Communication method and device thereof

Abstract

The disclosure relates to a 5G or 6G communication system for supporting a higher data transmission rate. The embodiments of the present disclosure provide a communication method and device thereof. A method performed by a communication node may include: obtaining channel state information on a second resource using a first neural network; obtaining, based on the channel state information, second information using a second neural network; updating the first neural network using the second information.

Description

COMMUNICATION METHOD AND DEVICE THEREOF

[0001] The present disclosure relates to a field of communication technology and specifically, to a communication method performed by a communication node, a communication node and a computer readable storage medium.

[0002] 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.

[0003] 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.

[0004] 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.

[0005] 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.

[0006] 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.

[0007] Furthermore, such development of 5G mobile communication systems will serve as a basis for developing not only new waveforms for providing coverage in terahertz bands of 6G mobile communication technologies, multi-antenna transmission technologies such as Full Dimensional MIMO (FD-MIMO), array antennas and large-scale antennas, metamaterial-based lenses and antennas for improving coverage of terahertz band signals, high-dimensional space multiplexing technology using OAM (Orbital Angular Momentum), and RIS (Reconfigurable Intelligent Surface), but also full-duplex technology for increasing frequency efficiency of 6G mobile communication technologies and improving system networks, AI-based communication technology for implementing system optimization by utilizing satellites and AI (Artificial Intelligence) from the design stage and internalizing end-to-end AI support functions, and next-generation distributed computing technology for implementing services at levels of complexity exceeding the limit of UE operation capability by utilizing ultra-high-performance communication and computing resources.

[0008] 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.

[0009] 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.

[0010] 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).

[0011] 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.

[0012] 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.

[0013] The purpose of the present disclosure is to be able to solve at least one of the technical defects in the existing communication methods to better meet the requirement of communication. In order to achieve this purpose, the technical solutions proposed in the present disclosure are as follows.

[0014] According to a first aspect of the embodiments of the present disclosure, there is provided a method performed by a communication node, the method includes: obtaining channel state information on a second resource using a first neural network; obtaining, based on the channel state information, second information using a second neural network; updating the first neural network using the second information.

[0015] Alternatively, the obtaining of the channel state information on the second resource using the first neural network includes: receiving a first signal on a first resource to obtain first information; obtaining the channel state information on the second resource using the first neural network based on the first information.

[0016] Alternatively, the first information includes at least one of: the first signal on the first resource, the first signal including all signals received on the first resource; a reference signal on the first resource; a second signal after specific processing of the first signal and / or the reference signal; channel state information corresponding to the first resource that is fed back; channel information that is inversely estimated based on received data; a physical resource containing the reference signal; channel state information measurement report information; first related information, the first related information including at least one of: information for indicating a position of the reference signal in the first resource, the reference signal, information related to the first resource and / or the second resource, and characteristic constraint information of a channel in a current network environment.

[0017] Alternatively, the second information includes at least one of: prediction information for data transmission based on the channel state information, the prediction information including at least one of: a probability of successful or failed data transmission, a bit error rate for data transmission, a symbol error rate for data transmission, an error rate for data transmission, and a signal-to-interference ratio resulting from data transmission; error evaluation information for the channel state information, the error evaluation information including at least one of: an estimation error of the channel state information, a quality classification label for the channel state information estimation, a deviation measure between characteristic information of the channel state information and a preset parameter value in the second neural network, and a probability of occurrence of the channel state information in a current network environment.

[0018] Alternatively, the method further includes: obtaining, based on the second information and / or third information related to data transmission, fourth information for assisting the data transmission using a third neural network.

[0019] Alternatively, the third information includes at least one of: a relevant parameter for data transmission, the relevant parameter for the data transmission including at least one of: a modulation method, a coding rate, an available physical resource, a quantity of a data volume to be transmitted in a cache, a quality of service requirement, and a set of pre-coded codebooks; information related to a network environment, the information related to the network environment including at least one of: an interference level of the environment, a degree of environmental change and experience data for a coherent time of the environment.

[0020] Alternatively, the fourth information includes at least one of: data transmission state indication information for indicating whether to use the channel state information for data transmission and / or whether to re-perform a complete channel estimation process and / or whether to update the first neural network based on the second information; recommendation information for a data transmission parameter for indicating the data transmission parameter recommended by the communication node.

[0021] Alternatively, in a case that the communication node is a user equipment, the fourth information is used by the user equipment for at least one of: determining whether to trigger re-performing the complete channel estimation process; reporting the fourth information to a base station as reference information for scheduling data transmission by the base station; wherein whether to trigger re-performing the complete channel estimation process includes at least one of whether to trigger an aperiodic channel state information measurement and reporting, and transmitting information about whether or not to trigger re-performing the complete channel estimation process to the base station.

[0022] Alternatively, in a case that the communication node is a base station, the fourth information is used by the base station for at least one of: determining whether to trigger re-performing the complete channel estimation process; determining whether to use the channel state information for data transmission; determining whether to configure a parameter used for data transmission; wherein the determining of whether to use the channel state information for the data transmission includes determining a resource allocation between user equipments for the data transmission; wherein whether to trigger re-performing the complete channel estimation process includes at least one of whether to trigger an aperiodic channel state information measurement and reporting, and whether to schedule a user equipment to transmit the reference signal.

[0023] Alternatively, the method further includes: obtaining fifth information related to performing data transmission based on the channel state information; updating at least part of parameters of the second neural network using the second information and / or the fifth information.

[0024] Alternatively, the method further includes: obtaining fifth information related to performing data transmission based on the channel state information and / or the third information and / or the fourth information; updating at least part of parameters of the third neural network using the fourth information and / or the fifth information.

[0025] Alternatively, the fifth information includes at least one of the following: feedback information of the data transmission; at least one of a cumulative bit error rate, a cumulative symbol error rate, a cumulative success rate, and a cumulative block success rate with respect to data transmission performed based on the channel state information obtained by the first neural network from a previous channel estimation process.

[0026] Alternatively, the first neural network, the second neural network, and the third neural network are trained jointly, or are trained separately; and / or at least one of the first neural network, the second neural network and the third neural network is updated based on a predetermined time interval, or based on a number of times of output information, or based on triggering a specific event, wherein the specific event includes at least one of prediction information or error evaluation information in the second information exceeding a predetermined threshold, a failure in decoding received data by the communication node, receiving a retransmission command or a parameter update command, receiving a negative confirmation (NACK) information that is fed back.

[0027] Alternatively, the updating of the first neural network using the second information includes: converting the second information into an error amount; back-propagating, according to a back-propagation rule, the error amount layer by layer for each neural network layer included in the first neural network, to obtain an error amount corresponding to a parameter in each of the neural network layers; calculating, using an optimization algorithm, an update amount of the parameter based on the error amount corresponding to the parameter, and updating the parameter.

[0028] Alternatively, the first resource includes the second resource, or the second resource includes the first resource, or the first resource and the second resource include at least part of identical resources, or the first resource and the second resource do not include identical resources.

[0029] According to a second aspect of the embodiments of the present disclosure, there is provided a communication node, which may include a transceiver; and a processor, coupled to the transceiver and configured to perform the above communication method performed by the communication node.

[0030] According to a third aspect of the embodiments of the present disclosure, there is provided an electronic device, including: at least one processor; and at least one memory storing computer-executable instructions, wherein the computer-executable instructions, when run by the at least one processor, cause the at least one processor to perform the communication method as described above.

[0031] According to a fourth aspect of the embodiments of the present disclosure, there is provided a computer-readable storage medium storing instructions, wherein the instructions, when run by at least one processor, cause the at least one processor to perform the communication method as described above.

[0032] The technical solutions provided by the embodiments of the present disclosure brings at least the following beneficial effects:

[0033] The parameters of the first neural network may be trained and updated online to avoid the decreased accuracy in acquiring the channel state information caused by changes in the external environment.

[0034] The beneficial effects brought by the technical solutions provided by the embodiments of the present disclosure will be described later in connection with specific optional embodiments, or may be known from the description of the embodiments, or may be learned from the implementation of the embodiments.

[0035] In order to more clearly and easily illustrate and understand the technical solutions in the embodiments of the present disclosure, the following is a brief description of the accompanying drawings that need to be used in the description of the embodiments of the present disclosure.

[0036] FIG. 1 illustrates an example wireless network according to embodiments of the present disclosure;

[0037] FIG. 2 illustrates an example base station according to embodiments of the present disclosure;

[0038] FIG. 3 illustrates an example user equipment according to embodiments of the present disclosure;

[0039] FIG. 4 illustrates a schematic diagram of SRS resource configuration using two antenna ports;

[0040] FIG. 5 is a flowchart of a method performed by a communication node according to an embodiment of the present disclosure;

[0041] FIG. 6 is a flowchart of a method performed by a communication node according to another embodiment of the present disclosure;

[0042] FIG. 7 is a flowchart of a method for online updating of a second neural network according to an embodiment of the present disclosure;

[0043] FIG. 8 is a flowchart of a method for online updating of a third neural network according to an embodiment of the present disclosure;

[0044] FIG. 9 illustrates a schematic structure of a first neural network according to an embodiment of the present disclosure;

[0045] FIG. 10 illustrates a schematic structure of a second neural network according to an embodiment of the present disclosure;

[0046] FIG. 11 illustrates a schematic structure of a third neural network according to an embodiment of the present disclosure;

[0047] FIG. 12 illustrates a schematic structure of a neural network unit according to an embodiment of the present disclosure;

[0048] FIG. 13 illustrates a block diagram of a network node in a communication system provided by an embodiment of the present disclosure.

[0049] 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.

[0050] 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.

[0051] 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.

[0052] 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.

[0053] FIGS. 1-3 below describe various embodiments of the present disclosure implemented in wireless communications systems. The descriptions of FIGS. 1-3 are not meant to imply physical or architectural limitations to the manner in which different embodiments may be implemented. Different embodiments of the present disclosure may be implemented in any suitably-arranged communications system.

[0054] 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.

[0055] 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.

[0056] 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.

[0057] 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).

[0058] 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.

[0059] 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.

[0060] 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.

[0061] 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.

[0062] 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.

[0063] 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.

[0064] 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.

[0065] 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.

[0066] 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.

[0067] 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.

[0068] 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.

[0069] 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).

[0070] 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.

[0071] 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.

[0072] 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.

[0073] 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).

[0074] 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.

[0075] 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.

[0076] The processor 307 is also capable of executing other processes and programs resident in the memory 311, such as processes for CSI reporting on uplink channel. The processor 307 can move data into or out of the memory 311 as required by an executing process. In some embodiments, the processor 307 is configured to execute the applications 313 based on the OS 312 or in response to signals received from gNBs or an operator. The processor 307 is also coupled to the I / O interface 308, which provides the UE 116 with the ability to connect to other devices, such as laptop computers and handheld computers. The I / O interface 308 is the communication path between these accessories and the processor 307.

[0077] 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.

[0078] 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.

[0079] 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.

[0080] One of the main means to ensure the communication rate and reliability in the current wireless communication systems is to process a signal or adjust a sending and receiving strategy by channel state information (CSI) between two nodes that transfer information (the two nodes acting as a sender and a receiver respectively, or acting as both the sender and the receiver). For example, a node (e.g., the gNB shown in FIG. 2), before transmitting a signal, pre-codes the transmit signal and adjusts a power and a modulation coding method of the transmit signal based on its known channel state information, and a node (e.g., the UE shown in FIG. 3), after receiving a signal, performs channel equalization of the receive signal and selects a different transmit / receive beam, etc. based on its known channel state information, so as to eliminate the effect of the channel on the signal as much as possible. As an example and not as a limitation, the channel state information may be at least one of a channel response, a reference signal receive power(RSRP), a signal to interference and noise ratio(SINR), a channel quality indicator (CQI), a precoding matrix indicator, a layer indicator (LI), a rank indicator (RI), a resource indicator (RI).

[0081] The current prosperity and development in smart mobile devices and related applications have stimulated the user demands for faster and lower latency wireless communications. These demands have led to the evolution of wireless communication networks towards wider bandwidths and more antennas, and accordingly, the resources required for acquiring the wireless channel state information and the difficulty in acquiring such information have also increased. In order to further improve the spectral efficiency of wireless communication systems, both industry and academia have identified the efficient acquisition and utilization of the channel state information as one of the key challenges for future wireless communication systems.

[0082] In existing wireless communication systems, for the aforementioned methods of ensuring the communication quality by eliminating the effect of the channel on the signal, the receiving node and / or the transmitting node needs to be informed of the channel state information of each antenna used for transmitting at any time point and any frequency point of information transmission. Generally, the channel state information described in the present disclosure is a combined effect of an entire wireless communication link on an amplitude and phase of a signal over all physical resources occupied / used for its transmission. Herein, the physical resources are resource entities in the communication systems that can be used for signal transmission (e.g., a demodulation reference signal (DM-RS), a channel state information reference signal (CSI-RS), a sounding reference signal (SRS)), for example, the resource entity may be a time domain physical resource, a frequency domain physical resource, and an antenna domain physical resource, and so on. Generally, the antenna described in the present disclosure is a generalized antenna characterizing a space resource occupied by the signal transmission. The antenna domain physical resource may be a physical antenna element, an antenna array including a plurality of physical antenna elements, a beam, an antenna port, or a precoding matrix at a transmitting end, etc.; and the time point characterizes the time domain physical resource occupied by the signal transmission, and may be a period of time with a minimum granularity of a time unit, wherein the time unit has a predetermined length of time, wherein the time unit may be a radio frame, a sub-frame, a slot, a subslot, or a symbol. By way of example only and not as a limitation, for example, the time point may be a slot consisting of 14 OFDM symbols (the time unit is an OFDM symbol); the frequency point characterizes the frequency domain resource occupied by the signal transmission, and is a frequency range with a minimum granularity of a frequency unit, wherein the frequency unit has a predetermined spectral width, which may be a sub-band, a bandwidth part (BWP), a resource block, a physical resource block (PRB), or a subcarrier, etc., as an example and not as a limitation, e.g., in the LTE and NR, a frequency point may be composed of 12 subcarriers spaced at 15 kHz (the frequency unit is the subcarrier) spaced at 15 kHz.

[0083] Typically, the transmission of information (e.g., a Physical Downlink Control CHannel (PDCCH), a Physical Downlink Shared CHannel (PDSCH), a Physical Uplink Shared CHannel (PUSCH), a Physical Uplink Control Channel (PUCCH), etc.) may occur on more than one physical resource (e.g., multiple time points, multiple frequency points, multiple antennas, and various combinations of the above time, frequency, and antennas). In existing wireless communication systems, a method for obtaining channel state information between two nodes is to send a reference signal (RS) by selecting a portion of physical resources that can be used for information transmission between the two nodes in a certain rule, and estimating the wireless channel state information accordingly. The wireless communication system may send a non-reference signal (e.g., a data signal and / or a control signal) on the remaining available physical resources at the same time. The reference signal is a sequence generated based on a particular rule and parameter, whose content (such as the rule and parameter used, and what kind of reference signal) and the physical resource where the reference signal is sent (i.e., the physical resource used for transmitting the reference signal) are shared by the two nodes. The reference signal can also be called a pilot signal, a training signal, etc.

[0084] The most widely used wireless communication systems are cellular communication systems based on the 3rd Generation Partnership Project (3GPP) protocol, for example, 4G communication systems such as Long Term Evolution (LTE), advanced LTE (LTE-Advanced, LTE-A), and 5G communication systems such as NR. In the LTE-A and NR systems, the channel state information may be obtained by a transmitted channel state information reference signal, a sounding reference signal (SRS), or a demodulation reference signal. Specifically, taking the SRS as an example, before sending the SRS, the base station first determines a first resource (i.e., a physical resource occupied by the SRS) and a second resource (i.e., a physical resource on which the channel state information needs to be acquired) and configures the SRS by control information, and then informs the user equipment / terminal of the configuration information (e.g., positions of time domain and frequency domain and antenna physical resources that may be included in the first and the second resources as well as relevant parameters required for generating the reference signal, etc.). Depending on the application scenario, the communication system determines the pattern and density of the first resource according to the trend of the channel scenario. For example, in the NR, a sub-band or a bandwidth part in the frequency domain needs to be configured with at least a portion of subcarriers in a resource block (RB) for placing the SRS corresponding to an antenna port, and it is guaranteed that at least one subcarrier for each antenna port is configured for placing the SRS. If the system is configured with multiple RBs, the SRSs for different antenna ports may also be placed on different RBs. In the time domain, the communication system periodically or aperiodically configures a slot where the SRS needs to be placed by taking the slot as the minimum unit. FIG. 4 illustrates a schematic diagram of SRS resource configuration using two antenna ports (i.e., an antenna port 1 and an antenna port 2) in the 3GPP NR protocol. As shown in FIG. 4, an RB consists of 12 subcarriers in the frequency domain and a slot consists of 14 OFDM symbols in the time domain. In this schematic diagram, a SRS 1, which uses the antenna port 1, occupies the 10th to 13th OFDM symbols in the time domain and the 1st, 3rd, 5th, 7th, 9th, and 11th subcarriers in the frequency domain; and a SRS 2 occupies the same 10th to 13th OFDM symbols in the time domain and the 2nd, 4th, 6th, 8th, 10th, and 12th subcarriers in the frequency domain. After determining information such as the first resource and the second resource of the SRS, the terminal may send the reference signal on the first resource, and the base station may, based on the reference signal received on the first resource, obtain the channel state information on the second resource by interpolation / prediction methods (e.g., a least square (LS) algorithm, a linear minimum meansquare error (LMMSE) algorithm). In some cases, the base station also needs to transmit the channel state information obtained by itself to the terminal through a SRS resource indicator (SRI) in the control information, so as to enable the terminal to obtain the necessary channel information for communication. For some other reference signals, such as the CSI-RS, the base station and the terminal conduct behavior exchange and repeat the above steps so that the two parties obtain the required channel state information.

[0085] However, the above method of obtaining the channel state information needs to be further improved.

[0086] In existing systems for obtaining the channel state information through a neural network, various parameters of the neural network are obtained by training based on a large amount of sample data. The acquisition of these sample data by the communication node incurs a large amount of additional overhead. For example, in order to obtain the real channel state information for training the neural network by the sender, the receiver needs to transmit the complete real channel state information to the sender via physical resources. In order to avoid incurring the additional overhead, neural networks in the system are all acquired through offline training before the system is deployed. After the actual deployment of the system, the parameters of the neural networks will not be changed anymore. However, the actual environment may change over time, resulting in a decrease in the accuracy of the channel state information acquired by the system, which in turn affects the reliability of uplink / downlink transmission.

[0087] The present disclosure proposes a neural network-based method for obtaining channel state information, which can realize online training and updating of parameters of the neural network, and avoid the decrease in the accuracy of obtaining the channel state information due to changes in the external environment. Meanwhile, the online updating process in the method of the present disclosure does not need to measure a target channel to obtain the channel state information, which effectively reduces the overhead of reference signal transmission and channel state information feedback. The method may be simultaneously applicable to various communication nodes of network, such as a base station and a terminal.

[0088] In the present disclosure, the communication node may be a base station, for example, a macro base station, a micro base station, a pico base station, a flying base station, a backhaul base station for unlimited backhaul, and a base station that integrates both access and backhaul functions, etc.; the communication node may also be a user equipment, for example, a cell phone, a laptop, a tablet, a smartwatch and the like that have wireless access functions.

[0089] FIG. 5 is a flowchart of a method performed by a communication node according to an embodiment of the present disclosure.

[0090] Referring to FIG. 5, at step S501, channel state information on a second resource may be obtained using a first neural network.

[0091] At step S502, based on the channel state information, second information related to the channel state information may be obtained using a second neural network. For example, the second information may be obtained by the second neural network based on the channel state information and second related information.

[0092] At step S503, the first neural network may be updated using the second information. According to the method illustrated as in FIG. 5, it is possible to accurately obtain the channel state information, thereby solving the problem that the wireless channel has complex and variable characteristics in the time, frequency, and spatial domains.

[0093] In some examples, the first neural network may include a preprocessing unit, a pre-trained neural network, etc., or the first neural network may include only a pre-trained neural network. For example, the first neural network first processes a first signal on a first resource and / or first related information by the preprocessing unit, and then obtains the channel state information on the second resource by the pre-trained neural network based on the processing result, as shown in FIG. 9.

[0094] The first information may include at least one of: the first signal on the first resource, the first signal including all signals received on the first resource; a reference signal on the first resource; a second signal after specific processing of the first signal and / or the reference signal; channel state information corresponding to the first resource that is fed back; channel information that is inversely estimated based on received data; a physical resource containing the reference signal; channel state information measurement report information; first related information, the first related information including at least one of information for indicating a position of the reference signal in the first resource, the reference signal, information related to the first resource and / or the second resource (e.g., a relative position of the second resource to the first resource, a structure of the second resource, etc.), and characteristic constraint information of a channel in a current network environment(e.g., a variance of the channel, a delay expansion, a correlation time). The above first information is only exemplary and the present disclosure is not limited thereto.

[0095] In some examples, where the first neural network is located on the base station side, the above first information may be a SRS signal received by the base station, a DM-RS signal in a PUSCH or PUCCH received by the base station, a CSI measurement report received by the base station. The above first information may also be channel information that is inversely estimated by the base station based on the received data. In other examples, where the first neural network is located on the terminal side, the above first information may be a CSI-RS signal received by the terminal, a DM-RS signal in the PDSCH or PDCCH received by the terminal, a SRI indication from the base station received by the terminal. The above first information may also be channel information that is inversely estimated by the terminal based on the received data.

[0096] In some examples, the first information may be a received first signal on the first resource, or a second signal after specific processing (e.g., denoising, compression, eigenvalue decomposition, etc.) of the first signal (e.g., the first information is a denoised signal obtained by inputting the first signal to a band-pass filter). In some examples, the first information is an eigenvector and eigenvalue obtained, after obtaining an intermediate signal of the first signal by the MMSE algorithm, by eigenvalue decomposition of the intermediate signal. Wherein, the first resource may refer to a physical resource in the communication system that is configured for transmitting the reference signal, and the second resource may refer to a physical resource that the communication node needs to accurately obtain the channel state information, and more specifically, the second resource may include the first resource, the first resource may include the second resource, and the first resource and the second resource may or may not include each other. For example, when the first neural network is located at the base station side, the second resource is a physical resource (such as an RB, an OFDM symbol, an antenna port, etc.) that is indicated by the upper layer to be used by a certain user for transmitting data.

[0097] The resource where the reference signal is located and the resource where the channel state information is located may be different, in this case, the channel state information on the resource without the reference signal may be estimated by the neural network of the present disclosure.

[0098] In some examples, when the first neural network is located on the base station side, the first information may be a sounding reference signal received by the base station, a complete OFDM symbol containing the sounding reference signal received by the base station, and channel state information corresponding to the first resource fed back to the base station by the terminal. Wherein, the channel state information is the combined effect of the entire wireless communication link on the amplitude and phase of the signal over all physical resources (herein, the first resource) occupied for its transmission.

[0099] After obtaining the first information, the first information is input to the pre-trained neural network in the first neural network to obtain the channel state information on the second resource. In some examples, the second resource may be a physical resource corresponding to the channel state information measured and / or reported by the communication node, or a physical resource where the channel state information to be obtained is located. In some examples, the second resource may include the first resource, the first resource may include the second resource, and the first resource and the second resource may not include each other. In some examples, when the first neural network is located on the base station side, the second resource is a physical resource (such as an RB, an OFDM symbol, an antenna port, etc.) that is indicated by the upper layer to be used by a certain user for transmitting data.

[0100] The second information is obtained through the second neural network based on the obtained channel state information. Wherein, the second information may be an evaluation of the channel state information. In some examples, the second neural network may include a preprocessing unit, at least one pre-trained neural network or sub-neural network, and the like. Alternatively, the second neural network may include only pre-trained neural network(s) or sub-neural network(s).

[0101] For example, the second neural network first processes the above channel state information through the preprocessing unit, and then passes the processing result and / or the second related information through each of the pre-trained neural networks in turn to obtain the second information, as shown in FIG. 10. Here, the processing performed by the preprocessing unit may include feature extraction, feature decomposition, covariance processing, and the like. The second related information may include at least one of predetermined threshold information, channel high-order statistics information under a target scenario, the above first information, or the first information after processing (such as compression, feature extraction). Here, the target scenario may refer to a scenario in which the communication node is located, i.e., the second resource is in the target scenario in a physical sense, and the real channel state information is determined by various objects in the target scenario. The real channel state information may also be referred to as target channel state information, which is obtained by estimating a reference signal on the resource on which this channel state information is located. For example, the real / target channel state information for the second resource may be obtained by estimating a reference signal on the second resource.

[0102] The second information may include at least one of: prediction information for data transmission based on the channel state information, the prediction information including at least one of a probability of successful or failed data transmission, a bit error rate for data transmission, a symbol error rate for data transmission, an error rate for data transmission, and a signal-to-interference ratio resulting from data transmission; error evaluation information for the channel state information, the error evaluation information including at least one of an estimation error of the channel state information, a quality classification label for the channel state information estimation, a deviation measure between characteristic information of the channel state information and a preset parameter value in the second neural network, and a probability of occurrence of the channel state information in a current network environment.

[0103] In some examples, the second information may include prediction information (e.g., performance prediction information) for data transmission based on the obtained channel state information, e.g., when the channel state information may include CSI-SINR information on the second resource, the second information may be prediction information for data transmission (e.g., PUSCH, PDSCH, etc.) when determining a modulation and coding method for the data transmission based on the CSI-SINR information; or, when the channel state information may include precoding matrix indicator (PMI) information on the second resource, the second information may be prediction information for data transmission (e.g., PUSCH, PDSCH, etc.)when determining a precoding matrix for the data transmission based on the PMI information. In some specific implementations of the example, the prediction information may be at least one of: a probability of successful or failed data transmission (e.g., a probability of feeding back an ACK by a receiving node when the second neural network is located at a transmitting node); a bit error rate (or, equivalently, a symbol error rate, an error rate) for data transmission (e.g., a ratio of the number of correct bits to the total number of bits, the correct bits being obtained by a channel equalization and adjudication to the received data, when the second neural network is located at the receiving node node); a signal-to-interference ratio resulting from data transmission (e.g., X dB, denoting a ratio of the received signal power of the target user to the sum of the received powers of the non-target users in the system after pre-coding when the second neural network is located at the transmitting node).

[0104] In other examples, the second information may also include an error evaluation of the channel state information output by the first neural network. In some specific implementations of the example, the error evaluation included in the second information may be an estimation error between the channel state information output by the first neural network and the real channel state information, e.g., when the channel state information is a channel vector, the outputted channel state information is noted as and the real channel state information is noted as , then the estimation error may be either (MSE) or (cosine similarity), where denotes a L2 paradigm operation. In some specific implementations of the example, the error evaluation included in the second information may be a quality classification label for the channel state information estimation, i.e., the output channel state information is marked as good when it approximates the real channel information and vice versa. For example, it is noted that the output channel state information is and the real channel state information is , the expected output label y of the second neural network is:

[0105]

[0106] wherein α is a fixed threshold value. In some specific implementations of the example, the error evaluation included in the second information may be a deviation measure between the characteristic information of the output channel state information and a predetermined parameter value in the second neural network. For example, a difference between a high-order statistic (such as a high-order distance, a high-order accumulation, a high-order spectrum, etc.) of the output channel state information and a predetermined parameter; in some specific implementations of the example, the error evaluation included in the second information may be a probability of occurrence of the output channel state information in the current network environment. For example, according to a probability distribution function (e.g., a Gaussian distribution function) predetermined by the system, the probability of occurrence of the output channel state information under the condition of the first information is , where h is the output channel state information and hpreis the first information.

[0107] Each parameter in the first neural network may be updated based on the second information. For example, the second information is first converted into an error amount, then the error amount is back-propagated layer by layer according to a back-propagation rule thereby obtaining an error amount corresponding to a parameter in each of neural network layers in the first neural network, and finally an optimization algorithm is used to compute an update quantity for the parameter based on the error amount of the parameter and the parameter is updated. In some examples, the error amount is generated by calculating a distance between the second information and a predetermined target value, and the distance may be a Euclidean distance, an L1 paradigm, a cross-entropy function, a DL divergence, and the like.

[0108] In one specific implementation of some examples, when the second information is the probability of successful data transmission (denoted as y), the target value may be 1 or 0.95 (denoted as x), i.e., the data transmission is successful with a very high probability, at which point the error amount between the second information and the predetermined target value may be obtained based on the Euclidean distance, i.e., . In another specific implementation of some examples, when the second information is the quality classification label for channel state information estimation (denoted as y), the target value may be 1, i.e., the channel state information output by the first neural network is a good estimation of the real channel state information, at which point the error amount between the second information and the predetermined target value may be obtained based on the cross-entropy function, i.e., . In some examples, the optimization algorithm may be a gradient descent algorithm, a stochastic gradient descent algorithm, a small batch gradient descent algorithm, a momentum gradient descent algorithm, a Nesterov gradient acceleration algorithm, an Adagrad algorithm, an AdaDelta algorithm , an Adam algorithm. Specifically, and by way of example only and not as a limitation, common machine learning training algorithms such as derivative trimming, regularization, model pruning, model quantization, and so forth, may also be optionally used in the process of updating the weights of the network parameters.

[0109] The updating of the parameters of the first neural network may be non-continuous. In some implementations of the example, the updating of the parameters of the first neural network may be periodic, e.g., the first neural network is performed a parameter update every 10 outputs of the channel state information or every 1 ms, wherein the period for performing the network parameter update may be pre-determined based on the coherence time of the scenario and the channel state information estimation accuracy requirement. In other embodiments of the example, the updating of the parameters of the first neural network may be event-based triggered. When the first neural network is located on the terminal side, the triggering event may be that the prediction information or the error evaluation in the second information exceeds a predetermined threshold; the terminal fails in decoding the received data; the terminal receives a retransmission command or a parameter update command scheduled by the base station. When the first neural network is located on the base station side, the triggering event may be that the prediction information or the error evaluation in the second information exceeds a predetermined threshold; the base station fails in decoding the received data; the base station receives a NACK information fed back from the terminal; and a certain event generated by the base station itself.

[0110] In addition, both the first neural network and the second neural network may be jointly and / or independently realized by the same physical entity or different entity units, and the physical entity may include hardware, software, or a combination thereof, which may be configured by a person skilled in the art according to the actual needs, and the combinations thereof may include, but are not limited to: the first neural network and the second neural network are respectively realized by independent entities; the first neural network and the second neural network are realized by the same entity.

[0111] In order to obtain the channel state information, the communication system needs to use a portion of the physical resources for transmitting the reference signal, resulting in a reduction of the physical resources for transmitting the user data, which affects the throughput of the communication system. For example, the SRS in FIG. 4 occupies about 30% of the physical resources in the slot, i.e., the throughput of the communication system is reduced by about 30% as compared to a theoretical upper limit of all physical resources used for transmitting the user data. The present disclosure enables the transmitting node and the receiving node to obtain the channel state information that satisfies accuracy requirements by online updating of the first neural network for estimating the channel state information, which ensures the reliability of uplink / downlink transmissions. (e.g., meeting BER requirements, etc.)

[0112] FIG. 6 is a flowchart of a method performed by a communication node according to another embodiment of the present disclosure.

[0113] Referring to FIG. 6, at step S601, a first signal on a first resource may be received to obtain first information, and channel state information on a second resource is obtained via a first neural network based on the first information. The specific process thereof may be referred to the above description of steps S501 and S502.

[0114] At step S602, second information may be obtained through a second neural network based on the channel state information. Wherein, the second information is an evaluation of the channel state information. The specific process thereof may refer to the above description of step S503.

[0115] At step S603, based on the second information and / or third information related to data transmission, fourth information for assisting the data transmission may be obtained using a third neural network. Wherein the third information is information related to the data transmission and the fourth information is information for assisting the data transmission. In some examples, the third neural network may include a preprocessing unit, at least one pre-trained neural network or sub-neural network, and the like. Alternatively, the third neural network may include only pre-trained neural network(s) or sub-neural network(s). For example, the third neural network first processes the second information and / or the third information described above through the preprocessing unit, and then passes the processing result sequentially through each of the pre-trained neural network structures to obtain the fourth information, as shown in FIG. 11.

[0116] The third information may include at least one of: a relevant parameter for data transmission, the relevant parameter for the data transmission including at least one of: a modulation method, a coding rate, an available physical resource, a quantity of a data volume to be transmitted in a cache, a quality of service requirement, and a set of pre-coded codebooks; information related to a network environment, the information related to the network environment including at least one of: an interference level of the environment, a degree of environmental change and experience data for a coherent time of the environment . The relevant parameter herein may be a parameter for current data transmission, a parameter for historical data transmission or a predicted parameter.

[0117] The fourth information may include at least one of: data transmission state indication information for indicating whether to use the channel state information for data transmission and / or whether to re-perform a complete channel estimation process and / or whether to update the first neural network based on the second information; recommendation information for a data transmission parameter for indicating the data transmission parameter recommended by the communication node. For example, the data transmission state indication information may include channel estimation indication information, indication information for network parameter update, data transmission quality indication information, the channel estimation indication information may be used to indicate whether to re-perform the complete channel estimation process (such as managing aperiodic CSI reporting), the indication information for network parameter update may be used to indicate whether to update the first neural network based on the second information, the data transmission quality indication information may be used to indicate whether to use the channel state information for data transmission (or a level of recommendation for using the channel state information for data output). The data transmission quality indication information may be used to assist the base station in data transmission scheduling. The forms and names of the above information are only exemplary and the present disclosure is not limited thereto.

[0118] According to embodiments, in a case where the communication node is a user equipment, the fourth information is used by the user equipment for at least one of: determining whether to trigger re-performing the complete channel estimation process; reporting the fourth information to a base station as reference information for scheduling data transmission by the base station; wherein whether to trigger re-performing the complete channel estimation process includes at least one of whether to trigger an aperiodic channel state information measurement and reporting, and transmitting information about whether or not to trigger re-performing the complete channel estimation process to the base station.

[0119] According to embodiments, in a case where the communication node is a base station, the fourth information is used by the base station for at least one of: determining whether to trigger re-performing the complete channel estimation process; determining whether to use the channel state information for data transmission; determining whether to configure a parameter used for data transmission; wherein the determining of whether to use the channel state information for the data transmission includes determining a resource allocation between user equipments for the data transmission; wherein whether to trigger re-performing the complete channel estimation process includes at least one of whether to trigger an aperiodic channel state information measurement and reporting, and whether to schedule a user equipment to transmit the reference signal.

[0120] For example, the base station may trigger re-performing the complete channel estimation process (e.g., the base station instructs the terminal to re-transmit the SRS (i.e., uplink channel estimation), and the base station informs the terminal to perform aperiodic CSI measurement and reporting (i.e., downlink channel estimation)). Alternatively, the base station may configure the parameter used for the data transmission based on the recommended parameter in the fourth message. Alternatively, the base station may determine resource allocation among user equipments for data transmission based on the data transmission quality indication information (e.g., the user equipments with good quality share resources and the user equipments with bad quality are not scheduled by the base station for data transmission). Alternatively, the base station may decide, based on the channel estimation indication information, whether to trigger an aperiodic CSI measurement and reporting or scheduling the user to send an SRS signal. Alternatively, the base station may decide to configure the parameters (a modulation order, a coding rate, etc.) to be used by each user equipment that is scheduled for data transmission based on the recommendation information for the data transmission parameter.

[0121] In some examples, the third information may include a relevant parameter for the current data transmission, e.g., a modulation method and a coding rate for the data transmission, an available physical resource, an amount of data volume to be transmitted in a cache, a QoS requirement for the data transmission. In some embodiments of the example, the relevant parameter for the data transmission may be historical, i.e., the relevant parameter used for the data transmission from a certain moment in the past up to the current moment, from which the third neural network may obtain experience information on the parameter configuration of the data transmission. In some embodiments of the example, the relevant parameter for the data transmission may be current, and the third neural network may assess the rationality of the parameter for the current data transmission. In some embodiments of the example, the relevant parameters of the data transmission may be predicted, and the third neural network may assess whether the parameter for the data transmission expected to be used is available and give an instruction in the fourth message to make the communication node prepare accordingly. In other examples, the third information may include information related to the current environment or environment related information, for example, a level of interference in the current environment, whether there is a sudden change in the current environment, experience data for a coherent time of the environment, and the like.

[0122] In some examples, the fourth information may be data transmission state indication information that indicates a recommended behavior of the communication node where the third neural network is located, including whether the channel state information output by the first neural network should be used for data transmission, whether the complete channel estimation process should be re-performed, and whether the first neural network should be updated based on the second information. In some specific implementations of the example, the fourth information includes a degree of recommendation to use the channel state information output by the first neural network for data transmission. For example, when the second information indicates that the cosine similarity between the channel state information and the real channel state information is 0.8, the degree of recommendation given by the fourth information may be 0.75. In the case where the second information indicates that the cosine similarity between the channel state information and the real channel state information is 0.7, the degree of recommendation given by the fourth information may be 0.5 when the third information indicates that the data transmission is to be performed using a higher-order modulation method (e.g., 256 QAM), and the degree of recommendation given by the fourth information may be 0.75 when the third information indicates that the data transmission is to be performed using a lower-order modulation method (such as QPSK). In other specific implementations of the example, the fourth information may be channel estimation indication information, which indicates that the communication node should re-perform the complete channel estimation process. For example, when the second information indicates that the channel state information contains a large estimation error (e.g., cosine similarity less than 0.5), or the third information indicates that the environment in which the communication node is located has changed drastically, the fourth information indicates that the communication node should retransmit the reference signal according to the channel estimation process in the existing protocol for a complete channel estimation. In other specific implementations of the example, the fourth information may be indication information for network parameter update, which indicates that the first neural network should be performed the parameter update. For example, when the second information indicates that the channel estimation quality label of the channel state information output by the first neural network is poor, the fourth information indicates the present structure to perform step S604 to update the first neural network.

[0123] In other examples, the fourth information may also be recommendation information for data transmission parameters. In some specific implementations of the example, the recommendation information may be a combination of a modulation method and a coding rate obtained based on the channel state information and the amount of data volume to be transmitted in the cache area. For example, when the second information evaluates the quality of the channel state information as good and the third information indicates that the amount of data volume to be transmitted in the cache is large, the recommendation information contained in the fourth information may be a combination of a higher modulation method and a higher coding rate that may be adopted by the system. In other specific implementations of the example, the recommendation information may be a recommendation to use or discard certain physical resources for data transmission and / or channel estimation, i.e., to give a non-uniformly distributed pattern of physical resources occupied by the reference signal. For example, if it may be concluded, based on the error information of the channel state in the second information, that the estimation error of certain physical resources in the second resource is very low, these physical resources may no longer be used for transmission of the reference signal or for transmission of important information (e.g., DCI). On the contrary, if the second information indicates that the channel estimation error of certain physical resources is high, the reference signal transmission should be increased in the vicinity of these physical resources, e.g., it is assumed that there are 10 second resources in total, numbered 0-9, and the data transmission is currently performed on the resources 0 and 5, and if the third information indicates that the channel estimation error is high in the vicinity of the resources 7, 8, and 9, the reference signals should be transmitted on the resources 0, 5, and 8. As another example, in the data transmission in the PDSCH channel of the NR system, the second resource contains 10 OFDM symbols numbered 0-9, the third information indicates that the current data transmission in the PDSCH channel is performed on the resources 3-8 for the data transmission, and the reference signals are transmitted on the resources 2 and 9(i.e., the pos1 format of the mapping type A in the NR standard). If the second information indicates that the channel estimation error in the vicinity of the resources 5, 6, and 7 is high, the fourth information recommends transmitting the reference signals on the resources 2, 6, and 9 and the data transmission on the resources 3, 4, 5, 7, and 8 (i.e., the pos2 format of the mapping type A in the NR standard). In other specific implementations of the example, the recommendation information may be a scheduling suggestion for the data transmission of the user. For example, the base station may increase the number of MU-MIMO users when the second information indicates that the estimation error of the channel state information is low.

[0124] The configuration of the physical resource occupied by the reference signal in the existing system is not intelligent enough, and it is difficult to make timely and flexible adjustments in response to dynamic changes in the physical environment, so as to achieve a dynamic balance between the reliability of the uplink / downlink transmission and the system throughput. For example, when a large vehicle enters a scenario, the system should timely increase the physical resource occupied by the reference signal to ensure transmission performance, and when the large vehicle leaves the scenario, the system should timely decrease the physical resource occupied by the reference signal to obtain better throughput, which is difficult to achieve with current communication system. The present disclosure uses the third neural network to obtain the fourth information for assisting data transmission, to make timely and flexible adjustments in response to dynamic changes in the physical environment, and thus to achieve a dynamic balance between the reliability of the uplink / downlink transmission and the system throughput.

[0125] In some examples, where the third neural network is located on the base station side, the above third information may be a scheduling decision made by the base station itself, a measurement function of the base station itself, a scheduling request received by the base station that has been reported by the terminal, and a service quality constraint received by the base station from an upper layer protocol or the core network. In some implementations of the example, the channel estimation indication information in above the fourth information may be used to manage aperiodic CSI measurement and reporting, e.g., when the channel estimation indication information indicates that the channel estimation process needs to be re-performed, the base station sends DCI information to trigger the CSI measurement and reporting process of the terminal. In some implementations of the example, the data transmission quality indication information in the above fourth information may be used to assist the base station in data transmission scheduling, e.g., when the data transmission quality indication information indicates that the degree of recommendation for data transmission of a user 1 is high and that the degree of recommendation for data transmission of a user 2 is low, the base station may schedule the user 1 for data transmission only by the DCI information, and wait until the degree of recommendation for data transmission of the user 2 returns to high before scheduling both the user 1 and the user 2 for data transmission. In other embodiments of the example, the recommendation information of the data transmission parameter in the above fourth information may be used as a reference for the base station to configure the data transmission of the user, e.g., when the recommendation information of the data transmission parameter indicates that the modulation method of the data transmission is recommended to use 64QAM modulation, the base station may instruct the terminal to switch to the 64QAM modulation for subsequent transmission in the DCI. Here, the complete channel estimation process may be an existing channel estimation process.

[0126] In other examples, where the third neural network is located on the terminal side, the above third information may be DCI information made by the base station that is received by the terminal, an environment-aware function of the terminal itself, and a service quality constraint of the terminal's own upper layer protocol. In some implementations of the example, the channel estimation indication information in the above fourth information may be used to trigger the terminal to re-perform the complete channel estimation process, e.g., the terminal may receive the CSI-RS signal within the second resource to perform the channel estimation thereby obtaining the real channel state information and correct / update the first neural network; the terminal may also report the event (i.e., the channel estimation indication information indicates that the complete channel estimation process needs to be re-performed) to the base station for processing according to the instruction of the base station. In some other implementations of the example, the recommendation information of the data transmission parameters in the above fourth information may be reported to the base station, thereby improving the accuracy of the base station scheduling.

[0127] At step S604, each parameter in the first neural network may be updated based on the second information and / or the fourth information. The specific process thereof may be referred to the description of step S504. In some examples, the performing of step S604 may be controlled by the fourth information. In some specific implementations of the example, the fourth information may include whether or not to update the first neural network by the second information. In some other specific implementations of the example, the performing of step 604 depends on whether the data transmission state indication information in the fourth information exceeds a predetermined threshold, for example, step 604 is not performed when the data transmission state indication information is below a first threshold, step 604 is performed when the data transmission state indication information is above the first threshold but below a second threshold, and the complete channel estimation process is re-performed when the data transmission state indication information is above the second threshold. The above examples are merely exemplary and the present disclosure is not limited thereto.

[0128] The method according to FIG. 6 can accurately obtain the channel state information and effectively utilize the channel state information to enhance transmission performance, and can solve the problem that wireless channels have complex and variable characteristics in the time, frequency, and spatial domains. FIG. 7 is a flowchart of a method for online updating of a second neural network according to an embodiment of the present disclosure.

[0129] Referring to FIG. 7, at step S701, second information may be obtained by a second neural network based on channel state information. Wherein, the second information is an evaluation of the channel state information. The specific process thereof may be referred to the description of step S503.

[0130] In some examples, the channel state information on the second resource is currently obtained from the output of the first neural network by the method described in FIG. 5 or FIG. 6. In other examples, the channel state information on the second resource may be channel state information obtained by the communication node performing a traditional channel estimation process (e.g., a CSI measurement and reporting process accomplished via CSI-RS). In other examples, the channel state information on the second resource may be channel state information used in the past to perform data transmission.

[0131] At step S702, data transmission may be performed based on the channel state information on the second resource. In some examples, the transmitting node, after obtaining the channel state information, calculates parameters such as a modulation order, a coding rate, a precoding matrix, etc., used for data transmission based on the channel state information, and then sends the data to the receiving node after sequentially performing the processes of channel coding, modulation, and precoding, etc.

[0132] At step S703, fifth information related to performing data transmission based on the channel state information may be obtained, and at least portion of parameters of the second neural network are updated based on the second information and / or the fifth information. Wherein, the fifth information may be information about a result of performing the data transmission based on the channel state information on the second resource. For example, in updating the parameters of the second neural network, the second information and the fifth information are first converted into an error amount, and then the error amount is back-propagated layer by layer according to a back-propagation rule thereby obtaining an error amount corresponding to a parameter in each of the neural network layers of the second neural network, and then finally an optimization algorithm is utilized to calculate an update amount of the parameter based on the error amount of the parameter and the parameter is updated.

[0133] In some examples, when the second neural network is located at the transmitting node, the fifth message may be feedback information (ACK or NACK) for data transmission. For example, in the NR system including the second neural network, the base station obtains the channel state information on the physical resource of the PDSCH through the first neural network based on the CSI measurement information fed back from the terminal, and transmits the data after pre-coding operation based on the channel state information, and the terminal transmits ACK feedback information indicating successful data transmission through the PUCCH after receiving the data, and at this time the fifth information is the ACK feedback information. In other examples, the fifth information may be a cumulative bit error rate (which may be equivalently replaced by a cumulative symbol error rate, a cumulative success rate, and a cumulative block success rate, etc.) with respect to data transmission performed based on the channel state information obtained by the first neural network from a previous channel estimation process. For example, starting from the channel estimation at the moment t0, the transmitting node continuously performs data transmission at the moments t1, ..., tn, and the receiving node continuously performs data reception based on the channel state information generated by the first neural network, then the fifth information is a ratio of the number of correctly received bits to the total number of bits.

[0134] In some examples, the error amount may be generated by calculating a distance between the second information and the fifth information, which may be a Euclidean distance, an L1 paradigm, a cross-entropy function, a DL divergence, and the like. In some specific implementations of the example, the second information is a quality classification label of the channel state information estimation (denoted as y, when y=1 it means that the channel state information outputted by the first neural network is of good quality), and the fifth information is the feedback information of the data transmission (denoted as x, when x=1 it means that the data transmission is successful), in this case, the error amount between the second information and the fifth information may be obtained by the cross-entropy function, that is, the error amount is . In some examples, the optimization algorithm may be a gradient descent algorithm, a stochastic gradient descent algorithm, a small batch gradient descent algorithm, a momentum gradient descent algorithm, a Nesterov gradient acceleration algorithm, an Adagrad algorithm, an AdaDelta algorithm, an Adam algorithm. Specifically, by way of example only and not as a limitation, common machine learning training algorithms such as derivative trimming, regularization, model pruning, model quantization, and the like may optionally be used in the process of updating the weights of the network parameters.

[0135] In some examples, when the structure of the second neural network is shown as in FIG. 10 below, i.e., when the second information output by the second neural network consists of a plurality of sub-information (such as the probability of successful data transmission, the error evaluation information, etc.), a plurality of sub-information in one or more of the second information may be selected to obtain the error amount in combination with the fifth information, and the neural network parameter corresponding to the error amount is updated. For example, the second information consists of two parts, the prediction information of the probability of successful data transmission and the evaluation error between the output channel state information and the real channel state information, and when the fifth information is the feedback information of the data transmission, the probability of successful data transmission in the second information may be selected to compute the error amount in combination with the fifth information. In this case, only the parameters in the first sub-neural network and the second sub-neural network in the second neural network are updated.

[0136] FIG. 8 is a flowchart of a method for online updating of a third neural network according to an embodiment of the present disclosure.

[0137] Referring to FIG. 8, at step S801, second information may be obtained through a second neural network based on channel state information. Wherein, the second information is an evaluation of the channel state information. The specific process thereof may be described with reference to step S503.

[0138] At step S802, fourth information may be obtained via the third neural network based on the second information and / or third information. Wherein, the third information is relevant information for data transmission and the fourth information is auxiliary information for data transmission. The specific process thereof may be described with reference to step S603.

[0139] At step S803, data transmission may be performed based on the channel state information on the second resource and / or the fourth information and / or the third information. In some examples, after the transmitting node obtains the channel state information, a part of parameters such as a modulation order, a coding rate, a precoding matrix, etc. used for data transmission is obtained through the fourth information and the remaining part is obtained through the calculation of the channel state information, and then the data is sent to the receiving end after being sequentially performed the processes of channel coding, modulation, precoding, and so on. In other examples, after the transmitting node obtains the channel state information, a part of the parameters such as the modulation order, the coding rate, the precoding matrix, etc. used for data transmission is obtained through the fourth information, and the remaining part is obtained through the third information, and then the data is sent to the receiving end after being sequentially performed the processes of channel coding, modulation, precoding, and so on. The above processes of determining the parameters are only exemplary, and the present disclosure is not limited thereto.

[0140] For example, the channel state information is used during data transmission, and the parameters used for data transmission (such as the modulation method, the coding rate, etc.) may be determined by the third or fourth information. For example, in the multi-user downlink transmission, the fourth information modifies the modulation method and coding rate used by each user, while the third information determines which users transmit simultaneously.

[0141] At step S804, fifth information may be obtained, at least part of parameters of the third neural network is updated based on the fourth information and / or the fifth information. Wherein, the fifth information is information about a result of data transmission based on the channel state information on the second resource and / or the third information and / or the fourth information. For example, the fifth information is resultant information generated by performing data transmission based on the channel state information on the second resource and the data transmission parameters determined by the third information and / or the fourth information. In updating the parameters of the third neural network, the fourth information and the fifth information are first converted into an error amount, and then the error amount is back-propagated layer by layer according to a back-propagation rule thereby obtaining an error amount corresponding to a parameter in each of the neural network layers of the third neural network, and finally, an update amount of the parameter is calculated using an optimization algorithm based on the error amount of the parameter and the parameter is updated.

[0142] In some examples, when the third neural network is located at the transmitting node, the fifth information may be feedback information (ACK or NACK) of the data transmission. For example, in the NR system, the base station obtains the channel state information on the physical resource of the PDSCH through the first neural network based on the CSI measurement information fed back from the terminal, and transmits the data after pre-coding operation based on the channel state information, and the terminal transmits ACK feedback information indicating successful data transmission through the PUCCH after receiving the data, and at this time the fifth information is the ACK feedback information. In other examples, the fifth information may be a cumulative bit error rate (which may be equivalently replaced by a cumulative symbol error rate, a cumulative success rate, and a cumulative block success rate, etc.) with respect to data transmission performed based on the channel state information obtained by the first neural network from a previous channel estimation process. For example, starting from the channel estimation at the moment t0, the transmitting node continuously performs data transmission at the moments t1, ..., tn, and the receiving node continuously performs data reception based on the channel state information generated by the first neural network, then the fifth information is a ratio of the number of correctly received bits to the total number of bits.

[0143] In some examples, the error amount may be generated by calculating a distance between the fourth information and the fifth information, which may be a Euclidean distance, an L1 paradigm, a cross-entropy function, a DL divergence, and the like. In some specific implementations of the example, the fourth information is channel estimation indication information (denoted as y, when y=0 it means that the channel estimation process needs to be re-performed), and the fifth information is the feedback information of the data transmission (denoted as x, when x=1 it means that the data transmission is successful), in this case, the error amount between the fourth information and the fifth information may be obtained by the cross-entropy function, that is, the error amount is . In some examples, the optimization algorithm may be a gradient descent algorithm, a stochastic gradient descent algorithm, a small batch gradient descent algorithm, a momentum gradient descent algorithm, a Nesterov gradient acceleration algorithm, an Adagrad algorithm, an AdaDelta algorithm, an Adam algorithm. Specifically, by way of example only and not as a limitation, common machine learning training algorithms such as derivative trimming, regularization, model pruning, model quantization, and the like may optionally be used in the process of updating the weights of the network parameters.

[0144] In some examples, when the structure of the third neural network is shown as in FIG. 11 below, i.e., when the fourth information output by the third neural network consists of a plurality of sub-information (such as the channel estimation indication information, the recommendation information of the modulation method, etc.), a plurality of sub-information in one or more of the fourth information may be selected to obtain the error amount in combination with the fifth information, and the neural network parameter corresponding to the error amount is updated. For example, the fourth information consists of two parts, the channel estimation indication information and the recommendation information of the modulation method, and when the fifth information is the feedback information of the data transmission, the channel estimation indication information in the fourth information may be selected to calculate the error amount in combination with the fifth information. In this case, only the parameters in the first sub-neural network and the second sub-neural network in the third neural network are updated.

[0145] FIG. 9 illustrates a schematic structure of a first neural network according to an embodiment of the present disclosure.

[0146] Referring to FIG. 9, the first neural network includes a preprocessing unit and a neural network (which may also be referred to as a neural network unit) in series, wherein the preprocessing unit may obtain first information based on a first signal on a first resource and / or related information (i.e., first related information), and obtain channel state information on a second resource based on the first information and / or the related information through the pre-trained neural network. For example, the preprocessing unit obtains the first information based on the first signal on the first resource and a reference signal contained in the related information, and then inputs the first information into the subsequent neural network. In some examples, the preprocessing unit may first input the first signal into a band-pass filter to obtain a denoised signal as a part of the first information, then obtain an intermediate signal by an MMSE algorithm based on the reference signal in the related information, and finally obtain an eigenvector matrix and eigenvalues by an eigenvalue decomposition on the intermediate signal, as another part of the first information, and input them into the neural network.

[0147] When the communication node is the base station, the related information containing the reference signal may be determined by the base station itself, and when the communication node is the user equipment, the related information containing the reference signal may be configured by the base station. In addition, the preprocessing unit may also input its input (i.e., the reference signal and the first signal on the first resource) directly to the neural network unit without additional processing. The neural network unit may be a pre-trained neural network, the specific structure of which is shown in FIG. 12 below, which may generate the channel state information on the second resource from the first information generated by the preprocessing unit and the related information input additionally. The structure of the first neural network shown in FIG. 9 is only exemplary and the present disclosure is not limited thereto.

[0148] FIG. 10 illustrates a schematic structure of a second neural network according to an embodiment of the present disclosure.

[0149] Referring to FIG. 10, the second neural network may include a preprocessing unit and three sub-neural networks (which may also be referred to as neural network units). Wherein, the preprocessing unit may extract feature information (e.g., a variance of a channel coefficient, a delay expansion, an inter-antenna correlation matrix, etc.) from input channel state information and input it to the first sub-neural network, or the preprocessing unit may directly input its input the channel state information to the first sub-neural network without additional processing. The first sub-neural network, the second sub-neural network, and the third sub-neural network can adopt the same or different neural network structures, and their various parameters may be first obtained through offline training, and then updated online by the method shown in FIG. 7 after the second neural network is deployed. The first sub-neural network may process the feature information and related information (i.e., the second related information, such as a predetermined threshold value or a channel high-order statistic in a target scenario), and the information generated by the first sub-neural network will undergo the subsequent second sub-neural network and the third sub-neural network to generate the probability of successful data transmission and the estimation error of the information state information in the second information, respectively. In some examples, the first sub-neural network may be formed using a transformer structure. In some examples, the second sub-neural network may be formed using an MLP-MIX network. In some examples, the third neural network may be formed using a DNN network. In some examples, the first sub-neural network, the second sub-neural network, and the third sub-neural network may be jointly and / or independently realized by the same physical entity or different physical units, and the physical entity may be formed by hardware, software, or a combination thereof, which may be configured by a person skilled in the art according to the actual needs, and the combination may include, but is not limited to: the first sub-neural network, the second sub-neural network, and the third sub-neural network are realized by separate entities; the first sub neural network, the second sub neural network, and the third sub neural network are realized by the same entity; the first sub neural network and the third sub neural network are realized by the same entity, and the second sub neural network is realized by another entity; the first sub neural network and the second sub neural network are realized by the same entity, and the third sub neural network is realized by another entity.

[0150] The number of sub-neural networks following the first sub-neural network in the second neural network described above may be determined based on the number of sub-information contained in the second information. A plurality of sub-neural networks may be used to obtain the corresponding sub-information in the second information separately. The structure of the second neural network shown in FIG. 10 is only exemplary and the present disclosure is not limited thereto.

[0151] FIG. 11 illustrates a schematic structure of a third neural network according to an embodiment of the present disclosure.

[0152] Referring to FIG. 11, the third neural network may include a preprocessing unit and three sub-neural networks. Wherein, the preprocessing unit may convert third information into at least one of a vector, a matric, and a tensor available for computation by a neural network layer and then input it to the first sub-neural network, or the preprocessing unit may input its input third information directly to the first sub-neural network without additional processing. In some examples, the preprocessing unit internally predefines vectors corresponding to each combination of a modulation method and a coding rate, and converts the combination of the modulation method and the coding rate in the third information into the corresponding vector by means of a table lookup or a calculation. The first sub-neural network, the second sub-neural network, and the third sub-neural network may have the same or different neural network structures, and various parameters thereof may first be obtained by offline training, and then updated online by the method shown in FIG. 8 after the third neural network is deployed. The first sub-neural network processes the second information and the converted third information, and the information generated by the first sub-neural network will undergo the subsequent second sub-neural network and the third sub-neural network to generate the channel estimation indication and the recommendation information of the modulation mode in the fourth information, respectively. In some examples, the first sub-neural network may use an MLP-MIX network. In some examples, the second sub-neural network may be a binary classification network constructed by a 3-layer DNN. In some examples, the third sub-neural network may be a multi-classification network constructed using a multi-layer CNN, with each label corresponding to a combination of a modulation method and a coding rate. In some examples, the first sub neural network, the second sub neural network, and the third sub neural network may be jointly and / or independently realized by the same physical entity or different physical units, and the physical entity may include hardware, software, or combinations thereof, which may be configured by a person skilled in the art according to the actual needs, and the combination includes, but is not limited to: the first sub neural network, the second sub neural network, and the third sub neural network are realized by separate entities; the first sub neural network, the second sub neural network, and the third sub neural network are realized by the same entity; the first sub neural network and the third sub neural network are realized by the same entity, and the second sub neural network is realized by another entity; the first sub neural network and the second sub neural network are realized by the same entity, and the third sub neural network is realized by another entity.

[0153] The number of sub-neural networks following the first sub-neural network in the third neural network described above may be determined based on the number of sub-information contained in the fourth information. A plurality of sub-neural networks may be used to obtain the corresponding sub-information in the fourth information separately. The structure of the third neural network shown in FIG. 11 is only exemplary and the present disclosure is not limited thereto.

[0154] FIG. 12 illustrates a schematic structure of a neural network unit according to an embodiment of the present disclosure.

[0155] FIG. 12 gives an example of the structure of a neural network unit or sub-neural network appearing in the first neural network, the second neural network, and the third neural network of the present disclosure.

[0156] Referring to FIG. 12, the neural network unit may include an information processing unit and a plurality of neural network layers. The information processing unit may convert input data (such as related information and input information in FIG. 12) of the sub-neural network into at least one of a data vector, a matrix, and a tensor available for computation by the sub-neural network, and the neural network layer may be at least one of an input layer, a hidden / intermediate layer, and an output layer shown in FIG. 12. In addition, each neural network layer may include a plurality of neurons n and may utilize at least one activation function to activate the neurons, for example, as an example only and not as a limitation, e.g., a tanh function, a ReLU function, an eLU function, a seLU function, a ceLU function, a preLU function, a geLU function, a LeakyReLU function, a Sigmoid function, a Softmax function, a Softplus function, etc. Each neural network layer may perform operations on its input data to realize functions such as matrix transformation, data dimensionality reduction, data feature extraction, data feature combination, and the like. By way of example only and not as a limitation, the multiple neural network layers may be connected in series or in parallel, etc., to form different neural network structures, including, but not limited to, a multilayer perceptron machine (MLP), a multilayer perceptron mixer (MLP-mixer), a convolutional neural network (CNN), a deep neural network (DNN), a recurrent neural network (RNN), a restricted Boltzmann machine (RBM), a deep Belief Networks (DBN), a bidirectional recurrent deep neural network (BRDNN), a generative adversarial network (GAN), a transformer network, etc.

[0157] The information processing unit may process (e.g., merge, position encoding, etc., as will be described below) the related information (such as the first related information or the second related information described above), so that the neural network may acquire prior information (e.g., the relative position of the second resource to the first resource, the structure of the second resource, etc.) implicit in the related information, in order to assist the neural network in improving the accuracy and flexibility of acquiring the channel state information. Here, only as an example and not as a limitation, the related information may be at least one of a position of the first resource and a position of the second resource. The related information may also be a kind of characteristic constraint of the channel in the current scenario, such as the variance of the channel, the delay expansion, the correlation time, and so on. The information processing unit may also convert the related information into at least one of a vector, a matrix, and a tensor available for computation by the neural network layer.

[0158] In some examples, the information processing unit may convert the input information (such as the first information, the channel state information output by the first neural network, the second information, or the third information) into at least one of a vector, a matrix, and a tensor available for computation by the neural network layer. By way of example only and not as a limitation, a set consisting of known channel state information is defined as CRS. First, the known channel state information is processed by a numerical mapping method (e.g., normalization, standardization, etc.) so that its numerical scale or distribution is suitable for computation by the neural network. More specifically, taking the minimum-maximum (Min-Max) standardization as an example, the maximum value max(CRS) and the minimum value min(CRS) of all the elements in CRSmay be computed separately, and then, for each element of CRS, the process of is performed. After the above numerical mapping has been performed, a set consisting of the processed elements may be converted into at least one of a vector, a matrix, and a tensor corresponding to the input dimension of the neural network layer.

[0159] In another example, the information processing unit may also perform position encoding of the input information and convert the information after position encoding into at least one of a vector, a matrix, and a tensor for neural network computation. Optionally, the position encoding may be a process of adding and / or multiplying the input information with a codeword in a predetermined codebook. By way of example only and not as a limitation, in a case where the preprocessing unit outputs the known channel state information (i.e., the preprocessing unit outputs the channel state information on the first resource based on the input first signal), the position encoding using the codebook may include: first, a set CRSconsisting of the known channel state information is processed according to a numerical mapping method to obtain a set including a number of elements that have undergone numerical mapping; subsequently, a codebook for position encoding is obtained according to the following equation.

[0160]

[0161] Where n denotes the physical resource (e.g., time domain, frequency domain, and space domain) position where the channel state information belongs to, d denotes the physical resource dimension of the channel state information, N is any positive number greater than the number of elements contained in the set , and i denotes the index of the physical resource dimension. Subsequently, the position encoding is performed on the known channel state information element by the equation to get the set ; and finally the set consisting of the processed elements is converted into at least one of a vector, a matrix, and a tensor corresponding to the input dimension of the neural network layer. In addition, the information processing unit may also input its input directly to the neural network unit without additional processing.

[0162] The operations in the neural network unit described above are merely exemplary and the present disclosure is not limited thereto.

[0163] FIG. 13 illustrates a block diagram of a communication node in a communication system provided by an embodiment of the present disclosure. Referring to FIG.13, the communication node 1300 may include a transceiver 1310 and a processor 1320, wherein the processor 1320 is coupled to the transceiver 1310 and configured to perform the communication method performed by the communication node described above. Although the transceiver 1310 and the processor 1320 are shown as separate entities, they may be implemented as a single entity, such as a single chip. The transceiver 1310 and the processor 1320 may be electrically connected or coupled to each other. The transceiver 1310 may transmit signals to and receive signals from other network nodes, such as a UE, a base station, a system simulator (such as a simulated base station), or a core network node. The processor 1320 may include one or more processing units and may control the communication node to perform at least one operation and / or function according to the above embodiments.

[0164] Details of the operations of the method performed by the communication node described above may refer to the description related to FIG. 5 -FIG. 12 and are not repeated here.

[0165] According to the embodiments of the present disclosure, an electronic device is further provided, the device includes at least one processor and at least one memory storing computer-executable instructions, wherein the computer-executable instructions, when run by the at least one processor, cause the at least one processor to perform any one of the methods as described above.

[0166] According to an embodiment of the present disclosure, a computer readable storage medium storing instructions is also provided. The instructions, when executed by at least one processor, causes the at least one processor to perform any of the above methods according to the exemplary embodiments of the present disclosure. Examples of computer-readable storage media herein include: Read Only Memory (ROM), Random Access Programmable Read Only Memory (RAPROM), Electrically Erasable Programmable Read Only Memory (EEPROM), Random Access Memory (RAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), flash memory, non-volatile memory, CD-ROM, CD-R, CD+R, CD-RW, CD+RW, DVD-ROM, DVD-R, DVD+R, DVD-RW, DVD+RW, DVD-RAM, BD-ROM, BD-R, BD-R LTH, BD-RE, Blue-ray or optical disk storage, Hard Disk Drive (HDD), Solid State Drive (SSD), card storage (such as multimedia cards, secure digital (SD) cards or extremely fast digital (XD) cards), magnetic tapes, floppy disks, magneto-optical data storage devices, optical data storage devices, hard disks, solid state disks, and any other devices that are configured to store computer programs and any associated data, data files and data structures in a non-transitory manner and provide the computer programs and any associated data, data files and data structures to a processor or computer so that the processor or computer can execute the computer programs. The instructions or computer programs in the computer-readable storage medium described above may be executed in an environment deployed in a computer device, such as client, host, proxy device, server, etc. In addition, in one example, the computer programs and any associated data, data files, and data structures are distributed on a networked computer system, so that the computer programs and any associated data, data files, and data structures are stored, accessed and executed through one or more processors or computers in a distributed manner.

[0167] At least one of the plurality of modules above may be implemented through an AI model. A function associated with AI may be performed through the non-volatile memory, the volatile memory, and the processor.

[0168] The processor may include one or a plurality of processors. At this time, one or a plurality of processors may be a general purpose processor, such as a central processing unit (CPU), an application processor (AP), or the like, a graphics-only processing unit such as a graphics processing unit (GPU), a visual processing unit (VPU), and / or an AI-dedicated processor such as a neural processing unit (NPU).

[0169] The one or a plurality of processors control the processing of the input data in accordance with a predefined operating rule or artificial intelligence (AI) model stored in the non-volatile memory and the volatile memory. The predefined operating rule or artificial intelligence model is provided through training or learning. Here, being provided through learning means that, by applying a learning algorithm to a plurality of learning data, a predefined operating rule or AI model of a desired characteristic is made. The learning may be performed in a device itself in which AI according to an embodiment is performed, and / o may be implemented through a separate server / device / system.

[0170] The learning algorithm is a method for training a predetermined target device (for example, a robot) using a plurality of learning data to cause, allow, or control the target device to make a determination or prediction. Examples of learning algorithms include, but are not limited to, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning.

[0171] The artificial intelligence model can be obtained through training. Here, "obtained through training" refers to training a basic artificial intelligence model with multiple training data through a training algorithm to obtain a predefined operational rule or artificial intelligence model configured to execute required features (or objectives).

[0172] As an example, the AI model may consist of a plurality of neural network layers. Each layer has a plurality of weight values, and performs neural network calculations through calculation between a result of a previous layer between the plurality of weights. Examples of neural networks include, but are not limited to, convolutional neural network (CNN), deep neural network (DNN), recurrent neural network (RNN), restricted Boltzmann Machine (RBM), deep belief network (DBN), bidirectional recurrent deep neural network (BRDNN), generative adversarial networks (GAN), and deep Q-networks.

[0173] It should be noted that the terms "first", "second", "third", " fourth", "1", "2", etc. (if present)used in the specification and claims and the accompanying drawings above of the present disclosure are used to distinguish similar objects and are not necessary for describing a particular order or sequence. It should be understood that the data so used is interchangeable in appropriate cases so that the embodiments of the present disclosure described herein may be implemented in an order other than that illustrated or described herein.

[0174] It should be understood that while the flowcharts of the embodiments of the present disclosure indicate the individual operational steps by arrows, the order of these implementation steps is not limited to the order indicated by the arrows. Unless explicitly stated herein, in some implementation scenarios of the embodiments of the present disclosure, the implementation steps in the respective flowcharts may be performed in other orders as desired. In addition, some or all of the steps in each flowchart may include multiple sub-steps or multiple stages based on actual implementation scenarios. Some or all of these sub-steps or stages may be executed at the same moment, and each of these sub-steps or stages may also be executed separately at different moments. In the scenarios where the execution moments are different, the order of execution of these sub-steps or stages may be flexibly configured according to the needs, and the embodiments of the present disclosure are not limited thereto.

[0175] The above description is only an optional implementation of part of the implementation scenarios of the present disclosure. It should be noted that for those ordinary skill in the art, other similar means of implementation based on the technical idea of the present disclosure, without departing from the technical idea of the present disclosure, also fall within the scope of protection of the embodiments of the present disclosure.

[0176] Other embodiments of the present disclosure will readily be conceived by those skill in the art after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variation, use, or adaptation of the present disclosure that follows the general principle of the present disclosure and includes commonly known or customary technical means in the art not disclosed herein. The specification and embodiments are to be considered exemplary only, and the true scope and spirit of the disclosure is limited by the claims.

Claims

1.A method performed by a communication node, the method comprising:obtaining channel state information on a second resource using a first neural network;obtaining, based on the channel state information, second information using a second neural network; andupdating the first neural network based on the second information.2.The method of claim 1, wherein the obtaining of the channel state information on the second resource using the first neural network comprises:receiving a first signal on a first resource to obtain first information; andobtaining the channel state information on the second resource using the first neural network based on the first information.3.The method of claim 2, wherein the first information comprises at least one of:the first signal on the first resource, the first signal comprising all signals received on the first resource;a reference signal on the first resource;a second signal after specific processing of the first signal and / or the reference signal;channel state information corresponding to the first resource that is fed back;channel information that is inversely estimated based on received data;a physical resource containing the reference signal;channel state information measurement report information; orfirst related information, the first related information comprising at least one of: information for indicating a position of the reference signal in the first resource, the reference signal, information related to the first resource and / or the second resource, and characteristic constraint information of a channel in a current network environment.4.The method of claim 1, wherein the second information comprises at least one of:prediction information for data transmission based on the channel state information, the prediction information comprising at least one of: a probability of successful or failed data transmission, a bit error rate for data transmission, a symbol error rate for data transmission, an error rate for data transmission, and a signal-to-interference ratio resulting from data transmission; orerror evaluation information for the channel state information, the error evaluation information comprising at least one of : an estimation error of the channel state information, a quality classification label for the channel state information estimation, a deviation measure between characteristic information of the channel state information and a preset parameter value in the second neural network, and a probability of occurrence of the channel state information in a current network environment.5.The method of claim 1, further comprising:obtaining, based on the second information and / or third information related to data transmission, fourth information for assisting the data transmission using a third neural network.6.The method of claim 5, wherein the third information comprises at least one of:a relevant parameter for data transmission, the relevant parameter for the data transmission comprising at least one of: a modulation method, a coding rate, an available physical resource, a quantity of a data volume to be transmitted in a cache, a quality of service requirement, and a set of pre-coded codebooks; orinformation related to a network environment, the information related to the network environment comprising at least one of: an interference level of the environment, a degree of environmental change and experience data for a coherent time of the environment.7.The method of claim 5, wherein the fourth information comprises at least one of:data transmission state indication information for indicating whether to use the channel state information for data transmission and / or whether to re-perform a complete channel estimation process and / or whether to update the first neural network based on the second information; orrecommendation information for a data transmission parameter for indicating the data transmission parameter recommended by the communication node.8.A communication node, comprising:a transceiver; andat least one processor configured to:obtain channel state information on a second resource using a first neural network,obtain, based on the channel state information, second information using a second neural network, andupdate the first neural network based on the second information.9.The communication node of claim 8, wherein the at least one processor is further configured to:receive a first signal on a first resource to obtain first information, andobtain the channel state information on the second resource using the first neural network based on the first information.10.The communication node of claim 9, wherein the first information comprises at least one of:the first signal on the first resource, the first signal comprising all signals received on the first resource;a reference signal on the first resource;a second signal after specific processing of the first signal and / or the reference signal;channel state information corresponding to the first resource that is fed back;channel information that is inversely estimated based on received data;a physical resource containing the reference signal;channel state information measurement report information; orfirst related information, the first related information comprising at least one of: information for indicating a position of the reference signal in the first resource, the reference signal, information related to the first resource and / or the second resource, and characteristic constraint information of a channel in a current network environment.11.The communication node of claim 8, wherein the second information comprises at least one of:prediction information for data transmission based on the channel state information, the prediction information comprising at least one of: a probability of successful or failed data transmission, a bit error rate for data transmission, a symbol error rate for data transmission, an error rate for data transmission, and a signal-to-interference ratio resulting from data transmission; orerror evaluation information for the channel state information, the error evaluation information comprising at least one of : an estimation error of the channel state information, a quality classification label for the channel state information estimation, a deviation measure between characteristic information of the channel state information and a preset parameter value in the second neural network, and a probability of occurrence of the channel state information in a current network environment.12.The communication node of claim 8, wherein the at least one processor is further configured to:obtain, based on the second information and / or third information related to data transmission, fourth information for assisting the data transmission using a third neural network.13.The communication node of claim 12, wherein the third information comprises at least one of:a relevant parameter for data transmission, the relevant parameter for the data transmission comprising at least one of: a modulation method, a coding rate, an available physical resource, a quantity of a data volume to be transmitted in a cache, a quality of service requirement, and a set of pre-coded codebooks; orinformation related to a network environment, the information related to the network environment comprising at least one of: an interference level of the environment, a degree of environmental change and experience data for a coherent time of the environment.14.The communication node of claim 12, wherein the fourth information comprises at least one of:data transmission state indication information for indicating whether to use the channel state information for data transmission and / or whether to re-perform a complete channel estimation process and / or whether to update the first neural network based on the second information; orrecommendation information for a data transmission parameter for indicating the data transmission parameter recommended by the communication node.15.The communication node of claim 14, wherein in a case that the communication node is a user equipment, the fourth information is used by the user equipment for at least one of:determining whether to trigger re-performing the complete channel estimation process;reporting the fourth information to a base station as reference information for scheduling data transmission by the base station;wherein whether to trigger re-performing the complete channel estimation process comprises at least one of whether to trigger an aperiodic channel state information measurement and reporting, and transmitting information about whether or not to trigger re-performing the complete channel estimation process to the base station.

Images