Apparatus and method for communication

Abstract

Embodiments of the present disclosure provide a solution for transmitting information for data collection. In one solution, a first device determines first information related to a machine learning (ML) model deployed at the first device, where the first information indicates at least one of: a first set of candidate cells associated with an output of the ML model, or a second set of candidate cells associated with an input of the ML model; and sending the first information to the second device.

Description

TECHNICAL FIELD

[0001] Example embodiments of the present disclosure generally relate to the field of communications technology, and in particular, to devices and methods for sending information for data collection. BACKGROUND

[0002] As communication networks and services grow in scale, complexity, and number of users, operations in the communication networks can become increasingly complex. To improve communication performance, machine learning (ML) / artificial intelligence (AI) techniques are proposed to be used in wireless communication networks. For example, terminal devices and network devices can use different ML models to assist communication-related functionalities, such as beam management (BM), mobility management, etc.

[0003] In some cases, a ML model is deployed at one communication device, such as a terminal device. In this case, the terminal device can need to collect data for model training inference / update / monitoring. However, the network device is not aware of the model training requirement, and thus the network device cannot configure appropriate resources to assist the terminal device to collect data. SUMMARY

[0004] Generally, embodiments of the present disclosure provide solutions for sending information for data collection.

[0005] In a first aspect, a first device is provided, comprising: a processor configured to cause the first device to: determine first information related to a ML model deployed at the first device, the first information indicating at least one of: a first set of candidate cells associated with an output of the ML model, or a second set of candidate cells associated with an input of the ML model; and send, to a second device, the first information.

[0006] In a second aspect, a second device is provided, comprising: a processor configured to cause the second device to: receive, from a first device having a ML model deployed, first information related to the ML model, the first information indicating at least one of: a first set of candidate cells associated with an output of the ML model, or a second set of candidate cells associated with an input of the ML model.

[0007] In a third aspect, a communication method performed by a first device is provided. The method comprises determining first information related to a ML model deployed at the first device, the first information indicating at least one of: a first set of candidate cells associated with an output of the ML model, or a second set of candidate cells associated with an input of the ML model; and transmitting, to a second device, the first information.

[0008] In a fourth aspect, a communication method performed by a second device is provided. The method comprises receiving, from a first device having a ML model deployed, first information related to the ML model, the first information indicating at least one of: a first set of candidate cells associated with an output of the ML model, or a second set of candidate cells associated with an input of the ML model.

[0009] In a fifth aspect, a computer readable medium having stored thereon instructions, which when executed on at least one processor, cause the at least one processor to perform the method according to the third aspect or the fourth aspect.

[0010] Other features of the present disclosure will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0011] The above and other objects, features and advantages of the present disclosure will become more apparent from the following description when taken in conjunction with the accompanying drawings, in which: Figure 1A An example communication environment in which example embodiments of the present disclosure can be implemented is illustrated; Figure 1A An example communication environment in which example embodiments of the present disclosure can be implemented is illustrated; Figure 2 A signaling procedure for transmitting information about a number of predicted beams according to some embodiments of the present disclosure is illustrated; Figure 3 Example blocks of different periods are illustrated; Figure 4 A flowchart of a method implemented at a first device according to some example embodiments of the present disclosure is illustrated; Figure 5 A flowchart of a method implemented at a second device according to some example embodiments of the present disclosure is illustrated; and Figure 6 A simplified block diagram of an apparatus suitable for implementing example embodiments of the present disclosure is illustrated.

[0012] Throughout the drawings, identical or similar reference numerals can represent same or similar elements. DETAILED DESCRIPTION

[0013] The principles of the present disclosure will now be described with reference to some example embodiments. It will be appreciated that these embodiments are described for purposes of illustration only and are not intended to limit the scope of the present disclosure in any way. Embodiments described herein can be implemented in various ways, other than those described below.

[0014] In the following description and claims, unless otherwise defined, 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.

[0015] As used herein, the term “terminal device” refers to any device with wireless or wired communication capabilities. Examples of terminal devices include, but are not limited to: a user equipment (UE); a personal computer; a desktop computer; a mobile computer; a cell phone; a cellular phone; a smart phone; a personal digital assistant (PDA); a portable computer; a tablet computer; a wearable device; an internet of things (IoT) device; an Ultra-reliable and Low Latency Communication (URLLC) device; an Internet of Everything (IoE) device; a machine type communication (MTC) device; a device for V2X communication on a vehicle, where X refers to a pedestrian, a vehicle, or infrastructure / network; a device for Integrated Access and Backhaul (IAB); a spaceborne or an airborne vehicle in a Non-terrestrial network (NTN), which includes satellites and High Altitude Platforms (HAPs) covering Unmanned Aircraft Systems (UAS); an eXtended Reality (XR) device including different types of realities such as Augmented Reality (AR), Mixed Reality (MR), and Virtual Reality (VR); an unmanned aerial vehicle (UAV), which is commonly known as a drone, which is an aircraft without any human pilot; a device on a high speed train (HST); or an image-capturing device such as a digital camera, a sensor; a gaming device; a music storage and playback appliance; or an Internet appliance enabling wireless or wired Internet access and browsing, etc. A “terminal device” can also have “multicast / broadcast” functionality to support public safety and mission critical, V2X applications, transparent IPv4 / IPv6 multicast delivery, IPTV, smart TV, radio services, wireless software delivery, group communications, and IoT applications. A “terminal device” can also incorporate one or more Subscriber Identity Modules (SIMs), in which case the latter is referred to as a multi-SIM. The term “terminal device” can be used interchangeably with UE, mobile station, subscriber station, mobile terminal, user terminal, or wireless device.

[0016] The term “network device” refers to a device capable of providing or hosting a cell or coverage in which a terminal device can communicate. Examples of network devices include, but are not limited to, Node B (NodeB or NB), evolved NodeB (eNodeB or eNB), generation NodeB (gNB), transmission reception point (TRP), remote radio unit (RRU), radio head (RH), remote radio head (RRH), IAB node, low power node (such as femto node, pico node), reconfigurable intelligent surface (RIS), and the like.

[0017] A terminal device or a network device can have an Artificial Intelligence (AI) or machine learning capability. A terminal device or a network device typically includes a model that has been trained for a specific function according to a large amount of collected data and can be used to predict some information.

[0018] A terminal device or a network device can operate in several frequency ranges, such as FR1 (e.g., 450-6000 MHz), FR2 (e.g., 24.25-52.6 GHz), bands above 100 GHz, and terahertz (THz). A terminal device or a network device can also operate on licensed / unlicensed / shared spectrum. In a multi-radio dual connectivity (MR-DC) application scenario, a terminal device can have more than one connection with a network device. A terminal device or a network device can operate in full duplex, flexible duplex, and cross-split duplex modes.

[0019] Embodiments of the present disclosure can be implemented in test equipment (e.g., signal generator, signal analyzer, spectrum analyzer, network analyzer, test terminal device, test network device, channel emulator). In some embodiments, a terminal device can connect with a first network device and a second network device. One of the first network device and the second network device can be a master node, and the other can be a secondary node. The first network device and the second network device can use different radio access technologies (RATs). In some embodiments, the first network device can be a first RAT device, and the second network device can be a second RAT device. In some embodiments, the first RAT device is an eNB, and the second RAT device is a gNB. Information related to different RATs can be sent from at least one of the first network device or the second network device to the terminal device. In some embodiments, first information can be sent from the first network device to the terminal device, and second information can be sent from the second network device to the terminal device directly or via the first network device. In some embodiments, information related to configuration for the terminal device configured by the second network device can be sent from the second network device via the first network device. Information related to reconfiguration for the terminal device configured by the second network device can be sent from the second network device to the terminal device directly or via the first network device.

[0020] As used herein, the singular forms “a,” “an,” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. The term “including” and variations thereof are to be construed as open-ended terms meaning “including, but not limited to.” The term “based on” is to be construed as “based at least in part on.” The terms “one embodiment” and “an embodiment” are to be understood as “at least one embodiment.” The term “another embodiment” is to be understood as “at least one other embodiment.” The terms “first,” “second,” etc. can refer to different or the same objects. Other explicitly and implicitly recited definitions can be given below.

[0021] In some examples, values, programs, or apparatuses are described as “best,” “lowest,” “highest,” “smallest,” “largest,” etc. It should be understood that such descriptions mean that a choice can be made among many used functional alternatives, and that such choices need not be better, smaller, higher, or otherwise more desirable than other choices.

[0022] As used herein, the term “resource,” “transmission resource,” “uplink resource,” or “downlink resource” can refer to any resource used to perform communication, such as a resource in time domain, a resource in frequency domain, a resource in space domain, a resource in code domain, or any other resource that enables communication, etc. In the following, unless explicitly stated, resources on frequency and time domain will be used as an example of transmission resource for describing some examples of the present disclosure. It is worth noting that example embodiments of the present disclosure are equally applicable to other resources in other domains.

[0023] As described above, to improve communication performance, it is proposed to use ML / AI techniques in wireless communication networks. For example, terminal devices and network devices can use different ML models to assist communication related functionalities, such as BM, mobility management, etc.

[0024] In the case of mobility management, it is desirable to support some use cases, such as: target cell prediction with one-sided model (such as predicting target cell and predicting when to handover to target cell); radio resource management (RRM) prediction with one-sided model (such as predicting future reference signal received power (RSRP) / signal to interference plus noise ratio (SINR)); time beam prediction for BM; handover parameter optimization (such as predicting future handover (HO) parameters, e.g., hysteresis, offset, time to trigger (TTT), cell individual offset (CIO), timer 304); trajectory (or radio link failure (RLF) / handover failure (HOF) avoidance) prediction with one-sided model (such as predicting location of coverage holes / barriers); cross-cell time or spatial beam prediction with one-sided model (such as beam prediction of spatial / time beam extended to multiple cells).

[0025] When operating mobility management prediction, a terminal device can use historical layer 1 (L1) measurements (e.g., L1-RSRP, L1-SINR) of candidate cell beams (and other possible assistance information at terminal device side) to predict target cell, or to predict future L1 measurements of candidate cell beams. That is, the terminal device needs to collect data for model training inference / update / monitoring. However, the network device is not aware of the model training requirements, so the network device cannot configure suitable resources to assist the terminal device to collect data.

[0026] According to example embodiments of the disclosure, a solution for sending information for data collection is proposed. In this solution, a first device (such as a terminal device) determines first information related to a ML model deployed at the first device, where the first information indicates at least one of: a first set of candidate cells associated with an output of the ML model, or a second set of candidate cells associated with an input of the ML model. Then, the first device sends the first information to a second device (e.g., a network device).

[0027] By sending the first information to the second device, the second device can allocate appropriate measurement resources for the first device, so that the first device can collect sufficient data to ensure the ML is functioning properly.

[0028] In the following, a terminal device and a network device will be used as examples of the first device and the second device for better understanding. It should be understood that the embodiments described herein can be implemented between any suitable communication devices unless there is a clear literal statement. Specifically, either of the first device and the second device can be a terminal device or a network device.

[0029] As used herein, the term “model” is referred to as an 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 ML techniques. The ML techniques can also be referred to as AI techniques. Generally, a ML model can be constructed that receives input information and makes predictions based on the input information.

[0030] As used herein, a model can be equivalent to at least one of: an AI / ML model, a ML model, an AI model, a data-driven, data processing model, an algorithm, a functionality, a program, a process, an entity, a function, a feature, a feature set, a model ID, a functionality ID, a configuration ID, a scenario ID, a site ID, or a dataset ID. Therefore, the above terms can be used interchangeably.

[0031] In some embodiments, a model can be represented by or associated with a channel, a resource, a resource set, a RS resource, a RS resource set, a RS port, a RS port set, a RS port ID, or a RS port ID set.

[0032] In some embodiments, a model can include a set of weight values that can be learned during training, e.g., for a particular architecture or configuration, where the set of weight values can also be referred to as a parameter set.

[0033] In some embodiments, the model can be used to predict a target cell, or to predict measurement results of a set of beams of a future set of candidate cells based on historical measurement results (e.g., L1-RSRP, L1-SINR) of a set of beams of at least one set of candidate cells.

[0034] In some embodiments, input of a ML model (i.e., AI input) can refer to input of a model and indicate data input into the model, which can be equivalent to data.

[0035] In some embodiments, output of a ML model (i.e., AI output) can refer to output of a model and indicate results output by the model, which is equivalent to labels / data.

[0036] In some embodiments, AI input or output of a model can be information included in meta information / description associated with the model.

[0037] In the present disclosure, a beam can be equivalent to (or represented by) the following: an RS (e.g., a channel state information-reference signal (CSI-RS), a synchronization signal and PBCH block (SSB)), an RS resource, an associated RS, an associated RS resource, an RS resource indicator (e.g., a CSI-RS resource indicator (CRI), an SSB resource indicator (SSBRI)), an RS index (e.g., a CSI-RS index, an SSB index), an associated RS resource indicator, or an associated RS index. It should also be understood that in fact, a beam can refer to a resource that enables spatially directional communication, and thus a beam can be identified by other suitable parameters. The present disclosure is not limited in this regard.

[0038] As used herein, data collection can be used for model training, model validation, model testing, model updating (e.g., fine-tuning), model inference, and / or model monitoring. Alternatively or additionally, data collection can refer to a process of collecting data by a network node, a management entity, a UE, or a terminal device for the purpose of AI / ML model training, data analysis, and inference. Further, data collection can be performed for different purposes, e.g., model training, model inference, model monitoring, model selection, model updating, etc., in lifecycle management (LCM).

[0039] As used herein, the terms “measurement quantity” and “beam measurement quantity” are used interchangeably and include, but are not limited to, (L1)-RSRP, (L1)-SINR, (L1)-received signal strength indicator (RSSI), or (L1)-reference signal received quality (RSRQ). Further, L1-RSRP can be equivalent to RSRP or RSRQ, and L1-SINR can be equivalent to SINR.

[0040] As used herein, a beam measurement resource can be equivalent to a channel measurement resource (CMR) or (and) an interference measurement resource (IMR).

[0041] As used herein, prediction can be equivalent to (model) inference.

[0042] As used herein, a cell can be equivalent to a (downlink or uplink) bandwidth part (BWP). Further, a cell can be equivalent to (or represented by) at least one of the following: an indicator of a cell (including, but not limited to, a cell ID, a physical cell identity (PCI), an additional PCI, a serving cell index), a cell identity (e.g., Cell-Identity), or an indicator or information of a frequency. In addition thereto, a cell can be a primary cell (PCell), a primary secondary cell (PSCell), or a secondary cell (SCell).

[0043] As used herein, a serving cell can be equivalent to a source cell or an intra- frequency cell, and a non-serving cell can be equivalent to a neighboring cell or an inter- frequency cell. Further, a candidate cell can be a serving cell or a non-serving cell.

[0044] As used herein, a cell (associated with the same frequency range / band) within the same frequency range (or band) can refer to a cell whose SSB has the same center frequency and sub-carrier space (SCS).

[0045] In the context of the present disclosure, - the terms “timestamp”, “period”, “interval”, “time interval”, “time period”, “gap”, “time gap”, and “time of recording data” are used interchangeably; - the terms“time instance,”“transmit time,”“time / transmit unit,”“time / transmit frame,”“time / transmit subframe,”“time / transmit time slot,”“time / transmit symbol,”“time / transmit point,”“time / transmit stamp,”“time / transmit occasion” are used interchangeably; - the terms“time instance,”“transmit time,”“time / transmit unit,”“time / transmit frame,”“time / transmit subframe,”“time / transmit time slot,”“time / transmit symbol,”“time / transmit point,”“time / transmit stamp,”“time / transmit occasion” are used interchangeably; - the terms“future,”“prediction,” and“predicted” are used interchangeably.

[0046] The principles and specific embodiments of the present disclosure will be described below in detail with reference to the accompanying drawings.

[0047] Example Environment Figure 1A A schematic diagram of an example communication environment 100A in which example embodiments of the present disclosure can be implemented is illustrated. In the communication environment 100A, multiple communication devices, including a first device 110 and a second device 120, can communicate with each other.

[0048] Further, multiple-input multiple-output (MIMO) is supported in the communication environment 100A such that the second device 120 and the first device 110 can communicate with each other via different beams to enable directional communication.

[0049] In the example of a cellular network, Figure 1A In this particular example embodiment, the link from the first device 110 to the second device 120 is referred to as the uplink, while the link from the second device 120 to the first device 110 is referred to as the downlink.

[0050] In the downlink, the second device 120 is the transmitting (TX) device (or transmitter) and the first device 110 is the receiving (RX) device (or receiver), and the second device 120 can transmit downlink transmissions to the first device 110 via one or more beams. As Figure 1A As illustrated, the second device 120 transmits downlink transmissions to the first device 110 via one or more of beams 140-1, 140-2, and 140-3. For purposes of discussion, the beams 140-1 through 140-3 are referred to collectively or individually as beams 140.

[0051] Correspondingly, in the uplink, the second device 120 is the RX device (or receiver) and the first device 110 is the TX device (or transmitter), and the first device 110 can transmit uplink transmissions to the second device 120 via one or more beams. As Figure 1A As illustrated, the first device 110 transmits uplink transmissions to the second device 120 via beams 130-1 through 130-3. For purposes of discussion, the beams 130-1 through 130-3 are referred to collectively or individually as beams 130.

[0052] It should be appreciated, Figure 1A The number of devices shown and their connections are for illustrative purposes only and are not intended to suggest any limitations. The communication environment 100A can include any suitable number of devices configured to implement example embodiments of the present disclosure.

[0053] In some embodiments, the first device 110 and the second device 120 communicate via a channel, such as a wireless communication channel over an air interface (e.g., a Uu interface). The wireless communication channel can include a physical uplink control channel (PUCCH), a physical uplink shared channel (PUSCH), a physical random-access channel (PRACH), a physical downlink control channel (PDCCH), a physical downlink shared channel (PDSCH), and a physical broadcast channel (PBCH). Of course, any other suitable channel is possible.

[0054] Communications in the communication environment 100A can conform to any suitable standards, including but not limited to Global System for Mobile Communication (GSM), Long Term Evolution (LTE), LTE- Evolution, LTE-Advanced (LTE-A), New Radio (NR), Wideband Code Division Multiple Access (WCDMA), Code Division Multiple Access (CDMA), GSM EDGE Radio Access Network (GERAN), Machine Type Communication (MTC), etc. Embodiments of the present disclosure can be performed according to any generation of communication protocol that is currently known or that will be developed in the future. Examples of communication protocols include, but are not limited to, first generation (1G), second generation (2G), 2.5G, 2.75G, third generation (3G), fourth generation (4G), 4.5G, fifth generation (5G), 5.5G, 5G-Advanced networks, or sixth generation (6G) networks.

[0055] In some embodiments, one or more models can be deployed at the first device 110. As Figure 1A illustrated, a model 115 is deployed at the first device 110. Further, in accordance with some embodiments of the present disclosure, for training data collection for the model 115 at the first device 110, training related information such as supported / preferred resource configurations and / or the number of data samples required can be reported to the second device 120, which can be discussed hereinafter.

[0056] In Figure 1A some embodiments, the model 115 can assist mobility management functionality. As Figure 1A illustrated, the model 115 can receive an input 150 and provide an output 170. More details regarding the input 150 and the output 170 will be discussed with reference to Figure 1B .

[0057] Figure 1BA schematic diagram of an example communication environment 100B in which example embodiments of the present disclosure can be implemented is illustrated. As Figure 1B As illustrated, the input 150 includes a set of data samples including data samples 155, where each data sample corresponds to a historical measurement time instance. In some embodiments, the data samples 155 can be measurement results (e.g., L1-RSRP, L1-SINR, L1-RSSI, or L1-RSRQ) of a plurality of sets of beams associated with a set of candidate cells, as illustrated by block 160.

[0058] According to some embodiments of the present disclosure, the output 170 can be represented by any suitable representation. In some embodiments, the output 170 can include a set of data samples including data samples 175.

[0059] In some embodiments, the output 170 can be an indicator of the target cell and / or time information indicating a time point to handover to the target cell, as illustrated by block 180-1.

[0060] In some embodiments, the output 170 can correspond to a set of future time instances. Further, for each future time instance, there can be a data sample. As Figure 1B As illustrated, the data samples 175 can be predicted L1-RSRP / L1-SINR of a plurality of sets of beams associated with a set of candidate cells. In some embodiments, the set of candidate cells / set of beams associated with the output 170 can be the same as the set of candidate cells / set of beams associated with the input 150, as illustrated by block 180-2.

[0061] Alternatively, in some embodiments, the set of candidate cells / set of beams associated with the output 170 can be an expanded set of the set of candidate cells / set of beams associated with the input 150, as illustrated by block 180-3.

[0062] In some embodiments, the data samples 175 can be predicted L1-RSRP / L1-SINR of a set of beams associated with the target cell, as illustrated by block 180-4. Further, the data samples 175 can correspond to future time instances.

[0063] As previously discussed, for model training of the AI / ML based mobility model trained at the first device 110, the first device 110 needs to collect data (including data samples and labels) required for model training based on measurement resources for beams and candidate cells configured by the second device 120.

[0064] However, the second device 120 does not know the details of the AI / ML model trained at the first device 110, e.g., the candidate cells and beams that need to be measured in the AI input, and the candidate cells and beams that are predictable in the AI output. Therefore, the second device 120 does not know how to configure the measurement resources for the beams and candidate cells needed for the data collection of the model 115.

[0065] According to example embodiments of the present disclosure, a solution for transmitting information for data collection, in particular for data collection of a model 115 applied for ML based mobility. In this solution, a first device, such as a terminal device, determines first information related to a ML model 115 deployed at the first device 110, wherein the first information indicates at least one of: a first set of candidate cells associated with an output of the ML model, or a second set of candidate cells associated with an input of the ML model. Then, the first device transmits the first information to a second device 120, such as a network device.

[0066] In this way, the second device 120 can be transmitted information related to the ML model 115 deployed at the first device 110. Therefore, the second device 120 can well understand how to configure the measurement resources for data collection (i.e., measurement resources for beams and candidate cells) based on the received information.

[0067] Example procedure Reference Figure 2 which illustrates a signaling procedure 200 for communicating information about the number of predicted beams according to some embodiments of the present disclosure. For the purpose of discussion, reference will be made to Figure 1A and Figure 1B The signaling procedure 200 will be discussed, e.g., by using the first device 110 and the second device 120.

[0068] It should be appreciated that the operations at the first device 110 and the second device 120 should be coordinated. In other words, the second device 120 and the first device 110 should have a common understanding of the configurations, parameters, etc. This common understanding can be achieved through any suitable interaction between the second device 120 and the first device 110, or by both the second device 120 and the first device 110 applying the same rules / policies. In the following, although some operations are described from the perspective of the first device 110, it should be appreciated that corresponding operations should be performed by the second device 120. Similarly, although some operations are described from the perspective of the second device 120, it should be appreciated that corresponding operations should be performed by the first device 110. Some identical or similar content is omitted here for brevity.

[0069] In addition, in the following description, some interactions (such as exchanging first information and second information, etc.) are performed between the first device 110 and the second device 120. It should be understood that these interactions can be implemented in a single signaling / message / configuration or multiple signaling / messages / configurations, including system information, radio resource control (RRC) messages, downlink control information (DCI) messages, uplink control information (UCI) messages, media access control (MAC) control elements (CEs), etc. The present disclosure is not limited thereto.

[0070] In some embodiments, the first device 110 can operate as a terminal device, and the second device 120 can operate as a network device.

[0071] In operation, the first device 110 determines 230 first information related to the ML model 115 deployed at the first device 110. In some embodiments, the first information can indicate a first set of candidate cells (hereinafter also referred to as Set C) associated with the output of the ML model 115. Alternatively or in addition, in some embodiments, the first information can indicate a second set of candidate cells (hereinafter also referred to as Set D) associated with the input of the ML model 115. Then, the first device 110 sends 240 the first information to the second device 120.

[0072] In some embodiments, based on the first information, the second device 120 can well understand the measurement requirements of the ML model 115. Then, the second device 120 can determine second information indicating the measurement resources to be used by the first device 110. Thereafter, the second device 120 can send 250 the second information to the first device 110. With the allocated resources, the first device 110 can collect sufficient data to perform mobility prediction.

[0073] In some embodiments, before sending the first information, the first device 110 can send 210 a request for resources for sending the first information to the second device 120. Therefore, the second device 120 can transfer 220 authorization (such as uplink authorization) for the request.

[0074] In some embodiments, the second set of candidate cells can be a part of the first set of candidate cells. Alternatively or in addition, in some embodiments, a part of the second set of candidate cells is the same as a part of the first set of candidate cells. Alternatively or in addition, in some embodiments, the second set of candidate cells is the same as the first set of candidate cells. Alternatively or in addition, in some embodiments, the second set of candidate cells is different from the first set of candidate cells.

[0075] In the following, how to indicate the first set of candidate cells and / or the second set of candidate cells will be discussed as follows.

[0076] In some embodiments, the first information can indicate a first number of candidate cells included in the first set of candidate cells and / or a second number of candidate cells included in the second set of candidate cells.

[0077] In some embodiments, the first number of candidate cells can comprise at least one of a maximum number of candidate cells or a minimum number of candidate cells included in the first set of candidate cells supported / allowed by the first device 110 or the ML model 115.

[0078] In some embodiments, the second number of candidate cells can comprise at least one of a maximum number of candidate cells or a minimum number of candidate cells included in the second set of candidate cells supported / allowed by the first device 110 or the ML model 115.

[0079] Alternatively or in addition, in some embodiments, the first information can indicate a first set of cell identities corresponding to the first set of candidate cells and / or a second set of cell identities corresponding to the second set of candidate cells.

[0080] Alternatively or in addition, in some embodiments, the first information can indicate a union of the first set of candidate cells and the second set of candidate cells and / or a third number of candidate cells included in the union.

[0081] Alternatively or in addition, in some embodiments, the first information can indicate: - a first indication indicating whether a serving cell of the first device 110 is included in the first set of candidate cells, - a second indication indicating whether the serving cell is included in the second set of candidate cells, - a third indication whether a neighbor cell of the first device 110 is included in the first set of candidate cells, - a fourth indication whether the neighbor cell is included in the second set of candidate cells.

[0082] Alternatively or additionally, in some embodiments, the first information can indicate a first number of neighboring cells included in the first group of candidate cells and / or a second number of neighboring cells included in the second group of candidate cells.

[0083] In some embodiments, the first number of neighboring cells can include at least one of a maximum number of neighboring cells or a minimum number of neighboring cells included in the first group of candidate cells supported / allowed by the first device 110 or the ML model 115.

[0084] In some embodiments, the second number of neighboring cells can include at least one of a maximum number of neighboring cells or a minimum number of neighboring cells included in the second group of candidate cells supported / allowed by the first device 110 or the ML model 115.

[0085] For better understanding, some example embodiments on how to indicate candidate cell related information are discussed below.

[0086] According to example embodiments below, the second device 120 can know the number of candidate cells that need to be configured for measurement and / or the specific candidate cell that need to be configured for measurement.

[0087] In some embodiments, the candidate cells can include at least one of the following: a serving cell or one or more non-serving cells (i.e., one or more neighboring cells).

[0088] In some embodiments, the first device 110 (e.g., a terminal device) can send, to the second device 120 (e.g., a network device), the first information on at least one of the following: a candidate cell group C (i.e., a first group of candidate cells, abbreviated as “group C”) and a candidate cell group D (i.e., a second group of candidate cells, abbreviated as “group D”). In some embodiments, the candidate cell group C can include a group of candidate cells corresponding to AI output, or the AI output is derived from the group of candidate cells. In some embodiments, the candidate cell group D can include a group of candidate cells corresponding to AI input, i.e., the corresponding measurement results (e.g., L1-RSRP) of group D need to be used as AI input.

[0089] As an example embodiment, the AI / ML model can use the measurement results of candidate cells 0, 2 and 4 to predict (an indicator of) a target cell from candidate cells 0, 1, 2, 3, 4, 5, 6 and 7. In this case, group D can include candidate cells 0, 2 and 4, and group C can include candidate cells 0, 1, 2, 3, 4, 5, 6 and 7.

[0090] In some embodiments, the relationship of group C and group D can be: group D is the same as group C, group D is a subset of group C, group D is different from group C, group D and group C partially overlap.

[0091] In some embodiments, the first device 110 can send information (or an indication) about at least one of: the size of the group C or the size of the group D, where the size of the group C or the group D indicates the number of candidate cells in the group C or the group D.

[0092] In some embodiments, the size of the group C or the group D can include a minimum size or (and) a maximum size supported by the first device 110 or associated with the ML model 115. In one example, the maximum size of the group C can indicate the maximum number of candidate cells that the first device 110 (or the ML model 115) can predict. In another example, the minimum size of the group D can indicate the minimum number of candidate cells that the first device 110 (or the ML model 115) predicts required / allowed / supported, i.e., those candidate cells that need to be measured.

[0093] In addition, in some embodiments, considering that the group D can be the same as the group C, a subset thereof, or different from it, the first device 110 can send the first information about the size of the new candidate cell group to the second device 120, i.e., the first information can indicate the union of the group C and the group D.

[0094] In addition, in some embodiments, considering that a candidate cell can be a serving cell or a non-serving cell, and the configuration method of the measurement resource of the serving cell and the non-serving cell can be different, the first device 110 can further send at least one of the following first information to the second device 120: an indication indicating whether the serving cell is included in the group C, an indication indicating whether the serving cell is included in the group D, an indication indicating whether at least one non-serving cell is included in the group C, or an indication indicating whether at least one non-serving cell is included in the group D.

[0095] In addition, in some embodiments, if at least one non-serving cell is included in the group C and the group D, the first device 110 can send at least one of the following first information to the second device 120: the number of non-serving cells in the group C or the number of non-serving cells in the group D.

[0096] In order to enable the second device 120 to know which candidate cells need to be configured, the first device 110 can determine the indicators of the candidate cells in the group C or the group D based on the cell IDs of the candidate cells configured by the second device 120. Then, the first device 110 can send the first information about at least one of: the indicators of the candidate cells in the group C, or the indicators of the candidate cells in the group D, to the second device 120.

[0097] In this way, based on the above information sent by the first device 110, the second device 120 can know how many (and which) candidate cells need to be configured for measurement. Therefore, unnecessary measurement resource overhead can be saved.

[0098] Alternatively or in addition, in some embodiments, the first information can be indicative of beam-related information about the ML model 115.

[0099] In some embodiments, the first information can be indicative of at least one first set of beams associated with the output of the ML model 115 or the first set of candidate cells.

[0100] In some embodiments, the at least one first set of beams comprises at least one of a set of beams corresponding to a serving cell included in the first set of candidate cells or a set of beams corresponding to at least one neighboring cell included in the first set of candidate cells.

[0101] In some embodiments, the first information can be indicative of the at least one first set of beams by at least one of a first number of beams included in the first set of beams and / or a first set of beam identifications corresponding to the first set of beams.

[0102] In some embodiments, the first number of beams comprises at least one of a maximum number of beams or a minimum number of beams included in the first set of beams supported by the first device 110 or the ML model 115.

[0103] Alternatively or in addition, in some embodiments, the first information can be indicative of at least one second set of beams associated with the input of the ML model 115 or the second set of candidate cells.

[0104] In some embodiments, the at least one second set of beams comprises at least one of a set of beams corresponding to a serving cell included in the second set of candidate cells or a set of beams corresponding to at least one neighboring cell included in the second set of candidate cells.

[0105] In some embodiments, the first information can be indicative of a second number of beams included in the second set of beams and / or a second set of beam identifications corresponding to the second set of beams.

[0106] In some embodiments, the second number of beams comprises at least one of a minimum number of beams or a maximum number of beams in the second set of beams supported by the first device 110 or the ML model 115.

[0107] Alternatively or in addition, in some embodiments, the first information can be indicative of a union of the one or more first sets of beams and the one or more second sets of beams.

[0108] In some embodiments, the beams included in the at least one second set of beams can be a part of the beams included in the at least one first set of beams.

[0109] Alternatively or in addition, in some embodiments, a portion of the beams included in the at least one second group of beams can be a portion of the beams included in the at least one first group of beams.

[0110] Alternatively or in addition, in some embodiments, the beams included in the at least one second group of beams can be the same as the beams included in the at least one first group of beams.

[0111] Alternatively or in addition, in some embodiments, the beams in the at least one second group of beams can be different from the beams in the at least one first group of beams.

[0112] For better understanding, some example embodiments on how to indicate the beam related information are discussed below.

[0113] In some embodiments, for each candidate cell in group C or group D, the second device 120 needs to know how many beams the second device 120 needs to configure for measurement and / or which beams the second device 120 needs to configure for measurement.

[0114] In some embodiments, as Figure 1B illustrated, the first device 110 can send to the second device 120 the first information on at least one of the following: - Beam group A S , where the beam group A S includes a group of beams associated with the serving cell, and the AI output corresponds to or originates from these beams (if the serving cell is included in group C); abbreviated as group A S . - Beam group A NS , where the beam group A NS includes a group of beams associated with the non-serving cell, and the AI output corresponds to or originates from these beams (if the non-serving cell is included in group C); abbreviated as group A SN . - Beam group B S , where the beam group B S includes a group of beams associated with the serving cell, and its corresponding measurement result (e.g., L1-RSRP) needs to be used as AI input (if the serving cell is included in group D); abbreviated as group B S ; or - Beam group B NS , where the beam group B NS includes a group of beams associated with the non-serving cell, and its corresponding measurement result needs to be used as AI input (if the non-serving cell is included in group D); abbreviated as group B NS .

[0115] In some embodiments, the first device 110 can send, to the second device 120, first information (or an indication) about at least one of: a size of the group A S , a size of the group A NS , a size of the group B S , or a size of the group B NS . In some embodiments, the size of a group of beams associated with a candidate cell indicates a number of beams in the group of beams associated with the candidate cell.

[0116] Additionally, in some embodiments, the size includes a minimum size or (and) a maximum size supported by the first device 110 or associated with the ML model 115. In one embodiment, the maximum size of the group A S indicates a maximum number of beams that the first device 110 (or the model) can predict for a serving cell. In another embodiment, the minimum size of the group B S indicates a minimum number of beams needed by the first device 110 (or the ML model 115) to predict for a serving cell (i.e., beams that need to be measured for the serving cell).

[0117] In some embodiments, given that the group B S or the group B NS may be the same as, a subset of, or different from the group A S or the group A NS , the first device 110 can send, to the second device 120, information about a size of a new first group of beams and / or a size of a new second group of beams, where the new first group of beams indicates a union of the group A S and the group B S , and the new second group of beams indicates a union of the group A NS and the group B NS .

[0118] Additionally, in some embodiments, to enable the second device 120 to know which beams need to be configured, the first device 110 can determine, based on an ID of a beam measurement resource associated with a candidate cell configured by the second device 120, an indicator of a beam in a group of beams associated with the candidate cell. Then, the first device 110 can send, to the second device 120, information about at least one of: the indicator of the beam in the group A S , the indicator of the beam in the group A NS , the indicator of the beam in the group B S , or the indicator of the beam in the group B NS .

[0119] In this way, based on the above information sent by the first device 110, for each candidate cell that needs to be configured, the second device 120 can know how many (and which) beams need to be configured for measurement. Therefore, unnecessary measurement resource overhead can be saved.

[0120] In some embodiments, the first information can indicate a first type of measurement quantity associated with the output of the ML model 115 or the first group of candidate cells.

[0121] Alternatively or additionally, in some embodiments, the first information can indicate a second type of measurement quantity associated with the input of the ML model 115 or the second group of candidate cells.

[0122] In some embodiments, the first type of measurement quantity can be associated with one of: - one or more candidate cells associated with the output of the ML model 115 or included in the first group of candidate cells, - one or more beams associated with the output of the ML model 115 or included in a first group of beams associated with the output of the ML model 115 or the first group of candidate cells, - a serving cell included in the first group of candidate cells, or - at least one neighboring cell included in the first group of candidate cells.

[0123] In some embodiments, the second type of measurement quantity is associated with one of: - one or more candidate cells associated with the input of the ML model 115 or included in the second group of candidate cells, - one or more beams associated with the input of the ML model 115 or included in a second group of beams associated with the input of the ML model 115 or the second group of candidate cells, - a serving cell included in the second group of candidate cells, or - at least one neighboring cell included in the second group of candidate cells.

[0124] In some embodiments, the first type of measurement quantity or the second type of measurement quantity can be one of: RSRP, SINR, RSSI, or RSRQ.

[0125] In some embodiments, the first information can indicate at least one of: whether a first interference of a neighboring cell on a serving cell is needed, whether a second interference of the serving cell on the neighboring cell is needed, or whether a third interference of a neighboring cell on another neighboring cell is needed.

[0126] In some embodiments, the other neighboring cell can be a default candidate cell, or determined by the first device or the second device 120.

[0127] Alternatively or in addition, in some embodiments, the first information can indicate a first amount of the first interference, a second amount of the second interference, or a third amount of the third interference.

[0128] Alternatively or in addition, in some embodiments, the first information can indicate a cell identity of a candidate cell corresponding to the first interference, an identity of a candidate cell corresponding to the second interference, or an identity of a candidate cell corresponding to the third interference.

[0129] In some embodiments, the first information can indicate a number of candidate cells corresponding to a particular type of measurement quantity.

[0130] Alternatively or in addition, in some embodiments, the first information can indicate a cell identity of a candidate cell corresponding to a particular type of measurement quantity.

[0131] In some embodiments, the first information can indicate a number of beams corresponding to a particular type of measurement quantity.

[0132] Alternatively or in addition, in some embodiments, the first information can indicate a beam identity of a beam corresponding to a particular type of measurement quantity.

[0133] For better understanding, some example embodiments on how to indicate the measurement quantity related information are discussed below.

[0134] In some embodiments, the type of (beam) measurement quantity required in the AI input or (and) AI output (e.g., L1-RSRP, L1-SINR) will affect the configuration of the beam measurement resource. Specifically, if L1-RSRP of the serving cell is required, the second device 120 only needs to configure a CMR for the serving cell to measure the L1-RSRP. In contrast, if L1-RSRP of the serving cell and L1-SINR between the serving cell and a non-serving cell are required, the second device 120 can need to configure an IMR associated with the configured CMR to measure the L1-SINR between the serving cell and the non-serving cell.

[0135] In some embodiments, the first device 110 can send information on the type of beam measurement quantity (e.g., L1-RSRP, L1-SINR, L1-RSSI, L1-RSRQ) associated with group C, group D, group A S , group A NS , group B S , or group B NS .

[0136] In some embodiments, the first device 110 can send to the second device 120 first information (or indication) on at least one of the following types of beam measurement quantities: L1-RSRP, L1-SINR, L1-RSSI, and / or L1-RSRQ.

[0137] In some embodiments, if L1-SINR is indicated (or included), the first device 110 can send to the second device 120 first information on at least one of the following: - an indication of whether the interference of a non-serving cell to a serving cell is needed; - an indication of whether the interference of a serving cell to a non-serving cell is needed. In other words, whether L1-SINR between the serving cell and the non-serving cell is needed; - an indication of whether the interference of a non-serving cell to another non-serving cell (e.g., a specific or predefined non-serving cell) is needed. In other words, whether L1-SINR between the non-serving cell and the other non-serving cell is needed.

[0138] In some embodiments, information on an indicator of a specific or predefined non-serving cell can be sent to the second device 120.

[0139] In some embodiments, the first device 110 can send to the second device 120 first information on a number indicating how many measurement quantities (e.g., L1-RSRP, L1-SINR, L1-RSSI, L1-RSRQ) are needed.

[0140] In some embodiments, if L1-RSRP (or L1-SINR / L1-RSSI / L1-RSRQ) is indicated, the first device 110 can send to the second device 120 information on at least one of the following: a number indicating how many candidate cells (or non-serving cells) for which its corresponding L1-RSRP (or L1-SINR / L1-RSSI / L1-RSRQ) is needed to be calculated, or a number indicating how many beams in a candidate cell for which its corresponding L1-RSRP (or L1-SINR / L1-RSSI / L1-RSRQ) is needed to be calculated.

[0141] In some embodiments, the first device 110 can send to the second device 120 first information on an indicator of a candidate cell (or non-serving cell) for which its corresponding L1-RSRP is needed to be calculated, and / or an indicator of a beam in a candidate cell for which its corresponding L1-RSRP is needed to be calculated.

[0142] In some embodiments, if L1-SINR is indicated, the first device 110 can send to the second device 120 information about: - a number indicating how many interferences (i.e., non-serving cell to serving cell interference) are needed, in other words, how many non-serving cells need to be calculated for non-serving cell to serving cell interference; - a number indicating how many interferences (i.e., serving cell to non-serving cell interference) are needed; - a number indicating how many interferences (i.e., non-serving cell to another non-serving cell interference) are needed.

[0143] In some embodiments, the first device 110 can send to the second device 120 information about at least one of: - an indicator of non-serving cells that need to be calculated for non-serving cell to serving cell interference; - an indicator of non-serving cells that need to be calculated for serving cell to non-serving cell interference; - an indicator of non-serving cells that need to be calculated for non-serving cell to another non-serving cell interference.

[0144] In some embodiments, the above-mentioned candidate cells belong to group C or group D, and the above-mentioned beams belong to group A S , group A NS , group B S , or group B NS .

[0145] In this way, based on the above-mentioned first information sent by the first device 110, the second device 120 can know how to configure the beam measurement resources, such as channel measurement resources (CMR), interference measurement resources (IMR), etc., needed for first device 110 side data collection.

[0146] In some embodiments, the first information can indicate at least one period between two adjacent input samples or two adjacent output samples.

[0147] In some embodiments, the period can be indicated by one of: an absolute value of a time length; a multiple of a specific time length, the specific time length being one of: a default time length, a measurement resource configuration period, or a measurement period.

[0148] In some embodiments, the at least one period can include: a first period corresponding to a serving cell of the first device 110, and a second period corresponding to at least one neighboring cell of the first device 110.

[0149] In some embodiments, the period can be associated with at least one of the following: one or more candidate cells, one or more beams, one or more types of measurement quantities, or one or more types of interference.

[0150] For better understanding, some example embodiments on how to indicate the at least one period are discussed below.

[0151] In some embodiments, the first device 110 can send to the second device 120 information about at least one timestamp associated with group C, group D, group A S , group A NS , group B S , or group B NS .

[0152] In some embodiments, a timestamp can refer to a time interval between any two (contiguous in time domain) measurement (or prediction) data samples used as AI input (or AI output).

[0153] In some embodiments, one timestamp can be associated with one candidate cell or a group of candidate cells or all candidate cells. In other words, multiple candidate cells can be associated with the same timestamp or different timestamps.

[0154] Reference is now made to Figure 3 , which illustrates example blocks 300 of different time periods. In Figure 3 , the at least one timestamp can include at least one of a first timestamp (period #1 in Figure 3 ) or a second timestamp (period #2 in Figure 3 ), where the first timestamp is associated with a serving cell and the second timestamp is associated with a non-serving cell.

[0155] In some embodiments, in addition to candidate cells, a timestamp can be associated with beams or (and) beam measurement quantities (e.g., L1-RSRP, L1-SINR, L1-RSSI, L1-RSRQ). Specifically, one timestamp can be associated with one beam in a candidate cell or a group of beams in a candidate cell or all beams in a candidate cell.

[0156] In some embodiments, for a timestamp associated with L1-SINR, the timestamp can be associated with at least one of the following: non-serving cell to serving cell interference, serving cell to non-serving cell interference, or non-serving cell to another non-serving cell interference.

[0157] In some embodiments, a timestamp can be associated with at least one of the following: candidate cells, beams, or specific (beam) measurement quantities.

[0158] In some embodiments, the timestamp can be indicated by a value in units of seconds, milliseconds, frames, subframes, slots, or symbols by the first device 110.

[0159] In some embodiments, the timestamp can be indicated by a value indicating a multiple of a certain time period. In addition, in some embodiments, the certain time period (e.g., T SSB_measurement_period_intra , T SSB_measurement_period_inter ) can be determined based on a periodicity of a beam measurement resource (e.g., periodic / semi-persistent CSI-RS resource, SSB) configured by the second device 120 or a measurement period (for intra / inter frequency measurement) configured by the second device 120.

[0160] In some embodiments, the above-mentioned candidate cells belong to group C or group D, and the above-mentioned beams belong to group A S , group A NS , group B S , or group B NS .

[0161] In this way, based on the above-mentioned information sent by the first device 110, the second device 120 can understand how to configure the measurement resources required for the first device 110 side data collection, e.g., the periodicity of the measurement resources.

[0162] In some embodiments, the first information can indicate at least one of: - whether the first device 110 or the ML model 115 supports input samples related to intra-frequency, - whether the first group of candidate cells supports intra-frequency, - whether the first device 110 or the ML model 115 supports input samples related to inter-frequency, - whether the first group of candidate cells supports inter-frequency.

[0163] In addition or other than this, in some embodiments, the first information can indicate: - whether the first device 110 or the ML model 115 supports input samples related to intra-frequency with a certain type of measurement quantity, - whether the first group of candidate cells supports intra-frequency with a certain type of measurement quantity, - whether the first device 110 or the ML model 115 supports input samples related to inter-frequency with a certain type of measurement quantity, - whether the first group of candidate cells supports inter-frequency with a certain type of measurement quantity.

[0164] In addition or other than this, in some embodiments, the first information can indicate: - whether the first device 110 or the ML model 115 supports output samples related to intra-frequency, - whether the second set of candidate cells supports intra-frequency, - whether the first device 110 or the ML model 115 supports output samples related to inter-frequency, - whether the second set of candidate cells supports inter-frequency.

[0165] Additionally or in addition, in some embodiments, the first information can indicate: - whether the first device 110 or the ML model 115 supports output samples related to intra-frequency with a specific type of measurement quantity, - whether the second set of candidate cells supports intra-frequency with a specific type of measurement quantity, - whether the first device 110 or the ML model 115 supports output samples related to inter-frequency with a specific type of measurement quantity, - whether the second set of candidate cells supports inter-frequency with a specific type of measurement quantity.

[0166] Additionally or in addition, in some embodiments, the first information can indicate: a maximum number of candidate cells associated with the same frequency range, or a maximum number of neighboring cells associated with the same frequency range.

[0167] For better understanding, some example embodiments on how to indicate the frequency measurement related information are discussed below.

[0168] In some embodiments, whether the first device 110 (or the ML model 115) supports intra-frequency measurement (or prediction) or inter-frequency measurement (or prediction) will affect the configuration of measurement resources. Specifically, if the ML model 115 does not support inter-frequency measurement (or prediction), and if the second device 120 configures measurement resources for candidate cells in different frequency ranges, obviously, a feasible and reasonable resource allocation will occur.

[0169] In some embodiments, the first device 110 can send the first information (or an indication indicating the following) to the second device 120 about at least one of: whether group D supports intra-frequency, whether group D supports inter-frequency, whether group C supports intra-frequency, or whether group C supports inter-frequency.

[0170] In some embodiments, “group D supports intra-frequency” can be equivalent to “supports intra-frequency measurement”, which means that the candidate cells (or non-serving cells) applied to the AI input (or measurement) are in the same frequency range as the serving cell.

[0171] In some embodiments, “candidate cells applied to the AI input (or AI output)” refers to the candidate cells whose measurement results or / and indicators are used as one of the AI inputs (or whose indicators or / and corresponding predicted measurement quantities are used as one of the AI outputs).

[0172] In some embodiments, “Group D supports inter-frequency measurement” can be equivalent to “supports inter-frequency measurement”, which means that the candidate cell (or non-serving cell) applied to the AI input (or measurement) is in a different frequency range from the serving cell.

[0173] In some embodiments, “Group C supports intra-frequency” can be equivalent to “supports intra-frequency prediction”, which means that the candidate cell (or non-serving cell) applied to the AI output (or prediction) is in the same frequency range as the serving cell.

[0174] In some embodiments, “Group C supports inter-frequency” can be equivalent to “supports inter-frequency prediction”, which means that the candidate cell (or non-serving cell) applied to the AI output (or prediction) is in a different frequency range from the serving cell.

[0175] In some embodiments, the first device 110 can send the second device 120 first information about at least one of: - a number indicating how many candidate cells can be in the same frequency range (or different frequency range); - a number indicating how many non-serving cells can be in the same frequency range as the serving cell (or in a different frequency range from the serving cell).

[0176] In some embodiments, the serving cell or the non-serving cell can be a candidate cell applied to the AI input (or AI output).

[0177] In some embodiments, the first device 110 can send the second device 120 first information about at least one of: - an indication of whether to support frequency L1-RSRP (for Group D or / and Group C); - an indication of whether to support inter-frequency L1-RSRP (for Group D or / and Group C); - an indication of whether to support frequency L1-SINR (for Group D or / and Group C); - an indication of whether to support inter-frequency L1-SINR (for Group D or / and Group C).

[0178] In some embodiments, “frequency L1-RSRP or L1-SINR” means that the candidate cell in which the beam measurement resource for calculating L1-RSRP or L1-SINR is located (or configured) is in the same frequency range as the serving cell, or the candidate cell is the serving cell.

[0179] In some embodiments, “inter-frequency L1-RSRP or L1-SINR” means that the candidate cell on which (or in which) the beam measurement resource for calculating L1-RSRP or L1-SINR is located (or configured) is in a different frequency range from the serving cell.

[0180] In some embodiments, the above-mentioned candidate cell belongs to group C or group D, and the above-mentioned beam belongs to group A S , group A NS , group B S , or group B NS .

[0181] In this way, based on the above-mentioned information sent by the first device 110, the second device 120 can know how many (and which) candidate cells need to be configured for measurement.

[0182] In some embodiments, the first information can be sent via at least one of the following: RRC signaling, MAC CE, UCI, user assistance information (UAI), measurement report, user equipment (UE) radio access capability parameter, or channel state information (CSI) report.

[0183] In one embodiment, the first information can be carried by one or more RRC messages (e.g., UE radio access capability parameter, UAI, or measurement report).

[0184] In another embodiment, the first device 110 can send a request (e.g., SR) dedicated to (or designated for) data collection. After receiving the request, the second device 120 can schedule uplink resources (e.g., PUCCH / PUSCH resources) to allow the first device 110 to send the above-mentioned first information, which can be carried by a MAC CE.

[0185] In another embodiment, the first device 110 can send the first information by using a CSI report that can be included in UCI.

[0186] According to the above-mentioned process, the first information related to the ML model deployed at the first device 110 can be sent to the second device 120, and the second device 120 can accordingly allocate appropriate resources for the first device 110, so that the first device 110 can collect data to ensure that the ML is running normally.

[0187] Example method Figure 4 A flowchart of a communication method 400 implemented at a first device according to some embodiments of the present disclosure is illustrated. For the purpose of discussion, the method 400 will be described from the perspective of the first device 110 in Figure 1A .

[0188] At block 410, the first device can determine first information related to a machine learning (ML) model deployed at the first device, the first information indicating at least one of: a first set of candidate cells associated with an output of the ML model, or a second set of candidate cells associated with an input of the ML model.

[0189] At block 420, the first device can transmit the first information to a second device.

[0190] In some example implementations, the second set of candidate cells can be a portion of the first set of candidate cells, the portion of the second set of candidate cells can be the same as the portion of the first set of candidate cells, the second set of candidate cells can be the same as the first set of candidate cells, or the second set of candidate cells can be different from the first set of candidate cells.

[0191] In some example implementations, the first information can indicate at least one of the first set of candidate cells and the second set of candidate cells by at least one of: a first number of candidate cells included in the first set of candidate cells, a first set of cell identities corresponding to the first set of candidate cells, a second number of candidate cells included in the second set of candidate cells, a second set of cell identities corresponding to the second set of candidate cells, a union of the first set of candidate cells and the second set of candidate cells, a third number of candidate cells included in the union, a first indication indicating whether a serving cell of the first device is included in the first set of candidate cells, a second indication indicating whether the serving cell is included in the second set of candidate cells, a third indication whether a neighbor cell of the first device is included in the first set of candidate cells, a fourth indication whether the neighbor cell is included in the second set of candidate cells, a first number of neighbor cells included in the first set of candidate cells, or a second number of neighbor cells included in the second set of candidate cells.

[0192] In some example implementations, the first number of candidate cells can include at least one of a maximum number of candidate cells or a minimum number of candidate cells included in the first set of candidate cells supported by the first device or the ML model, the second number of candidate cells can include at least one of a maximum number of candidate cells or a minimum number of candidate cells included in the second set of candidate cells supported by the first device or the ML model, the first number of neighbor cells can include at least one of a maximum number of neighbor cells or a minimum number of neighbor cells included in the first set of candidate cells supported by the first device or the ML model, and the second number of neighbor cells can include at least one of a maximum number of neighbor cells or a minimum number of neighbor cells included in the second set of candidate cells supported by the first device or the ML model.

[0193] In some example embodiments, the first information can further indicate at least one of: at least one first set of beams associated with the output of the ML model or the first set of candidate cells, at least one second set of beams associated with the input of the ML model or the second set of candidate cells, or a union of the one or more first set of beams and the one or more second set of beams.

[0194] In some example embodiments, the beams included in the at least one second set of beams can be a subset of the beams included in the at least one first set of beams, the beams included in the at least one second set of beams can be a superset of the beams included in the at least one first set of beams, the beams included in the at least one second set of beams can be the same as the beams included in the at least one first set of beams, or the beams included in the at least one second set of beams can be different from the beams included in the at least one first set of beams.

[0195] In some example embodiments, the at least one first set of beams can include at least one of: a set of beams corresponding to a serving cell included in the first set of candidate cells, or a set of beams corresponding to at least one neighboring cell included in the first set of candidate cells, and wherein the at least one second set of beams includes at least one of: a set of beams corresponding to a serving cell included in the second set of candidate cells, or a set of beams corresponding to at least one neighboring cell included in the second set of candidate cells.

[0196] In some example embodiments, the first information can indicate at least one of the first set of beams and the second set of beams by at least one of: a first number of beams included in the first set of beams, a first set of beam identifications corresponding to the first set of beams, a second number of beams included in the second set of beams, or a second set of beam identifications corresponding to the second set of beams.

[0197] In some example embodiments, the first number of beams can include at least one of a maximum number of beams or a minimum number of beams included in the first set of beams supported by the first device or the ML model, and wherein the second number of beams includes at least one of a minimum number of beams or a maximum number of beams in the second set of beams supported by the first device or the ML model.

[0198] In some example embodiments, the first information can further indicate at least one of: a first type of measurement quantity associated with the output of the ML model or the first set of candidate cells, or a second type of measurement quantity associated with the input of the ML model or the second set of candidate cells.

[0199] In some example embodiments, the first type of measurement quantity can be associated with one of: one or more candidate cells associated with or included in the output of the ML model, one or more beams associated with or included in a first set of beams associated with the output of the ML model or the first set of candidate cells, a serving cell associated with or included in the first set of candidate cells, or at least one neighboring cell associated with or included in the first set of candidate cells, and wherein the second type of measurement quantity can be associated with one of: one or more candidate cells associated with or included in the input of the ML model, one or more beams associated with or included in a second set of beams associated with the input of the ML model or the second set of candidate cells, a serving cell associated with or included in the second set of candidate cells, or at least one neighboring cell associated with or included in the second set of candidate cells.

[0200] In some example embodiments, the first type of measurement quantity or the second type of measurement quantity can be one of: a reference signal received power (RSRP), a signal to interference plus noise ratio (SINR), a received signal strength indicator (RSSI), or a reference signal received quality (RSRQ).

[0201] In some example embodiments, the first information can further indicate at least one of: whether a first interference of a neighboring cell to a serving cell is needed, a first amount of the first interference, a cell identification of a candidate cell corresponding to the first interference, whether a second interference of the serving cell to a neighboring cell is needed, a second amount of the second interference, an identification of a candidate cell corresponding to the second interference, whether a third interference of a neighboring cell to another neighboring cell is needed, a third amount of the third interference, or an identification of a candidate cell corresponding to the third interference.

[0202] In some example embodiments, the first information can further indicate at least one of: a number of candidate cells corresponding to a particular type of measurement quantity, a cell identification of a candidate cell corresponding to a particular type of measurement quantity, a number of beams corresponding to a particular type of measurement quantity, or a beam identification of a beam corresponding to a particular type of measurement quantity.

[0203] In some example embodiments, the first information can further indicate at least one period between two adjacent input samples or two adjacent output samples.

[0204] In some example embodiments, the period can be associated with at least one of: one or more candidate cells, one or more beams, one or more types of measurement quantities, or one or more types of interference.

[0205] In some example embodiments, the at least one period can comprise: a first period corresponding to a serving cell of the first device, and a second period corresponding to at least one neighboring cell of the first device.

[0206] In some example embodiments, the period can be indicated by one of: an absolute value of a time length; a multiple of a specific time length, the specific time length being one of: a default time length, a measurement resource configuration period, or a measurement period.

[0207] In some example embodiments, the first information can further indicate at least one of: whether the first device or the ML model supports input samples related to intra-frequency, whether the first group of candidate cells supports intra-frequency, whether the first device or the ML model supports input samples related to inter-frequency with a specific type of measurement quantity, whether the first group of candidate cells supports intra-frequency with the specific type of measurement quantity, whether the first device or the ML model supports input samples related to inter-frequency, whether the first group of candidate cells supports inter-frequency, whether the first device or the ML model supports input samples related to inter-frequency with a specific type of measurement quantity, whether the first group of candidate cells supports inter-frequency with the specific type of measurement quantity, whether the first device or the ML model supports output samples related to intra-frequency, whether the second group of candidate cells supports intra-frequency, whether the first device or the ML model supports output samples related to intra-frequency with a specific type of measurement quantity, whether the second group of candidate cells supports intra-frequency with the specific type of measurement quantity, whether the first device or the ML model supports output samples related to inter-frequency, whether the second group of candidate cells supports inter-frequency, whether the first device or the ML model supports output samples related to inter-frequency with a specific type of measurement quantity, whether the second group of candidate cells supports inter-frequency with the specific type of measurement quantity, a maximum number of candidate cells associated with a same frequency range, or a maximum number of neighboring cells associated with a same frequency range.

[0208] In some example embodiments, the first information can be transmitted via at least one of: radio resource control (RRC) signaling, medium access control (MAC) control element (CE), uplink control information (UCI), user assistance information (UAI), measurement report, user equipment (UE) radio access capability parameter, or channel state information (CSI) report.

[0209] In some example embodiments, the other neighboring cell can be a default candidate cell, or determined by the first or second device.

[0210] In some example embodiments, prior to transmitting the first information, the first device can transmit, to the second device, a request for resources for transmitting the first information.

[0211] In some example embodiments, the first device can receive, from the second device, second information indicating measurement resources to be used by the first device, the measurement resources determined by the second device based on the first information.

[0212] In some example embodiments, the first device can be a terminal device, and the second device can be a network device.

[0213] Figure 5 A flowchart of a method 500 of communication implemented at a second device is illustrated in accordance with some embodiments of the present disclosure. For purposes of discussion, the method 500 will be described from the perspective of the second device 120 in FIG. 1. Figure 1A

[0214] At block 510, the second device can receive, from a first device that deploys a machine learning (ML) model, first information related to the ML model, the first information indicating at least one of: a first set of candidate cells associated with an output of the ML model, or a second set of candidate cells associated with an input of the ML model.

[0215] Optionally, at block 520, the second device can determine, based on the first information, measurement resources to be used by the first device.

[0216] Optionally, at block 530, the second device can send, to the first device, second information indicating the measurement resources.

[0217] In some example embodiments, prior to receiving the first information, the second device can receive a request for resources for sending the first information to the second device.

[0218] In some example embodiments, the second set of candidate cells can be a part of the first set of candidate cells, a part of the second set of candidate cells can be the same as a part of the first set of candidate cells, the second set of candidate cells can be the same as the first set of candidate cells, or the second set of candidate cells can be different from the first set of candidate cells.

[0219] ​In some example embodiments, the first information can indicate at least one of the first set of candidate cells and the second set of candidate cells by at least one of a first number of candidate cells included in the first set of candidate cells, a first set of cell identities corresponding to the first set of candidate cells, a second number of candidate cells included in the second set of candidate cells, a second set of cell identities corresponding to the second set of candidate cells, a union of the first set of candidate cells and the second set of candidate cells, a third number of candidate cells included in the union, a first indication indicating whether a serving cell of the first device is included in the first set of candidate cells, a second indication indicating whether the serving cell is included in the second set of candidate cells, a third indication whether a neighboring cell of the first device is included in the first set of candidate cells, a fourth indication whether the neighboring cell is included in the second set of candidate cells, a first number of neighboring cells included in the first set of candidate cells, or a second number of neighboring cells included in the second set of candidate cells.

[0220] In some example embodiments, the first number of candidate cells can include at least one of a maximum number of candidate cells or a minimum number of candidate cells included in the first set of candidate cells supported by the first device or the ML model, the second number of candidate cells can include at least one of a maximum number of candidate cells or a minimum number of candidate cells included in the second set of candidate cells supported by the first device or the ML model, the first number of neighboring cells includes at least one of a maximum number of neighboring cells or a minimum number of neighboring cells included in the first set of candidate cells supported by the first device or the ML model, and the second number of neighboring cells includes at least one of a maximum number of neighboring cells or a minimum number of neighboring cells included in the second set of candidate cells supported by the first device or the ML model.

[0221] In some example embodiments, the first information can further indicate at least one of at least one first set of beams associated with the output of the ML model or the first set of candidate cells, at least one second set of beams associated with the input of the ML model or the second set of candidate cells, or a union of the one or more first set of beams and the one or more second set of beams.

[0222] In some example embodiments, the beams included in the at least one second set of beams can be a part of the beams included in the at least one first set of beams, the part of the beams included in the at least one second set of beams can be a part of the beams included in the at least one first set of beams, the beams included in the at least one second set of beams can be the same as the beams included in the at least one first set of beams, or the beams included in the at least one second set of beams can be different from the beams included in the at least one first set of beams.

[0223] In some example embodiments, the at least one first group of beams can include at least one of a group of beams corresponding to a serving cell included in the first group of candidate cells or a group of beams corresponding to at least one neighboring cell included in the first group of candidate cells, and wherein the at least one second group of beams can include at least one of a group of beams corresponding to a serving cell included in the second group of candidate cells or a group of beams corresponding to at least one neighboring cell included in the second group of candidate cells.

[0224] In some example embodiments, the first information can indicate at least one of the first group of beams or the second group of beams by at least one of a first number of beams included in the first group of beams, a first group of beam identifications corresponding to the first group of beams, a second number of beams included in the second group of beams, or a second group of beam identifications corresponding to the second group of beams.

[0225] In some example embodiments, the first number of beams can include at least one of a maximum number of beams or a minimum number of beams included in the first group of beams supported by the first device or the ML model, and wherein the second number of beams includes at least one of a minimum number of beams or a maximum number of beams in the second group of beams supported by the first device or the ML model.

[0226] In some example embodiments, the first information can further indicate at least one of a first type of measurement quantity associated with the output of the ML model or the first group of candidate cells or a second type of measurement quantity associated with the input of the ML model or the second group of candidate cells.

[0227] In some example embodiments, the first type of measurement quantity can be associated with one of one or more candidate cells associated with the output of the ML model or included in the first group of candidate cells, one or more beams associated with the output of the ML model or included in the first group of beams associated with the output of the ML model or the first group of candidate cells, a serving cell associated with the output of the ML model or included in the first group of candidate cells, or at least one neighboring cell associated with the output of the ML model or included in the first group of candidate cells, and wherein the second type of measurement quantity is associated with one of one or more candidate cells associated with the input of the ML model or included in the second group of candidate cells, one or more beams associated with the input of the ML model or included in the second group of beams associated with the input of the ML model or the first group of candidate cells, a serving cell associated with the input of the ML model or included in the second group of candidate cells, or at least one neighboring cell associated with the input of the ML model or included in the second group of candidate cells.

[0228] In some example embodiments, the first type of measurement quantity or the second type of measurement quantity can be one of: a reference signal received power (RSRP), a signal to interference plus noise ratio (SINR), a received signal strength indicator (RSSI), or a reference signal received quality (RSRQ).

[0229] In some example embodiments, the first information can further indicate at least one of: whether a first interference of a neighbor cell to a serving cell is needed, a first amount of the first interference, a cell identification of a candidate cell corresponding to the first interference, whether a second interference of the serving cell to a neighbor cell is needed, a second amount of the second interference, an identification of a candidate cell corresponding to the second interference, whether a third interference of the neighbor cell to another neighbor cell is needed, a third amount of the third interference, or an identification of a candidate cell corresponding to the third interference.

[0230] In some example embodiments, the first information can further indicate at least one of: a number of candidate cells corresponding to a particular type of measurement quantity, a cell identification of a candidate cell corresponding to a particular type of measurement quantity, a number of beams corresponding to a particular type of measurement quantity, or a beam identification of a beam corresponding to a particular type of measurement quantity.

[0231] In some example embodiments, the first information can further indicate at least one period between two adjacent input samples or two adjacent output samples.

[0232] In some example embodiments, the period can be associated with at least one of: one or more candidate cells, one or more beams, one or more types of measurement quantities, or one or more types of interference.

[0233] In some example embodiments, the at least one period can comprise: a first period corresponding to a serving cell of the first device, and a second period corresponding to at least one neighbor cell of the first device.

[0234] In some example embodiments, the period can be indicated by one of: an absolute value of a time length; a multiple of a particular time length, the particular time length being one of: a default time length, a measurement resource configuration period, or a measurement period.

[0235] In some example embodiments, the first information can further indicate at least one of whether the first device or the ML model supports input samples related to an intra- frequency, whether the first set of candidate cells supports intra-frequencies, whether the first device or the ML model supports input samples related to an inter- frequency with a specific type of measurement quantity, whether the first set of candidate cells supports intra-frequencies with the specific type of measurement quantity, whether the first device or the ML model supports input samples related to an inter- frequency, whether the first set of candidate cells supports inter-frequencies, whether the first device or the ML model supports input samples related to an inter- frequency with a specific type of measurement quantity, whether the first set of candidate cells supports inter-frequencies with the specific type of measurement quantity, whether the first device or the ML model supports output samples related to an intra- frequency, whether the second set of candidate cells supports intra-frequencies, whether the first device or the ML model supports output samples related to an intra- frequency with a specific type of measurement quantity, whether the second set of candidate cells supports intra-frequencies with the specific type of measurement quantity, whether the first device or the ML model supports output samples related to an inter- frequency, whether the second set of candidate cells supports inter-frequencies, whether the first device or the ML model supports output samples related to an inter- frequency with a specific type of measurement quantity, whether the second set of candidate cells supports inter-frequencies with the specific type of measurement quantity, a maximum number of candidate cells associated with a same frequency range, or a maximum number of neighboring cells associated with a same frequency range.

[0236] In some example embodiments, the first information can be transmitted via at least one of radio resource control (RRC) signaling, medium access control (MAC) control element (CE), uplink control information (UCI), user assistance information (UAI), a measurement report, a user equipment (UE) radio access capability parameter, or a channel state information (CSI) report.

[0237] In some example embodiments, the other neighboring cell can be a default candidate cell or determined by the first or second device.

[0238] In some example embodiments, the first device can be a terminal device and the second device can be a network device.

[0239] Example devices and apparatuses Figure 6 is a simplified block diagram of a device 600 suitable for implementing embodiments of the present disclosure. The device 600 can be considered another example implementation of any of the devices as shown in Figure 1A and Figure 1B Thus, the device 600 can be implemented at the first device 110 or the second device 120, or as at least a part of the first device or the second device.

[0240] As shown, the device 600 includes a processor 610, a memory 620 coupled to the processor 610, a suitable transceiver 640 coupled to the processor 610, and a communication interface coupled to the transceiver 640. The memory 610 stores at least a portion of a program 630. The transceiver 640 can be used for bi-directional communication or unidirectional communication according to needs. The transceiver 640 can include at least one of a transmitter 642 and a receiver 644. The transmitter 642 and the receiver 644 can be functional modules or physical entities. The transceiver 640 has at least one antenna to facilitate communication, but in fact the access node mentioned in the present application can have several antennas. The communication interface can represent any interface necessary for communication with other network elements, such as an X2 / Xn interface for bi-directional communication between eNBs / gNBs, an S1 / NG interface for communication between a Mobility Management Entity (MME) / Access and Mobility Management Function (AMF) / SGW / UPF and an eNB / gNB, an Un interface for communication between an eNB / gNB and a relay node (RN), or a Uu interface for communication between an eNB / gNB and a terminal device.

[0241] It is assumed that the program 630 includes program instructions that, when executed by the associated processor 610, enable the device 600 to operate in accordance with the embodiments of the present disclosure, as discussed herein with reference to FIGS. 1 to Figure 5 The embodiments discussed herein can be implemented by computer software executable by the processor 610 of the device 600, or by hardware, or by a combination of software and hardware. The processor 610 can be configured to implement various embodiments of the present disclosure. Furthermore, the combination of the processor 610 and the memory 620 can form a processing means 650 suitable to implement various embodiments of the present disclosure.

[0242] Memory 620 can be of any type suitable to the local technical network, and can be implemented using any suitable data storage technology, such as nonvolatile computer-readable storage media, semiconductor-based memory devices, magnetic memory devices and systems, optical memory devices and systems, fixed memory and removable memory, as non-limiting examples. Although only one memory 620 is shown in device 600, there can be several physically different memory modules in device 600. Processor 610 can be of any type suitable to the local technical network, and can include one or more of general purpose computers, special purpose computers, microprocessors, digital signal processors (DSPs), and processors based on multi-core processor architectures, as non-limiting examples. Device 600 can have multiple processors such as special-purpose integrated circuit chips that are subject to clocks that synchronize the master processor in time.

[0243] According to embodiments of the disclosure, there is provided a first device comprising circuitry. The circuitry is configured to determine first information related to a machine learning (ML) model deployed at the first device, the first information indicating at least one of: a first set of candidate cells associated with an output of the ML model, or a second set of candidate cells associated with an input of the ML model; and transmit the first information to a second device. According to embodiments of the disclosure, the circuitry can be configured to perform any of the methods implemented by the first device as discussed above.

[0244] According to embodiments of the disclosure, there is provided a second device comprising circuitry. The circuitry is configured to receive, from a first device having a machine learning (ML) model deployed, first information related to the ML model, the first information indicating at least one of: a first set of candidate cells associated with an output of the ML model, or a second set of candidate cells associated with an input of the ML model. According to embodiments of the disclosure, the circuitry can be configured to perform any of the methods implemented by the second device as discussed above.

[0245] The term “circuitry” as used herein can refer to hardware and / or a combination of hardware and software. For example, a circuit can be a combination of analog and / or digital hardware circuitry with software / firmware. As another example, a circuit can be any portion of a hardware processor, including a digital signal processor, software, and memory that work together to cause an apparatus, such as a terminal device or a network device, to perform various functions. In yet another example, a circuit can be a hardware circuit and / or a processor, such as a microprocessor or a portion of a microprocessor, that requires software / firmware to operate but that does not have software present when not needed to operate. The term “circuitry” as used herein also encompasses implementation in only hardware circuitry or a portion of hardware circuitry and its (or their) accompanying software and / or firmware.

[0246] In view of the above, the embodiments of the present disclosure provide the following aspects.

[0247] In one aspect, a first device is proposed, the first device comprising: a processor configured to cause the first device to: determine first information related to a machine learning (ML) model deployed at the first device, the first information indicating at least one of: a first set of candidate cells associated with an output of the ML model, or a second set of candidate cells associated with an input of the ML model; and transmit the first information to a second device.

[0248] In some embodiments, the second set of candidate cells is a part of the first set of candidate cells, the second set of candidate cells has a same part as the first set of candidate cells, the second set of candidate cells is the same as the first set of candidate cells, or the second set of candidate cells is different from the first set of candidate cells.

[0249] In some embodiments, the first information indicates at least one of the first set of candidate cells and the second set of candidate cells by at least one of: a first number of candidate cells included in the first set of candidate cells, a first set of cell identities corresponding to the first set of candidate cells, a second number of candidate cells included in the second set of candidate cells, a second set of cell identities corresponding to the second set of candidate cells, a union of the first set of candidate cells and the second set of candidate cells, a third number of candidate cells included in the union, a first indication indicating whether a serving cell of the first device is included in the first set of candidate cells, a second indication indicating whether the serving cell is included in the second set of candidate cells, a third indication whether a neighboring cell of the first device is included in the first set of candidate cells, a fourth indication whether the neighboring cell is included in the second set of candidate cells, a first number of neighboring cells included in the first set of candidate cells, or a second number of neighboring cells included in the second set of candidate cells.

[0250] In some embodiments, the first number of candidate cells includes at least one of a maximum number or a minimum number of candidate cells included in a first set of candidate cells supported by the first device or the ML model, the second number of candidate cells includes at least one of a maximum number or a minimum number of candidate cells included in a second set of candidate cells supported by the first device or the ML model, the first number of neighbor cells includes at least one of a maximum number or a minimum number of neighbor cells included in the first set of candidate cells supported by the first device or the ML model, and the second number of neighbor cells includes at least one of a maximum number or a minimum number of neighbor cells included in the second set of candidate cells supported by the first device or the ML model.

[0251] In some embodiments, the first information further indicates at least one of: at least one first set of beams associated with the output of the ML model or the first set of candidate cells, at least one second set of beams associated with the input of the ML model or the second set of candidate cells, or a union of the one or more first set of beams and the one or more second set of beams.

[0252] In some embodiments, the beams included in the at least one second set of beams are a portion of the beams included in the at least one first set of beams, the beams included in the at least one second set of beams are a different portion of the beams included in the at least one first set of beams, the beams included in the at least one second set of beams are the same as the beams included in the at least one first set of beams, or the beams included in the at least one second set of beams are different from the beams included in the at least one first set of beams.

[0253] In some embodiments, the at least one first set of beams includes at least one of: a set of beams corresponding to a serving cell included in the first set of candidate cells, or a set of beams corresponding to at least one neighbor cell included in the first set of candidate cells, and wherein the at least one second set of beams includes at least one of: a set of beams corresponding to a serving cell included in the second set of candidate cells, or a set of beams corresponding to at least one neighbor cell included in the second set of candidate cells.

[0254] In some embodiments, the first information indicates at least one of the first set of beams and the second set of beams by at least one of: a first number of beams included in the first set of beams, a first set of beam identifications corresponding to the first set of beams, a second number of beams included in the second set of beams, or a second set of beam identifications corresponding to the second set of beams.

[0255] In some embodiments, the first number of beams includes at least one of a maximum number of beams or a minimum number of beams included in a first set of beams supported by the first device or the ML model, and wherein the second number of beams includes at least one of a minimum number of beams or a maximum number of beams in a second set of beams supported by the first device or the ML model.

[0256] In some embodiments, the first information further indicates at least one of: a first type of measurement quantity associated with the output of the ML model or the first set of candidate cells, or a second type of measurement quantity associated with the input of the ML model or the second set of candidate cells.

[0257] In some embodiments, the first type of measurement quantity is associated with one of: one or more candidate cells associated with the output of the ML model or included in the first set of candidate cells, one or more beams associated with the output of the ML model or included in a first set of beams associated with the output of the ML model or the first set of candidate cells, a serving cell associated with the output of the ML model or included in the first set of candidate cells, or at least one neighboring cell associated with the output of the ML model or included in the first set of candidate cells, and wherein the second type of measurement quantity is associated with one of: one or more candidate cells associated with the input of the ML model or included in the second set of candidate cells, one or more beams associated with the input of the ML model or included in a second set of beams associated with the input of the ML model or the second set of candidate cells, a serving cell associated with the input of the ML model or included in the second set of candidate cells, or at least one neighboring cell associated with the input of the ML model or included in the second set of candidate cells.

[0258] In some embodiments, the first type of measurement quantity or the second type of measurement quantity is one of: a reference signal received power (RSRP), a signal to interference plus noise ratio (SINR), a received signal strength indicator (RSSI), or a reference signal received quality (RSRQ).

[0259] In some embodiments, the first information further indicates at least one of: whether a first interference of a neighboring cell to a serving cell is needed, a first amount of the first interference, a cell identification of a candidate cell corresponding to the first interference, whether a second interference of the serving cell to a neighboring cell is needed, a second amount of the second interference, an identification of a candidate cell corresponding to the second interference, whether a third interference of a neighboring cell to another neighboring cell is needed, a third amount of the third interference, or an identification of a candidate cell corresponding to the third interference.

[0260] In some embodiments, the first information further indicates at least one of: a number of candidate cells corresponding to a particular type of measurement quantity, a cell identification of a candidate cell corresponding to a particular type of measurement quantity, a number of beams corresponding to a particular type of measurement quantity, or a beam identification of a beam corresponding to a particular type of measurement quantity.

[0261] In some embodiments, the first information further indicates at least one period between two adjacent input samples or two adjacent output samples.

[0262] In some embodiments, the period is associated with at least one of: one or more candidate cells, one or more beams, one or more types of measurement quantity, or one or more types of interference.

[0263] In some embodiments, the at least one period comprises: a first period corresponding to a serving cell of the first device, and a second period corresponding to at least one neighboring cell of the first device.

[0264] In some embodiments, the period is indicated by one of: an absolute value of a time length; a multiple of a particular time length, the particular time length being one of: a default time length, a measurement resource configuration period, or a measurement period.

[0265] In some embodiments, the first information further indicates at least one of: whether the first device or the ML model supports input samples related to intra-frequency, whether the first group of candidate cells supports intra-frequency, whether the first device or the ML model supports input samples related to inter-frequency with a particular type of measurement quantity, whether the first group of candidate cells supports intra-frequency with a particular type of measurement quantity, whether the first device or the ML model supports input samples related to inter-frequency, whether the first group of candidate cells supports inter-frequency, whether the first device or the ML model supports input samples related to inter-frequency with a particular type of measurement quantity, whether the first group of candidate cells supports inter-frequency with a particular type of measurement quantity, whether the first device or the ML model supports output samples related to intra-frequency, whether the second group of candidate cells supports intra-frequency, whether the first device or the ML model supports output samples related to intra-frequency with a particular type of measurement quantity, whether the second group of candidate cells supports intra-frequency with a particular type of measurement quantity, whether the first device or the ML model supports output samples related to inter-frequency, whether the second group of candidate cells supports inter-frequency, whether the first device or the ML model supports output samples related to inter-frequency with a particular type of measurement quantity, whether the second group of candidate cells supports inter-frequency with a particular type of measurement quantity, a maximum number of candidate cells associated with a same frequency range, or a maximum number of neighboring cells associated with a same frequency range.

[0266] In some embodiments, the first information is sent via at least one of: radio resource control (RRC) signaling, medium access control (MAC) control element (CE), uplink control information (UCI), user assistance information (UAI), measurement report, user equipment (UE) radio access capability parameter, or channel state information (CSI) report.

[0267] In some embodiments, the other neighboring cell is a default candidate cell, or determined by the first device or the second device.

[0268] In some embodiments, the processor is further configured to cause the first device to: send, to the second device, a request for resources for sending the first information, before sending the first information.

[0269] In some embodiments, the processor is further configured to cause the first device to: receive, from the second device, second information indicating measurement resources to be used by the first device, the measurement resources determined by the second device based on the first information.

[0270] In some embodiments, the first device is a terminal device, and the second device is a network device.

[0271] In one aspect, a second device is presented, the second device comprising: a processor configured to cause the second device to: receive, from a first device deploying a machine learning (ML) model, first information related to the ML model, the first information indicating at least one of: a first set of candidate cells associated with an output of the ML model, or a second set of candidate cells associated with an input of the ML model.

[0272] In some embodiments, the second set of candidate cells is a part of the first set of candidate cells, a part of the second set of candidate cells is the same as a part of the first set of candidate cells, the second set of candidate cells is the same as the first set of candidate cells, or the second set of candidate cells is different from the first set of candidate cells.

[0273] In some embodiments, the first information indicates at least one of the first set of candidate cells and the second set of candidate cells by at least one of a first number of candidate cells included in the first set of candidate cells, a first set of cell identities corresponding to the first set of candidate cells, a second number of candidate cells included in the second set of candidate cells, a second set of cell identities corresponding to the second set of candidate cells, a union of the first set of candidate cells and the second set of candidate cells, a third number of candidate cells included in the union, a first indication indicating whether a serving cell of the first device is included in the first set of candidate cells, a second indication indicating whether the serving cell is included in the second set of candidate cells, a third indication whether a neighboring cell of the first device is included in the first set of candidate cells, a fourth indication whether the neighboring cell is included in the second set of candidate cells, a first number of neighboring cells included in the first set of candidate cells, or a second number of neighboring cells included in the second set of candidate cells.

[0274] In some embodiments, the first number of candidate cells includes at least one of a maximum number of candidate cells or a minimum number of candidate cells included in the first set of candidate cells supported by the first device or the ML model, the second number of candidate cells includes at least one of a maximum number of candidate cells or a minimum number of candidate cells included in the second set of candidate cells supported by the first device or the ML model, the first number of neighboring cells includes at least one of a maximum number of neighboring cells or a minimum number of neighboring cells included in the first set of candidate cells supported by the first device or the ML model, and the second number of neighboring cells includes at least one of a maximum number of neighboring cells or a minimum number of neighboring cells included in the second set of candidate cells supported by the first device or the ML model.

[0275] In some embodiments, the first information further indicates at least one of at least one first set of beams associated with the output of the ML model or the first set of candidate cells, at least one second set of beams associated with the input of the ML model or the second set of candidate cells, or a union of the one or more first set of beams and the one or more second set of beams.

[0276] In some embodiments, the beams included in the at least one second set of beams are a portion of the beams included in the at least one first set of beams, the portion of the beams included in the at least one second set of beams is a portion of the beams included in the at least one first set of beams, the beams included in the at least one second set of beams are the same as the beams included in the at least one first set of beams, or the beams included in the at least one second set of beams are different from the beams included in the at least one first set of beams.

[0277] In some embodiments, the at least one first group of beams includes at least one of a group of beams corresponding to a serving cell included in the first group of candidate cells or a group of beams corresponding to at least one neighboring cell included in the first group of candidate cells, and wherein the at least one second group of beams includes at least one of a group of beams corresponding to a serving cell included in the second group of candidate cells or a group of beams corresponding to at least one neighboring cell included in the second group of candidate cells.

[0278] In some embodiments, the first information indicates at least one of the first group of beams or the second group of beams by at least one of a first number of beams included in the first group of beams, a first group of beam identifications corresponding to the first group of beams, a second number of beams included in the second group of beams, or a second group of beam identifications corresponding to the second group of beams.

[0279] In some embodiments, the first number of beams includes at least one of a maximum number of beams or a minimum number of beams included in the first group of beams supported by the first device or the ML model, and wherein the second number of beams includes at least one of a minimum number of beams or a maximum number of beams in the second group of beams supported by the first device or the ML model.

[0280] In some embodiments, the first information further indicates at least one of a first type of measurement quantity associated with the output of the ML model or the first group of candidate cells or a second type of measurement quantity associated with the input of the ML model or the second group of candidate cells.

[0281] In some embodiments, the first type of measurement quantity is associated with one of one or more candidate cells associated with the output of the ML model or included in the first group of candidate cells, one or more beams associated with the output of the ML model or included in the first group of beams associated with the output of the ML model or the first group of candidate cells, a serving cell associated with the output of the ML model or included in the first group of candidate cells, or at least one neighboring cell associated with the output of the ML model or included in the first group of candidate cells, and wherein the second type of measurement quantity is associated with one of one or more candidate cells associated with the input of the ML model or included in the second group of candidate cells, one or more beams associated with the input of the ML model or included in the second group of beams associated with the input of the ML model or the first group of candidate cells, a serving cell associated with the input of the ML model or included in the second group of candidate cells, or at least one neighboring cell associated with the input of the ML model or included in the second group of candidate cells.

[0282] In some embodiments, the first type of measurement quantity or the second type of measurement quantity is one of: a reference signal received power (RSRP), a signal to interference plus noise ratio (SINR), a received signal strength indicator (RSSI), or a reference signal received quality (RSRQ).

[0283] In some embodiments, the first information further indicates at least one of: whether a first interference of a neighbor cell to a serving cell is needed, a first amount of the first interference, a cell identification of a candidate cell corresponding to the first interference, whether a second interference of the serving cell to a neighbor cell is needed, a second amount of the second interference, an identification of a candidate cell corresponding to the second interference, whether a third interference of the neighbor cell to another neighbor cell is needed, a third amount of the third interference, or an identification of a candidate cell corresponding to the third interference.

[0284] In some embodiments, the first information further indicates at least one of: a number of candidate cells corresponding to a particular type of measurement quantity, a cell identification of a candidate cell corresponding to a particular type of measurement quantity, a number of beams corresponding to a particular type of measurement quantity, or a beam identification of a beam corresponding to a particular type of measurement quantity.

[0285] In some embodiments, the first information further indicates at least one period between two adjacent input samples or two adjacent output samples.

[0286] In some embodiments, the period is associated with at least one of: one or more candidate cells, one or more beams, one or more types of measurement quantities, or one or more types of interference.

[0287] In some embodiments, the at least one period includes: a first period corresponding to a serving cell of the first device, and a second period corresponding to at least one neighbor cell of the first device.

[0288] In some embodiments, the period is indicated by one of: an absolute value of a time length; a multiple of a particular time length, the particular time length being one of: a default time length, a measurement resource configuration period, or a measurement period.

[0289] In some embodiments, the first information further indicates at least one of whether the first device or the ML model supports input samples related to an intra-frequency, whether the first set of candidate cells supports the intra-frequency, whether the first device or the ML model supports input samples related to an inter-frequency with a specific type of measurement quantity, whether the first set of candidate cells supports the inter-frequency with the specific type of measurement quantity, whether the first device or the ML model supports input samples related to the inter-frequency, whether the first set of candidate cells supports the inter-frequency, whether the first device or the ML model supports input samples related to the inter-frequency with the specific type of measurement quantity, whether the first set of candidate cells supports the inter-frequency with the specific type of measurement quantity, whether the first device or the ML model supports output samples related to the intra-frequency, whether the second set of candidate cells supports the intra-frequency, whether the first device or the ML model supports output samples related to the intra-frequency with the specific type of measurement quantity, whether the second set of candidate cells supports the intra-frequency with the specific type of measurement quantity, whether the first device or the ML model supports output samples related to the inter-frequency, whether the second set of candidate cells supports the inter-frequency, whether the first device or the ML model supports output samples related to the inter-frequency with the specific type of measurement quantity, whether the second set of candidate cells supports the inter-frequency with the specific type of measurement quantity, a maximum number of candidate cells associated with a same frequency range, or a maximum number of neighboring cells associated with the same frequency range.

[0290] In some embodiments, the first information is transmitted via at least one of radio resource control (RRC) signaling, medium access control (MAC) control element (CE), uplink control information (UCI), user assistance information (UAI), a measurement report, a user equipment (UE) radio access capability parameter, or a channel state information (CSI) report.

[0291] In some embodiments, the other neighboring cell is a default candidate cell or determined by the first device or the second device.

[0292] In some embodiments, the processor is further configured to cause the second device to: receive, prior to receiving the first information, a request for resources for transmitting the first information to the second device.

[0293] In some embodiments, the processor is further configured to cause the second device to: determine, based on the first information, measurement resources to be used by the first device; and transmit, to the first device, second information indicating the measurement resources.

[0294] In some embodiments, the first device is a terminal device and the second device is a network device.

[0295] In one aspect, a first device comprises: at least one processor; and at least one memory coupled to the at least one processor and storing instructions which, when executed by the at least one processor, cause the device to perform the method implemented by the first device discussed above.

[0296] In one aspect, a second device comprises: at least one processor; and at least one memory coupled to the at least one processor and storing instructions which, when executed by the at least one processor, cause the device to perform the method implemented by the second device discussed above.

[0297] In one aspect, a computer-readable medium has stored thereon instructions that, when executed on at least one processor, cause the at least one processor to perform the method implemented by the first device discussed above.

[0298] In one aspect, a computer-readable medium has stored thereon instructions that, when executed on at least one processor, cause the at least one processor to perform the method implemented by the second device discussed above.

[0299] In one aspect, a computer program comprises instructions which, when executed on at least one processor, cause the at least one processor to perform the method implemented by the first device discussed above.

[0300] In one aspect, a computer program comprises instructions which, when executed on at least one processor, cause the at least one processor to perform the method implemented by the second device discussed above.

[0301] In general, the various embodiments of the disclosure can be implemented in hardware or special-purpose circuits, software, logic or any combination thereof. Some aspects can be implemented in hardware, while other aspects can be implemented in firmware or software which can be executed by a controller, microprocessor or other computing device. While various aspects of the embodiments of the disclosure are illustrated and described as block diagrams, flow charts, or using some other pictorial representation, it is well understood that these blocks, apparatus, systems, techniques or methods described herein can be implemented in hardware, software, firmware, special purpose circuits or logic, general purpose hardware or controler or other computing devices, or some combination thereof.

[0302] The present disclosure also provides at least one computer program product which is tangibly stored on a non-transitory computer-readable storage medium. The computer program product includes computer-executable instructions, such as those included in program modules, which execute on a target real or virtual processor in an apparatus to perform the processes or methods described above, with reference to FIGS. 1 through Figure 6 Generally, program modules include routines, programs, libraries, objects, classes, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The functionality of the program modules can be combined or split between program modules as desired in various embodiments. Machine executable instructions for program modules can be executed within a local or distributed device. In a distributed device, program modules can be located in both local and remote memory storage media.

[0303] Program code utilized by or in connection with the described processes or methods can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions / acts specified in the flow diagrams and / or block diagrams to be implemented. The program code can be entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0304] The program code can be embodied on a machine readable medium, which can be any tangible media that includes or stores the program for use by or in connection with an instruction execution system, apparatus, or device. The machine readable medium can be a machine readable signal medium or a machine readable storage medium. A machine readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine readable storage medium would include an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0305] Furthermore, although the operations are described in a specific order, this should not be construed as requiring such operations to be performed in the specific order shown or in sequential order, or to perform all the illustrated operations to achieve the desired result. In some environments, multitasking and parallel processing can be advantageous. While several specific implementation details are included in the foregoing discussion, these details should not be construed as limiting the scope of this disclosure, but rather as descriptions of features that may be specific to particular embodiments. Certain features described in the context of individual embodiments may also be implemented in a single embodiment in combination. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0306] Although this disclosure has been described using language specific to structural features and / or methodological actions, it should be understood that the disclosure as defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are disclosed as examples of implementing the claims.

Claims

1. A first device, the first device comprising: Processor, the processor being configured to cause the first device to: Determine first information relating to a machine learning (ML) model deployed at the first device, the first information indicating at least one of the following: The first set of candidate cells associated with the output of the ML model, or A second set of candidate cells associated with the input of the ML model; and Send the first information to the second device.

2. The first device according to claim 1, wherein, The second group of candidate cells is a part of the first group of candidate cells. A portion of the second group of candidate cells is identical to a portion of the first group of candidate cells. The second group of candidate cells is the same as the first group of candidate cells, or The second group of candidate cells is different from the first group of candidate cells.

3. The first device according to claim 1 or 2, wherein the first information indicates at least one of the first group of candidate cells and the second group of candidate cells by at least one of the following: The first number of candidate cells included in the first group of candidate cells, The first group of cell identifiers corresponding to the first group of candidate cells, The second number of candidate cells included in the second group of candidate cells, The second group of cell identifiers corresponding to the second group of candidate cells, The union of the first group of candidate cells and the second group of candidate cells, The third number of candidate cells included in the above concentration A first indication indicating whether the serving cell of the first device is included in the first group of candidate cells. A second indication indicating whether the serving cell is included in the second group of candidate cells. The third indication is whether the neighboring cells of the first device are included in the first group of candidate cells. The fourth indication of whether the neighboring cells are included in the second group of candidate cells. The first number of neighboring cells included in the first group of candidate cells, or The second number of neighboring cells included in the second group of candidate cells.

4. The first device according to claim 3, wherein the first number of candidate cells includes at least one of the maximum number of candidate cells included in the first group of candidate cells supported by the first device or the ML model, or the minimum number of candidate cells. The second number of candidate cells includes at least one of the maximum number of candidate cells included in the second set of candidate cells supported by the first device or the ML model, or the minimum number of candidate cells. The first number of neighboring cells includes at least one of the maximum number of neighboring cells included in the first group of candidate cells supported by the first device or the ML model, or the minimum number of neighboring cells. Furthermore, the second number of neighboring cells includes at least one of the maximum number of neighboring cells or the minimum number of neighboring cells included in the second group of candidate cells supported by the first device or the ML model.

5. The first device according to any one of claims 1 to 4, wherein the first information further indicates at least one of the following: At least one first group of beams associated with the output of the ML model or the first group of candidate cells. At least one second set of beams associated with the input of the ML model or the second set of candidate cells, or The union of one or more first-group beams and one or more second-group beams.

6. The first device according to claim 5, wherein, The beams included in the at least one second group of beams are a part of the beams included in the at least one first group of beams. A portion of the beam included in the at least one second group of beams is a portion of the beam included in the at least one first group of beams. The beams included in the at least one second group of beams are the same as the beams included in the at least one first group of beams, or The beams included in the at least one second group of beams are different from the beams included in the at least one first group of beams.

7. The first device according to claim 5 or 6, wherein the at least one first set of beams comprises at least one of the following: A set of beams corresponding to the serving cells included in the first group of candidate cells, or A set of beams corresponding to at least one neighboring cell included in the first group of candidate cells. And said at least one second set of beams includes at least one of the following: A set of beams corresponding to the serving cells included in the second group of candidate cells, or A set of beams corresponding to at least one neighboring cell included in the second set of candidate cells.

8. The first device according to any one of claims 5 to 7, wherein the first information indicates at least one of the first set of beams and the second set of beams by at least one of the following: The first number of beams included in the first group of beams, The first group of beam identifiers corresponding to the first group of beams, The second number of beams included in the second group of beams, or The second group of beam identifiers corresponding to the second group of beams.

9. The first device of claim 8, wherein the first number of beams includes at least one of the maximum number of beams or the minimum number of beams included in the first set of beams supported by the first device or the ML model. And the second number of beams includes at least one of the minimum number of beams or the maximum number of beams in the second set of beams supported by the first device or the ML model.

10. The first device according to any one of claims 1 to 9, wherein the first information further indicates at least one of the following: The first type of measurement associated with the output of the ML model or the first group of candidate cells, or A second type of measurement associated with the input of the ML model or the second group of candidate cells.

11. The first device of claim 10, wherein the first type of measurement quantity is associated with one of the following: One or more candidate cells associated with or included in the first group of candidate cells, and the output of the ML model. One or more beams associated with or included in the first group of beams associated with the output of the ML model or the first group of candidate cells. The serving cell associated with or included in the first group of candidate cells, or The output of the ML model is associated with or included in at least one neighboring cell in the first group of candidate cells. And the second type of measurement is associated with one of the following: One or more candidate cells associated with or included in the second group of candidate cells, and the input of the ML model. One or more beams associated with or included in the second set of beams associated with the input of the ML model or the second set of candidate cells. The serving cell associated with or included in the second group of candidate cells, or The input of the ML model is associated with or included in at least one neighboring cell in the second group of candidate cells.

12. The first device of claim 11, wherein the first type of measurement quantity or the second type of measurement quantity is one of the following: Reference signal received power (RSRP) Signal-to-interference-plus-noise ratio (SINR) Received Signal Enhancement Indicator (RSSI), or Reference signal reception quality (RSRQ).

13. The first device according to any one of claims 1 to 12, wherein the first information further indicates at least one of the following: Is it necessary for adjacent cells to cause initial interference to the serving cell? The first quantity of the first interference Cell identifier of the candidate cell corresponding to the first interference, Is it necessary for the serving cell to cause secondary interference to neighboring cells? The second quantity of the second interference The identifier of the candidate cell corresponding to the second interference, Is it necessary for a third party to interfere with another adjacent cell? The third quantity of the third interference, or The identifier of the candidate cell corresponding to the third interference.

14. The first device according to any one of claims 1 to 13, wherein the first information further indicates at least one of the following: The number of candidate cells corresponding to a specific type of measurement, Cell identifiers of candidate cells corresponding to specific types of measurements. The number of beams corresponding to a specific type of measurement, or Beam identifiers for beams that correspond to a specific type of measurement.

15. The first device according to any one of claims 1 to 14, wherein the first information further indicates at least one cycle between two adjacent input samples or two adjacent output samples.

16. The first device of claim 15, wherein the cycle is associated with at least one of: One or more candidate cells One or more beams One or more types of measurement, or One or more types of interference.

17. The first device according to claim 15, wherein the at least one cycle comprises: The first period corresponding to the serving cell of the first device, and A second cycle corresponding to at least one neighboring cell of the first device.

18. The first device according to any one of claims 15 to 17, wherein the period is indicated by one of: The absolute value of the duration, or A multiple of a specific time length, wherein the multiple of the specific time length is one of the following: a default time length, a measurement resource configuration period, or a measurement period.

19. The first device according to any one of claims 1 to 18, wherein the first information further indicates at least one of the following: Does the first device or the ML model support input samples related to the same frequency? Does the first group of candidate cells support co-frequency? Does the first device or the ML model support input samples that are frequency-dependent with a specific type of measurement? Does the first group of candidate cells support co-frequency measurement with specific types of measurements? Does the first device or the ML model support input samples related to different frequencies? Does the first group of candidate cells support inter-frequency communication? Does the first device or the ML model support input samples with heterogeneous frequency correlation to measurements of a specific type? Does the first group of candidate cells support inter-frequency measurement with specific types of measurements? Does the first device or the ML model support output samples related to the same frequency? Does the second group of candidate cells support co-frequency? Does the first device or the ML model support output samples that are frequency-dependent with a specific type of measurement? Does the second group of candidate cells support co-frequency measurement with specific types of measurements? Does the first device or the ML model support output samples related to different frequencies? Does the second group of candidate cells support inter-frequency communication? Does the first device or the ML model support output samples that are correlated with different frequencies of a specific type of measurement? Does the second group of candidate cells support inter-frequency measurement with specific types of measurements? The maximum number of candidate cells associated with the same frequency range, or The maximum number of neighboring cells associated with the same frequency range.

20. The first device according to any one of claims 1 to 19, wherein the first information is transmitted via at least one of: Radio Resource Control (RRC) signaling Media Access Control (MAC) Control Element (CE) Uplink Control Information (UCI) User Assistance Information (UAI) Measurement report User equipment (UE) radio access capability parameters, or Channel State Information (CSI) Report.

Images