Data processing method and device, terminal, network equipment and storage medium

Abstract

The invention discloses a data processing method and device, a terminal, network equipment and a storage medium. The method comprises the following steps: receiving first channel data of a first codebook of a downlink channel of the terminal at first time; performing decompression calculation on the first channel data to obtain a second codebook; obtaining a third codebook according to the measurement result of the reference signal of the first time uplink channel; sending first configuration information to the terminal according to the correlation between the second codebook and the third codebook; wherein the first configuration information is configuration information of a model for compressing channel data of a codebook of a downlink channel. According to the scheme of the embodiment of the invention, the correlation between the uplink channel and the downlink channel can be determined by calculating the correlation between the second codebook and the third codebook; when the correlation between the uplink channel and the downlink channel is large, the characteristics of the downlink channel data are supplemented through the uplink channel data, so that the feedback accuracy of the codebook can be improved while the channel feedback quantity is reduced.

Description

Technical Field

[0001] This application relates to the field of mobile communication technologies, and particularly to a data processing method, apparatus, terminal, network device, and storage medium. Background Art

[0002] In the NR system, the terminal mainly relies on the codebook to feedback CSI. Currently, codebook types such as CSI type I, type II, and type II enhanced are supported, which are used to feedback information such as RI (rank indicator), PMI (Precoding matrix indicator), and CQI (Channel quality indicator).

[0003] The feedback overhead of the etype II codebook is proportional to the number of bits occupied by non-zero coefficients and the number of quantization parameters required. Directly expanding the low-Rank codebook to a high-Rank codebook will result in a significant increase in overhead. To reduce the codebook overhead of high Rank, existing solutions perform Rank expansion without increasing the feedback signaling overhead. The sum of the non-zero coefficients reported by all layers cannot be greater than a fixed constant configured by a certain higher layer, which limits the bits of non-zero coefficients. Although the feedback overhead of the codebook is controlled, the accuracy of the codebook feedback is also reduced accordingly. Summary of the Invention

[0004] At least one embodiment of this application provides a data processing method, apparatus, terminal, network device, and storage medium, which is used to solve the problem in the prior art that in order to reduce the codebook overhead of high Rank, the codebook feedback accuracy is reduced.

[0005] To solve the above technical problems, this application is implemented as follows:

[0006] In a first aspect, an embodiment of this application provides a data processing method, which is applied to a network device and includes:

[0007] Receiving first channel data of a first codebook of a downlink channel at a first time of a terminal;

[0008] Performing decompression calculation on the first channel data to obtain a second codebook;

[0009] Obtaining a third codebook according to the measurement result of a reference signal of an uplink channel at the first time;

[0010] Sending first configuration information to the terminal according to the correlation between the second codebook and the third codebook;

[0011] Wherein, the first configuration information is configuration information of a model for compressing channel data of a codebook of a downlink channel.

[0012] Further, receiving first-channel data of a first codebook of a downlink channel at a first time by a receiving terminal includes:

[0013] Determining a first target compression model, where the first target compression model is a model trained using channel data of the downlink channel;

[0014] Sending configuration information of the first target compression model to the terminal; the first target compression model is used to compress the channel data of the first codebook to obtain the first-channel data;

[0015] Receiving the first-channel data of the first codebook.

[0016] Further, the determining the first target compression model includes:

[0017] Determining the first target compression model according to the number of oversampled DFT beams, the number of configurable precoding matrices for each subband, and the number of downlink subbands.

[0018] Further, receiving first-channel data of a first codebook of a downlink channel at a first time by a receiving terminal further includes:

[0019] Receiving a first parameter and a second parameter of the first codebook;

[0020] where the first parameter is used to report a beam group; the second parameter includes DFT vectors for frequency-domain compression.

[0021] Further, decompressing and calculating the first-channel data to obtain a second codebook includes:

[0022] Using the first-channel data as an input to a first target decompression model to obtain second-channel data; the first target decompression model is a model corresponding to the first target compression model;

[0023] Determining the second codebook according to the second-channel data, the first parameter, and the second parameter.

[0024] Further, the sending first configuration information to the terminal according to the correlation between the second codebook and a third codebook includes:

[0025] Calculating the correlation between the second codebook and the third codebook;

[0026] When the correlation is greater than or equal to a preset threshold, sending the first configuration information for indicating a second target compression model to the terminal;

[0027] Among them, the second target compression model is a model trained using the channel data of the uplink channel and the channel data of the downlink channel.

[0028] Further, after sending the first configuration information to the terminal according to the correlation between the second codebook and the third codebook, it further includes:

[0029] Obtain a fourth codebook according to the measurement result of the reference signal of the second-time uplink channel; the second time is the time after the first time;

[0030] Decompose the fourth codebook to obtain third channel data;

[0031] Receive the fourth channel data of the fifth codebook of the downlink channel at the second time sent by the terminal;

[0032] Use the third channel data and the fourth channel data as the input of a second target decompression model to obtain fifth channel data; the second target decompression model is a model corresponding to the second target compression model, and the second target decompression model is a model trained using the channel data of the uplink channel and the channel data of the downlink channel;

[0033] Determine a sixth codebook of the downlink channel according to the fifth channel data.

[0034] Further, after sending the first configuration information to the terminal according to the correlation between the second codebook and the third codebook, it further includes:

[0035] Receive the third parameter and the fourth parameter of the fifth codebook sent by the terminal;

[0036] The determining the sixth codebook of the downlink channel according to the fifth channel data includes:

[0037] Determine the sixth codebook according to the fifth channel data, the third parameter, and the fourth parameter;

[0038] Among them, the third parameter is used to report a beam group; the fourth parameter includes a DFT vector for frequency-domain compression.

[0039] Further, the method further includes:

[0040] Collect first channel estimation data of the downlink channel;

[0041] Determine the sixth channel data of the downlink channel codebook according to the first channel estimation data;

[0042] Group the sixth channel data according to the number of oversampled DFT beams and the number of frequency basis vectors in the sixth channel data to obtain multiple groups of first target data;

[0043] Determine the first compression model and the first decompression model corresponding to each group of first target data;

[0044] Train the first compression model and the first decompression model corresponding to each group of the first target data with the first target data to obtain a first model database; the first model database is used to store the correspondence between the first compression model and the model configuration parameters and the correspondence between the first decompression model and the first compression model.

[0045] Further, the method further includes:

[0046] Collect second channel estimation data of the uplink channel;

[0047] Determine the seventh channel data of the uplink channel codebook according to the second channel estimation data;

[0048] Determine the eighth channel data, where the eighth channel data is a data pair composed of the sixth channel data and the seventh channel data;

[0049] Group the second target data corresponding to the number of oversampled DFT beams and the number of frequency basis vectors of the eighth channel data, and determine the second compression model and the second decompression model corresponding to each group of second target data;

[0050] Train the second compression model and the second decompression model corresponding to each group of the second target data with the grouped second target data to obtain a second model database; the second model database is used to store the correspondence between the second compression model and the model configuration parameters and the correspondence between the second decompression model and the second compression model.

[0051] In a second aspect, an embodiment of the present application provides a data processing method, which is applied to a terminal and includes:

[0052] Obtain the first channel data of the first codebook of the first-time downlink channel;

[0053] Send the first channel data to a network device, so that the network device performs decompression calculation on the first channel data to obtain a second codebook, and obtains a third codebook according to the measurement result of the reference signal of the first-time uplink channel;

[0054] Receive the first configuration information sent by the network device according to the correlation between the second codebook and the third codebook;

[0055] Among them, the first configuration information is the configuration information of a model for compressing channel data of a codebook for a downlink channel.

[0056] Further, obtaining first channel data of a first codebook of a downlink channel at a first time includes:

[0057] Receiving configuration information of a first target compression model sent by the network device, where the first target compression model is a model trained using channel data of a downlink channel;

[0058] Using the first target compression model to compress the channel data of the first codebook to obtain the first channel data.

[0059] Further, after obtaining the first channel data of the first codebook of the downlink channel at the first time, it further includes:

[0060] Sending a first parameter and a second parameter of the first codebook to the network device, so that the network device determines the second codebook according to second channel data, the first parameter, and the second parameter;

[0061] Among them, the first parameter is used to report a beam group; the second parameter includes a DFT vector for frequency-domain compression, the second channel data is obtained by the network device decompressing the first channel data through the first target decompression model, and the first target decompression model is a model corresponding to the first target compression model.

[0062] Further, the method further includes:

[0063] Obtaining a fifth codebook of a downlink channel at a second time;

[0064] Determining a second target compression model according to the first configuration information;

[0065] Using the second target compression model to compress the channel data of the fifth codebook to obtain fourth channel data of the fifth codebook;

[0066] Sending the fourth channel data to the network device, so that the network device obtains fifth channel data according to the second target decompression model and the fourth channel data; the second target decompression model is a model corresponding to the second target compression model, and the second target decompression model is a model trained using channel data of an uplink channel and channel data of a downlink channel.

[0067] Further, after sending the fourth channel data to the network device, it further includes

[0068] Send the third parameter and the fourth parameter of the fifth codebook to the network device, so that the network device determines a sixth codebook according to the fifth channel data, the third parameter, and the fourth parameter;

[0069] Among them, the third parameter is used to report beam groups; the fourth parameter includes a DFT vector for frequency domain compression.

[0070] In a third aspect, an embodiment of the present application provides a data processing device, including:

[0071] A first receiving module, configured to receive first channel data of a first codebook of a downlink channel at a first time of a terminal;

[0072] A calculation module, configured to perform decompression calculation on the first channel data to obtain a second codebook;

[0073] A determination module, configured to obtain a third codebook according to a measurement result of a reference signal of an uplink channel at the first time;

[0074] A first sending module, configured to send first configuration information to the terminal according to the correlation between the second codebook and the third codebook;

[0075] Among them, the first configuration information is configuration information of a model for compressing channel data of a codebook of a downlink channel.

[0076] In a fourth aspect, an embodiment of the present application provides a data processing device, including:

[0077] A first obtaining module, configured to obtain first channel data of a first codebook of a downlink channel at a first time;

[0078] A second sending module, configured to send the first channel data to a network device, so that the network device performs decompression calculation on the first channel data to obtain a second codebook, and obtains a third codebook according to a measurement result of a reference signal of an uplink channel at the first time;

[0079] A second receiving module, configured to receive first configuration information sent by the network device according to the correlation between the second codebook and the third codebook;

[0080] Among them, the first configuration information is configuration information of a model for compressing channel data of a codebook of a downlink channel.

[0081] In a fifth aspect, an embodiment of the present application provides a network device, including a transceiver and a processor, where

[0082] The transceiver is configured to receive first channel data of a first codebook of a downlink channel at a first time of a terminal;

[0083] The processor is configured to perform decompression calculation on the first channel data to obtain a second codebook;

[0084] According to the measurement result of the reference signal of the first-time uplink channel, obtain a third codebook;

[0085] The transceiver is further configured to send first configuration information to the terminal according to the correlation between the second codebook and the third codebook;

[0086] Wherein, the first configuration information is configuration information of a model for compressing channel data of a codebook of a downlink channel.

[0087] In a sixth aspect, an embodiment of the present application provides a terminal, including a transceiver, wherein,

[0088] The transceiver is configured to obtain first channel data of a first codebook of a first-time downlink channel;

[0089] Send the first channel data to a network device, so that the network device performs decompression calculation on the first channel data to obtain a second codebook, and obtains a third codebook according to the measurement result of the reference signal of the first-time uplink channel;

[0090] Receive the first configuration information sent by the network device according to the correlation between the second codebook and the third codebook;

[0091] Wherein, the first configuration information is configuration information of a model for compressing channel data of a codebook of a downlink channel.

[0092] In a seventh aspect, an embodiment of the present application provides a network device, including: a processor, a memory, and a program stored on the memory and executable on the processor, and when the program is executed by the processor, it implements the steps of the method described in the first aspect.

[0093] In an eighth aspect, an embodiment of the present application provides a terminal, including: a processor, a memory, and a program stored on the memory and executable on the processor, and when the program is executed by the processor, it implements the steps of the method described in the second aspect.

[0094] In a ninth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a program is stored, and when the program is executed by a processor, it implements the steps of the method described above.

[0095] Compared with the prior art, the data processing method, network device, terminal, and storage medium provided by the embodiments of the present application determine the correlation between the uplink channel and the downlink channel by calculating the correlation between the second codebook and the third codebook, so as to determine the configuration information of the compression model indicated by the first configuration information sent to the terminal; and when the correlation is relatively large, supplement the features of the downlink channel data with the uplink channel data, which can improve the feedback accuracy of the codebook while reducing the amount of channel feedback. BRIEF DESCRIPTION OF THE DRAWINGS

[0096] By reading the following detailed description of the preferred embodiments, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of illustrating the preferred embodiments and are not considered to be a limitation of the present application. Moreover, throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0097] Figure 1 is a schematic diagram of an application scenario of an embodiment of the present application;

[0098] Figure 2 is a schematic diagram of the general decomposition form of the precoding matrix of an embodiment of the present application;

[0099] Figure 3 is a schematic diagram of the model structure of an embodiment of the present application;

[0100] Figure 4 is a flowchart of the data processing method applied to a network device according to an embodiment of the present application;

[0101] Figure 5 is a schematic diagram of the model structure of another embodiment of the present application;

[0102] Figure 6 is a flowchart of the data processing method applied to a terminal according to an embodiment of the present application;

[0103] Figure 7 is a schematic diagram of the interaction process of the data processing method according to an embodiment of the present application;

[0104] Figure 8 is a schematic diagram of the structure of a data processing device according to an embodiment of the present application;

[0105] Figure 9 is a schematic diagram of the structure of a data processing device according to another embodiment of the present application;

[0106] Figure 10 is a schematic diagram of the structure of a network device according to an embodiment of the present application;

[0107] Figure 11 is a schematic diagram of the structure of a terminal according to an embodiment of the present application;

[0108] Figure 12 Structural schematic diagram of a network device according to another embodiment of the present application;

[0109] Figure 13 Structural schematic diagram of a terminal according to another embodiment of the present application. Detailed implementation manners

[0110] The exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present application can be more thoroughly understood and the scope of the present application can be fully conveyed to those skilled in the art.

[0111] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects and do not necessarily have to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present application described herein can be implemented in an order different from those illustrated or described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices. "And / or" in the specification and claims means at least one of the connected objects.

[0112] The techniques described herein are not limited to NR systems and Long Time Evolution (LTE) / LTE-Advanced (LTE-A) systems, and can also be used in various wireless communication systems, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access (OFDMA), Single-carrier Frequency-Division Multiple Access (SC-FDMA), and other systems. The terms "system" and "network" are often used interchangeably. CDMA systems can implement radio technologies such as CDMA2000, Universal Terrestrial Radio Access (UTRA), etc. UTRA includes Wideband Code Division Multiple Access (WCDMA) and other CDMA variants. TDMA systems can implement radio technologies such as Global System for Mobile Communication (GSM). OFDMA systems can implement radio technologies such as Ultra Mobile Broadband (UMB), Evolution-UTRA (E-UTRA), IEEE 802.21 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802.20, Flash-OFDM, etc. UTRA and E-UTRA are part of the Universal Mobile Telecommunications System (UMTS). LTE and more advanced LTE (such as LTE-A) are new UMTS versions using E-UTRA. UTRA, E-UTRA, UMTS, LTE, LTE-A, and GSM are described in literature from an organization called the "3rd Generation Partnership Project" (3GPP). CDMA2000 and UMB are described in literature from an organization called the "3rd Generation Partnership Project 2" (3GPP2).The techniques described herein can be used in the systems and radio technologies mentioned above, as well as in other systems and radio technologies. However, the following description describes the NR system for example purposes and uses NR terminology in most of the following description, although these techniques can also be applied to applications other than NR system applications.

[0113] The following description provides examples and is not intended to limit the scope, applicability, or configuration set forth in the claims. Changes may be made to the functions and arrangements of the elements discussed without departing from the spirit and scope of the disclosure. Various examples may appropriately omit, substitute, or add various procedures or components. For example, the methods described may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0114] Please refer to Figure 1 , Figure 1 FIG. shows a block diagram of a wireless communication system to which embodiments of the present application can be applied. The wireless communication system includes a terminal 11 and a network device 12. Among them, the terminal 11 can also be referred to as a user terminal or user equipment (UE, User Equipment). The terminal 11 can be a mobile phone, a tablet personal computer, a laptop computer, a personal digital assistant (PDA), a mobile Internet device (MID), a wearable device, or a vehicle-mounted device, etc. on the terminal side. It should be noted that the specific type of the terminal 11 is not limited in the embodiments of the present application. The network device 12 can be a base station and / or a core network element. Among them, the above base station can be a base station of 5G and later versions (for example: gNB, 5G NR NB, etc.), or a base station in other communication systems (for example: eNB, WLAN access point, or other access points, etc.). Among them, the base station can be referred to as Node B, evolved Node B, access point, base transceiver station (BTS), radio base station, radio transceiver, basic service set (BSS), extended service set (ESS), B node, evolved B node (eNB), home B node, home evolved B node, WLAN access point, WiFi node, or some other suitable term in the art. As long as the same technical effect is achieved, the base station is not limited to a specific technical term. It should be noted that in the embodiments of the present application, only the base station in the NR system is taken as an example, but the specific type of the base station is not limited.

[0115] The base station can communicate with the terminal 11 under the control of a base station controller. In various examples, the base station controller can be a part of the core network or some base stations. Some base stations can communicate control information or user data with the core network via a backhaul. In some examples, some of these base stations can communicate with each other directly or indirectly via a backhaul link, which can be a wired or wireless communication link. The wireless communication system can support operations on multiple carriers (waveform signals of different frequencies). The multi-carrier transmitter can simultaneously transmit modulated signals on these multiple carriers. For example, each communication link can be a multi-carrier signal modulated according to various radio technologies. Each modulated signal can be transmitted on a different carrier and can carry control information (such as reference signals, control channels, etc.), overhead information, data, etc.

[0116] The base station can communicate wirelessly with the terminal 11 via one or more access point antennas. Each base station can provide communication coverage for its respective coverage area. The coverage area of an access point can be divided into sectors that only constitute a part of the coverage area. The wireless communication system can include different types of base stations (such as macro base stations, micro base stations, or pico base stations). The base station can also utilize different radio technologies, such as cellular or WLAN radio access technologies. The base station can be associated with the same or different access network or operator deployments. The coverage areas of different base stations (including the coverage areas of the same or different types of base stations, the coverage areas using the same or different radio technologies, or the coverage areas belonging to the same or different access networks) can overlap.

[0117] The communication link in the wireless communication system can include an uplink for carrying uplink (UL) transmissions (e.g., from the terminal 11 to the network device 12), or a downlink for carrying downlink (DL) transmissions (e.g., from the network device 12 to the terminal 11). The UL transmission can also be referred to as a reverse link transmission, while the DL transmission can also be referred to as a forward link transmission. The downlink transmission can be performed using an authorized frequency band, an unlicensed frequency band, or both. Similarly, the uplink transmission can be performed using an authorized frequency band, an unlicensed frequency band, or both.

[0118] In an embodiment of the present invention, the number of transmit antennas on the base station side is N transmit and N receive, the number of receive antennas on the user side is N1 transmit and N1 receive, the Rank value RI of the channel matrix H (whose dimension is N1×N) is calculated, and the number of subbands is N sb , and the number of precoding matrices is N3, and N3 = N sb×R, where R is configured by the higher-layer parameter numberOf PMI Subbands PerCQI Subband-r16, and the value range is {1, 2}, representing the number of precoding matrices configurable for each subband. For the channel matrix corresponding to the frequency f of the Physical Resource Blocks (PRBs) selected in the subband perform eigenvalue decomposition (the superscript H represents conjugate transpose), record its first RI eigenvalues and sort them in descending order, and the corresponding eigenvectors are denoted as V f1 , V f2 , …, V fRI , and concatenate the eigenvectors corresponding to the l-th layer (stream) of all subbands to obtain which is denoted as W l . The codebook W (RI) can be expressed in the following form:

[0119]

[0120] According to the etypeII codebook, W 1 can be decomposed as follows:

[0121]

[0122] where W1 is used to report the beam group, and the form of W1 is [b0, L, b L-1 corresponding to L oversampled DFT beams, and the matrix is composed of DFT vectors for frequency-domain compression.

[0123] Specifically, the general decomposition form of the R16 eType II precoding matrix is as Figure 2 shown, where N is the number of CSI-RS ports and M is the number of frequency basis vectors.

[0124] It is necessary to quantize the coefficient matrix (such as by mapping to a vector quantization set), and then transmit it to the base station.

[0125] Similarly, for the uplink channel, a similar decomposition is performed, and the Rank value R u of the uplink channel matrix H u (whose dimension is N1×N) is calculated. The total number of precoding matrices is For the PRB part f selected in the subband u corresponding channel matrix perform eigenvalue decomposition, record its first R u eigenvalues and sort them in descending order, and the corresponding eigenvectors are respectively denoted as Concatenate the eigenvectors of the l-th uConcatenate the eigenvectors corresponding to the layer (flow) to obtain which is denoted as

[0126] For different RIs, is denoted as Let be denoted as W f ; Let be decomposed according to the eTypeII codebook of and is denoted as

[0127] When the uplink and downlink channel correlations are high, the terminal can collect and calculate the downlink channel data and the uplink channel data at the corresponding time Train the model (sequence-to-sequence auto-encoder), and synchronize the trained compression model to the terminal and the decompression model to the base station. On the terminal side, calculate by measuring the downlink channel and according to the etypeII codebook and complete channel compression through the compression model and feedback it to the base station; on the base station side, measure the uplink channel at the same time, and use the uplink channel data and the fed back by the terminal as the common input to perform decompression through the decompression model to obtain and according to W1(t), W f (t) to restore the preprocessing matrix of the downlink channel. The model architecture diagram based on the uplink and downlink channel correlations is as shown in Figure 3 shown.

[0128] Please refer to Figure 4 , A data processing method provided by an embodiment of the present application, which is applied to a network device, includes the following steps:

[0129] Step 401, receiving the first channel data of the first codebook of the downlink channel at the first time of the terminal;

[0130] Step 402, performing decompression calculation on the first channel data to obtain a second codebook;

[0131] Step 403, obtaining a third codebook according to the measurement result of the reference signal of the uplink channel at the first time;

[0132] Step 404, sending first configuration information to the terminal according to the correlation between the second codebook and the third codebook;

[0133] Wherein, the first configuration information is the configuration information of the model for compressing the channel data of the codebook of the downlink channel.

[0134] Optionally, the first time is a first time point or a first time period.

[0135] In an embodiment of the present invention, the first time is a first time point.

[0136] It should be noted that the terminal is a terminal that has accessed the network device and has entered the Radio Resource Control (RRC)-CONNECTED state.

[0137] In an embodiment of the present invention, the terminal measures the downlink channel reference signal CSI-RS, and calculates the first codebook according to the number L of oversampled DFT beams, the number P of DFT basis vectors v and R, and calculates and selects the first target compression model for the codebook data of the first codebook according to L, P v , R, and the number of downlink subbands, and compresses the codebook data of the first codebook to obtain the first channel data and sends the first channel data to the network device; at the same time, sends the first parameter and the second parameter of the first codebook to the network device according to the type II codebook feedback mode.

[0138] In an embodiment of the present invention, the network device measures the uplink reference signal SRS at the first time, and calculates the third codebook of the uplink channel according to the uplink reference signal SRS

[0139] In an embodiment of the present invention, a radio access network AI model training system (deployed on the CU and / or DU of the base station, or on a logical entity across the CU) collects downlink channel estimation data and uplink channel estimation data, records L, P v , R, and the number of uplink and downlink subbands, calculates the uplink Rank value Ru, and calculates the unquantized and the unquantized obtained by decomposing the type II codebook of the uplink channel at the corresponding moment to form a data pair (hereinafter all refer to the unquantized), groups the data according to and the relevant dimensions of its type II decomposition, and designs models with different dimensions for different groups of data dimensions, etc. (including the model trained only with Figure 5 as shown in and the model trained with Figure 3 ​​The model shown) is trained offline, and the trained compressed model, model number, and model number table related to model features are synchronized to the terminal. The decompressed model, number, and model number table related to model features are synchronized to the network device (base station); the network device sets a preset threshold δ according to the uplink and downlink channel correlation.

[0140] The data processing method provided by the embodiment of the present application determines the correlation between the uplink channel and the downlink channel by calculating the correlation between the second codebook and the third codebook, so as to determine the configuration information of the compressed model indicated by the first configuration information sent to the terminal; and when the correlation is relatively large, the characteristics of the downlink channel data are supplemented by the uplink channel data, which can improve the feedback accuracy of the codebook while reducing the amount of channel feedback.

[0141] Optionally, receiving the first channel data of the first codebook of the downlink channel of the receiving terminal for the first time includes:

[0142] Determine the first target compression model, where the first target compression model is a model trained using the channel data of the downlink channel;

[0143] Send the configuration information of the first target compression model to the terminal; the first target compression model is used to compress the channel data of the first codebook to obtain the first channel data;

[0144] Receive the first channel data of the first codebook.

[0145] Optionally, the channel data of the downlink channel is the unquantified channel data calculated according to a preset codebook format of the downlink channel codebook.

[0146] In an embodiment of the present invention, the channel data of the downlink channel is unquantified calculated according to the etypeII codebook format

[0147] Optionally, the determining the first target compression model includes:

[0148] According to L, P v , R, and the number of downlink subbands to determine the first target compression model and the configuration information of the first target compression model.

[0149] In the embodiment of the present invention, the network device (such as a base station) sends a Channel State Information-Reference Signal (CSI-RS) according to the configuration. In order to improve the accuracy of the uplink and downlink channel correlation calculation, from the optional configuration data values of L, the number of oversampled DFT beams P v and R, select the larger value of L×Pv and a smaller value of R, thereby improving the accuracy of downlink channel feedback, and configuring the time-frequency resources required for the terminal to feedback CSI compression feedback information, and sending the configuration information of the compression feedback model (the first target compression model) (including L, P v , R, and the time-frequency resources) to the terminal through the downlink channel (such as PDCCH / PDSCH);

[0150] The terminal measures the downlink channel reference signal CSI-RS, and calculates its type II codebook according to L, P v , R, and compresses the channel data of the first codebook through the first target compression model to obtain the first channel data and sends the first channel data to the network device. The data processing method provided by the embodiment of the present application, the network device determines the configuration information of the first target compression model for compressing the channel data of the first codebook, so that the terminal compresses the channel data of the first codebook according to the configuration information of the first target compression model to obtain the first channel data, and sends the first channel data to the network device, reducing the overhead of transmitting the first codebook.

[0151] Optionally, receiving the first channel data of the first codebook of the downlink channel at the first time of the receiving terminal further includes:

[0152] Receiving the first parameter and the second parameter of the first codebook;

[0153] wherein, the first parameter is used to report the beam group; the second parameter includes the DFT vector for frequency domain compression.

[0154] wherein, the first parameter is W1(t), and the second parameter is W

[0155] (t). f (t).

[0156] The data processing method provided by the embodiment of the present application, the network device can determine the second codebook through the received first channel data, the first parameter, and the second parameter, reducing the codebook overhead while ensuring the codebook feedback accuracy.

[0157] Optionally, decompressing and calculating the first channel data to obtain a second codebook includes:

[0158] Taking the first channel data as the input of the first target decompression model to obtain the second channel data; the first target decompression model is the model corresponding to the first target compression model;

[0159] Determine a second codebook according to the second channel data, the first parameter, and the second parameter. Optionally, the determining the second codebook according to the second channel data, the first parameter, and the second parameter may be understood as: restoring the codebook data of the downlink channel at the first time according to the second channel data, the first parameter, and the second parameter.

[0160] Optionally, the sending the first configuration information to the terminal according to the correlation between the second codebook and the third codebook includes:

[0161] Calculate the correlation between the third codebook and the second codebook;

[0162] When the correlation is greater than or equal to a preset threshold, send the first configuration information for indicating the second target compression model to the terminal;

[0163] Wherein, the decompression model corresponding to the second target compression model is a model trained by using the channel data of the uplink channel and the channel data of the downlink channel.

[0164] Optionally, the channel data of the uplink channel is the unquantized channel data calculated according to a preset codebook format by the codebook of the uplink channel;

[0165] The channel data of the downlink channel is the unquantized channel data calculated according to a preset codebook format by the codebook of the downlink channel.

[0166] In an embodiment of the present invention, the channel data of the uplink channel is the unquantized calculated according to the etypeII codebook format In an embodiment of the present invention, the channel data of the downlink channel is the unquantized calculated according to the etypeII codebook format

[0167] In an embodiment of the present invention, the correlation between the third codebook and the second codebook is calculated by the following method:

[0168] At time t, take N min = min(RI, R u ), and take the first R min rank-corresponding W l (t) and W lu (t)(l, l u = 1, L, R min ) for the uplink and downlink channels respectively, and sequentially select N l vectors in W and 3,min respectively, and sequentially splice the above N 3,min vectors into a vector Vl (t) and calculate V l (t) and V lu The cosine similarity between (t) is as follows:

[0169]

[0170] where, || represents the vector inner product, and |||| represents the 2-norm;

[0171] The channel eigenvector similarity threshold corresponding to the R at time t min for the calculation of the R ranks:

[0172]

[0173] where, and λ l (t) are respectively the l-th eigenvalue corresponding to the uplink and downlink channel when calculating the Rank value.

[0174] In the embodiments of the present invention, the base station root L, P v , R and the number of downlink subbands are selected to only train the corresponding decompression model number (i.e., the first target decompression model corresponding to the first target compression model), receive the first channel data fed back by the receiving terminal the first parameter W1(t) and the second parameter W f (t); decompress the first channel data through the first target compression model to obtain the second channel data and combine the first parameter and the second parameter to obtain the second codebook W (RI) (t);

[0175] Calculate the third codebook The correlation δ with the second codebook W (RI) (t) t ;

[0176] And compare the correlation δ between the third codebook and the second codebook t with the preset threshold δ.

[0177] In the embodiments of the present application, the data processing method provided enables the network device to determine the first configuration information according to the correlation between the third codebook and the second codebook, and send the first configuration information to the terminal, so that the terminal can determine the target compression model according to the first configuration information.

[0178] In the embodiments of the present invention, if the correlation δ between the third codebook and the second codebook tIf it is greater than or equal to a preset threshold δ, the network device calculates the uplink channel Ru according to the SRS, and adjusts L, P according to information such as historical information, complexity, and performance. v and R, and according to Ru, L, P v , R, and N3 to select the corresponding model (the second target compression model) trained for numbering and configuring the time-frequency resources required for the terminal to feedback CSI compression feedback information, and sending the compression feedback model configuration information (including the model number, L, P v , R, and feedback resources) to the terminal through the downlink channel (such as PDCCH / PDSCH).

[0179] Optionally, if the correlation δ between the third codebook and the second codebook t is less than the preset threshold δ, then send the first configuration information for indicating the first target compression model to the terminal.

[0180] In the embodiment of the present invention, if the correlation δ between the third codebook and the second codebook t is less than the preset threshold δ, then the network device selects only the corresponding model (the first target compression model) trained for numbering, reconfiguring the compression feedback model configuration information and sending it to the terminal, and the terminal modifies the model according to the compression feedback model configuration information and completes the compression.

[0181] In the data processing method provided by the embodiment of the present application, the network device determines the content indicated by the first configuration information sent to the terminal according to the correlation between the third codebook and the second codebook, and sends different configuration information indicating different models to the terminal according to the size relationship between the correlation and the preset threshold, and can determine different compression models according to the correlation between the third codebook and the second codebook, which can ensure the codebook feedback accuracy while reducing the codebook overhead.

[0182] Optionally, after sending the first configuration information to the terminal according to the correlation between the second codebook and the third codebook, it further includes:

[0183] Obtain a fourth codebook according to the measurement result of the reference signal of the second-time uplink channel; the second time is the time after the first time;

[0184] Decompose the fourth codebook to obtain third-channel data;

[0185] Receive the fourth-channel data of the fifth codebook of the second-time downlink channel sent by the terminal;

[0186] Use the third channel data and the fourth channel data as the input of a second target decompression model to obtain fifth channel data; the second target decompression model is a model corresponding to the second target compression model, and the second target decompression model is a model trained using the channel information of the uplink channel and the limited information of the downlink channel;

[0187] Determine a sixth codebook for the downlink channel according to the fifth channel data.

[0188] Optionally, the channel data of the uplink channel is unquantized channel data calculated from the codebook of the uplink channel according to a preset codebook format;

[0189] The channel data of the downlink channel is unquantized channel data calculated from the codebook of the downlink channel according to a preset codebook format.

[0190] In an embodiment of the present invention, the channel data of the uplink channel is unquantized calculated according to the etypeII codebook format The channel data of the downlink channel is unquantized calculated according to the etypeII codebook format

[0191] In an embodiment of the present invention, the terminal receives and measures the downlink channel reference signal CSI-RS at the next moment (the second time after the first time) and calculates it according to the etypeII codebook to obtain The terminal selects a channel compression model according to the model number in the received channel compression feedback model configuration information and completes compression, and the compressed channel information is recorded as the fourth channel data and feeds back the fourth channel data according to the resource configuration to the network device.

[0192] In an embodiment of the present invention, the network device measures the uplink reference signal SRS at time t + 1 and calculates the uplink channel data according to the etypeII codebook (the third channel data), receives the fourth channel data fed back by the terminal Use the third channel data and the fourth new guide data to obtain the fifth channel data through the decompression model corresponding to the model number Then determine the sixth codebook according to the fifth channel data.

[0193] In the data processing method provided by the embodiment of the present application, the network device decomposes the fourth codebook obtained by measuring the reference signal of the uplink channel at the second time to obtain the third channel data; determines the fifth channel matrix according to the fourth channel data of the fifth codebook of the downlink channel at the second time sent by the terminal, and thereby determines the sixth codebook.

[0194] Optionally, after sending the first configuration information to the terminal according to the correlation between the second codebook and the third codebook, it further includes

[0195] receiving the third parameter and the fourth parameter of the fifth codebook sent by the terminal;

[0196] The determining the sixth codebook of the downlink channel according to the fifth channel data includes:

[0197] determining the sixth codebook according to the fifth channel data, the third parameter, and the fourth parameter;

[0198] wherein, the third parameter is used to report the beam group; the fourth parameter includes a DFT vector for frequency domain compression.

[0199] Optionally, the determining the sixth codebook according to the fifth channel data, the third parameter, and the fourth parameter can be understood as restoring the codebook data of the downlink channel at the second time according to the fifth channel data, the third parameter, and the fourth parameter.

[0200] In the embodiment of the present invention, when the terminal feeds back the fourth channel data according to the resource configuration to the network device, it feeds back the third parameter W1(t + 1) and the fourth parameter W f (t + 1) in accordance with the etype II codebook feedback mode;

[0201] The network device measures the uplink reference signal SRS at time t + 1, calculates the uplink channel data (the third channel matrix), receives the third parameter W1(t + 1) fed back by the terminal, and the fourth parameter W f (t + 1), and obtains the fifth channel data through the decompression model corresponding to the model number calculates the sixth codebook W and W f (t + 1) T according to W1(t + 1), (RI) (t + 1).

[0202] Optionally, the method further includes:

[0203] Collect the first channel estimation data of the downlink channel;

[0204] Determine the sixth channel data of the downlink channel codebook according to the first channel estimation data;

[0205] Group the sixth channel data according to the number of oversampled DFT beams and the number of frequency basis vectors in the sixth channel data to obtain multiple groups of first target data;

[0206] Determine the first compression model and the first decompression model corresponding to each group of the first target data;

[0207] Train the first compression model and the first decompression model corresponding to each group of the first target data through the first target data to obtain a first model database, where the first model database is used to store the corresponding relationship between the first compression model and the model configuration parameters and the corresponding relationship between the first decompression model and the first compression model.

[0208] Optionally, after determining the first model database, the network device sends the first model database to the terminal.

[0209] In the embodiments of the present invention, there are two compression models in the first model database;

[0210] Among them, the first compression model is the model trained by :

[0211] First, calculate the Rank value of the uplink channel samples according to the collected uplink and downlink channel samples, L, P v and R, where P v is configured by higher-layer signaling, M = [P v × N3 / R], and it is assumed that a table as shown in Table 1 is formed according to the differences in the sample uplink Rank, L, and M.

[0212] Table 1 Model number table corresponding to uplink Rank, L, and M

[0213]

[0214] The input and output of the above 10 models are designed as follows:

[0215] The model architecture is in the form of sequence-to-sequence auto-encoder, as Figure 3 shown. The number of input elements of the compression model is 2 × L × M, and the number of output elements is O1; the number of input elements of the decompression model is O1 + 2 × L × M × R u, the number of output elements is 2×L×M; among them, O1 is adaptively adjusted according to the training accuracy during the training process to select the optimal number of output elements. The higher the correlation threshold δ, the fewer the optimal number of output elements O1, and the less the feedback amount from the terminal to the base station.

[0216] During the training process, it is necessary to the elements in pass through the compression / decompression model in sequence to obtain The compression / decompression requires RI times in total, and the obtained are concatenated to obtain That is

[0217] Optionally, the method further includes:

[0218] Collect the second channel estimation data of the uplink channel;

[0219] Determine the seventh channel data of the uplink channel codebook according to the second channel estimation data;

[0220] Determine the eighth channel data, where the eighth channel data is a data pair composed of the sixth channel data and the seventh channel data;

[0221] According to the number of oversampled DFT beams and the number of frequency basis vectors of the eighth channel data, group the eighth channel data to obtain the second target data;

[0222] Determine the second compression model and the second decompression model corresponding to each group of second target data;

[0223] Train the second compression model and the second decompression model corresponding to each group of the second target data through the second target data to obtain a second model database; the second model database is used to store the correspondence between the second compression model and the model configuration parameters and the correspondence between the second decompression model and the second compression model.

[0224] Optionally, the sixth channel data is the unquantified channel data calculated by the uplink channel codebook according to a preset codebook format;

[0225] The seventh channel data is the unquantified channel data calculated by the downlink channel codebook according to a preset codebook format.

[0226] In an embodiment of the present invention, the sixth channel data is the unquantified The seventh channel data is the unquantified The eighth channel data is

[0227] In the embodiments of the present invention, two compression models are included in the first model database;

[0228] Among them, the second compression model is the model trained with :

[0229] First, according to the collected downlink channel samples, the optional L and P of the base station v As shown in Table 2, R = {1, 2}.

[0230] Table 2 Model number table corresponding to L and P v

[0231] Number L <![CDATA[P v > 1 2 1 / 4 2 4 1 / 4 3 4 1 / 2 4 6 1 / 4 5 2 1 / 8 6 4 1 / 8

[0232] M = [P v × N3 / R]. Assuming that according to the difference between L × M, the data is grouped and the model is designed, and the input of the model is 2 × L × M to form the table shown in Table 3:

[0233] Table 3 Model number table corresponding to L × M

[0234] Model Number L×M 11 2 12 4 13 8 14 12 15 16 16 24 17 32

[0235] During the training / inference process, it is necessary to The elements in Pass through the compression / decompression model in sequence to obtain The compression / decompression requires RI times in total, and the obtained Are spliced together to obtain That is

[0236] As Figure 6 Shown, the embodiments of the present application provide a data processing method, which is applied to a terminal and includes the following steps:

[0237] Step 601, obtaining first channel data of a first codebook of a downlink channel at a first time;

[0238] Step 602, sending the first channel data to a network device so that the network device performs decompression calculation on the first channel data to obtain a second codebook, and obtains a third codebook according to a measurement result of a reference signal of the first-time uplink channel;

[0239] Step 603, receiving first configuration information sent by the network device according to the correlation between the second codebook and the third codebook;

[0240] Among them, the first configuration information is configuration information of a model for compressing channel data of a codebook of a downlink channel.

[0241] The data processing method provided by the embodiment of the present application determines the correlation between the uplink channel and the downlink channel by calculating the correlation between the second codebook and the third codebook, so as to determine the configuration information of the compression model indicated by the first configuration information sent to the terminal; and when the correlation is relatively large, the characteristics of the downlink channel data are supplemented by the uplink channel data, which can improve the feedback accuracy of the codebook while reducing the amount of channel feedback.

[0242] Optionally, obtaining the first channel data of the first codebook of the downlink channel at the first time includes:

[0243] Receiving the configuration information of the first target compression model sent by the network device, where the first target compression model is a model trained using the channel data of the downlink channel;

[0244] Compressing the channel data of the first codebook using the first target compression model to obtain the first channel data.

[0245] The data processing method provided by the embodiment of the present application reduces the transmission overhead of the first codebook by sending the configuration information of the first target compression model for compressing the channel data of the first codebook by the network device, so that the terminal compresses the channel data of the first codebook according to the configuration information of the first target compression model to obtain the first channel data and sends the first channel data to the network device.

[0246] Optionally, after obtaining the first channel data of the first codebook of the downlink channel at the first time, it further includes:

[0247] Sending the first parameter and the second parameter of the first codebook to the network device, so that the network device determines the second codebook according to the second channel data, the first parameter, and the second parameter;

[0248] Wherein, the first parameter is used to report the beam group; the second parameter includes a DFT vector for frequency domain compression, the second channel data is obtained by the network device decompressing the first channel data using the first target decompression model, and the first target decompression model is the model corresponding to the first target compression model.

[0249] The data processing method provided by the embodiment of the present application enables the network device to determine the second codebook through the received first channel data, the first parameter, and the second parameter, reducing the codebook overhead while ensuring the codebook feedback accuracy.

[0250] Optionally, the method further includes:

[0251] Obtaining a fifth codebook of the downlink channel at the second time;

[0252] Determine a second target compression model according to the first configuration information;

[0253] Use the second target compression model to compress the channel data of the fifth codebook to obtain the fourth channel data of the fifth codebook;

[0254] Send the fourth channel data to the network device, so that the network device can obtain the fifth channel data according to the second target decompression model and the fourth channel data; the second target decompression model is a model corresponding to the second target compression model, and the second target decompression model is a model trained using the channel data of the uplink channel and the channel data of the downlink channel.

[0255] In the data processing method provided by the embodiments of the present application, the terminal compresses the fifth codebook of the downlink channel at the second time obtained according to the second target compression model determined by the first configuration information to obtain the fourth channel data; by sending the compressed channel data to the network device, the transmission overhead of the codebook can be saved.

[0256] Optionally, after sending the fourth channel data to the network device, it further includes

[0257] Send the third parameter and the fourth parameter of the fifth codebook to the network device, so that the network device can determine the sixth codebook according to the fifth channel data, the third parameter, and the fourth parameter;

[0258] Wherein, the third parameter is used to report the beam group; the fourth parameter includes a DFT vector for frequency domain compression.

[0259] In the data processing method provided by the embodiments of the present application, the terminal sends the third parameter and the fourth parameter of the fifth codebook to the network device, so that the network device can determine the sixth codebook according to the third parameter and the fourth parameter, and in combination with the fourth channel data sent by the terminal, which can improve the feedback accuracy of the codebook while reducing the amount of channel feedback.

[0260] The above introduces various methods of the embodiments of the present application. An apparatus for implementing the above methods will be further provided below.

[0261] Such as Figure 7 , the data processing method of the embodiments of the present invention:

[0262] 1. The radio access network AI model training system (deployed on the CU and / or DU of the base station, or a logical entity across the CU) collects downlink channel estimation data and uplink channel estimation data, and records L, P v, R, and the number of uplink and downlink subbands, calculate the uplink Rank value Ru, and calculate the unquantized and the unquantized obtained by decomposing the uplink channel etype II codebook at the corresponding time to form a data pair (hereinafter all refer to the unquantized). According to and the relevant dimensions of its etypeII decomposition, group the data. For different groups of data due to differences in dimensions, etc., design models with different dimensions (including models trained only with such as the model shown in Figure 5 and models trained with such as the model shown in Figure 3 ) and perform offline training, and synchronize the trained compression model, model number, and model number table related to model features to the terminal, and synchronize the decompression model, number, and model number table related to model features to the network device (base station); the base station sets a preset threshold δ according to the uplink and downlink channel correlation;

[0263] 2. The terminal has accessed the network and enters the RRC - CONNECTED state; send SRS to the base station according to the configuration;

[0264] 3. The base station sends CSI - RS to the terminal according to the configuration. In order to improve the accuracy of calculating the uplink and downlink channel correlation, from L, the number of oversampled DFT beams P v and the optional configuration data values of R, select the larger value of L×P v and the smaller value of R, so as to improve the accuracy of downlink channel feedback, and configure the time - frequency resources required for the terminal to feedback CSI compressed feedback information, and send the configuration information of the compression feedback model (the first target compression model) (including L, P v , R, and time - frequency resources) to the terminal through the downlink channel (such as PDCCH / PDSCH);

[0265] 4. The terminal measures the downlink channel reference signal CSI - RS and calculates its etypeII codebook according to L, P v , R, calculates and selects the compression model number trained only with v , R and the number of downlink subbands, completes compression, and records the compressed channel information as and feedbacks to the base station, and at the same time feedbacks W1(t) and W (t) according to the etype II codebook feedback mode; f (t);

[0266] 5. The base station according to L, p v, R and the number of downlink subbands are selected only using the decompression model number corresponding to training, receive the W1(t), and W f (t) related information, and obtain through the decompression model According to W f (t), W f (t) to calculate W (RI) (t); Measure the uplink reference signal SRS at the same time, and calculate the uplink channel correlation with W (RI) (t) as δ t . If δ t ≥δ, then calculate the uplink channel Ru according to SRS, and adjust L, P v and R according to historical information, complexity, performance and other information, and select according to Ru, L, P v , R and N3 to use the corresponding model number (the second target compression model) trained and configure the time-frequency resources required for the terminal to feedback CSI compression feedback information, and send the compression feedback model configuration information (including the model number, L, P v , R and feedback resources) to the terminal through the downlink channel (such as PDCCH / PDSCH), go to 6; otherwise go to 9;

[0267] 6. The terminal receives and measures the downlink channel reference signal CSI-RS at the next moment and calculates according to the etypeII codebook to obtain The terminal selects the channel compression model according to the model number in the received channel compression feedback model configuration information and completes compression, and the compressed channel information is recorded as and feedback according to the resource configuration to the base station, and at the same time feedback W1(t + 1) and W f (t + 1) according to the etype II codebook feedback mode;

[0268] 7. The base station measures the uplink reference signal SRS at t + 1, and calculates the uplink channel data according to the etypeII codebook (the third channel matrix), receive the third parameter W1(t + 1), and the fourth parameter W f (t + 1), and obtain the fifth channel data through the decompression model corresponding to the model number obtain through the second target decompression model according to W1(t + 1), and W f (t + 1) TCalculate the sixth codebook W (RI) (t + 1);

[0269] 8. Subsequently, the terminal continues to listen to CSI-RS, and the base station continues to listen to SRS and analyze the feedback codebook, and adjusts L and P according to the situation of the feedback codebook (mainly considering complexity and performance). v , configure the terminal through high-layer signaling (such as RRC), adjust the compressed feedback model configuration information according to the model number table related to the model characteristics, and send it to the terminal. The terminal adjusts the calculation of the type II codebook and model selection according to the base station configuration to complete the feedback of the downlink channel. Overall, refer to steps 6 to 7; when the uplink Ru changes, the base station adjusts the compressed feedback model configuration information according to the model number table related to the model characteristics and sends it to the terminal. The terminal adjusts the compression model according to the base station configuration to complete the feedback of the downlink channel. Overall, refer to steps 6 to 7; the base station periodically calculates the correlation between the uplink channel and W (RI) (t). When the correlation is less than or equal to the threshold δ, then only select Train the corresponding compressed model number, reconfigure the compressed feedback model configuration information and send it to the terminal. The terminal modifies the model according to the compressed feedback model configuration information and completes the compression. Overall, refer to steps 3 to 5;

[0270] 9. The terminal listens to CSI-RS, and the base station analyzes the feedback codebook and adjusts L and P according to information such as historical information, complexity, and performance. v , configure the terminal through high-layer signaling (such as RRC), adjust the compressed feedback model configuration information according to the model number table related to the model characteristics, and send it to the terminal. The terminal adjusts the calculation of the type II codebook and model selection according to the base station configuration to complete the compressed feedback of the downlink channel.

[0271] As Figure 8 shown, an embodiment of the present application provides a data processing device 800, including:

[0272] A first receiving module 801, configured to receive first channel data of a first codebook of a downlink channel of a terminal at a first time;

[0273] A calculation module 802, configured to perform decompression calculation on the first channel data to obtain a second codebook;

[0274] A determination module 803, configured to obtain a third codebook according to a measurement result of a reference signal of an uplink channel at the first time;

[0275] A first sending module 804, configured to send first configuration information to the terminal according to the correlation between the second codebook and the third codebook;

[0276] Among them, the first configuration information is the configuration information of a model for compressing channel data of a codebook for a downlink channel.

[0277] The data processing device provided by the embodiment of the present application determines the correlation between the uplink channel and the downlink channel by calculating the correlation between the second codebook and the third codebook, so as to determine the configuration information of the compression model indicated by the first configuration information sent to the terminal; and when the correlation is relatively large, the characteristics of the downlink channel data are supplemented by the uplink channel data, which can improve the feedback accuracy of the codebook while reducing the amount of channel feedback.

[0278] It should be noted that the device in this embodiment is the device corresponding to the method applied to the network device above. The implementation manners in the above embodiments are all applicable to the embodiments of this device and can also achieve the same technical effects. The device provided by the embodiment of the present application can implement all the method steps implemented by the above method embodiment and can achieve the same technical effects. The same parts and beneficial effects as those in the method embodiment in this embodiment will not be specifically described herein.

[0279] As Figure 9 shown, the embodiment of the present application provides a data processing device 900, including:

[0280] A first acquisition module 901, configured to acquire first channel data of a first codebook of a downlink channel at a first time;

[0281] A second sending module 902, configured to send the first channel data to a network device, so that the network device performs decompression calculation on the first channel data to obtain a second codebook, and obtains a third codebook according to a measurement result of a reference signal of the uplink channel at the first time;

[0282] A second receiving module 903, configured to receive first configuration information sent by the network device according to the correlation between the second codebook and the third codebook;

[0283] Among them, the first configuration information is the configuration information of a model for compressing channel data of a codebook for a downlink channel.

[0284] The data processing device provided by the embodiment of the present application determines the correlation between the uplink channel and the downlink channel by calculating the correlation between the second codebook and the third codebook, so as to determine the configuration information of the compression model indicated by the first configuration information sent to the terminal; and when the correlation is relatively large, the characteristics of the downlink channel data are supplemented by the uplink channel data, which can improve the feedback accuracy of the codebook while reducing the amount of channel feedback.

[0285] It should be noted that the device in this embodiment is the device corresponding to the method applied to the terminal side above. The implementation manners in the above embodiments are all applicable to the embodiments of this device and can achieve the same technical effects. The device provided in the embodiments of this application can implement all the method steps implemented in the above method embodiments and can achieve the same technical effects. Therefore, the same parts and beneficial effects as those in the method embodiments will not be specifically described herein.

[0286] As Figure 10 shown, an embodiment of this application provides a network device, including a transceiver 1010 and a processor 1020. Among them,

[0287] the transceiver is configured to receive first channel data of a first codebook of a downlink channel at a first time of a terminal;

[0288] the processor is configured to perform decompression calculation on the first channel data to obtain a second codebook;

[0289] obtain a third codebook according to a measurement result of a reference signal of an uplink channel at the first time;

[0290] the transceiver is further configured to send first configuration information to the terminal according to the correlation between the second codebook and the third codebook;

[0291] wherein, the first configuration information is configuration information of a model for compressing channel data of a codebook of a downlink channel.

[0292] It should be noted that the device in this embodiment is the device corresponding to the method applied to the network device side above. The implementation manners in the above embodiments are all applicable to the embodiments of this device and can achieve the same technical effects. The device provided in the embodiments of this application can implement all the method steps implemented in the above method embodiments and can achieve the same technical effects. Therefore, the same parts and beneficial effects as those in the method embodiments will not be specifically described herein.

[0293] As Figure 11 shown, an embodiment of this application provides a terminal, including a transceiver 1110. Among them,

[0294] the transceiver is configured to obtain first channel data of a first codebook of a downlink channel at a first time;

[0295] send the first channel data to a network device, so that the network device performs decompression calculation on the first channel data to obtain a second codebook and obtains a third codebook according to a measurement result of a reference signal of an uplink channel at the first time;

[0296] Receive first configuration information sent by the network device according to the correlation between the second codebook and the third codebook;

[0297] Wherein, the first configuration information is configuration information of a model for compressing channel data of a codebook of a downlink channel, and the first configuration information is related to the correlation between an uplink channel and the downlink channel.

[0298] It should be noted that the device in this embodiment is a device corresponding to the method applied to the terminal side above. The implementation manners in the above embodiments are all applicable to the embodiments of this device and can achieve the same technical effects. The device provided in the embodiments of the present application can implement all the method steps implemented by the above method embodiments and can achieve the same technical effects. Here, the same parts and beneficial effects as those in the method embodiments in this embodiment will not be specifically described again.

[0299] Please refer to Figure 12 , the embodiments of the present application further provide a network device 1200, including a processor 1201, a memory 1202, and a computer program stored on the memory 1202 and executable on the processor 1201. When the computer program is executed by the processor 1201, it implements each process of the above data processing method embodiment executed by the network device and can achieve the same technical effects. To avoid repetition, it will not be elaborated here.

[0300] As Figure 13 shown, the embodiments of the present application further provide a terminal 1300, including a processor 1301, a memory 1302, and a computer program stored on the memory 1302 and executable on the processor 1301. When the computer program is executed by the processor 1301, it implements each process of the above data processing method embodiment executed by the terminal and can achieve the same technical effects. To avoid repetition, it will not be elaborated here.

[0301] The embodiments of the present application further provide a computer-readable storage medium. A computer program is stored on the computer-readable storage medium. When the computer program is executed by a processor, it implements each process of the above data processing method embodiment and can achieve the same technical effects. To avoid repetition, it will not be elaborated here. Among them, the computer-readable storage medium is, for example, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disc, etc.

[0302] It should be noted that in this article, the term "including", "containing" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such a process, method, article or device. Without further limitation, an element defined by the statement "including one..." does not exclude the presence of additional identical elements in the process, method, article or device including that element.

[0303] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-described example methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions for causing a terminal (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of the present application.

[0304] The embodiments of the present application have been described above in conjunction with the accompanying drawings. However, the present application is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Under the inspiration of the present application, those of ordinary skill in the art can also make many forms without departing from the purpose of the present application and the scope protected by the claims, and all of them fall within the protection scope of the present application.

Claims

1. A data processing method, applied to a network device, characterized in that, Including: Receiving first channel data of a first codebook of a downlink channel at a first time of a receiving terminal; Performing decompression calculation on the first channel data to obtain a second codebook; Obtaining a third codebook according to a measurement result of a reference signal of an uplink channel at the first time; Sending first configuration information to the terminal according to a correlation between the second codebook and the third codebook; Wherein, the first configuration information is configuration information of a model for compressing channel data of a codebook of a downlink channel.

2. The method according to claim 1, characterized in that, Receiving first channel data of a first codebook of a downlink channel at a first time of a receiving terminal includes: Determining a first target compression model, where the first target compression model is a model trained by using channel data of a downlink channel; Sending configuration information of the first target compression model to the terminal; the first target compression model is used for compressing channel data of the first codebook to obtain the first channel data; Receiving the first channel data of the first codebook.

3. The method according to claim 2, characterized in that, The determining the first target compression model includes: Determining the first target compression model according to the number of oversampled DFT beams, the number of precoding matrices configurable for each subband, and the number of downlink subbands.

4. The method according to claim 2, characterized in that, Receiving first channel data of a first codebook of a downlink channel at a first time of a receiving terminal further includes: Receiving a first parameter and a second parameter of the first codebook; Wherein, the first parameter is used for reporting a beam group; the second parameter includes a DFT vector for frequency-domain compression.

5. The method according to claim 4, characterized in that, Performing decompression calculation on the first channel data to obtain a second codebook includes: Using the first channel data as an input of a first target decompression model to obtain second channel data; the first target decompression model is a model corresponding to the first target compression model; Determining the second codebook according to the second channel data, the first parameter, and the second parameter.

6. The method according to claim 1, characterized in that, The sending first configuration information to the terminal according to the correlation between the second codebook and the third codebook includes: Calculating the correlation between the third codebook and the second codebook; When the correlation is greater than or equal to a preset threshold, sending the first configuration information for indicating a second target compression model to the terminal; Wherein, the second target compression model is a model trained by using channel data of an uplink channel and channel data of a downlink channel.

7. The method according to claim 6, characterized in that, After sending the first configuration information to the terminal according to the correlation between the second codebook and the third codebook, further includes: Obtaining a fourth codebook according to a measurement result of a reference signal of a second-time uplink channel; the second time is a time after the first time; Decomposing the fourth codebook to obtain third channel data; Receiving fourth channel data of a fifth codebook of a second-time downlink channel sent by the terminal; Using the third channel data and the fourth channel data as inputs of a second target decompression model to obtain fifth channel data; the second target decompression model is a model corresponding to the second target compression model, and the second target decompression model is a model trained by using channel data of an uplink channel and channel data of a downlink channel; Determine a sixth codebook of the downlink channel according to the fifth channel data.

8. The method according to claim 7, characterized in that, After sending the first configuration information to the terminal according to the correlation between the second codebook and the third codebook, it further includes: Receiving a third parameter and a fourth parameter of the fifth codebook sent by the terminal; The determining the sixth codebook of the downlink channel according to the fifth channel data includes: Determining the sixth codebook according to the fifth channel data, the third parameter, and the fourth parameter; Wherein, the third parameter is used to report a beam group; the fourth parameter includes a DFT vector for frequency domain compression.

9. The method according to claim 1, characterized in that The method further includes: Collecting first channel estimation data of the downlink channel; Determining sixth channel data of the downlink channel codebook according to the first channel estimation data; Grouping the sixth channel data according to the number of oversampled DFT beams and the number of frequency basis vectors in the sixth channel data to obtain multiple groups of first target data; Determining a first compression model and a first decompression model corresponding to each group of the first target data; Training the first compression model and the first decompression model corresponding to each group of the first target data with the first target data to obtain a first model database; the first model database is used to store the corresponding relationship between the first compression model and model configuration parameters and the corresponding relationship between the first decompression model and the first compression model.

10. The method according to claim 9, characterized in that The method further includes: Collecting second channel estimation data of the uplink channel; Determining seventh channel data of the uplink channel codebook according to the second channel estimation data; Determining eighth channel data, where the eighth channel data is a data pair composed of the sixth channel data and the seventh channel data; Grouping the eighth channel data according to the number of oversampled DFT beams and the number of frequency basis vectors in the eighth channel data to obtain second target data; Determining a second compression model and a second decompression model corresponding to each group of the second target data; Training the second compression model and the second decompression model corresponding to each group of the second target data with the second target data to obtain a second model database; the second model database is used to store the corresponding relationship between the second compression model and model configuration parameters and the corresponding relationship between the second decompression model and the second compression model.

11. A data processing method, applied to a terminal, characterized in that It includes: Obtaining first channel data of a first codebook of the downlink channel at a first time; Sending the first channel data to a network device, so that the network device performs decompression calculation on the first channel data to obtain a second codebook, and obtains a third codebook according to a measurement result of a reference signal of the first-time uplink channel; Receiving first configuration information sent by the network device according to the correlation between the second codebook and the third codebook; Wherein, the first configuration information is configuration information of a model for compressing channel data of the downlink channel codebook.

12. The method according to claim 11, characterized in that Obtaining first channel data of a first codebook of the downlink channel at a first time includes: Receive the configuration information of the first target compression model sent by the network device, where the first target compression model is a model trained using the channel data of the downlink channel; Compress the channel data of the first codebook using the first target compression model to obtain the first channel data.

13. The method according to claim 12, characterized in that After obtaining the first channel data of the first codebook of the downlink channel at the first time, it further includes: Send the first parameter and the second parameter of the first codebook to the network device, so that the network device determines the second codebook according to the second channel data, the first parameter, and the second parameter; Wherein, the first parameter is used to report the beam group; the second parameter includes the DFT vector for frequency domain compression, the second channel data is obtained by the network device decompressing the first channel data through the first target decompression model, and the first target decompression model is the model corresponding to the first target compression model.

14. The method according to claim 11, characterized in that The method further includes: Obtain the fifth codebook of the downlink channel at the second time; Determine the second target compression model according to the first configuration information; Compress the channel data of the fifth codebook using the second target compression model to obtain the fourth channel data of the fifth codebook; Send the fourth channel data to the network device, so that the network device obtains the fifth channel data according to the second target decompression model and the fourth channel data; the second target decompression model is the model corresponding to the second target compression model, and the second target decompression model is a model trained using the channel data of the uplink channel and the channel data of the downlink channel.

15. The method according to claim 14, characterized in that After sending the fourth channel data to the network device, it further includes: Send the third parameter and the fourth parameter of the fifth codebook to the network device, so that the network device determines the sixth codebook according to the fifth channel data, the third parameter, and the fourth parameter; Wherein, the third parameter is used to report the beam group; the fourth parameter includes the DFT vector for frequency domain compression.

16. A data processing device, characterized in that, It includes: The first receiving module is used to receive the first channel data of the first codebook of the downlink channel of the terminal at the first time; The calculation module is used to perform decompression calculation on the first channel data to obtain the second codebook; The determination module is used to obtain the third codebook according to the measurement result of the reference signal of the first time uplink channel; The first sending module is used to send the first configuration information to the terminal according to the correlation between the second codebook and the third codebook; Wherein, the first configuration information is the configuration information of the model for compressing the channel data of the codebook of the downlink channel.

17. A data processing device, characterized in that, It includes: The first obtaining module is used to obtain the first channel data of the first codebook of the downlink channel at the first time; The second sending module is used to send the first channel data to the network device, so that the network device performs decompression calculation on the first channel data to obtain the second codebook, and obtains the third codebook according to the measurement result of the reference signal of the first time uplink channel; A second receiving module, configured to receive first configuration information sent by the network device according to the correlation between the second codebook and the third codebook; Wherein, the first configuration information is configuration information of a model for compressing channel data of a codebook of a downlink channel.

18. A network device, characterized in that, It includes a transceiver and a processor, wherein, The transceiver is configured to receive first channel data of a first codebook of a downlink channel at a first time of the terminal; The processor is configured to perform decompression calculation on the first channel data to obtain a second codebook; Obtain a third codebook according to a measurement result of a reference signal of an uplink channel at the first time; The transceiver is further configured to send the first configuration information to the terminal according to the correlation between the second codebook and the third codebook; Wherein, the first configuration information is configuration information of a model for compressing channel data of a codebook of a downlink channel.

19. A terminal, characterized in that, It includes a transceiver, wherein, The transceiver is configured to obtain first channel data of a first codebook of a downlink channel at a first time; Send the first channel data to the network device, so that the network device performs decompression calculation on the first channel data to obtain a second codebook, and obtains a third codebook according to a measurement result of a reference signal of an uplink channel at the first time; Receive first configuration information sent by the network device according to the correlation between the second codebook and the third codebook; Wherein, the first configuration information is configuration information of a model for compressing channel data of a codebook of a downlink channel.

20. A network device, characterized in that, It includes: A processor, a memory, and a program stored on the memory and executable on the processor, and when the program is executed by the processor, it implements the steps of the method according to any one of claims 1 to 10.

21. A terminal, characterized in that, It includes: A processor, a memory, and a program stored on the memory and executable on the processor, and when the program is executed by the processor, it implements the steps of the method according to any one of claims 11 to 15.

22. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 15.

Images