Beam Prediction

Abstract

This application concerns Machine Learning (ML) based beam prediction applied at a UE. This involves measuring only a subset of beams and then applying a ML model to predict the best beams or beam pairs. However, it is important that the model is trained under configurations that closely resemble the actual conditions which the UE will operate in; there must be consistency between training and inference. The UE receives 204 a data collection configuration comprising a plurality of lists of channel state information (CSI) resource configurations. One of the lists is associated with the identity of the serving cell, which may be represented by a cell global identity (CGI). Each list comprises a plurality of resource configurations (308-312, Fig. 3). The resource configurations are associated with respective network side additional condition identifiers (NW-additional-condition-IDs). The UE may train several different ML models each associated with a respective NW-additional-condition-ID. At inference, the UE applies 224 an ML model associated with both the serving cell identity and a NW-additional-condition-ID communicated by a network device in a CSI reporting configuration message 222.

Description

FIELD

[0001] Various example embodiments generally relate to the field of communication, and in particular, to a terminal device, a network device, methods, apparatuses and a computer readable storage medium for predicting beams. BACKGROUND

[0002] A communication network can be seen as a facility that enables communications between two or more communication devices, or provides communication devices access to a data network. A mobile or wireless communication network is one example of a communication network.

[0003] Such communication networks operate in accordance with standards, such as those promulgated by the third generation partnership project (3 GPP) or European telecommunications standards institute (ETSI). Examples of such standards include the so-called 5th generation (5G) standard, advanced 5th generation (5G-Advanced) standard or other standards promulgated by 3GPP. SUMMARY

[0004] In general, example embodiments of the present disclosure provide a solution for predicting beams, especially for consistency between training and inference assisted by network identifier indication for beam prediction. For example, the solution provided by the example embodiments of the present disclosure can achieve consistency of inference at the terminal device on channel state information (CSI) configurations.

[0005] In a first aspect, there is provided a terminal device. The terminal device comprises at least one processor and at least one memory storing instructions that, when executed by the at least one processor, cause the terminal device at least to: receive a data collection configuration comprising a plurality of lists of CSI resource configurations for data collection associated with machine learning (ML) models, wherein a list of CSI resource configuration is associated with a serving cell through at least one of a serving cell identity in a system information block type 1 (SIB 1) message associated with the serving cell or a network additional condition identifier (ID) associated with a CSI reporting configuration for beam prediction; collect data for a measurement of beams determined based on the data collection configuration; transmit, based on the collected data, a report for beam prediction considering capability information of the terminal device; receive a CSI reporting configuration for the beam predicting; and apply an ML model trained with collected data for inference to be used for the beam prediction with respect to the serving cell identity and an associated network additional condition ID within the CSI reporting configuration.

[0006] In a second aspect, there is provided a network device. The network device comprises at least one processor and at least one memory storing instructions that, when executed by the at least one processor, cause the network device at least to: transmit a data collection configuration comprising a plurality of lists of CSI resource configurations for data collection associated with ML models, wherein a list of CSI resource configuration is associated with a serving cell through at least one of a serving cell identity in an SIB1 message associated with the serving cell or a network additional condition ID associated with a CSI reporting configuration for beam prediction; receive a report for beam prediction considering capability information of the terminal device; determine a CSI reporting configuration for the beam predicting based on an indication via capability reporting of the terminal device; and transmit the CSI reporting configuration.

[0007] In a third aspect, there is provided a method. The method comprises: receiving, at a terminal device, a data collection configuration comprising a plurality of lists of CSI resource configurations for data collection associated with ML models, wherein a list of CSI resource configuration is associated with a serving cell through at least one of a serving cell identity in an SIB 1 message associated with the serving cell or a network additional condition ID associated with a CSI reporting configuration for beam prediction; collecting data for a measurement of beams determined based on the data collection configuration; transmitting, based on the collected data, a report for beam prediction considering capability information of the terminal device; receiving a CSI reporting configuration for the beam prediction; and applying an ML model trained with collected data for inference to be used for the beam prediction with respect to the serving cell identity and an associated network additional condition ID within the CSI reporting configuration.

[0008] In a fourth aspect, there is provided a method. The method comprises: transmitting, at a network device, a data collection configuration comprising a plurality of lists of CSI resource configurations for data collection associated with ML models, wherein a list of CSI resource configuration is associated with a serving cell through at least one of a serving cell identity in an SIB1 message associated with the serving cell or a network additional condition ID associated with a CSI reporting configuration for beam prediction; receiving a report for beam prediction considering capability information of the terminal device; determining a CSI reporting configuration for the beam predicting based on an indication via capability reporting of the terminal device; and transmitting the CSI reporting configuration.

[0009] In a fifth aspect, there is provided an apparatus. The apparatus comprises: means for receiving, at a terminal device, a data collection configuration comprising a plurality of lists of CSI resource configurations for data collection associated with ML models, wherein a list of CSI resource configuration is associated with a serving cell through at least one of a serving cell identity in an SIB1 message associated with the serving cell or a network additional condition ID associated with a CSI reporting configuration for beam prediction; means for collecting data for a measurement of beams determined based on the data collection configuration; means for transmitting, based on the collected data, a report for beam predicting considering capability information of the terminal device; means for receiving a CSI reporting configuration for the beam prediction; and means for applying an ML model trained with collected data for inference to be used for the beam prediction with respect to the serving cell identity and an associated network additional condition ID within the CSI reporting configuration.

[0010] In a sixth aspect, there is provided an apparatus. The apparatus comprises: means for transmitting, at a network device, a data collection configuration comprising a plurality of lists of CSI resource configurations for data collection associated with ML models, wherein a list of CSI resource configuration is associated with a serving cell through at least one of a serving cell identity in an SIB1 message associated with the serving cell or a network additional condition ID associated with a CSI reporting configuration for beam prediction; means for receiving a report for beam prediction considering capability information of the terminal device; means for determining a CSI reporting configuration for the beam predicting based on an indication via capability reporting of the terminal device; and means for transmitting the CSI reporting configuration.

[0011] In a seventh aspect, there is provided a non-transitory computer readable medium comprising program instructions for causing an apparatus to perform at least the method according to the third or fourth aspect.

[0012] In an eighth aspect, there is provided a computer program comprising instructions, which, when executed by an apparatus, cause the apparatus to perform at least the method according to the third or fourth aspect.

[0013] In a ninth aspect, there is provided a terminal device. The terminal device comprises first receiving circuitry configured to receive a data collection configuration comprising a plurality of lists of CSI resource configurations for data collection associated with ML models, wherein a list of CSI resource configuration is associated with a serving cell through at least one of a serving cell identity in an SIB1 message associated with the serving cell or a network additional condition ID associated with a CSI reporting configuration for beam prediction; collecting circuitry configured to collect data for a measurement of beams determined based on the data collection configuration; transmitting circuitry configured to transmit, based on the collected data, a report for beam prediction considering capability information of the terminal device; second receiving circuitry configured to receive a CSI reporting configuration for the beam prediction; and applying circuitry configured to apply an ML model trained with collected data for inference to be used for the beam prediction with respect to the serving cell identity and an associated network additional condition ID within the CSI reporting configuration.

[0014] In a tenth aspect, there is provided a network device. The network device comprises a first transmitting circuitry configured to transmit a data collection configuration comprising a plurality of lists of CSI resource configurations for data collection associated with ML models, wherein a list of CSI resource configuration is associated with a serving cell through at least one of a serving cell identity in an SIB1 message associated with the serving cell or a network additional condition ID associated with a CSI reporting configuration for beam prediction; receiving circuitry configured to receive a report for beam prediction considering capability information of the terminal device; determining circuitry configured to determine a CSI reporting configuration for the beam predicting based on an indication via capability reporting of the terminal device; and second transmitting circuitry configured to transmit the CSI reporting configuration.

[0015] It is to be understood that the summary section is not intended to identify key or essential features of embodiments of the present disclosure, nor is it intended to be used to limit the scope of the present disclosure. Other features of the present disclosure will become easily comprehensible through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Some example embodiments will now be described with reference to the accompanying drawings, in which:

[0017] FIG. 1A illustrates an example network environment in which example embodiments of the present disclosure may be implemented;

[0018] FIG. IB illustrates an example CSI report and measurement hierarchy in 5G new radio (NR) in accordance with some example embodiments of the present disclosure;

[0019] FIG. 2 illustrates an example signaling process of beam prediction in accordance with some example embodiments of the present disclosure;

[0020] FIG. 3 illustrates an example data collection categorization in accordance with some example embodiments of the present disclosure;

[0021] FIG. 4 illustrates an example signaling process of data collection in accordance with some example embodiments of the present disclosure;

[0022] FIG. 5 illustrates an example signaling process of inference in accordance with some example embodiments of the present disclosure;

[0023] FIG. 6 illustrates an example flowchart of a process of beam prediction implemented at a terminal device in accordance with some example embodiments of the present disclosure;

[0024] FIG. 7 illustrates an example flowchart of a process of beam prediction implemented at a network device in accordance with some example embodiments of the present disclosure;

[0025] FIG. 8 illustrates an example simplified block diagram of a device that is suitable for implementing embodiments of the present disclosure; and

[0026] FIG. 9 illustrates an example block diagram of an example computer readable medium in accordance with some example embodiments of the present disclosure.

[0027] Throughout the drawings, the same or similar reference numerals represent the same or similar element. DETAILED DESCRIPTION

[0028] Principles of the present disclosure will now be described with reference to some example embodiments. It is to be understood that these embodiments are described only for the purpose of illustration and help those skilled in the art to understand and implement the present disclosure, without suggesting any limitation as to the scope of the disclosure. The disclosure described herein may be implemented in various manners other than the ones described below.

[0029] In the following description and claims, unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skills in the art to which the present disclosure belongs.

[0030] References in the present disclosure to “one embodiment,” “an embodiment,” “an example embodiment,” and the like indicate that the embodiment described may include a particular feature, structure, or characteristic, but it is not necessary that every embodiment includes the particular feature, structure, or characteristic. Moreover, such phrases are not necessarily referring to the same embodiment. Further, when a particular feature, structure, or characteristic is described in connection with an embodiment, it is submitted that it is within the knowledge of one skilled in the art to affect such feature, structure, or characteristic in connection with other embodiments whether or not explicitly described.

[0031] It may be understood that although the terms “first” and “second” etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first element could be termed a second element, and similarly, a second element could be termed a first element, without departing from the scope of example embodiments. As used herein, the term “and / or” includes any and all combinations of one or more of the listed terms.

[0032] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments. As used herein, the singular forms “a”, “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises”, “comprising”, “has”, “having”, “includes” and / or “including”, when used herein, specify the presence of stated features, elements, and / or components etc., but do not preclude the presence or addition of one or more other features, elements, components and / or combinations thereof. As used herein, “at least one of the following: ” and “at least one of ” and similar wording, where the list of two or more elements are joined by “and” or “or”, mean at least any one of the elements, or at least any two or more of the elements, or at least all the elements.

[0033] As used in this application, the term “circuitry” may refer to one or more or all of the following: (a) hardware-only circuit implementations (such as implementations in only analog and / or digital circuitry) and (b) combinations of hardware circuits and software, such as (as applicable): (i) a combination of analog and / or digital hardware circuit(s) with software / firmware and (ii) any portions of hardware processor(s) with software (including digital signal processor!s)), software, and memory(ies) that work together to cause an apparatus, such as a mobile phone or server, to perform various functions) and (c) hardware circuit(s) and or processor(s), such as a microprocessor s) or a portion of a microprocessors) that requires software (e.g., firmware) for operation, but the software may not be present when it is not needed for operation.

[0034] This definition of circuitry applies to all uses of this term in this application, including in any claims. As a further example, as used in this application, the term circuitry also covers an implementation of merely a hardware circuit or processor (or multiple processors) or portion of a hardware circuit or processor and its (or their) accompanying software and / or firmware. The term circuitry also covers, for example and if applicable to the particular claim element, a baseband integrated circuit or processor integrated circuit for a mobile device or a similar integrated circuit in server, a cellular network device, or other computing or network device.

[0035] As used herein, the term “communication network” refers to a network following any suitable communication standards, such as long term evolution (LTE), LTE-advanced (LTE-A), wideband code division multiple access (WCDMA), high-speed packet access (HSPA), narrow band Internet of things (NB-IoT) and so on. Furthermore, the communications between a terminal device and a network device in the communication network may be performed according to any suitable generation communication protocols, including, but not limited to, the third generation (3G), the fourth generation (4G), 4.5G, the fifth generation (5G) communication protocols, and / or beyond. Embodiments of the present disclosure may be applied in various communication systems. Given the rapid development in communications, there will of course also be future type communication technologies and systems with which the present disclosure may be embodied. It should not be seen as limiting the scope of the present disclosure to only the aforementioned system.

[0036] As used herein, the term “network device” refers to a node in a communication network via which a terminal device accesses the network and receives services therefrom. The network device may refer to a base station (BS) or an access point (AP), for example, a node B (NodeB or NB), an evolved NodeB (eNodeB or eNB), a NR NB (also referred to as a gNB), a remote radio unit (RRU), a radio header (RH), a remote radio head (RRH), a relay, a low power node such as a femto, a pico, and so forth, depending on the applied terminology and technology.

[0037] The term “terminal device” refers to any end device that may be capable of wireless communication. By way of example rather than limitation, a terminal device may also be referred to as a communication device, user equipment (UE), a subscriber station (SS), a portable subscriber station, a mobile station (MS), or an access terminal (AT). The terminal device may include, but not limited to, a mobile phone, a cellular phone, a smart phone, voice over IP (VoIP) phones, wireless local loop phones, a tablet, a wearable terminal device, a personal digital assistant (PDA), portable computers, desktop computer, image capture terminal devices such as digital cameras, gaming terminal devices, music storage and playback appliances, vehicle-mounted wireless terminal devices, wireless endpoints, mobile stations, laptop-embedded equipment (LEE), laptop-mounted equipment (LME), USB dongles, smart devices, wireless customer-premises equipment (CPE), an Internet of things (loT) device, a watch or other wearable, a head-mounted display (HMD), a vehicle, a drone, a medical device and applications (e.g., remote surgery), an industrial device and applications (e.g., a robot and / or other wireless devices operating in an industrial and / or an automated processing chain contexts), a consumer electronics device, a device operating on commercial, a relay node, an integrated access and backhaul (IAB) node, and / or industrial wireless networks, and the like. In the following description, the terms “terminal device”, “communication device”, “terminal”, “user equipment” and “UE” may be used interchangeably.

[0038] As used herein, the term “resource”, “transmission resource”, “resource block”, “physical resource block” (PRB), “uplink (UL) resource” or “downlink (DL) resource” may refer to any resource for performing a communication, for example, a communication between a terminal device and a network device, such as a resource in time domain, a resource in frequency domain, a resource in space domain, a resource in code domain, a resource in a combination of more than one domain or any other resource enabling a communication, and the like. In the following, a resource in time domain (such as, a subframe) will be used as an example of a transmission resource for describing some example embodiments of the present disclosure. It is noted that example embodiments of the present disclosure are equally applicable to other resources in other domains.

[0039] Artificial intelligence (AI) and ML enhancements related to beam management have two sub-use cases have been identified in radio access network 1 (RANI). They are (1) beam prediction in the spatial domain (BM-Casel) and (2) beam prediction in the time domain (BM-Case2). The primary motivation is to support a reduced overhead and lower beam measurements and reporting latency. Based on the evaluation, the benefits and gains were verified based on given metrics, and they could be supported by single-sided models and consider supporting the necessary / recommended LCM components for selected sub use cases. For an ML-based beam prediction applied at the UE, it is possible to use the ML model to predict the best transmission (Tx) beam or Tx-reception (Rx) beam pair(s) by using a subset of measurements at the input of the ML model and reporting the predicted Top-K best beam to the network (NW).

[0040] In RANI #114bis meeting, RANI agreed on four approaches related to handling consistency between training and inference when model is operated at UE side. For example, for inference for UE-side models, to ensure consistency between training and inference regarding NW-side additional conditions, information and / or indication on NW-side additional conditions is provided to UE.

[0041] Apart from above agreement, considering both functionality-based life cycle management (LCM) and model-ID based LCM, the need on whether and how addressing additional conditions aiding UE sided model were proposed but not discussed during study phase in Release-18. Focusing on BM-Casel and BM-Case2 with UE sided model, no further discussions were made to detail addressing the consistency mechanism. Additional conditions of a model can be interpreted into two following categories: (1) NW-side additional conditions, and (2) UE-side additional conditions (e.g., UE speed, UE-side beam pattern).

[0042] There is a need to keep consistency between training and inference via indicating a unique and codebook specific identifier introduced by the NW which is mapped to each CSI resource configuration. Therefore, example embodiments of the present disclosure provide a solution for predicting beams. The solution provides a possibility to the use of a NW identifier information to preserve NW-sided proprietary information and the coordination between NW vendors and gNB sites to determine such identifier. For example, a terminal device receives a data collection configuration comprising a plurality of lists of CSI resource configurations for data collection associated with ML models. A list of CSI resource configuration is associated with a serving cell through at least one of a serving cell identity in an SIB1 message associated with the serving cell or a network additional condition ID associated with a CSI reporting configuration for beam prediction. The terminal device further collects data for a measurement of beams determined based on the data collection configuration. The terminal device further receives a CSI reporting configuration for the beam predicting considering capability information of the terminal device. The terminal device further applies an ML model trained with collected data for inference to be used for the beam predicting with respect to the serving cell identity and an associated network additional condition ID within the CSI reporting configuration.

[0043] It is understood that the above procedure steps may work together, in a flow of operations as described in the next section, partly together or independently of each other. By implementing some embodiments of the present disclosure, consistency of inference at the terminal device on CSI configurations can be achieved. The solution fills in the gap to provide signaling essentials and determination to map between datasets of UE employed during data collection and Set B / Set A beams association during inference, via a unique NW identifier which can be carried along with each CSI resource configuration.

[0044] For illustrative purposes, principles and example embodiments of the present disclosure of beam prediction will be described below with reference to FIG. 1A- FIG. 9. However, it is to be noted that these embodiments are given to enable the skilled in the art to understand inventive concepts of the present disclosure and implement the solution as proposed herein, and not intended to limit scope of the present application in any way.

[0045] Reference is made to FIG. 1A, which illustrates an example network environment 100A in which example embodiments of the present disclosure may be implemented. The network environment 100A, which may be a part of a communication network, includes a terminal device 102 and a network device 104.

[0046] As illustrated in FIG. 1A, the terminal device 102 may also be referred as a user equipment 102 or a UE 102. The network device 104 may also be referred as a gNB 104. The terminal device 102 and the network device 104 can communicate with each other.

[0047] As discussed above, the data collection in RANI has mainly considered offline training. Thus, multiple UEs may collect data based on the Ll-RSRP measurements corresponding to different beams. It is assumed that the UE may not always train a beam prediction model at the UE device and may send the beam measurements to an external UE server, for example, located in a datacentre operated by the UE vendor, which will the train the model. The external UE server may receive data from multiple UEs from the same or from a different cell and / or from the same or multiple NW vendors. The UE server may aggregate the data received from multiple UEs to form a training dataset. The data may be categorized based on the site location and the external UE server may be able to train a specific model that can be applied for instance to a gNB site. Next, the beam prediction model will be downloaded to the UE and during the UE connection, a UE may require using a model while it is connected to the same gNB site.

[0048] A core challenge in developing a model for UE-side applications is the potential discrepancy between the beam configuration used during the data collection phase and the configuration employed during the inference process. This mismatch could lead to the UE employing an inappropriate model for inference. For instance, consider a scenario where the model has been trained using measurements derived from a gNB antenna array configuration that differs from the one in use during a training phase of the model. As a result, the accuracy of the predictions of the model may be compromised because the parameters of the model have been determined based on a distinct distribution of data. This highlights the importance of ensuring that the model is trained and applied under configurations that closely resemble the actual conditions in which the UE will operate, to maintain the integrity and reliability of the inferences of the model.

[0049] Consequently, the model can be utilized for inference purposes only when it aligns with the specific configurations linked to a particular gNB within a defined site or location, and / or when it is associated with a particular vendor. The processes involved in training and inference become more feasible if the UE has the capability to discern and categorize data that pertain to a distinct NW configuration, specific sites or locations, and / or are related to a certain vendor. In these scenarios, the UE’s understanding of the nature of the data it gathers becomes crucial for the effective collection of data from the perspective of the user and for the proper functioning of the model. The ability of the UE to accurately identify and segregate data based on these criteria is essential for ensuring that the model operates as intended and provides reliable results.

[0050] Reference is made to FIG. IB, which illustrates an example CSI report and measurement hierarchy 100B in 5G NR in accordance with some example embodiments of the present disclosure. As shown in FIG. IB, the CSI-RS reporting framework includes the procedure of indicating a particular CSI-RS resources to be measured by the NW and corresponding feedback information from the UE. The UE uses a physical uplink shared channel (PUSCH) transmission or a physical uplink control channel (PUCCH) transmission for CSI-RS reporting to NW to support its downlink (DL) transmissions.

[0051] The CSI reporting may include channel quality indicator (CQI), CSI-reference signal (RS) resource indicator, rank indicator, layer indication (LI), precoding matrix indicator (PMI), layer 1 reference signal received power (Ll-RSRP), synchronization signal (SS) / physical broadcast channel (PBCH) block resource indicator (SSBRI), or any combination thereof.

[0052] In general, CSI reporting framework capability describes the capability of the UE to support CSI reporting. It includes parameters defining the maximum number of periodic and / or aperiodic CSI reports which may be configured per component carrier (CC), per bandwidth part (BWP) and per beam. Moreover, it specifies the concurrent CSI reports per CC that the UE can measure and process, including periodic, semi-persistent and aperiodic CSI, including beam reports.

[0053] As shown in block 112, the CSI report configuration describes the configuration parameters used to set up periodic, aperiodic or semi-persistent CSI reports sent on the PUCCH or PUSCH for a particular cell or triggered by downlink control information (DCI). It includes fields such as report quantity, frequency domain configuration, time domain behaviour and channel measurement resource allocation which may affect how the UE perform reports based on different configurations.

[0054] As shown in block 114, the CSI measurement configuration describes the use of two CSI resource configurations including channel measurements interference measurements. CSI-RS configuration of type non-zero-power (NZP)-CSI-RS enables resources dedicated for channel measurements (also referred to as channel measurement resources (CMR)), whereas the CSI-RS configuration of the type zero-power (ZP)-CSI-RS enables resources dedicated for interference measurements (also referred to as information measurement (IM)).

[0055] As shown in block 116, the CSI resource set defines all related physical resources for an individual UE. The CSI resource set is used for reporting channel state information. It allows UE to measure the quality of the channel based on specific reference signal resources and report these measurements back to the gNB. These measurements assist the network in making more accurate resource allocations, scheduling decisions, and beamforming. CSI resource sets can be periodic, semi-persistent, or aperiodic, which determines how UE conducts channel state information measurements and reporting based on the network configuration. The periodic CSI resource sets allow UE to perform measurements according to predefined periods, while aperiodic CSI resource sets are activated by specific trigger conditions.

[0056] Reference is made to FIG. 2, which illustrates an example signaling process 200 of beam prediction in accordance with some example embodiments of the present disclosure. FIG. 2 will be described with reference to FIG. 1 A.

[0057] As shown in FIG. 2, the network device 104 transmits (202) a data collection configuration 206 to the terminal device 102. The data collection configuration 206 may comprise a plurality of lists of CSI resource configurations for data collection associated with ML models. A list of CSI resource configuration may be associated with a serving cell through at least one of a serving cell identity in an SIB 1 message associated with the serving cell or a network additional condition ID associated with a CSI reporting configuration for beam prediction.

[0058] The terminal device 102 receives (204) the data collection configuration 206 from the network device 104. The terminal device 102 collects (208) data for a measurement of beams determined based on the data collection configuration 206.

[0059] In some example embodiments, the network device 104 may configure the terminal device 102 with a configuration which allows data collection based on CSI-RS measurements. The network device 104 may configure the terminal device 102 with M CSL ResourceConfigs within CSI-MeasConfig via NZP-CSI-RS-ResourceToAddList, in which one or more CSI-ResourceConfig(s) of M CSI-ResourceConfigs may be associated with a set of NW-sided additional conditions.

[0060] In some example embodiments, the NW-sided additional condition may include a beam codebook, an SSB resource set (such as a CSI-SSB resource set). The CSI-SSB resource set may be associated with one NW-sided SSB beam codebook, and the CSI-RS resource set (such as an NZP-CSI-RS resource set) may be associated with another NW-sided CSI-RS beams codebook.

[0061] Now referring to FIG.3, which illustrates an example data collection categorization 300 in accordance with some example embodiments of the present disclosure. FIG. 3 shows UE data collection categorization for M CSI-ResourceConfig with additional-condition-IDs of NW vendorj. As shown in FIG. 3, one or more CSI-ResourceConfig(s) of M CSI-ResourceConfigs may be configured to carry a unique NW vendor identifier NW-additional-condition-ID. For example, in the list 304 of CSI report configuration, there are several NW-additional-condition-IDs, such as NWj-additional-condition-ID (1) associated with beam codebook#l, NWj-additional-condition-ID (2) associated with beam codebook#2, ..., and NWj-additional-condition-ID (M) associated with beam codebook#M.

[0062] In the list 306 of CSI resource configuration, there are several CSI resource configurations. For example, CSI resource configuration 308, CSI resource configuration 310, ..., CSI resource configuration 312. NWj-additional-condition-ID (1) may be associated with CSI resource configuration 308. NWj-additional-condition-ID (2) may be associated with CSI resource configuration 310. NWj-additional-condition-ID (M) may be associated with CSI resource configuration 312, and so on.

[0063] In some example embodiments, the terminal device 102 may use a new radio cell global identity (NR-CGI) which may be received via an SIB1 message and NW-additional-condition-IDs associated with CSI-MeasConfig to categorize measurements of CSI-RS beams and / or SSB beams.

[0064] Now referring back to FIG. 2, in some example embodiments, a separate RS configuration for data collection may be used. For example, the terminal device 102 may be configured with a multi-cell data collection configuration (e.g., DataCollection-Config). The multi-cell data collection configuration may provide one or more lists of data collection CSI resource configurations (e.g., datacollection-csi-ResourceConfigToAddModList) and each list of data collection CSI resource configuration may be associated with a corresponding serving cell identity.

[0065] In some example embodiments, for a list of data collection CSI resource configuration (such as datacollection-csi-ResourceConfigToAddModList), multiple data collection CSI resource configurations (e.g., datacollection-CSI-ResourceConfig) may be included in this list of data collection CSI resource configuration.

[0066] In some example embodiments, for each data collection CSI resource configuration (e g., datacollection-CSI-ResourceConfig), at least one data collection NZP-CSI-RS resource set (e g., datacollection-NZP-CSI-RS-Resourceset, which contains NZP-CSI-RS resources) and / or at least one data collection CSI-SSB-resource set (e.g., datacollection-CSI-SSB-ResourceSet, which contains SSB indices) may be considered.

[0067] In some example embodiments, the collected data may comprise DL RS resources. The DL RS resources (such as SSB indices, or CSI-RS resources) for data collection may contain information related to: subcarrier spacing; frequency information; time information; periodicity information; power information; scrambling information; quasi co-location (QCL) information; or at least one other physical layer property which allows detecting or measuring a RS resource.

[0068] In some example embodiments, the serving cell identity may be an NR-CGI, and the capability information of the terminal device may comprise at least one of applicable NR-CGIs or applicable network additional condition IDs in which can be indicated via capability reporting. For example, the cell identity which is associated with each list of data collection CSI resource configuration may be an NR-CGI which recognizes a cell in unique manner. For each data collection resource set (e.g., datacollection-NZP-CSI-RS-Resourceset or datacollection-CSI-SSB-ResourceSet), the configuration identifier (e.g., datacollection-NZP-CSI-RS-ResourcesetlD, datacollection-csi-SSB-ResourceSetID) may be used. NW-additional-condition-ID may be included within each data collection resource set.

[0069] In some example embodiments, the terminal device 102 may determine that measurements of beams are at least one of a measurement of CSI-RS beams or a measurement of SSB beams based on the serving cell identity and the network additional condition ID. The terminal device 102 may collect data corresponding to NZP-CSI-RS resource sets or CSI-SSB resource sets. A CSI-SSB resource set can be identified by a network additional condition ID. The terminal device 102 may further categorize the collected data with respect to serving cell identities or network additional condition IDs as respective datasets.

[0070] In some example embodiments, the terminal device 102 may collect data corresponding to each data collection resource set or CSI-ResourceConfig. Each i CSI-ResourceConfig may be identified by JVW)-additional-condition-ID(i). The terminal device 102 may categorize the collected data with respect to NR-CGI and NWj -additional-condition-ID(i . M). For example, the terminal device 102 may obtain CGIX of cell x from SIB 1 message and categorize training datasets considering both CGIX and Al / ^-additional-condition-ID (i...M).

[0071] In some example embodiments, the terminal device 102 may combine the datasets associated with respective network additional condition IDs, and associate, based on the network additional condition IDs, the datasets with respective ML models performed at the terminal device. For example, the terminal device 102 may combine the datasets collected under each Nlkj-additional-condition-ID(i) and associate the combined datasets to a model(s) performed at the terminal device 102.

[0072] In some example embodiments, the terminal device 102 may train an ML model corresponding to one or more network additional condition IDs. For example, the terminal device 102 may perform an ML model training corresponding to a single lVIV)-additional-condition-ID(i) or corresponding to multiple IWl^-additional-condition-IDs. As an example, dataset corresponding to the CSI-RS measurements (beam measurements) of NW vendor j of CSI-ResourceConfigl (which has NWj -additional-condition-IDl) and dataset corresponding to the CSI-RS measurements (beam measurements) of CSI-ResourceConfig2 (which has lVW^-additional-condition-ID2) may be used to train ML model(s).

[0073] In some example embodiments, an NW-additional-condition-ID corresponding to NW vendor j may be determined by the NW vendor j within a fixed bit field size which is predefined (e.g., a 7-bit field allowing 128 different IDs), and the same NW-additional-condition-ID may be used by NW vendor k without any coordination with the NW vendor / .

[0074] In some example embodiments, a NW-additional-condition-ID corresponding to NW vendor j may be assigned by the operator or as coordination among NW vendors, where NW-additional-condition-IDs used by the NW vendor j may be different from the NW vendor k.

[0075] The terminal device 102 transmits (210), based on the collected data, a report 214 for beam predicting considering capability information of the terminal device 102. For example, the terminal device 102 may report applicable NW-additional-condition-IDs and / or NR-CGIs for beam prediction reporting. The network device 104 receives (212) the report 214 from the terminal device 102. The network device 104 determines (216) a CSI reporting configuration for the beam predicting based on an indication via capability reporting of the terminal device.

[0076] For example, the terminal device 102 may detect an NR-CGI from an SIB1 message and for a given use-case (such as beam management herein), and may determine the ML models that are applicable for this NR-CGI. The terminal device 102 may inform (e.g., during UE capability reporting) the unique “NW-additional-condition-ID(s)” that are linked to this ML model. The network device 104 then may configure the terminal device 102 leading to use the ML models that match the given “NW-additional-condition-ID(s)”. If there is no match, then the terminal device 102 may not use the ML model in this serving cell (i.e., this NR-CGI). In some example embodiments, the network device 104 may configure the terminal device 102 based on the reported NW ID which causes the terminal device 102 using a matched ML model which was trained with the same ID for inference.

[0077] As an example, the network device 104 may consider the report 214 when deciding whether beam prediction can be supported in certain NR-CGIs and which NW-additional-condition-IDs to be considered within a CSI report. For example, NW-additional-condition-IDs may remain the same used in data collection if NW configuration is not changing. The terminal device 102 may use the serving cell identity and NW-additional-condition-IDs configured in DataCollection-Config to categorize measurements of CSI-RS beams and / or SSB beams.

[0078] The network device 104 transmits (218) the CSI reporting configuration 222 to the terminal device 102. The terminal device 102 receives (220) the CSI reporting configuration 222 to the network device 104. For example, resource sets for Set A and Set B may be provided as two different CSLReportConfigs in the CSI-ResourceConfig used for beam prediction reporting. Set B refers to a first reporting configuration for reporting measured beams applied as input of the ML model associated with network additional condition IDs. Set A refers to a second reporting configuration for reporting predicted beams applied as output of the ML model associated with network additional condition IDs.

[0079] The terminal device 102 applies (224) an ML model trained with collected data for inference to be used for the beam predicting with respect to the serving cell identity and an associated network additional condition ID within the CSI reporting configuration. For example, the terminal device supports the inference operation, based on matching ML model associated with the NW-additional-condition-IDs.

[0080] In some example embodiments, the terminal device may determine the ML model to be used for the beam predicting based on the network additional condition ID associated with the CSI reporting configuration and / or the NR-CGI. For example, the terminal device 102 may detect the NR-CGI, and determine the trained models applicable for the corresponding NR-CGI. The determined trained models may be further associated with the NW-additional-condition-IDs. The terminal device 102 may download ML models as needed depending on the configured CSI reports.

[0081] In some example embodiments, the terminal device 102 may determine NW-additional-condition-ID(s) associated with a beam prediction related CSI reporting configuration. Resource sets for measurements and reporting may be provided in a CSL ReportConfig (e.g., resource sets for Set A and Set B may be provided as two CSL ReportConfigs in the CSI-ResourceConfig used for beam prediction reporting).

[0082] In some example embodiments, the terminal device 102 may report an applicable network additional condition ID for the beam prediction, and / or receive the network additional condition ID associated with the ML model. For example, the terminal device 102 may support the inference operation, based on matching ML model associated with the NW-additional-condition-IDs. In some example embodiments, when the terminal device 102 detects the NR-CGI, the terminal device 102 may trigger or configured to report applicable NW-additional-condition-IDs for beam prediction reporting. The network device 104 may consider activating and / or selecting a suitable CSI report which contain applicable NW-additional-condition-ID(s).

[0083] With some embodiments of the signaling process 200, an approach for consistency of inference at the UE on CSI configurations can be achieved. A NW identifier information is used to preserve NW-side proprietary information. It helps assist UE to enable getting aligned with the configurations associated with the gNB in a certain sites / locations and / or belonging to a certain vendor.

[0084] Reference is made to FIG. 4, which illustrates an example signaling process 400 of data collection in accordance with some example embodiments of the present disclosure. As shown in FIG. 4, the UE 402 may correspond to the terminal device 102 in FIG. 1A. The network 404 may correspond to the network device 104 in FIG. 1 A.

[0085] The NW 404 may transmit (406) an SIB1 message 410 including NR-CGI of the primary cell via higher-layer signaling (e.g., SIB1). The UE 404 may receive (408) the SIB1 message 410 from the NW 404. The NW 404 may transmit (412) data collection configuration 416 to the UE 402. The UE 402 may receive (414) the data collection configuration 416 from the NW 404.

[0086] For example, the NW 404 may configure multi-cell data collection configuration using DataCollection-Config. The CSI-ResourceConfigToAddModList may provide one or more lists of data collection CSI resource configurations. Each list of data collection CSI resource configuration may be associated with a corresponding serving cell identity. NW-additional-condition-ID may be included within each resource set configured within CSI-ResourceConfigToAddModList. UE 402 may determine (418) a NR-CGI from the SIB1 message 410. UE 402 may categorize (420) the collected data based on the NR-CGI and corresponding NW-additional-condition-ID.

[0087] Reference is made to FIG. 5, which illustrates an example signaling process 500 of inference in accordance with some example embodiments of the present disclosure. As shown in FIG. 5, the UE 502 may correspond to the terminal device 102 in FIG. 1A. The network 504 may correspond to the network device 104 in FIG. 1A.

[0088] The UE 502 may report (506) applicable NW-additional-condition-IDs and / or NR-CGIs 510 for beam prediction reporting using UE capability framework. The NW 504 may receive (508) the applicable NW-additional-condition-IDs and / or the applicable NR-CGls 510.

[0089] The NW 504 may receive the UE capability signaling and may determine (512) if beam prediction can be supported in certain CGI and which NW-additional-condition-IDs to be considered within a configured CSI report. The NW 504 may configure beam prediction related CSI reporting configuration for Set A and Set B associated with NW-additional-condition-IDs. The NW 504 may transmit (514) the beam prediction related CSI reporting configuration 518 to the UE 502. The UE 502 may receive (516) the beam prediction related CSI reporting configuration 518.

[0090] The UE 502 may determine (520) matching trained ML model associated with NR-CGI and corresponding NW-additional-condition-ID. The UE 502 may perform (521) beam prediction based on configured CSI report. The UE 502 may transmit (522) the beam prediction report 526 based on the ML model to the NW 504. The NW 504 may receive (524) the beam prediction report 526.

[0091] Reference is made to FIG. 6, which illustrates an example flowchart of a process 600 of beam prediction implemented at a terminal device in accordance with some example embodiments of the present disclosure. FIG. 6 will be described with reference to FIG. 1A.

[0092] At 602, the terminal device 102 receives a data collection configuration comprising a plurality of lists of CSI resource configurations for data collection associated with ML models. A list of CSI resource configuration is associated with a serving cell through at least one of a serving cell identity in an SIB1 message associated with the serving cell or a network additional condition ID associated with a CSI reporting configuration for beam prediction.

[0093] At 604, the terminal device 102 collects data for a measurement of beams determined based on the data collection configuration. At 606, the terminal device 102 transmits, based on the collected data, a report for beam predicting considering capability information of the terminal device.

[0094] At 608, the terminal device 102 receives a CSI reporting configuration for the beam predicting. At 610, the terminal device 102 applies an ML model trained with collected data for inference to be used for the beam predicting with respect to the serving cell identity and an associated network additional condition ID within the CSI reporting configuration.

[0095] In some example embodiments, a list of CSI resource configuration may comprise a plurality of CSI resource configurations for the data collection. In some example embodiments, a CSI resource configuration for the data collection may comprise at least one of the following: at least one NZP-CSI-RS resource set; or at least one CSLSSB resource set.

[0096] In some example embodiments, the collected data may comprise DL RS resources comprising at least one of the following: subcarrier spacing; frequency information; time information; periodicity information; power information; scrambling information; QCL information; or at least one other physical layer property which allows detecting or measuring a RS resource.

[0097] In some example embodiments, the serving cell identity may be an NR-CGI, and the capability information of the terminal device may comprise at least one of applicable NR-CGIs or applicable network additional condition IDs in which can be indicated via capability reporting.

[0098] In some example embodiments, the terminal device 102 may determine that measurements of beams are at least one of a measurement of CSI-RS beams or a measurement of SSB beams based on the serving cell identity and the network additional condition ID.

[0099] In some example embodiments, the terminal device 102 may collect data corresponding to NZP-CSI-RS resource sets or CSI-SSB resource sets, in which a CSI-SSB resource set may be identified by a network additional condition ID. The terminal device 102 may categorize the collected data with respect to serving cell identities or network additional condition IDs as respective datasets.

[00100] In some example embodiments, the terminal device 102 may combine the datasets associated with respective network additional condition IDs. The terminal device 102 may associate, based on the network additional condition IDs, the datasets with respective ML models performed at the terminal device.

[00101] In some example embodiments, the terminal device 102 may train an ML model corresponding to one or more network additional condition IDs. In some example embodiments, the CSI reporting configuration for the beam predicting may comprises: a first reporting configuration for reporting measured beams applied as input of the ML model and a second reporting configuration for reporting predicted beams applied as output of the ML model associated with network additional condition IDs.

[00102] In some example embodiments, a CSI-SSB resource set may be associated with a SSB beam codebook and an NZP-CSI-RS resource set may be associated with a CSI-RS beams codebook.

[00103] In some example embodiments, the terminal device 102 may determine the ML model to be used for the beam predicting based on the network additional condition ID associated with the CSI reporting configuration and / or the NR-CGI.

[00104] In some example embodiments, the terminal device 102 may trigger to report an applicable network additional condition ID for the beam prediction. In some example embodiments, the terminal device 102 may receive the network additional condition ID associated with the ML model. In some example embodiments, the NR-CGI may be received via the SIB1 message.

[00105] Reference is made to FIG. 7, which illustrates an example flowchart of a process 700 of beam prediction implemented at a network device in accordance with some example embodiments of the present disclosure. FIG. 7 will be described with reference to FIG. 1 A.

[00106] At 702, the network device 104 transmits a data collection configuration comprising a plurality of lists of CSI resource configurations for data collection associated with ML models. A list of CSI resource configuration is associated with a serving cell through at least one of a serving cell identity in an SIB1 message associated with the serving cell or a network additional condition ID associated with a CSI reporting configuration for beam prediction.

[00107] At 704, the network device 104 receives a report for beam predicting considering capability information of the terminal device 102. At 706, the network device 104 determines a CSI reporting configuration for the beam predicting based on an indication via capability reporting of the terminal device 102. At 706, the network device 104 transmits the CSI reporting configuration. In some example embodiments, the UE capability signaling may be sent first, for example, prior to any of steps 702, 704 or 706.

[00108] In some example embodiments, the serving cell identity may be an NR-CGI. In some example embodiments, the network device 104 may determine whether beam prediction is supported in a certain CGI or determine a network additional condition ID associated with the CSI report.

[00109] In some example embodiments, the network device 104 may configure a first reporting configuration for measured beams applied as input of the ML model and a second reporting configuration for reporting predicted beams applied as output of the ML model associated with network additional condition IDs.

[00110] In some example embodiments, the serving cell identity may be an NR-CGI, and the capability information of the terminal device 102 may comprise at least one of applicable NR-CGIs or applicable network additional condition IDs in which can be indicated via capability reporting.

[00111] In some example embodiments, the network device 104 may determine to activate or select a CSI report which contains the applicable network additional condition IDs. In some example embodiments, the NR-CGI may be received via the SIB 1 message.

[00112] With some example embodiments of the processes 600 and 700, consistency of inference at the terminal device on CSI configurations can be achieved.

[00113] In some example embodiments, an apparatus capable of performing the process 600 (for example, the terminal device 102) may comprise means for performing the respective steps of the process 600. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module.

[00114] In some example embodiments, the apparatus may comprise means for receiving, at a terminal device, a data collection configuration comprising a plurality of lists of CSI resource configurations for data collection associated with ML models, wherein a list of CSI resource configuration is associated with a serving cell through at least one of a serving cell identity in an SIB1 message associated with the serving cell or a network additional condition ID associated with a CSI reporting configuration for beam prediction; means for collecting data for a measurement of beams determined based on the data collection configuration; means for transmitting, based on the collected data, a report for beam predicting considering capability information of the terminal device; means for receiving a CSI reporting configuration for the beam predicting; and means for applying an ML model trained with collected data for inference to be used for the beam predicting with respect to the serving cell identity and an associated network additional condition ID within the CSI reporting configuration.

[00115] In some example embodiments, the apparatus may further comprise means for determining that measurements of beams are at least one of a measurement of CSI-RS beams or a measurement of SSB beams based on the serving cell identity and the network additional condition ID.

[00116] In some example embodiments, the apparatus may further comprise means for collecting data corresponding to NZP-CSI-RS resource sets or CSLSSB resource sets, in which a CSLSSB resource set may be identified by a network additional condition ID; and means for categorizing the collected data with respect to serving cell identities or network additional condition IDs as respective datasets.

[00117] In some example embodiments, the apparatus may further comprise means for combining the datasets associated with respective network additional condition IDs; and means for associating, based on the network additional condition IDs, the datasets with respective ML models performed at the terminal device.

[00118] In some example embodiments, the apparatus may further comprise means for training an ML model corresponding to one or more network additional condition IDs.

[00119] In some example embodiments, the apparatus may further comprise means for determining the ML model to be used for the beam predicting based on the network additional condition ID associated with the CSI reporting configuration and / or the NR-CGI.

[00120] In some example embodiments, the apparatus may further comprise means for triggering to report an applicable network additional condition ID for the beam prediction; and means for receiving the network additional condition ID associated with the ML model.

[00121] In some example embodiments, the apparatus may further comprise means for performing other steps in some example embodiments of the process 600. In some example embodiments, the means comprises at least one processor and at least one memory including computer program code, the at least one memory and computer program code configured to, with the at least one processor, cause the performance of the apparatus.

[00122] In some example embodiments, an apparatus capable of performing the process 700 (for example, the network device 104) may comprise means for performing the respective steps of the process 700. The means may be implemented in any suitable form. For example, the means may be implemented in a circuitry or software module.

[00123] In some example embodiments, the apparatus may comprise means for transmitting, at a network device, a data collection configuration comprising a plurality of lists of CSI resource configurations for data collection associated with ML models, wherein a list of CSI resource configuration is associated with a serving cell through at least one of a serving cell identity in an SIB I message associated with the serving cell or a network additional condition ID associated with a CSI reporting configuration for beam prediction; means for receiving a report for beam predicting considering capability information of the terminal device; means for determining a CSI reporting configuration for the beam predicting based on an indication via capability reporting of the terminal device; and means for transmitting the CSI reporting configuration.

[00124] In some example embodiments, the apparatus may further comprise means for determining whether beam prediction is supported in a certain CGI or determine a network additional condition ID associated with the CSI report.

[00125] In some example embodiments, the apparatus may further comprise means for configuring a first reporting configuration for measured beams applied as input of the ML model and a second reporting configuration for reporting predicted beams applied as output of the ML model associated with network additional condition IDs.

[00126] In some example embodiments, the apparatus may further comprise means for determining to activate or select a CSI report which contains the applicable network additional condition IDs.

[00127] In some example embodiments, the apparatus may further comprise means for performing other steps in some example embodiments of the process 700. In some example embodiments, the means comprises at least one processor and at least one memory including computer program code, the at least one memory and computer program code configured to, with the at least one processor, cause the performance of the apparatus.

[00128] Reference is made to FIG. 8, which illustrates an example simplified block diagram of a device 800 that is suitable for implementing embodiments of the present disclosure. The device 800 may be provided to implement the communication device, for example the terminal device 102 as shown in FIG. 1A. As shown, the device 800 includes one or more processors 810, one or more memories 820 may couple to the processor 810, and one or more communication modules 840 may couple to the processor 810.

[00129] The communication module 840 is for bidirectional communications. The communication module 840 has at least one antenna to facilitate communication. The communication interface may represent any interface that is necessary for communication with other network elements, for example the communication interface may be wireless or wireline to other network elements, or software based interface for communication.

[00130] The processor 810 may be of any type suitable to the local technical network and may include one or more of the following: general purpose computers, special purpose computers, microprocessors, digital signal processors (DSPs) and processors based on multicore processor architecture, as non-limiting examples. The device 800 may have multiple processors, such as an application specific integrated circuit chip that is slaved in time to a clock which synchronizes the main processor.

[00131] The memory 820 may include one or more non-volatile memories and one or more volatile memories. Examples of the non-volatile memories include, but are not limited to, a read only memory (ROM) 824, an electrically programmable read only memory (EPROM), a flash memory, a hard disk, a compact disc (CD), a digital video disk (DVD), and other magnetic storage and / or optical storage. Examples of the volatile memories include, but are not limited to, a random access memory (RAM) 822 and other volatile memories that will not last in the power-down duration.

[00132] A computer program 830 includes computer executable instructions that are executed by the associated processor 810. The program 830 may be stored in the ROM 824. The processor 810 may perform any suitable actions and processing by loading the program 830 into the RAM 822.

[00133] The embodiments of the present disclosure may be implemented by means of the program so that the device 800 may perform any process of the disclosure as discussed with reference to FIG. 2 to FIG. 7. The embodiments of the present disclosure may also be implemented by hardware or by a combination of software and hardware.

[00134] In some example embodiments, the program 830 may be tangibly contained in a computer readable medium which may be included in the device 800 (such as in the memory 820) or other storage devices that are accessible by the device 800. The device 800 may load the program 830 from the computer readable medium to the RAM 822 for execution. The computer readable medium may include any types of tangible non-volatile storage, such as ROM, EPROM, a flash memory, a hard disk, CD, DVD, and the like. FIG. 9 shows an example of the computer readable medium 900 in form of CD or DVD. The computer readable medium has the program 830 stored thereon.

[00135] Generally, various embodiments of the present disclosure may be implemented in hardware or special purpose circuits, software, logic or any combination thereof. Some aspects may be implemented in hardware, while other aspects may be implemented in firmware or software which may be executed by a controller, microprocessor or other computing device. While various aspects of embodiments of the present disclosure are illustrated and described as block diagrams, flowcharts, or using some other pictorial representations, it is to be understood that the block, apparatus, system, technique or method described herein may be implemented in, as non-limiting examples, hardware, software, firmware, special purpose circuits or logic, general purpose hardware or controller or other computing devices, or some combination thereof.

[00136] The present disclosure also provides at least one computer program product tangibly stored on a non-transitory computer readable storage medium. The computer program product includes computer-executable instructions, such as those included in program modules, being executed in a device on a target real or virtual processor, to carry out the processes 600 or 700 as described above with reference to FIG. 6 or FIG. 7. Generally, program modules include routines, programs, libraries, objects, classes, components, data structures, or the like that perform particular tasks or implement particular abstract data types. The functionality of the program modules may be combined or split between program modules as desired in various embodiments. Machine-executable instructions for program modules may be executed within a local or distributed device. In a distributed device, program modules may be located in both local and remote storage media.

[00137] Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may execute entirely on a machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

[00138] In the context of the present disclosure, the computer program codes or related data may be carried by any suitable carrier to enable the device, apparatus or processor to perform various processes and operations as described above. Examples of the carrier include a signal, computer readable medium, and the like.

[00139] The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable medium may include but not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the computer readable storage medium would include an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. The term “non-transitory,” as used herein, is a limitation of the medium itself (i.e., tangible, not a signal) as opposed to a limitation on data storage persistency (e.g., RAM vs. ROM).

[00140] Further, while operations are depicted in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. In certain circumstances, multitasking and parallel processing may be advantageous. Likewise, while several specific implementation details are contained in the above discussions, these should not be construed as limitations on the scope of the present disclosure, but rather as descriptions of features that may be specific to particular 5 embodiments. Certain features that are described in the context of separate embodiments may also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment may also be implemented in multiple embodiments separately or in any suitable sub-combination.

[00141] Although the present disclosure has been described in languages specific to 10 structural features and / or methodological acts, it is to be understood that the present disclosure defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are disclosed as example forms of implementing the claims.

Claims

1. A terminal device comprising:at least one processor; andat least one memory storing instructions that, when executed by the at least one processor, cause the terminal device at least to:receive a data collection configuration comprising a plurality of lists of channel state information (CSI) resource configurations for data collection associated with machine learning (ML) models, wherein a list of CSI resource configuration is associated with a serving cell through at least one of a serving cell identity in a system information block type 1 (SIB1) message associated with the serving cell or a network additional condition identifier (ID) associated with a CSI reporting configuration for beam prediction;collect data for a measurement of beams determined based on the data collection configuration;transmit, based on the collected data, a report for beam predicting considering capability information of the terminal device;receive a CSI reporting configuration for the beam predicting; andapply an ML model trained with collected data for inference to be used for the beam predicting with respect to the serving cell identity and an associated network additional condition ID within the CSI reporting configuration.

2. The terminal device of claim 1, wherein a list of CSI resource configuration comprises a plurality of CSI resource configurations for the data collection, andwherein a CSI resource configuration for the data collection comprises at least one of the following:at least one non-zero power CSI reference signal (NZP-CSI-RS) resource set; orat least one CSI- synchronization signal block (CSI-SSB) resource set.

3. The terminal device of claim 1 or 2, wherein the collected data comprises downlink (DL) RS resources comprising at least one of the following:subcarrier spacing;frequency information;time information;periodicity information;power information;scrambling information;quasi co-location (QCL) information; orat least one other physical layer property which allows detecting or measuring a RS resource.

4. The terminal device of any of claims 1-3, wherein the serving cell identity is a new radio cell global identity (NR-CGI), and wherein the capability information of the terminal device comprises at least one of applicable NR-CGIs or applicable network additional condition IDs in which is capable of being indicated via capability reporting.

5. The terminal device of any of claims 1-4, wherein the measurement of beams is determined by:determining that measurements of beams are at least one of a measurement of CSL RS beams or a measurement of SSB beams based on the serving cell identity and the network additional condition ID.

6. The terminal device of any of claims 2-5, wherein the terminal device is further caused to:collect data corresponding to NZP-CSI-RS resource sets or CSI-SSB resource sets, wherein a CSI-SSB resource set is identified by a network additional condition ID; andcategorize the collected data with respect to serving cell identities or network additional condition IDs as respective datasets.

7. The terminal device of claim 6, wherein the terminal device is further caused to:combine the datasets associated with respective network additional condition IDs; andassociate, based on the network additional condition IDs, the datasets with respective ML models performed at the terminal device.

8. The terminal device of any of claims 1-7, wherein the terminal device is further caused to:train an ML model corresponding to one or more network additional condition IDs.

9. The terminal device of any of claims 1-8, wherein the CSI reporting configuration for the beam predicting comprises:a first reporting configuration for reporting measured beams applied as input of the ML model and a second reporting configuration for reporting predicted beams applied as output of the ML model associated with network additional condition IDs.

10. The terminal device of any of claims 1-9, wherein a CSLSSB resource set is associated with a SSB beam codebook and an NZP-CSLRS resource set is associated with a CSLRS beams codebook.

11. The terminal device of any of claims 4-10, wherein the terminal device is caused to apply the ML model trained with the collected data for inference by:determining the ML model to be used for the beam predicting based on the additional condition ID associated with the CSI reporting configuration and / or the NR-CGI.

12. The terminal device of claim 11, wherein the terminal device is further caused to: trigger to report an applicable network additional condition ID for the beam prediction.

13. The terminal device of any of claims 1-10, wherein the terminal device is caused to apply the ML model trained with the collected data for inference by:receiving the network additional condition ID associated with the ML model.

14. The terminal device of any of claims 1-13, wherein the NR-CGI is received via the SIB1 message.

15. A network device comprising:at least one processor; andat least one memory storing instructions that, when executed by the at least one processor, cause the network device at least to:transmit a data collection configuration comprising a plurality of lists of channel state information (CSI) resource configurations for data collection associated with machine learning (ML) models, wherein a list of CSI resource configuration is associated with a serving cell through at least one of a serving cell identity in a system information blocktype 1 (SIB1) message associated with the serving cell or a network additional condition identifier (ID) associated with a CSI reporting configuration for beam prediction;receive a report for beam predicting considering capability information of the terminal device;determine a CSI reporting configuration for the beam predicting based on an indication via capability reporting of the terminal device; andtransmit the CSI reporting configuration.

16. The network device of claim 15, wherein the serving cell identity is a new radio cell global identity (NR-CG1), and wherein the network device is further caused to determine the CSI reporting configuration by:determining whether beam prediction is supported in a certain CGI; anddetermining a network additional condition ID associated with the CSI report.

17. The network device of claim 15 or 16, wherein the network device is further caused to:configure a first reporting configuration for measured beams applied as input of the ML model and a second reporting configuration for reporting predicted beams applied as output of the ML model associated with network additional condition IDs.

18. The network device of any of claims 15-17, wherein the capability information of the terminal device comprises at least one of applicable NR-CGIs or applicable network additional condition IDs in which is capable of being indicated via the capability reporting.

19. The network device of claim 18, wherein the network device is further caused to: determine to activate or select a CSI report which contains the applicable network additional condition IDs.

20. The network device of any of claims 15-19, wherein the NR-CGI is transmitted via the SIB1 message.

21. A method comprising:receiving, at a terminal device, a data collection configuration comprising a plurality of lists of channel state information (CSI) resource configurations for data collectionassociated with machine learning (ML) models, wherein a list of CSI resource configuration is associated with a serving cell through at least one of a serving cell identity in a system information block type 1 (SIB1) message associated with the serving cell or a network additional condition identifier (ID) associated with a CSI reporting configuration for beam prediction;collecting data for a measurement of beams determined based on the data collection configuration;transmitting, based on the collected data, a report for beam predicting considering capability information of the terminal device;receiving a CSI reporting configuration for the beam predicting; andapplying an ML model trained with collected data for inference to be used for the beam predicting with respect to the serving cell identity and an associated network additional condition ID within the CSI reporting configuration.

22. A method comprising:transmitting, at a network device, a data collection configuration comprising a plurality of lists of channel state information (CSI) resource configurations for data collection associated with machine learning (ML) models, wherein a list of CSI resource configuration is associated with a serving cell through at least one of a serving cell identity in a system information block type 1 (SIB1) message associated with the serving cell or a network additional condition identifier (ID) associated with a CSI reporting configuration for beam prediction;receiving a report for beam predicting considering capability information of the terminal device;determining a CSI reporting configuration for the beam predicting based on an indication via capability reporting of the terminal device; andtransmitting the CSI reporting configuration.

23. An apparatus comprising:means for receiving, at a terminal device, a data collection configuration comprising a plurality of lists of channel state information (CSI) resource configurations for data collection associated with machine learning (ML) models, wherein a list of CSI resource configuration is associated with a serving cell through at least one of a serving cell identity in a system information block type 1 (SIB1) message associated with the serving cell or anetwork additional condition identifier (ID) associated with a CSI reporting configuration for beam prediction;means for collecting data for a measurement of beams determined based on the data collection configuration;means for transmitting, based on the collected data, a report for beam predicting considering capability information of the terminal device;means for receiving a CSI reporting configuration for the beam predicting; andmeans for applying an ML model trained with collected data for inference to be used for the beam predicting with respect to the serving cell identity and an associated network additional condition ID within the CSI reporting configuration.

24. An apparatus comprising:means for transmitting, at a network device, a data collection configuration comprising a plurality of lists of channel state information (CSI) resource configurations for data collection associated with machine learning (ML) models, wherein a list of CSI resource configuration is associated with a serving cell through at least one of a serving cell identity in a system information block type 1 (SIB1) message associated with the serving cell or a network additional condition identifier (ID) associated with a CSI reporting configuration for beam prediction;means for receiving a report for beam predicting considering capability information of the terminal device;means for determining a CSI reporting configuration for the beam predicting based on an indication via capability reporting of the terminal device; andmeans for transmitting the CSI reporting configuration.

25. Anon-transitory computer readable medium comprising program instructions for causing an apparatus to perform at least the method of claim 21 or 22.

Images