Data transmission method and apparatus, and storage medium

Abstract

Provided are a data transmission method and apparatus, and a storage medium. The method comprises: determining K pieces of predicted channel information of K second nodes; on the basis of the K pieces of predicted channel information, determining K pieces of first channel state information of the K second nodes; and on the basis of the K pieces of first channel state information, performing data transmission, wherein the first channel state information is channel state information in a first transmission mode, the first channel state information comprises at least one first precoding matrix and / or at least one modulation and coding scheme, and K is a positive integer greater than 1.

Description

Data transmission methods, devices and storage media

[0001] This disclosure claims priority to Chinese patent application No. 202510182056.1, filed on February 18, 2025, the entire contents of which are incorporated herein by reference. Technical Field

[0002] This disclosure relates to the field of wireless communication technology, and in particular to a data transmission method, apparatus and storage medium. Background Technology

[0003] In the field of wireless communication, improving spectral efficiency is key to development, and multi-antenna technology, as the core means to achieve this goal, relies heavily on accurate channel state information (CSI) for performance optimization. Multiple-input multiple-output (MIMO) technology, as a typical representative of multi-antenna technology, mainly includes single-user multiple-input multiple-output (SU-MIMO) and multiple-user multiple-input multiple-output (MU-MIMO).

[0004] In practical applications, base stations are typically equipped with a large number of antennas; while terminal devices, due to size and cost limitations, generally have fewer antennas. This difference allows MU-MIMO to reuse more data streams under the same time-frequency resource conditions compared to SU-MIMO, thereby significantly improving the system's spectral efficiency and throughput.

[0005] Despite the significant advantages of multi-antenna technology, fully unleashing its performance potential, especially in multi-user scenarios, still faces numerous technical challenges. Summary of the Invention

[0006] On the one hand, a data transmission method is provided, applied to the first node, the method comprising:

[0007] Determine the K predicted channel information for the K second nodes;

[0008] Based on K predicted channel information, determine K first channel state information for K second nodes;

[0009] Data transmission is performed based on K first channel state information.

[0010] Here, the first channel state information is the channel state information under the first transmission mode, and the first channel state information includes at least one first precoding matrix and / or at least one modulation and coding scheme, where K is a positive integer greater than 1.

[0011] On the other hand, a data transmission method is provided for application to a third node, the method comprising:

[0012] Receive data sent by the first node based on the first channel state information of the third node;

[0013] Here, the first channel state information is determined based on the K predicted channel information of the K second nodes; the first channel state information is the channel state information under the first transmission mode, and the first channel state information includes at least one first precoding matrix and / or at least one modulation and coding scheme, the K second nodes include third nodes, and K is a positive integer greater than 1.

[0014] On another front, a data transmission device is provided for use in a first node, the device comprising:

[0015] The processing module is used to determine the K predicted channel information for the K second nodes;

[0016] The processing module is also used to determine the K first channel state information of the K second nodes based on the K predicted channel information;

[0017] The communication module is used to transmit data based on K first channel state information.

[0018] Here, the first channel state information is the channel state information under the first transmission mode, and the first channel state information includes at least one first precoding matrix and / or at least one modulation and coding scheme, where K is a positive integer greater than 1.

[0019] On another front, a data transmission device is provided for use in a third node, the device comprising:

[0020] The communication module is used to receive data sent by the first node based on the first channel state information of the third node;

[0021] Here, the first channel state information is determined based on the K predicted channel information of the K second nodes; the first channel state information is the channel state information under the first transmission mode, and the first channel state information includes at least one first precoding matrix and / or at least one modulation and coding scheme, the K second nodes include third nodes, and K is a positive integer greater than 1.

[0022] In another aspect, a communication device is provided, comprising: a memory and a processor; the memory and the processor are coupled; the memory is used to store computer program instructions executable by the processor; and the processor implements the data transmission method provided in any of the above embodiments when executing the computer program instructions.

[0023] In another aspect, a computer-readable storage medium is provided, including a non-transitory computer-readable storage medium storing computer program instructions that, when executed on a computer (e.g., a communication device or a data transmission device), implement the data transmission method provided in any of the above embodiments.

[0024] In another aspect, a computer program product is provided, which includes computer program instructions that, when executed, implement the data transmission method provided in any of the above embodiments. Attached Figure Description

[0025] To more clearly illustrate the technical solutions in this disclosure, the accompanying drawings used in some embodiments of this disclosure will be briefly described below. Obviously, the drawings described below are merely drawings of some embodiments of this disclosure, and those skilled in the art can obtain other drawings based on these drawings.

[0026] Figure 1 is a schematic diagram of a wireless communication system according to some embodiments.

[0027] Figure 2 is a flowchart of a data transmission method according to some embodiments.

[0028] Figure 3 is a flowchart of another data transmission method provided according to some embodiments.

[0029] Figure 4 is a block diagram of a data transmission device according to some embodiments.

[0030] Figure 5 is a block diagram of another data transmission device according to some embodiments.

[0031] Figure 6 is a block diagram of a communication device according to some embodiments. Detailed Implementation

[0032] To enable those skilled in the art to better understand the technical solutions of the embodiments of this disclosure, the technical solutions of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0033] It should be understood that the specific implementations described herein are for interpreting this disclosure only and are not intended to limit this disclosure.

[0034] In the following description, the use of suffixes such as “module,” “part,” or “unit” to denote elements is solely for the purpose of illustrative purposes and has no particular meaning in itself. Therefore, “module,” “part,” or “unit” may be used interchangeably.

[0035] In this disclosure, unless otherwise stated, " / " means "or," for example, A / B can mean A or B. "And / or" in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone. Furthermore, "at least one" means one or more, and "multiple" means two or more. The terms "first," "second," etc., do not limit the quantity or order of execution, and "first," "second," etc., do not necessarily imply differences.

[0036] Unless the context otherwise requires, throughout the specification and claims, the term "comprise" and its other forms, such as the third-person singular "comprises" and the present participle "comprising," are interpreted as open-ended and encompassing, meaning "including, but not limited to." In the description of the specification, terms such as "one embodiment," "some embodiments," "exemplary embodiments," "example," "specific example," or "some examples," etc., are intended to indicate that a particular feature, structure, material, or characteristic associated with that embodiment or example is included in at least one embodiment or example of this disclosure. The illustrative representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics mentioned may be included in any suitable manner in any one or more embodiments or examples.

[0037] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this disclosure, unless otherwise stated, "a plurality of" means two or more.

[0038] In this disclosure, the terms "exemplarily" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplarily" or "for example" in this disclosure should not be construed as being more preferred or advantageous than other embodiments or designs. Rather, the use of the terms "exemplarily" or "for example" is intended to present the relevant concepts in a specific manner.

[0039] In addition, the use of “based on” implies openness and inclusivity, because processes, steps, calculations or other actions “based on” one or more of the stated conditions or values ​​may in practice be based on additional conditions or values ​​beyond those stated.

[0040] In the field of wireless communication, improving spectral efficiency is key to development, and multi-antenna technology, as the core means to achieve this goal, relies heavily on accurate channel state information (CSI) for performance optimization. Multiple-input multiple-output (MIMO) technology, as a typical representative of multi-antenna technology, mainly includes single-user multiple-input multiple-output (SU-MIMO) and multi-user multiple-input multiple-output (MU-MIMO).

[0041] SU-MIMO, abbreviated as SU, utilizes time and frequency resources by having a base station send multiple data streams to a single terminal using multiple antennas, while the user simultaneously receives data through multiple antennas. This technology significantly improves the data transmission rate of a single terminal, demonstrating its advantages in scenarios with urgent high-speed requirements, such as high-definition video transmission and large file downloads, ensuring a smooth and efficient data transmission experience.

[0042] MU-MIMO, or MU for short, is unique in that it allows a base station to serve multiple terminals on the same time and frequency resources. Compared to traditional single-user transmission modes, MU-MIMO significantly increases system capacity. It achieves this by spatially orthogonalizing the signals from multiple terminals, allowing signals from different users to transmit on the same time and frequency resources without interference, thus fully utilizing the potential of spectrum resources and effectively improving spectrum utilization. In practical applications, base stations are typically equipped with a large number of antennas, such as the common 32, 64, or even 128 antennas; while terminal devices, due to size and cost limitations, generally have fewer antennas, usually 2-4. This difference allows MU-MIMO, compared to SU-MIMO, to reuse more data streams under the same time and frequency resource conditions, thereby significantly improving the system's spectrum efficiency and throughput.

[0043] Despite the significant advantages of multi-antenna technology, fully realizing its performance potential, especially in multi-user scenarios, still faces numerous technical challenges. First, in frequency division duplexing (FDD) mode, interference estimation among multiple users is extremely complex. Because different user signals are transmitted simultaneously in the frequency domain, mutual interference is difficult to predict accurately and suppress effectively; however, interference estimation requires obtaining higher-precision CSI (Continuous Signal Indication) data in multi-user scenarios. Second, there is a lack of scientifically effective methods for the proper pairing of multiple users.

[0044] Within the framework of traditional technologies, solving the aforementioned problems faces numerous challenges. Traditional interference estimation methods suffer from high computational complexity and poor accuracy, making them unsuitable for complex environments with dynamic changes in multiple users. Multi-user pairing algorithms lack intelligence and adaptability, making it difficult to achieve optimal resource allocation. Traditional methods for obtaining CSI not only have limited accuracy but also suffer from significant deficiencies in feedback overhead and real-time performance, severely restricting the performance improvement of multi-antenna technology in multi-user scenarios.

[0045] In view of this, this disclosure provides a data transmission method, which includes: determining K predicted channel information for K second nodes; and determining K first channel state information for the K second nodes based on the K predicted channel information. The first channel state information is channel state information under a first transmission mode, and includes at least one first precoding matrix and / or at least one modulation and coding scheme. This method solves the problem of poor accuracy of channel state information determined by traditional methods under the first transmission mode (including multi-user multiple-input multiple-output mode), improves the accuracy of channel state information determination under the first transmission mode, thereby improving the performance of multi-user scheduling and contributing to increased spectrum efficiency. It is expected to promote the further development and application of multi-antenna technology in the field of wireless communication.

[0046] The technical means involved in the embodiments of this disclosure will be described below.

[0047] In this disclosure, higher-layer signaling includes, but is not limited to, radio resource control (RRC), media access control control element (MAC CE), and other higher-layer signaling other than physical layer signaling. Physical layer signaling includes, but is not limited to: downlink physical layer signaling transmitted on the physical downlink control channel (PDCCH), uplink physical layer signaling transmitted on the physical uplink control channel (PUCCH), and physical layer signaling transmitted on the physical uplink shared channel (PUSCH).

[0048] In some embodiments, physical channels are divided into physical downlink channels and physical uplink channels. The physical downlink channels include, but are not limited to, PDCCH and physical downlink shared channel (PDSCH). The physical uplink channels include, but are not limited to, PUCCH and PUSCH. In some embodiments, PDCCH is mainly used to transmit downlink control information (DCI). PUCCH is mainly used to transmit uplink control information (UCI), such as CSI, hybrid automatic repeat request (HARQ), and scheduling request. PDSCH is mainly used to transmit downlink data and downlink signaling. PUSCH is mainly used to transmit uplink data and uplink signaling.

[0049] In some embodiments, the indicators of various parameters may also be called indexes or identifiers (IDs). Indicators, identifiers, and indexes are equivalent concepts and can be used interchangeably in some embodiments.

[0050] In some embodiments, transmission includes sending or receiving. For example, transmitting data can be understood as sending or receiving data, and transmitting signals can be understood as sending or receiving signals. In some embodiments, physical layer signaling and / or higher layer signaling are also a type of data.

[0051] In some embodiments, to obtain channel state information or perform channel estimation, mobility management, positioning, etc., communication nodes need to transmit reference signals (RS). Here, reference signals include, but are not limited to, channel-state information reference signals (CSI-RS), channel-state information interference measurement (CSI-IM), sounding reference signals (SRS), synchronization signals blocks (SSB), physical broadcast channels (PBCH), and synchronization signal block / physical broadcast channel (SSB / PBCH). In some embodiments, SSB includes synchronization signals blocks and / or physical broadcast channels. In some embodiments, channel state information reference signals include zero-power CSI-RS (ZP CSI-RS) and non-zero-power CSI-RS (NZP CSI-RS). In addition, the time-frequency resources used to transmit reference signals are called reference signal resources. Reference signal resources consist of a set of one or more resource elements (REs), such as CSI-RS resource, SRS resource, CSI-IM resource, SSB resource, etc. Reference signals are transmitted on reference signal resources.

[0052] In some embodiments, a time instance represents a time period, such as a slot, mini-slot, or symbol group. A slot or mini-slot may include at least one symbol. In one embodiment, a symbol refers to a time unit within a subframe, frame, or slot, and the unit may be milliseconds, microseconds, nanoseconds, seconds, etc. In one embodiment, a symbol may be an orthogonal frequency division multiplexing (OFDM) symbol, a single-carrier frequency division multiple access (SC-FDMA) symbol, an orthogonal frequency division multiple access (OFDMA) symbol, or symbols corresponding to various waveforms in future communication systems, etc. In some embodiments, the slot may be replaced by a time instance, mini-slot, etc.

[0053] In some embodiments, the transmission unit carrying a modulation symbol is a resource element (RE), which is the minimum hourly frequency resource used to transmit a modulation symbol, including a subcarrier and radio resources on the symbol. The hourly frequency resources consisting of one or more subcarriers on one or more symbols constitute a physical resource block (PRB).

[0054] In some embodiments, threshold values, or preset threshold values, are required. These threshold values ​​can be at least one of the following: real numbers, positive integers, integers, Boolean values, characters, or strings. The threshold values ​​can be agreed upon by the base station and the terminal, or be default values, or empirical values ​​obtained from simulation or practice, or values ​​indicated to each other by communication nodes through higher-layer and / or physical-layer signaling. For ease of distinction, a first threshold, a second threshold, etc., can be included; these are only used to distinguish different threshold values, not for ordering. In other embodiments, thresholds can be replaced by threshold groups, each threshold group including one or more thresholds.

[0055] In some embodiments, the channel information is information obtained from a reference signal (such as CSI-RS) to describe the channel environment between communication nodes. In one embodiment, the channel information is a complex matrix, which may be called the channel matrix. The size of the channel matrix is ​​related to the number of transmitting antennas Nt, the number of receiving antennas Nr, and the number of resource elements.

[0056] In some embodiments, the channel information may include at least one of the following: time-domain channel information, frequency-domain channel information, one or more eigenvectors of the correlation matrix corresponding to the time-domain channel information, one or more singular vectors of the correlation matrix corresponding to the time-domain channel information, one or more eigenvectors of the correlation matrix corresponding to the frequency-domain channel information, one or more singular vectors of the correlation matrix corresponding to the frequency-domain channel information, a precoding matrix corresponding to the frequency-domain channel, a precoding matrix corresponding to the time-domain channel, one or more codewords corresponding to the frequency-domain channel, and one or more codewords corresponding to the time-domain channel. Here, both the time-domain channel information and the frequency-domain channel information can represent information describing channel characteristics between at least one transmit antenna and at least one receive antenna, and can be a matrix or a multi-dimensional array or matrix.

[0057] In some embodiments, the information processing methods include at least linear and nonlinear information processing methods. Here, nonlinear information processing methods include, but are not limited to, various advanced information processing technologies, such as artificial intelligence (AI). In some embodiments, for ease of description, nonlinear information processing methods are also referred to as first-type information processing methods, and linear information processing methods are also referred to as second-type information processing methods. In one embodiment, one information processing method corresponds to one information processing technology. In one embodiment, one information processing method corresponds to one model. In one embodiment, one information processing method corresponds to one function.

[0058] In some embodiments, CSI includes downlink channel state information and uplink channel state information, referred to as downlink channel state information and uplink channel state information, respectively.

[0059] In some embodiments, downlink channel state information includes, but is not limited to, at least one of the following: channel state information - reference signal resource indicator (CSI-RS resource indicator, CRI), synchronization signals block resource indicator (SSBRI), L1 reference signal received power (L1-RSRP), differential RSRP (differential L1-RSRP), L1 signal-to-interference noise ratio (L1-SINR), differential L1-SINR (differential L1-SINR), reference signal received quality (RSRQ), differential RSRQ, channel quality indicator (CQI), wideband CQI, subband CQI, precoding matrix indicator (PMI), layer indicator (LI), rank indicator (RI), precoding information, channel information, capability index, and time-domain channel properties (TDCP).

[0060] In some embodiments, L1-RSRP or differential RSRP are collectively referred to as L1-RSRP, or simply RSRP. In some embodiments, L1-SINR or differential SINR are collectively referred to as L1-SINR, or simply SINR.

[0061] In some embodiments, the uplink channel state information includes, but is not limited to, at least one of the following: uplink sounding signal resource indicator (SRS resource indicator, SRI), uplink sounding signal resource set indicator (SRSI), transmitted precoding matrix indicator (TPMI), transmitted rank indicator (TRI), and modulation and coding scheme (MCS). Additionally, TPMI and TRI may be jointly coded, using precoding information and the number of layers (PINL) field from the DCI.

[0062] In some embodiments, CSI includes wideband CSI and subband CSI, where subband CSI refers to a different CSI corresponding to each subband. The CSI may include, but is not limited to, at least one of the following: CRI, rank indication (RI), CQI, PMI, LI, L1-RSRP, L1 reference signal received quality (L1-RSRQ), L1-SINR, SRI, TPMI, TRI, and MCS. For example, in one embodiment, CQI is divided into wideband CQI and subband CQI. In one embodiment, PMI is divided into wideband PMI and subband PMI. In one embodiment, RI is divided into wideband RI and subband RI. In one embodiment, MCS is divided into wideband MCS and subband MCS. In some embodiments, subband CQI may also be replaced with subband differential CQI. In some embodiments, wideband PMI may also be replaced with the PMI wideband information field, and subband PMI may also be replaced with the PMI subband information field.

[0063] In some embodiments, the precoding information includes a first type of precoding information and a second type of precoding information. The precoding information may include the precoding itself or the quantization value corresponding to the precoding, precoding matrix indicators (PMIs) for various subbands or widebands, etc.

[0064] In some embodiments, the first type of precoding information is precoding information implemented in a nonlinear manner, such as precoding information obtained based on AI and other technologies, including CSI generated by compression based on at least one dimension of space-time-frequency, such as channel state information generated by joint space-frequency compression and channel state information generated by joint space-time-frequency compression.

[0065] In some embodiments, the second type of precoding information is traditional precoding information generated using linear techniques, such as codebook-based precoding information, or various codebook acquisition techniques based on discrete Fourier transform (DFT) vectors. In one embodiment, the codebook can be the codebook for N antennas in Long Term Evolution (LTE), where N is a positive integer greater than 2. In one embodiment, the codebook includes, but is not limited to, one of the following codebooks in NR: type I codebook, type II codebook, type II port selection codebook, enhanced type II codebook, enhanced type II selection codebook, further enhanced type II selection codebook, Doppler codebook, coherent joint transmission (CJT) codebook, etc. In one embodiment, it can also be a codebook generated using linear techniques by a future wireless communication system, such as various DFT-based codebooks. The precoding matrix indicator PMI in this disclosure is one type of codebook-based precoding information.

[0066] In some instances, location information includes, but is not limited to, at least one of the following: transmission time-related information, angle-related information, received reference signal quality-related information, multipath-related information, coordinates of the first node (including absolute and relative coordinates), and coordinates of the second node.

[0067] In some embodiments, transmission time-related information includes at least one of the following: time of arrival (TOA), reference signal time difference (RSTD), relative time of arrival (RTOA), transmit-receive time difference (Rx-Tx time difference), transmit-receive time difference (Tx-Rx time difference), etc.

[0068] In some embodiments, angle-related information includes at least one of the following: angle of arrival (AoA), angle of departure (AOD), zenith angle of arrival (ZOA), and azimuth angle of departure (AOD). The angle of departure includes the zenith angle of departure (ZOD) and / or the azimuth angle of departure (AOA).

[0069] In some embodiments, the information related to the quality of the received reference signal includes at least one of the following: reference signal received power (RSRP or L1-RSRP), SINR (or L1-SINR), CQI, signal-to-noise ratio (SNR), and RSRQ.

[0070] In some embodiments, to transmit measurement results, such as channel state information, at the physical layer, the communication node needs to configure a report (e.g., a CSI report or CSI report configuration). This report defines at least one of the following parameters: time-frequency resources used for transmitting the measurement results, report quantity, report time-domain type (reportConfigType), channel measurement resources, interference measurement resources, and measurement bandwidth. The report can be transmitted on uplink resources, including PUSCH and PUCCH, and the report time-domain type includes periodic reports (e.g., periodic CSI report, P-CSI), aperiodic reports (e.g., aperiodic CSI report, AP-CSI), and semi-persistent reports (e.g., semi-persistent CSI report, SP-CSI). The transmission of measurement resources is performed on the resources specified in the CSI report; this transmission includes sending or receiving.

[0071] In some embodiments, the antenna is a physical antenna. In some embodiments, the antenna is a logical antenna. In some embodiments, the port and antenna, antenna port, reference signal port, and pilot port are interchangeable. In some embodiments, the antenna is a transmitting antenna. In some embodiments, the antenna is a receiving antenna. In some embodiments, the antenna includes an antenna pair consisting of a transmitting antenna and a receiving antenna.

[0072] In some embodiments, the antenna includes an antenna pair consisting of a transmitting antenna and a receiving antenna. In some embodiments, the antenna may be a uniform linear array. In some embodiments, the antenna is a uniform planar array. In some embodiments, the antenna is a uniform circular array. In some embodiments, the antenna may be a non-uniform linear array. In some embodiments, the antenna is a non-uniform planar array. In some embodiments, the antenna is a non-uniform circular array. In some embodiments, the antenna is a directional antenna; in some embodiments, the antenna is an omnidirectional antenna. In some embodiments, the antenna is a dual-polarized antenna. In some embodiments, the antenna is a single-polarized antenna.

[0073] The communication network in this disclosure includes, but is not limited to, third-generation mobile communication technology (3G), fourth-generation mobile communication technology (4G), fifth-generation mobile communication technology (5G), and future mobile communication networks, such as (6th-generation mobile communication technology, 6G), (7th-generation mobile communication technology, 7G), etc. The network architecture may include network-side equipment (e.g., including but not limited to base stations) and receiving-side equipment (e.g., including but not limited to terminals). The first communication node and the second communication node may each be a base station or a terminal. The first communication node and the second communication node may be abbreviated as first node and second node, respectively. In one embodiment, the first communication node is a base station, and the second communication node is a terminal. In another embodiment, the first communication node is a base station, and the second communication node is a base station. In yet another embodiment, the first communication node is a terminal, and the second communication node is a base station. In some embodiments, a communication node includes a first node and / or a second node. In some embodiments, a communication node may also be simply referred to as a node, and a node may be either a first node or a second node.

[0074] In some embodiments, a wireless communication system includes one or more base stations and one or more terminals. Each base station includes multiple antennas, and each terminal may include one or more antennas. The base station transmits a reference signal on at least one reference signal resource, and the terminal receives the reference signal on at least one reference signal resource and measures the reference signal to obtain at least one channel state information.

[0075] Figure 1 is a schematic diagram of a wireless communication system according to some embodiments. As shown in Figure 1, the wireless communication system includes, but is not limited to, a first node 110 and a second node 120. Here, the first node 110 and the second node 120 can transmit and receive wireless signals and perform related interactions.

[0076] In a wireless communication scenario, the first node 110 and the second node 120 communicate via a wireless channel. For example, the first node 110 may be a base station, and the second node 120 a terminal; the base station and the terminal communicate via a wireless channel. Alternatively, the first node 110 may be a wireless router, and the second node 120 a terminal; the wireless router and the terminal communicate via a wireless channel. Another example is that the first node 110 may be a first base station, and the second node 120 a second base station; the first base station and the second base station communicate via a wireless channel. Yet another example is that the first node 110 may be a first terminal, and the second node 120 a second terminal; the first terminal and the second terminal communicate via a wireless channel. Finally, the first node 110 may be a base station, and the second node 120 a repeater; the base station and the repeater communicate via a wireless channel. Finally, the first node 110 may be a repeater, and the second node 120 a terminal; the repeater and the terminal communicate via a wireless channel. For example, node 110 is a first repeater, and node 120 is a second repeater; the first repeater and the second repeater communicate via a wireless channel. Alternatively, node 110 can be a base station, and node 120 a satellite; the satellite and the base station communicate via a wireless channel. Another example: node 110 can be a satellite, and node 120 a base station; the base station and the satellite communicate via a wireless channel. Yet another example: node 110 can be a terminal, and node 120 a satellite; the satellite and the terminal communicate via a wireless channel. Again, node 110 can be a satellite, and node 120 a terminal; the terminal and the satellite communicate via a wireless channel. Finally, node 110 can be ground equipment, and node 120 can be an aircraft; the aircraft and the ground equipment communicate via a wireless channel. Finally, node 110 can be a first aircraft, and node 120 a second aircraft; the first aircraft and the second aircraft communicate via a wireless channel.

[0077] In some embodiments, the base station may be a base station in LTE, long term evolution advanced (LTEA) or an evolved Node B (eNB or eNodeB), a base station device in a fifth-generation wireless communication system, or a base station in a future wireless communication system (such as 6G). The base station may include various macro base stations, micro base stations, home base stations (Femtocell or Home eNodeB), wireless remote extensions, reconfigurable intelligent surfaces (RISS), routers, wireless fidelity (WIFI) devices, and other network-side devices.

[0078] In some embodiments, the terminal is a device with wireless transceiver capabilities, which can be deployed on land, including indoors or outdoors, or inside a vehicle; it can also be deployed on water (such as on a ship); and it can also be deployed in the air (e.g., on airplanes, balloons, satellites, drones, various aircraft, etc.). The terminal can be a mobile phone, tablet computer, computer with wireless transceiver capabilities, virtual reality (VR) terminal, augmented reality (AR) terminal, wireless terminal in industrial control, wireless terminal in self-driving, wireless terminal in remote medical care, wireless terminal in smart grid, wireless terminal in transportation safety, wireless terminal in smart city, wireless terminal in smart home, wireless terminal on drones and other aircraft, etc. The embodiments disclosed herein do not limit the application scenarios. A terminal may also be referred to as a user, user equipment (UE), access terminal, UE unit, UE station, mobile station, mobile station, remote station, remote terminal, mobile device, UE terminal, wireless communication equipment, UE agent, or UE device, etc. The embodiments disclosed herein are not limited to these terms.

[0079] It should be noted that Figure 1 is only an exemplary framework diagram. The number of devices included in Figure 1 and the names of each device are not limited. In addition to the devices shown in Figure 1, the communication system may also include other devices, such as relay nodes, core network devices, etc.

[0080] The application scenarios of the embodiments disclosed herein are not limited. The system architecture and business scenarios described in the embodiments of this disclosure are for the purpose of more clearly illustrating the technical solutions of the embodiments of this disclosure, and do not constitute a limitation on the technical solutions provided by the embodiments of this disclosure. As those skilled in the art will know, with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided by the embodiments of this disclosure are also applicable to similar technical problems.

[0081] In some embodiments, data transmission between communication nodes includes a first transmission mode and a second transmission mode. The first transmission mode may include MU-MIMO with multiple base stations jointly transmitting data, or MU-MIMO with a single base station. The second transmission mode includes SU-MIMO with multiple base stations jointly transmitting data, or SU-MIMO with a single base station.

[0082] In some embodiments, the channel state information in the first transmission mode is referred to as the first channel state information, which includes, but is not limited to, at least one of the following: one or more first precoding matrices, one or more first channel quality indicators, one or more first MCSs, and one or more first SINRs. The channel state information in the second transmission mode is referred to as the second channel state information.

[0083] In some embodiments, the channel state information in the second transmission mode is referred to as the second channel state information, which includes, but is not limited to, at least one of the following: one or more second precoding matrices, one or more second channel quality indicators, one or more second MCSs, and one or more second SINRs.

[0084] In one embodiment, a wireless communication system includes at least one base station and at least one terminal. Here, the base station includes N... t The base station transmits a reference signal (CSI-RS) on at least one reference signal resource (e.g., a CSI-RS resource). The k-th terminal receives the reference signal on the at least one reference signal resource and measures the channel matrix H. k It is an N r ×N t ×N rb A complex matrix of dimension H. k The channel state information (i.e., channel state information in the second transmission mode) for each subband is obtained, including but not limited to at least one of the following: wideband precoding matrix p k At least one sub-band precoding matrix p k,u At least one sub-band CQI k,u Broadband CQI kThe channel state information includes parameters such as RI (Radio Frequency) and interference noise intensity. The terminal transmits the channel state information. The base station receives the channel state information and processes it for scheduling purposes.

[0085] In one example, the precoding matrix can also be a quantized value of a precoding matrix, such as a precoding matrix indicating a PMI, or a precoding matrix or its quantized value obtained through artificial intelligence or other means. If it is a PMI, then it needs to be mapped from the PMI to the precoding matrix according to the agreement between the base station and the terminal. If it is a quantized value of the precoding matrix output by an artificial intelligence encoder, then the base station needs to dequantize the quantized precoding to obtain a precoding matrix, and input it into a decoder to obtain the final precoding matrix. In some other embodiments, it will be said directly that the base station obtains one or more precoding matrices from the CSI sent by the terminal, and the operation process of recovering the precoding matrix from the quantized precoding matrix will not be described in detail.

[0086] In one embodiment, the sub-band CQI obtained by the k-th terminal is obtained by quantizing its acquired SINR. Here, the signal-to-interference-to-noise ratio of the k-th terminal under SU satisfies the following relationship:

[0087] Here, SINR SU,k,u h represents the signal-to-interference-to-noise ratio in the u-th subband of the k-th terminal under SU. k,u w k,u , I k,u Let represent the channel matrix, the second precoding matrix, the noise received, and the interference from neighboring cells received by the k-th terminal in the u-th subband under SU, respectively.

[0088] In one embodiment, to achieve higher spectral efficiency, the base station simultaneously schedules multiple terminals on the same time-frequency resources. These multiple terminals perform spatially multiplexed transmission. To determine whether two or more terminals are suitable for MU (Multi-Use Unit) transmission, the SINR of the MU needs to be calculated first, and the spectral efficiency or throughput of paired users under MU transmission is determined based on the SINR. Assume the base station plans to have K terminals perform MU transmission. Then, among the K terminals performing MU transmission, the SINR of the u-th subband of the k-th terminal is... MU,k,u The following relationship must be satisfied:

[0089] Here, h k,u w k,u , I k,u Let represent the channel matrix, precoding matrix, noise received, and interference from neighboring cells received by the k-th terminal in the u-th subband under SU, respectively. wj,u These represent the MU interference experienced by the k-th terminal in the u-th subband and the second precoding matrix of the j-th terminal in the u-th subband, respectively.

[0090] In one example, the wireless communication system is a time-division multiplexing system. The base station obtains the uplink reference signal by measurement, such as by measuring the SRS to obtain the uplink channel matrix h on the u-th subband of the k-th terminal. k,u .

[0091] In one example, the wireless communication system is a frequency division multiplexing system, in which case the base station cannot obtain the uplink channel matrix h of the u-th subband of the k-th terminal. k,u Yes, it can only obtain the following channel state information from the SU sent by the terminal, including but not limited to at least one of the following: wideband precoding matrix p k At least one sub-band precoding matrix p k,u At least one sub-band CQI k,u Broadband CQI k .

[0092] The following examples illustrate how a base station can predict a relatively accurate channel matrix and a precoding matrix of a MU based on the CSI under the SU fed back by the terminal, and how to calculate the modulation and coding scheme of each terminal in the MU based on the calculated channel matrix and precoding matrix.

[0093] In one embodiment, to fully realize the performance of multi-user MIMO, multiple high-performance artificial intelligence models are stored and maintained. These artificial intelligence models can be simply called models. In one embodiment, artificial intelligence includes machine learning (ML), deep learning, reinforcement learning, transfer learning, deep reinforcement learning, meta-learning, etc.

[0094] In one embodiment, artificial intelligence is implemented through an artificial intelligence model (or neural network). The model includes multiple layers, each layer including at least one node (a node in a neural network). In one embodiment, the neural network includes an input layer, an output layer, and at least one hidden layer. In one embodiment, the model refers to the data flow from the input to the output of a sample passing through multiple linear or non-linear components. The model includes a neural network model, a non-artificial intelligence module for processing information, and functional components or functions that map input information to output information, where the mapping includes linear and non-linear mappings. In one embodiment, each model corresponds to a model identity (Model ID). In one embodiment, the model identity may also have other equivalent names or concepts such as: model index, first identifier, function indicator (function ID), model indicator, etc.

[0095] In one embodiment, model parameters are obtained through online or offline training. For example, the model parameters are trained by inputting at least one sample. Here, the sample includes at least one feature and at least one label. The sample's features are used as input to the model, while the sample's label is the ideal value corresponding to the model's output, used for performance monitoring or calculating the loss function, etc.

[0096] In one embodiment, a sample includes P features and Q labels. Here, P is a positive integer, and Q is an integer greater than or equal to 0. Multiple samples constitute a dataset.

[0097] In one embodiment, a feature can be an array, and in another embodiment, a label can also be an array. Here, the array can be a vector, a matrix, or a tensor larger than two dimensions; the dimension of the array corresponding to the sample is also called the dimension of the sample array. Each element in the array can be a discrete value, a real number, a real number between 0 and 1, or a real number between -0.5 and 0.5, etc.

[0098] In one implementation, a base station may have multiple models. These models include, but are not limited to, neural networks of one or more of the following, as well as composite neural networks combining these: feedforward neural network (FNN), convolutional neural network (CNN), recurrent neural network (RNN), long short-term memory network (LSTM), gated recurrent unit (GRU), generative adversarial network (GAN), variational autoencoder (VAE), attention mechanism network, graph neural network (GNN), capsule network, etc. In these embodiments, for ease of distinction, the models are referred to as model 1, model 2, etc. The designation "first" and "second" is merely to distinguish different models and does not rank the models or imply any priority or quality.

[0099] In some embodiments, taking the k-th terminal among multiple terminals as an example, where k = 1, ..., K, and K is a positive integer representing the number of terminals served under a cell or the number of terminals that need to be paired as a MU. Similar operations apply to other terminals, and will not be described in detail here.

[0100] In some embodiments, to facilitate better processing by the AI ​​model, the input data to the model undergoes a series of preprocessing steps, including but not limited to: normalizing the input data, splitting each element of the input data into real and imaginary parts, grouping the input data, zero-padding, and dimensionality transformation, before the processed data is input into the AI ​​model. In some embodiments, the model's output also requires a series of post-processing steps to ensure that the processed data meets output format requirements. Here, post-processing can be a series of inverse processes of preprocessing. These will not be elaborated upon in subsequent embodiments.

[0101] The first transmission mode in this disclosure can be MU-MIMO, and the second transmission mode can be SU-MIMO.

[0102] This disclosure provides a data transmission method that can be applied to a first node. As shown in Figure 2, the method includes the following steps:

[0103] S101. Determine the K predicted channel information for the K second nodes.

[0104] In some embodiments, the K predicted channel information includes the predicted channel matrix on each subband of the K second nodes.

[0105] In this disclosure, the predicted channel matrix for each subband of the K second nodes can be represented as follows: k is a non-negative integer less than or equal to K. It can also be expressed as k = 1, ..., K, where K is the number of second nodes (terminals) paired in the first transmission mode, and is an integer greater than 1. u = 1, ..., U, where U is a positive integer, representing the number of subbands or resource blocks (RBs) of the second node (terminal).

[0106] In some embodiments, determining the K predicted channel information of K second nodes includes: for the kth second node among the K second nodes, obtaining the second channel state information of the kth second node; and based on the second channel state information of the kth second node, determining the predicted channel matrix on each subband of the kth second node, where k is a non-negative integer less than or equal to K.

[0107] Here, the second channel state information is the channel state information under the second transmission mode. The second channel state information of the kth second node includes the second precoding matrix on each subband of the kth second node, as well as the channel quality indication on each subband of the kth second node and / or the bandwidth channel quality indication of the kth second node.

[0108] In this disclosure, the second precoding matrix on each subband of the K second nodes can be represented as p k,u k is a non-negative integer less than or equal to K. It can also be expressed as k = 1, ..., K, where K is the number of paired second nodes (terminals) in the first transmission mode, and is an integer greater than 1. u = 1, ..., U, where U is a positive integer representing the number of subbands or RBs of the second node (terminal).

[0109] Example 1, taking the first node as the base station and the second node as the terminal as an example. The base station includes the first model, which receives the precoding matrix p of each subband of the k-th terminal under SU-MIMO transmitted by the k-th terminal. k,u (Generally obtained through channel heterogeneity or by looking up a table based on the precoding matrix indication fed back by the terminal, which will not be elaborated on further), and the channel quality indication (which can be represented as CQI) on each subband of the k-th terminal under SU-MIMO. k,u (where u = 1, ..., U, and U is a positive integer representing the number of sub-bands or RBs of the terminal). In some embodiments, the signal-to-interference-plus-noise ratio (SINR) is obtained by looking up a table using the channel quality indicator. SU,k,u and SINRSU,k,u Replace the aforementioned CQI k,u This will not be elaborated upon further. k,u and SINR SU,k,u Let Nt*Ns be a complex matrix. Multiply the precoding matrix of the i-th layer of the u-th subband of the k-th terminal under SU-MIMO by the SINR of the u-th subband of the k-th second node under SU-MIMO. SU,k,u The i-th value is used to obtain the weighted precoding matrix. In some embodiments, the weighted precoding matrix is ​​preprocessed and then input into the first model. The data output by the first model is processed to obtain the prediction channel matrix for each sub-band of the k-th terminal. Here, u = 1, ..., U, where U is a positive integer representing the number of sub-bands or RBs of the second node.

[0110] Example 2, taking the first node as the base station and the second node as the terminal as an example. The base station includes the second model, which receives the precoding matrix p of each subband of the k-th terminal under SU-MIMO transmitted by the k-th terminal. k,u And each subband of the k-th terminal under SU-MIMO corresponds to a wideband channel quality indicator (which can be represented as CQI). k In this embodiment or other embodiments, the signal-to-interference-noise ratio (SINR) is obtained by looking up a table using the channel quality indicator. SU,k and SINR SU,k Replace CQI k This will not be elaborated upon further. Here, p k,u Let Nt*Ns be a complex matrix. Multiply the precoding matrix of the i-th layer of the u-th subband of the k-th terminal under SU-MIMO by the wideband SINR. su,k The i-th value is used to obtain the weighted precoding matrix. In some embodiments, the weighted precoding matrix is ​​preprocessed and then input into the second model. The data output by the second model is processed to obtain the prediction channel matrix for each sub-band of the k-th terminal. U is a positive integer representing the number of subbands or RBs in the terminal.

[0111] In some embodiments, the channel quality indication on each subband of the kth second node is determined based on the bandwidth channel quality indication of the kth second node.

[0112] Example 3, taking the first node as the base station and the second node as the terminal as an example. The base station includes the third model, which receives the precoding matrix p of each subband of the k-th terminal under SU-MIMO transmitted by the k-th terminal. k,u And under SU-MIMO, each subband of the k-th terminal corresponds to a Wideband Channel Quality Indicator (CQI). k SINR can be obtained by looking up the table.SU,k And use a model to represent the SINR. SU,k Predict and generate the Channel Quality Indicator (SINR) for each subband of the k-th terminal. SU,k,u u = 1, ..., U, where U is a positive integer representing the number of subbands or RBs of the terminal. Here, p k,u and SINR SU,k,u Let Nt*Ns be a complex matrix. Multiply the precoding matrix of the i-th layer of the u-th subband of the k-th terminal by the SINR of the u-th subband of the k-th terminal. SU,k,u The i-th value is used to obtain the weighted precoding matrix. In some embodiments, the weighted precoding matrix is ​​preprocessed and then input into the third model. The data output by the third model is processed to obtain the prediction channel matrix for each subband of the k-th terminal.

[0113] In some embodiments, determining the predicted channel matrix on each subband of the kth second node based on the second channel state information of the kth second node includes: measuring the probe reference signal transmitted by the kth second node to obtain the uplink channel information of the kth second node; and determining the predicted channel matrix on each subband of the kth second node based on the uplink channel information and the second channel state information of the kth second node, where k is a non-negative integer less than or equal to K.

[0114] Example 4, taking the first node as the base station and the second node as the terminal as an example. The k-th terminal receives the configuration information related to the SRS resources from the base station and transmits SRS according to the configuration information. The base station receives SRS on the SRS resources and measures the uplink channel information of the k-th terminal (the uplink channel information of the k-th terminal can be represented as...). U is a positive integer, representing the number of subbands or RBs of the terminal; after a series of preprocessing steps on the uplink channel information, it is combined with the weighted precoding matrix obtained in Example 1, Example 2, or Example 3 as the input to the fourth model. The output data of the fourth model is then processed to obtain the prediction channel matrix for each subband of the k-th terminal.

[0115] In some embodiments, determining the K predicted channel information of the K second nodes includes: obtaining the location information of the K second nodes; and determining the predicted channel matrix on each subband of the K second nodes based on the location information of the K second nodes.

[0116] In some embodiments, obtaining the location information of K second nodes includes: obtaining the location information of K second nodes through sensing technology or artificial intelligence-based positioning technology.

[0117] Example 5 uses a base station as the first node and a terminal as the second node. The base station obtains the terminal's location information. In one example, the base station receives the terminal's location information to obtain the terminal's location information. In another example, it receives location information sent by the location manager to obtain the terminal's location information. In yet another example, it obtains the terminal's location information using its own single-base station positioning algorithm. And in yet another example, it obtains the terminal's location information using sensing technology. The descriptions of these methods of obtaining location information will not be elaborated upon further.

[0118] The base station performs a series of preprocessing steps on the terminal's location information and uses it as input to the fifth model. The output data of the fifth model is then processed to obtain the predicted channel matrix for each subband of the k-th terminal. U is a positive integer representing the number of sub-bands or RBs in the terminal. The fifth model has the ability to reconstruct channel information based on location information.

[0119] In some embodiments, determining the prediction channel matrix on each subband of the K second nodes based on the location information of the K second nodes includes: for the kth second node among the K second nodes, obtaining the second channel state information of the kth second node; and determining the prediction channel matrix on each subband of the kth second node based on the location information of the K second nodes and the second channel state information of the kth second node.

[0120] Here, the second channel state information is the channel state information under the second transmission mode. The second channel state information of the kth second node includes the second precoding matrix on each subband of the kth second node, and the channel quality indicator on each subband of the kth second node and / or the bandwidth channel quality indicator of the kth second node, where k is a non-negative integer less than or equal to K.

[0121] Example 6, taking the first node as the base station and the second node as the terminal as an example. The base station obtains the terminal's location information. After performing a series of preprocessing steps on the terminal's location information, the base station combines it with the weighted precoding matrix obtained in Example 1, Example 2, or Example 3 as the input to the sixth model. The output data of the sixth model is then processed to obtain the predicted channel matrix for each subband of the k-th terminal. U is a positive integer representing the number of subbands or RBs in the terminal.

[0122] In some embodiments, determining the prediction channel matrix for each subband of the kth second node based on the location information of the K second nodes and the second channel state information of the kth second node includes: measuring the probe reference signal transmitted by the kth second node to obtain the uplink channel information of the kth second node; and determining the prediction channel matrix for each subband of the kth second node based on the location information of the K second nodes, the uplink channel information of the kth second node, and the second channel state information of the kth second node, where k is a non-negative integer less than or equal to K.

[0123] Example 7, taking the first node as the base station and the second node as the terminal as an example. The base station obtains the location information of the terminal. After performing a series of preprocessing steps on the terminal's location information, the base station combines it with the weighted precoding matrix obtained in Example 1, Example 2, or Example 3, and the uplink channel information of the k-th terminal obtained in Example 4, as input to the seventh model. The output data of the seventh model is then processed to obtain the prediction channel matrix for each subband of the k-th terminal. U is a positive integer representing the number of subbands or RBs in the terminal.

[0124] In some embodiments, determining the prediction channel matrix on each subband of the K second nodes based on the location information of the K second nodes includes: measuring the probe reference signal transmitted by the kth second node to obtain the uplink channel information of the kth second node; and determining the prediction channel matrix on each subband of the kth second node based on the location information of the K second nodes and the uplink channel information of the kth second node, where k is a non-negative integer less than or equal to K.

[0125] Example 8, taking the first node as the base station and the second node as the terminal as an example. The base station obtains the terminal's location information. After performing a series of preprocessing steps on the terminal's location information, the base station combines it with the uplink channel information obtained in Example 4 above as input to the eighth model. The output data of the eighth model is then processed to obtain the predicted channel matrix for each subband of the k-th terminal. U is a positive integer representing the number of subbands or RBs in the terminal.

[0126] S102. Based on K predicted channel information, determine K first channel state information of K second nodes.

[0127] Here, the first channel state information is the channel state information under the first transmission mode, and the first channel state information includes at least one first precoding matrix and / or at least one modulation and coding scheme, where K is a positive integer greater than 1.

[0128] In this disclosure, the first precoding matrix on each subband of the K second nodes can be represented as w k,uk is a non-negative integer less than or equal to K. It can also be expressed as k = 1, ..., K, where K is the number of second nodes (terminals) paired in a transmission mode, and is an integer greater than 1. u = 1, ..., U, where U is a positive integer, representing the number of subbands or RBs of the second node (terminal).

[0129] In some embodiments, determining K first channel state information of K second nodes based on K predicted channel information includes: determining a first precoding matrix on each subband of K second nodes based on the predicted channel matrix on each subband of K second nodes.

[0130] For example, the prediction channel matrix of each sub-band of the kth second node and the prediction channel matrix of each sub-band of the paired second node under MU are input into the artificial intelligence model to obtain the first precoding matrix of the kth second node and the paired second node under MU.

[0131] Example 9, taking the first node as a base station and the second node as a terminal as an example. The base station obtains the predicted channel matrix for each subband of the K terminals according to any of the methods in the above examples or embodiments. The predicted channel matrix As input to the ninth model, the data output by the ninth model undergoes some subsequent processing to obtain the precoding matrix w for K terminals performing MU. k,u .

[0132] In some embodiments, based on the predicted channel matrix on each subband of the K second nodes, the first precoding matrix on each subband of the K second nodes can be determined by the zero flag (ZF) algorithm.

[0133] For example, the precoding method includes the ZF algorithm, and the first precoding matrix on each subband of the second node is the precoding matrix under the zero-breaking algorithm.

[0134] Example 10, taking the first node as a base station and the second node as a terminal as an example. The base station obtains the predicted channel matrix for each subband of the K terminals according to any of the methods in the above examples or embodiments. The predicted channel matrix As input to the tenth model, the tenth model outputs a diagonal loading coefficient. Of course, in other embodiments, the diagonal loading coefficient α can also be obtained by outputting other content from the model, such as neighboring cell interference information. The diagonal loading coefficient is then substituted into the calculation formula (or relation) corresponding to the first precoding matrix under the zero-breaking algorithm below to obtain the precoding matrix W when K terminals perform MU. u k = 1, ..., K, where K is the number of terminals paired by MU-MIMO and is an integer greater than 1. u = 1, ..., U, where U is a positive integer representing the number of subbands or RBs of the terminal.

[0135] In some embodiments, the first precoding matrices on each subband of the K second nodes under the zero-breaking algorithm satisfy the following relationship:

[0136] here, W represents the predicted channel matrix for the u-th subband of the i-th node among K second nodes, where i is a positive integer less than or equal to K; u w is the first precoding matrix on the u-th subband of K second nodes; j,u Let α be the first precoding matrix on the u-th subband of the j-th node among K second nodes, where j is a positive integer less than or equal to K; α is the diagonal loading coefficient, I is the identity matrix, and u is a positive integer.

[0137] Understandably, α is the diagonal loading coefficient. If this coefficient is too high, the zero-breaking algorithm will be poor, while if it is too small, the matrix will be... Illegible behavior occurs, leading to a decrease in the accuracy of its inverse. Diagonal loading coefficients obtained through AI can improve the performance of the zero-breaking algorithm. It should be noted that the zero-breaking algorithm treats each second node (terminal) as a layer. If a user has multiple layers, zero-breaking will also occur between them, resulting in performance degradation. One solution is block diagonalization.

[0138] In some embodiments, based on the predicted channel matrix on each subband of the K second nodes, the first precoding matrix on each subband of the K second nodes is determined by the block diagonalization (BD) algorithm.

[0139] For example, precoding methods include the BD algorithm, where the first precoding matrix on each subband of the K second nodes is the precoding matrix under the precoding block diagonalization algorithm.

[0140] Example 11, taking the first node as the base station and the second node as the terminal as an example. The base station obtains the predicted channel matrix for each subband of the K terminals according to any of the methods in the above examples or embodiments. The first precoding matrix under the BD algorithm can be obtained through the following steps. k = 1, ..., K, where K is the number of terminals paired by MU-MIMO and is an integer greater than 1. u = 1, ..., U, where U is a positive integer representing the number of subbands or RBs of the terminals.

[0141] The first precoding matrix under the BD algorithm of the computing terminal, namely:

[0142] Calculate the interfering user channel of the i-th terminal

[0143] Get H i,u null space: [U i,u D i,u V i,u ] = svd(H i,u );

[0144] Select at least one column of the null space as the first precoding matrix for the i-th terminal: w i,u =V i,u [:,1:,N i,s ];

[0145] here N i,s Let be the channel rank of the i-th terminal.

[0146] In some embodiments, the zero space of each terminal can be selected using artificial intelligence.

[0147] In some embodiments, determining the K first channel state information of the K second nodes based on the K predicted channel information further includes: for the kth second node among the K second nodes, obtaining the second SINR on each sub-band of the kth second node; determining the first SINR on each sub-band of the kth second node based on the second SINR on each sub-band of the kth second node, the predicted channel matrix on each sub-band of the K second nodes, and the first precoding matrix on each sub-band of the K second nodes; and determining the modulation and coding scheme of the kth second node based on the first SINR on each sub-band of the kth second node, where k is a non-negative integer less than or equal to K.

[0148] In some embodiments, the ratio of the first signal to the interference noise on each sub-band of the k-th second node satisfies the following relationship:

[0149] Here, SINR MU,k,u SINR is the first SINR of the u-th subband of the k-th second node. SU,k,u The second SINR on the u-th subband of the k-th second node; β k,k,u To determine β based on the predicted channel matrix on the u-th sub-band of the k-th second node and / or the first precoding matrix on the u-th sub-band of the k-th second node, using an artificial intelligence system. k,j,u It is determined by predicting through an artificial intelligence system and / or based on the predicted channel matrix on the u-th sub-band of the k-th second node and / or the first precoding matrix on the u-th sub-band of the j-th second node among K second nodes, where u is a positive integer and j is a non-negative integer less than or equal to K.

[0150] In some embodiments, β k,k,uThis can be predicted using an AI system. β k,k,u It can also be here, Let w be the predicted channel matrix for the u-th sub-band of the k-th second node. k,u β is the first precoding matrix on the u-th subband of the k-th second node. k,j,u It can be Let w be the predicted channel matrix for the u-th sub-band of the k-th second node. j,u This is the first precoding matrix on the u-th subband of the second node.

[0151] Example 12, taking the first node as a base station and the second node as a terminal as an example. The base station obtains the predicted channel matrix of multiple terminals according to a method in the above examples or embodiments. Furthermore, based on methods such as Example 10 or Example 11, the first precoding matrix w under the MU of multiple terminals was obtained. k,u Then it can be based on w k,u Calculate the SINR under the MU for each terminal. k = 1, ..., K, where K is the number of terminals paired with MU-MIMO, and is an integer greater than 1. u = 1, ..., U, where U is a positive integer representing the number of subbands or RBs of the terminal.

[0152] In some embodiments, the SINR under the MU of each second node is re-looked up to obtain the MCS when the second node performs the MU.

[0153] S103. Data transmission is performed based on K first channel state information.

[0154] For example, data transmission is performed based on the MCS obtained in Example Twelve and the first precoding matrix under the MU obtained in Example Ten or Example Eleven.

[0155] In some embodiments, K first channel state information messages are sent. Here, the first channel state information may include the identifier of the second node, so that the second node receives matching first channel state information and performs data transmission based on the first channel state information.

[0156] This disclosure provides a data transmission method that can be applied to a third node. As shown in Figure 3, the method includes the following steps:

[0157] S201, Receive data sent by the first node based on the first channel state information of the third node.

[0158] Here, the first channel state information is determined based on the K predicted channel information of the K second nodes. The first channel state information is the channel state information under the first transmission mode, and the first channel state information includes at least one first precoding matrix and / or at least one modulation and coding scheme. The K second nodes include third nodes, and K is a positive integer greater than 1.

[0159] In some embodiments, the first node receives first channel state information from the third node. This allows the first node to perform intelligent processing based on the first channel state information, thereby further improving the performance of the current multi-user scheduling.

[0160] In some embodiments, the K predicted channel information includes the predicted channel matrix on each subband of the K second nodes.

[0161] In some embodiments, the predicted channel matrix on each subband of the kth second node among the K second nodes is determined based on the second channel state information of the kth second node;

[0162] Here, the second channel state information is the channel state information under the second transmission mode. The second channel state information of the kth second node includes the second precoding matrix on each subband of the kth second node, the channel quality indicator on each subband of the kth second node and / or the bandwidth channel quality indicator of the kth second node, where k is a non-negative integer less than or equal to K.

[0163] In some embodiments, the second channel status information of the third node is transmitted.

[0164] In some embodiments, the predicted channel matrix of each subband of the kth second node among the K second nodes is determined based on the uplink channel information and the second channel state information of the kth second node;

[0165] Here, the uplink channel information of the kth second node is obtained by measuring the probe reference signal sent by the kth second node.

[0166] In some embodiments, the prediction channel matrix on each subband of the kth second node among the K second nodes is determined based on the location information of the K second nodes, where k is a non-negative integer less than or equal to K.

[0167] In some embodiments, the location information of the K second nodes is obtained through sensing technology or artificial intelligence-based positioning technology.

[0168] In some embodiments, the predicted channel matrix of each subband of the kth second node among the K second nodes is determined based on the location information of the K second nodes and the second channel state information of the kth second node;

[0169] Here, the second channel state information is the channel state information under the second transmission mode. The second channel state information of the kth second node includes the second precoding matrix on each subband of the kth second node, as well as the channel quality indication on each subband of the kth second node and / or the bandwidth channel quality indication of the kth second node.

[0170] In some embodiments, the predicted channel matrix of each subband of the kth second node among the K second nodes is determined based on the location information of the K second nodes, the uplink channel information of the kth second node, and the second channel state information of the kth second node.

[0171] Here, the uplink channel information of the kth second node is obtained by measuring the probe reference signal sent by the kth second node.

[0172] In some embodiments, the kth second node receives configuration information related to the probe reference signal resource sent by the first node, and transmits a probe reference signal according to the configuration information related to the probe reference signal resource. The first node receives the probe reference signal on the probe reference signal resource and measures the uplink channel information of the kth second node.

[0173] In some embodiments, the prediction channel matrix of each subband of the kth second node among the K second nodes is determined based on the location information of the K second nodes and the uplink channel information of the kth second node;

[0174] Here, the uplink channel information of the kth second node is obtained by measuring the probe reference signal sent by the kth second node.

[0175] In some embodiments, the channel quality indication on each subband of the kth second node is determined based on the bandwidth channel quality indication of the kth second node.

[0176] In some embodiments, the first precoding matrix on each subband of the third node is determined based on the predicted channel matrix on each subband of the K second nodes.

[0177] In some embodiments, the first precoding matrix on each subband of the third node is determined based on the predicted channel matrix on each subband of the K second nodes and by a zero-breaking algorithm.

[0178] For example, the precoding method includes the zero-breaking algorithm, and the first precoding matrix on each subband of the third node is the precoding matrix under the zero-breaking algorithm.

[0179] In some embodiments, the first precoding matrix on each subband of the third node is determined based on the predicted channel matrix on each subband of the K second nodes, and by a block diagonalization algorithm.

[0180] For example, the precoding method includes the precoding block diagonalization algorithm, where the first precoding matrix on each subband of the third node is the precoding matrix under the precoding block diagonalization algorithm.

[0181] In some embodiments, the modulation and coding scheme of the third node is determined based on the first SINR of each sub-band of the third node. The first SINR of each sub-band of the third node is determined based on the second SINR of each sub-band of the third node, the prediction channel matrix of each sub-band of the K second nodes, and the first precoding matrix of each sub-band of the K second nodes.

[0182] For a more detailed description of S201, as well as a more detailed description of its various technical features and a description of its beneficial effects, please refer to the descriptions in the above embodiments or examples, which will not be repeated here.

[0183] The foregoing primarily describes the solutions of the embodiments of this disclosure from a methodological perspective. A data transmission apparatus is also illustrated below for executing the data transmission methods in any of the above embodiments and their possible implementations. It is understood that the data transmission apparatus, in order to implement the data transmission method, includes hardware structures and / or software modules corresponding to the execution of various functions; those skilled in the art should readily recognize that, in conjunction with the algorithm steps of the examples described in the embodiments of this disclosure, this disclosure can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this disclosure.

[0184] This disclosure embodiment can divide the data transmission device into functional modules according to the above method embodiment. For example, each function can be divided into a separate functional module, or two or more functions can be integrated into one functional module. The integrated module can be implemented in hardware or software. It should be noted that the module division in this disclosure embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods. The following description uses the example of dividing each functional module according to each function.

[0185] Figure 4 is a block diagram of a data transmission device according to some embodiments, applied to a first node. The data transmission device 300 includes a processing module 301, a communication module 302, and a measurement module 303.

[0186] Here, the processing module 301 is used to determine the K predicted channel information of the K second nodes;

[0187] The processing module 301 is also used to determine the K first channel state information of the K second nodes based on the K predicted channel information;

[0188] Communication module 302 is used to transmit data based on K first channel state information;

[0189] Here, the first channel state information is the channel state information under the first transmission mode. The first channel state information includes at least one first precoding matrix and / or at least one modulation and coding scheme, where K is a positive integer greater than 1.

[0190] In some embodiments, the K predicted channel information includes the predicted channel matrix on each subband of the K second nodes.

[0191] In some embodiments, the processing module 301 is specifically used for:

[0192] For the kth second node among the K second nodes, obtain the second channel state information of the kth second node;

[0193] Based on the second channel state information of the kth second node, the predicted channel matrix on each sub-band of the kth second node is determined, where k is a non-negative integer less than or equal to K;

[0194] Here, the second channel state information is the channel state information under the second transmission mode. The second channel state information of the kth second node includes the second precoding matrix on each subband of the kth second node, as well as the channel quality indication on each subband of the kth second node and / or the bandwidth channel quality indication of the kth second node.

[0195] In some embodiments, the measurement module 303 is used to measure the probe reference signal sent by the kth second node to obtain the uplink channel information of the kth second node; the processing module 301 is used to determine the prediction channel matrix on each subband of the kth second node based on the uplink channel information and the second channel state information of the kth second node, where k is a non-negative integer less than or equal to K.

[0196] In some embodiments, the communication module 302 is used to acquire the location information of K second nodes; the processing module 301 is used to determine the prediction channel matrix on each subband of the K second nodes based on the location information of the K second nodes.

[0197] In some embodiments, the communication module 302 is used to acquire the location information of K second nodes through sensing technology or artificial intelligence-based positioning technology.

[0198] In some embodiments, the communication module 302 is used to obtain the second channel state information of the kth second node among the K second nodes;

[0199] Processing module 301 is used to determine the prediction channel matrix on each subband of the kth second node based on the location information of the K second nodes and the second channel state information of the kth second node;

[0200] Here, the second channel state information is the channel state information under the second transmission mode. The second channel state information of the kth second node includes the second precoding matrix on each subband of the kth second node, the channel quality indicator on each subband of the kth second node and / or the bandwidth channel quality indicator of the kth second node, where k is a non-negative integer less than or equal to K.

[0201] In some embodiments, the measurement module 303 is used to measure the probe reference signal sent by the kth second node to obtain the uplink channel information of the kth second node;

[0202] The processing module 301 is used to determine the prediction channel matrix of each subband of the kth second node based on the location information of the kth second nodes, the uplink channel information of the kth second node, and the second channel state information of the kth second node.

[0203] In some embodiments, the measurement module 303 is used to measure the probe reference signal sent by the kth second node to obtain the uplink channel information of the kth second node; the processing module 301 is used to determine the prediction channel matrix on each subband of the kth second node based on the location information of the K second nodes and the uplink channel information of the kth second node, where k is a non-negative integer less than or equal to K.

[0204] In some embodiments, the channel quality indication on each subband of the kth second node is determined based on the bandwidth channel quality indication of the kth second node.

[0205] In some embodiments, the processing module 301 is configured to determine a first precoding matrix on each subband of the K second nodes based on the predicted channel matrix on each subband of the K second nodes.

[0206] In some embodiments, the processing module 301 is used to determine the first precoding matrix on each subband of the K second nodes based on the predicted channel matrix on each subband of the K second nodes using a zero-breaking algorithm.

[0207] In some embodiments, the first precoding matrices on each subband of the K second nodes satisfy the following relationship:

[0208] here, W represents the predicted channel matrix for the u-th subband of the i-th node among K second nodes, where i is a positive integer less than or equal to K; u w is the first precoding matrix on the u-th subband of K second nodes; j,u Let α be the first precoding matrix on the u-th subband of the j-th node among K second nodes, where j is a positive integer less than or equal to K; α is the diagonal loading coefficient, I is the identity matrix, and u is a positive integer.

[0209] In some embodiments, the processing module 301 is used to determine the first precoding matrix on each subband of the K second nodes based on the predicted channel matrix on each subband of the K second nodes using a block diagonalization algorithm.

[0210] In some embodiments, the communication module 302 is configured to, for the kth second node among the K second nodes, obtain the second signal to interference noise ratio on each sub-band of the kth second node;

[0211] Processing module 301 is used to determine the first signal-to-interference-to-noise ratio in each sub-band of the k-th second node based on the second signal-to-interference-to-noise ratio in each sub-band of the k-th second node, the predicted channel matrix in each sub-band of the K-th second node, and the first precoding matrix in each sub-band of the K-th second node.

[0212] The processing module 301 is also used to determine the modulation and coding scheme of the kth second node based on the first signal-to-interference-noise ratio on each sub-band of the kth second node, where k is a non-negative integer less than or equal to K.

[0213] In some embodiments, the ratio of the second signal to the interference noise on each sub-band of the k-th second node satisfies the following relationship:

[0214] Here, SINR MU,k,u SINR is the signal-to-interference-to-noise ratio of the first subband of the k-th second node. SU,k,u β is the ratio of the second signal to the interference noise on the u-th subband of the k-th second node; k,k,u To determine β based on the predicted channel matrix on the u-th sub-band of the k-th second node and / or the first precoding matrix on the u-th sub-band of the k-th second node, using an artificial intelligence system. k,j,u It is determined by predicting through an artificial intelligence system and / or based on the predicted channel matrix on the u-th sub-band of the k-th second node and / or the first precoding matrix on the u-th sub-band of the j-th second node among K second nodes, where u is a positive integer and j is a non-negative integer less than or equal to K.

[0215] For a more detailed description of the processing module 301, communication module 302, and measurement module 303, as well as a more detailed description of the various technical features and the beneficial effects, please refer to the corresponding method embodiment section above, which will not be repeated here.

[0216] Figure 5 is a block diagram of another data transmission device according to some embodiments, applied to a third node. The data transmission device 400 includes a communication module 401 and a processing module 402.

[0217] Here, the communication module 401 is used to receive data sent by the first node based on the first channel state information of the third node;

[0218] The first channel state information is determined based on the K predicted channel information of the K second nodes; the first channel state information is the channel state information under the first transmission mode, and the first channel state information includes at least one first precoding matrix and / or at least one modulation and coding scheme, the K second nodes include third nodes, and K is a positive integer greater than 1.

[0219] In some embodiments, the processing module 402 is used to determine the second channel state information of the third node.

[0220] The communication module 401 is used to send the second channel status information of the third node.

[0221] For a more detailed description of the communication module 401 and the processing module 402, as well as a more detailed description of their respective technical features and beneficial effects, please refer to the corresponding method embodiment section above, which will not be repeated here.

[0222] It should be noted that the modules in Figure 4 and / or Figure 5 can also be referred to as units; for example, a communication module can be referred to as a communication unit. Furthermore, in the embodiments shown in Figure 4 and / or Figure 5, the names of the modules may not be those shown in the figures; for example, a communication module can also be referred to as a transmitting module or a receiving module.

[0223] If the units or modules in Figures 4 and / or 5 are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this disclosure, in essence, or the parts that contribute to the prior art, or all or part of the technical solutions, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods of the various embodiments of this disclosure. Storage media for storing computer software products include: USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, optical disks, and other media capable of storing program code.

[0224] In the case of implementing the functions of the integrated modules described above in hardware, embodiments of this disclosure also provide a possible structure for a communication device used to execute the data transmission method provided in embodiments of this disclosure. As shown in FIG6, the communication device 500 includes: a communication interface 503, a processor 502, and a bus 504. In some embodiments, the communication device may further include a memory 501.

[0225] Processor 502 may implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with embodiments of this disclosure. Processor 502 may be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with embodiments of this disclosure. Processor 502 may also be a combination that implements computational functions, such as a combination of one or more microprocessors, a digital signal processor (DSP), and a microprocessor, etc.

[0226] Communication interface 503 is used to connect to other devices via a communication network. This communication network can be Ethernet, wireless access network, wireless local area network (WLAN), etc.

[0227] The memory 501 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), disk storage medium or other magnetic storage device, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto.

[0228] In some embodiments, the memory 501 may exist independently of the processor 502. The memory 501 may be connected to the processor 502 via a bus 504 and is used to store instructions or program code. When the processor 502 calls and executes the instructions or program code stored in the memory 501, it can implement the data transmission method provided in the embodiments of this disclosure.

[0229] In other embodiments, memory 501 may also be integrated with processor 502.

[0230] Bus 504 can be an extended industry standard architecture (EISA) bus, etc. Bus 504 can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in Figure 6, but this does not mean that there is only one bus or one type of bus.

[0231] Some embodiments of this disclosure provide a computer-readable storage medium (e.g., a non-transitory computer-readable storage medium) storing computer program instructions that, when executed on a computer, cause the computer to perform the data transmission method as described in any of the above embodiments.

[0232] In some embodiments, the computer may be the aforementioned data transmission device, and this disclosure does not limit the specific form of the computer.

[0233] In some embodiments, the computer-readable storage media described above may include, but are not limited to: magnetic storage devices (e.g., hard disks, floppy disks, or magnetic tapes), optical disks (e.g., compact disks (CDs), digital versatile disks (DVDs), etc.), smart cards, and flash memory devices (e.g., erasable programmable read-only memory (EPROMs), cards, sticks, or key drives, etc.). The various computer-readable storage media described in this disclosure may represent one or more devices for storing information and / or other machine-readable storage media. The term "machine-readable storage media" may include, but is not limited to, wireless channels and various other media capable of storing, containing, and / or carrying instructions and / or data.

[0234] This disclosure provides a computer program product containing instructions that, when run on a computer, cause the computer to perform the data transmission method described in any of the above embodiments.

[0235] The above description is merely a specific embodiment of this disclosure, but the scope of protection of this disclosure is not limited thereto. Any changes or substitutions within the technical scope disclosed in this disclosure should be included within the scope of protection of this disclosure. Therefore, the scope of protection of this disclosure should be determined by the scope of the claims.

Claims

A data transmission method, wherein, Applied to the first node, the method includes: Determine the K predicted channel information for the K second nodes; Based on the K predicted channel information, determine the K first channel state information of the K second nodes; Data transmission is performed based on the K first channel state information; Wherein, the first channel state information is the channel state information under the first transmission mode, and the first channel state information includes at least one first precoding matrix and / or at least one modulation and coding scheme, and K is a positive integer greater than 1. According to the method of claim 1, wherein, The K predicted channel information includes the predicted channel matrix on each subband of the K second nodes. The method according to claim 2, wherein, The determination of the K predicted channel information for the K second nodes includes: For the kth second node among the K second nodes, obtain the second channel state information of the kth second node; Based on the second channel state information of the kth second node, the prediction channel matrix on each sub-band of the kth second node is determined, where k is a non-negative integer less than or equal to K; Wherein, the second channel state information is the channel state information under the second transmission mode, and the second channel state information of the kth second node includes the second precoding matrix on each subband of the kth second node, and the channel quality indication on each subband of the kth second node and / or the bandwidth channel quality indication of the kth second node. The method according to claim 3, wherein, The step of determining the predicted channel matrix for each sub-band of the k-th second node based on the second channel state information of the k-th second node includes: The uplink channel information of the kth second node is obtained by measuring the probe reference signal sent by the kth second node. Based on the uplink channel information and the second channel state information of the kth second node, the prediction channel matrix on each subband of the kth second node is determined, where k is a non-negative integer less than or equal to K. The method according to claim 2, wherein, The determination of the K predicted channel information for the K second nodes includes: Obtain the position information of the K second nodes; Based on the location information of the K second nodes, the prediction channel matrix on each subband of the K second nodes is determined. The method according to claim 5, wherein, The step of obtaining the location information of the K second nodes includes: The location information of the K second nodes is obtained through sensing technology or artificial intelligence-based positioning technology. The method according to claim 5, wherein, The step of determining the prediction channel matrix for each sub-band of the K second nodes based on their location information includes: For the kth second node among the K second nodes, obtain the second channel state information of the kth second node; Based on the location information of the K second nodes and the second channel state information of the kth second node, the prediction channel matrix on each sub-band of the kth second node is determined; Wherein, the second channel state information is the channel state information under the second transmission mode, and the second channel state information of the kth second node includes the second precoding matrix on each subband of the kth second node, and the channel quality indicator on each subband of the kth second node and / or the bandwidth channel quality indicator of the kth second node, where k is a non-negative integer less than or equal to K. The method according to claim 7, wherein, The step of determining the prediction channel matrix for each subband of the kth second node based on the location information of the K second nodes and the second channel state information of the kth second node includes: The uplink channel information of the kth second node is obtained by measuring the probe reference signal sent by the kth second node. Based on the location information of the K second nodes, the uplink channel information of the kth second node, and the second channel state information of the kth second node, the prediction channel matrix on each subband of the kth second node is determined. The method according to claim 5, wherein, The step of determining the prediction channel matrix for each sub-band of the K second nodes based on their location information includes: The uplink channel information of the kth second node is obtained by measuring the probe reference signal sent by the kth second node. Based on the location information of the K second nodes and the uplink channel information of the kth second node, the prediction channel matrix on each subband of the kth second node is determined, where k is a non-negative integer less than or equal to K. The method according to claim 3 or 7, wherein, The channel quality indication on each subband of the kth second node is determined based on the bandwidth channel quality indication of the kth second node. The method according to claim 2, wherein, The step of determining the K first channel state information of the K second nodes based on the K predicted channel information includes: Based on the predicted channel matrix of each sub-band of the K second nodes, the first precoding matrix of each sub-band of the K second nodes is determined. The method according to claim 11, wherein, The step of determining the first precoding matrix for each sub-band of the K second nodes based on the predicted channel matrix for each sub-band of the K second nodes includes: Based on the predicted channel matrix of each sub-band of the K second nodes, the first precoding matrix of each sub-band of the K second nodes is determined by the zero-breaking algorithm. The method according to claim 12, wherein, The first precoding matrix in each subband of the K second nodes satisfies the following relationship: in, W is the prediction channel matrix for the u-th subband of the i-th node among the K second nodes, where i is a positive integer less than or equal to K; u w is the first precoding matrix on the u-th subband of the K second nodes; j,u Let α be the first precoding matrix on the u-th subband of the j-th node among the K second nodes, where j is a positive integer less than or equal to K; α is the diagonal loading coefficient, I is the identity matrix, and u is a positive integer. The method according to claim 11, wherein, The step of determining the first precoding matrix for each sub-band of the K second nodes based on the predicted channel matrix for each sub-band of the K second nodes includes: Based on the predicted channel matrix of each sub-band of the K second nodes, the first precoding matrix of each sub-band of the K second nodes is determined by the block diagonalization algorithm. The method according to claim 11, wherein, The step of determining the K first channel state information of the K second nodes based on K predicted channel information further includes: For the kth second node among the K second nodes, obtain the second signal to interference noise ratio on each sub-band of the kth second node; Based on the second signal-to-interference-to-noise ratio (SNR) of each sub-band of the k-th second node, the predicted channel matrix of each sub-band of the k-th second node, and the first precoding matrix of each sub-band of the k-th second node, the first SNR of each sub-band of the k-th second node is determined. Based on the first signal-to-interference-to-noise ratio of each subband of the kth second node, the modulation and coding scheme of the kth second node is determined, where k is a non-negative integer less than or equal to K. The method according to claim 15, wherein, The ratio of the first signal to the interference noise in each sub-band of the k-th second node satisfies the following relationship: Among them, SINR MU,k,u SINR is the signal-to-interference-to-noise ratio of the first subband of the k-th second node. SU,k,u β is the ratio of the second signal to the interference noise on the u-th sub-band of the k-th second node; k,k,u To determine β by predicting and / or based on the predicted channel matrix on the u-th sub-band of the k-th second node and / or the first precoding matrix on the u-th sub-band of the k-th second node through an artificial intelligence system; k,j,u The prediction is made by an artificial intelligence system and / or based on the prediction channel matrix on the u-th sub-band of the k-th second node and / or the first precoding matrix on the u-th sub-band of the j-th second node among the K second nodes, where u is a positive integer and j is a non-negative integer less than or equal to K. A data transmission method, wherein, Applied to a third node, the method includes: Receive data sent by the first node based on the first channel state information of the third node; Wherein, the first channel state information is determined based on K predicted channel information of K second nodes; the first channel state information is channel state information under a first transmission mode, the first channel state information includes at least one first precoding matrix and / or at least one modulation and coding scheme, the K second nodes include the third node, and K is a positive integer greater than 1. The method according to claim 17, wherein, The K predicted channel information includes the predicted channel matrix on each subband of the K second nodes. The method according to claim 18, wherein, The predicted channel matrix on each subband of the kth second node among the K second nodes is determined based on the second channel state information of the kth second node; Wherein, the second channel state information is the channel state information under the second transmission mode, and the second channel state information of the kth second node includes the second precoding matrix on each subband of the kth second node, and the channel quality indicator on each subband of the kth second node and / or the bandwidth channel quality indicator of the kth second node, where k is a non-negative integer less than or equal to K. The method according to claim 19, wherein, The method further includes: Send the second channel status information of the third node. The method according to claim 19, wherein, The predicted channel matrix of each subband of the kth second node among the K second nodes is determined based on the uplink channel information and the second channel state information of the kth second node; The uplink channel information of the kth second node is obtained by measuring the probe reference signal sent by the kth second node. The method according to claim 18, wherein, The prediction channel matrix on each subband of the kth second node among the K second nodes is determined based on the location information of the K second nodes, where k is a non-negative integer less than or equal to K. The method according to claim 22, wherein, The location information of the K second nodes is obtained through sensing technology or artificial intelligence-based positioning technology. The method according to claim 22, wherein, The predicted channel matrix on each subband of the kth second node among the K second nodes is determined based on the location information of the K second nodes and the second channel state information of the kth second node; Wherein, the second channel state information is the channel state information under the second transmission mode, and the second channel state information of the kth second node includes the second precoding matrix on each subband of the kth second node, and the channel quality indication on each subband of the kth second node and / or the bandwidth channel quality indication of the kth second node. The method according to claim 24, wherein, The predicted channel matrix of each subband of the kth second node among the K second nodes is determined based on the location information of the K second nodes, the uplink channel information of the kth second node, and the second channel state information of the kth second node; The uplink channel information of the kth second node is obtained by measuring the probe reference signal sent by the kth second node. The method according to claim 22, wherein, The prediction channel matrix of each subband of the kth second node among the K second nodes is determined based on the location information of the K second nodes and the uplink channel information of the kth second node; The uplink channel information of the kth second node is obtained by measuring the probe reference signal sent by the kth second node. The method according to claim 19 or 24, wherein, The channel quality indication on each subband of the kth second node is determined based on the bandwidth channel quality indication of the kth second node. The method according to claim 18, wherein, The first precoding matrix on each subband of the third node is determined based on the prediction channel matrix on each subband of the K second nodes. The method according to claim 28, wherein, The modulation and coding scheme of the third node is determined based on the ratio of the first signal to the interference noise on each sub-band of the third node; The first signal-to-interference-to-noise ratio on each sub-band of the third node is determined based on the second signal-to-interference-to-noise ratio on each sub-band of the third node, the predicted channel matrix on each sub-band of the K second nodes, and the first precoding matrix on each sub-band of the K second nodes. A communication device, wherein, include: Memory and processor; The memory and the processor are coupled; The memory is used to store instructions that the processor can execute; When the processor executes the instructions, it performs the method as claimed in any one of claims 1 to 16 or claims 17-29. A computer-readable storage medium, wherein, The computer-readable storage medium includes a non-transitory computer-readable storage medium storing computer instructions that, when executed on a communication device, cause the communication device to perform the method as claimed in any one of claims 1 to 16 or claims 17 to 29. A computer program product, wherein, When the computer program product is executed, it implements the method as claimed in any one of claims 1 to 16 or claims 17-29.

Images