Method and apparatus for processing pilot and data signal in a wireless communication system

Abstract

The present disclosure relates to a 5G communication system or a 6G communication system for supporting higher data rates beyond a 4G communication system such as long term evolution (LTE). The present disclosure provides a method performed by a second node in a communication system, comprising: receiving first configuration information for first data from a first node; obtaining first predicted data signals of various layers of the first data based on the first configuration information; determining a first set including the first predicted data signal of at least one layer of the various layers and a second set including the first predicted data signals of one or more layers of multiple layers based on an accuracy of the first predicted data signals of the various layers; obtaining a third set based on the first configuration information and the first set, wherein the third set includes second predicted data signals corresponding to the one or more layers; obtaining a fourth set based on the second set and the third set, wherein the fourth set includes third predicted data signals corresponding to the one or more layers; obtaining soft bits of the first data based on the first set and the fourth set.

Description

METHOD AND APPARATUS FOR PROCESSING PILOT AND DATA SIGNAL IN A WIRELESS COMMUNICATION SYSTEM

[0001] The present disclosure relates to the field of communication, and more particularly, to methods and apparatuses for processing pilot and data signal in a wireless communication system.

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

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

[0004] In order to accomplish such a high data rate and an ultra-low latency, it has been considered to implement 6G communication systems in a terahertz band (for example, 95GHz to 3THz bands). It is expected that, due to severer path loss and atmospheric absorption in the terahertz bands than those in mmWave bands introduced in 5G, technologies capable of securing the signal transmission distance (that is, coverage) will become more crucial. It is necessary to develop, as major technologies for securing the coverage, radio frequency (RF) elements, antennas, novel waveforms having a better coverage than orthogonal frequency division multiplexing (OFDM), beamforming and massive multiple input multiple output (MIMO), full dimensional MIMO (FD-MIMO), array antennas, and multiantenna transmission technologies such as large-scale antennas. In addition, there has been ongoing discussion on new technologies for improving the coverage of terahertz-band signals, such as metamaterial-based lenses and antennas, orbital angular momentum (OAM), and reconfigurable intelligent surface (RIS).

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

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

[0007] The present disclosure relates to the field of communication, and more particularly, to methods and apparatuses for processing pilot and data signal in a wireless communication system.

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

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

[0010] For a more complete understanding of the present disclosure and its advantages, reference is now made to the following description taken in conjunction with the accompanying drawings, in which like reference numerals represent like parts:

[0011] Fig. 1 illustrates an example wireless network according to embodiments of the present disclosure;

[0012] Fig. 2 illustrates an example base station according to embodiments of the present disclosure;

[0013] Fig. 3 illustrates an example user equipment according to embodiments of the present disclosure;

[0014] Fig. 4 illustrates a schematic diagram of pilot deployment and channel estimation in current LTE and 5G NR;

[0015] Fig. 5 illustrates a Superimposed pilot (SP) deployment mode A;

[0016] Fig. 6 illustrates SP deployment mode B;

[0017] Fig. 7 illustrates an overall block diagram according to an embodiment of the present disclosure;

[0018] Fig. 7a illustrates a joint identification process of "application scenarios" according to an embodiment of the present disclosure;

[0019] Fig. 7b illustrates the configuration process of the superposition mode of pilot and data according to an embodiment of the present disclosure;

[0020] Fig. 7c illustrates the transmitting and receiving process of the transmitting end and the receiving end transmitting signals through the superposition of pilot and data according to an embodiment of the present disclosure;

[0021] Fig. 7d illustrates an initialization pilot and data superposition configuration process according to an embodiment of the present disclosure;

[0022] Fig. 7e illustrates the configuration process of online updating pilot and data superposition configuration according to an embodiment of the present disclosure;

[0023] Fig. 7f illustrates an example in which the network side and the terminal side are respectively the transmitting end and the receiving end according to an embodiment of the present disclosure;

[0024] Fig. 8 illustrates a pilot pattern design according to an embodiment of the present disclosure;

[0025] Fig. 9 illustrates another pilot pattern design according to an embodiment of the present disclosure;

[0026] Fig. 10 illustrates an AI receiver according to an embodiment of the present disclosure;

[0027] Fig. 11 illustrates an example structure of a spatial layer fusion enhanced AI modem receiver according to an embodiment of the present disclosure;

[0028] Fig. 11a illustrates another example structure of a spatial layer fusion enhanced AI modem receiver according to an embodiment of the present disclosure;

[0029] Fig. 11b illustrates the processing flow of a preprocessing module of the spatial layer fusion enhanced AI modem receiver in the inference stage according to the embodiment of the present disclosure;

[0030] Fig. 11c illustrates the processing flow of the preprocessing module of the spatial layer fusion enhanced AI modem receiver in the training stage according to the embodiment of the present disclosure;

[0031] Fig. 11d illustrates another example structure of the spatial layer fusion enhanced AI modem receiver according to an embodiment of the present disclosure;

[0032] Fig. 11e illustrates another processing flow of the preprocessing module of the spatial layer fusion enhanced AI modem receiver in the inference stage according to an embodiment of the present disclosure;

[0033] Fig. 11f illustrates yet another example structure of the spatial layer fusion enhanced AI modem receiver according to an embodiment of the present disclosure.

[0034] Fig. 12 illustrates an E2E AI receiver according to an embodiment of the present disclosure;

[0035] Fig. 12a illustrates another specific implementation of an E2E AI receiver according to an embodiment of the present disclosure;

[0036] Fig. 13 illustrates a specific implementation of an E2E AI receiver according to an embodiment of the present disclosure;

[0037] Fig. 14 illustrates a specific embodiment of high accuracy spatial layer selection according to an embodiment of the present disclosure;

[0038] Fig. 14a illustrates the definition of EVM used by an embodiment of the present disclosure;

[0039] Fig. 14b illustrates a specific implementation of the high accuracy spatial layer threshold, EVM threshold, according to an embodiment of the present disclosure;

[0040] Fig. 15 illustrates a specific embodiment of a low accuracy spatial layer AI enhancer according to an embodiment of the present disclosure;

[0041] Fig. 16 illustrates a specific embodiment of a low accuracy spatial layer AI enhancer according to an embodiment of the present disclosure;

[0042] Fig. 17 illustrates an exemplary way of transmitting initial parameters according to an embodiment of the present disclosure;

[0043] Fig. 18 illustrates another exemplary way of transmitting initial parameters according to an embodiment of the present disclosure;

[0044] Fig. 19 illustrates an exemplary way of transmitting dynamic parameters according to an embodiment of the present disclosure;

[0045] Fig. 20 illustrates another exemplary way of transmitting dynamic parameters according to an embodiment of the present disclosure;

[0046] Fig. 21 illustrates another exemplary way of calculating frequency offset according to an embodiment of the present disclosure;

[0047] Fig. 22 illustrates another exemplary way of transmitting initial parameters and dynamic parameters according to an embodiment of the present disclosure;

[0048] Fig. 23 illustrates another exemplary way of transmitting initial parameters and dynamic parameters according to an embodiment of the present disclosure;

[0049] Fig. 24 illustrates an example way to reduce the complexity of a Transformer receiver by using coherence time and coherence bandwidth characteristics according to an embodiment of the present disclosure;

[0050] Fig. 25 illustrates a block diagram of a UE according to various embodiments of the present disclosure; and

[0051] Fig. 26 illustrates a block diagram of a base station or a network entity according to various embodiments of the present disclosure.

[0052] Before undertaking the Mode for Invention 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. In the present disclosure, elements expressed in the singular form may also be understood to be expressed in the plural form. Similar words such as singular forms “a”, “an” or “the” do not express a limitation of quantity, but express the existence of at least one of the referenced item, unless the context clearly dictates otherwise. For example, reference to “a component surface” includes reference to one or more of such surfaces.

[0053] 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.

[0054] 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.

[0055] 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.

[0056] 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.

[0057] FIG. 1 illustrates an example wireless network according to an embodiment 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.

[0058] 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.

[0059] 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 service; 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.

[0060] 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).

[0061] 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.

[0062] 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.

[0063] 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.

[0064] FIG. 2 illustrates an example base station according to an embodiment 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.

[0065] 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.

[0066] 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.

[0067] 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.

[0068] 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.

[0069] 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.

[0070] 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.

[0071] 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.

[0072] 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).

[0073] 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.

[0074] FIG. 3 illustrates an example user equipment according to an embodiment 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.

[0075] 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.

[0076] 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).

[0077] 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.

[0078] 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.

[0079] The processor 307 is also capable of executing other processes and programs resident in the memory 311, such as processes for channel state information (CSI) reporting on uplink channel. The processor 307 can move data into or out of the memory 311 as required by an executing process. In some embodiments, the processor 307 is configured to execute the applications 313 based on the OS 312 or in response to signals received from gNBs or an operator. The processor 307 is also coupled to the I / O interface 308, which provides the UE 116 with the ability to connect to other devices, such as laptop computers and handheld computers. The I / O interface 308 is the communication path between these accessories and the processor 307.

[0080] 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.

[0081] 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.

[0082] 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.

[0083] Exemplary embodiments of the present disclosure are further described below with reference to the accompanying drawings.

[0084] Text and drawings are provided as examples only to help readers understand the present disclosure. They are not intended and should not be construed to limit the scope of the present disclosure in any way. Although certain embodiments and examples have been provided, based on the disclosure herein, it is obvious to those skilled in the art that changes can be made to the illustrated embodiments and examples without departing from the scope of this disclosure.

[0085] In order to cope with the service traffic growth brought by the explosive development of mobile Internet, mobile communication networks need to greatly improve the spectrum efficiency and increase the transmission rate. MIMO (Multiple Input Multiple Output) is one of the key technologies. MIMO deploys multiple antennas (up to hundreds or more) on the base station or access point to improve the spatial multiplexing ability, thus greatly improving the spectrum efficiency without increasing the density and bandwidth of the base station. In the future, 6G will use ultra-large-scale MIMO system and deploy more dense antenna arrays.

[0086] MIMO detection is divided into blind detection and non-blind detection based on pilot training. Blind channel estimation is generally based on the second-order statistics or higher-order statistics of signal and noise, and there are also studies on blind channel estimation based on neural network. The main disadvantages of blind detection are slow convergence or convergence to wrong detection results, which cannot meet the requirements of wireless communication systems. However, it has the advantages of no pilot overhead and saving time and frequency resources.

[0087] In order to ensure the performance, most existing wireless communication systems are non-blind detection based on pilot channel estimation to better resist the multipath effect of wireless channels. In non-blind channel estimation, pilot signals need to be used. The receiving end estimates the channel according to the received pilot signal. However, with the increase of spatial multiplexing layers in MIMO technology, more and more pilot signals are needed. How to deploy pilot signals is a complex problem. The denser the pilot signals, the more accurate the channel estimation, but the more resources they occupy.

[0088] In the current 3GPP LTE and 5G NR communication systems, data symbols and pilot symbols (reference signals) are placed in different resource locations, which are independent and orthogonal to each other in time and frequency resources, that is, only one of data symbols or pilot symbols can be placed in the same resource location. Please refer to Fig. 4. Fig. 4 illustrates a schematic diagram of pilot deployment and channel estimation in current LTE and 5G NR. The receiver in LTE and 5G NR is a signal processing module. As shown in Figure 4, pilot deployment and channel estimation may include the following processing procedures:

[0089] Step 1: Perform channel estimation (LS (Least Squre) algorithm, etc.) on pilot symbols to accurately estimate the channel response of pilot symbols in time-frequency domain.

[0090] Step 2: Use interpolation algorithm to extend the channel response of the pilot position to data symbols.

[0091] Step 3: Based on the channel response of the data symbols and the received signals, the transmission signal is recovered by using the equalization demodulation algorithm.

[0092] In addition to the pilot deployment mode orthogonal to data symbols adopted in LTE and 5G NR, a Superimposed pilot (SP) deployment mode has also been widely studied. Superimposed pilot (SP) is deployed in such a way that data symbols and pilot symbols are superimposed and transmitted at the same time, which can avoid the decrease of spectrum efficiency or data rate caused by pilot overhead.

[0093] Please refer to Fig. 5 and Fig. 6. Fig. 5 illustrates a Superimposed pilot (SP) deployment mode A. Fig. 6 illustrates SP deployment mode B. In the SP deployment mode B, the pilot and data are partially overlapped and pilots are orthogonal.

[0094] As shown in Figure 5 and Figure 6, the current SP technology can be divided into two schemes, A and B, in which data and pilot are superimposed according to different weights. A is that for the same layer, all data are superimposed with pilots, which belongs to complete superposition. Another B is that for the same layer, the pilot weight of some time-frequency resources is 0, which belongs to partial superposition.

[0095] In the following description, this disclosure refers to the orthogonal allocation of pilot and data in the existing 4G / 5G system as a traditional non- Superimposed way (as shown in Figure 4); When SP deployment is adopted as shown in Figure 5, the pilot allocation mode in which pilots and data are completely superimposed is called SP complete superposition mode. When SP deployment is adopted as shown in Figure 6, the pilot allocation mode in which pilot and data are partially superimposed is called SP partial superposition mode. They belong to different superposition modes of pilot and data.

[0096] In the above scenario, both the network side equipment and the user side equipment only support one pilot pattern, so how to configure the flexible SP pilot pattern is an urgent problem.

[0097] The present disclosure relates to the field of communication, and more particularly, to a method performed by a first node in a communication system, a method performed by a second node in the communication system, the first node, and the second node.

[0098] Various embodiments of the present disclosure provide a method performed by a second node in a communication system, comprising: receiving first configuration information for first data from a first node; obtaining first predicted data signals of various layers of the first data based on the first configuration information; determining a first set including the first predicted data signal of at least one layer of the various layers and a second set including the first predicted data signals of one or more layers of multiple layers based on an accuracy of the first predicted data signals of the various layers; obtaining a third set based on the first configuration information and the first set, wherein the third set includes second predicted data signals corresponding to the one or more layers; obtaining a fourth set based on the second set and the third set, wherein the fourth set includes third predicted data signals corresponding to the one or more layers; obtaining soft bits of the first data based on the first set and the fourth set; wherein the first configuration information includes first information and / or second information, wherein the first information includes information associated with a pilot pattern of a pilot signal of a layer, and the second information includes information associated with a transmission power corresponding to a data signal and / or a pilot signal of a layer of the first node.

[0099] Through the above scheme, the SP pilot pattern and related configuration parameters supporting SP transmission can be flexibly defined, SP deployment can be supported, interference between data and pilots during SP transmission can be reduced, spectrum efficiency brought by SP transmission can be improved, and it can adapt to different transmission environments. Moreover, the BER performance of the low accuracy layer can be effectively improved through the processing of the receiver.

[0100] It can be understood that the above technical problems are only examples of technical problems that can be solved by various embodiments of the present disclosure, and are not limitations on the technical problems that can be solved by the present disclosure. Any technical problems that can be solved by the technical scheme of the present disclosure belong to the technical problems that can be solved by the present disclosure. In the following, some technical problems that can be solved by the present disclosure are shown by way of example.

[0101] For example, in the pilot deployment mode adopted by LTE and 5G NR in the current 3GPP standard, when the total transmission resources are fixed, the relationship between pilot and data is competitive for transmission resources, and it is a trade-off relationship. Although increasing the pilot resource overhead can bring more accurate channel estimation, the resources used to transmit data are reduced and the utilization rate of data transmission resources is low. On the contrary, reducing the pilot resource overhead will lead to the decline of the accuracy of channel estimation and the performance of the receiver. In a word, the resource competition between pilot and data becomes the bottleneck of throughput improvement.

[0102] For another example, when the deployment mode of Superimposed pilot (SP) is adopted, the pilot and data are superimposed together, and the pilot and data interfere with each other. At present, the related research in academic circles and industry on how to superimpose the pilot and data, and how to estimate and detect the channel after the superposition of the pilot and data is still in the primary stage, and there is no standardized definition at present. For another example, although the deployment mode of Superimposed pilot (SP) can solve the resource competition problem between pilot and data. However, at present, the traditional receiver processing flow, as shown in Figure 4, has defects in processing the superimposed pilot. Non-orthogonality between the pilot and the data will cause the received signals of the data and the pilot to be mixed together and cannot be separated. In addition, because the constellation points selected for transmitting the data symbols are statistically uniformly distributed, the received signals of the data will cause totally unknown strong interference to the received signals of the pilot. In channel estimation step 1 in Fig. 4, strong data and interlayer interference will remain in the channel estimation result, and errors will propagate and accumulate in steps 2 and 3, which will lead to the performance degradation of equalization result, the data bit error rate (BER) increase, and the gain brought by the improvement of SP spectrum efficiency cannot be obtained.

[0103] For another example, the current deployment mode of Superimposed pilot (SP) adopts the complete superposition of pilot and data on time-frequency resources, as shown in Figure 5. The more flexible superposition mode of pilot and data is not considered to adapt to different scenarios in channel transmission, such as different frequency selective fading and Doppler spectrum. The scenario of partial superposition (SP partial superposition mode) is shown in Figure 6.

[0104] For another example, for the deployment mode of Superimposed pilot (SP), the existing AI MIMO receiver is an end-to-end model, and the channel detection is a black-box processing, so the performance cannot meet the requirements of reliable communication transmission.

[0105] For another example, in the existing scheme, orthogonal data and pilot transmission schemes are generally used for pilot and data transmission. In order to save pilot resources, pilot patterns are generally designed reasonably for the scenarios supported by communication. In order to improve the receiving performance of SP pilots and resist the interference of data on pilots, the receivers of superimposed pilots are mostly iterative structures or AI receivers, but they are not enhanced for different SP scenarios.

[0106] Various embodiments of the present disclosure propose a communication mechanism for Superimposed pilot (SP). By defining a flexible SP pilot pattern, defining relevant configuration parameters supporting SP transmission, and the protocol flow of parameter interaction, SP deployment can be supported, interference between data and pilots during SP can be reduced, spectrum efficiency brought by SP transmission can be improved, and different transmission environments can be adapted.

[0107] Various embodiments of the present disclosure propose an AI MIMO receiver scheme applied to the SP partial superposition mode of pilot and data superposition. The scheme aims to suppress the interference of data signals to pilot signals in this scenario, and optimizes the design for three problems of the existing AI MIMO receiver, which not only improves the receiving performance, but also enhances the interpretability of the system. This receiver scheme will make SP a better solution to the resource competition bottleneck between pilot and data.

[0108] Various embodiments of the present disclosure analyze the SP partial superposition mode based on data features, and design an AI MIMO receiver model. Vision Transformer model is introduced as the AI backbone network, and on this basis, the input feature layout and training loss function are designed, and the model structure is optimized. The BER performance of the receiver applied to SP partial superposition mode is obviously better than that of the AI MIMO receiver designed for SP complete superposition mode in the paper.

[0109] Various embodiments of the present disclosure propose a strategy for fusion enhancement of low accuracy spatial layers. Firstly, according to the prediction result of model 1, the spatial layer is divided into two categories: a high accuracy layer and a low accuracy layer. Then, an additional AI model, Low Accuracy Layer AI Enhancer, is designed, and the prediction result of high accuracy layer is used as input to make secondary prediction of the low accuracy layer. Finally, the BER performance of the low accuracy layer is effectively improved by combining the results of the two predictions.

[0110] The pilot and data superposition mode of the SP partial superposition mode is between the traditional non-superposition mode and the SP complete superposition mode, so various embodiments of the present disclosure propose a receiving scheme combining the traditional non-superposition mode 5G NR pipeline receiver and the SP complete superposition mode end-to-end AI MIMO receiver. In this disclosure, some differentiable classical signal processing modules in the 5G NR pipeline receiver are integrated into the AI model for end-to-end training, which increases the interpretability of the model while ensuring the performance.

[0111] Various embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. In this disclosure, the weight related information may include the weight coefficient or the ratio of the weight coefficient, etc. In addition, the weight coefficient may be used interchangeably with the weight, power factor, weight factor, power weight, weight ratio, power weight information, or may be replaced by other names. The pilot pattern index may be used interchangeably with the pilot pattern number, pilot number, pilot pattern information, etc., or may be replaced by other names, which is not limited by this disclosure. Moreover, in the subsequent description of this disclosure, downlink data transmission is described as an example, and various embodiments of this disclosure can also be applied to uplink data transmission, which is not limited by this disclosure.

[0112] 1) Overall scheme design

[0113] The superposition mode of pilot and data is related to channel conditions, network deployment and services, which has a direct impact on data detection accuracy, channel estimation accuracy, transmission reliability, frequency efficiency and system throughput. The channel conditions, network deployment, services and other factors that affect the superposition of pilot and data are defined as "application scenarios". A variety of network indicators, such as data detection accuracy, channel estimation accuracy, data transmission reliability, spectrum efficiency, system throughput and so on, which are affected by pilot and data mode, are defined as "performance metrics". The present disclosure may provide a determination method of pilot and data superposition mode determined by based on multi-performance metric and identified by the application scenario, which includes the process of joint identification of application scenario by the sending end and the receiving end, the process of determining the superposition mode of pilot and data, and the process of transmitting and receiving signals sent by the sending end and the receiving end through the superposition mode of pilot and data.

[0114] Fig. 7 illustrates an overall block diagram according to an embodiment of the present disclosure.

[0115] Referring to Fig. 7, there are three functional parts: scenario recognition, configuration and function. The specific processes involved in each functional part are shown in Figures 7a, 7b and 7c respectively, and will be introduced in detail below.

[0116] Without losing generality, the sending end and the receiving end in the communication system can be communication entities such as network side, terminal side and relay node, etc. Figure 7c takes the network side and the terminal side as the sending end and the receiving end respectively as an example.

[0117] Without losing generality, the transmitting end and the receiving end in the communication system can be one communication entity or multiple communication entities. For example, multiple network transmission points send signals to the same terminal, one network transmission point sends signals to multiple terminals, or multiple network transmission points send signals to multiple terminals.

[0118] Fig. 7a illustrates a joint identification process of "application scenarios" according to an embodiment of the present disclosure.

[0119] As shown in Figure 7a, the joint identification process of "application scenario" by the sending end and the receiving end includes two processes: initial application scenario identification and online application scenario identification.

[0120] Initial application scenario identification is a process in which the sending end determines the application scenario and reaches a consensus based on the network deployment, capabilities of the sending end and the receiving end, auxiliary function information, service requirements, etc.

[0121] Specifically, application scenarios are identified based on network deployment situations such as transmission frequency bands, macro stations or small stations, indoor or outdoor, terrestrial or non-terrestrial systems, etc.

[0122] Specifically, application scenarios are identified based on capabilities such as the sending end's RF nominal performance metric, the receiving end's nominal performance metric, and whether AI signal processing is supported or not, etc.

[0123] Specifically, application scenarios are identified based on auxiliary information such as digital twinning, Integrated sensing and communication, and positioning functions, etc.

[0124] Specifically, application scenarios are identified based on service demand information such as a service type, a service volume and a network load. After the sending end or the receiving end completes the identification of the initial application scenario, they can reach a consensus on the initial application scenario through the preset criteria without additional interaction process.

[0125] Online application scenario identification is a process of determining application scenarios based on the measurement and interaction by the sending end and receiving end.

[0126] Specifically, the sending end can send measurement signals such as pilots superimposed with data or pilots not superimposed with data, and the receiving end can receive the measurement signals to determine the application scenarios.

[0127] Specifically, the receiving end can send measurement signals such as pilots superimposed with data or pilots not superimposed with data, and the sending end can receive the measurement signals to determine the application scenarios.

[0128] Specifically, the application scenario information known by the sending end can be sent by the sending end, so that the sending end and the receiving end can reach a consensus on the application scenario.

[0129] Specifically, the receiving end can send the application scenario information known by the receiving end, so that the transmitting and receiving ends can reach a consensus on the application scenario.

[0130] Fig. 7b illustrates the configuration process of the superposition mode of pilot and data according to an embodiment of the present disclosure.

[0131] As shown in Figure 7b, the process of determining the "superposition mode of pilot and data" by the sending end and the receiving end includes two types: initializing the superposition mode configuration of pilot and data, and online updating the superposition mode configuration of pilot and data. Each configuration process includes the process of determining parameters, and the process of configuring parameters and reaching a consensus.

[0132] The superposition modes of pilot and data include: a power weight of pilot and data, a superposition pattern of pilot and data, a frequency domain granularity of pilot superposition, a time domain granularity of pilot superposition, whether to spread code division, etc.

[0133] Fig. 7d illustrates an initialization pilot and data superposition configuration process according to an embodiment of the present disclosure.

[0134] As shown in Figure 7d, the configuration process of the superposition mode of the initial pilot and data is a process of determining the initial superposition mode of the pilot and data based on the identification of the initial application scenario and the optimal mode of statistical "performance metric" and reaching a consensus.

[0135] Specifically, several superposition mode parameters of pilots and data, such as the power weight of pilots and data, the superposition pattern of pilots and data, the frequency domain granularity of pilot superposition, the time domain granularity of pilot superposition, and whether to spread code division are predefined in the communication protocol. When the user initially accesses, the sending end and the receiving end adopt the initial SP parameters by default, or determine the initial SP parameters through system messages, or determine the initial SP parameters through semi-static configuration signaling when establishing the connection, the initial SP parameters including pilot pattern number, pilot and data weight factors, etc.

[0136] Specifically, if long term "performance metric" statistics are carried out for various "application scenarios" in actual network deployment, based on the initial application scenario identification, the preferred initial superposition mode of pilot and data is determined.

[0137] Fig. 7e illustrates the configuration process of online updating pilot and data superposition configuration according to an embodiment of the present disclosure

[0138] As shown in Figure 7e, online updating the configuration process of superposition mode of pilots and data is a process of determining the initial superposition mode of pilots and data based on the identification of online application scenarios and the optimal mode of "performance metric" and reaching a consensus. The configuration related to the superposition mode of pilot and data includes the power weight of pilot and data, the superposition pattern of pilot and data, the frequency domain granularity of pilot superposition, the time domain granularity of pilot superposition, whether to spread code and so on.

[0139] Specifically, based on the identification of online application scenarios, the sending end or the receiving end determines the preferred initial superposition mode of pilot and data to optimize the end-to-end "performance metric" and configure it to the receiving end or sending end through interactive signaling.

[0140] Specifically, based on the identification of online application scenarios, the sending end or the receiving end determines the preferred initial superposition mode of pilot and data by means of specific criteria or AI-based method, so as to optimize the end-to-end "performance metric".

[0141] Specifically, the specific criteria include, for example, determining the power weights of pilots and data based on the detected signal-to-noise ratio. For the application scenarios with poor signal-to-noise ratio, high pilot power weight is configured to ensure the accuracy of channel estimation, thus making the end-to-end channel estimation accuracy optimal.

[0142] Specifically, the specific criteria include, for example, determining the superposition pattern of pilot and data, frequency domain granularity of pilot superposition, and time domain granularity of pilot superposition based on channel time-varying and frequency selectivity, ect. For high time-varying application scenarios, smaller time-domain granularity is configured to ensure the accuracy of channel time-varying tracking, thus making the end-to-end channel estimation accuracy optimal.

[0143] Specifically, the methods of specific criteria include, for example, determining the power weights of pilots and data, the superposition pattern of pilots and data, the frequency domain granularity of pilot superposition, the time domain granularity of pilot superposition, whether to spread code division, etc., based on the reliability feedback of link transmission, etc. For the application scenarios with insufficient link transmission reliability, the combination configuration to improve transmission reliability is adopted.

[0144] Specifically, the specific criteria include, for example, based on the application scenario information such as the number of communication entities at the transmitting end and the number of communication entities at the receiving end, considering the mutual joint channel transmission gain or the same time-frequency interference, optimizing the joint "performance metric" of point-to-multipoint, multipoint-to- point , or multipoint-to-multipoint, and determining each end-to-end superposition mode of pilots and data.

[0145] Specifically, AI-based methods include, for example, based on supervised learning, semi-supervised learning and reinforcement learning, the preferred initial pilot and data superposition mode by the transmitting terminal or the receiving terminal is determined to optimize the end-to-end "performance metric".

[0146] Without losing generality, the above configuration information can be configured separately, or by a combination of multiple items.

[0147] Without losing generality, the above configuration information can be exchanged through broadcast information, semi-static configuration signaling, media Access control layer control unit, physical layer control signaling (including downlink control signaling (DCI) and uplink control signaling (UCI)), etc.

[0148] Fig. 7c illustrates the transmitting and receiving process of the transmitting end and the receiving end transmitting signals through the superposition of pilot and data according to an embodiment of the present disclosure.

[0149] As shown in Figure 7c, it is the "function" process, that is, the transmitting and receiving process in which the sending end and the receiving end send signals through the superposition of pilot and data.

[0150] The following is a concrete example of the online updating configuration process of the superposition mode of pilot and data.

[0151] Several pilot pattern formats and their serial numbers, as well as the weight factors of pilots and data, are predefined through the communication protocol. When the user initially accesses, the network configures initial SP parameters for the user, including the serial number of pilot pattern, the weight factor of pilots and data. The network uses the initial SP pattern and parameters for pilot and data transmission, and the user uses the initial SP parameters for parameter processing and receiving. The user measures the received data and pilot, and reports the measurement results to the network side. The network side dynamically adjusts SP parameters according to the measurement report of the user, and configures them to the user through relevant signaling. A specific implementation is shown in Fig. 22 and Fig. 23, the initial SP pattern information and data weight factor can be notified to the terminal equipment in one of three ways: (1) through the physical broadcast channel (PBCH); or (2) through the system information block (SIB) or (3) through the radio resource control (RRC) message; the terminal equipment can report its ability to support SP through RRC message; the dynamic updating of the corresponding SP pattern information and data weight factor can be realized by RRC message or DCI.

[0152] Fig. 7f illustrates an example in which the network side and the terminal side are respectively the transmitting end and the receiving end according to an embodiment of the present disclosure.

[0153] As shown in Figure 7f, the transmitting end and the receiving end perform the above operations referred to FIG. 7 to FIG. 7e. Furthermore, the transmitting end and the receiving end include at least one configuration for performing the above operations.

[0154] 2) Pilot pattern design

[0155] Please refer to Figs. 8 to 9. Fig. 8 illustrates a pilot pattern design according to an embodiment of the present disclosure, and Fig. 9 illustrates another pilot pattern design according to an embodiment of the present disclosure.

[0156] In Fig. 8, SP scheme B is adopted, and different interlayer pilots adopt orthogonal patterns (different interlayer pilots are time-frequency orthogonal). In Fig. 9, SP scheme B is adopted, and different interlayer pilots also adopt orthogonal patterns.

[0157] The above-mentioned communication system adopts SP scheme B, the pilot pattern with time-frequency orthogonality between layers, and defines one or more preset pilot patterns and the indexes in the protocol, so that only the index of the pattern is needed to transmit without transmitting the pattern itself, thus saving signaling parameter overhead.

[0158] Interlayer orthogonal pilots is used, so that the pilots of each layer only receive interference from the data of the same layer and / or other layers, and are not interfered by the pilots of other layers. Defining one or more preset pilot patterns in the protocol can enable the network side equipment to select the appropriate pilot pattern according to the user's channel and receiving conditions to dynamically configure the pilot pattern for the user.

[0159] As shown in Fig. 8, there are two pilot pattern configurations, in which pattern a (corresponding to the pattern on the left of Fig. 8) is suitable for users with high Doppler and rapid time change, and pattern b (corresponding to the pattern on the right of Fig. 8) is suitable for users with large multipath delay spread and severe frequency selective fading. However, what the two patterns have in common is that they all need to ensure that the pilots between different layers are time-frequency orthogonal. Two patterns are defined in the protocol, and users are informed by signaling. However, it is not limited to the specific example and number of orthogonal patterns shown in Fig. 8, for example, it can be extended to three optional pilot patterns in Fig. 9.

[0160] 3) Design of pilot and data weight

[0161] Furthermore, by designing the weight ratio of pilot and data in each layer, the interference increase and spectrum efficiency improvement are compromised to achieve the optimal communication capacity; the data weight of some or all pilot positions can even be configured to zero, and dynamically switch between SP and non-SP.

[0162]

[0163] The pilot signal and the data signal are superimposed according to the weight coefficient and the transmission signal is generated. D and P are the data signal and the pilot signal to be transmitted respectively, parameters and define the power weights of each other. In the process of data transmission, the power weight of pilot signal and data signal will affect the performance of receiver. When the channel transmission conditions are good, the channel can be accurately estimated with low pilot signal power. More transmission power is reserved for data signals to improve the transmission gain of the system. When the channel transmission conditions deteriorate, for example, when the UE is located at the edge of the cell or the wireless transmission channel is deeply fading, the signal-to-noise ratio (SNR) will drop sharply, which increases the difficulty of channel estimation and signal detection. At this time, it is necessary to increase the power of the pilot signal, or even set the data weight of the pilot position to zero, in order to improve the channel estimation and improve the performance of signal detection.

[0164] The cell-level parameters and define the initial weight coefficients. The initial weight coefficients need to be sent to the receiving end. On the basis of the initial value, each flow of each UE dynamically selects the appropriate weight coefficients. The weight coefficients can be adjusted based on the ACK / NACK result of downlink data, or through other measurements and measurement results, such as CQI, SINR, etc. When the number of NACK of downlink data exceeds the threshold in a given period, and / or some other measurements meet certain conditions, the power weight of the pilot signal is considered to be increased. On the contrary, it is reduced.

[0165] As an embodiment, the network side cannot only update the pilot pattern index and weight coefficient based on the feedback result or measurement result of downlink data transmission, but also update the pilot pattern index and weight coefficient based on the information fed back by the UE. For example, the network side can receive the first information sent by the UE, where the first information includes the pilot pattern index and / or weight related information recommended or suggested by the UE. The network side can update them according to the pilot pattern index and / or weight related information recommended or suggested by the UE.

[0166] 4) Information and signaling design

[0167] The network side and the UE terminal define corresponding signaling and processes, interact and transmit the following information:

[0168] (1) a network side sends initial pilot pattern information to a UE terminal;

[0169] (2) the network side sends the initial power weight information of data signal and the pilot signal to the UE terminal;

[0170] (3) the network side sends dynamically updated pilot pattern information to the UE terminal;

[0171] (4) the network side sends the dynamically updated power weight information of the data signal and the pilot signal to the UE terminal;

[0172] (5) The terminal side feeds back or reports the measurement information to the network side.

[0173] The above information can be combined into one, or can be split and completed through multiple signaling interaction processes.

[0174] When the user initially accesses, the base station side configures the initial pilot pattern to the user side through (1), configures initial pilot and data signal weights through (2), dynamically updates or reconfigures the pilot pattern index to the terminal through the signaling of (3), dynamically updates or reconfigures the pilot and data weight coefficients through the signaling of (4), and the terminal feeds back the reception quality or channel state information to the network side through (5).

[0175] The transmitting and receiving process done by the sending end and the receiving end through the superposition mode of pilot and data includes that the sending end sends pilot and signals based on the configured superposition mode of pilot and data, and the receiving end receives data based on the configured superposition mode of pilot and data.

[0176] Specifically, the sending end sends the pilot and the signal based on the configured superposition mode of the pilot and the data, including one or more communication entities transmitting signals to one or more communication entities. For example, multiple network transmission points send signals to the same terminal, one network transmission point sends signals to multiple terminals, or multiple network transmission points send signals to multiple terminals, etc.

[0177] When a communication entity sends signals to multiple communication entities, multiple receiving communication entities can only know the specific configuration of the superposition mode of pilots and data between the transmitting end and the present communication entity, or not only know the specific configuration of the superposition mode of pilots and data between the transmitting end and the present communication entity, but also know the specific configuration of the superposition mode of pilots and data between the transmitting end and other receiving communication entities.

[0178] Without losing generality, the way, that a receiving communication entity learns about the specific configuration of the superposition of pilots and data of other communication entities can be obtained through information interaction with the transmitting communication entity or through direct information interaction with the other communication entities.

[0179] When multiple communication entities send signals to one communication entity, multiple transmitting communication entities can only know the specific configuration of the superposition mode of pilots and data between the transmitting end and the present communication entity, or not only know the specific configuration of the superposition mode of pilots and data between the present transmitting end and the receiving communication entity, but also know the specific configuration of the superposition mode of pilots and data between other transmitting ends and the receiving communication entity.

[0180] Specifically, the receiving end receives the data based on the superposition of the configured pilot and data, and can receive the signal based on channel processing, or based on AI, or based on signal processing combined with AI. The invention adopts a mode based on signal processing combined with AI to receive signals. Among them, the signal processing part preprocesses the received superimposed signal of pilot and data, and its function is to enhance the data, reduce the difficulty of model training and reduce the model size. After the preprocessed data is input into the AI-based receiver processing module, the channel estimation results, signal detection results, application scenario identification results or the optimal superposition mode of pilot and data are obtained through spatial layer fusion enhanced architecture AI model; the channel feature measurement extraction part extracts the channel features by analyzing the channel estimation results, which will be used as the input information of the next data preprocessing characteristics..

[0181] The following is a concrete example of the online updating configuration process of the superposition mode of pilot and data.

[0182] As an embodiment, after the UE accesses, the UE can report the SP capability, and the base station can configure SP transmission for the terminal with SP capability. For example, the base station may receive second information from the UE, wherein the second information includes information related to whether the UE supports superimposed pilot (SP) transmission.

[0183] 5) receiver scheme

[0184] The invention also provides an AI MIMO receiver scheme based on spatial layer fusion enhancement, and a multi-precision neural network model based on ViT is used for extracting channel features and their correlations in frequency and time domains, and improving decoding accuracy through structural design that adapts to different signal-to-noise ratio features of data. This scheme is applied to the SP partial superposition of pilot and data, including two parts: a spatial layer fusion enhanced AI modem receiver and a decoder. The former completes the process of channel estimation, equalization and demodulation in an integrated way, and the obtained soft bits are sent to the decoder for decoding to recover the original information bits.

[0185] Please refer to Fig. 11. Fig. 11 illustrates an example structure of a spatial layer fusion enhanced AI modem receiver according to an embodiment of the present disclosure. The spatial layer fusion enhanced AI MIMO receiver may include four modules:

[0186] Module 0-1: Data preprocessing module based on channel awareness mechanism, which uses signal processing technology to enhance the input original data and features, including data enhancement, input feature enhancement and training label enhancement, and finally outputs the enhanced data and features to the receiver.

[0187] Module 0-2: channel feature measurement and extraction module, which uses the channel result estimated in the previous frame to complete the measurement and extraction of channel features, and finally outputs it to the data preprocessing module for feature input in the next frame.

[0188] Module 1: End-to-End AI receiver (E2E AI Receiver), which preliminarily predicts the soft bits and modulation symbols of the transmission data of all spatial layers.

[0189] Module 2: High Accuracy Layer Selection, which uses the output of module 1 to classify the spatial layers into two categories by using the error vector magnitude (EVM) metric. For the high accuracy spatial layer, the prediction result of module 1 can be used as the output of the receiver, while the prediction result of the low accuracy spatial layer needs to be further improved.

[0190] Module 3: Low Accuracy Layer AI Enhancer, which uses the AI model designed by iterative enhancement idea to add the modulation symbol result of the predicted transmission data of the high accuracy layer to the model input, output the channel measurement result and further predicts the transmission data of the low accuracy layer.

[0191] Module 4: Low Accuracy Layer Ensemble, which fuses and enhances the low accuracy spatial layer results output by modules 1 and 3, and the enhanced results are used as the output of the receiver.

[0192] Next, modules 1 to 4 will be described in detail with the attached drawings.

[0193] User initial access obtains initial SP parameter configuration by receiving broadcast messages from the network device. The UE receives and detects the downlink data according to these parameters, and measures the channel quality and / or reception quality in the process, and feeds it back to the network side through signaling. The network side decides whether to reconfigure the SP parameters for the UE through a certain decision-making mechanism. If reconfiguration is needed, the SP parameters are updated through the reconfiguration process.

[0194] Please refer to Fig. 11a. Fig. 11a illustrates another example structure of a spatial layer fusion enhanced AI modem receiver according to an embodiment of the present disclosure.

[0195] In Fig. 11a, H is a high-precision port index set, L is a low-precision port index set, X is transmission symbols, Y is reception symbols, P is pilot symbols, is a extracted received pilot, is estimated signal bits, and is the correct decoding probabilities.

[0196] As shown in Fig. 11a, inspired by image processing, this disclosure regards the channel as a fixed-size image, and regards the response of the channel in the antenna domain as the features of pixel points, and proposes a multi-precision neural network receiver based on ViT, as shown in Fig. 11a. The whole architecture consists two parts: high accuracy port decoder aims to recognize and extract features from the superimposed signals to accurately estimate the transmitted data of high accuracy ports; and the low accuracy port enhancer aims to remove interference, extract pilot using high accuracy port results and update signal decoding results of low accuracy ports by the subsequent channel equalization and fractional fusion module.

[0197] Please refer to Fig. 11d, which illustrates another example structure of the spatial layer fusion enhanced AI modem receiver according to an embodiment of the present disclosure. In Fig. 11d, the input of AI receiver includes received signal, weight coefficient, pilot pattern index and Modulation and Coding Scheme (MCS). MCS is used to determine the threshold of high accuracy layer selection.

[0198] Please refer to Fig. 11f, which illustrates another example structure of the spatial layer fusion enhanced AI modem receiver according to an embodiment of the present disclosure. In Fig. 11f, the input of AI receiver includes received signal, weight coefficient, pilot pattern index and Modulation and Coding Scheme (MCS). MCS is used to determine the threshold of high accuracy layer selection. In Fig. 11f, the channel feature measurement module is used to measure the channel features. The input of the module is the received signal and the results of channel estimation of each layer of the low accuracy layer enhancer. The output of the module is the results of channel feature measurement, including frequency offset, coherent time and coherent band blocks. The output of the module is used for data preprocessing.

[0199] Specifically, the specific implementation method of each module is as follows:

[0200] Please refer to Fig. 11. Fig. 11 illustrates an E2E AI receiver according to an embodiment of the present disclosure.

[0201] As shown in Fig. 11, the receiver is implemented as follows:

[0202] Module 0-1 is a data preprocessing process of signal processing technology based on channel awareness mechanism, and the flow chart is as follows. The inputs of the module are the superimposed received signal of pilot and data, SP parameter pilot pattern index and pilot / data power allocation weight coefficient, application scenario information, Modulation and Coding Scheme (MCS), channel feature information of the previous frame and label data of training samples (transmission data bit). This module includes four sub-modules: pilot mapping, data enhancement, input feature enhancement and training label enhancement. The pilot mapping sub-module uses SP pilot pattern index and communication protocol to generate pilot transmission signals. The data enhancement sub-module performs signal transformation on the input training data, MCS information to generate more training data in line with the communication process, so as to enrich the application scenarios, improve the model performance and enhance the generalization ability. The input feature enhancement sub-module fuses the input original features with channel feature information of the previous frame to generate secondary features with physical significance, which are merged with the original features and output to the receiver. The training label enhancement sub-module transforms the input original labels into more forms, which provides more information for model training. The purpose of input feature enhancement and training label enhancement is to reduce the training difficulty of AI receiver model, and then improve the receiving performance and make the model lighter.

[0203] A more specific embodiment of module 0-1 is as follows:

[0204] The data enhancement method includes: a. Gaussian white noise is added to the received signal according to the signal-to-noise ratio; b. cutting input and label data in time domain / frequency domain; c. analyzing the pilot signal, and introducing position transformation of input and label data, such as time domain / frequency domain offset and time domain / frequency domain interchange, on the premise that the pilot signal is unchanged; d. estimating the channel response H by using the pilot signal, the label transmission data and the received signal, and generating more training data based on the H and the random transmitted data.

[0205] The input feature enhancement methods include: a. ignoring data interference, directly applying the 5G NR channel estimation technology (LS, MMSE estimation) to the pilot signal and the received signal, and generating an interfered channel estimation as a secondary feature; b. the coherent time feature of time selective fading are calculated using the position and velocity information in the application scene, and the coherent time feature can also be measured by module 0-2.; c. the coherence bandwidth feature of frequency selective fading are estimated using the network deployment information in the application scenario (such as city / village / mountain area, etc.), and the coherence bandwidth feature can also be measured by module 0-2; d. frequency offset characteristics estimated by module 0-2.

[0206] As shown in Figure 11e, the training label enhancement method comprises: a. modulating the transmitted data bit into constellation points according to MCS allocation, and adding complex domain information; b. the pilot signal and the data constellation points being weighted and superimposed according to the SP parameter pilot / data power allocation weight coefficient to restore the transmission signal of the transmitting end.

[0207] Module 0-2 is the measurement and extraction process of channel features of baseband signals. The input of this module is the channel estimation results of each data transport layer output by module 3. This module includes two sub-modules, the measurement of coherence time and coherence bandwidth, and frequency offset estimation. Its result will be fed back to module 0-1 as data enhancement information for the next frame data preprocessing. The coherent time features are obtained by measuring the Doppler frequency shift of the channel. Coherence bandwidth features are obtained by measuring the power delay spectrum (PDP) of the channel. One implementation of frequency offset estimation is shown in Fig. 21. On the one hand, it calculates the frequency offset in the past time according to the channel estimation output from the low-accuracy spatial layer AI enhancer; on the other hand, it preliminarily estimates the frequency offset at the current time according to the locally generated pilot signal and the received signal. Next, perform a moving average of the estimated the frequency offset at the current time and the frequency offset in the past time. The coefficients used in the moving average need to be adjusted adaptively according to the CRC results, and the corresponding moving average coefficients need to be increased if the CRC results are correct historical frequency offset estimates.

[0208] Module 1 is an end-to-end AI model, and the flow chart is as follows. Based on the preprocessed data and features of module 0-1, this model predicts the data bits to be sent. The model consists of three sub-modules, input feature layer (Embedding), encoder (Encoder) and decoder (Decoder). The pilot and received signals inputted by the model are both complex domain signals, and the input feature layer is responsible for reconstructing and mapping the two signals into the original features which is suitable for Encoder. The Encoder is responsible for gradually abstracting the original features into deep features. The Decoder is responsible for simultaneously predicting the data symbols of all spatial layers transmission according to the features coming from Encoder.

[0209] A more detailed model structure of module 1 is shown in the following figure 13. In this disclosure, Vision Transformer is used as the backbone network. Compared with the network structure based on CNN, Transformer is better at using information in the global scope. Next, the three sub-modules are introduced in turn.

[0210] Sub-module 1: Embedding layer. Both the input received signal Y and the Pilot contain four dimensions of information, namely, frequency domain, time domain, spatial domain and real and imaginary parts. The frequency domain corresponds to the subcarriers of MIMO-OFDM system, the time domain corresponds to the symbols, and the spatial domain corresponds to the transmitted spatial layer and the received multi-antenna signals. The present disclosure designs an input feature arrangement format:

[0211] - The frequency domain and time domain dimensions are combined as the sequence dimension (width: Freq×Time) of transformer.

[0212] - The spatial domain and the imaginary part and the real part are combined as the channel dimension, and the input Y and Pilot signals are combined in the channel dimension (width: TxLayer×2+RxAnt×2).

[0213] - The input features are arranged in this way because:

[0214] - Transformer's self-attention operation can extract and merge similar features along the sequence dimension. However, in the input time-frequency resource block, there are some time-frequency positions with the same pilot symbols and similar received signals. Putting the time domain and frequency domain in the sequence dimension is convenient for self-attention to combine the features of these time-frequency resources to complete the receiving work together.

[0215] - The input and output of the model keep the same width in frequency domain and time domain, but the width changes in spatial domain.

[0216] Embedding layer extends the channel dimension of input features to the width C of hidden layer by linear projection.

[0217] Sub-module 2: Encoder sub-module is mainly the superposition of Transformer Block. Each Transformer Block contains a multi-head self-attention layer that globally extracts and merges similar features along the sequence dimension, and a fully connected layer (FFN) that mixes channel dimension features. On this basis, the feature fusion operation is added in this disclosure, and the output of each Transformer Block is combined and then decodes it. It is generally believed that the low-level features of the network contain more details, while the high-level features contain more abstract common features, and the combination of them can enrich the hierarchy of feature expression. Especially in the communication receiving task, because the data symbols sent by each time-frequency point are different, the similarity of the received signals between time-frequency points is low, and the input features are very detailed. Therefore, it is beneficial to the decoding process for the encoder to keep low-level features and high-level features.

[0218] The Encoder submodule uses relative position encoding. The coherent bandwidth and coherence time features output by module 0 can be used to guide the generation of relative position codes. Specifically, within the coherent bandwidth and coherence time range, the correlation of channel response is very strong, so it is necessary to use fine-grained relative position coding, while outside the range, the granularity of relative position coding is gradually enlarged.

[0219] Sub-module 3: Decoder sub-module is lightweight, which first mixes the low-level and high-level features of the encoder through an MLP layer and then outputs it through an MLP layer. The disclosure uses a multi-task way to train the network:

[0220] - Task 1 is a regression task, with the constellation point label constructed by module 0 as the target, and the loss function adopts L1Loss. This task adds modulation information in complex domain to model training. This task mainly plays a role in the middle and early stage of training, which can obviously accelerate the convergence of the network.

[0221] - The second task is a binary classification task, which predicts the bit value of the transmitted data, and the loss function adopts Binary Cross Entropy Loss. The second task is the task of end-to-end training, which mainly plays a role in the later stage of training, aiming at directly improving the performance of the model.

[0222] The invention provides a method for reducing the computational complexity of a ViT receiver by using the coherence time and coherence bandwidth features of a wireless channel. The received signals whose time interval is greater than the coherence time and whose frequency interval is greater than coherence bandwidth have little correlation, so the ViT receiver can skip the attention calculation between such signals, which has little impact on the performance. By reducing the number of attention calculations, the computational complexity of ViT can be reduced. Specifically, the coherence time and coherence bandwidth features come from the output of module 0-1; as shown in Fig. 24, for the signal received on any resource unit (RE) (for example, it can be called the first time-frequency unit or the central resource unit), attention calculation is only performed on the signals received on the high correlation RE within the coherence time and coherence bandwidth, and attention calculation is not performed on the signals received on the RE outside the coherence time or coherence bandwidth.

[0223] The specific implementation of module 2 is as follows.

[0224] Based on the accuracy of all spatial layers output by module 1, module 2 uses thresholds to divide spatial layers into two categories: high accuracy layers and low accuracy layers. The specific flow chart is as follows, which is divided into four steps:

[0225] Step 1: Set the accuracy threshold (for example, it can be the first preset condition or the third preset condition) according to the target bit error rate and error vector amplitude (EVM). Select the spatial layers with accuracy higher than the threshold, and define them as a set of high accuracy layer. Other layers belong to a set of the low accuracy layers.

[0226] In this step, in order to distinguish between high and low accuracy layers, it is necessary to choose appropriate metric criteria. A step of selecting appropriate metric criteria and thresholds is as follows:

[0227] Step 1.1: Considering that the demodulated signal conforms to a certain constellation distribution, the average EVM can be selected as the metric criterion for the quality evaluation of the demodulated signal.

[0228] Please refer to Fig. 14a, which illustrates the definition of EVM. The value of EVM is the square root of the ratio of the error power (Perror) between the detected symbol and the standard constellation point to the average power Pref of the standard constellation point, that is .

[0229] The average EVM is defined as the average EVM of all detected symbols in each layer, that is . Wherein M is the symbol number of each layer, n is the layer number, and i is the symbol number.

[0230] Step 1.2: The relationship between signal-to-noise ratio (SNR) and bit error rate (BER) at each MCS level can be obtained by link simulation (LLS), and the SNR threshold is determined according to the input MCS level, which is the minimum SNR that meets the target BER.

[0231] As shown in Fig. 14b, different MCS levels, SNR and BER curves are also different. When meeting certain BER requirements, different MCS levels correspond to different SNR thresholds.

[0232] Step 1.3: As shown in Figure 14b, according to the relationship between EVM and SNR, , determine the EVM threshold (for example, it can be the third preset condition) to distinguish the high accuracy layer from the low accuracy layer.

[0233] Step 2: If all spatial layers belong to the set of high accuracy layers, it is considered that the accuracy is up to standard, and the enhancement operation of modules 3 and 4 is no longer needed.

[0234] Step 3: Set the threshold (for example, it can be the second preset condition or the fourth preset condition) of the minimum number of high accuracy layers. If the number of high accuracy layers is too small, the AI model of module 3 can obtain less additional information than that of module 1, and the final enhancement effect is limited. The recommended default value is half the number of spatial layers.

[0235] Step 4: If the number of high accuracy layers is greater than the threshold set in step 3, the division of high accuracy layers and low accuracy layers ends. Otherwise, it is necessary to continuously select the optimal layer from the set of the low accuracy layers (for example, the element with the lowest bit error rate in the set of the low accuracy layers) and supplement it to the set of the high accuracy layers until the minimum number threshold is met.

[0236] The specific process of another module 2 using EVM is as follows, which is also divided into four steps:

[0237] Step 1: Calculate EVM

[0238] Input: data symbol; output: the average EVM value of each layer.

[0239] Step 2: Count the number of layers meeting the absolute threshold.

[0240] Input: average EVM value and MCS level of each layer.

[0241] Output: the number of layers that meet the absolute threshold.

[0242] Function: the performance of different MCS levels is different, and the absolute threshold can be obtained from MCS levels. According to the EVM absolute threshold, the number of layers meeting the threshold is determined.

[0243] Step 3: dynamically adjust the threshold.

[0244] Judgment method:

[0245] (1) If the average EVM values of all layers meet the absolute threshold, the layer with the worst average EVM is regarded as the low accuracy layer.

[0246] (2) If the average EVM values of all layers do not meet the absolute threshold, the layer with the optimal average EVM is regarded as the high accuracy layer.

[0247] (3) Other cases: The layer whose average EVM does not meet the absolute threshold is regarded as the low accuracy layer.

[0248] Step 4: Output the result.

[0249] Output: data symbols of high accuracy layer, soft bits of high accuracy layer and soft bits of low accuracy layer.

[0250] The specific implementation of module 3 is as follows.

[0251] Module 3 is an AI Enhancer model designed based on the idea of iterative enhancement. Compared with the E2E receiver of module 1, the input information of the Enhancer model is increased, and the prediction results of the high accuracy layers of module 1 X1highis additionally introduced, while the output information is reduced, and only the transmission data of the low accuracy layers X2low is predicted, so that the overall task difficulty is reduced and the expected performance is higher. The reason why the input of the Enhancer only adds the high accuracy layer results of module 1 instead of all the spatial layer results is to prevent the prediction errors of the low accuracy layer from further accumulating in module 3 and deteriorating the performance. The two thresholds used to divide high accuracy layers in module 2 can also be used as hyperparameters for training in module 3 for joint optimization.

[0252] The structure of the Enhancer model is pipeline module, which is no longer an end-to-end AI model. The idea of structural design is that the main contradiction between pilot and data superimposed scenario 3 is that accurate channel estimation cannot be performed directly, because the received signals of all data layers are mixed with the received signals of pilot. Once the pilot is separated from the received signals of all data layers, scenario 3 can be simplified to scenario 1, and then the 5G NR pipeline receiver and AI receiver technology of scenario 1 can be utilized. Therefore, the Enhancer model designed in this disclosure includes three modules, a pilot and received signal separation module, a channel estimation module (from 5G NR channel estimation algorithm) and an equalizer module (AI equalizer). The Pipeline module structure has two advantages:

[0253] - Strong interpretability. The function of the module fits the communication process, and the output has physical significance, which is convenient for problem analysis and metric statistics.

[0254] - More flexible and easy to deploy. All modules can be combined for end-to-end training, or each module can be trained and upgraded separately.

[0255] The advantage of end-to-end training is that it only needs the basic input and output data of the receiver (Y, Pilot, X), but the disadvantage is that the training complexity is higher and it is suitable for off-line training. The advantage of module training alone is that the complexity is lower than that of the whole model training, and it can be used for online training, but the disadvantage is that it needs to collect the label data of the intermediate state Ypilot. Ypilotdata can be collected by simulation, but the simulation is different from the real environment of the cell. In the real environment, Ypilotcan only be collected by only transmitting pilot signal, while Y needs to be collected by transmitting pilot and data at the same time, which conflicts in time-frequency resources and can only be collected by approximate method. For example, when the terminal is moving at a low speed, adjacent symbol channels are similar, so adjacent symbols, one transmitting single pilot and one transmitting pilot and data, can be used to collect Ypilotand Y.

[0256] The E2E receiver adopts pipeline module structure, which has the following problems: E2E receiver, as the initial estimation module, lacks knowledge of transmission data X, only relies on input Y and Pilot, and the separated Ypilotis inaccurate. The following describes each module in turn:

[0257] Module 1: separation of pilot and received signals, and the logic is Ypilot= Sep (Y, Pilot, Xhigh). The model adopts the structure of Vision Transformer in Module 1. In order to support multiple pilot patterns and power mixing factors in a single model at the same time, in addition to mixing training data, this disclosure also adds pilot pattern index and power mixing factor to model features, reducing the difficulty of the task.

[0258] Module 2: Channel estimation, the logic is H = CE (Pilot, Ypilot). This disclosure recommends using the Least Square channel estimation and linear interpolation algorithm in the 5G NR receiver. The advantage of this method is low complexity, and it can be differentiated and embedded into AI model for end-to-end training. The formula of LS channel estimation is channel response H = Ypilot / Pilot. The accurate channel estimation result of module 2 can also be used as the output of the receiver. Accurate channel estimation results can be used to assist the evaluation of application scenarios and the selection of superposition modes of pilots and data.

[0259] Module 3: equalizer, the logic is Xlow= EQ (H, Xhigh, Y-Ypilot). The recommendation of this disclosure is to use an AI-based equalizer, because the input H has a certain error (the LS channel estimation complexity of module 2 is low, and noise is not considered), and the input Xhighis not 100% accurate. The AI-based equalizer can improve the output performance and robustness of the module through supervised learning and data enhancement methods (such as adding random noise to the input).

[0260] The concrete implementation of module 4 is as follows.

[0261] Module 4 aims to fuse the probability per bit of the low accuracy spatial layers output by the classifier of module 1 and the probability per bit output by the classifier of module 3, and finally improve the hard decision accuracy of the low accuracy layers. It is divided into three steps:

[0262] Step 1: Set the fusion coefficient alpha of module 1 and module 3. The setting method is to list a series of candidate values manually, and the optimal value is selected based on the criterion that the output accuracy of module 4 is the highest on the training set data.

[0263] Step 2: Linear fuse the probability per bit output by modules 1 and 3 with alpha.

[0264] Herein alpha is selected according to EVM, and the maximum value is 1 / 2.

[0265] Step 3: Use the fused probability and threshold to make bit hard decision.

[0266] Specific embodiments of the signaling processing flow of various embodiments of the present disclosure:

[0267] As for the pilot pattern, both the network and UE prestore the information of various pilot patterns supported, and the network only needs to send the serial number of the selected pilot pattern.

[0268] About the transmitting of initial parameters:

[0269] The initial parameters include initial pilot pattern information and initial power weight coefficient.

[0270] One way to achieve this is to use the system broadcast of the cell to send the initial parameters to the UE, such as shown in Fig. 17.

[0271] Another implementation method is to send the initial parameters to the UE through the higher layer message of the UE, for example, through a radio resource control (RRC) message of Layer 3, as shown in Figure 18.

[0272] About the transmitting of dynamic parameters:

[0273] Dynamic parameters include dynamically selected pilot pattern information and power weight coefficient. As an embodiment, the dynamic parameters can be sent to the UE through the message of the medium access control (MAC) layer. As shown in Fig. 19. As another embodiment, the dynamic parameters can also be sent to the UE through a higher layer message, such as an RRC message of Layer 3, as shown in Figure 20.

[0274] The pilot and data superposition pattern based on Fig. 6 is compared with the scheme of the embodiment of the present disclosure as follows.

[0275] Based on the superposition pattern of pilot and data in Figure 6, the pilot weight coefficient is 1.6 and the data weight coefficient is 1.0, and the training data set (Y, Pilot, X) is generated by system simulation. When only the E2E receiver of module 1 is used for receiving, the bit accuracy of verification set reaches 97.692%. When using complete scheme modules 1-4, layers 3 and 4 are fused and enhanced as low accuracy layers, and the bit accuracy is improved to 97.702%.

[0276]

[0277] Fig. 25 illustrates a block diagram of a UE according to various embodiments of the present disclosure. Furthermore, the UE of Fig. 25 corresponds to the UE of Fig. 1 and Fig. 3.

[0278] As shown in Fig. 25, the UE according to an embodiment may include a transceiver 2510, a memory 2520, and a processor 2530. The transceiver 2510, the memory 2520, and the processor 2530 of the UE may operate according to a communication method of the UE described above. However, the components of the UE are not limited thereto. For example, the UE may include more or fewer components than those described above. In addition, the processor 2530, the transceiver 2510, and the memory 2520 may be implemented as a single chip. Also, the processor 2530 may include at least one processor.

[0279] The transceiver 2510 collectively refers to a UE receiver and a UE transmitter, and may transmit / receive a signal to / from a base station or a network entity. The signal transmitted or received to or from the base station or a network entity may include control information and data. The transceiver 2510 may include a RF transmitter for up-converting and amplifying a frequency of a transmitted signal, and a RF receiver for amplifying low-noise and down-converting a frequency of a received signal. However, this is only an example of the transceiver 2510 and components of the transceiver 2510 are not limited to the RF transmitter and the RF receiver.

[0280] Also, the transceiver 2510 may receive and output, to the processor 2530, a signal through a wireless channel, and transmit a signal output from the processor 2530 through the wireless channel.

[0281] The memory 2520 may store a program and data required for operations of the UE. Also, the memory 2520 may store control information or data included in a signal obtained by the UE. The memory 2520 may be a storage medium, such as read-only memory (ROM), random access memory (RAM), a hard disk, a CD-ROM, and a DVD, or a combination of storage media.

[0282] The processor 2530 may control a series of processes such that the UE operates as described above. For example, the transceiver 2510 may receive a data signal including a control signal transmitted by the base station or the network entity, and the processor 2530 may determine a result of receiving the control signal and the data signal transmitted by the base station or the network entity.

[0283] Fig. 26 illustrates a block diagram of a base station or a network entity according to various embodiments of the present disclosure. Furthermore, the base station or the network entity of Fig. 26 corresponds to the network entity of Fig. 1, and the base station of Fig. 26 corresponds to the base station of Fig. 2.

[0284] As shown in Fig. 26, the base station(or the network entity receiver) according to an embodiment may include a transceiver 2610, a memory 2620, and a processor 2630. The transceiver 2610, the memory 2620, and the processor 2630 of the base station(or the network entity receiver) may operate according to a communication method of the base station(or the network entity receiver) described above. However, the components of the base station(or the network entity receiver) are not limited thereto. For example, the base station may include more or fewer components than those described above. In addition, the processor 2630, the transceiver 2610, and the memory 2620 may be implemented as a single chip. Also, the processor 2630 may include at least one processor.

[0285] The transceiver 2610 collectively refers to the base station(or the network entity receiver) and a base station(or the network entity) transmitter, and may transmit / receive a signal to / from a terminal or a network entity or a base station. The signal transmitted or received to or from the terminal or a network entity or the base station may include control information and data. The transceiver 2610 may include a RF transmitter for up-converting and amplifying a frequency of a transmitted signal, and a RF receiver for amplifying low-noise and down-converting a frequency of a received signal. However, this is only an example of the transceiver 2610 and components of the transceiver 2610 are not limited to the RF transmitter and the RF receiver.

[0286] Also, the transceiver 2610 may receive and output, to the processor 2630, a signal through a wireless channel, and transmit a signal output from the processor 2630 through the wireless channel.

[0287] The memory 2620 may store a program and data required for operations of the base station(or the network entity receiver). Also, the memory 2620 may store control information or data included in a signal obtained by the base station. The memory 2620 may be a storage medium, such as read-only memory (ROM), random access memory (RAM), a hard disk, a CD-ROM, and a DVD, or a combination of storage media.

[0288] The processor 2630 may control a series of processes such that the base station(or the network entity receiver) operates as described above. For example, the transceiver 2610 may receive a data signal including a control signal transmitted by the terminal or the network entity or the base station, and the processor 2630 may determine a result of receiving the control signal and the data signal transmitted by the terminal or the network entity or the base station.

[0289] According to an aspect of the present disclosure, there is provided a method performed by a second node in a communication system, comprising: receiving first configuration information for first data from a first node; obtaining first predicted data signals of various layers of the first data based on the first configuration information; determining a first set including the first predicted data signal of at least one layer of the various layers and a second set including the first predicted data signals of one or more layers of multiple layers based on an accuracy of the first predicted data signals of the various layers; obtaining a third set based on the first configuration information and the first set, wherein the third set includes second predicted data signals corresponding to the one or more layers; obtaining a fourth set based on the second set and the third set, wherein the fourth set includes third predicted data signals corresponding to the one or more layers; obtaining soft bits of the first data based on the first set and the fourth set; wherein the first configuration information includes first information and / or second information, wherein the first information includes information associated with a pilot pattern of a pilot signal of a layer, and the second information includes information associated with a transmission power corresponding to a data signal and / or a pilot signal of a layer of the first node.

[0290] According to the method performed by the second node in the communication system provided by the present disclosure, wherein the method further comprises: receiving third information from the first node, the first configuration information being determined based on the third information, the third information includes at least one of: information related to a network deployment, information related to a service, information related to a channel state, information related to a reception quality and auxiliary information, and the auxiliary information includes at least one of digital twinning, Integrated sensing and communication, and a positioning function.

[0291] According to the method performed by the second node in the communication system provided by the present disclosure, wherein the third information further comprises at least one of: information related to an ability of the second node to support SP; information related to an ability of the second node to support SP transmission; information related to an ability of the second node to support SP reception; a joint channel transmission gain; a co-time interference and / or a co-frequency interference.

[0292] According to the method performed by the second node in the communication system provided by the present disclosure, wherein the information related to the network deployment includes at least one of: a transmission frequency band, a macro station or a small station, indoor or outdoor, a terrestrial or non-terrestrial system.

[0293] According to the method performed by the second node in the communication system provided by the present disclosure, wherein the information related to the service includes at least one of: a service type, a traffic volume and a network load status.

[0294] According to the method performed by the second node in the communication system provided by the present disclosure, wherein the information related to the channel state includes at least one of: a reference signal reception power (RSRP), a reference signal reception quality (RSRQ), a signal-to-interference-noise ratio (SINR), a channel quality indicator (CQI), Doppler, channel time variability, frequency selectivity and multipath delay spread.

[0295] According to the method performed by the second node in the communication system provided by the present disclosure, wherein the first configuration information being determined based on the third information comprises: determining a superimposed pilot (SP) scenario based on the third information; determining the first configuration information based on the SP scenario and fourth information corresponding to the determined SP scenario, wherein the fourth information includes information associated with statistical performance parameters.

[0296] According to the method performed by the second node in the communication system provided by the present disclosure, wherein the first configuration information being determined based on the third information comprises: the first configuration information is determined through an artificial intelligence (AI) model based on the third information.

[0297] According to the method performed by the second node in the communication system provided by the present disclosure, wherein the method further comprises: transmitting fifth information and / or sixth information to the first node, wherein the fifth information includes information associated with a pilot pattern of a pilot signal of at least one layer of the multiple layers recommended or suggested by the second node, and the sixth information includes information associated with a transmission power corresponding to a data signal and / or a pilot signal of at least one layer of the multiple layers of the first node recommended or suggested by the second node.

[0298] According to the method performed by the second node in the communication system provided by the present disclosure, wherein the method further comprises: receiving second configuration information from the first node or a third node, wherein the second configuration information includes information associated with the SP configuration of the third node.

[0299] According to the method performed by the second node in the communication system provided by the present disclosure, wherein receiving the first data comprises: obtaining pilot signals and data signals of various layers of the first data using an artificial intelligence (AI) model based on Transformer.

[0300] According to the method performed by the second node in the communication system provided by the present disclosure, wherein when the AI model based on Transformer is used, for a signal received on a first time-frequency unit, attention calculation is only performed on signals received within coherent time of the first time-frequency in the time domain and within coherence bandwidth of the first time-frequency unit in the frequency domain.

[0301] According to the method performed by the second node in the communication system provided by the present disclosure, wherein the method further comprises: generating seventh information based on the first information, the second information, the third information and the first data, wherein the seventh information includes at least one of: information associated with pilot channel estimation with a data interference; information associated with a coherence time feature; information associated with a coherent bandwidth feature; frequency offset information.

[0302] According to the method performed by the second node in the communication system provided by the present disclosure, wherein obtaining the first set and the second set comprises: determining whether bit error rates of various layers meet a first preset condition; based on the bit error rate of the layer meeting the first preset condition, taking a first predicted data signal corresponding to the layer as an element of the first set, based on the bit error rate of the layer not meeting the first preset condition, taking the first predicted data signal corresponding to the layer as an element of the second set.

[0303] According to the method performed by the second node in the communication system provided by the present disclosure, wherein the method further comprises: determining whether a number of elements in the first set meets a second preset condition; based on the number of elements in the first set not meeting the second preset condition, selecting a preset number of elements from the second set into the first set based on the bit error rates.

[0304] According to the method performed by the second node in the communication system provided by the present disclosure, wherein obtaining the first set and the second set comprises: determining whether average error vector amplitude (EVM) of various layers meet a third preset condition; based on the average EVM of the layer meeting the third preset condition, taking a first predicted data signal corresponding to the layer as an element of the first set, based on the average EVM of the layer not meeting the third preset condition, taking the first predicted data signal corresponding to the layer as an element of the second set, wherein the third preset condition is determined according to Modulation and Coding Scheme (MCS).

[0305] According to the method performed by the second node in the communication system provided by the present disclosure, wherein the method further comprises: determining whether a number of elements in the first set meets a fourth preset condition; based on the number of elements in the first set not meeting the fourth preset condition, selecting a preset number of elements from the second set into the first set based on the average EVM.

[0306] According to another aspect of the present disclosure, there is provided a method performed by a first node in a communication system, the method comprising: determining first configuration information for second data; obtaining first predicted data signals of various layers of the second data based on the first configuration information; determining a first set including the first predicted data signal of at least one layer of the various layers and a second set including the first predicted data signals of one or more layers of multiple layers based on an accuracy of the first predicted data signals of the various layers; obtaining a third set based on the first configuration information and the first set, wherein the third set includes second predicted data signals corresponding to the one or more layers; obtaining a fourth set based on the second set and the third set, wherein the fourth set includes third predicted data signals corresponding to the one or more layers; obtaining soft bits of the second data based on the first set and the fourth set; wherein the first configuration information includes first information and / or second information, wherein the first information includes information associated with a pilot pattern of a pilot signal of a layer, and the second information includes information associated with a transmission power corresponding to a data signal and / or a pilot signal of a layer of the first node.

[0307] According to the method performed by the first node in the communication system provided by the present disclosure, wherein the method further comprises: determining the first configuration information based on third information, wherein the third information includes at least one of: information related to a network deployment, information related to a service, information related to a channel state, information related to a reception quality and auxiliary information, and the auxiliary information includes at least one of digital twinning, Integrated sensing and communication and a positioning function.

[0308] According to the method performed by the first node in the communication system provided by the present disclosure, wherein the third information further comprises at least one of: information related to an ability of the second node to support SP; information related to an ability of the second node to support SP transmission; information related to an ability of the second node to support SP reception; a joint channel transmission gain; a co-time interference and / or a co-frequency interference.

[0309] According to the method performed by the first node in the communication system provided by the present disclosure, wherein receiving the second data comprises: obtaining pilot signals and data signals of various layers of the second data using an artificial intelligence (AI) model based on Transformer.

[0310] According to the method performed by the first node in the communication system provided by the present disclosure, wherein the method further comprises: generating seventh information based on the first information, the second information, the third information and the first data, wherein the seventh information includes at least one of: information associated with pilot channel estimation with a data interference; information associated with a coherence time feature; information associated with a coherent bandwidth feature.

[0311] According to another aspect of the present disclosure, there is provided a first node comprising: a transceiver configured to transmit and receive signals with the outside; and a controller configured to control the transceiver to perform the above method performed by the first node.

[0312] According to another aspect of the present disclosure, there is provided a second node comprising: a transceiver configured to transmit and receive signals with the outside; and a controller configured to control the transceiver to perform the above method performed by the second node.

[0313] According to another aspect of the present disclosure, there is provided a non-transitory computer-readable recording medium having stored thereon a program which, when being executed by a computer, performs any of the above methods.

[0314] Those skilled in the art will understand that the illustrative embodiments described above are described herein and are not intended to be limiting. It should be understood that any two or more of the embodiments disclosed herein can be combined in any combination. In addition, other embodiments can be utilized and other changes can be made without departing from the spirit and scope of the subject matter presented herein. It will be readily understood that aspects of the present invention of the present disclosure, as generally described herein and shown in the accompanying drawings, can be arranged, substituted, combined, separated and designed in various different configurations, all of which are contemplated herein.

[0315] Those skilled in the art will understand that the various illustrative logical blocks, modules, circuits, and steps described in the present application can be implemented as hardware, software, or a combination of both. In order to clearly illustrate this interchangeability between hardware and software, various illustrative components, blocks, modules, circuits, and steps are generally described above in the form of their function set. Whether such a function set is implemented as hardware or software depends on the specific application and the design constraints imposed on the overall system. Skilled people can implement the described function set in different ways for each specific application, but such design decisions should not be interpreted as causing a departure from the scope of the present application.

[0316] The various illustrative logic blocks, modules, and circuits described in the present application can be implemented in a general-purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic devices, discrete gate or transistor logic, discrete hardware component, or any combination thereof designed to perform the functions described herein. A general-purpose processor may be a microprocessor, but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors cooperating with a DSP core, or any other such configuration.

[0317] The steps of the method or technique described in the present application can be embodied directly in hardware, in a software module executed by a processor, or in a combination of both. Software modules may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, register, hard disk, removable disk, or any other form of storage media known in the art. An exemplary storage medium is coupled to a processor to enable the processor to read and write information from / to the storage medium. In the alternative, the storage medium may be integrated into the processor. The processor and storage medium may reside in an ASIC. The ASIC may reside in the UE. In the alternative, the processor and the storage medium may reside in the UE as discrete components.

[0318] In one or more exemplary designs, the described functions can be implemented in hardware, software, firmware, or any combination thereof. If implemented in software, each function can be stored on or transferred by a computer-readable medium as one or more instructions or codes. Computer-readable media include both computer storage media and communication media, which includes any media that facilitates the transfer of computer programs from one place to another. The storage medium may be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0319] What has been described above is only an exemplary embodiment of the present disclosure, and is not used to limit the protection scope of the present disclosure, which is determined by the appended claims.

Claims

1.A method performed by a second node in a wireless communication system, the method comprising:receiving first configuration information for first data from a first node;obtaining first predicted data signals of various layers of the first data based on the first configuration information;determining a first set including the first predicted data signal of at least one layer of the various layers and a second set including the first predicted data signals of one or more layers of multiple layers based on an accuracy of the first predicted data signals of the various layers;obtaining a third set based on the first configuration information and the first set, wherein the third set includes second predicted data signals corresponding to the one or more layers;obtaining a fourth set based on the second set and the third set, wherein the fourth set includes third predicted data signals corresponding to the one or more layers;obtaining soft bits of the first data based on the first set and the fourth set;wherein the first configuration information includes first information and / or second information, wherein the first information includes information associated with a pilot pattern of a pilot signal of a layer, and the second information includes information associated with a transmission power corresponding to a data signal and / or a pilot signal of a layer of the first node.2.The method of claim 1, wherein the method further comprises:receiving third information from the first node, the first configuration information being determined based on the third information,the third information includes at least one of: information related to a network deployment, information related to a service, information related to a channel state, information related to a reception quality and auxiliary information, and the auxiliary information includes at least one of digital twinning, Integrated Sensing and Communication, and a positioning function.3.The method of claim 2, wherein the third information further comprises at least one of:information related to an ability of the second node to support superimposed pilot (SP);information related to an ability of the second node to support SP transmission;information related to an ability of the second node to support SP reception;a joint channel transmission gain;a co-time interference and / or a co-frequency interference.4.The method of claim 2, wherein the information related to the network deployment includes at least one of: a transmission frequency band, a macro station or a small station, indoor or outdoor, a terrestrial or non-terrestrial system.5.The method of claim 2, wherein the information related to the channel state includes at least one of: a reference signal reception power (RSRP), a reference signal reception quality (RSRQ), a signal-to-interference-noise ratio (SINR), a channel quality indicator (CQI), Doppler, channel time variability, frequency selectivity and multipath delay spread.6.The method of claim 2, wherein the first configuration information being determined based on the third information comprises:determining a superimposed pilot (SP) scenario based on the third information;determining the first configuration information based on the SP scenario and fourth information corresponding to the determined SP scenario, wherein the fourth information includes information associated with statistical performance parameters.7.The method of claim 1, wherein the method further comprises:transmitting fifth information and / or sixth information to the first node, wherein the fifth information includes information associated with a pilot pattern of a pilot signal of at least one layer of the multiple layers recommended or suggested by the second node, and the sixth information includes information associated with a transmission power corresponding to a data signal and / or a pilot signal of at least one layer of the multiple layers of the first node recommended or suggested by the second node.8.The method of claim 1, wherein the method further comprises:receiving second configuration information from the first node or a third node, wherein the second configuration information includes information associated with the SP configuration of the third node.9.The method of claim 1,wherein receiving the first data comprises:obtaining pilot signals and data signals of various layers of the first data using an artificial intelligence (AI) model based on Transformer, andwherein when the AI model based on Transformer is used, for a signal received on a first time-frequency unit, attention calculation is only performed on signals received within coherent time of the first time-frequency unit in the time domain and within coherence bandwidth of the first time-frequency unit in the frequency domain.10.The method of claim 2, wherein the method further comprises:generating seventh information based on the first information, the second information, the third information and the first data,wherein the seventh information includes at least one of:information associated with pilot channel estimation with a data interference;information associated with a coherence time feature;information associated with a coherent bandwidth feature;frequency offset information.11.The method of claim 1, wherein obtaining the first set and the second set comprises:determining whether average error vector amplitude (EVM) of various layers meet a third preset condition;based on the average EVM of the layer meeting the third preset condition, taking a first predicted data signal corresponding to the layer as an element of the first set,based on the average EVM of the layer not meeting the third preset condition, taking the first predicted data signal corresponding to the layer as an element of the second set,wherein the third preset condition is determined according to Modulation and Coding Scheme (MCS).12.The method of claim 11, wherein the method further comprises:determining whether a number of elements in the first set meets a fourth preset condition;based on the number of elements in the first set not meeting the fourth preset condition, selecting a preset number of elements from the second set into the first set based on the average EVM.13.A method performed by a second node in a wireless communication system, comprising:determining first configuration information for second data;obtaining first predicted data signals of various layers of the second data based on the first configuration information;determining a first set including the first predicted data signal of at least one layer of the various layers and a second set including the first predicted data signals of one or more layers of multiple layers based on an accuracy of the first predicted data signals of the various layers;obtaining a third set based on the first configuration information and the first set, wherein the third set includes second predicted data signals corresponding to the one or more layers;obtaining a fourth set based on the second set and the third set, wherein the fourth set includes third predicted data signals corresponding to the one or more layers;obtaining soft bits of the second data based on the first set and the fourth set;wherein the first configuration information includes first information and / or second information, wherein the first information includes information associated with a pilot pattern of a pilot signal of a layer, and the second information includes information associated with a transmission power corresponding to a data signal and / or a pilot signal of a layer of first node.14.A second node in a wireless communication system, comprising:a transceiver; anda controller coupled with the transceiver and configured to:receive first configuration information for first data from a first node;obtain first predicted data signals of various layers of the first data based on the first configuration information;determine a first set including the first predicted data signal of at least one layer of the various layers and a second set including the first predicted data signals of one or more layers of multiple layers based on an accuracy of the first predicted data signals of the various layers;obtain a third set based on the first configuration information and the first set, wherein the third set includes second predicted data signals corresponding to the one or more layers;obtain a fourth set based on the second set and the third set, wherein the fourth set includes third predicted data signals corresponding to the one or more layers;obtain soft bits of the first data based on the first set and the fourth set;wherein the first configuration information includes first information and / or second information, wherein the first information includes information associated with a pilot pattern of a pilot signal of a layer, and the second information includes information associated with a transmission power corresponding to a data signal and / or a pilot signal of a layer of the first node.15.A second node in a wireless communication system, comprising:a transceiver; anda controller coupled with the transceiver and configured to:determine first configuration information for second data;obtain first predicted data signals of various layers of the second data based on the first configuration information;determine a first set including the first predicted data signal of at least one layer of the various layers and a second set including the first predicted data signals of one or more layers of multiple layers based on an accuracy of the first predicted data signals of the various layers;obtain a third set based on the first configuration information and the first set, wherein the third set includes second predicted data signals corresponding to the one or more layers;obtain a fourth set based on the second set and the third set, wherein the fourth set includes third predicted data signals corresponding to the one or more layers;obtain soft bits of the second data based on the first set and the fourth set;wherein the first configuration information includes first information and / or second information, wherein the first information includes information associated with a pilot pattern of a pilot signal of a layer, and the second information includes information associated with a transmission power corresponding to a data signal and / or a pilot signal of a layer of first node.

Images