Method and apparatus for transmitting and receiving uplink signal

Abstract

The disclosure relates to a 5G or 6G communication system for supporting a higher data transmission rate. The present disclosure relates to a method and an apparatus of transmitting and receiving an uplink signal. In one aspect, there is provided a method performed by a user equipment (UE) in a communication system, including: determining a first processing method of a plurality of methods of obtaining complex-valued information associated with channel state information (CSI), wherein the plurality of methods comprises: a first method of obtaining complex-valued information based on a bit sequence, wherein the bit sequence is obtained through a process of bit sequence generation and channel coding on CSI, and, a second method of obtaining complex-valued information based on CSI, wherein the CSI is not subjected to bit sequence generation and channel coding; processing CSI based on the first processing method to obtain complex-valued information associated with the CSI; transmitting an uplink channel or signal based on the complex-valued information.

Description

METHOD AND APPARATUS FOR TRANSMITTING AND RECEIVING UPLINK SIGNAL

[0001] The present application relates to the technical field of wireless communication, and more particularly, to a method and apparatus for transmitting and receiving uplink signals in a wireless communication network.

[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 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. 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 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 band (for example, 95GHz 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 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.

[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] 5th generation (5G) or new radio (NR) mobile communications is recently gathering increased momentum with all the worldwide technical activities on the various candidate technologies from industry and academia. The candidate enablers for the 5G / NR mobile communications include massive antenna technologies, from legacy cellular frequency bands up to high frequencies, to provide beamforming gain and support increased capacity, new waveform (e.g., a new radio access technology (RAT)) to flexibly accommodate various services / applications with different requirements, new multiple access schemes to support massive connections, and so on.

[0008] 5G mobile communication technologies define broad frequency bands such that high transmission rates and new services are possible, and can be implemented not only in “Sub 6GHz” bands such as 3.5GHz, but also in “Above 6GHz” bands referred to as mmWave including 28GHz and 39GHz. In addition, it has been considered to implement 6G mobile communication technologies (referred to as Beyond 5G systems) in terahertz bands (for example, 95GHz to 3THz bands) in order to accomplish transmission rates fifty times faster than 5G mobile communication technologies and ultra-low latencies one-tenth of 5G mobile communication technologies.

[0009] At the beginning of the development of 5G mobile communication technologies, in order to support services and to satisfy performance requirements in connection with enhanced Mobile BroadBand (eMBB), Ultra Reliable Low Latency Communications (URLLC), and massive Machine-Type Communications (mMTC), there has been ongoing standardization regarding beamforming and massive MIMO for mitigating radio-wave path loss and increasing radio-wave transmission distances in mmWave, supporting numerologies (for example, operating multiple subcarrier spacings) for efficiently utilizing mmWave resources and dynamic operation of slot formats, initial access technologies for supporting multi-beam transmission and broadbands, definition and operation of BWP (BandWidth Part), new channel coding methods such as a LDPC (Low Density Parity Check) code for large amount of data transmission and a polar code for highly reliable transmission of control information, L2 pre-processing, and network slicing for providing a dedicated network specialized to a specific service.

[0010] Currently, there are ongoing discussions regarding improvement and performance enhancement of initial 5G mobile communication technologies in view of services to be supported by 5G mobile communication technologies, and there has been physical layer standardization regarding technologies such as V2X (Vehicle-to-everything) for aiding driving determination by autonomous vehicles based on information regarding positions and states of vehicles transmitted by the vehicles and for enhancing user convenience, NR-U (New Radio Unlicensed) aimed at system operations conforming to various regulation-related requirements in unlicensed bands, NR UE Power Saving, Non-Terrestrial Network (NTN) which is UE-satellite direct communication for providing coverage in an area in which communication with terrestrial networks is unavailable, and positioning.

[0011] Moreover, there has been ongoing standardization in air interface architecture / protocol regarding technologies such as Industrial Internet of Things (IIoT) for supporting new services through interworking and convergence with other industries, IAB (Integrated Access and Backhaul) for providing a node for network service area expansion by supporting a wireless backhaul link and an access link in an integrated manner, mobility enhancement including conditional handover and DAPS (Dual Active Protocol Stack) handover, and two-step random access for simplifying random access procedures (2-step RACH for NR). There also has been ongoing standardization in system architecture / service regarding a 5G baseline architecture (for example, service based architecture or service based interface) for combining Network Functions Virtualization (NFV) and Software-Defined Networking (SDN) technologies, and Mobile Edge Computing (MEC) for receiving services based on UE positions.

[0012] As 5G mobile communication systems are commercialized, connected devices that have been exponentially increasing will be connected to communication networks, and it is accordingly expected that enhanced functions and performances of 5G mobile communication systems and integrated operations of connected devices will be necessary. To this end, new research is scheduled in connection with eXtended Reality (XR) for efficiently supporting AR (Augmented Reality), VR (Virtual Reality), MR (Mixed Reality) and the like, 5G performance improvement and complexity reduction by utilizing Artificial Intelligence (AI) and Machine Learning (ML), AI service support, metaverse service support, and drone communication.

[0013] A method performed by a user equipment (UE) in a communication system, comprising: determining a first processing method of a plurality of methods of obtaining complex-valued information associated with channel state information (CSI), wherein the plurality of methods comprises: a first method of obtaining complex-valued information based on a bit sequence, wherein the bit sequence is obtained through a process of bit sequence generation and channel coding on CSI, and, a second method of obtaining complex-valued information based on CSI, wherein the CSI is not subjected to bit sequence generation and channel coding; processing CSI based on the first processing method to obtain complex-valued information associated with the CSI; transmitting an uplink channel or signal based on the complex-valued information.

[0014] A method performed by a base station in a communication system, comprising: transmitting, to a UE, high layer signaling including first information, the first information including at least one of: related information of a first processing method, information of at least one set of parameters associated with a second method; transmit, to the UE, physical layer signaling including second information of one set of parameters of the at least one set of parameters, wherein the first processing method is one of a plurality of methods of obtaining complex-valued information associated with CSI, wherein the plurality of methods comprises: a first method of obtaining complex-valued information based on a bit sequence, wherein the bit sequence is obtained through a process of bit sequence generation and channel coding on CSI, and, a second method of obtaining complex-valued information based on CSI, wherein the CSI is not subjected to bit sequence generation and channel coding.

[0015] FIG. 1 illustrates an example wireless network according to embodiments of the present disclosure;

[0016] FIG. 2 illustrates an example base station according to embodiments of the present disclosure;

[0017] FIG. 3 illustrates an example user equipment according to embodiments of the present disclosure;

[0018] FIG. 4 illustrates a diagram of a method for reporting uplink control information by a UE in a communication system according to at least one embodiment of the present disclosure;

[0019] FIG. 5 illustrates a schematic diagram of determining a method and a scheme of obtaining complex-valued information characterizing CSI by a UE using first and second configuration information in a communication system according to the present disclosure;

[0020] FIG. 6 illustrates a schematic diagram in which a UE side derives complex-valued information based on a bit sequence of CSI and CSI reconstruction at a base station side in a communication system according to the present disclosure;

[0021] FIG. 7 shows a schematic diagram of a neural network model used by a first method of training in a communication system according to the present disclosure;

[0022] FIG. 8 shows a schematic diagram of a neural network structure for acquisition of a bit sequence carrying CSI eigenvectors at a UE side and CSI reconstruction at a base station side in a communication system according to the present disclosure;

[0023] FIG. 9 illustrates a schematic diagram of a method for a UE to obtain complex-valued information using a neural network in a communication system according to the present disclosure;

[0024] FIG. 10 illustrates a schematic diagram of an autoencoder including a neural network model for acquiring complex-valued information of CSI in a communication system according to the present disclosure;

[0025] FIG. 11 illustrates a schematic diagram of acquisition of complex-valued information of CSI at UE side and CSI reconstruction at a base station side in a communication system according to the present disclosure;

[0026] FIG. 12 shows a schematic diagram of a neural network structure for acquisition of complex-valued information of CSI at UE side and CSI reconstruction at a base station side in a communication system according to the present disclosure;

[0027] FIG. 13 illustrates a schematic diagram of training an autoencoder in accordance with the present disclosure;

[0028] FIG. 14 illustrates a schematic diagram of a UE multiplexing the uplink channel or signal to carry complex-valued information of second uplink control information in a communication system according to the present disclosure;

[0029] FIG. 15 illustrates a schematic diagram of a circular buffer for rate matching in a communication system according to the present disclosure;

[0030] FIG. 16 illustrates a schematic diagram of a user mapping complex symbols in complex-valued information with time-frequency resource units indicated by configuration in a communication system according to the present disclosure;

[0031] FIG. 17 illustrates a schematic diagram of time-frequency resource unit mapping of pilot-related complex-valued symbols by users in a communication system according to the present disclosure;

[0032] FIG. 18 illustrates a schematic diagram of a user in a communication system obtaining complex-valued information including pilots associated with time-frequency resources according to a method of time-division multiplexing according to the present disclosure;

[0033] FIG. 19 illustrates a schematic diagram of a user in a communication system obtaining complex-valued information including pilots associated with time-frequency resources according to a method of frequency division multiplexing according to the present disclosure;

[0034] FIG. 20 illustrates a schematic diagram of an example of method for a user reporting CSI in a communication system according to the present disclosure;

[0035] FIG. 21 illustrates a diagram of a method of obtaining complex-valued information related to uplink control information by a UE in a communication system according to the present disclosure;

[0036] FIG. 22 illustrates a schematic diagram of an identification table including N neural network models in a communication system according to the present disclosure;

[0037] FIG. 23 illustrates a schematic diagram of an information table in which a UE determines two information tables of methods of obtaining complex values according to first configuration information in a communication system according to the present disclosure;

[0038] FIG. 24 illustrates a schematic diagram in which a UE in a communication system determines an information table including two methods according to an indication of first configuration information according to the present disclosure;

[0039] FIG. 25 illustrates a PUCCH procedure according to at least one embodiment of the present disclosure;

[0040] FIG. 26 illustrates a method of training a JSCM model for implementation according to at least one embodiment of the present disclosure.

[0041] FIG. 27 illustrates a block diagram of a UE in accordance with at least one embodiment of the present disclosure;

[0042] FIG. 28 is a block diagram illustrating a base station in accordance with at least one embodiment of the present disclosure.

[0043] At least one embodiment of the present disclosure provides a method performed by a user equipment (UE) in a communication system, comprising:

[0044] determining a first processing method of a plurality of methods of obtaining complex-valued information associated with channel state information (CSI), wherein the plurality of methods comprises:

[0045] a first method of obtaining complex-valued information based on a bit sequence, wherein the bit sequence is obtained through a process of bit sequence generation and channel coding on CSI, and,

[0046] a second method of obtaining complex-valued information based on CSI, wherein the CSI is not subjected to bit sequence generation and channel coding;

[0047] processing CSI based on the first processing method to obtain complex-valued information associated with CSI;

[0048] transmitting an uplink channel or signal based on the complex-valued information.

[0049] In an implementation, transmitting the uplink channel or signal based on the complex-valued information comprises:

[0050] mapping and transmitting the complex-valued information onto an uplink channel or signal.

[0051] In an implementation, the method further includes receiving higher layer signaling including first information, the first information includes at least one of:

[0052] information related to the first processing method;

[0053] information of at least one set of parameters associated with the second method;

[0054] the method further includes receiving physical layer signaling including second information of one of the at least one set of parameters.

[0055] In an implementation, the first information comprises at least one of an index, a name, a table of at least one set of parameters associated with the second method.

[0056] In an implementation, the second information comprises information associated with at least one of an index, a name, a modulation order, a signal-to-noise ratio (SNR), a signal-to-interference-plus-noise ratio (SINR), an SINR section, an SINR upper bound, an SINR lower bound, an output type, an output length, an output format corresponding to the one set of parameters.

[0057] In an implementation, the second method comprises a method based on a neural network model, the method further comprises determining a set of parameters of the neural network based on the second information, wherein the set of parameters comprises at least one of a type of the model, a structure of the model, a number of layers of the model, a number of neurons of the model, an activation function of the model, an input length equal to a number of elements in the channel state information, an output format of the model, weights of the model.

[0058] In an implementation, the output format of the model further comprises at least one of: data format of the output, data structure of the output, a number of output elements, priority of the output elements, indexes of the output elements.

[0059] In an implementation, the method further comprises: before the UE maps the complex-valued information associated with the CSI onto an uplink channel or signal, the UE multiplexes the uplink channel or signal to carry the complex-valued information associated with the second uplink control information;

[0060] wherein the method of multiplexing comprises combining and mapping the complex-valued information associated with the CSI and the complex-valued information associated with the second uplink control information onto an uplink channel or signal;

[0061] wherein the complex-valued information associated with the second uplink control information may be obtained by one of the following methods:

[0062] a third method of obtaining complex-valued information based on a bit sequence obtained by performing bit sequence generation and channel coding on a second uplink control information, and a fourth method of obtaining complex-valued information based on a second uplink control information, wherein the second uplink control information is not subjected to bit sequence generation and channel coding.

[0063] In an implementation, the method further comprises: before the UE maps the complex-valued information associated with the CSI onto an uplink channel or signal, the UE obtains matched complex-valued information based on the complex-valued information and the number of time-frequency resource units associated with reporting the CSI, wherein the number of complex-valued symbols included in the matched complex-valued information is the same as the number of time-frequency resource units associated with reporting the CSI.

[0064] In an implementation, the obtaining of the matched complex-valued information may further include the UE matching output elements of the neural network model with time-frequency resource units associated with reporting CSI in order of priority from large to small in order according to the priorities of the output elements, to obtain a matched sequence of complex-valued symbols with priority.

[0065] In an implementation, the obtaining of the matched complex-valued information may further include the UE matching, according to indexes of output elements of the neural network model, the output elements with the time-frequency resource units associated with reporting CSI in order of the indexes, to obtain a sequence of matched complex-valued symbols related to the indexes.

[0066] In an implementation, the method further includes determining the first processing method of a plurality of methods of obtaining complex-valued information associated with the CSI based on the content and / or format of the uplink control information.

[0067] In an implementation, the method further includes the UE reporting capability of the UE to the base station, the capability of the UE includes at least one of:

[0068] a first capability representing the UE has a capability of the first method;

[0069] a second capability representing the UE has a capability of the second method;

[0070] a third capability representing the UE has a capability of the first method and the second method.

[0071] At least one embodiment of the present disclosure provides a method performed by a base station in a communication system, comprising:

[0072] transmitting, to a UE, high layer signaling including first information, the first information including at least one of: related information of a first processing method, information of at least one set of parameters associated with a second method;

[0073] transmit, to a UE, physical layer signaling including second information of one of the at least one set of parameters,

[0074] wherein the first processing method is one of a plurality of methods of obtaining complex-valued information associated with CSI, wherein the plurality of methods comprises:

[0075] a first method of obtaining complex-valued information based on a bit sequence, wherein the bit sequence is obtained through a process of bit sequence generation and channel coding on CSI, and,

[0076] a second method of obtaining complex-valued information based on CSI, wherein the CSI is not subjected to bit sequence generation and channel coding.

[0077] In an implementation, the second information comprises information associated with at least one of an index, a name, a modulation order, a SNR, an SINR, an SINR section, an SINR upper bound, an SINR lower bound, an output type, an output length, an output format corresponding to the one set of parameters.

[0078] In an implementation, the second method comprises a method based on a neural network model, the method further comprises determining a set of parameters of the neural network based on the second information, wherein the set of parameters comprises at least one of a type of the model, a structure of the model, a number of layers of the model, a number of neurons of the model, an activation function of the model, an input length equal to a number of elements in the channel state information, an output format of the model, weights of the model.

[0079] In an implementation, the output format of the model further comprises at least one of: data format of the output, data structure of the output, a number of output elements, priority of the output elements, an index of the output elements.

[0080] In an implementation, the method further comprises:

[0081] receiving capability of the UE reported by the UE, the capability of the UE comprises at least one of:

[0082] a first capability representing the UE has a capability of the first method;

[0083] a second capability representing the UE has a capability of the second method;

[0084] a third capability, representing the UE has a capability of the first method and the second method.

[0085] At least one embodiment of the present disclosure provides a user equipment (UE) in a communication system, comprising:

[0086] a transceiver configured to transmit and / or receive a signal;

[0087] a controller configured to control the UE to perform the method according to at least one embodiment of the present disclosure.

[0088] At least one embodiment of the present disclosure provides a base station in a communication system, comprising:

[0089] a transceiver configured to transmit and / or receive a signal;

[0090] a controller configured to control the base station to perform a method according to at least one embodiment of the present disclosure.

[0091] 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.

[0092] 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.

[0093] 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.

[0094] 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.

[0095] FIGS. 1-28 below describe various embodiments of the present disclosure implemented in wireless communications systems. The descriptions of FIGS. 1-28 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.

[0096] 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.

[0097] 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.

[0098] 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.

[0099] 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).

[0100] 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.

[0101] 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.

[0102] 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.

[0103] 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.

[0104] 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.

[0105] 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.

[0106] 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.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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).

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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).

[0116] 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.

[0117] 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.

[0118] The processor 307 is also capable of executing other processes and programs resident in the memory 311, such as processes for channel state information (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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] Modern wireless communication systems employ three steps to achieve the reporting of uplink control information (including channel state related information, scheduling request, acknowledgement, etc.) by a user equipment (UE), including: 1) first, converting the uplink control information into bit information using bit generation methods (also referred to as source coding methods, quantization methods, etc.), which act to obtain the bit information and reduce the inherent redundancy in the uplink control information, and in turn reduce the amount of data that needs to be transmitted; 2) thereafter, channel coding (also referred to as error correction coding) is performed on the obtained bit information, which functions to implement error correction control so that, when the information is in error during the channel transmission, error correction can be performed and the data recovered; 3) finally, the channel-coded bit information is modulated to obtain complex-valued information characterizing the uplink control information (or referred to as complex information, complex-valued modulation symbols, complex-valued symbols, symbols, etc., which are used interchangeably in this disclosure), enabling transmission of the information payload on the carrier signal.

[0123] For any uplink control information, existing systems typically need to perform the three steps described above separately to achieve reporting. However, for some uplink control information (e.g., channel state related information, etc.), it is not optimal for the wireless communication system to perform the above three steps for reporting. According to some embodiments of the present disclosure, by some technical means, the system can use only one or two of the above steps to achieve the same function as performing the above three steps and achieve higher reporting performance. On the other hand, the inventor has realized that the existing system does not support switching methods with respect to the content of uplink control information, but can only be reported using the above-described three-step related process for all types of control information, and thus the performance is not high. According to some embodiments of the present disclosure, a corresponding processing method may be selected according to a type of control information to be reported, thereby achieving a function of higher reporting performance.

[0124] It should be understood that the technical problems that can be solved by the present disclosure are not limited only to the problems mentioned in the above description, but may include any technical problems that can be solved according to the substance and principle of the technical contents described throughout the present disclosure, all of which are within the scope of the present disclosure. Further, the present disclosure need not address all of the technical problems explicitly listed.

[0125] Advantageous Effects

[0126] The present disclosure provides a method for a UE to report uplink control information (e.g., channel state information (CSI)) in a communication system. According to a method of at least one embodiment of the present disclosure, efficiency and reliability of communication can be improved. The efficiency improvement of the communication may be manifested in that the method according to at least one embodiment of the present disclosure may achieve information reporting, e.g. reporting of channel state information, with the same accuracy using less communication resources than conventional methods under the same signal-to-interference-plus-noise ratio (SINR) conditions. The improved reliability of the communication may be manifested in that the method according to at least one embodiment of the present disclosure may achieve higher accuracy of information reporting, such as channel state information reporting, by utilizing the same communication resources under the same SINR conditions than the conventional method. Further, in some aspects, according to a method according to at least one embodiment of the present disclosure, a corresponding processing method may be selected according to the type of control information to be reported to obtain complex-valued information characterizing the control information to transmit, thereby further improving performance.

[0127] Embodiments of the present disclosure will be described in more detail below in conjunction with examples.

[0128] Embodiment 1

[0129] FIG. 4 illustrates a diagram of a method 400 for reporting uplink control information by a UE in a communication system in accordance with at least one embodiment of the present disclosure. For convenience of description, in the following description, it will be mainly described with channel state information (CSI) as an example of uplink control information to be reported by the UE. It is to be understood that this description in terms of CSI as an example is merely exemplary and does not limit the type of uplink control information to which the method is applicable to only CSI, but may cover scenarios where various other types of uplink control information are reported.

[0130] As shown in FIG. 4, the method 400 comprises steps 401 to 403:

[0131] Step 401: The UE determines a first processing method among a plurality of methods of obtaining complex-valued information associated with Channel State Information (CSI), wherein the plurality of methods include:

[0132] a first method of obtaining complex-valued information based on a bit sequence, wherein the bit sequence is obtained through a process of bit sequence generation and channel coding on CSI, and,

[0133] a second method of obtaining complex-valued information based on CSI, wherein the CSI is not subjected to bit sequence generation and channel coding;

[0134] Step 402: The UE processes the CSI based on the first processing method to obtain complex-valued information associated with the CSI;

[0135] Step 403: UE performs uplink channel or signal transmission based on the complex-valued information.

[0136] According to the method of embodiments of the present disclosure, it may be determined to use different methods for processing CSI to obtain complex-valued information for transmission.

[0137] Various aspects of the present disclosure are described in more detail below.

[0138] In some examples, the "channel state information (CSI)" may comprise one of a vector, matrix, tensor comprising an estimated channel impulse response (CIR) in no less than one dimension. For example, the no less than one dimension may include at least one of time domain, frequency domain, spatial domain. Wherein the granularity of the channel impulse response per unit in the time domain dimension may include a symbol, a slot, a subframe, a frame, etc.; the granularity of the channel impulse response per unit in the frequency domain dimension may include a subcarrier, a resource block, multiple resource blocks of fixed length, a subband, a wideband, and the like; the granularity of the channel impulse response per unit in the spatial dimension may include an antenna, an antenna port, an antenna panel, a beam, and the like. The channel impulse response in the spatial dimension may include a channel impulse response associated with a UE or a channel impulse response associated with a base station. The CSI may include the channel impulse response over both spatial dimensions of the UE and the base station. Taking CSI being a tensor of channel impulse response in four dimensions including time domain, frequency domain, spatial domain of UE, spatial domain of base station as an example, granularity units of CSI in time domain, frequency domain, spatial domain of UE, spatial domain of base station are symbol, subcarrier, antenna port of UE, antenna port of base station, respectively, and number of samples of channel impulse response in time domain, frequency domain, spatial domain of UE, spatial domain of base station are T, F, RX, TX, respectively, then CSI is a tensor of dimension [T, F, RX, TX]. Dimensions of the CSI may also include [T, F, TX, RX], [T, TX, F, RX], [TX, T, F, RX], [T, RX, F, TX], [RX, T, F, TX], [F, T, RX, TX], and the like. Taking the example that the CSI is for 14 time domain symbols, 936 frequency domain subcarriers, 4 receive antenna ports, 64 transmit antenna ports, the CSI is a tensor of dimension [T, F, RX, TX] = [14, 936, 4, 64].

[0139] For example, the estimated channel impulse response may include a channel impulse response obtained based on a pilot signal. Wherein, the pilot signals may include demodulation reference signals (DMRS), sounding reference signals (SRS), channel state information reference signals (CSI-RS), and the like. Wherein, the pilot signal used to acquire the estimated channel impulse response may be configured by the base station. Wherein the method of acquiring the channel impulse response based on the pilot signal may include a channel estimation (CE) method including least squares channel estimation (LS CE), minimum mean square error channel estimation (MMSE CE), maximum likelihood estimation channel estimation (ML CE), Kalman filter estimation channel estimation (KF CE), and the like. The channel state information may also include an estimated channel impulse response vector having only one dimension, or an estimated channel impulse response tensor having no less than three dimensions. The channel state information may also be referred to as raw channel matrix, estimated raw channel matrix.

[0140] In some examples, the "channel state information (CSI)" may also include an autocorrelation matrix of the estimated channel impulse response matrix. The autocorrelation matrix may be obtained by multiplying the estimated channel impulse response matrix with a conjugate matrix of the estimated channel impulse response matrix.

[0141] In some examples, the "channel state information (CSI)" may also be channel state information after transform related to signal processing. For example, the channel state information after transform related to signal processing is obtained through transform related to signal processing of the estimated channel impulse response matrix, the transform related to signal processing may comprise one of the following methods: Fourier transform, Laplace transform, wavelet transform, Hilbert-Huang transform, bispectral transform, etc. For example, the channel state information after transform related to signal processing may include delay domain or angle domain information of the channel state obtained by Fourier transforming the estimated channel impulse response matrix.

[0142] In some examples, the "Channel State Information (CSI)" may also include a Precoding matrix including precoding weights in at least one dimension of time domain, frequency domain, space domain. For example, the precoding matrix includes not less than one eigenvector. Wherein the feature vector may comprise a representation of spatial domain or a representation of an angle-latency domain. For example, the precoding matrix may be obtained based on the estimated channel impulse response matrix by a precoding method, wherein the precoding method may include zero forcing precoding (ZF precoding), block diagonal precoding (BD precoding), minimum mean square error precoding (MMSE precoding), TH precoding (Tomlinson-Harashima precoding), codebook-based precoding, and the like. Wherein a codebook in the codebook-based precoding may be obtained by a discrete Fourier transform (DFT) matrix. For example, the channel state information may also include a precoding vector having only one dimension, or a precoding tensor having no less than three dimensions.

[0143] In some examples, the "Channel State Information (CSI)" may further include one of the following: Precoding Matrix Indication (PMI), Channel Quality Indication (CQI), CSI-RS Resource Indication (CRI), SS / PBCH Resource Block Indication (SSBRI), Layer Indication (LI), Rank Indication (RI), Reference Signal Receiving Power (RSRP), etc.

[0144] In some examples, the "complex-valued information associated with CSI" may include information characterizing or carrying CSI, including one of a sequence, a vector, a matrix, a tensor of no less than one complex-valued modulation symbols. Wherein the complex-valued modulation symbols are represented by complex values within a fixed range. Wherein the complex-valued information may include discrete or continuous complex-valued information. In particular, the complex-valued modulation symbols in the discrete complex-valued information are represented by a finite number of fixed values quantizing a range, and the complex-valued modulation symbols in the continuous complex-valued information are represented by arbitrary values within the range. For example, a complex-valued modulation symbol may be represented by two values , a method known as BPSK modulation, by which the complex-valued information formed is discrete. The complex-valued modulation symbols may be represented by any number in the range , and the complex-valued information constructed by the method is continuous.

[0145] In one approach, the method by which the UE reports the CSI is to report the precoding matrix indication. For example, the UE and the base station have the same precoding codebook in which not less than one eigenvector carrying signature is included, the base station acquires the precoding matrix by mapping the obtained precoding matrix indication to the corresponding eigenvector. In contrast to the above, the proposed method of the present invention can directly generate complex-valued information and report the raw CSI to the base station by one method. Compared to the above, the reporting method proposed by the present invention can have a finer reporting granularity, which can result in higher accuracy of the reported information, thereby improving the performance of the system. The method of directly reporting the raw CSI proposed by the present invention allows the base station to have more flexibility to select the method of precoding instead of being limited to the method provided in the codebook, and thus can have a higher performance upper limit.

[0146] In some examples, the "determining a first processing method of a plurality of methods of obtaining complex-valued information associated with Channel State Information (CSI)" includes determining, by the UE, a first processing method of a plurality of methods of obtaining complex-valued information characterizing the CSI according to indication of configuration information. In particular, the UE includes a plurality of methods and information related to each method, such as an identification. In the present disclosure, the description is made using "identification" as an example of information related to a method, scheme, or table for convenience of description, it may be understood that this is merely exemplary, and the "identification" of a method, scheme, or table may also be replaced with other information or expressions that may be used to represent, indicate, or determine the method, scheme, or table, such as "name," "type," "indication," "identifier," "index," or the like. Where the indication is an identity of one method, the UE determines the selected method by matching the indication to the identification of the plurality of methods. Wherein the identification may include an index, a name, or the like of the method. Wherein the configuration information may comprise one of higher layer signaling, MAC layer signaling, physical layer signaling, e.g. Radio Resource Control (RRC), Downlink Control Information (DCI).

[0147] In some examples, the configuration information may include an uplink shared channel configuration (also referred to as PUSCH-Config) or an uplink control channel configuration (also referred to as PUCCH-Config) in RRC. The configuration information may also include downlink control signaling (DCI).

[0148] In some examples, each of the "methods" may be implemented with no less than one scheme. Wherein said scheme represents an implementation means for the method based on a set of parameters, wherein said set of parameters needs to be determined or configured by the UE. For example, when the method is the first method, the scheme may comprise a Modulation and Coding Scheme (MCS), wherein the required set of parameters comprises a Modulation Order and a Target code Rate. For example, when the method is the second method, the set of parameters of the scheme may include parameters including at least one of: a model type, a number of model layers, a number of model neurons, a model activation function, model weights, an input format, an output format, and the like.

[0149] In some examples, the determining the first processing method further includes determining, by the UE, one of a plurality of methods of obtaining complex-valued information characterizing the CSI and the scheme for performing the method according to the indication of the configuration information. For example, the UE includes information on a plurality of methods, and includes a plurality of schemes and an identification of each scheme in each method of the UE; The indication includes a method identification and a scheme identification. After the UE determines the method according to the method identification in the indication, the UE determines the selected scheme by matching the scheme identification in the indication to the identification of the various schemes contained by the UE. Wherein the scheme identification may include an index, a name, a feature, or the like of the scheme.

[0150] FIG. 5 illustrates a schematic diagram of determining a method and a scheme of obtaining complex-valued information characterizing CSI by a UE using first and second configuration information in a communication system according to the present disclosure.

[0151] In some examples, the determining the first processing method further includes determining, by the UE, one of a plurality of methods of obtaining complex-valued information characterizing the CSI according to an indication of first configuration information, and determining, by the UE, a scheme for performing the method according to an indication of second configuration information. For example, the UE determines, according to the method identification indicated by the radio resource control information, that the method of obtaining the complex-valued information characterizing the CSI is the second method; Thereafter, the UE determines a scheme for performing the method based on the scheme identification indicated by the downlink control information, wherein the scheme is a neural network model and includes the following parameters: model type, number of model layers, number of model neurons, model activation function, model weights, input format, output format.

[0152] In some examples, the first method may include the UE obtaining a bit sequence related to uplink control information by bit sequence generation of the uplink control information; The UE performs segmentation of the bit sequence and adds parity to each bit sequence block, obtaining bits after CRC attachment; The UE performs channel coding on the bits after CRC attachment to obtain a channel-coded bit sequence; The UE modulates the channel-coded bit sequence according to the configured modulation order to obtain complex-valued information comprising no less than one complex-valued modulation symbol.

[0153] In some examples, the first method may further include the UE obtaining a bit sequence related to uplink control information by bit sequence generation of uplink control information; The UE performs segmentation of the bit sequence and adds parity to each bit sequence block, obtaining bits after CRC attachment; The UE performs bit-interleaving of the bits after CRC attachment, obtaining an interleaved bit sequence; The UE performs channel-coding on the interleaved bit sequence according to a polarization sequence to obtain a channel-coded bit sequence; The UE modulates the channel-coded bit sequence according to the configured modulation order to obtain complex-valued information comprising no less than one complex-valued modulation symbol.

[0154] In some examples, the first method may include the UE obtaining a bit sequence related to uplink control information by bit sequence generation of uplink control information; The UE adds parity at the end of the bit sequence, obtaining bits after CRC attachment; The UE performs segmentation of the bits after CRC attachment and optionally adds an additional sequence of CRC at the end of each bit sequence block; The UE performs channel-coding on the segmented bit sequence block according to pattern based on low density parity check to obtain a channel-coded bit sequence; The UE modulates the channel-coded bit sequence according to the configured modulation order to obtain complex-valued information comprising no less than one complex-valued modulation symbol. In some examples, the first method may further include the UE obtaining the channel-coded bit sequence through a neural network model; The UE modulates the channel-coded bit sequence according to the configured modulation order to obtain complex-valued information comprising no less than one complex-valued modulation symbol. Wherein the method in which the UE obtains the channel-coded bit sequence through a neural network model may include: the UE inputting CSI into a neural network model to obtain an output; The UE inputs the output of the neural network model into a quantizer to obtain a channel-coded bit sequence. Wherein the neural network model of the UE may comprise an encoder part of an autoencoder.

[0155] FIG. 6 illustrates a schematic diagram in which a UE side derives complex-valued information based on a bit sequence of CSI and CSI reconstruction at a base station side in a communication system according to the present disclosure.

[0156] In some examples, a UE is configured with an encoder portion in an autoencoder and a quantizer, the base station is configured with a decoder portion in the same autoencoder and a de-quantizer paired with the quantizer in the UE. Wherein the method of obtaining the encoder and decoder is to train the autoencoder they constitute. Wherein, the quantizer functions to obtain a sequence of bits from a vector of floating-point numbers, and the de-quantizer functions to obtain a floating-point vector from a sequence of bits. Wherein the quantizer and the de-quantizer are paired with each other to indicate that the bit sequence generated by the quantizer can be restored to a vector of floating-point numbers by the de-quantizer, and the restored vector of floating-point numbers is the same as the vector of floating-point numbers. Wherein the same means the same with a loss of quantization precision.

[0157] The method in which the UE acquires complex information carrying CSI may include: the UE obtaining a vector of floating-point numbers carrying CSI based on the configured encoder; The UE obtains a bit sequence carrying CSI based on the quantizer and the vector of floating-point numbers; The UE obtains complex-valued information carrying CSI by modulating a bit sequence carrying CSI. The method of acquiring CSI based on complex-valued information carrying CSI by the base station may include: the UE demodulating the complex-valued information carrying CSI to obtain a bit sequence carrying CSI; The UE obtains a vector of floating-point numbers carrying CSI based on the de-quantizer and the bit sequence carrying CSI; The CSI is obtained based on the vector of floating-point numbers carrying the CSI and the configured decoder.

[0158] FIG. 7 shows a schematic diagram of a neural network model used by a first method of training in a communication system according to the present disclosure.

[0159] In some examples, a UE is configured with an encoder portion in an autoencoder and a quantizer, and the base station is configured with a decoder portion in the same or a corresponding autoencoder and a de-quantizer. The method of obtaining the encoder and the decoder is to train an autoencoder consisting of the encoder, the channel network and the decoder, e.g. training jointly or separately. Wherein when training the autoencoder, the method of inputting CSI into the autoencoder for forward propagation comprises: inputting CSI into the encoder, obtaining a vector of floating-point numbers characterizing the CSI; Inputting the vector of floating-point numbers into a quantizer to obtain a sequence of bits characterizing the CSI; Inputting the bit sequence characterizing the CSI into a channel network to obtain a bit sequence passed through the channel; Inputting the bit sequence passed through the channel into a de-quantizer to obtain a vector of floating-point numbers passed through the channel; The vector of floating-point numbers passed through the channel is input to a decoder to obtain reconstructed CSI. Wherein the channel network is a neural network that warps the input information by simulating a real channel, and the input of the channel network is bit information and the output is bit information passed through the channel. For example, the channel network may include a neural network that simulates a binary symmetric channel or a binary erasure channel, acting to flip each bit in the bit information according to a probability corresponding to the SINR of the channel. When training the autoencoder, updating the weights of the autoencoder for gradient descent further comprises locking the weights of the quantizer, the channel network, and the de-quantizer. The meaning of locking is that the weights are not updated.

[0160] In some examples, the method of paired training an autoencoder comprises: inputting CSI to the autoencoder for forward propagating, to obtain reconstructed CSI output by a decoder; Calculating a loss function based on the CSI input into the autoencoder and the reconstructed CSI output from the decoder; updating the weights of the autoencoder with gradient descent by the loss function according to the method of backpropagation. The loss function may include mean square error (MSE), normalized mean square error (NMSE), cosine similarity (GCS), and the like.

[0161] FIG. 8 shows a schematic diagram of a neural network structure of a bit sequence acquisition carrying a CSI eigenvector at a UE side and a CSI reconstruction at a base station side in a communication system according to the present disclosure.

[0162] In some examples, a UE is configured with an encoder portion in an autoencoder and a quantizer, and base station is configured with a decoder portion in the same or a corresponding autoencoder and a de-quantizer. The structure of the autoencoder may include that the encoder and the decoder comprise a plurality of transformer layers, respectively. For example, the input to the encoder may include a CSI eigenvector over N subbands. By inputting the CSI eigenvector into an encoder, after processing by a linear layer, a multi-layer transformer, and a linear layer, a vector of floating-point numbers carrying the CSI eigenvector is obtained, the vector of floating-point numbers is then input into a quantizer to obtain a bit sequence carrying the CSI eigenvector. Wherein, before inputting the CSI eigenvector into the encoder, the method for the UE to acquire CSI eigenvector may include performing SVD decomposition based on the estimated raw channel matrix. The structure of decoder is in accordance with that of the encoder, by inputting the bit sequence carrying the CSI eigenvector into a de-quantizer, a vector of floating-point numbers carrying the CSI eigenvector is obtained, and the vector of floating-point numbers is then input into the decoder, after processing by a linear layer, a multi-layer transformer, and a linear layer, a reconstructed CSI eigenvector is obtained.

[0163] FIG. 9 illustrates a schematic diagram of a method for a UE to obtain complex-valued information using a neural network in a communication system according to the present disclosure.

[0164] In some examples, the second method may include obtaining complex-valued information based on CSI and a neural network model. For example, the method of obtaining complex-valued information using a neural network model may include: obtaining a CSI input consistent with data format and structure of the input layer of the neural network by transforming data format and structure of the CSI; Inputting the transformed CSI into the neural network to obtain output of the neural network related to complex-valued information; Obtaining the complex-valued information from the output of the neural network.

[0165] Wherein the structure of the "neural network model" includes, but is not limited to, an Auto-encoder, a Denoising Autoencoder, a Variational Autoencoder, an Generative Adversarial Network (GAN), a Diffusion model, a Multilayer Perceptron (MLP), a Convolutional Neural Network (CNN), a Deep Neural Network (DNN), a Recurrent Neural Network (RNN), a Restricted Boltzmann Machine (RBM), a Graph Neural Network (GNN), a Deep Belief Network (DBN), a Bidirectional Recurrent Deep Neural Network (BRDNN), a neural network with a self-attention mechanism (e.g., Transformer), and the like.

[0166] In some examples, the complex-valued information obtained in the obtaining complex-valued information based on CSI without bit sequence generation and channel coding may not carry check information.

[0167] In some examples, the complex-valued information obtained in the method of obtaining complex-valued information based on CSI without bit sequence generation and channel coding may carry check information. The check information may comprise a cyclic redundancy check (CRC). The method of adding check information in the complex-valued information may include at least one of: adding CRC before inputting the CSI to the neural network; Adding CRC in complex-valued information obtained from an output of the neural network.

[0168] In some examples, the data format of the CSI in the "obtaining a CSI input consistent with data format and structure of the input layer of the neural network" may include complex numbers, and the data format of the neural network model may include floating-point numbers. The method of transforming the data format of the CSI may include separating a real part and an imaginary part of a complex number in the CSI to obtain two floating-point numbers. Wherein the data structure of the CSI may comprise one of a vector, a matrix, a tensor, and the structure of the neural network input may also comprise one of a vector, a matrix, a tensor. Wherein the method of transforming the data structure of the CSI is performing dimension transform on the CSI according to the data structure of the input layer of the neural network. Wherein the dimension transform may also be referred to as permute, permutation, transpose, rearrange, rearrangement, alteration, and the like. Taking the CSI is a channel impulse response of four dimensions including time domain, frequency domain, spatial domain of a UE, spatial domain of a base station, and a structure of input of a neural network is a vector as an example, the number of samples of the channel impulse response on the time domain, the frequency domain, the spatial domain of a UE, the spatial domain of a base station for the CSI are T, F, RX, TX respectively, forming a tensor of dimension [T, F, RX, TX], a method of obtaining a CSI input consistent with data format and structure of the input layer of a neural network includes: first, converting the data format of the CSI from complex numbers into floating-point numbers, forming a tensor of dimension [T, F, RX, TX, RI], where RI = 2 carries floating-point numbers representing real and imaginary parts of complex-valued symbols; The tensor of dimension [T, F, RX, TX, RI] is then subjected to dimension transform, resulting in a vector comprising T * F * RX * TX * RI elements after dimension reduction.

[0169] In some examples, the data format of output of the neural network may also include complex numbers, the data structure of output of the neural network may include one of a sequence, a vector, a matrix, a tensor, and the structure of the complex-valued information may include one of a sequence, a vector, a matrix, a tensor. The method of obtaining complex-valued information from the output of the neural network may comprise obtaining complex-valued information from the output of the neural network using a method of data format and structure transform. The method of transforming the data format of output of the neural network may include combining floating-point numbers into complex numbers two by two. Wherein the method of structure transform of output of the neural network is dimension transform of output of the neural network according to a specified data format of complex-valued information. Taking output of the neural network being a vector and the complex-valued information including two dimensions in the time domain and the frequency domain as an example, the output vector of the neural network has a length of Tout*Fout*RI where RI = 2, the method of obtaining the complex-valued information includes: first, performing dimension transform of the output vector of the neural network to obtain a tensor including a dimension of [Tout, Fout, RI] after dimension increase; Then, 2 floating-point numbers in each set of data in RI dimensions in the above tensor are formed into complex numbers as real and imaginary parts, respectively, to obtain a tensor of dimension [Tout, Fout], which is complex-valued information containing Tout*Foutcomplex-valued modulation symbols.

[0170] FIG. 10 illustrates a schematic diagram of an autoencoder including a neural network model for acquiring complex-valued information of CSI in a communication system according to the present disclosure.

[0171] In some examples, the neural network model used by the UE to obtain the complex-valued information of CSI may include an encoder portion in an autoencoder. Where the autoencoder includes three part, an encoder, a channel network, and a decoder, each of the autoencoders may include a neural network of no less than one layer. Wherein the input to the encoder is CSI and the output is complex-valued information. Where the input to the decoder is complex-valued information passed through the channel and the output is CSI. Wherein the channel network is a neural network that warps the input information by simulating a real channel, the input of the channel network is complex-valued information and the output is complex-valued information passed through the channel. For example, the channel network may comprise a neural network that simulates a Gaussian channel, acting to add Gaussian noise to the complex-valued information.

[0172] In some examples, a method for a base station to obtain CSI may include: a base station receiving a radio frequency signal and extracting complex-valued information carrying the CSI from the radio frequency signal; The base station inputs the complex-valued information into a decoder for reconstructing the CSI, and obtaining the CSI from the output of the decoder. Wherein the radio frequency signal received by the base station is radio frequency signal transmitted by the UE that carries complex-valued information of CSI, and the decoder for the base station to reconstruct CSI is a decoder paired with the encoder for the UE to obtain the complex-valued information. Wherein the pairing means that the decoder for the base station to reconstruct CSI is trained in pair with the encoder for the UE to obtain complex-valued information of CSI.

[0173] FIG. 11 illustrates a schematic diagram of acquisition of complex-valued information of CSI at UE side and CSI reconstruction at a base station side in a communication system according to the present disclosure.

[0174] In some examples, a UE is configured with an encoder portion in an autoencoder and the base station is configured with a decoder portion in the same or a corresponding autoencoder. Wherein the method of obtaining the encoder and the decoder is to train, e.g. jointly or separately, an autoencoder consist of three parts, the encoder, the decoder and the channel network. The method for the UE to acquire the complex-valued information carrying the CSI may include that the UE acquires the complex-valued information carrying the CSI based on the configured encoder, and base station acquires the CSI according to the received complex-valued information based on the configured decoder. Wherein the UE acquires complex-valued information carrying CSI through an output of the encoder without passing through a quantizer, and base station acquires CSI according to an output of the decoder without passing through a de-quantizer. The benefit of not using a quantizer and de-quantizer is that quantization errors are eliminated. Wherein the UE acquires complex-valued information carrying CSI from the output of the encoder without additional modulation, and the base station acquires CSI from the output of decoders without additional demodulation. Wherein no additional modulation and demodulation is used because the encoder and decoder are capable of modulation and demodulation, and the output of the encoder is the modulated complex-valued modulation symbols and the output of the decoder is the demodulated vector of floating-point numbers carrying the CSI.

[0175] FIG. 12 shows a schematic diagram of a neural network structure for acquisition of complex-valued information of CSI at UE side and CSI reconstruction at a base station side in a communication system according to the present disclosure.

[0176] In some examples, a UE is configured with an encoder portion in an autoencoder and the base station is configured with a decoder portion in the same or a corresponding autoencoder. The structure of the autoencoder may include that the encoder and the decoder comprise a plurality of transformer layers, respectively. For example, the input to the encoder may include a CSI eigenvector over N subbands. By inputting the CSI eigenvector into an encoder, after processing by a linear layer, a multi-layer transformer, and a linear layer, complex-valued information carrying the CSI eigenvector is obtained. Wherein, before inputting the CSI eigenvector into the encoder, the method for the UE to acquire CSI eigenvector may include performing SVD decomposition based on the estimated raw channel matrix. The structure of decoder is in accordance with that of the encoder, by inputting the complex-valued information carrying the CSI eigenvector into the decoder, after processing by a linear layer, a multi-layer transformer, and a linear layer, a reconstructed CSI eigenvector is obtained.

[0177] In some examples, the method of training an autoencoder in pair comprises: inputting the CSI into the autoencoder for forward propagating, to obtain reconstructed CSI output by the decoder; Calculating a loss function based on the CSI input into the autoencoder and the reconstructed CSI output from the decoder; Updating the weights of the autoencoder with gradient descent with the loss function according to the method of backpropagation. The loss function may include mean square error (MSE), normalized mean square error (NMSE), cosine similarity (GCS), and the like.

[0178] FIG. 13 illustrates a schematic diagram of training an autoencoder in accordance with the present disclosure.

[0179] In some examples, a method of inputting CSI into an autoencoder for forward propagation when training the autoencoder in pair includes: inputting CSI into the encoder, to obtain complex-valued information characterizing the CSI; Inputting the complex-valued information into a channel network to obtain complex-valued information passed through the channel; inputting the complex-valued information passed through the channel to a decoder to obtain reconstructed CSI. Wherein the role of the channel network may include adding a random number characterizing a Gaussian channel to each complex-valued symbol in the input complex-valued information and outputting it. When the autoencoder is trained in pair, updating the weights of the autoencoder with gradient descent further comprises locking the weights of the channel network. The locking means the weights of the channel network will not be updated.

[0180] In some examples, the autoencoder may be trained at the UE. For example, the UE trains an autoencoder according to the acquired CSI and reports a trained decoder to the base station.

[0181] In some examples, the autoencoder may also be trained at the base station. For example, the UE reports the acquired CSI to a base station, and the base station trains an autoencoder according to the acquired CSI and transmits the trained encoder to the UE. The process of the UE reporting the CSI to a base station may include: the UE acquiring the CSI and storing the CSI in a buffer; The UE collects a certain amount of CSI to form a CSI data set; The UE reports the CSI data set.

[0182] In some examples, the autoencoder may also be trained offline. For example, an autoencoder is obtained by a method of off-line training, and an encoder and a decoder are deployed on the UE and the base station, respectively. In some examples, the "uplink channel or signal" may include a physical channel for carrying uplink control information or a physical channel for carrying uplink shared information. The physical channel for carrying uplink control information may comprise a Physical Uplink Control Channel (also referred to as PUCCH). The physical channel for carrying uplink shared information may include a Physical Uplink Shared Channel (also referred to as PUSCH).

[0183] FIG. 14 illustrates a schematic diagram of a UE multiplexing the uplink channel or signal to carry complex-valued information of second uplink control information in a communication system according to the present disclosure.

[0184] In some examples, prior to the UE mapping and transmitting the complex-valued information onto an uplink channel or signal, it further comprises UE multiplexing the uplink channel or signal to carry the complex-valued information of the second uplink control information. The method of multiplexing may include first obtaining multiplexed complex-valued information based on the complex-valued information related to CSI and the complex-valued information related to second uplink control information, and then mapping the multiplexed complex-valued information onto an uplink channel or signal. The method of obtaining of the complex-valued information of the second uplink control information may include one of a method of obtaining the complex-valued information based on a bit sequence, wherein the bit sequence is obtained by a process of a bit sequence generation and channel coding on the second uplink control information, or a method of obtaining the complex-valued information based on the second uplink control information, wherein the second uplink control information is not subjected to bit sequence generation and channel coding. Wherein the CSI may also be referred to as first uplink control information.

[0185] In some examples, the "second uplink control information" may include at least one of the following information: Channel State Information (CSI), Scheduling Request (SR), Acknowledgement (ACK). The second uplink control information may be the same as the first uplink control information. For example, the first uplink control information is CSI and the second uplink control information is also CSI. The second uplink control information may be different from the first uplink control information. For example, the first uplink control information is CSI and the second uplink control information is an scheduling request or an acknowledgement.

[0186] In some examples, prior to obtaining the complex-valued information of the second uplink control information, it further comprises determining, by the UE, one of a plurality of methods of obtaining the complex-valued information characterizing the second uplink control information based on the indication of the configuration information. In some examples, each of the "a plurality of methods of obtaining the complex-valued information characterizing the second uplink control information" may be implemented with no less than one scheme. For example, when the method is "a method of obtaining complex-valued information based on a bit sequence obtained by performed a procedure of bit sequence generation and channel coding on the second uplink control information", the scheme may include a modulation and coding scheme (MCS) in which required parameters include a Modulation Order and a Target code Rate. For example, when the method is "a method of obtaining complex-valued information based on second uplink control information, wherein the second uplink control information is not subjected to bit sequence generation and channel coding", the parameters that may be included in the scheme includes at least one of a model type, a number of model layers, a number of model neurons, a model activation function, a model weight, an input format, an output format, and the like.

[0187] In some examples, the method of "obtaining the complex-valued information of the second uplink control information" may be different from the method of obtaining the complex-valued information of the first uplink control information. For example, the method of obtaining second uplink control information obtains the complex-valued information based on a method in which channel coding and modulation are performed to obtain the complex-valued information, and the method of obtaining first uplink control information obtains the complex-valued information based on a method in which at least one of the channel coding and modulation steps is not performed.

[0188] In some examples, the multiplexed complex-valued information includes the same number of complex-valued symbols as the sum of the number of complex-valued symbols in the complex-valued information related to the first uplink control information and the complex-valued information related to the second uplink control information. Wherein the multiplexed complex-valued information comprises a first portion of complex symbols that are complex symbols in the first or second uplink control information and a second portion of complex symbols that are complex symbols in the first or second uplink control information other than the first portion of complex symbols. For example, if the complex symbols included in the first uplink control information are , the complex symbols included in the second uplink control information are , and the multiplexed complex-valued information includes first uplink control information as the first portion of the complex symbols, then the multiplexed complex-valued information is , where , when , when .

[0189] In some examples, "multiplexed complex-valued information" further includes multiplexed complex-valued information obtained according to different priorities. Wherein the first uplink control information and the second uplink control information used to obtain the multiplexed complex-valued information are configured to have different priorities, and the multiplexed complex-valued information comprises a first portion of the complex symbols of the uplink control information having a higher priority and a second portion of the complex symbols of the uplink control information having a lower priority. In an example where the first uplink control information has a higher priority than the second uplink control information, the first portion of the complex symbols included in the multiplexed complex-valued information are the complex symbols of the first uplink control information and the second portion of the complex symbols are the complex symbols of the second uplink control information.

[0190] In some examples, prior to the UE mapping the complex-valued information onto an uplink channel or signal and transmitting the same, it further comprises: the UE multiplexing the uplink channel or signal to carry the complex-valued information of the other information. Wherein the other information may comprise data information. The method of multiplexing may include first obtaining multiplexed complex-valued information based on the complex-valued information related to the uplink control information and the complex-valued information related to the other information, and then mapping the multiplexed complex-valued information onto the uplink channel or signal. Wherein the obtaining of the complex-valued information of the other information may include one of a method of obtaining the complex-valued information by performing channel coding and modulation based on the other information, or a method of obtaining the complex-valued information without performing at least one of channel coding and modulation based on the other information.

[0191] In some examples, the "uplink channel or signal" may include a physical uplink control channel (PUCCH) or a physical uplink shared channel (PUSCH).

[0192] In some examples, prior to the UE mapping the complex-valued information onto the uplink channel or signal, it further comprises obtaining, by the UE, matched complex-valued information based on the complex-valued information and the number of time-frequency resource units used for reporting the uplink control information, wherein the number of complex-valued symbols included in the matched complex-valued information is the same as the number of time-frequency resource units used for reporting the uplink control information. The method of matching may also be referred to as: rate matching, symbol selection, symbol level rate matching, and the like. The time-frequency resource unit may comprise a resource element (RE).

[0193] For convenience, the "time-frequency resource unit used for reporting uplink control information" will be referred to as "resource unit" in the following, and the "number of time-frequency resource units used for reporting uplink control information" will be referred to as "number of resource units" in the following.

[0194] In some examples, the method for the UE to obtain "the number of time-frequency resource units used for reporting uplink control information" may include: the UE acquires it according to the configured time-frequency resource information and pilot information. Wherein, the pilot may include a demodulated reference signal (DM-RS). Specifically, the UE obtains the number of symbols related to the uplink control information, the number of physical resource blocks (PRB), the spreading factor and the location information of the pilot according to the configuration. The UE obtains the number of time-frequency resource units in each symbol and each PRB that can be used for the uplink control information based on the location information of the pilot, and obtains the number of resource units associated with reporting uplink control information based on the above information. For example, the number of symbols related to the uplink control information, the number of physical resource blocks (PRB), and the spreading factor are Nsymb,UCI, NPRB, NSF, respectively, and the number of time-frequency resource units within each PRB of each symbol that can be used for the uplink control information is 8 or 12, then the number of resource units associated with reporting uplink control information is 8*Nsymb,UCI*NPRB / NSFor 16*Nsymb,UCI*NPRB / NSF.

[0195] In some examples, the method for the UE to obtain the matched complex-valued information based on the complex-valued information and the number of time-frequency resource units used to report the uplink control information may comprise: the UE writing the complex-valued information into a Circular buffer, wherein the Circular buffer has a length equal to the number of complex symbols in the complex-valued information; The UE reads the complex symbols from the circular buffer according to the configured method to obtain the matched complex-valued information. Wherein the configured method may include the UE extracting complex symbols from the circular buffer according to the configured starting position and / or reading order to obtain matched complex-valued information. Wherein the number of complex-valued symbols included in the matched complex-valued information is the same as the number of resource units. Wherein the starting position, reading order, the number of resource units may be obtained based on configuration information.

[0196] In some examples, the "circular buffer" is characterized in that the first complex symbol and the last complex symbol of the complex-valued information stored in the circular buffer are adjacent to each other. Taking the example that E complex symbols e0,e1,e2,…,eE-1are included in the complex-valued information, where the length of the circular buffer is E and the symbol following eE-1in the circular buffer is e0.Taking the example of extracting E+3 symbols starting from symbol e0in the circular buffer described above, the matched complex-valued information obtained is e0,e1,e2,…,eE-1,e0,e1,e2.

[0197] FIG. 15 illustrates a schematic diagram of a circular buffer for rate matching in a communication system according to the present disclosure.

[0198] In some examples, the method for the UE to read complex symbols from the circular buffer according to the configured method to obtain the matched complex-valued information may include, when the length of the complex-valued information is greater than the number of resource units, calculating a difference value of the length of the complex-valued information and the number of resource units, and taking the difference value as a starting position of the circular buffer for reading, extracting the complex symbols in order until complex symbols equal to the number of resource units are obtained, which may be referred to as Puncturing. A benefit of rate matching using puncturing is that when the priority of complex symbols in the circular buffer increases with position, the priority of complex symbols retained by the UE through puncturing is higher than the priority of lost complex symbols, and the effectiveness of the signal recovered at the receiving side may be achieved by the UE transmitting complex symbols with higher priority. Taking the example in which complex-valued information is y0,y1,y2,…,yN-1, wherein N complex-valued modulation symbols are included, and the number of resource units is E, where N > E, the UE first stores the complex-valued information y0,y1,y2,…,yN-1in a circular buffer and then reads from the (N-E)-th complex-valued modulation symbol in the circular buffer to obtain matched complex-valued information e0,e1,e2,…,eE-1. For example, the method is to let k = 0 to E-l, and let ek=yk+N-E.

[0199] In some examples, the method for the UE to read complex symbols from the circular buffer according to the configured method to obtain matched complex-valued information may include, when the length of the complex-valued information is greater than the number of resource units, extracting complex symbols in order starting from the first complex symbol of the circular buffer until complex symbols equal to the number of resource units are obtained, which may be referred to as Shortening. The benefit of using the method of shortening for rate matching is that when the priority of the complex symbols in the circular buffer decreases with position, the priority of the complex symbols retained by the UE through puncturing is higher than the priority of the lost complex symbols, and the effectiveness of the signal recovered at the receiving side may be increased by the UE transmitting complex symbols with the higher priority. Taking the example in which complex-valued information is y0,y1,y2,…,yN-1, wherein N complex-valued modulation symbols are included, and the number of resource units is E, where N > E, the UE first stores the complex-valued information y0,y1,y2,…,yN-1in a circular buffer and then reads from the first complex-valued modulation symbol in the circular buffer to obtain matched complex-valued information e0,e1,e2,…,eE-1. For example, the method is to let k = 0 to E-l, and let ek=yk.

[0200] In some examples, the method for the UE to read the complex symbols from the circular buffer according to the configured method to obtain the matched complex-valued information may include, when the length of the complex-valued information is less than the number of resource units, extracting the complex symbols in forward or reverse order starting from the first complex symbol of the circular buffer until complex symbols equal to the number of resource units are obtained, which may be referred to as Repetition. The reason why this method is referred to as repetitive is that when the entire circular buffer is first traversed by sequentially extracting complex symbols, the number of extracted complex symbols does not reach the required length of the rate-matched output sequence, then the complex symbols are sequentially extracted starting from the first complex symbol of the circular buffer again, until complex symbols equal to the number of resource units are obtained. The advantage of using repetition to implement rate matching is that the UE achieves diversity gain of high priority complex symbols by repeatedly transmitting complex symbols with high priority when the priority of the complex symbols in the circular buffer increases or decreases with position, thereby improving the accuracy of the signal recovered at the receiving side. Taking the example in which complex-valued information is y0,y1,y2,…,yN-1, wherein N complex-valued modulation symbols are included, and the number of resource units is E, where N < E, the UE first stores the complex-valued information y0,y1,y2,…,yN-1in a circular buffer and then reads from the first complex-valued modulation symbol in the circular buffer to obtain matched complex-valued information e0,e1,e2,…,eE-1.For example, the method is to let k = 0 to E-l, and let ek=ymod(k,N).

[0201] In some examples, prior to the UE mapping the complex-valued information onto an uplink channel or signal, it further comprises: the UE multiplexing the uplink channel or signal for carrying second uplink control information to obtain multiplexed complex-valued information; The UE obtains the matched complex-valued information based on the multiplexed complex-valued information and the number of time-frequency resource units used to report the uplink control information, wherein the number of complex-valued symbols included in the matched complex-valued information is the same as the number of time-frequency resource units used to report the uplink control information.

[0202] In some examples, prior to the UE mapping the complex-valued information onto the uplink channel or signal, it further comprises interleaving complex symbols in the complex-valued information according to the configuration information to obtain interleaved complex-valued information. For example, a method of interleaving complex symbols in complex-valued information includes: determining, by the UE, an interleaving order according to uplink signal-related configuration information; determining, by the UE, an interleaving mapping pattern according to the interleaving order and interleaving and mapping the second sequence.

[0203] For example, a total of E complex symbols e0,e1,e2,…,eE-1are included in the second sequence of the UE, the E complex symbols are interleaved into a complex symbol sequence f0,f1,f2,…,fE-1, and the UE determines that the interleaving order is Qmthrough the uplink signal related configuration information, then the pseudo code of the method for the UE to obtain the complex symbol sequence f0,f1,f2,…,fE-1through interleaving is as follows:

[0204]

[0205] In some examples, a method for a UE to map and transmit the complex-valued information onto an uplink channel or signal includes: the UE mapping complex-valued symbols in the complex-valued information with time-frequency resource units indicated by a configuration to obtain complex-valued information associated with time-frequency resources; The UE obtains and transmits a radio frequency signal according to the complex-valued information associated with the time-frequency resource.

[0206] FIG. 16 illustrates a schematic diagram of a user mapping complex symbols in complex-valued information with time-frequency resource units indicated by a configuration in a communication system according to the present disclosure.

[0207] In some examples, the method for the UE mapping the complex-valued symbols in the complex-valued information with the time-frequency resource units indicated by the configuration to obtain the complex-valued information associated with the time-frequency resources comprises the UE multiplying each complex-valued symbol in the complex-valued information by an amplitude scaling factor and sequentially mapping the same onto all compliant (not reserved) resource units in sequence. Wherein each complex symbol is multiplied by an amplitude scaling factor such that each symbol conforms to a specified transmit power. Wherein the compliant resource units comply with the following requirements: the resource units are located on a resource block allocated to the UE for transmission; Resource units are not allocated to be associated with demodulation reference signals (DM-RS). Wherein the order of mapping complex symbols to resource units is to sequentially map to compliant frequency-domain resource units in the order of sequence numbers on one time-domain symbol, and when all frequency-domain resources on one time-domain symbol are filled, frequency-domain resource units on the next time-domain symbol are mapped. For example, the time-frequency resource unit is represented by (k, l), where k represents the sequence number of a subcarrier and l represents the sequence number of a time-domain symbol, and the UE first sequentially maps complex symbols to unallocated resource units in the order of increasing number k, and then maps resources in the next time-domain symbol in the order of increasing number l when all frequency-domain resources in one time-domain symbol are filled.

[0208] FIG. 17 illustrates a schematic diagram of time-frequency resource unit mapping of pilot-related complex symbols by a user in a communication system according to the present disclosure.

[0209] In some examples, prior to the UE obtaining and transmitting the radio frequency signal according to the complex-valued information associated with the time-frequency resources, it further comprises: the UE generating a signal sequence for a pilot according to the configuration information; The UE maps the signal sequence for the pilot with the pilot-related time-frequency resource units indicated in the time-frequency resource information. Wherein the pilot may comprise a reference signal for demodulation (DM-RS). For example, the UE first generates a signal sequence for the pilot according to the configuration information, multiplies each complex symbol of the signal sequence for the pilot by an amplitude scaling factor, and sequentially maps the same onto the resource units reserved for the pilot in order. Wherein each complex symbol is multiplied by the amplitude scaling factor such that each symbol conforms to a specified transmit power. Taking the example in which the time-frequency resource units are denoted by (k, l), k represents the sequence number of a subcarrier, and l represents the sequence number of a time-domain symbol, when the resources reserved for the pilot are distributed on the time domain, the UE generates the signal sequence z(m) for the pilot, and sequentially maps the complex symbols in the signal sequence z(m) for the pilot starting from z(0) onto the resource units reserved for the pilot in the order of increasing sequence number as l=0,2,4,…

[0210] FIG. 18 illustrates a schematic diagram of a user in a communication system obtaining complex-valued information including pilots associated with time-frequency resources according to a method of time-division multiplexing according to the present disclosure.

[0211] In some examples, prior to the UE obtaining and transmitting the radio frequency signal according to the complex-valued information associated with the time-frequency resource, it further comprises mapping the complex-valued information and the signal sequence of the pilots with the time-frequency resource units indicated by the configuration according to a method of time division multiplexing, to obtain the complex-valued information including the pilots associated with the time-frequency resources. Wherein the complex-valued information may be obtained by a method based on not performing steps of channel coding and modulation on the uplink control information. The method of not performing the steps of channel coding and modulation may include a method of obtaining complex-valued information based on a neural network model. Wherein the method of time-division multiplexing may include a method of mapping a signal sequence of complex-valued information and a pilot on different time-domain symbols. For example, by the time-division method of multiplexing, complex-valued information and the signal sequence are mapped onto time-frequency resource units having the same subcarrier sequence number and different time-domain symbol sequence numbers. Taking the example that the time-frequency resource units are denoted by (k, l), k represents the sequence number of the subcarrier, and 1 represents the sequence number of the time-domain symbol, the UE sequentially maps the complex symbols in the signal sequence for pilots z(m) to the resource units with the sequence number of time-domain symbols l∈Lzin the order of frequency-domain first and then time-domain, and the UE sequentially maps the complex symbols in the complex-valued information to the resource units with the sequence number of time-domain symbols l∈Lfin the order of frequency-domain first and then time-domain. Where Lzdenotes a set of sequence numbers of time-domain symbols for pilots, Lfdenotes a set of sequence numbers of time-domain symbols for complex-valued information, and Lz∩Lf=Ø,Lz∪Lfincludes sequence numbers of all time-domain symbols assigned to uplink control information associated with complex-valued information. For example, Lz=[0,2], Lf=[1,3], the UE maps the signal sequence for pilots z(m) with the sequence number of time-domain symbols l=0,2 on the time-frequency resource units (k, l), and the UE maps the complex-valued information with the sequence number of time-domain symbols l=1,3.

[0212] FIG. 19 illustrates a schematic diagram of a user in a communication system obtaining complex-valued information including pilots associated with time-frequency resources according to a method of frequency division multiplexing according to the present disclosure.

[0213] In some examples, prior to the UE obtaining and transmitting the radio frequency signal according to the complex-valued information associated with the time-frequency resource, it further comprises the UE mapping the complex-valued information and the signal sequence of the pilots with the time-frequency resource units indicated by the configuration according to a method of frequency division multiplexing, to obtain the complex-valued information including the pilots associated with the time-frequency resources. Wherein the complex-valued information may be obtained by a method based on not performing the steps of channel coding and modulation on the uplink control information. The method of not performing the steps of channel coding and modulation may include a method of obtaining complex-valued information based on a neural network model. Wherein the method of frequency division multiplexing may include a method of mapping complex-valued information and signal sequences of pilots on different frequency-domain resources. For example, by the frequency division method of multiplexing, complex-valued information and signal sequences are mapped onto time-frequency resource units with different sequence numbers of subcarriers and the same sequence numbers of time-domain symbols. Taking the example in which the time-frequency resource units are denoted by (k, l), where k represents the sequence number of a subcarrier, and l represents the sequence number of a time-domain symbol, the UE sequentially maps complex symbols in the signal sequence for pilots z(m)to the resource units with the sequence numbers of frequency-domain subcarriers k∈Kzin the order of frequency-domain first and then time-domain, and the UE sequentially maps complex symbols in the complex-valued information to the resource units with the sequence numbers of the time-domain symbols k∈Kfin the order of frequency-domain first and then time-domain. Where Kzdenotes a set of sequence numbers of subcarriers for the pilot, Lfdenotes a set of sequence numbers of subcarriers for the complex-valued information, and it is satisfied that Kz∩Kf=Ø, and Kz∪Kfincludes sequence numbers of all subcarriers assigned to uplink control information associated with the complex-valued information.

[0214] In some examples, the method of mapping, by the UE, the complex-valued information and the signal sequence of the pilots with the time-frequency resource units indicated by the configuration according to the method of frequency division multiplexing further comprises the UE mapping the signal sequence of the pilots onto the time-frequency resource units in a comb form. Said mapping in a comb form means, there are the same number, greater than one, of time-frequency resource units associated with complex-valued information between the time-frequency resource units to which any two pilot symbols consecutive in the frequency domain are mapped. Taking the example in which there are 3 time-frequency resource units associated with complex-valued information between the time-frequency resource units to which any two pilot symbols consecutive in the frequency domain are mapped, the UE generates a pilot sequence zl(m) for each time-domain symbol l, and sequentially maps the complex symbols in the signal sequence zl(m) for pilots onto the resource units reserved for pilots starting from zl(0) and in the order of sequence number k = 3m + l.

[0215] In some examples, the method for the UE to obtain and transmit a radio frequency signal according to the complex-valued information associated with time-frequency resources comprises: the UE first obtaining a time-domain continuous orthogonal frequency division multiplexing (OFDM) baseband signal according to the complex-valued information associated with time-frequency resources; then, the UE obtains a radio frequency signal by modulating and upconversion of the time-domain baseband signal to a carrier frequency; Finally, the UE transmits the radio frequency signals on respective antenna ports.

[0216] In some examples, the method for the UE to obtain and transmit a radio frequency signal according to the complex-valued information associated with time-frequency resources further comprises: the UE mapping the complex-valued information and a signal sequence of pilots with time-frequency resource units indicated by configuration according to a method of time division multiplexing, to obtain complex-valued information associated with time-frequency resources including pilots; the UE obtaining, according to complex-valued information associated with time-frequency resource units and pilot information associated with time-frequency resource units, time-domain continuous orthogonal frequency division multiplexing baseband signals corresponding to the complex-valued information and the pilot information, respectively, and combining the baseband signals in time domain; then, the UE obtaining a radio frequency signal by modulating and up-conversion of the time-domain baseband signals to the carrier frequency; Finally, the UE transmitting the radio frequency signal on respective antenna ports.

[0217] FIG. 20 illustrates a schematic diagram of an example of method for a user reporting CSI in a communication system according to the present disclosure.

[0218] In some examples, the CSI reported by the UE may include one of a vector, a matrix, or a tensor that includes the estimated channel impulse response in no less than one dimension. For example, the CSI is a tensor of channel impulse response in four dimensions including time domain, frequency domain, spatial domain of UE, spatial domain of base station, the granularity units of the CSI in time domain, frequency domain, spatial domain of UE, spatial domain of base station are symbol, subcarrier, antenna port of UE, antenna port of base station, and the number of samples of the channel impulse response in time domain, frequency domain, spatial domain of UE, spatial domain of base station are T, F, RX, TX, respectively, then the CSI is a tensor of dimension [T, F, RX, TX].

[0219] The UE determines one method of a plurality of methods of obtaining complex-valued information characterizing the CSI according to indication of first configuration information, and the UE determines a scheme of performing the method according to indication of second configuration information. For example, the UE determines a method of obtaining complex-valued information based on CSI, wherein bit sequence generation and channel coding are not performed on the CSI, according to the method identification in the first configuration information, and the UE determines a neural network model for obtaining complex-valued information according to the scheme identification in the second configuration information.

[0220] The UE obtains complex-valued information based on the CSI and the determined neural network model. For example, the method of obtaining complex-valued information using a neural network model may include: obtaining a CSI input consistent with data format and structure of input layer of a neural network by transforming data format and structure of the CSI; Inputting the transformed CSI into the neural network to obtain output of the neural network related to complex-valued information; Obtaining complex-valued information from the output of the neural network. For example, the CSI is a tensor of dimension [T, F, RX, TX], first, transforming the data format of the CSI from complex numbers to floating-point numbers to form a tensor of dimension [T, F, RX, TX, RI], where RI = 2 carries floating-point numbers representing the real and imaginary parts of complex-valued symbols; then, performing dimension transform of the tensor of dimension [T, F, RX, TX, RI] to a vector comprising T*F*RX*TX*RI elements; then, inputting the vector into a neural network, and obtaining output of the neural network vector of length Tout*Fout*RI where RI = 2; performing dimension transform of the output vector of the neural network into a tensor comprising dimension [Tout, Fout, RI] after dimension increase; Finally, 2 floating-point numbers in each set of data of in RI dimensions in the above tensor are formed into complex numbers as real and imaginary parts, respectively, to obtain a tensor of dimension [Tout, Fout], which is complex-valued information containing Tout*Foutcomplex-valued modulation symbols.

[0221] The UE multiplexes the uplink channel or signal to carry complex-valued information of second uplink control information, wherein the second uplink control information may comprise at least one of Channel State Information (CSI), Scheduling Request (SR), Acknowledgement (ACK). For example, the second information is a scheduling request.

[0222] The UE determines one method of a plurality of methods of obtaining complex-valued information characterizing the second uplink control information according to indication of the first configuration information, and the UE determines a scheme for performing the method according to indication of the second configuration information. For example, the UE determines, according to the method identification in the first configuration information, a method of obtaining complex-valued information based on a bit sequence obtained by performing a procedure of bit sequence generation and channel coding on the second uplink control information, and the UE determines, according to the scheme identification in the second configuration information, parameters necessary to perform the method including a modulation order and a target coding rate.

[0223] The UE obtains complex-valued information carrying the second uplink control information based on a bit sequence obtained by performing a procedure of bit sequence generation and channel coding on the second uplink control information. The UE performs bit sequence generation by the uplink control information. For example, the UE obtains a bit sequence carrying the second uplink control information; The UE segments the bit sequence and adds parity at the end of each block of bit sequence to obtain bits after CRC attachment; The UE bit-interleaving the bits after CRC attachment to obtain an interleaved bit sequence; The UE performs channel coding on the interleaved bit sequence according to a polarization sequence to obtain a channel-coded bit sequence; The UE modulates the channel-coded bit sequence according to the configured modulation order to obtain second complex-valued information comprising no less than one complex-valued modulation symbol.

[0224] The UE multiplexes the uplink channel or signal to carry complex-valued information of the second uplink control information. For example, the UE concatenates the last complex symbol of the second complex-valued information with the start complex symbol of the first complex-valued information to obtain multiplexed complex-valued information of length N.

[0225] The UE obtains the matched complex-valued information based on the multiplexed complex-valued information and the number of time-frequency resource units used to report the uplink control information, wherein the number of complex-valued symbols included in the matched complex-valued information is the same as the number of time-frequency resource units used to report the uplink control information. For example, the UE acquires the number of resource units as E according to the configured time-frequency resource information and DM-RS information, and the multiplexed complex-valued information as y0,y1,y2,…,yN-1, where N complex-valued modulation symbols are included, and N > E, and the UE determines to perform rate matching by the method of puncturing. The UE first stores the complex-valued information y0,y1,y2,…,yN-1in the circular buffer, and then reads from the (N-E)-th complex-valued modulation symbol in the circular buffer to obtain the matched complex-valued information e0,e1,e2,…,eE-1. For example, the method is to let k = 0 to E-l, and let ek=yk+N-E.

[0226] The UE interleaves complex symbols in the matched complex-valued information according to the configuration information to obtain interleaved complex-valued information. For example, a total of E complex-valued modulation symbols e0,e1,e2,…,eE-1are included in the matched complex-valued information of the UE, the UE determines the interleaving order as Qmthrough the configuration information, and the UE obtains the interleaved complex-valued information including the complex-valued modulation symbols f0,f1,f2,…,fE-1according to the interleaving order Qm.

[0227] The UE maps the interleaved complex-valued information and the signal sequence of the pilots with the time-frequency resource units indicated by the configuration according to the method of frequency division multiplexing, to obtain complex-valued information including the pilots associated with the time-frequency resources. For example, the time-frequency resource unit is represented by (k, l), where k represents the sequence number of the subcarrier, and l represents the sequence number of the time-domain symbol, the UE sequentially maps complex symbols in the signal sequence of pilots z (m) to the resource units with the frequency-domain subcarrier sequence number k∈Kzin the order of frequency-domain first and then time-domain, and the UE sequentially maps complex symbols in the interleaved complex-valued information f0,f1,f2,…,fE-1to the resource units with the time-domain sequence number k∈Kfin the order of frequency-domain first and then time-domain. Where Kzdenotes a set of sequence numbers of subcarriers for the pilots, Lfdenotes a set of sequence numbers of subcarriers for the complex information, and it is satisfied that Kz∩Kf=Ø, and Kz∪Kfincludes sequence numbers of all subcarriers assigned to uplink control information associated with the complex information.

[0228] The UE obtains a time-domain continuous orthogonal frequency division multiplexing baseband signal according to the complex-valued information associated with the time-frequency resources.

[0229] The UE obtains a radio frequency signal by modulating and up-converting the time-domain baseband signal to a carrier frequency.

[0230] The UE transmits the radio frequency signal on respective antenna ports.

[0231] Embodiment 2

[0232] In some examples, the UE determines one of a plurality of methods of obtaining complex-valued information characterizing the CSI, and a scheme of performing the method, according to indication of configuration information. For example, the UE has information on a plurality of methods, and a plurality of schemes are included in each method of the UE, and an identification table of the plurality of schemes is included for each method of the UE. Wherein the identification table includes no less than one identification for each scheme. Based on the identification table, the method for the UE to determine the selected scheme is to match the scheme identification in the indication to the corresponding identification in the identification table of the UE. It should be understood that, for convenience of description, the expression "identification table" is used with respect to the schemes comprised by the method, intended to refer to a table or set of parameters used to represent at least one scheme to which the method corresponds, through the “identification table”, the respective schema or at least one set of parameters to which the method corresponds can be identified or determined. The expression "identification table" is not intended to be limiting, and other expressions having the same or similar meaning may be used, for example, "index table", "set of parameters", "scheme list", and the like. Similarly, it is understood that "identification" may also be replaced with other expressions, such as "index", "name", "number", "associated information", and the like.

[0233] In some examples, the "UE determines one of a plurality of methods of obtaining complex-valued information characterizing the CSI, and a scheme of performing the method, according to indication of configuration information" may further include: determining, by the UE, one of a plurality of methods of obtaining complex-valued information characterizing CSI and an identification table of a plurality of schemes, according to indication of the first configuration information; determining, by the UE, a scheme for performing the method according to the identification table of a plurality of schemes according to the indication of the second configuration information.

[0234] FIG. 21 illustrates a diagram of a method of obtaining complex-valued information related to uplink control information by a UE in a communication system according to the present disclosure.

[0235] In some examples, the "UE determines one of a plurality of methods of obtaining complex-valued information characterizing the CSI, and a scheme of performing the method, according to indication of configuration information" may further comprise: determining, by the UE, an identification table comprising a plurality of schemes according to the indication of the first configuration information, implicitly determining one of a plurality of methods of obtaining complex-valued information characterizing CSI according to the table; determining, by the UE, a scheme for performing the method according to an identification table of a plurality of schemes according to the indication of the second configuration information.

[0236] In some examples, the identification of the plurality of schemes included in the identification table may include an index, a name, a number, a modulation order, a target code Rate, a spectral efficiency, a signal-to-noise ratio (SNR), a signal-to-interference-plus-noise ratio (SINR), an SINR section, an SINR upper bound, an SINR lower bound, an output type, an output format, an output length, and / or the like. Wherein the SINR section comprises an SINR upper bound and an SINR lower bound representing a maximum and a minimum SINR, respectively, at which the corresponding scheme can operate. Wherein the output length indicates the number of complex-valued symbols in the complex-valued information associated with the uplink control information obtained by the corresponding method. Wherein the output type represents a data type of each element in the information related to the uplink control information obtained by the corresponding scheme, and the data type may include one of a complex number, a floating-point number, and an integer.

[0237] Taking the example in which the UE obtains complex-valued information based on CSI without bit sequence generation and channel coding through a neural network model, first, the UE determines an identification table including a plurality of schemes according to first configuration information, the table including identifications of N neural network models, and the UE also includes structures and weights of the N neural network models corresponding to the table. Identifications in the table include model number, SINR lower bound, output length. Second, the UE determines the neural network model according to an identification in the second configuration information, the identification may include at least one of a model number, an SINR lower bound, an output length. Finally, the UE obtains complex-valued information based on the CSI without bit sequence generation and channel coding according to the neural network model determined through the identification.

[0238] FIG. 22 illustrates a schematic diagram of an identification table including N neural network models in a communication system according to the present disclosure.

[0239] In some examples, the "UE determines one of a plurality of methods of obtaining complex-valued information characterizing the CSI, and a scheme of performing the method, according to indication of configuration information", may further include determining, by the UE, according to the indication of the first configuration information, no less than two identification tables including a plurality of schemes; determining, by the UE, a method and a corresponding identification table according to the indication of the second configuration information, and then determining a scheme for performing the corresponding method according to the table. For example, the UE determines two information tables of methods of obtaining complex values according to the first configuration information, and a first identification table implicitly identifies a method in which the UE obtains complex-valued information based on the CSI without bit sequence generation and channel coding through a neural network model, and a second identification table implicitly identifies a method in which the UE obtains complex-valued information based on the bit sequence obtained by performing bit sequence generation and channel coding on the CSI, and the identification in the first identification table includes a model number, an SINR lower bound, an output length, and the identification in the second identification table includes a scheme number, a modulation order, a target coding rate, a spectral efficiency.

[0240] FIG. 23 illustrates a schematic diagram of an information table in which a UE determines two information tables of methods of obtaining complex values according to first configuration information in a communication system according to the present disclosure.

[0241] In some examples, the "UE determines one of a plurality of methods of obtaining complex-valued information characterizing the CSI, and a scheme of performing the method, according to indication of configuration information" may further include determining, by the UE, an information table including not less than two methods and including a plurality of schemes for each method according to the indication of the first configuration information; determining, by the UE, a method and a scheme for performing the corresponding method according to the indication of the second configuration information. The identification table may include a number of each scheme. For example, the identification table comprises two methods, a first method comprising N1schemes and a second method comprising N2schemes, and the table comprises a total of N1+N2schemes and a scheme number corresponding to each scheme.

[0242] For example, the UE determines an information table including two methods according to the indication of the first configuration information. Wherein the first method may include a method of obtaining complex-valued information based on a bit sequence obtained through a process of bit sequence generation and channel coding on CSI; The second method may include a method of obtaining complex-valued information based on CSI without bit sequence generation and channel coding. The identification in the identification table includes a scheme number, an SINR lower bound, an output length, a modulation order, a target coding rate, a spectral efficiency. The UE determines a method and a scheme for performing the corresponding method according to the scheme number indicated in the second configuration information.

[0243] FIG. 24 illustrates a schematic diagram in which a UE in a communication system determines an information table including two methods according to an indication of first configuration information according to the present disclosure.

[0244] In some examples, the "UE determines one of a plurality of methods of obtaining complex-valued information characterizing the CSI, and a scheme of performing the method, according to indication of configuration information" may further include: determining, by the UE, an identification table comprising a plurality of schemes according to a table name indicated by RRC, and implicitly determining one of a plurality of methods of obtaining complex-valued information characterizing CSI according to the table; determining, by the UE, the scheme for performing the method according to the identification table according to the scheme index indicated in DCI.

[0245] In some examples, according to indication of configuration information, the UE may also determine one of a plurality of methods of obtaining complex-valued information characterizing the first uplink control information and the scheme for performing the method, and determine one of a plurality of methods of obtaining complex-valued information characterizing the second uplink control information and the scheme for performing the method. Wherein the first and second uplink control information may include CSI, scheduling request, acknowledgment, or the like. For example, the UE determines a first identification table including a plurality of schemes of obtaining complex-valued information characterizing the CSI and a second identification table including a plurality of schemes of obtaining complex-valued information characterizing the second uplink control information according to indication of the first configuration information; determining, by the UE, a scheme for performing the method according to an identification table of a plurality of schemes according to the indication of the second configuration information. Wherein determining, by the UE, the scheme for performing the method according to the identification table of a plurality of schemes according to the indication of the second configuration information further comprises: the UE first determining one of the first and second identification tables according to the indication of the second configuration information; The UE then determining a scheme for performing the method according to the indication of the second configuration information and the determined identification table. Wherein the UE determines the scheme for performing the method according to the identification table of a plurality of schemes based on the indication of the second configuration information may further comprise: the UE first determining one of the first and second identification tables based on the content of the uplink control information; The UE then determining a scheme for performing the method according to the indication of the second configuration information and the determined identification table.

[0246] For example, the UE determines a first identification table for obtaining complex-valued information of CSI (first uplink control information) according to the first configuration information, the method corresponding to the first identification table is a method based on not performing bit sequence generation and channel coding through a neural network model; The UE also determines a second identification table for obtaining the complex-valued information of the scheduling request (second uplink control information), the method corresponding to the second identification table is a method of obtaining the complex-valued information based on the bit sequence obtained by the process of bit sequence generation and channel coding on the CSI. The UE selects the first or second identification table based on the content of the obtained uplink control information and determines the scheme for performing the method based on the indication of the second configuration information and the determined identification table.

[0247] In some examples, the UE may also determine one of a plurality of methods of obtaining complex-valued information and the scheme for performing the method according to the indication of the configuration information. Wherein the method and the scheme for performing the method determined by the UE may be used to obtain the complex-valued information of the first uplink control information and may be also used to obtain the complex-valued information characterizing the second uplink control information. The uplink control information may include one of CSI, scheduling request, acknowledgment. For example, the UE may determine an information table including not less than one method and including a plurality of schemes for each method according to the indication of the configuration information; the UE determines a method and a scheme for performing the corresponding method according to the indication of the second configuration information.

[0248] For example, the UE determines an information table including two methods according to the indication of the configuration information. Wherein the first method may include a method of obtaining complex-valued information based on a bit sequence obtained through a process of bit sequence generation and channel coding on CSI; The second method may include a method of obtaining complex-valued information based on CSI, wherein the CSI is not subjected to bit sequence generation and channel coding. The identification in the identification table includes a scheme number, an SINR lower bound, an output length, a modulation order, a target coding rate, a spectral efficiency. The UE determines a method and a scheme for performing the corresponding method according to the indicated scheme number in the second configuration information. When the uplink control information is CSI, the UE determines one scheme of the first method according to the second configuration information, and when the uplink control information is a scheduling request or an acknowledgement, the UE determines one scheme of the second method according to the second configuration information.

[0249] In some examples, prior to the UE determining one of a plurality of methods of obtaining complex-valued information characterizing channel state information (CSI), it further comprises: the UE reporting capability information, the capability information comprising a capability of the UE to obtain complex-valued information based on the CSI without bit sequence generation and channel coding. The base station may determine configuration information based on the UE capability information, the configuration information including indication to the UE the method of complex-valued information characterizing channel state information (CSI). A benefit of the UE reporting capability information is that the base station can play capability of the UE at the most extent based on the capability information by appropriately configuring the method of obtaining complex values, which can increase the efficiency and stability for the UE reporting uplink control information.

[0250] In some examples, the capability information reported by the UE to the base station includes an identification corresponding to the capability. Wherein the capability comprises at least one of:

[0251] a first capability representing the UE has a capability of the first method of obtaining complex-valued information based on a bit sequence, wherein the bit sequence is obtained through a process of bit sequence generation and channel coding on CSI;

[0252] a second capability representing the UE has a capability of the second method of obtaining complex-valued information based on CSI, wherein the CSI is not subjected to bit sequence generation and channel coding;

[0253] a third capability representing the UE has a capability of the first method of obtaining complex-valued information based on a bit sequence, wherein the bit sequence is obtained through a process of bit sequence generation and channel coding on CSI, and the second method of obtaining complex-valued information based on CSI, wherein the CSI is not subjected to bit sequence generation and channel coding.

[0254] Wherein the identification corresponding to the capability may include an index, a name, or the like of the capability.

[0255] Embodiment 3

[0256] In some examples, a method of a UE obtaining complex-valued information based on CSI without bit sequence generation and channel coding may include obtaining complex-valued information based on the CSI and a neural network model. For example, the method of obtaining complex-valued information using a neural network model may include: obtaining a CSI input consistent with data format and structure of input layer of a neural network by transforming data format and structure of the CSI; Inputting the transformed CSI into a neural network to obtain output of the neural network related to complex-valued information; Obtaining complex-valued information from an output of the neural network.

[0257] In some examples, the data format of the CSI in the "obtaining a CSI input consistent with data format and structure of input layer of a neural network by transforming data format and structure of the CSI" may include one of a complex number, a floating-point number, and an integer, and the data format of the neural network model may also include one of a complex number, a floating-point number, and an integer. The method of transforming the data format of the CSI may include at least one of: combining floating-point numbers into complex numbers two by two; Separating the real part and the imaginary part of a complex number to obtain two floating-point numbers; Quantizing floating points into integers; dequantizing integers into floating-point numbers.

[0258] For example, when the data format of the elements in the CSI is consistent with the data format of the neural network model, the neural network model includes an input length equal to the number of elements in the CSI. When the data format of the elements in the CSI is complex number, and the data format of the output of the neural network model is not complex number, the neural network model includes an input length that is twice the number of elements in the CSI. When the data format of the elements in the CSI is not complex number and the data format of the output of the neural network model is complex number, the neural network model includes an input length that is half the number of elements in the CSI.

[0259] In some examples, the data format of output of the neural network may also include one of a complex number, a floating-point number, an integer. Wherein the method of obtaining complex-valued information according to the output of the neural network may include one of the following: when the output of the neural network is complex number, the method of obtaining complex-valued information may include structure transform of the output of the neural network according to a structure of the complex-valued information; When the output of the neural network is floating-point number, the method of obtaining the complex-valued information may include first composing the floating-point numbers into complex numbers and then performing structure transform of the obtained floating-point numbers according to the structure of the complex-valued information; When the output of the neural network is integer number, the method of obtaining the complex-valued information may include first mapping the obtained integer numbers into floating-point numbers according to a mapping relationship of an integer number to a floating-point number, then composing the obtained floating-point numbers into complex numbers, and finally performing structure transform of the obtained floating-point numbers according to a structure of the complex-valued information.

[0260] In some examples, prior to inputting the CSI into the neural network, it further comprises pre-processing the CSI by the UE to obtain pre-processed CSI. Wherein the method for the UE to pre-process the CSI may include performing signal processing-related transform on the CSI to obtain signal processing-related transformed CSI. For example, performing the signal processing-related transform on the CSI may include one of the following methods: Fourier transform, Laplace transform, Wavelet transform, Hilbert-Huang transform, bispectral transform, and the like. A benefit of performing a signal processing-related transform on the CSI is that the CSI can be transformed into a form that facilitates subsequent processing or facilitates processing by a neural network model. Wherein the method for the UE to pre-process the CSI may further include performing redundancy-related processing on the CSI to obtain redundancy-related processed CSI.

[0261] For example, a method for performing redundancy-related processing on CSI may include setting a threshold for redundancy and zeroing out elements in the CSI that are less than the threshold for redundancy. The benefit of performing redundancy-related processing on the CSI is to reduce redundant information in the CSI, which in turn reduces the total amount of information that needs to be transmitted. The process for the UE pre-processing the CSI may further include normalizing or standardizing the CSI to obtain normalized or standardized uplink control information. For example, normalizing or standardizing the uplink control information may include one of the following methods: max-min normalization, z-score standardization, log function normalization, arctangent function normalization, L2-norm normalization, and the like. The benefit of normalizing or standardizing the CSI is to confine the data to a fixed range, thereby eliminating the adverse effects of singular samples on the data as a whole, thereby reducing the loss of neural network model performance. Taking CSI being an estimated raw channel matrix as an example: the UE first Fourier transforms the channel state information to obtain the delay-domain channel state information; then, the UE sets a threshold for redundancy and zeros out symbols in the delay-domain channel state information lower than the threshold for redundancy; Finally, the UE performs max-min normalization on the channel state information after redundancy processing. In this example, through signal processing and redundancy processing, the UE has compressed the time-domain redundant information in the source sequence, thereby reducing the amount of information that needs to be transmitted. In this example, through the max-min normalization process, the UE confines the compressed data within a fixed range, thereby eliminating the adverse effects of singular samples on the data as a whole, and thus eliminating the loss of neural network model performance.

[0262] In some examples, the "inputting the transformed CSI into a neural network to obtain output of the neural network related to complex-valued information" by the UE may further include combining configuration information related to uplink control information with the structure-transformed CSI and inputting the same into the neural network to obtain output of the neural network related to complex-valued information. Wherein the configuration information related to uplink control information may include at least one of the following: a number, an SINR, an SINR section, an SINR upper bound, an SINR lower bound, the number of time-frequency resources, location of time-frequency resources. Combining the configuration information related to uplink control information with the CSI may include one of the following methods: directly concatenating the configuration information related to uplink control information with the CSI, encoding the configuration information related to uplink control information as a location of the CSI. The advantage of combining the configuration information related to uplink control information with the CSI is that the complex-valued information output by the neural network model is associated with the configuration information of uplink control information.

[0263] Embodiment 4

[0264] In some examples, the method for the UE obtaining matched complex-valued information may further include the UE matching output to resource units in the order of priority according to priority of output of the neural network model, to obtain matched complex-valued symbols information with priorities. Wherein the priority of output of the neural network model comprises priority weights for each output neuron in the neural network. The method of matching the output to the number of resource units sequentially in the order of priority may include: the UE writing the complex-valued information into a circular buffer in the order of ordering weights from large to small or from small to large according to priority weights of output neurons associated with complex symbols in the complex-valued information, wherein the circular buffer has a length equal to the number of complex symbols in the complex-valued information; The UE reads the complex symbols from the circular buffer according to the configured method to obtain the matched complex value information. Wherein the configured method may include the UE extracting complex symbols from the circular buffer according to the configured starting position and / or reading order to obtain matched complex-valued information. Wherein the number of complex-valued symbols included in the matched complex-valued information is the same as the number of time-frequency resource units associated with reporting the uplink control information. Wherein the starting position, reading order, the number of resource units may be obtained based on configuration information.

[0265] In some examples, in a UE extracting complex symbols from a circular buffer according to the configured starting position and / or reading order, a method of determining the starting position and the reading order may include determining, by the UE, the starting position and the reading order for extracting the complex symbols from the circular buffer by comparing a length of the complex-valued information to the number of resource units and according to priority of the complex symbols in the complex-valued information. For example, if the length of the complex-valued information is less than the number of resource units and the priority of the complex symbols in the circular buffer decreases with position, the UE extracts the complex symbols by extracting the complex symbols from the circular buffer in a forward order by a method of repetition; If the length of complex-valued information is less than the number of resource units and the priority of the complex symbols in the circular buffer increases with position, the UE extracts the complex symbols by extracting the complex symbols from the circular buffer in reverse order by a method of repetition; If the length of complex-valued information is greater than the number of resource units and the priority of the complex symbols in the circular buffer decreases with position, the UE extracts the complex symbols by extracting the complex symbols from the circular buffer by a method of shortening; If the length of complex-valued information is greater than the length of the number of resource units and the priority of the complex symbols in the circular buffer increases with position, the UE extracts the complex symbols by extracting the complex symbols from the circular buffer by a method of puncturing.

[0266] For example, the UE determines a neural network modelzthrough the related configuration information, and obtains complex-valued information of length N through the neural network modelzand uplink control information, complex symbols in the obtained complex-valued information being arranged in priority from large to small. Meanwhile, the UE determines that the number of resource units is E through the related configuration information, and N > E. Based on the above information, the UE determines to implement rate matching by extracting complex symbols from the circular buffer by a method of shortening.

[0267] In some examples, the method of obtaining the matched complex-valued information by the UE may further comprise: based on indexes of output of the neural network model, the UE sequentially matches the output with time-frequency resource units associated with reporting the uplink control information in the order of the indexes to obtain the matched complex-valued information related to the indexes. Wherein the method of sequentially matching the output with the number of resource units in the order of the indexes may comprise: the UE writing the complex-valued information into a circular buffer in the order of the indexes being arranged from large to small or from small to large, according to the indexes of the output neurons associated with the complex symbols in the complex-valued information, wherein the circular buffer has a length equal to the number of complex symbols in the complex-valued information; The UE reading the complex symbols from the circular buffer according to the configured method to obtain the matched complex-valued information.

[0268] In some examples, prior to the UE mapping the complex-valued information onto an uplink channel or signal, it further comprises: multiplexing, by the UE, the uplink channel or signal to carry second uplink control information having a different priority, to obtain multiplexed complex-valued information; determining, by the UE, a starting position and a reading order of extracting the complex symbols from the circular buffer by comparing the length of the complex-valued information with the number of resource units and according to priorities of the complex symbols in the complex-valued information, and obtaining multiplexed and matched complex-valued information through the circular buffer. The method of multiplexing may include obtaining multiplexed complex-valued information based on complex-valued information associated with the first uplink control information and complex-valued information associated with the second uplink control information. The method of obtaining the multiplexed complex-valued information based on the first complex-valued information and the second complex-valued information may include determining, by the UE, priority relation of the first and second uplink control information and combining the first complex-valued information with the second complex-valued information according to the priority relation. For example, if the priority of the complex symbols of the first complex-valued information decreases with position, a second complex-valued information sequence having a higher priority is connected with the starting complex symbol of the first complex-valued information, and a second complex-valued information sequence having a lower priority is connected with the last complex symbol of the first complex-valued information; If the priority of the complex symbols in the first complex-valued information increases with position, the second complex-valued information having a higher priority is connected to the last complex symbol of the first complex-valued information, and the second complex-valued information having a lower priority is connected to the starting complex symbol of the first complex-valued information. The advantage of performing the combining of the first complex-valued information with the second complex-valued information in this way is that it is possible to avoid losing high-priority information sequences in rate matching, thereby guaranteeing the effectiveness of the information obtained at the receiving side.

[0269] Taking the example in which the first complex-valued information includes the CSI and the second complex-valued information includes the scheduling request, the UE obtains the first complex-valued information based on the CSI without bit sequence generation and channel coding, and the UE obtains the second complex-valued information based on the bit sequence of the second uplink control information obtained through the process of bit sequence generation and channel coding. Then, the UE determines that the priority of the complex symbols in the first complex-valued information decreases with position, and determines that the priority of the second complex-valued information is higher than the first complex-valued information, so the UE connects the second complex-valued information with the starting complex symbol of the first complex-valued information to obtain multiplexed complex-valued information. With the length of the multiplexed complex-valued information being N, the UE determines that the number of resource units is E through configuration, and N > E, complex symbols in the multiplexed complex-valued information are arranged with priorities from large to small, and the UE determines to perform rate matching through a method of shortening. For example, the UE sequentially stores the complex symbols in the multiplexed complex-valued information in the circular buffer, extracts the complex symbols in order, starting with the first complex symbol in the circular buffer, until the number of complex symbols equal to the number of resource units is obtained.

[0270] In some examples, the neural network model that is used by the UE for obtaining the complex-valued information of CSI and of which the output has priority may include an encoder portion in an autoencoder. Where the autoencoder includes three portions, an encoder, a channel network, and a decoder, each portion of the autoencoders may include a neural network of no less than one layer. Where the input to the encoder is CSI and the output is complex-valued information with priority. Wherein the method for obtaining the encoder is modifying the output of the encoder portions according to priority during training of the autoencoder to obtain complex-valued information with some of the complex-valued symbols lost. Wherein the complex-valued information with some of the complex-valued symbols lost may include zeroing the symbol in the lost position or replacing the symbol in the lost position with a random number.

[0271] Wherein the method of determining the position and number of partial complex-valued symbols that are lost may comprise matching a loss probability for each output neuron of the encoder portion, for each output, determining whether to lose the complex-valued symbol to which the output corresponds according to the matched loss probability. For example, a method for determining whether a loss is made is to generate a random number for each output neuron, and to determine whether a loss is made by comparing the random number and the loss probability. For example, the loss probability of each output neuron is ranked from large to small according to the priority of the output neuron. In the training process, the above method of determining the position and number of partial complex-valued symbols to loss and performing loss may comprise adding a drop-out function after each output neuron of the encoder portion and setting a weight of the drop-out function according to the loss probability.

[0272] Wherein the method of determining the position and number of the partial complex-valued symbols to loss may further comprise ranking the complex-valued symbols according to the priorities of the output neurons to generate a random number of complex-valued symbols to loss, and sequentially discarding the ranked complex-valued symbols in order of priority from small to large to generate the number.

[0273] FIG. 25 shows a schematic diagram of a PUCCH procedure (which may be called an Enhanced Joint source and channel coding based - PUCCH (EJ-PUCCH) procedure) and a first PUCCH procedure according to at least one embodiment of the present disclosure.

[0274] The PUCCH procedure in some examples of this disclosure may also be called EJ-PUCCH. As shown in FIG. 25, the EJ-PUCCH procedure does not include separate CSI compression, channel coding and modulation modules. Wherein, JSCM module is included and responsible for generating complex-valued modulation symbols. In EJ-PUCCH procedure, symbol-level multiplexing, rate matching and interleaving are included after JSCM module. One straightforward approach to enable EJ-PUCCH is to retain the mechanism of these three modules from the legacy PUCCH, simply adapting the objective from bits to symbols. However, reusing the existing principles may not fully exploit the potential of JSCM, and more tailored designs of EJ-PUCCH to optimize JSCM are anticipated. Additionally, a reverse procedure is necessary in the receiver side, and corresponding UE capability reporting, model scheduling, model monitoring, and a robust fallback mechanism may be included for ensuring the reliability of the system.

[0275] FIG. 26 shows a method for implementing the training of the JSCM model according to at least one embodiment of the present disclosure.

[0276] In some examples, the JSCM model can be used to directly generate complex-valued modulation symbols, so the quantizer and de-quantizer are omitted. The CSI is fed forward into the encoder on the UE side, producing a set of floating numbers. These floating numbers are then combined to form the complex-valued modulation symbols. After passing through the channel, the BS receives the complex-valued modulation symbols and decomposes them back into floating numbers, which are then passed to the decoder for CSI reconstruction. Among them, the JSCM model is implemented using the network architecture of Transformer.

[0277] In some examples, during the training phase, three additional functions are incorporated between the encoder and decoder, which are imperfection emulation module, noisy channel emulation module, and prioritized noise emulation module. The imperfection emulation module multiplex a noise to the output of the encoder to make the AI model to learn to handle the errors of channel estimation and RF imperfections. This noise is obtained by a Rician distribution, where its mean may be equal to one and its variance may be an negative value proportional to the SNR. This design targets on the emulation of the channel estimation error that is negatively coherent with the SNR.

[0278] In some examples, after the imperfection emulation module, a noisy channel emulation module may be added to imitate the uplink channel experienced by PUCCH. This allows the model to learn how to handle channel distortion caused by additive white Gaussian noise (AWGN). The AWGN is considered in this position due to the fact that fading is eliminated at most by the equalization and the remained error is handled by the imperfection emulation module.

[0279] In some examples, after the noisy channel emulation module, the prioritized noise emulation module is incorporated to teach the model to prioritize outputs by adding customized Gaussian noise to each output neuron of the encoder, weighted by its likelihood of being punctured or repeated during rate-matching. Symbols with a higher chance of being punctured receive a larger weight. During passing this module, each floating number in the set is added with a Gaussian noise multiplexing with its prioritized weight. By doing so, we obtain a JSCM model whose output neurons have customized priorities, ensuring that complex-valued modulation symbols likely to be punctured carry less important information. Accordingly, the downlink CSI is fed forward sequentially through the encoder, imperfection emulation module, noisy channel emulation module, prioritized noise emulation module, and decoder, and then the weights are updated in the direction of minimizing the loss of NMSE and GCS.

[0280] In some examples, the "imperfection emulation module" may also be implemented by simulating residual fading and radio frequency imperfection from channel estimation errors. The residual fading may be obtained by the following formula:

[0281]

[0282] where, sPUCCH,RSis the signal before the imperfection emulation module, may be a vector obtained by a sine function, and the step size of the sine function may be related to the number of paths of the channel. βCEmay be a constant, representing the residual channel fading degree obtained according to the channel estimation capability, and nRSmay be obtained from a Gaussian distribution, representing the noise intensity on the reference signal. Among them, radio frequency imperfection may be simulated by a radio frequency power amplifier model. For example, the radio frequency power amplifier model may be the Rapp radio frequency amplifier model, which is expressed as:

[0283]

[0284] Where G, VSAT, and p are the parameters of the power amplifier, which may be fixed values or obtained from a random distribution. For example, the parameters may be obtained from the Gaussian distribution, and the mean values of Gaussian distributions corresponding to G, VSAT, and p are equal to 31.6228, 79.339 and 3 respectively, and the variances are equal to 1, 2 and 0.2 respectively. ΓFFT() and ΓIFFT() respectively represent fast Fourier transform and inverse fast Fourier transform. Among them, may also be obtained by the signal which has undergone residual fading, and the specific formula is as follows:

[0285]

[0286] In some examples, the noisy channel emulation module and the noisy channel emulation module with priority may also be jointly implemented, and the specific method is as follows:

[0287]

[0288] Where α is a configurable constant related to the influence degree of rate matching, βpis a vector with multiple probabilities in the same dimension as sPUCCH,RSto represent the priority weight of elements in sPUCCH,RS, and n is a vector with noise in the same dimension as sPUCCH,RS, and each noise value may be obtained by Gaussian distribution.

[0289] In some examples, the noisy channel emulation module and the noisy channel emulation module with priority may also be implemented on the basis of the signals passed through the imperfection emulation module, and the specific implementation method is as follows:

[0290] .

[0291] It will be appreciated that the above methods described in embodiments of the present disclosure are equally applicable to other sources, such as image signals, speech signals, video signals, sampled analog signals, source encoded images, speech or video signals, and the like, as sources.

[0292] FIG. 27 illustrates a block diagram of a user equipment 2500 in accordance with at least one embodiment of the present disclosure. Referring to FIG. 27, the user equipment 2500 includes a transceiver 2501 and a controller 2502. The transceiver 2501 is configured to transmit data or signals and to receive data or signals. The controller 2502 is coupled with the transceiver 2501, and configured to perform control such that the user equipment 2500 performs a method according to an embodiment of the present disclosure. In an implementation, the user equipment 2500 may further include a memory (not shown) having stored thereon computer-executable instructions that, when executed by the controller 2502, may perform at least one method according to the above-described embodiments of the present disclosure.

[0293] FIG. 28 is a block diagram illustrating a base station 2600 in accordance with at least one embodiment of the present disclosure. Referring to FIG. 28, the base station 2600 includes a transceiver 2601 and a controller 2602. The transceiver 2601 is configured to transmit data or signals and to receive data or signals. The controller 2602 is coupled with the transceiver 2601 and configured to perform control such that the base station 2600 performs a method according to an embodiment of the present disclosure. In an implementation, the base station 2600 may further include a memory (not shown) having stored thereon computer-executable instructions that, when executed by the controller 2602, may perform at least one method according to the above-described embodiments of the present disclosure.

[0294] While the present invention has been particularly shown and described with reference to the accompanying drawings, it is to be understood that various modifications and variations can be made therein without departing from the spirit and scope of the invention as defined by the appended claims.

[0295] Those skilled in the art will appreciate that the present invention includes apparatus for performing one or more of the operations described herein. These devices may be specially designed and manufactured for the desired purpose, or may include known devices in general purpose computers. These devices have a computer program stored therein which is selectively activated or reconfigurable. Such a computer program may be stored in a device (e.g., a computer) readable medium including, but not limited to, any type of disk including floppy disks, hard disks, optical disks, CD-ROMs, and magnetic-optical disks, ROM (Read-Only Memory), RAM (Random Access Memory), EPROM (Erasable Programmable Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), flash memory, magnetic cards, or optical cards or in any type of media suitable for storing electronic instructions, and respectively coupled to a bus. That is, the readable medium includes any medium that can store or transmit information in a form that can be read by a device (e.g., a computer).

[0296] It will be understood by those of skill in the art that each block of the structure diagrams and / or block diagrams and / or flow diagrams, and combinations of blocks in the structure diagrams and / or block diagrams and / or flow diagrams, can be implemented by computer program instructions. Those skilled in the art can understand that these computer program instructions can be provided to a processor of a general-purpose computer, a specialized computer, or other programmable data processing methods to be implemented, so that the schemes specified in the block or blocks of the structure diagrams and / or block diagrams and / or flow diagrams disclosed in the present invention are executed by the processor of the computer or other programmable data processing methods.

[0297] It will be appreciated by those skilled in the art that various operations, methods, steps in processes, measures, schemes that have been discussed in the present invention may be alternated, altered, combined, or deleted. Further, other steps, measures, schemes of the various operations, methods, processes, processes that have been discussed in the present invention may also be alternated, altered, rearranged, disassembled, combined, or deleted. Further, steps, measures, schemes of various operations, methods, processes and processes disclosed in the present invention may also be alternated, modified, rearranged, broken down, combined or deleted.

[0298] While the foregoing is merely a partial implementation of the present invention, it will be appreciated by those skilled in the art that numerous modifications and adaptations may be made without departing from the principles of the present invention, and that such modifications and adaptations are to be considered as being within the scope of the present invention.

Claims

1.A method performed by a user equipment (UE) in a communication system, comprising:determining a first processing method of a plurality of methods of obtaining complex-valued information associated with channel state information (CSI), wherein the plurality of methods comprises:a first method of obtaining complex-valued information based on a bit sequence, wherein the bit sequence is obtained through a process of bit sequence generation and channel coding on CSI, and,a second method of obtaining complex-valued information based on CSI, wherein the CSI is not subjected to bit sequence generation and channel coding;processing CSI based on the first processing method to obtain complex-valued information associated with the CSI;transmitting an uplink channel or signal based on the complex-valued information.2.The method of claim 1, wherein transmitting an uplink channel or signal based on the complex-valued information comprises:mapping the complex-valued information onto the uplink channel or signal and transmitting the same.3.The method of claim 1, further comprising receiving higher layer signaling including first information, the first information including at least one of:information related to the first processing method;information of at least one set of parameters associated with the second method;the method further comprises receiving physical layer signaling including second information of one set of parameters of the at least one set of parameters.4.The method of claim 3, wherein the first information includes at least one of an index, a name, a table of at least one set of parameters associated with the second method.5.The method of claim 3, wherein the second information comprises information associated with at least one of an index, a name, a modulation order, a signal-to-noise ratio (SNR), a signal-to-interference-plus-noise ratio (SINR), an SINR section, an SINR upper bound, an SINR lower bound, an output type, an output length, an output format corresponding to the one set of parameters.6.The method of claim 3, wherein the second method comprises a method based on neural network model, the method further comprising determining, based on the second information, a set of parameters of the neural network, wherein the set of parameters comprises at least one of a type of the model, a structure of the model, a number of layers of the model, a number of neurons of the model, an activation function of the model, an input length equal to a number of elements in the channel state information, an output format of the model, weights of the model.7.The method of claim 6, wherein the output format of the model further comprises at least one of: data format of the output, data structure of the output, a number of output elements, priority of the output elements, indexes of the output elements.8.The method of claim 1, wherein the method further comprises: before the UE maps the complex-valued information associated with the CSI onto an uplink channel or signal, the UE multiplexes the uplink channel or signal to carry the complex-valued information associated with the second uplink control information;wherein the method of multiplexing comprises combining and mapping the complex-valued information associated with the CSI and the complex-valued information associated with the second uplink control information onto an uplink channel or signal;wherein the complex-valued information associated with the second uplink control information is obtained by one of the following methods:a third method of obtaining complex-valued information based on a bit sequence obtained by performing bit sequence generation and channel coding on second uplink control information, and a fourth method of obtaining complex-valued information based on second uplink control information, wherein the second uplink control information is not subjected to bit sequence generation and channel coding.9.The method of claim 7, further comprising: before the UE maps the complex-valued information associated with the CSI onto an uplink channel or signal, obtaining, by the UE, matched complex-valued information based on the complex-valued information and the number of time-frequency resource units associated with reporting the CSI, wherein the number of complex-valued symbols included in the matched complex-valued information is the same as the number of time-frequency resource units associated with reporting the CSI.10.The method according to claim 9, the obtaining matched complex-valued information comprising: matching, by the UE, output elements of the neural network model in sequence with time-frequency resource units associated with reporting CSI in order of priority from large to small according to priorities of the output elements, to obtain a sequence of matched complex-valued symbols with priorities.11.The method according to claim 9, the obtaining of the matched complex-valued information further comprises: matching, by the UE, according to indexes of output elements of the neural network model, the output elements with the time-frequency resource units associated with reporting CSI in order of the indexes, to obtain a sequence of matched complex-valued symbols related to the indexes.12.The method of claim 1, further comprising: determining the first processing method of a plurality of methods of obtaining complex-valued information associated with the CSI based on the content and / or format of the uplink control information.13.A method performed by a base station in a communication system, comprising:transmitting, to a UE, high layer signaling including first information, the first information including at least one of: related information of a first processing method, information of at least one set of parameters associated with a second method;transmit, to the UE, physical layer signaling including second information of one set of parameters of the at least one set of parameters,wherein the first processing method is one of a plurality of methods of obtaining complex-valued information associated with CSI, wherein the plurality of methods comprises:a first method of obtaining complex-valued information based on a bit sequence, wherein the bit sequence is obtained through a process of bit sequence generation and channel coding on CSI, and,a second method of obtaining complex-valued information based on CSI, wherein the CSI is not subjected to bit sequence generation and channel coding.14.A user equipment (UE) in a communication system, comprising:a transceiver configured to transmit and / or receive a signal;a controller configured to control the UE to perform the method according to any of claims 1-12.15.A base station in a communication system, comprising:a transceiver configured to transmit and / or receive a signal;a controller configured to control the base station to perform the method according to claim 13.

Images