0056] As used herein, the term “semi-supervised learning” refers to the process of training a model using a mixture of labeled and unlabeled data.

[0057] As used herein, the term “reinforcement learning (RL)” refers to the process of training an AI / ML model based on the inputs (also called states) and feedback signals (also called rewards) generated from the model’s outputs in the environment with which the model interacts.

[0058] As used herein, the term “model activation” refers to launching an AI / ML model for a specific function.

[0059] As used herein, the term “model deactivation” refers to deactivating an AI / ML model for a specific functionality.

[0060] As used herein, the term “model switching” refers to deactivating a currently activated AI / ML model and activating a different AI / ML model for a specific function.

[0061] As described above, AI / ML models can be applied in the NR radio interface to assist model functions or communication-related functions, such as channel state information (CSI) feedback overhead reduction, improved accuracy, prediction or beam management, enhanced positioning, etc. For example, AI / ML-based beam management targets spatial and / or temporal beam prediction to reduce overhead and latency, and / or improve beam selection accuracy. AI / ML-based functions need to be improved.

[0062] In some mechanisms, for the UE-side model and / or the UE part of the bilateral model, it is recommended to define and study the applicability conditions (sets) for the functions / models. The applicability conditions can be used to enable the development of scenario / configuration / site specific models and, if necessary, report the applicability of these models to the network. Whether and how to define performance targets for the functions / models (possibly as part of the applicability conditions) needs to be considered. Whether and how the UE reports the applicability conditions (sets) for supported functions (and, if necessary, for supported models) and / or supported function sets needs to be considered.

[0063] In some mechanisms, the general aspects of AI / ML frameworks consider the problem of signaling dynamic capabilities in addition to static capabilities. However, they only consider the context but lack any method to solve this problem.

[0064] In some mechanisms, mechanisms / signaling to dynamically handle UE capabilities for AI / ML-enabled features (e.g., in the presence of handover) are proposed. For example, terms such as dynamic UE capability reporting can be found.

[0065] Among some mechanisms, for lifecycle management (LCM), a possibility is proposed that the network is allowed to configure AI / ML models that are not available on the UE side with possible signaling indications of model transfer / delivery pending and model transfer / delivery completed.

[0066] In some mechanisms, the network (e.g., Next Generation (NG)-Radio Access Network (RAN)) is allowed to configure AI / ML models that are not available at the UE.

[0067] In some mechanisms, if the network is allowed to configure a supported model at the UE but it is not available for immediate use at the UE, the following signaling may be supported: model transfer / delivery pending indication (if the configured model is not available at the UE), and / or model transfer / delivery complete indication (when the configured model is ready for use at the UE).

[0068] In some mechanism, for those use cases, the benefits need to be evaluated (using developed methodologies and defined key performance indicators (KPIs)), and the potential impact on the specifications, including physical (PHY) layer aspects, protocol aspects, needs to be evaluated.

[0069] AIML requires the UE to support one or more logical ML models to support a given use case that needs to be considered (e.g., CSI compression, beam prediction, positioning).

[0070] Each logical ML model may also be implemented by the UE using one or more physical ML models with different architectures and implementation options.

[0071] A UE vendor may consider UE capabilities represented by a logical ML model, but may not have a physical ML model for a given capability combination, e.g., whether the physical ML model can be downloaded only when a feature is needed to be configured. This means that UE capabilities are statically represented by a logical ML model, but may change dynamically due to the presence or absence of an associated physical model.

[0072] When the UE downloads the ML model, it may acquire new capabilities and it shall indicate this to the network to allow the network to configure the newly acquired capabilities.

[0073] Typically, RAN2 has been doing this by either using some kind of assistance information or a new capability exchange triggered from the non-access stratum (NAS) layer. At this point, the network can trigger a new configuration, i.e. the principle is that the radio resource control (RRC) configuration follows the capability transfer and not the other way around.

[0074] Typically, when RAT capabilities are affected, the UE will perform a detach and reattach, such as a mandatory capability exchange procedure. The main issue is that the transfer / delivery model to the UE results in a change in its capabilities. Therefore, it is necessary to determine a mechanism that does not allow abuse / overload of the capability exchange procedure (or UAI or other things). Abuse / overload means that the signaling procedure will cause significant control plane signaling overhead on the network, because each capability query procedure may require the UE to detach and attach to the network, which requires performing a registration procedure every time, which is very inefficient because it involves dozens of signaling messages.

[0075] In order to solve at least part of the above problems or other potential problems, a solution for capability information transmission is proposed. According to an example embodiment, a second device (e.g., a network device) transmits a capability query to a first device (e.g., a terminal device), the capability query including an ML capability with one or more applicable conditions and an indication requesting the first device to indicate support for at least one activation condition for the applicable conditions. In response to receiving the capability query, the first device transmits capability information to the second device, the capability information including the applicable conditions and at least one activation condition for the applicable conditions. The at least one activation condition indicates whether the corresponding applicable condition is currently supported.

[0076] In this way, the second device can be notified of the applicable condition and the activation condition for the applicable condition. As a result, the second device can control the update of the ML capability (e.g., of the ML model). Therefore, the performance of the ML capability can be enhanced.

[0077] The following will refer to Figures 1A to 10 The principles and embodiments of the present disclosure are described in detail.

[0078] Figure 1A An example communication environment 100 is shown in which example embodiments of the present disclosure may be implemented. In the communication environment 100, a plurality of communication devices, including a first apparatus 110 and a second apparatus 120, may communicate with each other.

[0079] exist Figure 1A In the example of FIG. 1 , the second device 120 has a certain coverage area, which can be referred to as a service area or cell 102. The first device 110 is located in the cell covered by the second device 120. In the communication environment 100, the second device 120 can transmit data and control information to the first device 110, and the first device 110 can also transmit data and control information to the second device 120.

[0080] In some example embodiments, model functionality, such as AI / ML-based functionality, may be provided to first device 110. The functionality may be provided by one or more AI / ML models, such as model 130. Model 130 may be implemented at first device 110, or at second device 120, or at both first device 110 and second device 120.

[0081] Model 130 may be a logical model that supports functionality for a given use case (e.g., CSI compression, beam prediction, positioning). As used herein, the term "logical model" may refer to the association between inputs and outputs learned from training data, so that corresponding outputs can be generated for given inputs after training. The generation of the model may be based on ML techniques. ML techniques may also be referred to as AI techniques. Typically, an ML model may be established that receives input information and makes predictions based on the input information. As used herein, a model is equivalent to an AI / ML model or an ML model, or a data-driven / data processing algorithm / program.

[0082] The logical model may be implemented by the first device 110 and / or the second device 120 using one or more physical ML models with different architectures and implementation options. As used herein, the term "physical model" may refer to a physical element or unit that implements the operation or data processing of the logical model. Hereinafter, unless explicitly stated otherwise, the term "model" may be referred to as a logical model.

[0083] It should be understood that although Figure 1A A single model 130 is shown in FIG. 1 , but there may be a plurality of models implemented by the first device 110 and / or the second device 120 to implement the model functionality.

[0084] It should be understood that Figure 1A The number of devices and their connections shown in FIG. 1 are for illustration purposes only and do not imply any limitation. Communication environment 100 may include any suitable number of devices configured to implement example embodiments of the present disclosure.

[0085] In the following, for the purpose of explanation, some example embodiments are described as the first device 110 operating as a terminal device and the second device 120 operating 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.

[0086] In some example embodiments, if the first device 110 is a terminal device and the second device 120 is a network device, the model 130 implemented at the first device 110 may be referred to as a UE-side model, the model 130 implemented at the second device 120 may be referred to as a network (NW) side model, and the model 130 implemented at both sides may be referred to as a dual-sided model.

[0087] In some example embodiments, if the first device 110 is a terminal device and the second device 120 is a network device, the link from the second device 120 to the first device 110 is referred to as a downlink (DL), and the link from the first device 110 to the second device 120 is referred to as an uplink (UL). In the DL, the second device 120 is a transmission (TX) device (or transmitter), and the first device 110 is a reception (RX) device (or receiver). In the UL, the first device 110 is a TX device (or transmitter), and the second device 120 is an RX device (or receiver).

[0088] The communication in the communication environment 100 may be implemented according to any suitable communication protocol, including but not limited to cellular communication protocols of the first generation (1G), second generation (2G), third generation (3G), fourth generation (4G), fifth generation (5G), sixth generation (6G), etc., wireless local area network communication protocols such as Institute of Electrical and Electronics Engineers (IEEE) 802.11, etc., and / or any other protocol currently known or developed in the future. In addition, the communication may use any suitable 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.

[0089] As briefly mentioned, the model 130 may provide different model functions. Figure 1B An example communication environment 140 is shown in which example embodiments of the present disclosure may be implemented. Figure 1B In the example, model functionality may include AI / ML-based beam management (BM).

[0090] like Figure 1B As shown, the second device 120 transmits downlink transmissions to the first device 110 via one or more beams 152-1, 152-2, 152-3, ..., and 152-N (N is an integer greater than or equal to 1). For purposes of discussion, beams 152-1, 152-2, 152-3, ..., and 152-N are collectively or individually referred to as beams 152.

[0091] Accordingly, in the uplink, the first device 110 transmits uplink transmissions to the second device 120 via beams 162-1, 162-2, ..., and 162-M (M is an integer greater than or equal to 1). For purposes of discussion, beams 162-1, 162-2, ..., and 162-M are collectively or individually referred to as beams 162.

[0092] In the communication environment 140, the model 130 implemented at the first device 110 and / or the second device 120 can perform AI / ML-based beam management (BM), such as spatial beam prediction (also referred to as BM-use case 1). Spatial beam prediction is used to predict one or more optimal Tx beams or Tx-Rx beam pairs or corresponding reference signal received power (RSRP) values ​​in different spatial locations. For example, the spatial beam prediction can be a DL Tx beam prediction that can be considered as a P1 / P2 joint optimization, or a DL Tx-Rx beam pair prediction that can be considered as a P1 / P2 / P3 joint optimization.

[0093] Figure 1C An example communication environment 170 is shown in which example embodiments of the present disclosure may be implemented. Figure 1C In an example, the model 130 implemented at the first device 110 and / or the second device 120 can perform AI / ML-based beam management (BM), such as time-domain beam prediction (also referred to as BM-use case 2). The time-domain beam prediction aims to predict the best Tx beam or Tx-Rx beam pair for the next moment, for example, beam prediction in the spatial domain for the next moment (BM-use case 1). For example, the time-domain beam prediction can be a DL Tx beam prediction that can be considered as a P1 / P2 joint optimization, or a DL Tx-Rx beam pair prediction that can be considered as a P1 / P2 / P3 joint optimization.

[0094] As shown, the first device 110 may move from a first position at time T to a second position at time T+K. The model 130 may predict the best Tx beam or Tx-Rx beam pair for the next time T+K based on measurements at time T or any other time before time T+K.

[0095] Compared with the conventional beam management process (e.g., P1, P2, or P3), the conventional beam management process requires a time-consuming operation of configuring the first device to scan all Tx and Rx beams with a large number of synchronization signal blocks (SSB) / channel state information (CSI)-reference signal (RS) measurements. Figure 1B and Figure 1CThe AI / ML-assisted beam management shown can achieve overhead savings and latency reduction. For example, key performance indicators (KPIs) related to beam prediction accuracy (e.g., prediction accuracy or RSRP difference) can be improved. In addition, system performance-related KPIs, including throughput, control signal overhead, and power consumption of the first device 110, can be enhanced.

[0096] It should be understood that in some example embodiments, the model 130 may perform Figure 1B The spatial beam prediction and Figure 1C The time domain beam prediction is shown in .

[0097] In some example embodiments, for different model functions, different configurations may be configured for the model 130. For example, the model 130 may be configured to receive different data or information inputs. Figure 2 An example configuration 200 for AI / ML based beam management is shown.

[0098] In some example embodiments, the model 130 may perform training or run inference to predict beam set A or the top K of beam set A, or the RSRP of set A or the RSRP of the top K of set A. Beam set A may be referred to as a candidate beam set. The top K of beam set A may be a subset of beam set A. At least one predicted beam, at least one predicted first beam, and / or at least one predicted second beam may be the predicted set A or a subset of set A.

[0099] The measurement results of beam set B can be used to predict beam set A. That is, set B beam RSRP measurements can be input to model 130. In an example, set B can be different from set A. For example, set B represents a wide beam set, and set A represents a narrow beam set. Figure 2 As shown, model input 210 corresponds to set B beam RSRP measurements, which corresponds to a set B that is different from set A.

[0100] In another example, beam set B may be a subset of set A, such as a subset of narrow beams. Figure 2 As shown, model input 220 corresponds to set B beam RSRP measurements, which corresponds to a subset of set A. In another example, beam set B may be the same as beam set A (not shown).

[0101] In some example embodiments, auxiliary information may be further input into the model 130, including but not limited to beam shape information, a beam identifier (ID), and the like.

[0102] In the example of beam management, the output 230 of the model may include the best narrow beam ID or the best narrow beam RSRP. In addition, the quality of service (QoS) value of the beam selection may be determined by the model 130.

[0103] Model 130 may be pre-trained or trained. For example, model 130 may be trained using model training data from an offline 5G system-level simulator.

[0104] Already referenced Figures 1A-1C Several example embodiments of AI / ML-based functions are described. For the purpose of illustration, some example embodiments will be described below using beam prediction as a model function. It should be understood that the model function may also be any other suitable function, including but not limited to CSI prediction, positioning prediction, etc. The scope of the present disclosure is not limited in this respect.

[0105] In some example embodiments, model 130 may be a logical model configured to implement model functionality. In some example embodiments, the applicability conditions of the supported functionality / (multiple) functionality for a given sub-use case (ML-enabled feature) need to be identified. As used herein, the term "applicability condition" or "condition" may refer to a condition that determines whether the corresponding functionality is applied. This means that UE capabilities are statically represented by the logical ML model, but may change dynamically due to the absence or presence of an associated physical model. This difference is noteworthy because the logical model capabilities may be quite advanced (e.g., as agreed upon during standardization discussions), such as supporting many combinations of different parameters representing the capabilities of the underlying AIML use case, but in reality, due to practical / implementation limitations, the physical model may only implement a subset of the logical model capabilities. In addition, support for this subset will change / update dynamically over time.

[0106] As briefly mentioned, a solution for capability information transmission is proposed. According to an example embodiment, a second device (e.g., a network device) transmits a capability query to a first device (e.g., a terminal device), the capability query including an ML capability with one or more applicable conditions and an indication requesting the first device to indicate support for at least one activation condition for the applicable conditions. In response to receiving the capability query, the first device transmits capability information to the second device, the capability information including the applicable conditions and at least one activation condition for the applicable conditions. The at least one activation condition indicates whether the corresponding applicable condition is currently supported.

[0107] In this way, the second device can be notified of the applicable condition and the activation condition for the applicable condition. Thus, the second device can control the update of the ML capability of the ML model. Therefore, the performance of the ML capability can be enhanced.

[0108] Figure 3FIG. 3 shows a signaling process 300 for capability information transmission according to some example embodiments of the present disclosure. The signaling process 300 involves Figure 1A For the purpose of illustration, reference will be made to the first device 110 and the second device 120. Figure 1A The signaling flow 300 is described.

[0109] Although in Figure 3 A single first device 110 and a single second device 120 are shown in FIG. 1 , but it should be understood that there may be multiple devices that perform similar operations as described below with respect to the first device 110 or the second device 120 .

[0110] It is noted that the example embodiments of the present disclosure may be applied to any suitable scenario or use case, such as beam management, positioning accuracy enhancement or CSI. For illustrative purposes only, the example embodiments of the present disclosure are described with reference to the scenario or use case of beam management.

[0111] In operation, the second device 120 transmits (304) a capability query to the first device 110. The capability query includes an ML capability with one or more applicable conditions and an indication of at least one activation condition requesting the first device 110 to indicate support for the applicable conditions. For example, the capability query may be a request including an ML capability with a dynamic applicable condition. The first device 110 receives (308) the capability query.

[0112] As used herein, the term "activation condition" may refer to a condition for activating a corresponding applicable condition. For example, if the activation condition of the applicable condition is met, the applicable condition may be activated or enabled. Otherwise, the applicable condition may be deactivated or disabled. Such examples are whether the underlying capability depends on discontinuous reception (DRX) parameters, or whether the UE's mobile speed exceeds a speed (e.g., 30kmph), or whether a given number of component carriers are enabled (across different frequency bands), etc.

[0113] In response to receiving (308) the capability query, the first device 110 transmits (312) capability information to the second device 120. The capability information includes an applicable condition and at least one activation condition for the applicable condition. The at least one activation condition indicates whether the corresponding applicable condition is currently supported. The second device 120 receives (316) the capability information. For example, the first device 110 can transmit (312) the capability information for each applicable condition combination together with at least one activation condition for the applicable condition and additional information on whether the applicable conditions are currently supported or not supported.

[0114] In some example embodiments, the transmission (304) / reception (308) of capability queries and the transmission (312) / reception (316) of capability information may be via any suitable signaling. Figure 4AAn example signaling flow 400 between a first device 110 and a second device 120 is shown. As shown, the second device 120 may transmit 410 a UECapabilityEnquiry to the first device 110. The first device 110 receives 420 the UECapabilityEnquiry. The capability query is included in the UECapabilityEnquiry.

[0115] In response to receiving (420) UECapabilityEnquiry, the first device 110 may transmit (430) UECapabilityInformation to the second device 120. The second device 120 may receive (440) UECapabilityInformation. UECapabilityInformation includes capability information.

[0116] Such static signaling between the first device 110 and the second device 120 may allow the network to query the UE for each radio access technology (RAT) capability. Furthermore, the request may include filters for adjusting the size of the capability container. Filtering allows reducing the number of frequency bands, frequency band combinations, component carrier specific attributes.

[0117] Typically, such transmission / reception of capability information may be performed once when the first device 110 obtains an International Mobile Subscriber Identity (IMSI) to attach to the network, as this process is heavy on the air interface capacity.

[0118] Now return to reference Figure 3 In some example embodiments, the first device 110 is in a connected mode (eg, RRC_CONNECTED). The second device 120 may acquire capabilities of the first device 110 in the RRC_CONNECTED mode (here the context is for ML-specific capabilities).

[0119] Figure 4BAnother example signaling flow 450 between the first device 110 and the second device 120 in RRC_CONNECTED mode is shown. For example, RRCReconfiguration can be transmitted / received between the first device 110 and the second device 120. The first device 110 can transmit (460) UEAssistanceInformation to the second device 120. The second device 120 can receive (470) UEAssistanceInformation. UEAssistanceInformation may include further information about capability information. By using semi-static UEAssistanceInformation signaling, it allows the network to configure the first device 110 to report temporary changes in static capabilities. For example, temporary changes may be due to overheating, multi-universal user identity module (MUSIM) operation, dual connection restrictions (e.g., power limitations, etc.). A gap may be required. It allows the first device 110 to indicate the need for a gap in the RRC reconfiguration completion.

[0120] Still refer to Figure 3 In some example embodiments, different applicability conditions may be configured for different supported functions for various use cases (or sub-use cases). As used herein, a use case or sub-use case may be referred to as an ML-enabled feature or FG. The applicability conditions of the functions / functions supported by a given sub-use case (ML-enabled feature) may be identified. In function identification and function-based LCM, as a first step before any other steps, the second device 120 needs to know the conditions (including parameters / configurations) of the first device 110, as this may reveal the background conditions when using the ML model to support a given ML-enabled feature. These applicability conditions may depend on different sub-use cases.

[0121] In some example embodiments, at least a set of common applicability conditions may be derived across all sub-use cases under discussion (ie, the definition of parameters is common, but parameter values ​​may differ by function or feature).

[0122] Figure 5 An example diagram 500 showing features supporting ML according to some example embodiments of the present disclosure is shown. For example, box 510 shows a function identified based on the configuration of condition #1. For another example, box 520 shows a function identified based on the configuration of condition #2. For another example, box 530 shows a function identified based on the configuration of condition #3.

[0123] Figure 5 The potential uses of the applicable conditions are shown in . Each function can be identified by a subset of applicable conditions, which does not prevent individual applicable conditions from being reused in different sets and / or different functions.

[0124] Several example applicable conditions for different use cases are described in Tables 1 to 3 below. Table 1 shows example applicable conditions for BM-use case 1. Table 2 shows example applicable conditions for CSI compression. Table 3 shows example applicable conditions for positioning case 1, such as direct AI / ML positioning based on channel impulse response (CIR) (AI / ML_direct_DL_CIR_UE side). Table 1 Applicable conditions for BM-Use Case 1 Table 2: Applicable conditions for CSI compression Table 3: Applicable conditions for positioning situation 1

[0125] In some example embodiments, the logical ML model may serve specific ML-enabled use cases (e.g., CSI compression, beam management, positioning, channel prediction / mapping, etc.). The logical ML model may support a set of applicable conditions (or capabilities) such as those shown in Tables 1-3. In some example embodiments, the applicable conditions may be combined into different combinations. For example, the applicable conditions are numbered #1 to #4, i.e., a total of 4 combinations as shown in Table 4. Table 4

[0126] Several example applicable conditions and applicable condition combinations have been described with respect to Tables 1-4. Return to Reference Figure 3 , the first device 110 may transmit capability information for each applicable condition combination together with at least one activation condition for the applicable conditions and additional information on whether the applicable conditions are currently supported or not supported (312).

[0127] In some example embodiments, the physical ML model supports one or more applicability conditions and represents a binary / executable that supports the ML functionality of a given logical ML model. It may occur that the physical ML model cannot be generalized, often due to practical implementation reasons, such as the use of a specific deep neural network (DNN) structure, such as a convolutional neural network (CNN), a long short-term memory (LSTM), or a residual network (ResNet). For example, the physical ML model may not support all applicability conditions related to the logical ML model, or it may be limited in performance to a given applicability condition in a given scenario (e.g., cells bound to a specific deployment, such as frequency range 1 (FR1) or FR2, or for beam prediction, using different beam codebooks, resulting in different relationships between set A and set B for two different cells). This may result in the physical model having the ability to support a given applicability condition.

[0128] In some example embodiments, the applicable conditions may be associated with different physical ML models. For example, it may not have a physical ML model to support all combinations. For another example, the capabilities of the physical ML model may be affected in a given deployment condition (e.g., cell or location).

[0129] Taking Table 1 as an example, the first group of applicable conditions is supported, which includes the measured DLRS (SSB), the measured DL RS set dimension (4, 8), the measured DL RS set mode (e.g., a fixed, pre-configured list), the predicted DL RS set dimension (16), support for the measurement of the predicted DLRS set (full set A), the measurement period (100ms), the maximum number of supported functions (1, 2) and the delay of activating the function (2ms). The second group of applicable conditions is also supported, which includes the measured DL RS (CSI-RS), the measured DL RS set dimension (12), the predicted DL RS set dimension (32), support for the measurement of the predicted DLRS set (partial set A), the maximum number of supported functions (4) and the delay of activating the function (4ms).

[0130] However, the third set of applicable conditions, which includes the measured DL RS (SSB and CSI-RS), the measured DL RS set dimension (16), the measured DL RS set pattern (random), the predicted DL RS set dimension (64), the measurement period (200ms), and the maximum number of supported functions (8), requires downloading the physical ML model to obtain these capabilities. Therefore, activation conditions can be configured for the third set of applicable conditions. Since the third set of applicable conditions is associated with the same physical ML model, the third set of applicable conditions can be considered as a combination of applicable conditions or as a single applicable condition.

[0131] Figure 6600 is shown as an example mapping 600 based on conditions from a logical model to a physical model according to some example embodiments of the present disclosure. As shown, multiple applicable conditions 610, 620, 630, and 640 can be configured for physical model A 650, physical model B 660, and physical model C 670. It should be understood that Figure 6 The applicable conditions shown may be a single applicable condition or a combination of applicable conditions. The scope of the present invention is not limited thereto.

[0132] Physical model A 650 may support applicable condition 610. If physical model A 650 satisfies condition X, it may also support applicable condition 620. Condition X may be referred to as an activation condition for applicable condition 610. As an example, condition X may be that discontinuous reception (DRX) is not configured.

[0133] Likewise, if condition Y is satisfied, physical model B 660 may support the applicable condition 620. Condition Y is an activation condition for the applicable condition. For example, condition X may be that the speed of the first device 110 is less than 30 kmph.

[0134] Physical model B 660 may support applicable condition 630 without any activation condition for applicable condition 630. Physical model C 670 may support applicable condition 640 without any activation condition for applicable condition 640.

[0135] Mapping 600 can also be illustrated by Table 5 below. Table 5 Physical Model Applicable conditions combination A #1 and #2 (Condition X) B #2 (Condition Y) and #3 C #4

[0136] It should be understood that Figure 6 The mapping 600 and the example activation conditions described in Table 5 are for illustration purposes only and do not imply any limitation. Based on the capability information received (316) from the first device 110, the mapping 600 can be determined.

[0137] Return to reference Figure 3 In some example embodiments, the capability information may be updated. The updating of the capability information may be triggered by the second device 120.

[0138] In some example embodiments, the second device 120 may determine (320) an indication indicating which applicable condition the second device 120 is interested in monitoring for changes. The indication may also be referred to as a notification.

[0139] The second device 120 may transmit (324) the indication to the first device 110. The first device 110 may receive (328) the indication. The indication may be included in an uplink trigger or message. As an example, the indication may be transmitted (324) / received (328) via a medium access control (MAC) or RRC message or any other suitable signaling.

[0140] In this way, the second device 120 configures the first device 110 with notifications about which applicable conditions the network is interested in monitoring changes. For example, condition X and condition Y may be set, or when the first device 110 is able to meet applicable condition #4.

[0141] The signaling shown between the first device 110 and the second device 120 can dynamically adapt the applicable conditions based on network control. In this way, when the first device 110 gains or loses the ability to support the listed applicable conditions, the second device 120 can set a notification-based approach instead of requiring the first device 110 to detach / attach. Therefore, dynamic applicable conditions can be retrieved and notifications can be configured for further updates.

[0142] In some example embodiments, the ML update may be received (332) by the first device 110 via an over-the-top service (OTT), i.e., from an external server (i.e., gNB) that is transparent to the radio access network, to add / update the physical ML model to the UE, thereby affecting the UE capabilities. If one of the at least one activation condition is met, the first device 110 may transmit (336) a message to the second device 120 to indicate the satisfied activation condition. The second device 120 may receive (340) the message.

[0143] In some example embodiments, second device 120 may transmit (344) a query for a subset of applicable conditions to first device 110. First device 110 may receive (348) the query. For example, if condition X is met, for example, first device 110 may format a message to indicate this to second device 120. If second device 120 is only interested in a subset of updates, second device 120 may decide to filter the number of requests. For example, second device 120 may choose to activate functionality corresponding to a subset of updates, so it may intelligently avoid receiving all updates from first device 110, thereby saving signaling capacity on the air interface.

[0144] In some example embodiments, the first device 110 may transmit (352) information about the subset of applicable conditions to the second device 120. The second device 120 may receive (356) the information. The second device 120 may also store (360) the received (356) information.

[0145] That is, the first device 110 can provide updated applicable conditions, and the second device 120 can store them for further use and use them to potentially configure features related to the newly updated applicable conditions. If the first device 110 obtains an ML model that enables the suspended applicable conditions, the suspended applicable conditions can be unsuspended through signaling between the first device 110 and the second device 120.

[0146] Alternatively or in addition, in some example embodiments, regardless of whether operations 320 to 360 are performed, the first device 110 may be provided with a conditional reconfiguration of the underlying applicable condition for pausing. For example, the second device 120 may transmit (364) a conditional reconfiguration message to the first device 110. The conditional reconfiguration message includes an activation condition configured for one of the applicable conditions. The first device 110 receives (368) the conditional reconfiguration message. For example, Figure 4B As shown, the conditional reconfiguration message may be included in the RRC reconfiguration message.

[0147] The second device 120 may decide to provide a conditional reconfiguration message with an activation condition to the first device 110, for example, if condition X is met (e.g., DRX is activated), then start using the function configured in the RRC reconfiguration message. The second device 120 may further provide a monitoring configuration as part of the conditional reconfiguration message to ensure that the first device 110 verifies the function before putting it into use.

[0148] In some example embodiments, first device 110 may transmit (372) a confirmation indication, for example, to second device 120, indicating that first device 110 confirms the reconfigured activation condition. Second device 120 may receive (376) the confirmation indication. The confirmation indication may be referred to as an acknowledgment (ACK). As an example, the confirmation indication may be included in an RRC reconfiguration complete message.

[0149] The first device 110 may determine (380) whether at least one activation condition is satisfied. If the first device 110 determines (380) that a first activation condition among the at least one activation condition is satisfied, the first device 110 may perform (384) a conditional reconfiguration for the first activation condition. Similarly, the first device 110 may determine (380) whether each activation condition is satisfied. If a particular activation condition is satisfied, the first device 110 may perform (384) a conditional reconfiguration for the particular activation condition. That is, if the activation condition is satisfied, the first device 110 executes (384) a conditional reconfiguration message.

[0150] In some example embodiments, first device 110 may transmit (388) information to second device 120 regarding an update to the first activation condition and one or more updated applicable conditions corresponding to the first activation condition. Second device 120 may receive (392) the information. As an example, the information may be included in an RRC reconfiguration complete message. Second device 120 may store (396) the information.

[0151] That is, the first device 110 may provide updated applicable conditions. The second device 120 may store them for further use and use them to potentially reconfigure features related to the newly updated applicable conditions.

[0152] Through the signaling flow 300, the network sees the ML functionality from a logical perspective. The configured events allow the network to smoothly take into account the affected applicable conditions. It also allows the network to be in full control even when physical models are added / modified / removed in the UE. The network is able to take into account the entire radio capabilities, including model updates. By using this notification-based approach, rather than triggering a reattachment based on the entire radio capabilities, abuse of the capability exchange process can therefore be reduced.

[0153] Furthermore, capabilities are suddenly gained / lost / updated in a very dynamic manner in sync with the network. That is, network providers can avoid unexpected situations where configured functionality fails or is affected without notice.

[0154] Also, the UE does not have to detach / reattach. This is important not only for 5G+ advanced features but also for the 6G standard where AI / ML features are no longer low-hanging fruit but many features in the UE will be ML-assisted and we need better mechanisms to handle ML capability exchange.

[0155] In this way, the air interface can be enhanced with features that can support AI / ML-based algorithms to enhance performance and / or reduce complexity / overhead. By enhancing the air interface with features, support for AI / ML-based algorithms can be improved to enhance performance and / or reduce complexity / overhead. Enhanced performance may include, but is not limited to, improved throughput, robustness, accuracy, or reliability, etc.

[0156] It should be noted that the example functions or use cases are for illustrative purposes only, and other use cases and applications may also be addressed. In some example embodiments, sufficient use cases may be considered to enable identification of common AI / ML frameworks, including functional requirements of AI / ML architectures, which may be used in subsequent projects. Areas where AI / ML can improve the performance of air interface functions may also be identified.

[0157] Figure 7A flowchart of an example method 700 implemented at a first device according to some example embodiments of the present disclosure is shown. For the purpose of discussion, Figure 1A The method 700 is described from the perspective of the first device 110.

[0158] At block 710 , the first device 110 receives a capability query from a second device, the capability query including a machine learning (ML) capability having one or more applicable conditions and an indication requesting the first device to indicate support for at least one activation condition for the applicable conditions.

[0159] At box 720, the first device 110 transmits capability information to the second device, the capability information including the applicable conditions and at least one activation condition for the applicable conditions, the at least one activation condition indicating whether the corresponding applicable conditions are currently supported.

[0160] In some example embodiments, the method 700 further comprises: receiving an indication from the second device, the indication indicating which applicable condition the second device is interested in monitoring for changes.

[0161] In some example embodiments, the indication is included in an uplink trigger or message.

[0162] In some example embodiments, the method 700 further includes: based on determining that one of the at least one activation condition is satisfied, transmitting a message to the second apparatus to indicate the satisfied activation condition.

[0163] In some example embodiments, the method 700 further includes: receiving a query for the subset of applicable conditions from the second device; and transmitting information about the subset of applicable conditions to the second device.

[0164] In some example embodiments, the method 700 further includes: receiving a condition reconfiguration message from the second device, the condition reconfiguration message including an activation condition reconfigured for one of the applicable conditions.

[0165] In some example embodiments, the method 700 further comprises transmitting a confirmation indication to indicate that the first device confirms the reconfigured activation condition.

[0166] In some example embodiments, the method 700 further includes: performing conditional reconfiguration for the first activation condition in accordance with determining that a first activation condition among the at least one activation condition is satisfied.

[0167] In some example embodiments, the method 700 further includes transmitting information to the second device, the information including an update of the first activation condition and one or more updated applicable conditions corresponding to the first activation condition.

[0168] In some example embodiments, the first apparatus comprises a terminal device and the second apparatus comprises a network device.

[0169] Figure 8 A flowchart of an example method 800 implemented at a second device according to some example embodiments of the present disclosure is shown. For the purpose of discussion, Figure 1A The method 800 is described from the perspective of the second device 120 in FIG.

[0170] At block 810 , the second device 120 transmits a capability query to the first device, the capability query including a machine learning (ML) capability having one or more applicable conditions and an indication requesting the first device to indicate support for at least one activation condition for the applicable conditions.

[0171] In block 820 , the second device 120 receives capability information from the first device, the capability information including an applicability condition and at least one activation condition for the applicability condition, the at least one activation condition indicating whether the corresponding applicability condition is currently supported.

[0172] In some example embodiments, the method 800 further comprises transmitting to the first apparatus an indication indicating which applicable condition the second apparatus is interested in monitoring for changes.

[0173] In some example embodiments, the indication is included in an uplink trigger or message.

[0174] In some example embodiments, the method 800 further comprises: receiving a message from the first device indicating which activation condition is satisfied.

[0175] In some example embodiments, the method 800 further comprises: transmitting a query for the subset of applicable conditions to the first device; and receiving information about the subset of applicable conditions from the first device.

[0176] In some example embodiments, method 800 further comprises storing a subset of applicable conditions.

[0177] In some example embodiments, the method 800 further includes transmitting a condition reconfiguration message to the first apparatus, the condition reconfiguration message including an activation condition reconfigured for one of the applicable conditions.

[0178] In some example embodiments, the method 800 further comprises: receiving a confirmation indication from the first device to indicate that the first device confirms the reconfigured activation condition.

[0179] In some example embodiments, the method 800 further comprises: receiving information from the first device regarding an update of the first activation condition and one or more updated applicable conditions corresponding to the first activation condition.

[0180] In some example embodiments, the first apparatus comprises a terminal device and the second apparatus comprises a network device.

[0181] In some example embodiments, a first device (eg, Figure 1A The first device 110 in the method 700 may include a component for performing the corresponding operation of the method 700. The component may be implemented in any suitable form. For example, the component may be implemented in a circuit or a software module. The first device may be implemented as Figure 1A The first device 110 in or included in Figure 1A In the first device 110.

[0182] In some example embodiments, a first device includes: a component for receiving a capability query from a second device, the capability query including a machine learning (ML) capability having one or more applicable conditions and a request for the first device to indicate support for at least one activation condition for the applicable conditions; and a component for transmitting capability information to the second device, the capability information including the applicable conditions and at least one activation condition for the applicable conditions, the at least one activation condition indicating whether the corresponding applicable condition is currently supported.

[0183] In some example embodiments, the first apparatus further comprises means for receiving an indication from the second apparatus, the indication indicating which applicable condition the second apparatus is interested in monitoring for changes.

[0184] In some example embodiments, the indication is included in an uplink trigger or message.

[0185] In some example embodiments, the first apparatus further comprises means for transmitting a message to the second apparatus indicating the satisfied activation condition based on determining that one of the at least one activation condition is satisfied.

[0186] In some example embodiments, the first apparatus further comprises: means for receiving a query for the subset of applicable conditions from the second apparatus; and means for transmitting information about the subset of applicable conditions to the second apparatus.

[0187] In some example embodiments, the first apparatus further comprises: means for receiving a conditional reconfiguration message from the second apparatus, the conditional reconfiguration message comprising an activation condition reconfigured for one of the applicable conditions.

[0188] In some example embodiments, the first apparatus further comprises means for transmitting a confirmation indication to indicate that the first apparatus confirms the reconfigured activation condition.

[0189] In some example embodiments, the first apparatus further comprises means for performing conditional reconfiguration for the first activation condition in accordance with determining that the first activation condition of the at least one activation condition is satisfied.

[0190] In some example embodiments, the first device further comprises means for transmitting information to the second device, the information including an update of the first activation condition and one or more updated applicable conditions corresponding to the first activation condition.

[0191] In some example embodiments, the first apparatus comprises a terminal device and the second apparatus comprises a network device.

[0192] In some example embodiments, the first device further comprises means for performing the method 700 or other operations in some example embodiments of the first device 110. In some example embodiments, the means comprises at least one processor and at least one memory storing instructions that, when executed by the at least one processor, cause the first device to perform the operations.

[0193] In some example embodiments, a second device (eg, Figure 1A The second device 120 in the method 800 may include a component for performing the corresponding operation of the method 800. The component may be implemented in any suitable form. For example, the component may be implemented in a circuit or a software module. The second device may be implemented as Figure 1A The second device 120 in or included in Figure 1A In the second device 120.

[0194] In some example embodiments, the second device includes: a component for transmitting a capability query to the first device, the capability query including a machine learning (ML) capability having one or more applicable conditions and a request for the first device to indicate an indication of support for at least one activation condition for the applicable conditions; and a component for receiving capability information from the first device, the capability information including the applicable conditions and at least one activation condition for the applicable conditions, the at least one activation condition indicating whether the corresponding applicable condition is currently supported.

[0195] In some example embodiments, the second apparatus further comprises means for transmitting an indication to the first apparatus, the indication indicating which applicable condition the second apparatus is interested in monitoring for changes.

[0196] In some example embodiments, the indication is included in an uplink trigger or message.

[0197] In some example embodiments, the second apparatus further comprises means for receiving a message from the first apparatus indicating which activation condition is satisfied.

[0198] In some example embodiments, the second apparatus further comprises: means for transmitting a query for the subset of applicable conditions to the first apparatus; and means for receiving information about the subset of applicable conditions from the first apparatus.

[0199] In some example embodiments, the second apparatus further comprises means for storing the subset of applicable conditions.

[0200] In some example embodiments, the second apparatus further comprises: means for transmitting a condition reconfiguration message to the first apparatus, the condition reconfiguration message comprising an activation conditional setting reconfigured for one of the applicable conditions.

[0201] In some example embodiments, the second apparatus further comprises means for receiving a confirmation indication from the first apparatus to instruct the first apparatus to confirm the reconfigured activation condition.

[0202] In some example embodiments, the second apparatus further comprises means for receiving information from the first apparatus regarding an update of the first activation condition and one or more updated applicable conditions corresponding to the first activation condition.

[0203] In some example embodiments, the first apparatus comprises a terminal device and the second apparatus comprises a network device.

[0204] In some example embodiments, the second device further comprises means for performing the method 800 or other operations in some example embodiments of the second device 120. In some example embodiments, the means comprises at least one processor and at least one memory storing instructions that, when executed by the at least one processor, cause the second device to perform the operations.

[0205] Fig. 9 900 is a simplified block diagram of an apparatus 900 suitable for implementing an example embodiment of the present disclosure. Apparatus 900 may be provided to implement a communication apparatus, such as Figure 1A The first device 110 or the second device 120 is shown. As shown in the figure, the device 900 includes one or more processors 910, one or more memories 920 coupled to the processor 910, and one or more communication modules 940 coupled to the processor 910.

[0206] The communication module 940 is used for two-way communication. The communication module 940 has one or more communication interfaces to facilitate communication with one or more other modules or devices. The communication interface may represent any interface necessary to communicate with other network elements. In some example embodiments, the communication module 940 may include at least one antenna.

[0207] Processor 910 may be of any type suitable for the local technology network and may include one or more of the following: 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, as non-limiting examples. Device 900 may have multiple processors, such as application specific integrated circuit chips that are time slaved to a clock that synchronizes a main processor.

[0208] The memory 920 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) 924, electrically programmable read-only memory (EPROM), flash memory, hard disk, compact disk (CD), digital video disk (DVD), optical disk, laser disk, and other magnetic and / or optical memories. Examples of volatile memories include, but are not limited to, random access memory (RAM) 922 and other volatile memories that will not last for the duration of a power outage.

[0209] The computer program 930 includes computer executable instructions executed by the associated processor 910. The instructions of the program 930 may include instructions for performing the operations / actions of some example embodiments of the present disclosure. The program 930 may be stored in a memory such as ROM 924. The processor 910 may perform any suitable actions and processes by loading the program 930 into the RAM 922.

[0210] The exemplary embodiments of the present disclosure may be implemented by a program 930 so that the device 900 may execute the Figures 3 to 8 Any process of the present disclosure discussed. Example embodiments of the present disclosure may also be implemented by hardware or a combination of software and hardware.

[0211] In some example embodiments, the program 930 may be tangibly contained in a computer-readable medium, which may be contained in the device 900 (e.g., in the memory 920) or in other storage devices accessible by the device 900. The device 900 may load the program 930 from the computer-readable medium to the RAM 922 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 of the medium itself (i.e., tangible, not a signal), as opposed to a limitation on data storage persistence (e.g., RAM vs. .ROM).

[0212] Fig.10 An example of a computer readable medium 1000 is shown, which may be in the form of a CD, DVD or other optical storage disk. The computer readable medium 1000 has a program 930 stored thereon.

[0213] Generally, 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 as block diagrams, flow charts, or using some other graphical representations, it should be understood that, as non-limiting examples, the blocks, 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.

[0214] Some example embodiments of the present disclosure also provide at least one computer program product tangibly stored on a computer-readable medium (e.g., a non-volatile computer-readable medium). The computer program product includes computer executable instructions, such as those included in a program module that are executed in a device on a target physical or virtual processor to perform any method as described above. Typically, a program module includes routines, programs, libraries, objects, classes, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The functionality of a program module can be combined or split between program modules as needed in different embodiments. 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.

[0215] The program code for performing 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 the program code, when executed by the processor or controller, causes the implementation of the functions / operations specified in the flow chart and / or block diagram. The program code may be executed entirely on the machine, partially on the machine, as an independent software package, partially on the machine, partially on a remote machine, or entirely on a remote machine or server.

[0216] 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 various processes and operations described above. Examples of carriers include signals, computer readable media, etc.

[0217] 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 devices, or any suitable combination of the foregoing. More specific examples of computer readable storage media will include an electrical connection with one or more wires, a portable computer 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 foregoing.

[0218] Further, although the operations are depicted in a particular order, this should not be construed as requiring the execution of such operations in the particular order shown or in a sequential order, or the execution of all described operations, 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 should not be construed as limitations on the scope of the present disclosure, but rather as descriptions of features that may be specific to a particular embodiment. Unless explicitly stated, certain features described in the context of a separate embodiment may also be implemented in combination in a single embodiment. On the contrary, unless explicitly stated, the different features described in the context of a single embodiment may also be implemented in multiple embodiments individually or in any suitable subcombination.

[0219] Although the disclosure has been described in language specific to structural features and / or methodological actions, it is to be understood that the disclosure defined in the appended claims is not necessarily limited to the specific features or actions described above. Instead, the specific features and actions described above are disclosed as example forms of implementing the claims.

[0220] Example 1. A first device, comprising:

[0221] at least one processor; and

[0222] at least one memory, wherein the at least one memory stores instructions, which, when executed by the at least one processor, cause the first device to at least:

[0223] receiving a capability query from a second device, the capability query including a machine learning (ML) capability having one or more applicable conditions and an indication requesting the first device to indicate support for at least one activation condition for the applicable conditions; and

[0224] Capability information is transmitted to the second device, the capability information including an applicable condition and at least one activation condition for the applicable condition, the at least one activation condition indicating whether the corresponding applicable condition is currently supported.

[0225] Example 2. The first apparatus of example 1, the first apparatus being caused to: receive an indication from a second apparatus indicating which applicable condition the second apparatus is interested in monitoring for changes.

[0226] Example 3. The first apparatus of Example 2, wherein the indication is included in an uplink trigger or message.

[0227] Example 4. The first apparatus of Example 2, wherein the first apparatus is caused to: based on determining that one of the at least one activation condition is satisfied, transmit a message to the second apparatus to indicate the satisfied activation condition.

[0228] Example 5. The first apparatus of Example 4, the first apparatus being caused to: receive a query for a subset of applicable conditions from a second apparatus; and transmit information about the subset of applicable conditions to the second apparatus.

[0229] Example 6. The first apparatus of Example 1, the first apparatus being caused to: receive a condition reconfiguration message from the second apparatus, the condition reconfiguration message comprising an activation condition reconfigured for one of the applicable conditions.

[0230] Example 7. The first apparatus of Example 6, the first apparatus being caused to transmit a confirmation indication to indicate that the first apparatus confirms the reconfigured activation condition.

[0231] Example 8. The first apparatus of Example 7, the first apparatus being caused to: perform conditional reconfiguration for the first activation condition based on determining that a first activation condition among the at least one activation condition is satisfied.

[0232] Example 9. The first device of Example 8, wherein the first device is caused to transmit information about an update of the first activation condition and one or more updated applicable conditions corresponding to the first activation condition to the second device.

[0233] Example 10. According to the first device described in any one of Examples 1 to 9, the first device includes a terminal device and the second device includes a network device.

[0234] Example 11. A second device is provided, comprising:

[0235] at least one processor; and

[0236] at least one memory, wherein the at least one memory stores instructions, which, when executed by the at least one processor, cause the second device to at least:

[0237] transmitting a capability query to the first device, the capability query comprising a machine learning (ML) capability having one or more applicable conditions and an indication requesting the first device to indicate support for at least one activation condition for the applicable conditions; and

[0238] Capability information is received from a first device, the capability information including an applicability condition and at least one activation condition for the applicability condition, the at least one activation condition indicating whether the corresponding applicability condition is currently supported.

[0239] Example 12. The second apparatus of Example 11, the second apparatus being caused to transmit an indication to the first apparatus, the indication indicating which applicable condition the second apparatus is interested in monitoring for changes.

[0240] Example 13. The second apparatus of Example 12, wherein the indication is included in an uplink trigger or message.

[0241] Example 14. The second apparatus of Example 12, the second apparatus being caused to: receive a message from the first apparatus indicating which activation condition is satisfied.

[0242] Example 15. The second apparatus of Example 14, the second apparatus being caused to: transmit a query for a subset of applicable conditions to the first apparatus; and receive information about the subset of applicable conditions from the first apparatus.

[0243] Example 16. The second apparatus of example 15, the second apparatus being caused to store a subset of applicable conditions.

[0244] Example 17. The second apparatus of Example 11, the second apparatus being caused to transmit a condition reconfiguration message to the first apparatus, the condition reconfiguration message comprising an activation condition reconfigured for one of the applicable conditions.

[0245] Example 18. The second device of Example 17, the second device being caused to: receive a confirmation indication from the first device to instruct the first device to confirm the reconfigured activation condition.

[0246] Example 19. The second device according to Example 18 is caused to: receive information from the first device, the information regarding an update of the first activation condition and one or more updated applicable conditions corresponding to the first activation condition; and store the received information.

[0247] Example 20. According to the second device according to any one of Examples 11 to 19, the first device includes a terminal device and the second device includes a network device.

[0248] Example 21. A method is provided, comprising:

[0249] At the first device, receiving a capability query from the second device, the capability query including a machine learning (ML) capability having one or more applicable conditions and an indication requesting the first device to indicate support for at least one activation condition for the applicable conditions; and

[0250] Capability information is transmitted to the second device, the capability information including an applicable condition and at least one activation condition for the applicable condition, the at least one activation condition indicating whether the corresponding applicable condition is currently supported.

[0251] Example 22. The method of Example 21 further comprising: receiving an indication from the second device indicating which applicable condition the second device is interested in detecting a change.

[0252] Example 23. The method of Example 22, wherein the indication is included in an uplink trigger or message.

[0253] Example 24. The method of Example 22 further includes: based on determining that one of the at least one activation condition is satisfied, transmitting a message to the second device to indicate the satisfied activation condition.

[0254] Example 25. The method of Example 24, further comprising: receiving a query for the subset of applicable conditions from the second device; and transmitting information about the subset of applicable conditions to the second device.

[0255] Example 26. The method of Example 21, further comprising: receiving a conditional reconfiguration message from the second device, the conditional reconfiguration message comprising an activation condition reconfigured for one of the applicable conditions.

[0256] Example 27. The method of Example 26 further includes: transmitting a confirmation indication to indicate that the first device confirms the reconfigured activation condition.

[0257] Example 28. The method according to Example 27 further includes: performing conditional reconfiguration for the first activation condition based on determining that at least a first activation condition among the activation conditions is satisfied.

[0258] Example 29. The method of Example 28 further includes: transmitting information to the second device, the information regarding an update of the first activation condition and one or more updated applicable conditions corresponding to the first activation condition.

[0259] Example 30. According to the method of any one of Examples 21 to 29, the first device includes a terminal device and the second device includes a network device.

[0260] Example 31. A method is provided, comprising:

[0261] At the second device, transmitting to the first device a capability query, the capability query comprising a machine learning (ML) capability having one or more applicable conditions and an indication requesting the first device to indicate support for at least one activation condition for the applicable conditions; and

[0262] Capability information is received from a first device, the capability information including an applicability condition and at least one activation condition for the applicability condition, the at least one activation condition indicating whether the corresponding applicability condition is currently supported.

[0263] Example 32. The method of Example 31 further comprising: transmitting an indication to the first device indicating which applicable condition the second device is interested in monitoring for changes.

[0264] Example 33. The method of Example 32, wherein the indication is included in an uplink trigger or message.

[0265] Example 34. The method of Example 32 further includes: receiving a message from the first device indicating which activation condition is met.

[0266] Example 35. The method of Example 34 further includes: transmitting a query for the subset of applicable conditions to the first device; and receiving information about the subset of applicable conditions from the first device.

[0267] Example 36. The method according to Example 35 also includes: storing a subset of applicable conditions.

[0268] Example 37. The method of Example 31 further includes: transmitting a conditional reconfiguration message to the first device, the conditional reconfiguration message including an activation condition reconfigured for one of the applicable conditions.

[0269] Example 38. The method of Example 37 further includes: receiving a confirmation indication from the first device to indicate that the first device confirms the reconfigured activation condition.

[0270] Example 39. The method according to Example 38 also includes: receiving information from the first device, the information regarding an update of the first activation condition and one or more updated applicable conditions corresponding to the first activation condition; and storing the received information.

[0271] Example 40. According to the method described in any one of Examples 31 to 39, the first device includes a terminal device and the second device includes a network device.

[0272] Example 41. A first device is provided, comprising:

[0273] means for receiving a capability query from a second device, the capability query comprising a machine learning (ML) capability having one or more applicable conditions and an indication requesting the first device to indicate support of at least one activation condition for the applicable conditions; and

[0274] A component for transmitting capability information to a second device, the capability information including an applicability condition and at least one activation condition for the applicability condition, the at least one activation condition indicating whether the corresponding applicability condition is currently supported.

[0275] Example 42. A second device is provided, comprising:

[0276] means for transmitting a capability query to a first device, the capability query comprising a machine learning (ML) capability having one or more applicable conditions and a request for the first device to indicate an indication of support for at least one activation condition for the applicable conditions; and

[0277] A component for receiving capability information from a first device, the capability information including an applicability condition and at least one activation condition for the applicability condition, the at least one activation condition indicating whether the corresponding applicability condition is currently supported.

[0278] Example 43. Provided is a computer-readable medium comprising instructions stored thereon, the instructions being used to cause an apparatus to at least perform a method according to any one of Examples 21 to 30 or a method according to any one of Examples 31 to 40.

Claims

1. A first device, comprising: at least one processor; as well as at least one memory storing instructions, which, when executed by the at least one processor, cause the first device to at least: receiving a capability query from a second device, the capability query comprising a machine learning (ML) capability having one or more applicable conditions and an indication requesting the first device to indicate support for at least one activation condition for the applicable condition; as well as Capability information is transmitted to the second device, the capability information including the applicability condition and the at least one activation condition for the applicability condition, the at least one activation condition indicating whether the corresponding applicability condition is currently supported.

2. The first device according to claim 1, wherein the first device is caused to: An indication is received from the second device, the indication indicating which applicable condition the second device is interested in monitoring for changes.

3. The first apparatus of claim 2, wherein the indication is included in an uplink trigger or message.

4. The first device of claim 2, wherein the first device is caused to: Based on determining that one of the at least one activation condition is satisfied, a message is transmitted to the second device to indicate the activation condition being satisfied.

5. The first device according to claim 4, wherein the first device is caused to: receiving a query for a subset of the applicable conditions from the second device; and Information about the subset of the applicable conditions is transmitted to the second device.

6. The first device of claim 1, wherein the first device is caused to: A condition reconfiguration message is received from the second device, the condition reconfiguration message including an activation condition reconfigured for one of the applicable conditions.

7. The first device of claim 6, wherein the first device is caused to: A confirmation indication is transmitted to instruct the first device to confirm the reconfigured activation condition.

8. The first device of claim 7, wherein the first device is caused to: According to determining that a first activation condition among the at least one activation condition is satisfied, conditional reconfiguration for the first activation condition is performed.

9. The first device of claim 8, wherein the first device is caused to: Information regarding an update of the first activation condition and one or more updated applicable conditions corresponding to the first activation condition is transmitted to the second device.

10. The first apparatus according to any one of claims 1 to 9, wherein the first apparatus comprises a terminal device, and the second apparatus comprises a network device.

Images