Method performed by electronic apparatus and electronic apparatus in a wireless communication system

Abstract

The present disclosure relates to a 5G communication system or a 6G communication system for supporting higher data rates beyond a 4G communication system such as long term evolution (LTE). The present application relates to a method performed by an electronic apparatus and an electronic apparatus, the method includes: obtaining a first reference signal pattern; performing channel estimation, based on Channel State Information (CSI) measured using a reference signal associated with the first reference signal pattern, wherein the first reference signal pattern is associated with a second reference signal pattern that is determined according to a plurality of sparse weight factors and at least one candidate reference signal pattern set, the plurality of sparse weight factors are obtained by training the first AI model, and each of the plurality of sparse weight factors represents　a degree of importance of an spatial-domain position and / or a frequency-domain position associated with a resource of the corresponding reference signal with respect to channel estimation.

Description

METHOD PERFORMED BY ELECTRONIC APPARATUS AND ELECTRONIC APPARATUS IN A WIRELESS COMMUNICATION SYSTEM

[0001] The present application relates to a field of wireless communication, and specifically, the present application relates to a method performed by an electronic apparatus and the electronic apparatus.

[0002] Considering the development of wireless communication from generation to generation, the technologies have been developed mainly for services targeting humans, such as voice calls, multimedia services, and data services. Following the commercialization of 5G (5th generation) communication systems, it is expected that the number of connected devices will exponentially grow. Increasingly, these will be connected to communication networks. Examples of connected things may include vehicles, robots, drones, home appliances, displays, smart sensors connected to various infrastructures, construction machines, and factory equipment. Mobile devices are expected to evolve in various form-factors, such as augmented reality glasses, virtual reality headsets, and hologram devices. In order to provide various services by connecting hundreds of billions of devices and things in the 6G (6th generation) era, there have been ongoing efforts to develop improved 6G communication systems. For these reasons, 6G communication systems are referred to as beyond-5G systems.

[0003] 6G communication systems, which are expected to be commercialized around 2030, will have a peak data rate of tera (1,000 giga)-level bit per second (bps) and a radio latency less than 100μsec, and thus will be 50 times as fast as 5G communication systems and have the 1 / 10 radio latency thereof.

[0004] In order to accomplish such a high data rate and an ultra-low latency, it has been considered to implement 6G communication systems in a terahertz (THz) band (for example, 95 gigahertz (GHz) to 3THz bands). It is expected that, due to severer path loss and atmospheric absorption in the terahertz bands than those in mmWave bands introduced in 5G, technologies capable of securing the signal transmission distance (that is, coverage) will become more crucial. It is necessary to develop, as major technologies for securing the coverage, Radio Frequency (RF) elements, antennas, novel waveforms having a better coverage than Orthogonal Frequency Division Multiplexing (OFDM), beamforming and massive Multiple-input Multiple-Output (MIMO), Full Dimensional MIMO (FD-MIMO), array antennas, and multiantenna transmission technologies such as large-scale antennas. In addition, there has been ongoing discussion on new technologies for improving the coverage of terahertz-band signals, such as metamaterial-based lenses and antennas, Orbital Angular Momentum (OAM), and Reconfigurable Intelligent Surface (RIS).

[0005] Moreover, in order to improve the spectral efficiency and the overall network performances, the following technologies have been developed for 6G communication systems: a full-duplex technology for enabling an uplink transmission and a downlink transmission to simultaneously use the same frequency resource at the same time; a network technology for utilizing satellites, High-Altitude Platform Stations (HAPS), and the like in an integrated manner; an improved network structure for supporting mobile base stations and the like and enabling network operation optimization and automation and the like; a dynamic spectrum sharing technology via collision avoidance based on a prediction of spectrum usage; an use of Artificial Intelligence (AI) in wireless communication for improvement of overall network operation by utilizing AI from a designing phase for developing 6G and internalizing end-to-end AI support functions; and a next-generation distributed computing technology for overcoming the limit of UE computing ability through reachable super-high-performance communication and computing resources (such as Mobile Edge Computing (MEC), clouds, and the like) over the network. In addition, through designing new protocols to be used in 6G communication systems, developing mechanisms for implementing a hardware-based security environment and safe use of data, and developing technologies for maintaining privacy, attempts to strengthen the connectivity between devices, optimize the network, promote softwarization of network entities, and increase the openness of wireless communications are continuing.

[0006] It is expected that research and development of 6G communication systems in hyper-connectivity, including person to machine (P2M) as well as machine to machine (M2M), will allow the next hyper-connected experience. Particularly, it is expected that services such as truly immersive eXtended Reality (XR), high-fidelity mobile hologram, and digital replica could be provided through 6G communication systems. In addition, services such as remote surgery for security and reliability enhancement, industrial automation, and emergency response will be provided through the 6G communication system such that the technologies could be applied in various fields such as industry, medical care, automobiles, and home appliances.

[0007] The present disclosure relates to method performed by electronic apparatus and electronic apparatus in a wireless communication system.

[0008] According to an aspect of an exemplary embodiment, there is provided a communication method in a wireless communication system.

[0009] Aspects of the present disclosure provide efficient communication methods in a wireless communication system.

[0010] In order to more clearly and easily explain and understand technical solutions in embodiments of the present application, a brief introduction will be given to the accompanying drawings required in the description of the embodiments of the present application below.

[0011] FIG. 1 illustrates an example wireless network according to an embodiment of the present disclosure.

[0012] FIG. 2 illustrates an example base station according to an embodiment of the present disclosure.

[0013] FIG. 3 illustrates an example user equipment according to an embodiment of the present disclosure.

[0014] FIG. 4 is a diagram illustrating a reference signal and channel estimation method in a Multiple-Input Multiple-Output (MIMO) system.

[0015] FIG. 5 is a diagram illustrating an example of a reference signal pattern.

[0016] FIG. 6A is a flowchart of a method performed by an electronic apparatus according to an exemplary embodiment of the present disclosure.

[0017] FIG. 6B is a schematic diagram illustrating a structure of a reference signal pattern design and channel estimation module according to exemplary embodiments of the present application.

[0018] FIG. 6C is a schematic diagram illustrating a structure of a reference signal design and channel estimation module according to another exemplary embodiment of the present application.

[0019] FIG. 6D is a schematic diagram illustrating a structure of a reference signal design and channel estimation module according to another exemplary embodiment of the present application.

[0020] FIG. 6E is a schematic diagram illustrating a structure of a reference signal design and channel estimation module according to another exemplary embodiment of the present application.

[0021] FIG. 7 is a diagram illustrating a structure of a sparse reference signal and channel estimation module according to an exemplary embodiment of the present application.

[0022] FIG.8 is a schematic illustrating a KL divergence when a sparsity ratio is a specific value (i.e., ρ=0.2).

[0023] FIG. 9 is a diagram illustrating a result of weight factors after a certain number of epochs of training.

[0024] FIG. 10 is a flowchart illustrating a procedure for determining a second reference signal pattern according to an exemplary embodiment of the present application.

[0025] FIG. 11 is a schematic diagram illustrating a procedure for determining a second reference signal pattern according to an exemplary embodiment of the present application.

[0026] FIG. 12A is a flowchart illustrating a procedure for performing channel estimation when an electronic apparatus is a base station, according to an exemplary embodiment of the present application.

[0027] FIG. 12B illustrates an air interface process when an electronic apparatus is a base station (i.e., when a first AI model and a second AI model are deployed on the base station).

[0028] FIG. 13A illustrates an example of configuration information indicating Channel State Information (CSI) via DCI format 2-X.

[0029] FIG. 13B is a diagram illustrating an example of indicating a reference signal pattern via time-domain resources and / or frequency-domain resources of a CSI-RS according to an exemplary embodiment of the present application.

[0030] FIG. 14A is a flowchart illustrating a procedure for performing channel estimation when an electronic apparatus is a UE, according to an exemplary embodiment of the present application.

[0031] FIG. 14B illustrates an air interface process when an electronic apparatus is a UE (i.e., when a first AI model and a second AI model are deployed on the base station).

[0032] FIG. 15 is a schematic diagram illustrating a procedure for determining a monitoring reference signal pattern according to an exemplary embodiment of the present application.

[0033] FIG. 16 is a schematic diagram illustrating a procedure for triggering update according to an exemplary embodiment of the present application.

[0034] FIG. 17 is a schematic diagram illustrating a procedure of a data pre-processing operation according to exemplary embodiments of the present application.

[0035] FIG. 18 is a flowchart illustrating a procedure for compressing a channel matrix of a UE to obtain a compressed channel matrix according to an exemplary embodiment of the present application.

[0036] FIG. 19A is a schematic illustrating a procedure for obtaining a time-invariant frequency-domain channel feature according to an exemplary embodiment of the present application.

[0037] FIG. 19B is a schematic illustrating a procedure for obtaining a compressed channel matrix according to an exemplary embodiment of the present application.

[0038] FIG. 19C is a schematic illustrating a procedure for obtaining a channel matrix corresponding to a full spatial-domain position and a full frequency-domain position according to an exemplary embodiment of the present application.

[0039] FIG. 20 is a diagram illustrating an example of grouping UEs when the UEs are in different positions according to an exemplary embodiment of the present application.

[0040] FIG. 21A is an air interface flow diagram when an AI model is deployed on a base station according to an exemplary embodiment of the present application.

[0041] FIG. 21B is a schematic diagram illustrating an example procedure for designing a reference signal pattern in a case where UEs are grouped when an electronic apparatus is a base station according to an exemplary embodiment of the present application.

[0042] FIG. 22 is a schematic diagram illustrating a procedure for grouping UEs and determining a reference signal pattern for the same group of UEs according to an exemplary embodiment of the present application.

[0043] FIG. 23 is an air interface flow diagram when an AI model is deployed on a UE according to an exemplary embodiment of the present application.

[0044] FIG. 24A is a diagram illustrating an overall process for determining a reference signal pattern in a case where a first AI model and a second AI model are deployed on a base station according to an exemplary embodiment of the present application.

[0045] FIG. 24B is a flowchart illustrating a method performed by an electronic apparatus according to another exemplary embodiment of the present application.

[0046] FIG. 25 is a block diagram illustrating an electronic apparatus according to an exemplary embodiment of the present disclosure.

[0047] FIG. 26 illustrates a block diagram of a user equipment, according to embodiments of the present disclosure.

[0048] FIG. 27 illustrates a block diagram of a base station, according to embodiments of the present disclosure.

[0049] FIG. 28 illustrates a block diagram of a network entity, according to embodiments of the present disclosure.

[0050] The purpose of the present application is aimed at addressing at least one of technical deficiencies in the existing communication manners, so as to better meet communication requirements. In order to achieve this purpose, technical solutions proposed in the present application are as follows.

[0051] According to a first aspect of an embodiment of the present application, a method performed by an electronic apparatus is provided, which includes: obtaining a first reference signal pattern; performing channel estimation, based on Channel State Information (CSI) measured using a reference signal associated with the first reference signal pattern, wherein the first reference signal pattern is associated with a second reference signal pattern that is determined according to a plurality of sparse weight factors and at least one candidate reference signal pattern set, the plurality of sparse weight factors are obtained by training the first AI model, and each of the plurality of sparse weight factors represents　a degree of importance of an spatial-domain position and / or a frequency-domain position associated with a resource of the corresponding reference signal with respect to channel estimation.

[0052] Alternatively, the training the first AI model includes: determining a first loss function, according to KL divergences corresponding to mapping coefficients between inputs and outputs of a first sub-network in the first AI model and / or a channel estimation error; training the first AI model using a first training dataset, according to the first loss function, wherein the mapping coefficients in the trained first AI model are determined as the plurality of sparse weight factors.

[0053] Alternatively, the second reference pattern is determined according to the plurality of sparse weight factors and the at least one candidate reference signal pattern set by: performing a dimensional conversion on the plurality of sparse weight factors; selecting one candidate reference signal pattern from among each candidate reference signal pattern set by: generating a plurality of pattern-based sparse weight factors based on the plurality of sparse weight factors after the dimensional conversion and a candidate reference signal pattern set, and selecting one candidate reference signal pattern among the candidate reference signal pattern set according to the plurality of pattern-based sparse weight factors; and determining a candidate reference signal pattern satisfying a predetermined condition in the selected at least one candidate reference signal pattern as the second reference signal pattern.

[0054] Alternatively, each candidate reference signal pattern set is predefined, or is determined by predefined parameters for the reference signal pattern set.

[0055] Alternatively, the generating the plurality of pattern-based sparse weight factors based on the plurality of sparse weight factors after the dimensional conversion and the candidate reference signal pattern set includes: for each candidate reference signal pattern in the candidate reference signal pattern set, obtaining the pattern-based sparse weight factor by: summing sparse weight factors corresponding to each transmitting antenna and each frequency-domain position on the candidate reference signal pattern, to obtain the pattern-based sparse weight factor of the candidate reference signal pattern with respect to each receiving antenna.

[0056] Alternatively, the selecting one candidate reference signal pattern in the candidate reference signal pattern set according to the plurality of pattern-based sparse weight factors includes: determining a largest pattern-based sparse weight factor from among the plurality of pattern-based sparse weight factors; selecting one candidate reference signal pattern corresponding to the largest pattern-based sparse weight factor from among the candidate reference signal pattern set.

[0057] Alternatively, the selecting one candidate reference signal pattern in the candidate reference signal pattern set according to the plurality of pattern-based sparse weight factors includes: by summing or averaging weight factors corresponding to the respective candidate reference signal patterns on different receiving antennas in the plurality of pattern-based sparse weight factors, obtaining weight sums or weight averages corresponding to the respective candidate reference signal patterns; selecting one candidate reference signal pattern corresponding to the largest of the weight sums or the weight averages from among the candidate reference signal pattern set.

[0058] Alternatively, when the electronic apparatus is a base station, the performing the channel estimation based on the Channel State Information (CSI) measured using the reference signal associated with the first reference signal pattern includes: transmitting, to the UE, information associated with the first reference signal pattern and / or Channel State Information (CSI) feedback configuration, wherein the first reference signal pattern is the second reference signal pattern or is determined by the base station according to the second reference signal pattern; transmitting, to a UE, the reference signal based on the first reference signal pattern; receiving, from the UE, the CSI measured using the reference signal; performing the channel estimation through a second AI model, according to the CSI.

[0059] Alternatively, the information associated with the first reference signal pattern is transmitted to the UE via Downlink Control Information (DCI) signaling, Media Access Control (MAC) Control Element (CE) signaling, or radio resource control (RRC) signaling.

[0060] Alternatively, the DCI signaling, the MAC CE signaling, or the RRC signaling includes at least one of information for indicating a spatial-domain and / or frequency-domain associated with the first reference signal pattern, information for indicating one of at least one predefined reference signal pattern, or the information for indicating one of the at least one predefined reference signal pattern and information associated with an offset of the first reference signal pattern.

[0061] Alternatively, the information for indicating the spatial-domain and / or frequency-domain associated with the first reference signal pattern includes starting values of spatial-domain positions and / or frequency-domain positions of reference signals, an interval of the spatial-domain positions and / or the frequency-domain positions, the number of the spatial-domain positions and / or the frequency-domain positions.

[0062] Alternatively, the DCI signaling, the MAC CE signaling or the RRC signaling includes information indicating a resource for transmitting the reference signal, and there is a mapping relationship between the resource for transmitting the reference signal and the first reference signal pattern.

[0063] Alternatively, the mapping relationship is determined based on at least two of parameters: a sequence number of the reference signal, a size of a Code Division Multiplexing (CDM) group, the number of CDM groups, the number of antenna ports for the reference signal, a time-domain position and a frequency-domain position of the reference signal.

[0064] Alternatively, the CSI feedback configuration is used to indicate feedback of a quantized CSI phase and amplitude of the reference signal on the receiving antenna.

[0065] Alternatively, the quantized CSI phase is represented by 3 bits and the quantized CSI amplitude is represented by 4 bits, or the quantized CSI phase is represented by 4 bits and the quantized CSI amplitude is represented by 3 bits.

[0066] Alternatively, the quantized CSI phase and amplitude are one of: a quantized CSI phase and amplitude of a reference signal on one receiving antenna, wherein the one receiving antenna is indicated via DCI signaling, MAC-CE signaling, or RRC signaling; and quantized CSI phases and amplitudes of reference signals on all receiving antennas.

[0067] Alternatively, when the electronic apparatus is a UE, the performing the channel estimation based on the Channel State Information (CSI) measured using the reference signal associated with the first reference signal pattern includes: transmitting, to a base station, information associated with the second reference signal pattern; receiving, from the base station, information associated with the first reference signal pattern; receiving, from the base station, the reference signal corresponding to the first reference signal pattern; performing the channel estimation through a second AI model, according to the CSI measured using the reference signal, wherein the first reference signal pattern is the second reference signal pattern or is determined by the base station according to the second reference signal pattern.

[0068] Alternatively, the transmitting, to the base station, the information associated with the second reference signal pattern includes: sorting reference signals in the second reference signal pattern according to importance of the reference signals in the second reference signal pattern, wherein the importance is determined at least according to values of sparse weight factors; transmitting, to the base station, information about the top G reference signals with highest importance in the second reference signal pattern, wherein G is an integer greater than or equal to 1 and is configured by the base station via RRC signaling, MAC CE signaling, or DCI signaling.

[0069] Alternatively, the second AI model is trained by: generating a second training dataset from a first training dataset used in training the first AI model, according to the second reference signal pattern; training the second AI model using the second training dataset.

[0070] Alternatively, the method further includes: determining whether to update the first reference signal pattern and the second AI model.

[0071] Alternatively, when the electronic apparatus is the base station, the determining whether to update the first reference signal pattern and the second AI model includes: transmitting a monitoring reference signal to the UE periodically or when a degradation in system performance is detected by the base station; determining whether to update the first reference signal pattern and the second AI model, according to the channel information measured using the monitoring reference signal and the channel information estimated by the second AI model.

[0072] Alternatively, when the electronic apparatus is the UE, the determining whether to update the first reference signal pattern and the second AI model includes: receiving the monitoring reference signal from the base station periodically, or requesting the monitoring reference signal from the base station when the UE detects a degradation in the system performance and receiving the monitoring reference signal from the base station; determining whether to update the first reference signal pattern and the second AI model, according to the channel information measured using the monitoring reference signal and the channel information estimated by the second AI model.

[0073] Alternatively, the determining whether to update the first reference signal pattern and the second AI model according to the channel information measured using the monitoring reference signal and the channel information estimated by the second AI model includes: determining a Normalized Mean Square Error (NMSE) of the channel information measured using the monitoring reference signal and the channel information estimated by the second AI model; if the NMSE is greater than a first threshold, determining to update the first reference signal pattern and the second AI mode.

[0074] Alternatively, the determining whether to update the first reference signal pattern and the second AI model includes: determining to update the first reference signal pattern and the second AI model when the electronic apparatus detects a degradation in the system performance.

[0075] Alternatively, when the electronic apparatus is the base station, the determining whether to update the first reference signal pattern and the second AI model may include: when the base station detects a degradation in the system performance and a specific uplink resource of the UE is available, receiving a Sounding Reference Signal (SRS) from the UE via the specific uplink resource; determining whether to update the first reference signal pattern and the second AI model according to the channel information measured using the SRS and the channel information estimated by the second AI model.

[0076] Alternatively, the determining whether to update the first reference signal pattern and the second AI model according to the channel information measured using the SRS and the channel information estimated by the second AI model includes: determining a Cosine Similarity (SGCS) of the channel information measured using the SRS and the channel information estimated by the second AI model; if the SGCS is less than a second threshold, determining to update the first reference signal pattern and the second AI model.

[0077] Alternatively, when the electronic apparatus is the UE, in a case of determining to update the first reference signal pattern and the second AI model, the method further includes: transmitting, to the base station, a request for update of the reference signal pattern; receiving, from the base station, third training data; determining a third reference signal pattern, based on the third training data and the first AI model; transmitting, to the base station, information associated with the third reference signal pattern, and receiving, from the base station, information associated with a fourth reference signal pattern to be applied to the UE, wherein the fourth reference signal pattern may be the third reference signal pattern or may be determined by the base station according to the third reference signal pattern.

[0078] Alternatively, the monitoring reference signal is determined according to a monitoring reference signal pattern or by multiplexing　 an existing reference signal, wherein the monitoring reference signal pattern is determined according to one of manners: determining the monitoring reference signal pattern according to a position of a reference signal corresponding to a NMSE that is below a third threshold in training procedure of the second AI model; sorting the reference signals based on magnitudes of NMSEs in training procedure of the second AI model, and determining the monitoring reference signal pattern according to positions of the top W reference signals with lowest NMSE among the sorted reference signals; and determining the monitoring reference signal pattern from the first reference signal pattern according to a predetermined offset.

[0079] Alternatively, the monitoring reference signal pattern is not overlapped with the reference signal pattern.

[0080] Alternatively, the plurality of sparse weight factors are obtained by training the first AI model using a compressed channel matrix, wherein the compressed channel matrix is obtained by compressing a channel matrix of the UE.

[0081] Alternatively, the compressed channel matrix is obtained by compressing the channel matrix of the UE by: obtaining a time-invariant frequency-domain channel feature based on the channel matrix of the UE; based on the time-invariant frequency-domain channel feature, obtaining a time-invariant sparse frequency-domain channel feature, with minimizing an error power of a sparse frequency-domain channel feature; obtaining the compressed channel matrix based on the time-invariant sparse frequency-domain channel feature.

[0082] Alternatively, the method further includes: recovering a channel matrix that is obtained by the channel estimation through the second AI model to a channel matrix corresponding to full spatial-domain positions and full frequency-domain positions, by using the time-invariant frequency-domain channel feature and the time-invariant sparse frequency-domain channel feature.

[0083] Alternatively, the spatial-domain position is an antenna port or a beam.

[0084] Alternatively, the first reference signal pattern is obtained by the base station by: calculating a channel feature of each UE, wherein the channel feature includes at least one of position information, Reference Signal Received Power (RSRP), Line-of-Sight (LOS) / Non-Line-of-Sight (NLOS) state information, Doppler delay, and a direction angle; grouping UEs according to the calculated channel feature; determining a first reference signal pattern for UEs belonging to the same group of UEs, according to the second reference signal pattern.

[0085] Alternatively, the method further includes: when a reference signal pattern update request is received from a first UE in a first group of UEs, when the base station detects a degradation in transmission performance with respect to the first UE, when a NMSE of channel information estimated by the second AI model and channel information measured using a monitoring reference signal received from the first UE is greater than a first threshold, or when a SGCS of channel information measured using a SRS received from the first UE and the channel information estimated by the second AI model is less than a second threshold, re-determining a reference signal pattern to be indicated to the first UE.

[0086] Alternatively, the re-determining the reference signal pattern to be indicated to the first UE includes: when a channel feature of the first UE is similar to a channel feature of another group of UEs, grouping the first UE to the other group of UEs, and determining a reference signal pattern for the other group of UEs as the reference signal pattern to be indicated to the first UE; when the channel feature of the first UE is not similar to a channel feature of any group of UEs, for the first UE, determining a plurality of new sparse weight factors by training the first AI model, and re-determining the reference signal pattern to be indicated to the first UE according to the plurality of new sparse weight factors and at least one candidate reference signal pattern set.

[0087] Alternatively, the first reference signal pattern is determined by the base station according to the second reference signal pattern by: grouping UEs, by the base station, according to similarities between the second reference signal pattern and reference signal patterns of other UEs, and determining the first reference signal pattern for one group of UEs to which the UE belongs.

[0088] Alternatively, the method further includes: when the UE detects a degradation in transmission performance, transmitting a reference signal pattern update request to the base station; obtaining a plurality of new sparse weight factors according to the training of the first AI model using training data that is newly received from the base station; determining another reference signal pattern according to the plurality of new sparse weight factors and at least one candidate reference signal pattern set; transmitting information associated with this other reference signal pattern; receiving, from the base station, information associated with a reference signal pattern that is re-determined for this UE according to this other reference signal pattern.

[0089] According to a second aspect of an embodiment of the present application, a method performed by an electronic apparatus is provided, which includes: transmitting, to a UE, information associated with a first reference signal pattern and / or CSI feedback configuration via DCI signaling, MAC CE signaling, or RRC signaling, wherein the information associated with the first reference signal pattern is transmitted to the UE by: including, in the DCI signaling, the MAC CE signaling, or the RRC signaling, at least one of information for indicating a spatial-domain and / or frequency-domain associated with the first reference signal pattern, information for indicating one of at least one predefined reference signal patterns, or information for indicating one of the at least one predefined reference signal patterns and information associated with an offset of the first reference signal pattern; or including, in the DCI signaling, the MAC CE signaling, or the RRC signaling, information indicating a resource for transmitting a reference signal, wherein there is a mapping relationship between the resource for transmitting the reference signal and the first reference signal pattern.

[0090] Alternatively, the information for indicating the spatial-domain and / or frequency-domain associated with the first reference signal pattern includes starting values of spatial-domain positions and / or frequency-domain positions of reference signals, an interval of the spatial-domain positions and / or the frequency-domain positions, the number of the spatial-domain positions and / or the frequency-domain positions.

[0091] Alternatively, the mapping relationship is determined based on at least two of parameters: a sequence number of the reference signal, a size of a Code Division Multiplexing (CDM) group, the number of CDM groups, the number of antenna ports for the reference signal, a time-domain position and a frequency-domain position of the reference signal.

[0092] Alternatively, the CSI feedback configuration is used to indicate feedback of a quantized CSI phase and amplitude of the reference signal on the receiving antenna.

[0093] Alternatively, the quantized CSI phase is represented by 3 bits and the quantized CSI amplitude is represented by 4 bits, or the quantized CSI phase is represented by 4 bits and the quantized CSI amplitude is represented by 3 bits.

[0094] Alternatively, the quantized CSI phase and amplitude are one of: a quantized CSI phase and amplitude of a reference signal on one receiving antenna, wherein the one receiving antenna is indicated via DCI signaling, MAC-CE signaling, or RRC signaling; and quantized CSI phases and amplitudes of reference signals on all receiving antennas.

[0095] According to a third aspect of an embodiment of the present application, an electronic apparatus is provided, which includes: a transceiver for transmitting and receiving a signal; and a processor coupled to the transceiver and configured to perform the method as described above.

[0096] According to a fourth aspect of an embodiment of the present application, a computer-readable storage medium storing instructions is provided, wherein the instructions, when being executed by at least one processor, cause the at least one processor to perform the method as described above.

[0097] The beneficial effects brought by technical solutions provided by the embodiments of the present application will be described　in the following in combination with specific alternative embodiments, or may be learned from descriptions of the embodiments, or may be learned from implementation of the embodiments.

[0098] Hereinafter, embodiments of the disclosure will be described in detail with reference to the accompanying drawings.

[0099] In describing the embodiments, while numerous details are set forth for the purpose of illustration, it is understood that some aspects of the disclosure may be practiced with less than all of these details. Numerous variations and alternatives to the details provided herein are possible and are considered within the scope of the disclosure. In some instances, descriptions related to technical contents well-known in the art may be omitted so as to not obscure an understanding of the disclosure, and such omitted descriptions are understood to be within the scope of the disclosure.

[0100] For the same reason, in the accompanying drawings, some elements may be exaggerated, omitted, or schematically illustrated. Further, the size of each element does not completely reflect the actual size. In the drawings, identical or corresponding elements are provided with identical reference numerals or different reference numerals.

[0101] The advantages and features of the disclosure and ways to achieve them will be apparent by making reference to embodiments as described herein in detail in conjunction with the accompanying drawings. However, the disclosure is not limited to the embodiments set forth herein, but may be implemented in various different forms. Other features, aspects, and advantages of the subject matter described herein will become apparent from the disclosure. The following embodiments are merely examples to aid in an understanding of the disclosure and should not be construed to narrow the scope or spirit of the subject matter described herein in any way, but on the contrary, the disclosure covers all modifications, equivalents and alternatives falling within the spirit and scope of the subject matter as defined by the appended claims and equivalents thereof. Throughout the specification, the same or like reference numerals designate the same or like elements. Furthermore, terms which will be described herein are terms defined in consideration of the functions in the disclosure, and may be different according to users, intentions of the operators, or customs. Therefore, the definitions of the terms should be made based on the contents throughout the specification.

[0102] Herein, it will be understood that each block of flowchart illustrations, and combinations of blocks in the flowchart illustrations, may be performed based on computer program instructions. These computer program instructions may be loaded collectively onto at least one processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which perform through any one of, or in any combination of, the at least one processor of the computer or other programmable data processing apparatus, create means for performing the functions specified in the flowchart block(s). These computer program instructions may also be stored in a non-transitory computer usable or computer-readable memory that may direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer usable or computer-readable memory produce an article of manufacture including instruction means that perform the function specified in the flowchart block(s). The computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable data processing apparatus to produce a computer executed process such that the instructions that perform on the computer or other programmable data processing apparatus provide steps for executing the functions specified in the flowchart block(s).

[0103] Further, each block may represent a module, segment, or portion of code, which includes one or more executable instructions for executing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the blocks may occur out of the order. For example, two blocks(or functions) shown in succession may in fact be performed substantially concurrently or the blocks may sometimes be performed in the reverse order, depending upon the functionality involved.

[0104] As used in embodiments of the disclosure, a "~unit / module" may refer to a software element or a hardware element, such as a field programmable gate array (FPGA) or an application specific integrated circuit (ASIC), which performs a predetermined function. However, the term including the word "~unit / module" does not always have a meaning limited to software or hardware. The "~unit / module" may be constructed either to be stored in an addressable storage medium or to execute one or more processors. Therefore, the "~unit / module" includes, for example, software elements, object-oriented software elements, components such as class elements and task elements, processes, functions, properties, procedures, sub-routines, segments of a program code, drivers, firmware, micro-codes, circuits, data, database, data structures, tables, arrays, and parameters. The components and functions provided by the "~unit / module" may be either combined into a smaller number of components and a "~unit / module," or divided into additional components and a "~unit / module." Moreover, the components and "~units / modules" may be implemented to reproduce one or more central processing units (CPUs) within a device or a security multimedia card. Further, in the embodiments, the "~unit / module" may include one or more processors.

[0105] The entirety of the one or more computer programs may be stored in a single memory device or the one or more computer programs may be divided with different portions stored in different multiple memory devices.

[0106] Any of the functions or operations described herein can be processed by one processor or a combination of processors. The one processor or the combination of processors is circuitry performing processing and includes circuitry like an application processor (AP, e.g. a CPU), a communication processor (CP, e.g., a modem), a graphics processing unit (GPU), a neural processing unit (NPU) (e.g., an artificial intelligence (AI) chip), a Wi-Fi chip, a Bluetooth® chip, a global positioning system (GPS) chip, a near field communication (NFC) chip, connectivity chips, a sensor controller, a touch controller, a finger-print sensor controller, a display driver integrated circuit (IC), an audio CODEC chip, a universal serial bus (USB) controller, a camera controller, an image processing IC, microprocessors, microcontrollers, digital signal processors, FPGA, ASIC, a microprocessor unit (MPU), a system on chip (SoC), an IC, or the like. The one processor or the combination of processors executes instructions that can be stored in a memory, such as the operating system, in order to control the overall operation of the device. Also, the one processor or the combination of processors is also capable of executing other processes and programs resident in the memory, such as processes for the disclosure.

[0107] It will be appreciated that various embodiments of the disclosure according to the claims and description in the specification can be realized in the form of hardware, software or a combination of hardware and software.

[0108] Any such software may be stored in non-transitory computer readable storage media. The non-transitory computer readable storage media store one or more computer programs (software modules), the one or more computer programs include computer-executable instructions that, when executed by one or more processors of an electronic device individually or collectively, cause the electronic device to perform a method of the disclosure. Additionally, or alternatively, such software may be a computer program [product] comprising instructions which, when executed by one or more processors of an electronic device individually or collectively, cause the electronic device to perform a method of the disclosure.

[0109] Any such software may be stored in the form of volatile or non-volatile storage such as, for example, a storage device like read only memory (ROM), whether erasable or rewritable or not, or in the form of memory such as, for example, random access memory (RAM), memory chips, device or integrated circuits or on an optically or magnetically readable medium such as, for example, a compact disk (CD), digital versatile disc (DVD), magnetic disk or magnetic tape or the like. It will be appreciated that the storage devices and storage media are various embodiments of non-transitory machine-readable storage that are suitable for storing a computer program or computer programs comprising instructions that, when executed, implement various embodiments of the disclosure. Accordingly, various embodiments of the present disclosure may provide a program comprising code for implementing apparatus or a method as claimed in any one of the claims of this specification and a non-transitory machine-readable storage storing such a program.

[0110] Hereinafter, the determination of priority between A and B in the present disclosure may refer to various actions such as selecting the one having a higher priority based on a predefined priority rule and performing an operation corresponding thereto, or omitting or dropping an operation corresponding to the one having a lower priority.

[0111] Hereinafter, "A or B" as described in the present disclosure may be understood as "A and / or B," which may include A, or B, or both A and B.

[0112] In addition, "at least one of A, B, and C" as described in the present disclosure may be understood to include A, or B, or C, or any combination of A, B, and C.

[0113] In addition, "at least one of A, B, or C" as described in the present disclosure may be understood to include A, or B, or C, or any combination of A, B, and C.

[0114] Furthermore, "A / B" as described in the present disclosure may be understood as "A and / or B," which may include A, or B, or both A and B.

[0115] Furthermore, "A, B" as described in the present disclosure may be understood as "A and / or B," which may include A, or B, or both A and B.

[0116] Furthermore, "A and B" as described in the present disclosure may be understood as "A and / or B," which may include A, or B, or both A and B.

[0117] Furthermore, "if condition A and condition B are satisfied," as described in the present disclosure, may not be limited to a case where both condition A and condition B are satisfied, but may be understood to include a case where either condition A or condition B is individually satisfied, both condition A and condition B are satisfied, or one or more additional conditions are satisfied in combination.

[0118] Furthermore, throughout this disclosure, ordinal terms such as "first," "second," "third," etc., (and similar qualifiers) are used merely to distinguish between different instances, occurrences, configurations, messages, stages, elements or aspects of elements, operations, or information as described herein. Unless the context clearly dictates otherwise, the use of such ordinal terms does not itself require that the elements, operations, or information distinguished by these terms be structurally different, numerically distinct, or substantively dissimilar. For example, a "first signal" and a "second signal" may refer to instances of the same signal transmitted at different times or containing the same core information despite minor variations, or they may refer to signals with different content or characteristics, depending on the specific context. Similarly, a "first value" and a "second value" may represent the same magnitude but measured or applied in different circumstances, or they may represent different magnitudes. The interpretation should be guided by the specific technical context, function, and relationship described in the relevant portion of the specification and claims.

[0119] Furthermore, the terms "first ~", "second ~", etc., as described in the present disclosure with respect to various elements (e.g., information, objects, operation, sequences, or the like), should not limit those elements. These terms may only be intended to distinguish one element from another, and may not be intended to indicate a specific order. For example, a first element could be termed a second element, and, similarly, a second element could be termed a first element.

[0120] Furthermore, even if "first ~" and "second ~" are described in the present disclosure, it may be understood that element(s) referred to by "first ~" and "second ~" may be the same or different. For example, in case of element(s) being information, first information and second information may both be same information and, in some cases, are separate and different information.

[0121] In addition, the terms "if ~" and "in case that ~" as used in the disclosure or claims may be interpreted to include the meanings of "when (or upon) ~," "in response to ~," "based on ~," or "according to ~," and may be used interchangeably with these expressions. In addition, expressions other than those exemplified herein may also be used, as long as they have substantially the same meaning and do not impair the technical features of the present disclosure. If a method step (e.g. transmit a signal) is performed according to the disclosure of the application in connection with one of the above terms (such as "in case that ~" or the like), it may be interpreted to include the meanings (disclosure) of a prior determination that a feature has a specific state "~" (e.g. a bit length is above X), and then perform the method step in response to said determination.

[0122] For example, the physical layer signaling may be referred to as Layer 1 (L1) signaling and may include downlink control information (DCI). In addition, the higher layer signaling may include a medium access control (MAC) control message, a radio resource control (RRC) signaling message, a non-access stratum (NAS) signaling message, or an application layer message. The RRC signaling message may be referred to as L3 (layer 3) signaling. It should be noted, however, that the higher layer signaling is not limited to the aforementioned examples.

[0123] In addition, the term "not perform" as used in the present disclosure or claims may, in context, be understood to mean that the corresponding step is omitted or skipped. Such a term may be replaced with other terms having the same or substantially equivalent meaning.

[0124] In addition, "transmitting a message including A and B" as described in the present disclosure, may be understood as encompassing both (i) transmitting A and B in a single message, and (ii) transmitting A and B separately via multiple messages (e.g., transmitting a first message including A and a second message including B). This interpretation may also apply to messages that include two or more items (e.g., A, B, C), transmitted either together or separately.

[0125] In addition, "transmitting a message including A and transmitting a message including B" may also be interpreted as transmitting a message including A and B in a single message.

[0126] In the embodiments of the present disclosure described herein, terms or components included in the disclosure may be expressed in singular or plural form depending on the specific embodiments presented. However, such singular or plural expressions are selected appropriately for convenience of description, and the present disclosure is not limited to a singular or plural number of components. A component expressed in the plural form may be implemented as a single component, and a component expressed in the singular form may be implemented as multiple components.

[0127] The drawings or flowcharts described herein illustrate example methods that may be implemented according to the principles of the present disclosure, and various modifications may be made to the methods illustrated in the flowcharts of the present disclosure. For example, although illustrated as a series of steps, various steps in each drawing or flowchart may overlap, occur in parallel, occur in a different order, or be repeated. In other examples, any step may be omitted or replaced with another step.

[0128] The process of the flowchart may be performed by a device. One or more of the steps of the flowchart can be implemented by one or more processors / computer programs executing instructions to perform the noted functions.

[0129] The methods and apparatuses proposed in the embodiments of the present disclosure may be disclosed in connection with drawings disclosing flowcharts to illustrate example methods that may be implemented according to the principles of the present disclosure. Such flowcharts may contain different branches and / or sub-branches. It is understood that the principles of the present disclosure do not only contain the combination of all branches / sub-branches disclosed in the embodiment, but the present disclosure also contains at least one isolated branch / isolated sub-branch, in particular to a single branch / single sub-branch.

[0130] The methods and apparatuses proposed in the embodiments of the present disclosure are not limited to each embodiment individually, but may also be applied in combination of all or some of the embodiments proposed in the disclosure. Therefore, the embodiments of the present disclosure may be modified and applied without significantly departing from the scope of the present disclosure, as would be understood by those skilled in the art.

[0131] In this case, even if certain wordings are described differently across embodiments, they may be used interchangeably or in substitution or in combination if their underlying concepts are equivalent. For example, for the same or equivalent concept, even if one embodiment uses the expression "A" and another embodiment uses the expression "B", such expressions may be understood interchangeably, in substitution, or in combination.

[0132] The terms used in the following description to refer to access nodes, network entities, messages, interfaces between network entities, various types of identification information, and the like, are provided merely for the convenience of explanation by way of example. Therefore, the present disclosure is not limited to the terms describedherein, and other terms having equivalent technical meanings may also be used. Such terms may also be interchangeable with terms defined in any 3rd generation partnership project (3GPP) technical specifications (TS) or similar technical specifications, e.g., from the European telecommunications standards institute (ETSI), where appropriate.

[0133] Hereinafter, a base station (BS) is an entity that allocates resources to terminals, and may be at least one of a gNode B, an eNode B, a Node B, a wireless access unit, a BS controller, or a node on a network.

[0134] Furthermore, the base station of the present disclosure may include a split architecture comprising a central unit (CU) and a distributed unit (DU). In this structure, the CU is configured to process the higher layers of the control and user planes, while the DU is configured to process lower-layer radio resource functions. The embodiments of the present disclosure may be equally applicable to 5th generation (5G) base station architectures in which such CU and DU functional splits are implemented.

[0135] A terminal may include a user equipment (UE), a mobile station (MS), a cellular phone, a smartphone, a computer, a tablet, a wearable device, an Internet of Things (IoT) device, or any other device / system capable of performing communication functions.

[0136] In the disclosure, a downlink (DL) refers to a radio link through which a BS transmits a signal to a terminal, and an uplink (UL) refers to a radio link through which a terminal transmits a signal to a BS.

[0137] Furthermore, hereinafter, 5G mobile communication technologies (e.g., 5G new radio (NR)), 6th generation (6G) mobile communication technologies may be described by way of example, but the embodiments of the present disclosure may also be applied to other communication systems having similar technical backgrounds or channel types. For example, newly evolved mobile communication systems developed after 5G and 6G may be included. Furthermore, based on determinations by those skilled in the art, the embodiments of the present disclosure may also be applied to other communication systems (e.g., Wi-Fi systems) through some modifications without significantly departing from the scope of the present disclosure

[0138] In the following description, the terms physical channel and signal may be used interchangeably with data or control signal. For example, the term physical downlink shared channel (PDSCH) refers to a physical channel through which data is transmitted, but the term PDSCH may also be used to refer to the data itself. That is, in the present disclosure, the expression "transmit a physical channel" may be interpreted as being equivalent to the expression "transmit data or a signal via a physical channel."

[0139] Hereinafter, in the context of the present disclosure, higher layer signaling may refer to signaling corresponding to at least one or any combination of the following: master information block (MIB), system information block (SIB) or SIB M (M = 1, 2, ...), RRC, or MAC control element (CE), or a non-access stratum (NAS) signaling message, or an application layer message. The RRC signaling message may be referred to as Layer 3 (L3) signaling.

[0140] In addition, L1 signaling may refer to signaling corresponding to at least one or any combination of signaling techniques using the at least one or any combination of the following physical layer channels or signaling: physical downlink control channel (PDCCH), DCI, UE-specific DCI, group-common DCI, common DCI, scheduling DCI (e.g., DCI used for scheduling downlink or uplink data), non-scheduling DCI (e.g., DCI not used for scheduling downlink or uplink data) physical uplink control channel (PUCCH), or uplink control information (UCI). The L1 signaling message may be referred to as a physical layer signaling.

[0141] Hereinafter, the expression that information is configured by the BS, as used in the present disclosure or claims, may, in context, be understood to mean that the terminal receives the corresponding information from the BS via a physical layer signaling or a higher layer signaling. Such an expression may be replaced with other terms having the same or substantially equivalent meaning.

[0142] Hereinafter, the operational principle of the present disclosure will be described in detail with reference to the accompanying drawings.

[0143] Before undertaking the DETAILED DESCRIPTION below, it may be advantageous to set forth definitions of certain words and phrases used throughout this patent document. The term "couple" and its derivatives refer to any direct or indirect communication between two or more elements, whether those elements are in physical contact with one another. The terms "transmit," "receive," and "communicate," as well as derivatives thereof, encompass both direct and indirect communication. The terms "include" and "comprise," as well as derivatives thereof, mean inclusion without limitation. The term "or" is inclusive, meaning and / or. The phrase "associated with," as well as derivatives thereof, means to include, be included within, interconnect with, contain, be contained within, connect to or with, couple to or with, be communicable with, cooperate with, interleave, juxtapose, be proximate to, be bound to or with, have, have a property of, have a relationship to or with, or the like. The term "controller" means any device, system or part thereof that controls at least one operation. Such a controller may be implemented in hardware or a combination of hardware and software and / or firmware. The functionality associated with any particular controller may be centralized or distributed, whether locally or remotely. The phrase "at least one of," when used with a list of items, means that different combinations of one or more of the listed items may be used, and only one item in the list may be needed. For example, "at least one of: A, B, and C" includes any of the following combinations: A, B, C, A and B, A and C, B and C, and A and B and C. Likewise, the term "set" means one or more. Accordingly, a set of items can be a single item or a collection of two or more items.

[0144] Moreover, various functions described below can be implemented or supported by one or more computer programs, each of which is formed from computer readable program code and embodied in a computer readable medium. The terms "application" and "program" refer to one or more computer programs, software components, sets of instructions, procedures, functions, objects, classes, instances, related data, or a portion thereof adapted for implementation in a suitable computer readable program code. The phrase "computer readable program code" includes any type of computer code, including source code, object code, and executable code. The phrase "computer readable medium" includes any type of medium capable of being accessed by a computer, such as read only memory (ROM), random access memory (RAM), a hard disk drive, a compact disc (CD), a digital video disc (DVD), or any other type of memory. A "non-transitory" computer readable medium excludes wired, wireless, optical, or other communication links that transport transitory electrical or other signals. A non-transitory computer readable medium includes media where data can be permanently stored and media where data can be stored and later overwritten, such as a rewritable optical disc or an erasable memory device.

[0145] Definitions for other certain words and phrases are provided throughout this patent document. Those of ordinary skill in the art should understand that in many if not most instances, such definitions apply to prior as well as future uses of such defined words and phrases.

[0146] The figures included herein, and the various embodiments used to describe the principles of the present disclosure are by way of illustration only and should not be construed in any way to limit the scope of the disclosure. Further, those skilled in the art will understand that the principles of the present disclosure may be implemented in any suitably arranged wireless communication system.

[0147] Considering the development of wireless communication from generation to generation, the technologies have been developed mainly for services targeting humans, such as voice calls, multimedia services, and data services. Following the commercialization of 5th-generation (5G) communication systems, it is expected that the number of connected devices will exponentially grow. Increasingly, these will be connected to communication networks. Examples of connected things may include vehicles, robots, drones, home appliances, displays, smart sensors connected to various infrastructures, construction machines, and factory equipment. Mobile devices are expected to evolve in various form-factors, such as augmented reality glasses, virtual reality headsets, and hologram devices. In order to provide various services by connecting hundreds of billions of devices and things in the 6th-generation (6G) era, there have been ongoing efforts to develop improved 6G communication systems.

[0148] 6G communication systems, which are expected to be commercialized around 2030, have various significantly improved metrics compared to the current 5G communication systems. The peak data rate will reach at least 50 Gbit / s, and the user experienced data rate will reach at least 300 Mbit / s, the air-interface latency will be less than 1 ms, and the air-interface reliability will reach 10^(-5). In addition to the above basic communication metrics, the 6G communication systems will also have sensing capabilities, AI-related capabilities, better security, better interoperability and better sustainability.

[0149] In order for the 6G communication systems to fulfill the above metrics, more advanced air-interface technologies and network technologies need to be developed. The evolution of extreme Multiple Input Multiple Output (extreme MIMO) has been already under consideration, including the use of ultra-large scale antenna arrays, the development and evolution of distributed antenna systems, and the design of MIMO air-interface algorithms assisted by Artificial Intelligence (AI). This technology enables higher spectral efficiency, greater coverage, and precise localization and sensing capabilities. Additionally, for technologies that contribute to improve high-frequency band coverage, including metamaterial-based lenses and antennas, new antenna architectures, and reconfigurable intelligent surface (RIS), etc., they also need to be better evolved and developed.

[0150] In order to meet some of newly added functions of the 6G communication systems, new technologies need to be developed in the terms of network energy saving, air-interface security, and network security, meanwhile the feasibility of fusion technologies such as Integrated Sensing and Communication, needs to be studied.

[0151] Moreover, in order to improve the spectral efficiency and the overall network performances, the following technologies have been developed for 6G communication systems: a full-duplex technology for enabling an uplink transmission and a downlink transmission to simultaneously use the same frequency resource at the same time; a network technology for utilizing satellites, high-altitude platform stations (HAPS), and the like in an integrated manner; an improved network structure for supporting mobile base stations and the like and enabling network operation optimization and automation and the like; a dynamic spectrum sharing technology via collision avoidance based on a prediction of spectrum usage; an use of artificial intelligence (AI) in wireless communication for improvement of overall network operation by utilizing AI from a designing phase for developing 6G and internalizing end-to-end AI support functions; and a next-generation distributed computing technology for overcoming the limit of user equipment (UE) computing ability through reachable super-high-performance communication and computing resources (such as mobile edge computing (MEC), clouds, and the like) over the network. In addition, through designing new protocols to be used in 6G communication systems, developing mechanisms for implementing a hardware-based security environment and safe use of data, and developing technologies for maintaining privacy, attempts to strengthen the connectivity between devices, optimize the network, promote softwarization of network entities, and increase the openness of wireless communications are continuing.

[0152] It is expected that research and development of 6G communication systems in hyper-connectivity, including person to machine (P2M) as well as machine to machine (M2M), will allow the next hyper-connected experience. Particularly, it is expected that services such as truly immersive extended reality (XR), high-fidelity mobile hologram, and digital replica could be provided through 6G communication systems. In addition, services such as remote surgery for security and reliability enhancement, industrial automation, and emergency response will be provided through the 6G communication system such that the technologies could be applied in various fields such as industry, medical care, automobiles, and home appliances.

[0153] FIGS. 1-3 below describe various embodiments of the present disclosure implemented in wireless communications systems. The descriptions of FIGS. 1-3 are not meant to imply physical or architectural limitations to the manner in which different embodiments may be implemented. Different embodiments of the present disclosure may be implemented in any suitably-arranged communications system.

[0154] FIG. 1 illustrates an example wireless network according to embodiments of the present disclosure. The embodiment of the wireless network shown in FIG. 1 is for illustration only. Other embodiments of the wireless network 100 could be used without departing from the scope of the present disclosure.

[0155] As shown in FIG. 1, the wireless network includes a base station (next generation nodeB, gNB or gNodeB) 101, a gNB 102, and a gNB 103. The gNB 101 communicates with the gNB 102 and the gNB 103. The gNB 101 also communicates with at least one network 130, such as the Internet, a proprietary Internet Protocol (IP) network, or other data network.

[0156] The gNB 102 provides wireless broadband access to the network 130 for a first plurality of user equipments (UEs) within a coverage area 120 of the gNB 102. The first plurality of UEs includes a UE 111, which may be located in a small business; a UE 112, which may be located in an enterprise (E); a UE 113, which may be located in a WiFi hotspot (HS); a UE 114, which may be located in a first residence (R1); a UE 115, which may be located in a second residence (R2); and a UE 116, which may be a mobile device (M), such as a cell phone, a wireless laptop, a wireless personal digital assistant (PDA), or the like. The gNB 103 provides wireless broadband access to the network 130 for a second plurality of UEs within a coverage area 125 of the gNB 103. The second plurality of UEs includes the UE 115 and the UE 116, as well as subscriber stations (SS, for example, UEs) 117, 118 and 119. In some embodiments, one or more of the gNBs 101-103 may communicate with each other and with the UEs 111-116 using existing wireless communication techniques, and one or more of the UE 111-119 may communicate directly with each other (e.g., UEs 117-119) using other existing or proposed wireless communication techniques.

[0157] Depending on the network type, the term "base station" or "BS" can refer to any component (or collection of components) configured to provide wireless access to a network, such as transmit point (TP), transmit-receive point (TRP), an enhanced (or "evolved") base station (eNodeB or eNB), a 5G base station (gNB), a macrocell, a femtocell, a wireless fidelity (WiFi) access point (AP), or other wirelessly enabled devices. Base stations may provide wireless access in accordance with one or more wireless communication protocols, e.g., 3GPP 5G New Radio (NR), Long Term Evolution (LTE), LTE Advanced (LTE-A), high speed packet access (HSPA), Wi-Fi 802.11a / b / g / n / ac, etc. For the sake of convenience, the various names for a base station-type apparatus and functionality are used interchangeably in this patent document to refer to network infrastructure components that provide wireless access to remote terminals. Also, depending on the network type, the term "user equipment" (UE) can refer to any component such as a mobile station (MS), subscriber station (SS), remote terminal, wireless terminal, receive point, or user device. For the sake of convenience, the various names for a user equipment-type device and functionality are used interchangeably in this patent document to refer to remote wireless equipment that wirelessly accesses a BS, whether the UE is a mobile device (such as a mobile telephone or smartphone) or is normally considered a stationary device (such as a desktop computer or vending machine).

[0158] Dotted lines show the approximate extents of the coverage areas 120 and 125, which are shown as approximately circular for the purposes of illustration and explanation only. It should be clearly understood that the coverage areas associated with gNBs, such as the coverage areas 120 and 125, may have other shapes, including irregular shapes, depending upon the configuration of the gNBs and variations in the radio environment associated with natural and man-made obstructions.

[0159] As described in more detail below, one or more of the UEs 111-119 include circuitry, programing, or a combination thereof. In certain embodiments, and one or more of the gNBs 101-103 includes circuitry, programing, or a combination thereof.

[0160] Although FIG. 1 illustrates one example of a wireless network, various changes may be made to FIG. 1. For example, the wireless network could include any number of gNBs and any number of UEs in any suitable arrangement. Also, the gNB 101 could communicate directly with any number of UEs and provide those UEs with wireless broadband access to the network 130. Similarly, each gNB 102-103 could communicate directly with the network 130 and provide UEs with direct wireless broadband access to the network 130. Further, the gNBs 101, 102, and / or 103 could provide access to other or additional external networks, such as external telephone networks or other types of data networks.

[0161] FIG. 2 illustrates an example base station according to embodiments of the present disclosure. The embodiment of the gNB 102 illustrated in FIG. 2 is for illustration only, and the gNBs 101 and 103 of FIG. 1 could have the same or similar configuration. However, gNBs come in a wide variety of configurations, and FIG. 2 does not limit the scope of the present disclosure to any particular implementation of a gNB.

[0162] As shown in FIG 2, the gNB 102 includes multiple antennas 200a-200n, multiple radio frequency (RF) transceivers 201a-201n, transmit (TX) processing circuitry 203, and receive (RX) processing circuitry 204. The gNB 102 also includes a controller / processor 205, a memory 206, and a backhaul or network interface 207.

[0163] The RF transceivers 201a-201n receive, from the antennas 200a-200n, incoming RF signals, such as signals transmitted by UEs in the network 100. The RF transceivers 201a-201n down-convert the incoming RF signals to generate intermediate frequency (IF) or baseband signals. The IF or baseband signals are sent to the RX processing circuitry 204, which generates processed baseband signals by filtering, decoding, and / or digitizing the baseband or IF signals. The RX processing circuitry 204 transmits the processed baseband signals to the controller / processor 205 for further processing.

[0164] The TX processing circuitry 203 receives analog or digital data (such as voice data, web data, electronic mail, or interactive video game data) from the controller / processor 205. The TX processing circuitry 203 encodes, multiplexes, and / or digitizes the outgoing baseband data to generate processed baseband or IF signals. The RF transceivers 201a-201n receive the outgoing processed baseband or IF signals from the TX processing circuitry 203 and up-converts the baseband or IF signals to RF signals that are transmitted via the antennas 201a-201n.

[0165] The controller / processor 205 can include one or more processors or other processing devices that control the overall operation of the gNB 102. For example, the controller / processor 205 could control the reception of forward channel signals and the transmission of reverse channel signals by the RF transceivers 201a-201n, the RX processing circuitry 204, and the TX processing circuitry 203 in accordance with well-known principles. The controller / processor 205 could support additional functions as well, such as more advanced wireless communication functions.

[0166] For instance, the controller / processor 205 could support beam forming or directional routing operations in which outgoing signals from multiple antennas 200a-200n are weighted differently to effectively steer the outgoing signals in a desired direction. Any of a wide variety of other functions could be supported in the gNB 102 by the controller / processor 205.

[0167] The controller / processor 205 is also capable of executing programs and other processes resident in the memory 206, such as an operating system (OS). The controller / processor 205 can move data into or out of the memory 206 as required by an executing process.

[0168] The controller / processor 205 is also coupled to the backhaul or network interface 207. The backhaul or network interface 207 allows the gNB 102 to communicate with other devices or systems over a backhaul connection or over a network. The interface 207 could support communications over any suitable wired or wireless connection(s). For example, when the gNB 102 is implemented as part of a cellular communication system (such as one supporting 5G, LTE, or LTE-A), the interface 207 could allow the gNB 102 to communicate with other gNBs over a wired or wireless backhaul connection. When the gNB 102 is implemented as an access point, the interface 207 could allow the gNB 102 to communicate over a wired or wireless local area network or over a wired or wireless connection to a larger network (such as the Internet). The interface 207 includes any suitable structure supporting communications over a wired or wireless connection, such as an Ethernet or RF transceiver.

[0169] The memory 206 is coupled to the controller / processor 205. Part of the memory 206 could include a random access memory (RAM), and another part of the memory 206 could include a Flash memory or other read only memory (ROM).

[0170] Although FIG. 2 illustrates one example of gNB 102, various changes may be made to FIG. 2. For example, the gNB 102 could include any number of each component shown in FIG. 2. As a particular example, an access point could include a number of interfaces 207, and the controller / processor 205 could support routing functions to route data between different network addresses. As another particular example, while shown as including a single instance of TX processing circuitry 203 and a single instance of RX processing circuitry 204, the gNB 102 could include multiple instances of each (such as one per RF transceiver). Also, various components in FIG. 2 could be combined, further subdivided, or omitted and additional components could be added according to particular needs.

[0171] FIG. 3 illustrates an example user equipment according to embodiments of the present disclosure. The embodiment of the UE 116 illustrated in FIG. 3 is for illustration only, and the UEs 111-115 and 117-119 of FIG. 1 could have the same or similar configuration. However, UEs come in a wide variety of configurations, and FIG. 3 does not limit the scope of the present disclosure to any particular implementation of a UE.

[0172] As shown in FIG. 3, the UE 116 includes an antenna 301, a radio frequency (RF) transceiver 302, TX processing circuitry 303, a microphone 304, and receive (RX) processing circuitry 305. The UE 116 also includes a speaker 306, a controller or processor 307, an input / output (I / O) interface (IF) 308, an input device 309, a touchscreen display 310, and a memory 311. The memory 311 includes an OS 312 and one or more applications 313.

[0173] The RF transceiver 302 receives, from the antenna 301, an incoming RF signal transmitted by a gNB of the network 100. The RF transceiver 302 down-converts the incoming RF signal to generate an IF or baseband signal. The IF or baseband signal is sent to the RX processing circuitry 305, which generates a processed baseband signal by filtering, decoding, and / or digitizing the baseband or IF signal. The RX processing circuitry 305 transmits the processed baseband signal to the speaker 306 (such as for voice data) or to the processor 307 for further processing (such as for web browsing data).

[0174] The TX processing circuitry 303 receives analog or digital voice data from the microphone 304 or other outgoing baseband data (such as web data, e-mail, or interactive video game data) from the processor 307. The TX processing circuitry 303 encodes, multiplexes, and / or digitizes the outgoing baseband data to generate a processed baseband or IF signal. The RF transceiver 302 receives the outgoing processed baseband or IF signal from the TX processing circuitry 303 and up-converts the baseband or IF signal to an RF signal that is transmitted via the antenna 301.

[0175] The processor 307 can include one or more processors or other processing devices and execute the OS 312 stored in the memory 311 in order to control the overall operation of the UE 116. For example, the processor 307 could control the reception of forward channel signals and the transmission of reverse channel signals by the RF transceiver 302, the RX processing circuitry 305, and the TX processing circuitry 303 in accordance with well-known principles. In some embodiments, the processor 307 includes at least one microprocessor or microcontroller.

[0176] The processor 307 is also capable of executing other processes and programs resident in the memory 311, such as processes for CSI reporting on uplink channel. The processor 307 can move data into or out of the memory 311 as required by an executing process. In some embodiments, the processor 307 is configured to execute the applications 313 based on the OS 312 or in response to signals received from gNBs or an operator. The processor 307 is also coupled to the I / O interface 308, which provides the UE 116 with the ability to connect to other devices, such as laptop computers and handheld computers. The I / O interface 308 is the communication path between these accessories and the processor 307.

[0177] The processor 307 is also coupled to the touchscreen display 310. The user of the UE 116 can use the touchscreen display 310 to enter data into the UE 116. The touchscreen display 310 may be a liquid crystal display, light emitting diode display, or other display capable of rendering text and / or at least limited graphics, such as from web sites.

[0178] The memory 311 is coupled to the processor 307. Part of the memory 311 could include RAM, and another part of the memory 311 could include a Flash memory or other ROM.

[0179] Although FIG. 3 illustrates one example of UE 116, various changes may be made to FIG. 3. For example, various components in FIG. 3 could be combined, further subdivided, or omitted and additional components could be added according to particular needs. As a particular example, the processor 307 could be divided into multiple processors, such as one or more central processing units (CPUs) and one or more graphics processing units (GPUs). Also, while FIG. 3 illustrates the UE 116 configured as a mobile telephone or smartphone, UEs could be configured to operate as other types of mobile or stationary devices.

[0180] In a Multiple-Input Multiple-Output (MIMO) system, reference signal pattern design has a critical impact on an accuracy of channel estimation and system performance, and therefore, an enhancement to the existing reference signal design method and / or channel estimation method is needed, to achieve more accurate channel estimation.

[0181] FIG. 4 is a diagram illustrating a reference signal and channel estimation method in a MIMO system.

[0182] As shown in FIG. 4, firstly, a base station randomly generates a reference signal pattern as shown in FIG. 5 in a frequency and antenna domains, and then, the randomly generated reference signal pattern is indicated to a User Equipment (UE). Since the number of transmitting antennas is large and the transmitting antennas occupy more resource positions, positions of the reference signals are generated, based on a sparsity of a channel and jointly in two dimension spaces of frequency-domain and antennas. In addition, it is assumed that the transmitting positions of the reference signals in the antenna dimension and in the frequency-domain dimension are randomly distributed independently of each other. Specifically, an antenna pattern ( ) is randomly generated in one frequency-domain dimension (RE), and an antenna pattern ( ) is generated in another frequency-domain dimension in the case of satisfying a condition of the following Equation (1), and then, the reference signal pattern C is obtained.

[0183] (1)

[0184] (2)

[0185] Thereafter, the UE obtains the reference signal pattern indicated by the base station and receives the reference signal corresponding to the reference signal pattern from the base station, measures Channel State Information (CSI) based on the reference signal, and then, feeds back the CSI to the base station. The base station performs channel estimation based on the CSI fed back by the UE, and then, performs scheduling and precoding.

[0186] The present application introduces a certain constraint condition when generating the reference signal pattern, so that a final generated reference signal pattern can be easily standardized. In addition, the present application improves the system efficiency by jointly considering a design of the reference signal pattern and terminal channel estimation, and utilizing the sparsity of the channel to reduce resource positions occupied when transmitting the reference signal as much as possible on a basis of ensuring the channel estimation performance.

[0187] FIG. 6A is a flowchart illustrating a method performed by an electronic apparatus according to an exemplary embodiment of the present disclosure. FIG. 6B is a schematic diagram illustrating a structure of a reference signal pattern design and channel estimation module according to an exemplary embodiment of the present application. FIG. 6C is a schematic diagram illustrating a structure of a reference signal pattern design and channel estimation module according to another exemplary embodiment of the present application. FIG. 6D is a schematic diagram illustrating a structure of a reference signal pattern design and channel estimation module according to another exemplary embodiment of the present application. FIG. 6E is a schematic diagram illustrating a structure of a reference signal pattern design and channel estimation module according to another exemplary embodiment of the present application. In the present application, an electronic apparatus may be a UE, a base station, a component (e.g., a Centralized Unit (CU), a Distributed Unit (DU), etc.) of a base station, and the like. As shown in FIG. 6B, the reference signal pattern design and channel estimation module may include a reference signal design module, a channel estimation module, and an AI model update module, however, the present application is not limited thereto, and the reference signal pattern design and channel estimation module may further include other modules. Furthermore, in an example as shown at in FIG. 6C, the reference signal pattern design and channel estimation module may include a pre-processing module and a post-processing module in addition to the modules illustrated in FIG. 6B. Furthermore, in the example shown in FIG. 6D, the reference signal pattern design and channel estimation module may include a UE grouping module in addition to the modules shown in FIG. 6B. Furthermore, in the example shown in FIG. 6E, the reference signal pattern design and channel estimation module may include the pre-processing module and the post-processing module as well as the UE grouping module, in addition to the modules shown in FIG. 6B.

[0188] As shown in FIG. 6A, at step S610, a first reference signal pattern is obtained.

[0189] In the present application, the first reference signal pattern is associated with a second reference signal pattern, the second reference signal pattern may be determined according to a plurality of sparse weight factors and at least one candidate reference signal pattern set, the plurality of sparse weight factors are obtained by training the first AI model, each of the plurality of sparse weight factors represents　a degree of importance of a spatial-domain position and / or a frequency-domain position associated with a resource of the corresponding reference signal with respect to channel estimation. In other words, the first reference signal pattern may be the second reference signal pattern or may be determined by the base station according to the second reference signal pattern. The procedure for obtaining the first reference signal pattern is described in detail below.

[0190] An operation of obtaining the plurality of sparse weight factors is firstly described below. This operation may be performed by a sparse reference signal and channel estimation module in the reference signal design module of FIG. 6B. This is described in detail below with reference to FIG. 7.

[0191] The sparse reference signal and channel estimation module obtains sparse weight factors that reflect a sparse feature of the channel by training an AI model, and this module may include a first AI model (may also be referred to as "model 1") that may be consist of a reference signal network (may also be referred to as a first sub-network) and a channel estimation network (may also be referred to as a second sub-network), as shown in FIG. 7.

[0192] As illustrated in FIG. 7, a network architecture of the reference signal network (i.e., the first sub-network) is a network in which there are one-to-one correspondences between inputs and outputs, wherein corresponding weight values (also referred to as mapping coefficients, or weight factors) between the inputs and the outputs are referred to as sparse weight factors, and each sparse weight factor represents a degree of importance of an spatial-domain position and / or the frequency-domain position associated with a resource of the corresponding reference signal with respect to the channel estimation.

[0193] The input of the reference signal network is full channel data, i.e., all channels in the spatial-domain and the frequency-domain, of which a dimension is2*L, wherein , wherein 2 represents real and imaginary parts, represents the number of Resource Blocks (RBs) or carriers in the frequency-domain), represents the number of transmitting antennas, and represents the number of receiving antennas. The output of the reference signal network is weighted channel data, i.e., the weighted all channels in the spatial-domain and the frequency-domain, of which the dimension is also2*L.

[0194] A network architecture of the channel estimation network (i.e., the second sub-network) may be one of a variety of existing network architectures , for example, it may be, but is not limited to, a Transformer network, a Mabma network, a Multilayer Perceptron (MLP), a Deep Neural Network (DNN), Convolutional Neural Network (CNN).

[0195] The input of the channel estimation network is the output of the reference signal network, i.e., the weighted all channels in the spatial-domain and the frequency-domain. The output of the channel estimation network is estimated full-channel data, i.e., the estimated all channels in the spatial-domain and the frequency-domain, of which the dimension is 2*L.

[0196] In the present application, the training the first AI model includes: determining a first loss function, according to KL divergences corresponding to mapping coefficients between inputs and outputs of a first sub-network in the first AI model and / or a channel estimation error; training the first AI model using a first training dataset, according to the first loss function, wherein the mapping coefficients in the trained first AI model are determined as the plurality of sparse weight factors.

[0197] Specifically, in order to not only enable better channel estimation but also ensure the sparsity of the reference signals, the present application uses the channel estimation error and / or the KL divergence to construct the first loss function of the first AI model. The channel estimation error is used to ensure the accuracy of the recovery of the channel estimation, and the KL divergence is used to ensure the sparsity of the sparse weight factors. In one exemplary embodiment of the present application, Mean Squared Error (MSE) may be used to represent the channel estimation error, but the present application is not limited thereto, and Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), and Symmetric Mean Absolute Percentage Error (SMAPE) may also be used. For example, the MSE and the KL divergence may be used to construct the first loss functionlossas shown in Equation (3) below.

[0198]

[0199] Wherein is referred to as a sparsity ratio, wherein RS_size represents the desired number of reference signals and channel_size represents a size L of the channel matrix, and ρ is used to control the number of reference signals; is a penalty factor for the KL divergence, which is used to control a relative weight of the accuracy of the recovery of the channel estimation with respect to the sparsity of the reference signals, wherein is a value that is greater than or equal to 0 and less than or equal to 1 .

[0200] The KL divergence is commonly used to measure a distribution between two different random variables, and in the present application, is used to control a sparsity (may also be referred to as "average activity level") of the mapping coefficients such that the sparsity of is close to a predefined sparsity ratio. For example, FIG. 8 is a schematic diagram illustrating the KL divergence when the sparsity ratio is a specific value (i.e., ρ=0.2). As can be seen in FIG. 8, the KL divergence is minimized when the sparsity of is close to or equal to 0.2.

[0201] For example, FIG. 9 illustrates a result of the mapping coefficients after 100 epochs of training in a case that the first loss functionlossshown in Equation (3) above is used. As shown in FIG. 9, compared to the initial mapping coefficients , the mapping coefficients after 100 epochs of training have a very high sparsity. Thus, in the present application, the first AI model is trained using the first training dataset according to the first loss function, and when the first loss function converges, the mapping coefficients of the first sub-network in the trained first AI model are determined to be the plurality of sparse weight factors, or, when the first AI model is trained for a predetermined number of epochs, the mapping coefficients of the first sub-network in the trained first AI model are determined as the plurality of sparse weight factors. In the present application, the sparse weight factors represent importance of different spatial-frequency positions in the channel estimation.

[0202] After the plurality of sparse weight factors are determined, the second reference signal pattern may be determined based on the plurality of sparse weight factors and the at least one candidate reference signal pattern set, as described above. This operation may be performed by a reference signal pattern design module in the reference signal design module of FIG. 6B.

[0203] Specifically, since the sparse weight factors generated by the sparse reference signal and channel estimation module are sparse but random, a function of the reference signal pattern design module is to design or select a reference signal pattern using the sparse weight factors and the candidate reference signal pattern set, so as to obtain a reference signal pattern with a certain degree of regularity and friendly to the air interface protocol.

[0204] In one exemplary embodiment of the present application, the second reference signal pattern may be determined according to the plurality of sparse weight factors and the at least one candidate reference signal pattern set by: performing a dimensional conversion on the plurality of sparse weight factors; selecting one candidate reference signal pattern from among each candidate reference signal pattern set by: generating a plurality of pattern-based sparse weight factors based on the plurality of sparse weight factors after the dimensional conversion and a candidate reference signal pattern set, and selecting one candidate reference signal pattern in the candidate reference signal pattern set according to the plurality of pattern-based sparse weight factors; and determining a candidate reference signal pattern satisfying a predetermined condition among the selected at least one candidate reference signal pattern as the second reference signal pattern. This is described in detail below with reference to FIGS. 10 and 11.

[0205] FIG. 10 is a flowchart illustrating a procedure for determining a second reference signal pattern according to exemplary embodiments of the present application. FIG. 11 is a schematic diagram illustrating a procedure for determining a second reference signal pattern according to exemplary embodiments of the present application.

[0206] As shown in FIG. 10, at step S1010, a dimension conversion is performed on the plurality of sparse weight factors.

[0207] Specifically, as shown in FIG. 11, at operation 1101, the dimensional conversion is performed on the plurality of sparse weight factors, i.e., a conversion from a dimension of to a dimension of , e.g., the input sparse weight factors are converted from the dimension of to the dimension of and thus the sparse weight factor after the dimensional conversion is obtained, which represents the sparse weight factor corresponding to ai-th frequency-domain position, aj-th transmitting antenna and ak-th receiving antenna. Since the receiving antennas do not affect the design of the reference signal pattern, the reference signal pattern can be designed under the dimension of the receiving antennas in the present application.

[0208] At step S1020, one candidate reference signal pattern is selected from among each candidate reference signal pattern set. In one example, the candidate reference signal pattern set may be predefined, e.g., may be predefined by a 3GPP standard. In another example, the candidate reference signal pattern set may be determined by predefined parameters for the reference signal pattern set, e.g., may be determined by combining some parameters (e.g., an offset of a transmitting antenna ports from a X-th antenna; the number of transmitting antennas; an offset from a position of a Y-th carrier or RB position; the number of carriers or RBs, and so on) of reference signal pattern sets predefined by the 3GPP standard.

[0209] Specifically, at operation 1102, a plurality of pattern-based sparse weight factors are generated based on the plurality of sparse weight factors after the dimensional conversion and the candidate reference signal pattern set. In one exemplary embodiment, the generating the plurality of pattern-based sparse weight factors based on the plurality of sparse weight factors after dimensional conversion and the candidate reference signal pattern set includes: for each candidate reference signal pattern in the candidate reference signal pattern set, obtaining a pattern-based sparse weight factor by: summing sparse weight factors corresponding to each transmitting antenna and each frequency-domain position on the candidate reference signal pattern, to obtain the pattern-based sparse weight factor of the candidate reference signal pattern with respect to each receiving antenna.

[0210] For example, the pattern-based sparse weight factors of the respective candidate reference signal patterns with respect to the respective receiving antennas may be obtained according to the following Equation (4).

[0211]

[0212] That is, a pattern-based sparse weight factor is generated based on the sparse weight factor and the current candidate reference signal pattern set, wherein represents a pattern-based sparse weight factor corresponding to ag-th candidate reference signal pattern in the current candidate reference signal pattern set with respect to ak-th receiving antenna. As shown in FIG. 11, the pattern-based sparse weight factors may be obtained for the current candidate reference signal pattern set by process 1102.

[0213] Then, at process 1103, one candidate reference signal pattern in the candidate reference signal pattern set is selected according to the plurality of pattern-based sparse weight factors.

[0214] In one exemplary embodiment of the present application, the selecting one candidate reference signal pattern in the candidate reference signal pattern set according to the plurality of pattern-based sparse weight factors includes: determining a largest pattern-based sparse weight factor from among the plurality of pattern-based sparse weight factors; selecting one candidate reference signal pattern corresponding to the largest pattern-based sparse weight factor from among the candidate reference signal pattern set.

[0215] For example, as shown in FIG. 11, for the current candidate reference signal pattern set, a largest pattern-based sparse weight factor may be selected from among 4 pattern-based sparse weight factors corresponding to one row of each candidate reference signal pattern, thereby obtaining 18 pattern-based sparse weight factors, and a largest pattern-based sparse weight factor may be selected from among these 18 pattern-based sparse weight factors, and then, a candidate reference signal pattern corresponding to this largest pattern-based sparse weight factor is selected from among the current candidate reference signal pattern set. For example, as shown in FIG. 11, , and , if other , just like , are smaller than , finally, a candidate reference signal pattern corresponding to (i.e., a candidate reference signal pattern corresponding to index N4) may be selected from among the current candidate reference signal pattern set.

[0216] In another exemplary embodiment of the present application, the selecting one candidate reference signal pattern in the candidate reference signal pattern set according to the plurality of pattern-based sparse weight factors includes: by summing or averaging weight factors corresponding to the respective candidate reference signal patterns on different receiving antennas in the plurality of pattern-based sparse weight factors, obtaining weight sums or weight averages corresponding to the respective candidate reference signal patterns; selecting one candidate reference signal pattern corresponding to the largest of the weight sums or the weight averages from among the candidate reference signal pattern set.

[0217] For example, as shown in FIG. 11, the current candidate reference pattern set includes 18 candidate reference signal patterns (indexes Ngbeing 0, 2, 4, 6...34). For the current candidate reference signal pattern set, 4 pattern-based sparse weight factors corresponding to the respective candidate reference signal patterns Ngon 4 receiving antennas may be summed or averaged, thereby obtaining 18 weight sums or weight averages, and the largest weight sum or weight average may be selected from among these 18 weight sums or weight averages, and then, a candidate reference signal pattern corresponding to this largest weight sum or weight average is selected from among the current candidate reference signal pattern set.

[0218] Similarly, for each candidate reference signal pattern set, one candidate reference signal pattern is selected by the above operations, thereby obtaining at least one candidate reference signal pattern.

[0219] Referring back to FIG. 10, at step S1030, a candidate reference signal pattern satisfying a predetermined condition in the selected at least one candidate reference signal pattern is determined as the second reference signal pattern. Wherein, the predetermined condition is that it has the largest pattern-based sparse weight factor, that is, the candidate reference signal pattern with the largest pattern-based sparse weight factor in the selected at least one candidate reference signal pattern is determined as the second reference signal pattern.

[0220] Specifically, the pattern-based sparse weight factor corresponding to each selected candidate reference pattern may be compared with each other, and the candidate reference signal pattern with the largest pattern-based sparse weight factor in the selected at least one candidate reference signal pattern may be determined as the second reference signal pattern according to a comparison result. The second reference signal pattern determined above by step S1030 or the first reference signal pattern determined by adjusting the second reference signal pattern may be used for channel estimation.

[0221] Referring back to FIG. 6A, at step S620, the channel estimation is performed based on Channel State Information (CSI) measured using a reference signal associated with the first reference signal pattern. In the present application, in performing the channel estimation, a second AI model (which may also be referred to as "model 2") may be used for the channel estimation.

[0222] As mentioned in the above description, the electronic apparatus may be a base station (or a component of a base station) or a UE, in the following description, step S620 is further described firstly with the electronic apparatus being the base station.

[0223] FIG. 12A is a flowchart illustrating a procedure for performing channel estimation when an electronic apparatus is a base station (i.e., when the first AI model and the second AI model are deployed on the base station) according to exemplary embodiments of the present application. FIG. 12B illustrates an air interface process when an electronic apparatus is the base station (i.e., when the first AI model and the second AI model are deployed on the base station).

[0224] As shown in FIG. 12A, at step S1210, the base station transmits, to a UE, information associated with the first reference signal pattern and / or Channel State Information (CSI) feedback configuration. In the present application, CSI feedback configuration may also be referred to as "CSI report configuration". As shown in FIG. 12B, the base station indicates the first reference signal pattern and the CSI feedback configuration (i.e., the CSI feedback method) to a UE1 and a UE2. In the present application, depending on different design schemes, the first reference signal pattern may be the second reference signal pattern, or may be determined by the base station based on the second reference signal pattern, for example, may be determined by making adjustments to the second reference signal pattern, but the present application does not make any specific limitation thereto. In one exemplary embodiment of the present application, the information associated with the first reference signal pattern may be transmitted to the UE via Downlink Control Information (DCI) signaling, Media Access Control (MAC) Control Element (CE) signaling, or radio resource control RRC signaling.

[0225] In one example, the DCI information, MAC CE signaling, or RRC signaling may include at least one of the following information associated with the reference signal pattern:

[0226] (1) Information for indicating an spatial-domain and / or frequency-domain associated with the first reference signal pattern, wherein the information for indicating the spatial-domain and / or frequency-domain associated with the first reference signal pattern may include starting values of spatial-domain positions and / or a frequency-domain positions of the reference signals, an interval of the spatial-domain positions and / or the frequency-domain positions, the number of the spatial-domain positions and / or the frequency-domain positions, and wherein the spatial-domain positions may be antenna ports or beams, and in the present application, the description is given with the spatial-domain positions being antenna ports as an example, but the present application does not make any specific limitation thereto, and the corresponding description may be equally applicable to a case where the spatial-domain positions are beams;

[0227] (2) Information for indicating one of the predefined at least one reference signal pattern;

[0228] (3) Information for indicating one of the predefined at least one reference signal pattern and information related to an offset of the first reference signal pattern.

[0229] For example, FIG. 13A illustrates an example of indicating Channel State Information (CSI) configuration feedback via a DCI format 2-X.

[0230] In another example, the DCI signaling, the MAC CE signaling or the RRC signaling may include information indicating a resource for transmitting the reference signal, that is, the first reference signal pattern may be indicated by including, in the signaling, the information indicating the resource for transmitting the reference signal, wherein there is a mapping relationship between the resource for transmitting the reference signal and the first reference signal pattern. The mapping relationship may be determined based on at least two of parameters: a sequence number of the reference signal, a size of a Code Division Multiplexing (CDM) group, the number of CDM groups, the number of antenna ports for the reference signal, a time-domain position and a frequency-domain position of the reference signal.

[0231] For example, the first reference signal pattern may be implicitly indicated by including, in the information indicating the resource for transmitting the reference signal, information indicating a resource for a Channel State Information Reference Signal (CSI-RS), wherein there is a mapping relationship between the CSI-RS resource and the reference signal pattern as follows.

[0232] (5)

[0233] (6)

[0234] (7)

[0235] whereinsrepresents the sequence number of the reference signal;Mis the size of the Code Division Multiplexing (CDM) group;Qis the number of CDM groups; andNis the number of CSI-RS ports. For example, Table 1 below illustrates an example of the mapping relationship between antenna ports and CSI-RS.

[0236]

[0237] In another example, there may be a mapping relationship between the CSI-RS resources and the reference signal pattern as follows. For example, the second reference signal pattern may be indicated by indicating the time-domain resource and / or the frequency-domain resource of the CSI-RS, i.e., the second reference signal pattern may be indicated implicitly as described above. Wherein, there is the following mapping relationship between the time-domain resource and / or the frequency-domain resource of the CSI-RS and the reference signal pattern.

[0238] Starting position of antenna ports = b1 * Starting position of CSI-RS time-domain resource + b2

[0239] Interval of antenna ports = c1 * interval of CSI-RS time-domain resources+ c2

[0240] Number of antenna ports = d * number of CSI-RS time-domain resources

[0241] Frequency-domain position = CSI-RS frequency-domain position

[0242] Wherein, b1 represents a coefficient and takes a value of a natural number, b2 is an offset and takes a value of an integer, c1 is a coefficient and takes a value of a natural number, c2 is an offset and takes a value of an integer, and d is a coefficient and takes a value of an integer, and furthermore, d may typically be equal to 1, but the present application is not limited thereto and may also take other values. In addition, the values of b1, b2, c1, c2, and d may be indicated by RRC signaling, MAC-CE signaling, or DCI signaling, or may be predefined by protocol. Furthermore, in the above mapping relationship, at least one value of {x1, x2} and at least one value of {y1, y2} are needed to be included.

[0243] For example, as shown in FIG. 13B, when b1 = 1, b2 = 0, c1 = 2 and c2 = 0, positions of antenna ports thereof are [1, 3, 5] and frequency-domain positions are [2, 4, 6, 8]; when b1 = 4, b2 = 2, c1 = 4 and c2 = 1, the positions of antenna ports thereof are [6, 11, 16] and the frequency-domain positions are [2, 4, 6, 8]. Wherein gray areas in FIG. 13B indicate positions of the resources at which the CSI-RS is transmitted.

[0244] When d>1, the CSI-RS is transmitted on d subcarriers in the indicated RBs or Resource Block Group (RBG), e.g., when d = 2, and when b1 = 1, b2 = 0, c1 = 2 and c2 = 0, the positions of antenna ports are [1, 3, 5, 7, 9, 11], and the frequency-domain positions are two subcarriers in RBs of [2, 4, 6, 8].

[0245] In one exemplary embodiment of the present application, unlike feedback of a codebook-based Precoding Matrix Indicator (PMI), a Channel Quality Indicator (CQI), and a Rank Indication (RI) information in the prior art, in the present application, the CSI feedback configuration is used to indicate feedback of quantization information (including CSI phase information and amplitude information) of a channel of the reference signal, and specifically, the CSI feedback configuration is used to indicate feedback of the quantized CSI phase and amplitude of the reference signal on the receiving antenna.

[0246] In one example, the CSI feedback configuration is used to indicate CSI feedback on one receiving antenna, i.e., the quantized CSI phase and amplitude of the reference signal on the one receiving antenna, wherein the one receiving antenna is indicated via DCI signaling, MAC-CE signaling, or RRC signaling. Furthermore, the quantized CSI amplitude of each reference signal may be represented by X bits, and the quantized CSI phase of each reference signal may be represented by Y bits, wherein X and Y may be 3 and 4, respectively, or 4 and 3, respectively.

[0247] In another example, the CSI feedback configuration is used to indicate CSI feedback on all receiving antennas, i.e., the quantized CSI phases and amplitudes of reference signals on all receiving antennas. For example, similar to a case of CSI feedback on one receiving antenna, the quantized CSI amplitude of each reference signal may be represented by X bits and the quantized CSI phase of each reference signal may be represented by Y bits.

[0248] At step S1220, the reference signal is transmitted to the UE based on the first reference signal pattern. That is, the base station transmits the reference signal to the UE using the first reference signal pattern.

[0249] At step S1230, the CSI measured using the reference signal is received from the UE. Specifically, the UE performs measurement using the reference signal received from the base station that is transmitted using the first reference signal pattern (which may also be referred to as "reference signal corresponding to the first reference signal pattern"), thereby obtaining the CSI, and then transmits the obtained CSI to the base station.

[0250] At step S1240, the channel estimation is performed through the second AI model, according to the CSI. This operation may be performed by a channel estimation module in the reference signal design and channel estimation module of FIG. 6B, and the channel estimation module is implemented through the second AI model.

[0251] Specifically, a network architecture of the second AI model may be one of the existing network architectures, e.g., may be, but is not limited to, one of a Transformer network, a Mabma network, an MLP, a DNN, a CNN. In one exemplary embodiment of the present application, the network architecture of the second AI model may be the same as (i.e., remain consistent with) the network architecture of the channel estimation network (i.e., the second sub-network) of the first AI model. Furthermore, alternatively, the initial network weights of the second AI model in training may use the network weights of the channel estimation network of the trained first AI model, so as to decrease a training time of the second AI model. However, the present application is not limited thereto, and the network structure of the second AI model may also be different from the network structure of the channel estimation network of the first AI model.

[0252] In the present application, the second AI model is trained by: generating a second training dataset from a first training dataset used in training the first AI model, according to the second reference signal pattern; and training the second AI model using the second training dataset.

[0253] In the present application, when the electronic apparatus is the base station (i.e., when the first AI model and the second AI model are deployed on the base station), when performing the channel estimation, an input of the second AI model is a channel determined according to the reference signal corresponding to the first reference signal pattern with the dimension of2*P, wherein is the number of frequency-domain positions at which the reference signal is transmitted; and is the number of transmitting antennas at which the reference signal is transmitted. The output of the second AI model is the estimated all channel in the spatial-domain and frequency-domain with the dimension of2*L.

[0254] Alternatively, when the UE feeds back channel information corresponding to the reference signal on all of the receiving antenna ports, wherein is the number of receiving antennas.

[0255] Alternatively, since the channel information of the reference signal has been fed back, the output of the second AI model is a difference between the estimated channel of all the spatial-domain and frequency-domain and the corresponding channel information of the reference signal, and the difference has a dimension of 2*(L-P).

[0256] The above describes a detailed procedure of step S620 when the electronic apparatus is the base station. The detailed procedure of step S620 when the electronic apparatus is the UE will be described below with reference to FIGS. 14A and 14B.

[0257] FIG. 14A is a flowchart illustrating a procedure for performing channel estimation when the electronic apparatus is a UE (i.e., when a first AI model and a second AI model are deployed on the UE) according to an exemplary embodiment of the present application. FIG. 14B illustrates an air interface process when an electronic apparatus is the UE (i.e., when a first AI model and a second AI model are deployed on the UE).

[0258] As shown in FIG. 14A, at step S1410, the UE transmits the information associated with the second reference signal pattern to the base station.

[0259] In one example, the transmitting information associated with the second reference signal pattern to the base station may include: sorting reference signals in the second reference signal pattern according to importance of the reference signals in the second reference signal pattern, wherein the importance is determined at least according to values of sparse weight factors; transmitting, to the base station, information of the top G reference signals with highest importance in the second reference signal pattern, wherein G may be an integer greater than or equal to 1, and may be configured by the base station via RRC signaling, MAC CE signaling, or DCI signaling.

[0260] At step S1420, information associated with the first reference signal pattern is received from the base station, wherein the first reference signal pattern may be the second reference signal pattern, or may be determined by the base station based on the second reference signal pattern, e.g., by making adjustments to the second reference signal pattern by the base station.

[0261] As shown in FIG. 14B, unlike the prior art, the UE feeds back the second reference signal pattern (i.e., an UE-specific reference signal pattern of the UE) to the base station, and the base station indicates the first reference signal pattern to the UE, wherein, as described above, the first reference signal pattern is the second reference signal pattern, or is determined by the base station based on the second reference signal pattern. Furthermore, since the second AI model is obtained, according to performing training based on training data obtained by using the second reference signal pattern, in another exemplary embodiment, after the UE obtains the first reference signal pattern that is different from the second reference signal pattern, the UE may fine-tune the second AI model based on the first reference signal pattern, such that the second AI model may perform more accurate channel estimation according to channel information measured using the reference signal corresponding to the first reference signal pattern..

[0262] At step S1430, the reference signal corresponding to the first reference signal pattern (i.e., the reference signal transmitted using the first reference signal pattern) is received from the base station. Specifically, the base station transmits the reference signal to the UE based on the first reference signal pattern, and accordingly, the UE receives the reference signal transmitted by the base station.

[0263] At step S1440, the channel estimation is performed through the second AI model, according to the CSI measured using the reference signal. This operation may be performed by the channel estimation module of FIG. 6B, which is implemented through the second AI model, and this operation will not be repeated herein since the procedure of training and using the second AI model has been similarly described above.

[0264] In the present application, when the electronic apparatus is the UE (i.e., when the first AI model and the second AI model are deployed on the UE), the UE measures the CSI using the reference signal received from the base station corresponding to the first reference signal pattern, and then performs the channel estimation based on the CSI through the second AI model. In one example, the UE may also indicate the estimated channel or Precoding Matrix Indicator (PMI) to the base station.

[0265] The detailed procedure of step S620 when the electronic apparatus is the base station and when the electronic apparatus is the UE has been described above with reference to FIGS. 12A and 14A respectively. Since the determination of the reference signal pattern is related to a channel environment (e.g., a position of a scatterer, a position of the UE, a Doppler effect, etc.), when the channel environment or the position of the UE changes, it is necessary to update the AI model and the reference signal pattern. Therefore, the method described above with reference to FIG. 6A may further include: determining whether to update the first reference signal pattern and the second AI model. This operation may be performed by the AI model update module in the reference signal design and channel estimation module of FIG. 6B.

[0266] In the present application, whether to update the first reference signal pattern and the second AI model may be determined under one of cases: (1) measuring a certain metric by periodically using a monitoring reference signal, and determining whether to update the first reference signal pattern and the second AI model based on a comparison result between the metric and a corresponding threshold; (2) measuring a certain metric when a decrease in a performance (e.g., a decrease in a throughput or an increase in a call drop rate, etc.) of a system is detected, and determining whether to update the first reference signal pattern and the second AI model based on a comparison result between the metric and a corresponding threshold; and (3) when a decrease in the performance (e.g., a decrease in the throughput or an increase in the call drop rate, etc.) of the system is detected, determining directly to update the first reference signal pattern and the second AI model.

[0267] In the present application, the above metric may be one of metrics: (1) a Normalized Mean Square Error (NMSE) of channel information estimated by the second AI model and channel information measured according to the monitoring reference signal; and (2) a cosine similarity (SGCS) of the channel information estimated by the second AI model and channel information measured according to, for example, a Sounding Reference Signal (SRS). However, the present application is not limited thereto, and may also employ other metrics.

[0268] In the present application, the monitoring reference signal may be determined according to a monitoring reference signal pattern, or, by multiplexing　an existing reference signal (e.g., Phase Tracking Reference Signal (PTRS)). The monitoring reference signal pattern may be determined according to a position of a reference signal corresponding to a NMSE that is below a third threshold in training procedure of the second AI model, as illustrated in FIG. 15, wherein both NMSE=3×10-6and NMSE=2.2×10-5are below the third threshold (e.g., 1×10-4), and thus positions of reference signals corresponding to NMSE=3×10-6and NMSE=2.2×10-5may be determined as positions of the monitoring reference signals, that is, the monitoring reference signal pattern may be determined based on the positions of these two reference signals.

[0269] Alternatively, the monitoring reference signals may also be determined by: sorting the reference signals based on magnitudes of NMSEs in training procedure of the second AI model, and determining the monitoring reference signal pattern according to positions of the top W reference signals with lowest NMSE among the sorted reference signals. In the present application, W may be a positive integer greater than or equal to 1. For example, as shown in FIG. 15, the positions of the top 2 reference signals with the lowest NMSE among the sorted reference signals are used as the monitoring reference signal pattern.

[0270] Alternatively, the monitoring reference signal pattern may be determined from the first reference signal pattern according to a predetermined offset, and in the present application, it may be specified that there is a predetermined offset between the monitoring reference signal pattern and the first reference signal pattern, as illustrated in FIG. 15, the monitoring reference signal pattern may be determined by performing a predetermined offset on the first reference signal pattern.

[0271] In addition, when designing the monitoring reference signal pattern, the monitoring reference signal pattern needs to not overlap with the first reference signal pattern.

[0272] In the following, the procedure for determining whether to update the first reference signal pattern and the second AI model is described for cases where the electronic apparatus is the base station and the UE, respectively.

[0273] In one exemplary embodiment of the present application, when the electronic apparatus is the base station (i.e., when the first AI model and the second AI model are deployed on the base station), the determining whether to update the first reference signal pattern and the second AI model may include: transmitting a monitoring reference signal to the UE periodically or when a degradation in system performance is detected by the base station; determining whether to update the first reference signal pattern and the second AI model, according to channel information measured using the monitoring reference signal and channel information estimated by the second AI model.

[0274] Specifically, in one example, the base station may periodically transmit the monitoring reference signal to the UE, and the UE may perform channel measurement according to the received monitoring reference signal to obtain the channel information, and then feed back the obtained channel information to the base station, and in this case, the base station may determine whether to update the first reference signal pattern and the second AI model, according to the channel information measured using the monitoring reference signal reported by the UE and the channel information estimated by itself through the second AI model.

[0275] In another example, as shown in FIG. 16, when the base station detects a degradation in the performance of the system (i.e., the base station considers that the performance of the system degrades when it receives a Negative Acknowledgement (NACK) from the UE), the base station transmits the monitoring reference signal to the UE, and the UE performs the channel measurement according to the received monitoring reference signal to obtain, for example, a monitoring CSI (i.e., the channel information), and transmits the monitoring CSI to the base station. In this case, the base station may determine whether to update the first reference signal pattern and the second AI model according to the channel information measured using the monitoring reference signal reported by the UE and the channel information estimated by itself through the second AI model.

[0276] In another exemplary embodiment of the present application, when the electronic apparatus is the UE (i.e., when the first AI model and the second AI model are deployed on the UE), the determining whether to update the first reference signal pattern and the second AI model may include: receiving the monitoring reference signal from the base station periodically, or requesting the monitoring reference signal from the base station when the UE detects a degradation in the system performance and receiving the monitoring reference signal from the base station; determining whether to update the first reference signal pattern and the second AI model according to the channel information measured using the monitoring reference signal and the channel information estimated by the second AI model.

[0277] Specifically, in one example, the UE periodically receives the monitoring reference signal from the base station, measures the channel information using the received monitoring reference signal and estimates the channel information based on the second AI model, and then determines whether to update the first reference signal pattern and the second AI model according to the channel information measured using the received monitoring reference signal and the channel information estimated by the second AI model.

[0278] In another example, as shown in FIG. 16, in the case where the first AI model and the second AI model are deployed on the UE, when the UE detects a degradation in the performance of the system, the UE requests a monitoring reference signal from the base station, and then the base station transmits the monitoring reference signal to the UE according to the request from the UE, and the UE, after receiving the monitoring reference signal, measures the channel information by using the monitoring reference signal, and determines whether to update the first reference signal pattern and the second AI model, according to the channel information measured using the monitoring reference signal and the channel information estimated by itself based on the second AI model.

[0279] As described above, the NMSE may be used as a metric for determining whether to update the first reference signal pattern and the second AI model, and in this case, the determining whether to update the first reference signal pattern and the second AI model according to the channel information measured using the monitoring reference signal and the channel information estimated by the second AI model includes: determining an NMSE of the channel information measured using the monitoring reference signal and the channel information estimated by the second AI model; if the NMSE is greater than a first threshold, determining to update the first reference signal pattern and the second AI model, thereby triggering an update of the first reference signal pattern and the second AI model.

[0280] Furthermore, in the present application, when the electronic apparatus is the UE, in a case where the first reference signal pattern and the second AI model are determined to be updated, the method described in FIG. 6A may further include: transmitting, to the base station, a request for update of the reference signal pattern; receiving, from the base station, third training data; determining a third reference signal pattern, based on the third training data and the first AI model; transmitting, to the base station, information associated with the third reference signal pattern, and receiving, from the base station, information associated with a fourth reference signal pattern to be applied to the UE, wherein the fourth reference signal pattern may be the third reference signal pattern or may be determined by the base station according to the third reference signal pattern. In the above description, the procedure for determining the third reference signal pattern is the same as the procedure of step S610 above with reference to FIG. 6A, and therefore will not be repeated herein, and furthermore, just like the relationship between the first reference signal pattern and the second reference signal pattern, the fourth reference signal pattern may be the same as the third reference signal pattern, or may be obtained by the base station by making adjustments to the third reference signal pattern.

[0281] In another exemplary embodiment of the present application, whether the electronic apparatus is the base station or the UE, the determining whether to update the first reference signal pattern and the second AI model may include determining to update the first reference signal pattern and the second AI model when the electronic apparatus detects a degradation in the system performance. That is, when the electronic apparatus detects a degradation in the performance of the system (e.g., Signal to Interference plus Noise Ratio (SINR) decreases, a Block Error Rate (BLER) increases, Channel Quality Indicator (CQI) decreases, a throughput (Tput) decreases, etc.), the electronic apparatus may determine to update the first reference signal pattern and the second AI model, thereby triggering an update of the first reference signal pattern and the second AI model.

[0282] In another exemplary embodiment of the present application, when the electronic apparatus is the base station, the determining whether to update the first reference signal pattern and the second AI model may include: when the base station detects a degradation in the system performance and a specific uplink resource of the UE is available, receiving a Sounding Reference Signal (SRS) from the UE via the specific uplink resource; determining whether to update the first reference signal pattern and the second AI model according to the channel information measured using the SRS and the channel information estimated by the second AI model.

[0283] Specifically, in a case where the first AI model and the second AI model are deployed on the base station, when the base station detects a degradation in the performance of the system, it may determine whether the specific uplink resource associated with the SRS of the UE is available, and if the specific uplink resource associated with the SRS of the UE is available, the base station may detect the specific uplink resource, obtain the SRS therefrom, and then, measure the channel information using the SRS, and estimate the channel information based on the second AI model, and thereafter determine whether to update the first reference signal pattern and the second AI model according to the channel information measured using the SRS and the channel information estimated based on the second AI model.

[0284] As described above, the SGCS may be used as a metric for determining whether to update the first reference signal pattern and the second AI model, and in this case, the determining whether to update the first reference signal pattern and the second AI model according to the channel information measured using the SRS and the channel information estimated by the second AI model may include: determining the SGCS of the channel information measured using the SRS and the channel information estimated by the second AI model; and if the SGCS is less than a second threshold, determining to update the first reference signal pattern and the second AI model.

[0285] Furthermore, in the present application, when the electronic apparatus is the base station, in the case where the first reference signal pattern and the second AI model are determined to be updated, the method described in FIG. 6A may further include: requesting a fourth training dataset from the UE; receiving the fourth training dataset from the UE; determining a fifth reference signal pattern, based on the fourth training dataset and the first AI model; determining a sixth reference signal pattern to be applied to the UE, according to the fifth reference signal pattern; and transmitting information associated with the sixth reference signal pattern to the UE. In the above description, the procedure of determining the fifth reference signal pattern is the same as the procedure of step S610 above with reference to FIG. 6A, and therefore will not be repeated herein. In addition, just like the relationship between the first reference signal pattern and the second reference signal pattern, the sixth reference signal pattern may be the same as the fifth reference signal pattern or may be obtained by adjusting the fifth reference signal pattern by the base station.

[0286] Various examples of determining to update the first reference signal pattern and the second AI model are described above.

[0287] In addition, when an antenna dimension and bandwidth increase substantially, the AI model training overhead increases substantially. To this end, based on the method described above with reference to FIG. 6A, the problem of a substantial increase in the AI model training overhead caused by a substantial increase in the antenna dimension and bandwidth may be solved by adding a data pre-processing operation and a data post-processing operation. Corresponding operations may be performed by a data pre-processing module and a data post-processing module in the reference signal design and channel estimation module in FIG. 6C, which serve to find carriers or RBs at key frequency positions in channel information of an entire bandwidth by using channel information of one symbol, to recover the channel information of the entire bandwidth, so as to reduce the number of training data of the AI and then improve a training efficiency, thereby meeting business requirements.

[0288] Thus, in the above procedure of obtaining the plurality of sparse weight factors, a compressed channel matrix may be obtained by compressing the channel matrix of the UE, and accordingly, the plurality of sparse weight factors may be obtained by training the first AI model using the compressed channel matrix. Correspondingly, this compressed channel matrix may likewise be applied to train the second AI model, such that the trained second AI model may obtain a channel matrix compressed in the frequency-domain by the channel estimation. The compression operation may be performed by the data preprocessing module as shown in FIG. 6C. As shown in FIG. 17, the data preprocessing module may reduce a dimension of the channel matrix of the UE to the frequency-domain compressed channel matrix, thereby reducing model parameters and training data of the first AI model of the sparse reference signal and channel estimation module, and at the same time, reducing model parameters and training data of the second AI model.

[0289] Specifically, the obtaining the compressed channel matrix by compressing the channel matrix of the UE includes: obtaining a time-invariant frequency-domain channel feature based on the channel matrix of the UE; based on the time-invariant frequency-domain channel feature, obtaining a time-invariant sparse frequency-domain channel feature, with minimizing an error power of a sparse frequency-domain channel feature; obtaining the compressed channel matrix based on the time-invariant sparse frequency-domain channel feature. This is described in detail below with reference to FIG. 18.

[0290] FIG. 18 is a flowchart illustrating a procedure for compressing a channel matrix of a UE to obtain a compressed channel matrix according to an exemplary embodiment of the present application.

[0291] As shown in FIG. 18, at step S1810, a time-invariant frequency-domain channel feature is obtained based on the channel matrix of the UE. As shown in FIG. 19A, firstly, the channel matrix of the UEs is obtained by performing channel combination on 1-symbol channels of K UEs, and then, the time-invariant frequency-domain channel feature is obtained by performing Singular Value Decomposition (SVD) computation on the channel matrix of the UEs.

[0292] At step S1820, based on the time-invariant frequency-domain channel feature, a time-invariant sparse frequency-domain channel feature is obtained, with minimizing an error power of the sparse frequency-domain channel feature. The time-invariant sparse frequency-domain channel feature may be obtained by an error suppression algorithm.

[0293] Specifically, the minimization of the error power of the sparse frequency-domain channel featureFsubmay be defined as the following equation (5).

[0294]

[0295] In theory, a combined UE channel informationHcombmay be computed according to the following Equation (6).

[0296]

[0297] Wherein,Hcomb,subrepresents UE channel information compressed in the frequency-domain.

[0298] However, in practice, the actual combined UE channel informationHcomb,realis computed according to Equation (7) below.

[0299]

[0300] The error power of the sparse frequency-domain channel featureFsubmay be calculated according to Equation (8) below.

[0301]

[0302] Based on this, the time-invariant sparse frequency-domain channel featureFsubmay be finally obtained by the following operations.

[0303] (1) Define a maximum number of RBs based on a rank r of the matrix.

[0304] (2) Find one row (i.e.,f1) from F, andFsub,1=f1, such that is minimized.

[0305] (3) Find another row (i.e.,f2) from F, and , such that is minimized.

[0306] (4) Return to execute (3) untilFsub=Fsub,ror the error powerPerroris above a sixth threshold.

[0307] The time-invariant sparse frequency-domain channel featureFsubmay be obtained by the above process, which may be used as an input of the sparse reference signal and channel estimation module for training the first AI model.

[0308] At step S1830, the compressed channel matrix is obtained based on the time-invariant sparse frequency-domain channel featuresFsub.

[0309] Specifically, as shown in FIG. 19B, the compressed channel matrixHcomb,subis obtained by selectingNf,subrows fromHcom, wherein the indexes of theNf,subrows are the same index asFsub.

[0310] In the above description,Hirepresents the channel information (i.e., channel matrix) of ani-th UE;Hcombrepresents the combined UE channel information (i.e., combined channel matrix);Hcomb,subrepresents UE channel information compressed in the frequency domain (i.e., compressed channel matrix);Frepresents a channel frequency-domain feature;Urepresents a left singularity vector;Σrepresents a feature value;Krepresents the number of UEs;Ntrepresents the number of transmitting antenna ports;Nrrepresents the number of receiving antenna ports;Nfrepresents the number of RBs or subcarriers;Nf,subrepresents the number of RBs or subcarriers after compression;rrepresents the rank of the matrix.

[0311] Accordingly, in the case of pre-processing the training data using the data pre-processing module, the channel matrix that is obtained by the channel estimation through the second AI model is actually the channel matrix compressed in the frequency-domain, and therefore, the method described with reference to FIG. 6A further needs to include: recovering a channel matrix that is obtained by the channel estimation through the second AI model to a channel matrix corresponding to full spatial-domain positions and full frequency-domain positions, by using the time-invariant frequency-domain channel feature and the time-invariant sparse frequency-domain channel feature, and in the present application, the spatial-domain position may be an antenna port or a beam. That is, the data post-processing module as shown in FIG. 6C may be used to recover the channel matrix compressed in the frequency-domain that is obtained by the channel estimation through the second AI model, to the channel matrix (or channel information) corresponding to the full spatial-domain positions and the full frequency-domain positions by using the time-invariant frequency-domain channel feature and the time-invariant sparse frequency-domain channel feature output from the pre-processing module.

[0312] Specifically, the channel matrix (or channel information)Hcombcorresponding to the full spatial-domain positions and the full frequency-domain positions, which can also be referred to as original channel information (or channel matrix), may be obtained by using Equation (9) below.

[0313]

[0314] Wherein represents the post-processing of the AI channel estimation, and represents an estimated matrix of the channel matrix compressed in the frequency-domain from the second AI model. As shown in FIG. 19C, after is subjected to the post-processing of , the channel matrixHcombcorresponding to the full spatial-domain positions and the full frequency-domain positions may be obtained.

[0315] The operation of the above data pre-processing module and the data post-processing module may solve the problem of a significant increase in the AI model training overhead caused by a significant increase in antenna dimension and bandwidth.

[0316] Furthermore, as the number of UEs increases, the CSI-RS overhead and indication information may increase. To this end, the method described above with reference to FIG. 6A may group UEs having the same channel feature into one group and the UEs in the same group share a customized reference signal pattern, so that the problem of increased overhead and indication information of the CSI-RS caused by an increase in the number of UEs may be solved. This operation may be performed by a UE grouping module in the reference signal design and channel estimation module of FIG. 6D. For example, FIG. 20 illustrates a diagram of an example of grouping UEs when the UEs are in different positions, according to an exemplary embodiment of the present application. As shown in FIG. 20, a reference signal pattern suitable for a first group of UEs is a reference signal pattern 1, a reference signal pattern suitable for a second group of UEs is a reference signal pattern 2, and a reference signal pattern suitable for a third group of UEs is a reference signal pattern 3.

[0317] The following descriptions are given by grouping procedures when the electronic apparatus is the base station and when the electronic apparatus is the UE, respectively.

[0318] In one exemplary embodiment of the present application, when the electronic apparatus is the base station, firstly, the base station calculates a channel feature of each UE, wherein the channel feature may include at least one of position information, Reference Signal Received Power (RSRP), Line-of-Sight (LOS) / Non-Line-of-Sight (NLOS) state information, Doppler delay, and a direction angle. Then, the base station may group the UEs according to the calculated channel feature, for example, group UEs having similar channel feature into the same group, for example, as shown in FIG. 20, the UEs are grouped into three groups according to position information of the UEs. Thereafter, the base station may determine a first reference signal pattern for UEs belonging to the same group of UEs, according to the second reference signal pattern obtained through the AI model training.

[0319] For example, as shown in FIG. 21A, the base station may predefine one group of second reference signal patterns based on the training of the AI model, and then, calculate the channel feature of each UE to be grouped according to the CSI measurement requests from the UEs, and group the UEs based on the calculated channel feature, and thereafter, the base station determines the first reference signal pattern belonging to each group of UEs according to the predefined one group of second reference signal patterns, and indicates the corresponding first reference signal pattern and CSI feedback configuration to respective UEs.

[0320] Further, in the case where the UEs are grouped, when the base station receives a reference signal pattern update request from, for example, a first UE in a first group, when the base station detects a degradation in transmission performance with respect to the first UE, when the NMSE of the channel information estimated by the second AI model and the channel information received from the first UE measured using the monitoring reference signal is greater than a first threshold, or when the SGCS of the channel information measured using the SRS received from the first UE and the channel information estimated by the second AI model is less than a second threshold, the base station may re-group the first UE and re-determine the reference signal pattern to be indicated to the UE. For example, as shown in FIG. 21A, when the UE1 detects a degradation in transmission performance and transmits a reference signal pattern update request to the base station, the base station may re-group the UE1 based on the channel feature of the UE1, re-determine the reference signal pattern to be indicated to the UE1, and indicate this re-determined reference signal pattern to the UE1.

[0321] In one example, the re-determining the reference signal pattern to be indicated to the first UE includes: when a channel feature of the first UE is similar to a channel feature of another group of UEs, grouping the first UE to the other group of UEs, and determining a reference signal pattern for the other group of UEs as the reference signal pattern to be indicated to the first UE; when the channel feature of the first UE is not similar to a channel feature of any group of UEs, for the first UE, determining a plurality of new sparse weight factors by training the first AI model, and re-determining the reference signal pattern to be indicated to the first UE according to the plurality of new sparse weight factors and the at least one candidate reference signal pattern set. In the present application, when the similarity between the channel features of two UEs is greater than or equal to a fourth threshold, the channel features of the two UEs are considered to be similar, and when the similarity between the channel features of the two UEs is less than the fourth threshold, the channel features of the two UEs are considered to be dissimilar. The above-described procedure for re-determining the reference signal pattern to be indicated to the first UE is the same as the step S610 described above with reference to FIG. 6A, and therefore will not be repeated herein. In the following, an example procedure of reference signal pattern design in the case of grouping UEs when the electronic apparatus is the base station will be described in more detail with reference to the flowchart shown in FIG. 21B.

[0322] As shown in FIG. 21B, the left drawing illustrates a flowchart of reference signal pattern design in the case of grouping of the UEs, and the right drawing illustrates a signal flow diagram of the reference signal pattern design and channel estimation module.

[0323] At step S2101, the base station determines that a UE access the network.

[0324] At step S2102, the base station determines whether the UE is capable of being grouped into any UE group that already exists, e.g., calculates the channel feature of the UE and determine whether its channel feature is similar to that of any group of UEs.

[0325] If a similarity between the channel feature of the UE and the channel feature of a certain group of UEs is greater than or equal to the fourth threshold, then at step S2103, the UE is grouped into this group of UEs, and a reference signal pattern of this group of UEs is determined to be the reference signal pattern to be indicated to the UE, and then it proceeds to step S2106.

[0326] If the similarity between the channel feature of the UE and the channel feature of any group of UEs is less than the fourth threshold, reference signal patterns for current respective groups of UEs are considered to be unsuitable for the UE, and therefore, it proceeds to step S2104. At step S2104, the base station determines, for the UE, the reference signal pattern to be indicated to the UE by the AI model training, as shown in the figure, the reference signal pattern design module in the reference signal pattern design and channel estimation module designs the reference signal pattern to be indicated to the UE. Further, at step S2104, the base station also trains the second AI model.

[0327] Then, at step S2105, the base station transmits information associated with the re-determined reference signal pattern to the UE and transmits a reference signal to the UE according to the reference signal pattern, as shown in the figure, the base station transmits the reference signal pattern designed by the reference signal pattern design module and a CSI-RS corresponding to the reference signal pattern, to the UE. Furthermore, as shown in the figure, the reference signal pattern design module indicates the designed reference signal pattern for the UE, to the channel estimation module.

[0328] At step S2106, the base station performs channel estimation, according to the channel information (e.g., CSI) measured using the reference signal described above that is received from the UE. As shown in the figure, the UE measures the channel information (e.g., CSI) using the CSI-RS received from the base station, and then feed back the channel information to the base station, and a channel estimation module in the base station performs the channel estimation based on the received measurement information, using the second AI model.

[0329] At step S2107, the base station determines whether the second AI model and the reference signal pattern for the UE need to be updated, as shown in the figure, an AI model update module in the reference signal design and channel estimation module of FIG. 6B may determine whether the second AI model and the reference signal pattern for the UE need to be updated. If it is determined that the second AI model and the reference signal pattern for the UE need to be updated, it returns to step S2104 to re-determine the reference signal pattern to be indicated to the UE by the AI model training, and to train the second AI model. If it is determined that the second AI model and the reference signal pattern for the UE are not to be updated, at step S2108, the base station performs processing of precoding, scheduling, and so on.

[0330] The above describes the UE grouping procedure when the electronic apparatus is the base station. Below, the UE grouping procedure when the electronic apparatus is the UE will be described.

[0331] As in the method described above with reference to FIG. 6A, each UE transmits information associated with the determined second reference signal pattern to the base station, and then, receives information associated with the first reference signal pattern from the base station, wherein the first reference signal pattern is determined by the base station based on the second reference signal pattern. Specifically, the first reference signal pattern is determined by the base station based on the second reference signal pattern, by: grouping UEs, by the base station, according to similarities between the second reference signal pattern obtained from the UE and reference signal patterns from other UEs, and determining the first reference signal pattern for one group of UEs to which the UE belongs. In the present application, the similarity between the reference signal patterns mentioned herein may refer to an overlap ratio of reference signal positions in the reference signal patterns. For example, as shown in FIG. 22, when the similarities among the reference signal patterns for UE1, UE2, and UE3 are high and above a fifth threshold, UE1, UE2, and UE3 may be grouped into the same group, and a group reference signal pattern as shown in FIG. 22 is determined as the first reference signal pattern for each UE of this group of UEs, and in one example, the first reference signal pattern may be an union of the reference signal patterns for UE1, UE2, and UE3, however, the present application is not limited thereto.

[0332] Furthermore, in the case of grouping of the UEs, when the UE detects a degradation in transmission performance, the UE transmits a reference signal pattern update request to the base station, obtains a plurality of new sparse weight factors according to the training of the first AI model using training data that is newly received from the base station, determines another reference signal pattern according to the plurality of new sparse weight factors and the at least one candidate reference signal pattern set, transmits information associated with this other reference signal pattern to the base station, and then, receives, from the base station, information associated with a reference signal pattern that is re-determined for this UE according to this other reference signal pattern.

[0333] For example, as shown in FIG. 23, when a UE1 detects a degradation in the transmission performance, the UE1 transmits the reference signal pattern update request to the base station, the base station transmits training data to the UE1, the UE1 obtains a plurality of new sparse weight factors by training the first AI model using the training data that is newly received from the base station, and determines another reference signal pattern according to the plurality of new coefficient weight factors and at least one candidate reference signal pattern set, and thereafter, the UE1 feeds this other reference signal pattern back to the base station, the base station re-groups the UE1 based on this other reference signal pattern and indicates, to the UE1, a reference signal pattern for a group of UEs into which the UE1 is re-grouped, and furthermore, the UE1 fine-tunes the second AI model using this received reference signal pattern.

[0334] In order to enable those skilled in the art to understand the technical solutions of the present application, the general flow of the present application in the case where the first AI model and the second AI model are deployed on the base station is described in detail below with reference to FIG. 24A.

[0335] As shown in FIG. 24A, at step S2401, the training data is collected based on historical CSI, or the training data is obtained through estimation of an uplink SRS, to obtain a first training data set finally.

[0336] At step S2402, a sparse reference signal and channel estimation module (i.e., the first AI model) is trained by the first training dataset, so as to obtain the sparse weight factors from the trained first AI model.

[0337] At step S2403, a second reference signal pattern is determined using the sparse weight factors obtained above and at least one candidate reference signal pattern set.

[0338] At step S2404, a second training dataset for a channel estimation module (i.e., the second AI model) is generated from the first training dataset based on the second reference signal pattern, and the second AI model is trained based on the second training dataset.

[0339] At step S2405, the base station indicates a first reference signal pattern to the UE via air-interface signaling, and transmits a reference signal corresponding to the first reference signal pattern to the UE, wherein the first reference signal pattern may be the second reference signal pattern or may be obtained by adjusting the second reference signal pattern by the base station.

[0340] At step S2406, the UE feeds CSI back to the base station based on the air-interface signaling, after measuring channel information using the reference signal received from the base station.

[0341] At step S2407, the base station performs channel estimation in the spatial-domain and frequency-domain based on the CSI fed back by the UE, using the second AI model trained at step S2404, i.e., obtains an entire channel matrix.

[0342] At step S2408, the base station determines whether the second AI model and the second reference signal pattern need to be updated, by evaluating the second AI model based on the estimated channel matrix. If the update is needed, steps S2401 to S2407 may be repeated.

[0343] If no update is needed, step S2409 is performed, and the base station performs subsequent operations of pre-coding, scheduling, and so on., based on the estimated channel matrix.

[0344] The process described above with reference to FIG. 24A may correspond to the structure diagram of FIG. 6B. In addition, the above flowchart may also include a data pre-processing operation and a data post-processing operation and / or a UE grouping operation. For example, in another embodiment (corresponding to the structural diagram of FIG. 6C), the data pre-processing operation may be performed on the collected first training dataset prior to step S2402, and then, at step S2402, a plurality of sparse weight factors may be obtained by training the first AI model using the compressed channel matrix. Accordingly, at step S2407, after the channel estimation through the second AI model, the base station, by performing the data post-processing operation, recovers the channel matrix compressed in the frequency-domain that is obtained by performing the channel estimation through the second AI model, to the channel matrix (or channel information) corresponding to the full spatial-domain positions and the full frequency-domain positions. In another embodiment (corresponding to the structural diagram of FIG. 6D), before step S2401, the base station may further determine whether the channel feature of the UE is similar to the channel feature of a certain group of UEs. If similar, this UE may be grouped into this group of UEs, and the reference signal pattern for this group of UEs may be directly determined as the reference signal pattern to be indicated to the UE, and correspondingly, the first reference signal pattern and the second reference signal pattern are no longer determined through the above steps S2401 to S2404. If the channel feature of the UE is not similar to the channel feature of any group of UEs, the base station may determine the second reference signal pattern through steps S2401 to S2404 above, and transmit, to the UE, the information associated with the first reference signal pattern associated with the second reference signal pattern ( i.e., transmit, to the UE, the information associated with the second reference signal pattern, or transmit, to the UE, the information associated with the first reference signal pattern obtained by adjusting the second reference signal pattern). In another embodiment (corresponding to the structure diagram of FIG. 6E), the above flowchart may further include all the data pre-processing operation, the data post-processing operation and the UE grouping operation, which will not be described herein.

[0345] Since the above procedures have been similarly described above with reference to FIGS. 6A to 23, it will not be repeated here.

[0346] FIG. 24B is a flowchart illustrating a method performed by an electronic apparatus according to another exemplary embodiment of the present application.

[0347] As shown in FIG. 24B, at step S241, information associated with the first reference signal pattern and / or CSI feedback configuration are transmitted to the UE via DCI signaling, MAC CE signaling, or RRC signaling. The first reference signal pattern may be the first reference signal pattern as described above with reference to FIG. 6A, but the present application is not limited thereto, and may be, a reference signal pattern determined according to existing methods.

[0348] In the present application, the information associated with the first reference signal pattern may be transmitted to a UE by: including, in the DCI signaling, the MAC CE signaling, or the RRC signaling, at least one of information for indicating a spatial-domain and / or frequency-domain associated with the first reference signal pattern, information for indicating one of at least one predefined reference signal patterns, or the information for indicating one of the at least one predefined reference signal patterns and information associated with an offset of the first reference signal pattern. That is, the first reference signal pattern may be transmitted to the UE in an explicit manner. In the present application, the information for indicating the spatial-domain and / or frequency-domain associated with the first reference signal pattern may include starting values of spatial-domain positions and / or frequency-domain positions of the reference signals, an interval of the spatial-domain positions and / or the frequency-domain positions, and the number of the spatial-domain positions and / or the frequency-domain positions.

[0349] Alternatively, the information associated with the first reference signal pattern may indicate the first reference signal pattern to the UE, by transmitting, to the UE, the DCI signaling, the MAC CE signaling, or the RRC signaling that includes the information indicating the resource for transmitting the reference signal, wherein there is a mapping relationship between the resource for transmitting the reference signal and the first reference signal pattern. In one exemplary embodiment of the present application, the mapping relationship may be determined based on at least two of parameters: a sequence number of the reference signal, a size of a Code Division Multiplexing (CDM) group, the number of CDM groups, the number of antenna ports for the reference signal, a time-domain position and a frequency-domain position of the reference signal. That is, the first reference signal pattern may be transmitted to the UE in an implicit manner. Since it has been described in detail above, it will not be elaborated further here.

[0350] In the present application, the CSI feedback configuration may be used to indicate feedback of the quantized CSI phase and amplitude of the reference signal on the receiving antenna. In one example, the quantized CSI phase may be represented by 3 bits and the quantized CSI amplitude may be represented by 4 bits. In another example, the quantized CSI phase may be represented by 4 bits and the quantized CSI amplitude may be represented by 3 bits. In the present application, the quantized CSI phase and amplitude are one of: a quantized CSI phase and amplitude of a reference signal on one receiving antenna, wherein the one receiving antenna is indicated via DCI signaling, MAC-CE signaling, or RRC signaling; and quantized CSI phases and amplitudes of reference signals on all receiving antennas. Since it has been described in detail above, it will not be elaborated further here.

[0351] The present application jointly considers the design of the reference signal pattern and the terminal channel estimation, and utilizes the sparsity of the user channel to reduce the resource positions that need to be occupied for transmitting the reference signal as much as possible on abasis of ensuring the channel estimation performance, and therefore improves the system efficiency. In addition, the present application, in order to enable the final generated reference signal pattern to be applied in a standardization of 3GPP, predefines some alternative reference signal patterns in accordance with the 3GPP protocol standard, dot-products the input sparse weight factors and the alternative reference signal patterns (i.e., introduces a constraint condition in the reference signal pattern), and selects a reference signal pattern type that is most suitable for the current user channel among the alternative reference signal patterns, so that the generated reference signal pattern can be standardized. In addition, the present application, by taking into account that the channel feature of the UE is closely related to the reference signal pattern and the channel estimation, groups different channel types, and use the same reference signal pattern for UEs belonging to the same group, and re-design the reference signal patterns for UEs belonging to different groups independently, so as to solve the problem of the increase in the CSI-RS overhead and the increase in the indication information caused by an increase in the number of UEs. In addition, the present application, by adding the data pre-processing operation and the data post-processing operation, solves the problem of a significant increase in the overhead of AI model training caused by a significant increase in antenna dimension and bandwidth.

[0352] FIG. 25 is a block diagram illustrating an electronic apparatus 2500 according to an exemplary embodiment of the present disclosure.

[0353] As shown in FIG. 25, the electronic apparatus 2500 includes a transceiver 2510 and a processor 2520, wherein the processor 2520 is coupled to the transceiver 2510 and configured to perform the method described above with reference to FIGS. 6A to 24B. Details of the operations of the above method may be referred to the description of FIGS. 6A to 24B, which will be not repeated herein.

[0354] FIG. 26 is a block diagram of a terminal or user equipment (UE) 2600 according to an embodiment of the disclosure. Furthermore , the UE of FIG. 26 may correspond to UE (or terminal) of FIG. 3.

[0355] The terminal is an electronic device capable of wireless communication and having various form factors, examples of the terminal may include a UE, a mobile station (MS), a cellular phone, a smartphone, a computer, a tablet, a wearable device, an Internet of Things (IoT) device, or any other device / system capable of performing wireless communication with a base station (BS) and / or another terminal through a wireless channel.

[0356] Referring to FIG. 26, the UE 2600 may include at least one transceiver (hereinafter, referred to as simply "transceiver") 2601, at least one processor (hereinafter, referred to as simply "processor") 2602, and at least one memory (hereinafter, referred to as simply "memory") 2603. According to at least one or a combination of methods corresponding to the embodiments described in the present disclosure, the transceiver 2601, the processor 2602, and the memory 2603 of the UE 2600 may operate. However, components of the UE 2600 are not limited to the example components illustrated in FIG. 26. In another embodiment, the UE 2600 may further include additional components in addition to the above-mentioned components, or some components may be omitted. Further, in some embodiments, any combination of the transceiver 2601, the processor 2602, or the memory 2603 may be integrated in the form of one component.

[0357] The transceiver 2601 may be a communication circuit or communication circuitry that enables the UE 2600 to perform wireless communication with a node or an entity of a network. For example, the transceiver 2601 may enable the UE 2600 to transmit or receive a signal to or from a BS through cellular communication, or to transmit or receive a signal to or from another UE through cellular communication. For example, the transceiver 2601 may support at least one of various cellular communication technologies including 3rd generation (3G), 4th generation (4G), long term evolution (LTE), 5th generation (5G) NR, 6th generation (6G), and various cellular wireless communication technologies supported by the transceiver (2601) may include all subsequent generations of evolved wireless communications.

[0358] According to an embodiment, the UE 2600 may include a plurality of transceivers. For example, in the case of supporting evolved-universal terrestrial radio access-new radio (E-UTRA-NR) dual connectivity (EN-DC), the UE 2600 may include a first transceiver supporting the 4G LTE wireless communication and a second transceiver supporting the 5G NR wireless communication. According to another embodiment, in the case of supporting NR-dual connectivity (NR-DC), the UE 2600 may include a plurality of transceivers supporting the 5G NR wireless communication. According to still another embodiment, in the case of supporting near field wireless communication, the UE 2600 may separately include a transceiver supporting at least one standard in the group of wireless communication protocol standards as defined in the protocol standards for Bluetooth®, wireless local area network (WLAN) network (including institute of electrical and electronics engineers (IEEE) 802.11-2016 standard or its amendments, e.g., 802.11ah, 802.11ad, 802.11ay, 802.11ax, 802.11az, 802.11ba, and 802.11be, without being limited thereto).

[0359] According to an embodiment, the transceiver 2601 may include various circuit structures used to transmit or receive signals to or from a BS through a wireless channel. The signals may include control information and data. For example, the transceiver 2601 may include a radio frequency (RF) transmitter for up-converting and amplifying the frequency of a transmitted signal and an RF receiver for low-noise-amplifying a received signal and down-converting the frequency thereof. The transceiver 2601 may output a signal received through a wireless channel to the processor 2602 and may transmit, through a wireless channel, a signal output from the processor 2602.

[0360] The processor 2602 may control general operations of the UE 2600 according to embodiments of the disclosure. The processor 2602 may be implemented by one or more integrated circuit (or circuitry) (IC) chips and may execute various data processing operations. The processor 2602 may include at least one electric circuit, and may execute instructions (or a program, codes, data, etc.) stored in the memory 2603, individually, collectively or in any combination thereof. Further, the processor 2602 may include a single-core processor or multi-core processor, and may include a processor assembly including a plurality of processing circuits (circuitry) according to a specific implementation scheme.

[0361] The processor 2602 may be electrically, operatively, and / or communicatively coupled to the transceiver 2601 to control the transceiver 2601.

[0362] The processor 2602 may include at least one processor (or processing circuitry), and the at least one processor may perform the following operations individually, collectively or in any combination thereof. For example, the processor 2602 may include a communication processor (CP) configured to control communication operations and an application processor (AP) configured to control execution of an upper layer (for example, an application layer). In a specific embodiment, at least a part of the processor 2602 may be included in one chip (or IC) and the other part of the processor 2602 may be included in another chip (or IC). Otherwise, at least one processor may be included in another component, for example, the transceiver 2601 or the memory 2603.

[0363] The processor 2602 may perform or control or cause an operation of the UE 2600 for executing at least one or a combination of methods according to embodiments of the disclosure. For example, the processor 2602 may control operations of the UE 2600 for processing a downlink signal received from a BS or generating and transmitting an uplink signal to a BS. To this end, the processor 2602 may execute a computer program, codes, or instructions stored in the memory 2603, so as to control other components of the UE 2600 to enable execution of various operations.

[0364] The memory 2603 corresponds to a hardware storage device capable of temporarily or permanently storing information and may include one or more storage media. For example, the memory 2603 may include a memory assembly including one or more storage media. For example, the one or more storage media may include permanent memory, such as a hard drive, flash memory, or read-only memory (ROM), semipermanent memory, such as random access memory (RAM), cache memory, or a combination thereof.

[0365] The memory 2603 may be electrically, operatively, and / or communicatively coupled to the processor 2602 and may be accessed by the processor 2602.

[0366] The memory 2603 may store a computer program, codes, or instructions executable by the processor 2602. According to an embodiment, a computer program, codes, or instructions executable by the processor 2602 may be either stored in a single memory device or separated and distributedly stored in two or more memory devices. By executing the instructions stored in the memory 2603, the processor 2602 may perform various functions according to an embodiment of the disclosure.

[0367] According to an embodiment of the disclosure, operations of the UE 2600 may be caused to be performed based on execution of instructions (or a computer program or codes) stored in the memory 2603 by at least one processor (or processing circuitry) configured to execute the same individually, collectively, or in any combination thereof, based on processing circuitry that is not configured to execute instructions, and / or based on components of processing circuitry that is not configured to execute instructions.

[0368] FIG. 27 is a block diagram of a base station (BS) 2700 according to an embodiment of the disclosure. Furthermore, the base station of FIG. 27 may correspond to the base station of FIG. 2.

[0369] The BS 2700 may perform wireless communication with at least one user equipment (UE) located within the area of the BS 2700 through a wireless channel. The BS 2700 may perform communication with a node or an entity of a network through wired or wireless communication.

[0370] Referring to FIG. 27, the BS 2700 may include at least one transceiver (hereinafter, referred to as simply "transceiver") 2701, at least one processor (hereinafter, referred to as simply "processor") 2702, and at least one memory (hereinafter, referred to as simply "memory") 2703. According to at least one or a combination of methods corresponding to the embodiments described in the present disclosure, the transceiver 2701, the processor 2702, and the memory 2703 of the BS 2700 may operate. However, components of the BS 2700 are not limited to the example components illustrated in FIG. 27. In another embodiment, the BS 2700 may further include additional components in addition to the above-mentioned components, or some components may be omitted. Further, in some embodiments, any combination of the transceiver 2701, the processor 2702, or the memory 2703 may be integrated in the form of one component.

[0371] The transceiver 2701 may be a communication circuit or communication circuitry that enables the BS 2700 to perform wireless communication with a node or an entity of a network. For example, the transceiver 2701 may enable the BS 2700 to transmit or receive a signal to or from the UE 2600 through cellular communication, or to transmit or receive a signal to or from another network entity through wireless communication. For example, the transceiver 2701 may support various cellular communication technologies including 3rd generation (3G), 4th generation (4G), long term evolution (LTE), 5th generation (5G) NR, 6th generation (6G), and various cellular wireless communication technologies supported by the transceiver (2701) may include all subsequent generations of evolved wireless communications.. According to an embodiment, the transceiver 2701 may include various circuit structures used to transmit or receive signals to or from a UE through a wireless channel. The signals may include control information and data. For example, the transceiver 2701 may include a radio frequency (RF) transmitter for up-converting and amplifying the frequency of a transmitted signal and an RF receiver for low-noise-amplifying a received signal and down-converting the frequency thereof. The transceiver 2701 may output a signal received through a wireless channel to the processor 2702 and may transmit, through a wireless channel, a signal output from the processor 2702.

[0372] Meanwhile, according to an embodiment of the present disclosure, the BS 2700 may perform communication with a node or an entity of a network through wired or wireless communication. For example, the BS 2700 may perform wired or wireless communication with an adjacent BS, or a node or an entity of a core network through a backhaul network. Although not illustrated in FIG. 27, when the BS 2700 performs wired communication, the BS 2700 may further include a separate network interface for wired communication in addition to the transceiver 2701. The network interface may be referred to as network interface circuitry or communication interface circuitry.

[0373] The processor 2702 may control general operations of the BS 2700 according to embodiments of the disclosure. The processor 2702 may be implemented by one or more integrated circuit (or circuitry) (IC) chips and may execute various data processing operations. The processor 2702 may include at least one electric circuit, and may execute instructions (or a program, codes, data, etc.) stored in the memory 2703, individually, collectively or in any combination thereof. Further, the processor 2702 may include a single-core processor or multi-core processor, and may include a processor assembly including a plurality of processing circuits (circuitry) according to a specific implementation scheme.

[0374] The processor 2702 may be electrically, operatively, and / or communicatively coupled to the transceiver 2701 to control the transceiver 2701.

[0375] The processor 2702 may include at least one processor (or processing circuitry), and the at least one processor may perform the following operations individually, collectively or in any combination thereof. In a specific embodiment, at least a part of the processor 2702 may be included in one chip (or IC) and the other part of the processor 2702 may be included in another chip (or IC). Otherwise, at least one processor may be included in another component, for example, the transceiver 2701 or the memory 2703.

[0376] The processor 2702 may perform or control or cause an operation of the BS 2700 for executing at least one or a combination of methods according to embodiments of the disclosure. For example, the processor 2702 may control operations of the BS 2700 for generating and transmitting a downlink signal to a UE or processing an uplink signal received from a UE. Otherwise, the BS 2700 may transmit or receive a signal to or from a neighboring BS, transfer a signal received from a UE to an upper node of the network, or transmit a signal transferred from an upper node of the network to a UE. To this end, the processor 2702 may execute a computer program, codes, or instructions stored in the memory 2703, so as to control other components of the BS 2700 to enable execution of various operations.

[0377] The memory 2703 corresponds to a hardware storage device capable of temporarily or permanently storing information and may include one or more storage media. For example, the memory 2703 may include a memory assembly including one or more storage media. For example, the one or more storage media may include permanent memory, such as a hard drive, flash memory, or read-only memory (ROM), semipermanent memory, such as random access memory (RAM), cache memory, or a combination thereof.

[0378] The memory 2703 may be electrically, operatively, and / or communicatively coupled to the processor 2702 and may be accessed by the processor 2702.

[0379] The memory 2703 may store a computer program, codes, or instructions executable by the processor 2702. According to an embodiment, a computer program, codes, or instructions executable by the processor 2702 may be either stored in a single memory device or separated and distributedly stored in two or more memory devices. By executing the instructions stored in the memory 2703, the processor 2702 may perform various functions according to an embodiment of the disclosure.

[0380] According to an embodiment of the disclosure, operations of the BS 2700 may be caused to be performed based on execution of instructions (or a computer program or codes) stored in the memory 2703 by at least one processor (or processing circuitry) configured to execute the same individually, collectively, or in any combination thereof, based on processing circuitry that is not configured to execute instructions, and / or based on components of processing circuitry that is not configured to execute instructions.

[0381] The UE or the base station may perform various communication procedures related to the control plane or the user plane by cooperating with one or more network entities based on wireless communication. For example, the UE may communicate with a network entity (for example, an Access and Mobility Management Function (AMF), a Session Management Function (SMF), rtc.) via the base station, or the base station may perform at least one communication procedure by directly transmitting and receiving signals to / from, or relaying signals between, the network entities.

[0382] The structure of the above-described network entity will be described in more detail with reference to the drawings.

[0383] FIG. 28 is a block diagram of a network entity 2800 according to an embodiment of the disclosure.

[0384] The network entity 2800 may include an entity (apparatus, device, or server, etc.) that performs one or more network functions (NFs) or a part of a network function constituting a core network (e.g., a 5th generation (5G) core (5GC)) in a communication system. In this case, multiple NFs may be implemented within a single network entity, or a single NF may be distributed and implemented across a plurality of network entities. In addition, when an NF is implemented within the network entity, the NF may be implemented in the form of software, and in such a case, a program for operating the NF may be stored in memory of the network entity 2800.

[0385] A single NF may be implemented by one or more instances, which may be deployed on the same network entity or distributed across multiple network entities to operate. The instance may be a software unit that logically executes a specific network function, and may be implemented in a form that is decoupled from physical hardware resources. Further, one or more NFs may be implemented in the form of one network slice to operate to satisfy specifications required by a particular service.

[0386] The NF may include at least one of an access and mobility management function (AMF), a session management function (SMF), a local session management function (L-SMF), a user plane function (UPF), a local user plane function (L-UPF), a policy control function (PCF), a unified data management (UDM), a unified data repository (UDR), a network exposure function (NEF), a network repository function (NRF), an application function (AF), a network slice selection function (NSSF), a network data analytics function (NWDAF), a network slice admission control function (NSACF), an authentication server function (AUSF), or a data network (DN), etc.

[0387] Referring to FIG. 28, the network entity 2800 may include at least one network interface 2801, at least one processor 2802 (hereinafter, "processor"), and at least one memory 2803 (hereinafter, "memory"). As described above, a NF may be implemented in the form of a physical device such as the network entity 2800, or may be virtualized and executed in the form of an instance. When implemented as an instance, the NF need not necessarily include physical components as illustrated in FIG. 28. In such a case, the instance may be logically represented as comprising one or more logical functional elements.

[0388] According to at least one or a combination of methods corresponding to the embodiments described in the present disclosure, the network interface 2801, the processor 2802, and the memory 2803 of the network entity 2800 may operate. However, components of the network entity 2800 are not limited to the example components illustrated in FIG. 28. In another embodiment, the network entity 2800 may further include additional components in addition to the above-mentioned components, or some components may be omitted. Further, in an embodiment, the network interface 2801, the processor 2802, or the memory 2803 may be integrated in the form of one component.

[0389] The network interface 2801 is a collective term for a transmitter part of the network entity 2800 and a receiver part of the network entity 2800, and may be a communication circuit for transmitting or receiving a signal to or from a user equipment (UE), a base station (BS), or another network entity. Here, the communication circuit may include both a communication circuit for wireless communication and a communication circuit for a wired communication. For example, the network interface 2801 may include a circuit, logic, hardware, etc., configured to exchange a control plane message or a user plane message with a UE, a BS, or other core network entities through wireless communication or wired communication. The network interface 2801 may operate using various protocols (e.g., non-access stratum (NAS) protocol). The network interface 2801 may also be referred to, for convenience of description or depending on implementation, as communication circuitry, network interface circuitry, or a communication interface circuitry.

[0390] The processor 2802 may control general operations of the network entity 2800 according to embodiments of the disclosure. The processor 2802 may be implemented by one or more integrated circuit (or circuitry) (IC) chips and may execute various data processing operations. The processor 2802 may include at least one electric circuit, and may execute instructions (or a program, codes, data, etc.) stored in the memory 2803, individually, collectively or in any combination thereof. Further, the processor 2802 may include a single-core processor or multi-core processor, and may include a processor assembly including a plurality of processing circuits (circuitry) according to a specific implementation scheme. Further, it should be noted that, according to another embodiment, in a case where NF is implemented in the form of an instance, the network function may be not necessarily configured by physical hardware.

[0391] According to an embodiment, the processor 2802 may be electrically, operatively, and / or communicatively coupled to the network interface 2801 to control the network interface 2801.

[0392] The processor 2802 may include at least one processor (or processing circuitry), and the at least one processor may perform the following operations individually, collectively or in any combination thereof. In a specific embodiment, at least a part of the processor 2802 may be included in one chip (or IC) and the other part of the processor 2802 may be included in another chip (or IC). Otherwise, at least one processor may be included in another component, for example, the network interface 2801 or the memory 2803.

[0393] The processor 2802 may perform or control or cause an operation of the network entity 2800 for executing at least one or a combination of methods according to embodiments of the disclosure. For example, the processor 2802 may control operations of the network entity 2800 for exchanging a control plane message or a user plane message with a UE, a BS, or other core network entities through wireless or wired communication, using various protocols (e.g., NAS protocol). To this end, the processor 2802 may execute a computer program, codes, or instructions stored in the memory 2803, so as to control other components of the network entity 2800 to enable execution of various operations.

[0394] The memory 2803 corresponds to a hardware storage device capable of temporarily or permanently storing information and may include one or more storage media. For example, the memory 2803 may include a memory assembly including one or more storage media. For example, the one or more storage media may include permanent memory, such as a hard drive, flash memory, or read-only memory (ROM), semipermanent memory, such as random access memory (RAM), cache memory, or a combination thereof.

[0395] The memory 2803 may be electrically, operatively, and / or communicatively coupled to the processor 2802 and may be accessed by the processor 2802.

[0396] The memory 2803 may store a computer program, codes, or instructions executable by the processor 2802. According to an embodiment, a computer program, codes, or instructions executable by the processor 2802 may be either stored in a single memory device or separated and distributedly stored in two or more memory devices. By executing the instructions stored in the memory 2803, the processor 2802 may perform various functions according to an embodiment of the disclosure.

[0397] According to an embodiment of the disclosure, operations of the network entity 2800 may be caused to be performed based on execution of instructions (or a computer program or codes) stored in the memory 2803 by at least one processor (or processing circuitry) configured to execute the same individually, collectively, or in any combination thereof, based on processing circuitry that is not configured to execute instructions, and / or based on components of processing circuitry that is not configured to execute instructions.

[0398] In one embodiment, a method performed by an electronic apparatus is provided, which comprises: obtaining a first reference signal pattern; performing channel estimation, based on Channel State Information (CSI) measured using a reference signal associated with the first reference signal pattern, wherein the first reference signal pattern is associated with a second reference signal pattern that is determined according to a plurality of sparse weight factors and at least one candidate reference signal pattern set, the plurality of sparse weight factors are obtained by training the first AI model, and each of the plurality of sparse weight factors represents a degree of importance of an spatial-domain position and / or a frequency-domain position associated with a resource of the corresponding reference signal with respect to channel estimation.

[0399] In another embodiment, a method is provided, wherein the training the first AI model comprises: determining a first loss function, according to KL divergences corresponding to mapping coefficients between inputs and outputs of a first sub-network in the first AI model and / or a channel estimation error; training the first AI model using a first training dataset, according to the first loss function, wherein the mapping coefficients in the trained first AI model are determined as the plurality of sparse weight factors.

[0400] In another embodiment, a method is provided, wherein the second reference pattern is determined according to the plurality of sparse weight factors and the at least one candidate reference signal pattern set by: performing a dimensional conversion on the plurality of sparse weight factors; selecting one candidate reference signal pattern from among each candidate reference signal pattern set by: generating a plurality of pattern-based sparse weight factors based on the plurality of sparse weight factors after the dimensional conversion and a candidate reference signal pattern set, and selecting one candidate reference signal pattern in the candidate reference signal pattern set according to the plurality of pattern-based sparse weight factors; and determining a candidate reference signal pattern satisfying a predetermined condition among the selected at least one candidate reference signal pattern as the second reference signal pattern.

[0401] In another embodiment, a method is provided, wherein each candidate reference signal pattern set is predefined, or is determined by predefined parameters for the reference signal pattern set.

[0402] In another embodiment, a method is provided, wherein the generating the plurality of pattern-based sparse weight factors based on the plurality of sparse weight factors after the dimensional conversion and the candidate reference signal pattern set comprises: for each candidate reference signal pattern in the candidate reference signal pattern set, obtaining a pattern-based sparse weight factor by: summing sparse weight factors corresponding to each transmitting antenna and each frequency-domain position on the candidate reference signal pattern, to obtain the pattern-based sparse weight factor of the candidate reference signal pattern with respect to each receiving antenna.

[0403] In another embodiment, a method is provided, wherein the selecting one candidate reference signal pattern in the candidate reference signal pattern set according to the plurality of pattern-based sparse weight factors comprises:determining a largest pattern-based sparse weight factor from among the plurality of pattern-based sparse weight factors; selecting one candidate reference signal pattern corresponding to the largest pattern-based sparse weight factor from among the candidate reference signal pattern set.

[0404] In another embodiment, a method is provided, wherein the selecting one candidate reference signal pattern in the candidate reference signal pattern set according to the plurality of pattern-based sparse weight factors comprises: by summing or averaging weight factors corresponding to the respective candidate reference signal patterns on different receiving antennas in the plurality of pattern-based sparse weight factors, obtaining weight sums or weight averages corresponding to the respective candidate reference signal patterns; selecting one candidate reference signal pattern corresponding to the largest of the weight sums or the weight averages from among the candidate reference signal pattern set.

[0405] In another embodiment, a method is provided, wherein, when the electronic apparatus is a base station, the performing the channel estimation based on the Channel State Information (CSI) measured using the reference signal associated with the first reference signal pattern comprises: transmitting, to a user equipment(UE), information associated with the first reference signal pattern and / or Channel State Information (CSI) feedback configuration, wherein the first reference signal pattern is the second reference signal pattern or is determined by the base station according to the second reference signal pattern; transmitting, to the UE, the reference signal based on the first reference signal pattern; receiving, from the UE, the CSI measured using the reference signal; performing the channel estimation through a second AI model, according to the CSI.

[0406] In another embodiment, a method is provided, wherein, when the electronic apparatus is a user equipment(UE), the performing the channel estimation based on the Channel State Information (CSI) measured using the reference signal associated with the first reference signal pattern comprises: transmitting, to a base station, information associated with the second reference signal pattern; receiving, from the base station, information associated with the first reference signal pattern; receiving, from the base station, the reference signal corresponding to the first reference signal pattern; performing the channel estimation through a second AI model, according to the CSI measured using the reference signal, wherein the first reference signal pattern is the second reference signal pattern or is determined by the base station according to the second reference signal pattern.

[0407] In another embodiment, a method is provided, wherein the transmitting, to the base station, the information associated with the second reference signal pattern comprises: sorting reference signals in the second reference signal pattern according to importance of the reference signals in the second reference signal pattern, wherein the importance is determined at least according to values of sparse weight factors; transmitting, to the base station, information about the top G reference signals with highest importance in the second reference signal pattern, wherein G is an integer greater than or equal to 1 and is configured by the base station via RRC signaling, MAC CE signaling, or DCI signaling.

[0408] In another embodiment, a method is provided, wherein the second AI model is trained by: generating a second training dataset from a first training dataset used in training the first AI model, according to the second reference signal pattern; training the second AI model using the second training dataset.

[0409] In another embodiment, a method is provided, wherein the plurality of sparse weight factors are obtained by training the first AI model using a compressed channel matrix, wherein the compressed channel matrix is obtained by compressing a channel matrix of the UE.

[0410] In another embodiment, a method is provided, wherein the compressed channel matrix is obtained by compressing the channel matrix of the UE by: obtaining a time-invariant frequency-domain channel feature based on the channel matrix of the UE; based on the time-invariant frequency-domain channel feature, obtaining a time-invariant sparse frequency-domain channel feature, with minimizing an error power of a sparse frequency-domain channel feature; obtaining the compressed channel matrix based on the time-invariant sparse frequency-domain channel feature.

[0411] In another embodiment, a method is provided, which further comprise: recovering a channel matrix that is obtained by the channel estimation through the second AI model to a channel matrix corresponding to full spatial-domain positions and full frequency-domain positions, by using the time-invariant frequency-domain channel feature and the time-invariant sparse frequency-domain channel feature.

[0412] In another embodiment, a method is provided, wherein the first reference signal pattern is obtained by the base station by: calculating a channel feature of each UE, wherein the channel feature comprises at least one of position information, Reference Signal Received Power (RSRP), Line-of-Sight (LOS) / Non-Line-of-Sight (NLOS) state information, Doppler delay, and a direction angle; grouping UEs according to the calculated channel feature; determining a first reference signal pattern for UEs belonging to the same group of UEs, according to the second reference signal pattern.

[0413] In another embodiment, a method is provided, which further comprise: when a reference signal pattern update request is received from a first UE in a first group of UEs, when the base station detects a degradation in transmission performance with respect to the first UE, when a Normalized Mean Square Error (NMSE) of channel information estimated by the second AI model and channel information measured using a monitoring reference signal received from the first UE is greater than a first threshold, or when a Cosine Similarity (SGCS) of channel information measured using Sounding Reference Signal (SRS) received from the first UE and the channel information estimated by the second AI model is less than a second threshold, re-determining a reference signal pattern to be indicated to the first UE.

[0414] In another embodiment, a method is provided, wherein the re-determining the reference signal pattern to be indicated to the first UE comprises: when a channel feature of the first UE is similar to a channel feature of another group of UEs, grouping the first UE to the other group of UEs, and determining a reference signal pattern for the other group of UEs as the reference signal pattern to be indicated to the first UE; when the channel feature of the first UE is not similar to a channel feature of any group of UEs, for the first UE, determining a plurality of new sparse weight factors by training the first AI model, and re-determining the reference signal pattern to be indicated to the first UE according to the plurality of new sparse weight factors and at least one candidate reference signal pattern set.

[0415] In another embodiment, a method is provided, wherein the first reference signal pattern is determined by the base station according to the second reference signal pattern by: grouping the UE, by the base station, according to similarities between the second reference signal pattern and reference signal patterns of other UEs, and determining the first reference signal pattern for one group of UEs to which the UE belongs.

[0416] In one embodiment, a method performed by an electronic apparatus is provided, which comprises: transmitting, to a UE, information associated with a first reference signal pattern and / or CSI feedback configuration via DCI signaling, MAC CE signaling, or RRC signaling, wherein the information associated with the first reference signal pattern is transmitted to the UE by: including, in the DCI signaling, the MAC CE signaling, or the RRC signaling, at least one of information for indicating a spatial-domain and / or frequency-domain associated with the first reference signal pattern, information for indicating one of at least one predefined reference signal patterns, or information for indicating one of the at least one predefined reference signal patterns and information associated with an offset of the first reference signal pattern; or including, in the DCI signaling, the MAC CE signaling, or the RRC signaling, information indicating a resource for transmitting a reference signal, wherein there is a mapping relationship between the resource for transmitting the reference signal and the first reference signal pattern.

[0417] In one embodiment, an electronic apparatus is provided, which comprises: at least one transceiver; at least one processor communicatively coupled to the at least one transceiver; and at least one memory, communicatively coupled to the at least one processor, storing instructions executable by the at least one processor individually or in any combination to cause the electronic apparatus to: obtain a first reference signal pattern and perform channel estimation, based on Channel State Information (CSI) measured using a reference signal associated with the first reference signal pattern, wherein the first reference signal pattern is associated with a second reference signal pattern that is determined according to a plurality of sparse weight factors and at least one candidate reference signal pattern set, the plurality of sparse weight factors are obtained by training the first AI model, and each of the plurality of sparse weight factors represents a degree of importance of an spatial-domain position and / or a frequency-domain position associated with a resource of the corresponding reference signal with respect to channel estimation.

[0418] In addition, according to an embodiment of the present application, there is provided an electronic apparatus, which includes: at least one processor; and at least one memory storing computer executable instructions, wherein the computer executable instructions, when executed by the at least one processor, cause the at least one processor to perform the method as described above.

[0419] As an example, the electronic apparatus may be a PC computer, a tablet device, a personal digital assistant, a smartphone, or other devices capable of executing a set of instructions described above. Here, the electronic apparatus does not have to be a single electronic apparatus, but can also be any collection of devices or circuits capable of executing the above instructions (or the set of instructions) individually or jointly. The electronic apparatus may also be part of an integrated control system or system manager, or a portable electronic apparatus that may be configured to be interconnected with an interface locally or remotely (e.g., via wireless transmission).

[0420] In the electronic apparatus, the processor may include a central processing unit (CPU), a graphics processing unit (GPU), a programmable logic device, a dedicated processor system, a microcontroller, or a microprocessor. By way of example and not limitation, the processor may also include an analog processor, a digital processor, a microprocessor, a multi-core processor, a processor array, a network processor, and the like.

[0421] The processor may execute instructions or codes stored in the memory, wherein the memory may also store data. The instructions and data may also be transmitted and received through a network via a network interface device, wherein the network interface device may use any known transmission protocol.

[0422] The memory may be integrated with the processor as a whole, for example, RAM or a flash memory is arranged in an integrated circuit microprocessor or the like. In addition, the memory may include an independent device, such as an external disk drive, a storage array, or other storage device that may be used by any database system. The memory and the processor may be operatively coupled, or may communicate with each other, for example, through an I / O port, a network connection, or the like, so that the processor may read files stored in the memory.

[0423] In addition, the electronic apparatus may also include a video display (such as a liquid crystal display) and a user interaction interface (such as a keyboard, a mouse, a touch input device, etc.). All components of the electronic apparatus may be connected to each other via a bus and / or a network.

[0424] According to an embodiment of the present application, there may also be provided a computer-readable storage medium storing instructions, wherein the instructions, when being executed by at least one processor, cause the at least one processor to execute the above method performed by the electronic apparatus according to the exemplary embodiment of the present application. Examples of the computer-readable storage medium here include: Read Only Memory (ROM), Random Access Programmable Read Only Memory (PROM), Electrically Erasable Programmable Read Only Memory (EEPROM), Random Access Memory (RAM) , Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), flash memory, non-volatile memory, CD-ROM, CD-R, CD+R, CD-RW, CD+RW, DVD-ROM , DVD-R, DVD+R, DVD-RW, DVD+RW, DVD-RAM, BD-ROM, BD-R, BD-R LTH, BD-RE, Blu-ray or optical disc storage, Hard Disk Drive (HDD), Solid State Drive (SSD), card storage (such as multimedia card, secure digital (SD) card or extremely fast digital (XD) card), magnetic tape, floppy disk, magneto-optical data storage device, optical data storage device, hard disk, solid state disk and any other devices which are configured to store computer programs and any associated data, data files, and data structures in a non-transitory manner, and provide the computer programs and any associated data, data files, and data structures to the processor or the computer, so that the processor or the computer may execute the computer programs. The instructions and the computer programs in the above computer-readable storage mediums may run in an environment deployed in computer equipment such as a client, a host, an agent device, a server, etc. In addition, in one example, the computer programs and any associated data, data files and data structures are distributed on networked computer systems, so that computer programs and any associated data, data files, and data structures are stored, accessed, and executed in a distributed manner through one or more processors or computers.

[0425] It should be noted that the terms "first", "second", "third", "fourth", "1", "2" and the like (if exists) in the description and claims of the present application and the above drawings are used to distinguish similar objects, and need not be used to describe a specific order or sequence. It should be understood that data used as such may be interchanged in appropriate situations, so that the embodiments of the present application described here may be implemented in an order other than the illustration or text description.

[0426] It should be understood that although each operation step is indicated by arrows in the flowcharts of the embodiments of the present application, an implementation order of these steps is not limited to an order indicated by the arrows. Unless explicitly stated herein, in some implementation scenarios of the embodiments of the present application, the implementation steps in the flowcharts may be executed in other orders according to requirements. In addition, some or all of the steps in each flowchart may include a plurality of sub steps or stages, based on an actual implementation scenario. Some or all of these sub steps or stages may be executed at the same time, and each sub step or stage in these sub steps or stages may also be executed at different times. In scenarios with different execution times, an execution order of these sub steps or stages may be flexibly configured according to requirements, which is not limited by the embodiment of the present application.

[0427] Meanwhile, although specific embodiments of the present disclosure have been described in detail, various modifications may be made without departing from the scope of the present disclosure. Therefore, the scope of the present disclosure should not be limited to the described embodiments, but should be defined by the claims and equivalents thereof.

Claims

1.A method performed by an electronic apparatus, comprising:obtaining a first reference signal pattern;performing channel estimation, based on Channel State Information (CSI) measured using a reference signal associated with the first reference signal pattern,wherein the first reference signal pattern is associated with a second reference signal pattern that is determined according to a plurality of sparse weight factors and at least one candidate reference signal pattern set, the plurality of sparse weight factors are obtained by training the first AI model, and each of the plurality of sparse weight factors represents　a degree of importance of an spatial-domain position and / or a frequency-domain position associated with a resource of the corresponding reference signal with respect to channel estimation.2.The method according to claim 1, wherein the training the first AI model comprises:determining a first loss function, according to KL divergences corresponding to mapping coefficients between inputs and outputs of a first sub-network in the first AI model and / or a channel estimation error;training the first AI model using a first training dataset, according to the first loss function,wherein the mapping coefficients in the trained first AI model are determined as the plurality of sparse weight factors.3.The method according to claim 1, wherein the second reference pattern is determined according to the plurality of sparse weight factors and the at least one candidate reference signal pattern set by:performing a dimensional conversion on the plurality of sparse weight factors;selecting one candidate reference signal pattern from among each candidate reference signal pattern set by: generating a plurality of pattern-based sparse weight factors based on the plurality of sparse weight factors after the dimensional conversion and a candidate reference signal pattern set, and selecting one candidate reference signal pattern in the candidate reference signal pattern set according to the plurality of pattern-based sparse weight factors; anddetermining a candidate reference signal pattern satisfying a predetermined condition among the selected at least one candidate reference signal pattern as the second reference signal pattern.4.The method according to claim 1, wherein each candidate reference signal pattern set is predefined, or is determined by predefined parameters for the reference signal pattern set.5.The method according to claim 3, wherein the generating the plurality of pattern-based sparse weight factors based on the plurality of sparse weight factors after the dimensional conversion and the candidate reference signal pattern set comprises:for each candidate reference signal pattern in the candidate reference signal pattern set, obtaining a pattern-based sparse weight factor by: summing sparse weight factors corresponding to each transmitting antenna and each frequency-domain position on the candidate reference signal pattern, to obtain the pattern-based sparse weight factor of the candidate reference signal pattern with respect to each receiving antenna.6.The method according to claim 3, wherein the selecting one candidate reference signal pattern in the candidate reference signal pattern set according to the plurality of pattern-based sparse weight factors comprises:determining a largest pattern-based sparse weight factor from among the plurality of pattern-based sparse weight factors;selecting one candidate reference signal pattern corresponding to the largest pattern-based sparse weight factor from among the candidate reference signal pattern set.7.The method according to claim 3, wherein the selecting one candidate reference signal pattern in the candidate reference signal pattern set according to the plurality of pattern-based sparse weight factors comprises:by summing or averaging weight factors corresponding to the respective candidate reference signal patterns on different receiving antennas in the plurality of pattern-based sparse weight factors, obtaining weight sums or weight averages corresponding to the respective candidate reference signal patterns;selecting one candidate reference signal pattern corresponding to the largest of the weight sums or the weight averages from among the candidate reference signal pattern set.8.The method according to claim 1, wherein, when the electronic apparatus is a base station, the performing the channel estimation based on the Channel State Information (CSI) measured using the reference signal associated with the first reference signal pattern comprises:transmitting, to a user equipment(UE), information associated with the first reference signal pattern and / or Channel State Information (CSI) feedback configuration, wherein the first reference signal pattern is the second reference signal pattern or is determined by the base station according to the second reference signal pattern;transmitting, to the UE, the reference signal based on the first reference signal pattern;receiving, from the UE, the CSI measured using the reference signal;performing the channel estimation through a second AI model, according to the CSI.9.The method according to claim 1, wherein, when the electronic apparatus is a user equipment(UE), the performing the channel estimation based on the Channel State Information (CSI) measured using the reference signal associated with the first reference signal pattern comprises:transmitting, to a base station, information associated with the second reference signal pattern;receiving, from the base station, information associated with the first reference signal pattern;receiving, from the base station, the reference signal corresponding to the first reference signal pattern;performing the channel estimation through a second AI model, according to the CSI measured using the reference signal,wherein the first reference signal pattern is the second reference signal pattern or is determined by the base station according to the second reference signal pattern,wherein the first reference signal pattern is determined by the base station according to the second reference signal pattern by: grouping the UE, by the base station, according to similarities between the second reference signal pattern and reference signal patterns of other UEs, and determining the first reference signal pattern for one group of UEs to which the UE belongs.10.The method according to claim 9, wherein the transmitting, to the base station, the information associated with the second reference signal pattern comprises:sorting reference signals in the second reference signal pattern according to importance of the reference signals in the second reference signal pattern, wherein the importance is determined at least according to values of sparse weight factors;transmitting, to the base station, information about the top G reference signals with highest importance in the second reference signal pattern, wherein G is an integer greater than or equal to 1 and is configured by the base station via RRC signaling, MAC CE signaling, or DCI signaling.11.The method according to claim 8, wherein the second AI model is trained by:generating a second training dataset from a first training dataset used in training the first AI model, according to the second reference signal pattern;training the second AI model using the second training dataset.12.The method according to claim 8, further comprising:recovering a channel matrix that is obtained by the channel estimation through the second AI model to a channel matrix corresponding to full spatial-domain positions and full frequency-domain positions, by using the time-invariant frequency-domain channel feature and the time-invariant sparse frequency-domain channel feature,wherein the plurality of sparse weight factors are obtained by training the first AI model using a compressed channel matrix, wherein the compressed channel matrix is obtained by compressing a channel matrix of the UE,wherein the compressed channel matrix is obtained by compressing the channel matrix of the UE by:obtaining a time-invariant frequency-domain channel feature based on the channel matrix of the UE;based on the time-invariant frequency-domain channel feature, obtaining a time-invariant sparse frequency-domain channel feature, with minimizing an error power of a sparse frequency-domain channel feature;obtaining the compressed channel matrix based on the time-invariant sparse frequency-domain channel feature.13.The method according to claim 8, further comprising:when a reference signal pattern update request is received from a first UE in a first group of UEs, when the base station detects a degradation in transmission performance with respect to the first UE, when a Normalized Mean Square Error (NMSE) of channel information estimated by the second AI model and channel information measured using a monitoring reference signal received from the first UE is greater than a first threshold, or when a Cosine Similarity (SGCS) of channel information measured using Sounding Reference Signal (SRS) received from the first UE and the channel information estimated by the second AI model is less than a second threshold, re-determining a reference signal pattern to be indicated to the first UE,wherein the first reference signal pattern is obtained by the base station by:calculating a channel feature of each UE, wherein the channel feature comprises at least one of position information, Reference Signal Received Power (RSRP), Line-of-Sight (LOS) / Non-Line-of-Sight (NLOS) state information, Doppler delay, and a direction angle;grouping UEs according to the calculated channel feature;determining a first reference signal pattern for UEs belonging to the same group of UEs, according to the second reference signal pattern,wherein the re-determining the reference signal pattern to be indicated to the first UE comprises:when a channel feature of the first UE is similar to a channel feature of another group of UEs, grouping the first UE to the other group of UEs, and determining a reference signal pattern for the other group of UEs as the reference signal pattern to be indicated to the first UE;when the channel feature of the first UE is not similar to a channel feature of any group of UEs, for the first UE, determining a plurality of new sparse weight factors by training the first AI model, and re-determining the reference signal pattern to be indicated to the first UE according to the plurality of new sparse weight factors and at least one candidate reference signal pattern set.14.A method performed by an electronic apparatus, comprising:transmitting, to a UE, information associated with a first reference signal pattern and / or CSI feedback configuration via DCI signaling, MAC CE signaling, or RRC signaling,wherein the information associated with the first reference signal pattern is transmitted to the UE by:including, in the DCI signaling, the MAC CE signaling, or the RRC signaling, at least one of information for indicating a spatial-domain and / or frequency-domain associated with the first reference signal pattern, information for indicating one of at least one predefined reference signal patterns, or information for indicating one of the at least one predefined reference signal patterns and information associated with an offset of the first reference signal pattern; orincluding, in the DCI signaling, the MAC CE signaling, or the RRC signaling, information indicating a resource for transmitting a reference signal, wherein there is a mapping relationship between the resource for transmitting the reference signal and the first reference signal pattern.15.An electronic apparatus comprising:at least one transceiver;at least one processor communicatively coupled to the at least one transceiver; andat least one memory, communicatively coupled to the at least one processor, storing instructions executable by the at least one processor individually or in any combination to cause the electronic apparatus to: obtain a first reference signal pattern,perform channel estimation, based on Channel State Information (CSI) measured using a reference signal associated with the first reference signal pattern,wherein the first reference signal pattern is associated with a second reference signal pattern that is determined according to a plurality of sparse weight factors and at least one candidate reference signal pattern set, the plurality of sparse weight factors are obtained by training the first AI model, and each of the plurality of sparse weight factors represents a degree of importance of an spatial-domain position and / or a frequency-domain position associated with a resource of the corresponding reference signal with respect to channel estimation.

Images