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 configuration information of a codebook sent by the network equipment; obtaining a first codebook according to the first configuration information; determining a second codebook according to the first codebook; the second codebook is a codebook which corresponds to the first codebook and is not subjected to decomposition calculation; sending first indication information to the network device according to the first codebook and the second codebook; wherein the first indication information is used for indicating whether a feedback mode of an AI compression model is adopted or not. According to the scheme of the invention, through the first indication information, the network equipment can be indicated to adopt the feedback mode of the AI compression model, and the codebook feedback precision can be ensured under the condition that the codebook overhead is reduced.

Description

Technical Field

[0001] This application relates to the field of mobile communication technologies, and in particular, 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 feedback accuracy of the codebook 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 are used to solve the problem in the prior art that in order to reduce the codebook overhead of high Rank, the feedback accuracy of the codebook 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 terminal and includes:

[0007] Receiving first configuration information of a codebook sent by a network device;

[0008] Obtaining a first codebook according to the first configuration information;

[0009] Determining a second codebook according to the first codebook; the second codebook is the codebook corresponding to the first codebook that has not undergone decomposition calculation;

[0010] Sending first indication information to the network device according to the first codebook and the second codebook;

[0011] Wherein, the first indication information is used to indicate whether to adopt the feedback method of the AI compression model.

[0012] Further, the first configuration information includes:

[0013] The number of oversampled DFT beams, the number of DFT basis vectors, and the number of precoding matrices configurable for each subband.

[0014] Further, obtaining a first codebook according to the first configuration information includes:

[0015] Performing decomposition calculation on the first configuration information according to a preset codebook format to obtain decomposition data;

[0016] Encoding the decomposition data to obtain the first codebook.

[0017] Further, sending first indication information to the network device according to the first codebook and the second codebook includes:

[0018] Determining a first coefficient matrix of the first codebook according to the first codebook;

[0019] Determining a second coefficient matrix of the second codebook according to the second codebook;

[0020] Calculating the difference between the first coefficient matrix and the second coefficient matrix;

[0021] Comparing the difference with a preset threshold to obtain a comparison result;

[0022] Sending the first indication information to the network device according to the comparison result.

[0023] Further, the sending the first indication information to the network device according to the comparison result includes:

[0024] When the difference is greater than the preset threshold, sending first indication information for indicating to adopt the AI compression model feedback method to the network device.

[0025] Further, after sending the first indication information to the network device according to the first codebook and the second codebook, it further includes:

[0026] When the first indication information indicates to adopt the feedback method of the AI compression model, receiving second configuration information of the codebook and second indication information, where the second indication information is used to indicate a target compression model for compressing the coefficient matrix of the codebook;

[0027] Determining a third codebook according to the second configuration information;

[0028] Determining a third coefficient matrix of the third codebook according to the third codebook;

[0029] Compress the third coefficient matrix through the target compression model to obtain a fourth coefficient matrix;

[0030] Send the fourth coefficient matrix to the network device.

[0031] Further, the second indication information includes:

[0032] Used to indicate the target configuration parameters of the target compression model;

[0033] Wherein, the target configuration parameters include at least one of the following: the number of DFT basis vectors, the number of oversampled DFT beams, the number of precoding matrices configurable for each subband, and the model number.

[0034] Further, the method further includes:

[0035] Send the first parameter and the second parameter of the third codebook to the network device;

[0036] Wherein, the first parameter is used to report the beam group; the second parameter includes the DFT vectors for frequency domain compression.

[0037] In a second aspect, an embodiment of the present application provides a data processing method, which is applied to a network device and includes:

[0038] Determine the first configuration information of the codebook;

[0039] Send the first configuration information to the terminal, so that the terminal obtains a first codebook according to the first configuration information and determines a second codebook according to the first codebook; wherein, the second codebook is the undecoded codebook corresponding to the first codebook;

[0040] Receive the first indication information sent by the terminal according to the first codebook and the second codebook;

[0041] Wherein, the first indication information is used to indicate whether to adopt the feedback method of the AI compression model.

[0042] Further, after receiving the first indication information sent by the terminal, it further includes:

[0043] In the case of receiving the first indication information for indicating the feedback method of the AI compression model, determine the second configuration information of the codebook and the second indication information for indicating the target compression model;

[0044] Send the second configuration information and the second indication information to the terminal.

[0045] Further, after sending the second configuration information and the second indication information to the terminal, it further includes:

[0046] Receive a fourth coefficient matrix sent by the terminal; wherein, the fourth coefficient matrix is obtained by the terminal compressing a third coefficient matrix of a third codebook determined according to the second configuration information through the target compression model;

[0047] Decompress the fourth coefficient matrix by using a target decompression model to obtain a fifth coefficient matrix;

[0048] Determine a codebook of a channel according to the fifth coefficient matrix.

[0049] Further, after sending the second configuration information and the second indication information to the terminal, it further includes:

[0050] Receive a first parameter and a second parameter of the third codebook sent by the terminal;

[0051] The determining a codebook of a channel according to the fifth coefficient matrix includes:

[0052] Determine a codebook of a channel according to the fifth coefficient matrix, the first parameter, and the second parameter;

[0053] Wherein, the first parameter is used to report a beam group; the second parameter includes a DFT vector for frequency domain compression.

[0054] Further, the method further includes:

[0055] Collect downlink channel estimation data;

[0056] Determine configuration data optional for the network device according to the downlink channel estimation data; the configuration data includes: the number of DFT basis vectors, the number of oversampled DFT beams, the number of precoding matrices configurable for each subband, and the number of frequency basis vectors;

[0057] Decompose a codebook corresponding to the downlink channel estimation data according to the configuration data to obtain a sixth coefficient matrix;

[0058] Group the sixth coefficient matrix according to the number of oversampled DFT beams and the number of frequency basis vectors in the sixth coefficient matrix to obtain multiple groups of target data;

[0059] Determine a compression model and a decompression model corresponding to each group of the target data;

[0060] Train the compression model and the decompression model corresponding to each group of the target data by using the target data to obtain a model database; the model database is used to store the correspondence between the compression model and model configuration parameters and the correspondence between the decompression model and the compression model

[0061] Send the model database to the terminal.

[0062] Furthermore, the method further includes:

[0063] Determine the target number of elements of the samples for training the compression model and the decompression model according to the number of elements of the sixth coefficient matrix;

[0064] If the number of elements of the sixth coefficient matrix is less than the target number of elements, adjust the target data by padding with zeros to obtain target sample data;

[0065] Train the compression model and the decompression model with the target sample data;

[0066] Wherein, the number of the sixth coefficient matrix is the number of elements corresponding to the matrix composed of the number of oversampled DFT beams and the number of frequency basis vectors.

[0067] In a third aspect, an embodiment of the present application provides a data processing device, including:

[0068] A first receiving module, configured to receive first configuration information of a codebook sent by a network device;

[0069] A first determining module, configured to obtain a first codebook according to the first configuration information;

[0070] A second determining module, configured to determine a second codebook according to the first codebook; the second codebook is the codebook corresponding to the first codebook that has not undergone decomposition calculation;

[0071] A first sending module, configured to send first indication information to the network device according to the first codebook and the second codebook;

[0072] Wherein, the first indication information is used to indicate whether to adopt the feedback method of the AI compression model.

[0073] In a fourth aspect, an embodiment of the present application provides a data processing device, including:

[0074] A third determining module, configured to determine first configuration information of a codebook;

[0075] A second sending module, configured to send the first configuration information to a terminal, so that the terminal obtains a first codebook according to the first configuration information and determines a second codebook according to the first codebook; wherein, the second codebook is the codebook corresponding to the first codebook that has not undergone decomposition calculation;

[0076] A second receiving module, configured to receive first indication information sent by the terminal according to the first codebook and the second codebook;

[0077] Wherein, the first indication information is used to indicate whether to adopt the feedback mode of the AI compression model.

[0078] In a fifth aspect, an embodiment of the present application provides a network device, including a transceiver and a processor, wherein,

[0079] The processor is configured to determine first configuration information of a codebook;

[0080] The transceiver is configured to send the first configuration information to a terminal, so that the terminal obtains a first codebook according to the first configuration information, and determines a second codebook according to the first codebook; wherein, the second codebook is an undecomposed calculated codebook corresponding to the first codebook;

[0081] Receive first indication information sent by the terminal according to the first codebook and the second codebook;

[0082] Wherein, the first indication information is used to indicate whether to adopt the feedback mode of the AI compression model.

[0083] In a sixth aspect, an embodiment of the present application provides a terminal, including a transceiver and a processor, wherein,

[0084] Receive first configuration information of a codebook sent by a network device;

[0085] Obtain a first codebook according to the first configuration information;

[0086] Determine a second codebook according to the first codebook; the second codebook is an undecomposed calculated codebook corresponding to the first codebook;

[0087] Send first indication information to the network device according to the first codebook and the second codebook;

[0088] Wherein, the first indication information is used to indicate whether to adopt the feedback mode of the AI compression model.

[0089] In a seventh 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, the steps of the method described in the first aspect are implemented.

[0090] In an eighth 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, the steps of the method described in the second aspect are implemented.

[0091] In a ninth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a program is stored. When the program is executed by a processor, the steps of the method described above are implemented.

[0092] Compared with the prior art, the data processing method, apparatus, terminal, network device, and storage medium provided by the embodiments of the present application can determine a first codebook based on the first configuration information of the received codebook; obtain a second codebook after restoring the first codebook; and then send first indication information of a feedback manner of whether to adopt an AI compression model to the network device according to the first codebook and the second codebook. In the solution of the present invention, through the first indication information, the feedback manner of the network device adopting the AI compression model can be indicated, and the accuracy of codebook feedback can be ensured while reducing the codebook overhead. BRIEF DESCRIPTION OF THE DRAWINGS

[0093] By reading the detailed description of the preferred embodiments below, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing 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:

[0094] Figure 1 is a schematic diagram of an application scenario of an embodiment of the present application;

[0095] Figure 2 is a schematic diagram of a general decomposition form of a precoding matrix of an embodiment of the present application;

[0096] Figure 3 is a flowchart when the data processing method of an embodiment of the present application is applied to the terminal side;

[0097] Figure 4 is a flowchart of a data processing method according to an embodiment of the present application;

[0098] Figure 5 is a flowchart when the data processing method of an embodiment of the present application is applied to the network device side;

[0099] Figure 6 is a schematic structural diagram of a data processing apparatus according to an embodiment of the present application;

[0100] Figure 7 is a schematic structural diagram of a data processing apparatus according to another embodiment of the present application;

[0101] Figure 8 is a schematic structural diagram of a network device according to an embodiment of the present application;

[0102] Figure 9Structural schematic diagram of a terminal according to an embodiment of the present application;

[0103] Figure 10 Structural schematic diagram of a terminal according to another embodiment of the present application;

[0104] Figure 11 Structural schematic diagram of a network device according to another embodiment of the present application. Detailed implementation manners

[0105] 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.

[0106] The terms "first", "second", etc. in the description and claims of the present application are used to distinguish similar objects and do not necessarily need 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, for example, in an order other than 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 comprising 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 description and claims means at least one of the connected objects.

[0107] The techniques described herein are not limited to NR systems and Long Term 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 that use E-UTRA. UTRA, E-UTRA, UMTS, LTE, LTE-A, and GSM are described in documents from an organization called the "3rd Generation Partnership Project" (3GPP). CDMA2000 and UMB are described in documents 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.

[0108] 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 function and arrangement 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.

[0109] 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. 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 specific technical terms. 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.

[0110] 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 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). A 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.

[0111] 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.

[0112] 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). UL transmissions can also be referred to as reverse link transmissions, while DL transmissions can also be referred to as forward link transmissions. The downlink transmission can be carried out using an authorized frequency band, an unlicensed frequency band, or both. Similarly, the uplink transmission can be carried out using an authorized frequency band, an unlicensed frequency band, or both.

[0113] In an embodiment of the present invention, the number of transmit antennas on the base station side is N, the number of receive antennas on the user side is N1, the Rank value RI of the channel matrix H (with a dimension of N1×N) is calculated, and the number of sub-bands is N sb , 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 takes values in {1, 2}, representing the number of precoding matrices configurable for each subband. The channel matrix corresponding to the physical resource block (PRB) frequency f selected in the subband is denoted as N3. 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 . 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:

[0114]

[0115] According to the etypeII codebook, W 1 can be decomposed as follows:

[0116]

[0117] Among them, 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.

[0118] 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 (corresponding to N transmissions of the antenna), and M is the number of frequency basis vectors.

[0119] The current transmission method of the eType II codebook needs to quantize the coefficient matrix by mapping it to a low-precision quantization set, and then transmit it to the base station;

[0120] For different RIs, denote as Denote as W f .

[0121] As Figure 3 shown, the embodiment of the present application provides a data processing method applied to a terminal, including the following steps:

[0122] Step 301, receive the first configuration information of the codebook sent by the network device;

[0123] Step 302: Obtain a first codebook according to the first configuration information.

[0124] Step 303: Determine a second codebook according to the first codebook; the second codebook is the codebook corresponding to the first codebook that has not undergone decomposition calculation.

[0125] Step 304: Send first indication information to the network device according to the first codebook and the second codebook.

[0126] Wherein, the first indication information is used to indicate whether to adopt the feedback mode of the AI compression model.

[0127] Optionally, the terminal is a terminal that has accessed the network device and has entered the Radio Resource Control (RRC)-CONNECTED state.

[0128] In an embodiment of the present invention, a wireless access network AI model training system (deployed on the CU and / or DU of a base station, or a logical entity across CUs) collects downlink channel estimation data, sets the number of oversampled DFT beams and R that can be selected by the network device; and decomposes the channel estimation data in the etype II codebook format according to the downlink self-carried data to obtain an unquantized

[0129] After that, design a model (auto-encoder) through the dimension of the data and perform offline training, synchronize the trained compression model, number, and an optional model number table related to the model features to the terminal, and synchronize the decompression model, number, and the model number table (optional) to the network device (such as a base station);

[0130] Finally, the base station preset a difference threshold δ according to the accuracy requirement of the feedback channel and RI (1≤RI≤RImax) RI ; wherein, the higher the accuracy requirement of the feedback channel, the higher the RI, and the lower the difference threshold.

[0131] In an embodiment of the present invention, the network device (such as a base station) sends RI (1≤RI≤RImax) and the corresponding difference threshold δ RI to the terminal through broadcast, unicast or multicast;

[0132] and configure the first configuration information (the number L of oversampled DFT beams, the number P of DFT basis vectors used to determine, v and R) according to information such as historical information, complexity, and performance and send it to the terminal;

[0133] The terminal determines the first codebook according to the first configuration information; the first codebook is obtained through decomposition calculation and then recombined in the general form of the precoding matrix as shown below. Figure 2 The codebook is recombined in the general form of the precoding matrix as shown below.

[0134] The terminal restores the first codebook to the codebook format (the second codebook) after decomposition calculation.

[0135] In the data processing method of the embodiment of the present application, the first codebook can be determined by the first configuration information of the received codebook; the second codebook is obtained after restoring the first codebook; thus, according to the first codebook and the second codebook, the first indication information of the feedback method of whether to use the AI compression model is sent to the network device. In the solution of the present invention, through the first indication information, the feedback method of the network device using the AI compression model can be indicated, and the accuracy of codebook feedback can be ensured while reducing the codebook overhead.

[0136] Optionally, the first configuration information includes:

[0137] The number of oversampled DFT beams, the number of DFT basis vectors, and the number of precoding matrices configurable for each subband.

[0138] Optionally, obtaining the first codebook according to the first configuration information includes:

[0139] Performing decomposition calculation on the first configuration information according to a preset codebook format to obtain decomposition data;

[0140] Encoding the decomposition data to obtain the first codebook.

[0141] Optionally, sending the first indication information to the network device according to the first codebook and the second codebook includes:

[0142] Determining the first coefficient matrix of the first codebook according to the first codebook;

[0143] Determining the second coefficient matrix of the second codebook according to the second codebook;

[0144] Calculating the difference between the first coefficient matrix and the second coefficient matrix;

[0145] Comparing the difference with a preset threshold to obtain a comparison result; the preset threshold is configured and sent to the terminal by the network device;

[0146] Sending the first indication information to the network device according to the comparison result.

[0147] In an embodiment of the present invention, the difference between the first coefficient matrix and the second coefficient matrix is calculated using the norm between matrices. Specifically:

[0148]

[0149] Where W (RI) represents the first coefficient matrix, W (RI)″ represents the second coefficient matrix, Δ represents the difference between the first coefficient matrix and the second coefficient matrix, and F represents the norm.

[0150] The data processing method according to the embodiment of the present application can determine the impact of the decomposition calculation on the integrity of the codebook by comparing the differences between the coefficient matrices of the codebooks before and after the decomposition calculation, thereby determining the feedback method of the terminal, and can ensure the accuracy of the codebook feedback while reducing the codebook overhead.

[0151] Optionally, the sending of the first indication information to the network device according to the comparison result includes:

[0152] When the difference is greater than the preset threshold, send the first indication information for indicating the feedback method using the AI compression model to the network device.

[0153] Optionally, the threshold is sent by the network device to the terminal.

[0154] Optionally, the format of the first indication information is a flag bit.

[0155] In an embodiment of the present invention, when the first indication information is used to indicate the feedback method using the AI compression model, the flag bit is 1; when the first indication information is used to indicate the feedback method using the etype II codebook, the flag bit is 0.

[0156] In an embodiment of the present invention, the difference being greater than the preset threshold (difference threshold δ RI ) indicates that the decomposition calculation has a greater impact on the integrity of the codebook, and using the feedback method of the etype II codebook will result in insufficient feedback accuracy; therefore, it is necessary to send the first indication information indicating the feedback method using the AI compression model to the network device;

[0157] If the difference is less than the preset threshold, the feedback method of the etype II codebook is used.

[0158] Optionally, after sending the first indication information to the network device according to the first codebook and the second codebook, it further includes:

[0159] When the first indication information indicates the feedback mode using the AI compression model, receive the second configuration information of the codebook and the second indication information, where the second indication information is used to indicate the target compression model for compressing the coefficient matrix of the codebook;

[0160] Determine a third codebook according to the second configuration information;

[0161] Determine the third coefficient matrix of the third codebook according to the third codebook;

[0162] Compress the third coefficient matrix through the target compression model to obtain a fourth coefficient matrix;

[0163] Send the fourth coefficient matrix to the network device.

[0164] Optionally, the sending the fourth coefficient matrix to the network device includes:

[0165] Send the fourth coefficient matrix on a first resource;

[0166] where the first resource is determined according to the resource information in the second indication information.

[0167] Optionally, the determining the third codebook according to the second configuration information includes:

[0168] Calculate the third codebook according to the second configuration information in a preset codebook format.

[0169] In the embodiments of the present invention, when the first indication information is used to indicate the AI compression model feedback mode, the network device receives the first indication information and reselects the configuration information according to information such as historical experience to determine the second configuration information (L, the number P of oversampled DFT beams v , R, and the time-frequency resources required for the terminal to feedback CSI compression feedback information (such as resource elements, RE)); and send the second configuration information and the configuration information of the compression feedback model (the second indication information) to the terminal through the downlink channel;

[0170] The terminal measures the CSI-RS of the downlink channel reference signal and calculates the unquantized third codebook in the etypeII codebook format according to the received second configuration information;

[0171] And select a channel compression model according to the calculation model number in the second configuration information, and compress the third codebook through the channel compression model.

[0172] In an embodiment of the present invention, compressing the third codebook includes: compressing a third coefficient matrix of the third codebook to obtain a fourth coefficient matrix

[0173] and determining the first resource according to the resource configuration, and sending the fourth coefficient matrix to the network device on the first resource.

[0174] The data processing method in an embodiment of the present application can reduce data overhead by compressing the third coefficient matrix and then sending it to the network device.

[0175] Optionally, the second indication information includes:

[0176] target configuration parameters for indicating the target compression model;

[0177] wherein the target configuration parameters include at least one of the following: the number of DFT basis vectors, the number of oversampled DFT beams, the number of precoding matrices configurable for each subband, and the model number.

[0178] Optionally, the second indication information further includes:

[0179] resource information of the terminal for sending the fourth coefficient matrix;

[0180] wherein the resource information includes time-frequency resources.

[0181] The data processing method in an embodiment of the present application determines the third codebook according to the received second configuration information, and compresses the third codebook according to the received second indication information; enabling the network device to parse the third codebook according to the compressed third codebook to obtain all data of the third codebook, which can ensure the integrity and accuracy of the third codebook data.

[0182] In an embodiment of the present invention, compressing the third codebook includes: compressing a third coefficient matrix of the third codebook to obtain a fourth coefficient matrix

[0183] and determining the first resource according to the resource configuration, and sending the fourth coefficient matrix to the network device on the first resource.

[0184] The data processing method in an embodiment of the present application can reduce data overhead by compressing the third coefficient matrix and then sending it to the network device.

[0185] Optionally, the method further includes:

[0186] Send the first parameter and the second parameter of the third codebook to the network device;

[0187] Among them, the first parameter is used to report the beam group; the second parameter includes the DFT vector for frequency domain compression.

[0188] Optionally, the sending the first parameter and the second parameter of the third codebook to the network device includes:

[0189] Feedback the first parameter and the second parameter to the network device through the type II codebook feedback mode.

[0190] In the embodiment of the present invention, the first parameter W1(t) and the second parameter W f (t) are fed back to the network device through the type II codebook feedback mode.

[0191] The data processing method in the embodiment of the present application can reduce the data overhead by compressing the third coefficient matrix and sending it to the network device; and by sending the first parameter and the second parameter to the network device, the network device can parse out the third codebook according to the fourth coefficient matrix, the first parameter and the second parameter, so as to obtain all the data information of the third codebook.

[0192] In the embodiment of the present invention, after the network device receives the fourth coefficient matrix it decompresses the fourth coefficient matrix through the decompression model to obtain the fifth coefficient matrix and performs supplementary calculations on the fifth coefficient matrix according to the first parameter W1(t) and the second parameter W f (t) to obtain the codebook W (RI) (T);

[0193] Subsequently, the terminal continues to monitor the CSI-RS;

[0194] The network device adjusts L, P (RI) v and R according to the situation of the codebook W v (mainly considering the complexity and performance of the codebook), and configures the terminal through high-layer signaling (such as RRC), and adjusts the model configuration information of the compression feedback model to the terminal;

[0195] The terminal adjusts the calculation of the codebook and the selection of the model according to the model configuration information adjusted by the network device, so as to complete the compression feedback of the channel.

[0196] As Figure 4 shown, the data processing method in the embodiment of the present invention:

[0197] 1. Collect downlink channel data and calculate the unquantified and based on Offline train an AI-based channel compression / decompression model, synchronize the model and the model number table to the base station and the terminal; at the same time, the base station pre-configures the difference threshold δ RI ;

[0198] 2. The terminal is connected to the network and has entered the RRC-CONNECTED state;

[0199] 3. The base station sends the difference threshold δ RI to the terminal and configures the transmission of CSI-RS, L, P v and R to the terminal;

[0200] 4. The terminal measures CSI-RS, calculates the type II codebook and restores it to W (RI)″ , calculates its difference Δ from W (RI) , compares Δ with the difference threshold δ RI ; and feeds back a flag bit to the base station. If Δ and the difference threshold δ RI , then go to step 5, otherwise go to step 9;

[0201] 5. The base station re-selects L, P v and R according to the flag bit fed back by the terminal, and configures the time-frequency resources and model configuration information fed back by the terminal to the terminal;

[0202] 6. The terminal measures and calculates the unquantified and determines the compression model for according to the model configuration information to perform compression to obtain and feeds back W1(t) and W f (t);

[0203] 7. The base station decompresses and calculates the type II codebook according to W1(t) and W f (t);

[0204] 8. The terminal continuously monitors CSI-RS, modulates L, P v and R according to the feedback codebook, thereby adjusting the model configuration information; periodically tests the difference between W (RI)″ and W (RI) , and feeds back a flag bit to the base station. If the base station determines that it is necessary to use the type II codebook, it re-allocates resources and goes to step 9, otherwise goes to step 8;

[0205] 9. The base station configures the resources for the terminal to feedback the type II codebook, and the terminal feeds back the type II codebook according to the configuration of the base station, and then goes back to step 4.

[0206] As shown Figure 5 in the figure, an embodiment of the present invention further provides a data processing method, which is applied to a network device and includes the following steps:

[0207] Step 501, determine the first configuration information of the codebook;

[0208] Step 502, send the first configuration information to the terminal, so that the terminal obtains a first codebook according to the first configuration information and determines a second codebook according to the first codebook, where the second codebook is the undecoded codebook corresponding to the first codebook;

[0209] Step 503, receive the first indication information sent by the terminal according to the first codebook and the second codebook;

[0210] Wherein, the first indication information is used to indicate whether to adopt the feedback mode of the AI compression model.

[0211] In the data processing method of the embodiment of the present invention, by determining the first configuration information of the codebook by the network device, the terminal can determine the first indication information according to the first configuration information, so that the network device determines whether to adopt the feedback mode of the AI compression model according to the first configuration information, thereby ensuring the accuracy of the codebook feedback while reducing the codebook overhead.

[0212] Optionally, after receiving the first indication information sent by the terminal, it further includes:

[0213] In the case of receiving the first indication information indicating to adopt the feedback mode of the AI compression model, determine the second configuration information of the codebook and the second indication information indicating the target compression model;

[0214] Send the second configuration information and the second indication information to the terminal.

[0215] Optionally, the second indication information includes:

[0216] The configuration parameters and resource information of the target compression model;

[0217] Wherein, the configuration parameters of the target compression model include at least one of the following: the number of DFT basis vectors, the number of oversampled DFT beams, the number of pre-coding matrices configurable for each sub-band, and the model number.

[0218] In the data processing method according to the embodiment of the present invention, in the case of determining that the feedback method of the AI compression model needs to be adopted, the configuration information of the codebook is adjusted to obtain the second configuration information, and the configuration parameters of the target compression model for compressing the coefficient matrix of the codebook are obtained, so that the terminal can determine the third coefficient matrix of the codebook according to the second configuration information, and determine the target model for compressing the third coefficient matrix through the configuration parameters of the target compression model.

[0219] Optionally, after sending the second configuration information and the second indication information to the terminal, it further includes:

[0220] Receiving a fourth coefficient matrix sent by the terminal; wherein, the fourth coefficient matrix is obtained by the terminal compressing the third coefficient matrix of the third codebook determined according to the second configuration information through the target compression model;

[0221] Using a target decompression model to decompress the fourth coefficient matrix to obtain a fifth coefficient matrix;

[0222] Determining the codebook of the channel according to the fifth coefficient matrix.

[0223] It should be noted that the target decompression model is a model corresponding to the target compression model.

[0224] Optionally, receiving the fourth coefficient matrix sent by the terminal includes:

[0225] Receiving the fourth coefficient matrix on a first resource; the first resource is determined according to the second indication information;

[0226] The first resource includes: time-frequency resources.

[0227] In the data processing method according to the embodiment of the present invention, through the decompression of the fourth coefficient matrix, the fifth coefficient matrix can be obtained, and thus the codebook can be determined according to the fifth coefficient matrix. While reducing the codebook overhead, the accuracy of the codebook feedback can be ensured.

[0228] Optionally, after sending the second configuration information and the second indication information to the terminal, it further includes:

[0229] Receiving the first parameter and the second parameter of the third codebook sent by the terminal;

[0230] The determining the channel codebook according to the fifth coefficient matrix includes:

[0231] Determining the codebook of the channel according to the fifth coefficient matrix, the first parameter, and the second parameter;

[0232] Among them, the first parameter is used to report a beam group; the second parameter includes a DFT vector for frequency domain compression.

[0233] In the data processing method of the embodiment of the present invention, all data of the codebook can be restored through the fifth coefficient matrix, the first parameter, and the second parameter, ensuring the accuracy of codebook feedback while reducing the codebook overhead.

[0234] Optionally, the method further includes:

[0235] Collecting downlink channel estimation data;

[0236] Determining configurable data optional for the network device according to the downlink channel estimation data; the configurable data includes: the number of DFT basis vectors, the number of oversampled DFT beams, the number of precoding matrices configurable for each subband, and the number of frequency basis vectors;

[0237] Decomposing the codebook corresponding to the downlink channel estimation data according to the configurable data to obtain a sixth coefficient matrix;

[0238] Grouping the sixth coefficient matrix according to the number of oversampled DFT beams and the number of frequency basis vectors in the sixth coefficient matrix to obtain multiple groups of target data;

[0239] Determining a compression model and a decompression model corresponding to each group of the target data;

[0240] Training the compression model and the decompression model corresponding to each group of the target data through the target data to obtain a model database; the model database is used to store the correspondence between the compression model and the model configuration parameters and the correspondence between the decompression model and the compression model

[0241] Sending the model database to the terminal.

[0242] Optionally, the sixth coefficient matrix is unquantized channel data calculated from the codebook of the uplink channel according to a preset codebook format.

[0243] In an embodiment of the present invention, the sixth coefficient matrix is unquantized calculated according to the etypeII codebook format

[0244] In the embodiment of the present invention, a wireless 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, sets the number of oversampled DFT beams and R optional for the network device; and decomposes the channel estimation data according to the downlink self - carried data in the etype II codebook format to obtain unquantized

[0245] After that, a model (auto-encoder) is designed based on the dimension of the data and offline training is performed. The trained compression model, number, and the model number table (optional) related to the model features are synchronized to the terminal, and the decompressed model, number, and model number table (optional) are synchronized to the network device (such as a base station).

[0246] Optionally, the method further includes:

[0247] Determining the target number of elements of the samples for training the compression model and the decompression model according to the number of elements of the sixth coefficient matrix;

[0248] If the number of elements of the sixth coefficient matrix is less than the target number of elements, adjusting the target data by padding with zeros to obtain target sample data;

[0249] Training the compression model and the decompression model with the target sample data;

[0250] Wherein, the number of the sixth coefficient matrix is the number of elements corresponding to the matrix composed of the number of oversampled DFT beams and the number of frequency basis vectors.

[0251] In the data processing method of the embodiment of the present invention, both the compression model and the decompression model are models with generalizable input element numbers, and can perform model training for different configuration parameters, improving the applicable range of the model.

[0252] In the embodiment of the present invention, the model training method may be:

[0253] First, according to the collected downlink channel samples, the optional L, P of the base station v and R, M = P v ×N3×R, assuming that according to the difference of L×M, the data is grouped and a model is designed, and the input of the model is 2×L×M to form a table as shown in Table 1:

[0254] Table 1 Model number table corresponding to L×M

[0255] Model Number L×M 1 2 2 4 3 8 4 12 5 16 6 24 7 32

[0256] During the model training process, it is necessary to the elements in pass through the compression / decompression model in sequence to obtain the compression / decompression process RI times, and splice the obtained together to obtain i.e., W (RI)′ .

[0257] In the embodiment of the present invention, the training method of the model can also be: according to the collected samples Medium Element The dimension is 2×L×M. The largest 2×L×M value is selected as [2×L×M]max as the number of input elements to design the AI ​​model. When the model is trained / inferred, when the sample Elements in When the dimension is 2×L×M<[2×L×M]max, After expanding into a vector, it is padded with zeros to extend its length to [2×L×M]max, and passes through the compression / decompression model in sequence. Model training / inference requires RI times in total. According to the above design, the model is a model that can be generalized to the number of input elements, so only one is needed.

[0258] The wireless access network AI model training system (deployed in the CU and / or DU of the base station, or in the logical entity across CUs) collects downlink channel estimation data and sets the optional L and P v and R, according to different L, P v , R and the number of downlink subbands to decompose the data in etype II codebook format to obtain the unquantized Design a model (auto-encoder) according to the data dimension and perform offline training. Synchronize the trained compression model, number and Table 1 to the terminal, and synchronize the decompression model, number and Table 1 to the base station. The base station pre-sets the difference threshold δ according to the accuracy requirements of the feedback channel and RI. RI =0.1;

[0259] The terminal has been connected to the network and entered the RRC-CONNECTED state;

[0260] The base station sends (can be broadcast or unicast, multicast) RI (1≤RI≤RImax) and its corresponding δ RI To the terminal, configure the number of downlink subbands to 16, send CSI-RS to the terminal according to the configuration, and configure L=4, P according to historical information, complexity, performance and other information v =1 / 8, R=1 and sent to the terminal;

[0261] The terminal measures the downlink channel reference signal CSI-RS and calculates its etypeII codebook and RI, and restores the decomposed codebook to the format before decomposition, which is recorded as W (RI)″ , calculate its difference with W (RI) The difference Δ between them is compared with a threshold value of 0.1. When Δ is greater than 0.1, the flag bit 1 of using AI compression feedback is fed back to the base station.

[0262] If the base station receives the flag bit of AI compression feedback, it will reselect L and P based on historical experience and other information. vAnd R, if configured as follows: L = 4, P v = 1 / 8, R = 1, thus calculating M = 2. According to M = 2 and L = 4, select the corresponding model number 3 in Table 1, configure the time-frequency resources (such as the number of REs) required for the terminal to feedback CSI compression feedback information, and send the compressed feedback model configuration information (including the re-selected L, P v 、R and resources) to the terminal through PDCCH / PDSCH;

[0263] The terminal measures the downlink channel reference signal CSI-RS and calculates the unquantized v according to P 、L、R in the model configuration information according to the etypeII codebook The terminal selects the channel compression model according to the calculated selection number 3 in the received channel compression feedback model configuration information and completes compression. The compressed channel information is denoted as and feedbacks it to the base station according to the resource configuration, and at the same time feedbacks W1(t) and W f (t) in the etype II codebook feedback mode;

[0264] The base station receives the W1(t), and W f (t) fed back by the terminal, and obtains through the decompression model calculates W (RI) (T).

[0265] The 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, sets the optional L, P v and R of the base station, decomposes the data in the etype II codebook format according to L, P v 、R and the number of downlink subbands, calculates the unquantized records [2×L×M]max, designs the model (auto-encoder) with [2×L×M]max as the number of elements of the model input, and at the same time pads the samples with a dimension of 2×L×M < [2×L×M]max with zeros to form new samples, trains the model offline, synchronizes the trained compression model to the terminal, and synchronizes the decompression model to the base station; The base station pre-sets the difference threshold δ according to the accuracy requirement of the feedback channel and the RI pre-set difference RI = 0.1;

[0266] The terminal has accessed the network and enters the RRC-CONNECTED state;

[0267] The base station sends (which can be broadcast, unicast, or multicast) RI (1 ≤ RI ≤ RImax) and its corresponding δ RI to the terminal, configures the number of downlink subbands to 16, sends CSI-RS to the terminal according to the configuration, and configures L = 4, P v = 1 / 8, R = 1 and sends them to the terminal;

[0268] The terminal measures the downlink channel reference signal CSI-RS and calculates its etypeII codebook and RI, restores the decomposed codebook to the format before decomposition, denoted as W (RI)″ , calculates the difference Δ between it and W (RI) , compares Δ with the threshold 0.1. When Δ is greater than 0.1, it feeds back the flag bit 1 of AI compression feedback to the base station;

[0269] If the base station receives the flag bit of AI compression feedback, it reselects L, P v and R according to information such as historical experience, and makes the following configuration: L = 4, P v = 1 / 8, R = 1, configures the time-frequency resources (such as the number of REs) required for the terminal to feedback CSI compression feedback information, and sends the compression feedback model configuration information (including the reselected L, P v , R and resources) to the terminal through PDCCH / PDSCH;

[0270] The terminal measures the downlink channel reference signal CSI-RS and calculates the unquantized v according to P in the model configuration information, L, and R according to the etypeII codebook, and completes the zero-padding of the samples with a dimension of 2 × L × M < [2 × L × M]max and compresses them. The compressed channel information is denoted as and feeds it back to the base station according to the resource configuration, and at the same time feeds back W1(t) and W (t) in the etype II codebook feedback mode; f (t);

[0271] The base station receives the W1(t), and W f (t) fed back by the terminal, and obtains through the decompression model and calculates W (RI) (T).

[0272] The above describes various methods of the embodiments of the present application. Next, an apparatus for implementing the above methods will be further provided.

[0273] Such as Figure 6As shown in the figure, an embodiment of the present application further provides a data processing device 600, including:

[0274] A first receiving module 601, configured to receive first configuration information of a codebook sent by a network device;

[0275] A first determining module 602, configured to obtain a first codebook according to the first configuration information;

[0276] A second determining module 603, configured to determine a second codebook according to the first codebook; the second codebook is an undecomposed calculated codebook corresponding to the first codebook;

[0277] A first sending module 604, configured to send first indication information to the network device according to the first codebook and the second codebook;

[0278] Wherein, the first indication information is used to indicate whether to adopt the feedback method of the AI compression model.

[0279] It should be noted that the device in this embodiment is a device corresponding to the method applied to the terminal 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 above 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. Here, the same parts and beneficial effects as those in the method embodiment in this embodiment will not be specifically described again.

[0280] As Figure 7 shown in the figure, an embodiment of the present application further provides a data processing device 700, including:

[0281] A third determining module 701, configured to determine first configuration information of a codebook;

[0282] A second sending module 702, configured to send the first configuration information to a terminal, so that the terminal obtains a first codebook according to the first configuration information and determines a second codebook according to the first codebook; wherein, the second codebook is an undecomposed calculated codebook corresponding to the first codebook;

[0283] A second receiving module 703, configured to receive the first indication information sent by the terminal according to the first codebook and the second codebook;

[0284] Wherein, the first indication information is used to indicate whether to adopt the feedback method of the AI compression model.

[0285] It should be noted that the device in this embodiment corresponds to the method applied to the network 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 above device provided in the embodiments of the present 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 again.

[0286] Please refer to Figure 8 , the embodiments of the present application further provide a network device 800, including a transceiver 810 and a processor 820, where,

[0287] the processor is configured to determine the first configuration information of the codebook;

[0288] the transceiver is configured to send the first configuration information to a terminal, so that the terminal obtains a first codebook according to the first configuration information and determines a second codebook according to the first codebook; wherein, the second codebook is the codebook corresponding to the first codebook that has not undergone decomposition calculation;

[0289] receive the first indication information sent by the terminal according to the first codebook and the second codebook;

[0290] wherein, the first indication information is used to indicate whether to adopt the feedback manner of the AI compression model.

[0291] Please refer to Figure 9 , the embodiments of the present application further provide a terminal, including a transceiver 910 and a processor 920, where,

[0292] receive the first configuration information of the codebook sent by the network device;

[0293] obtain a first codebook according to the first configuration information;

[0294] determine a second codebook according to the first codebook; the second codebook is the codebook corresponding to the first codebook that has not undergone decomposition calculation;

[0295] send the first indication information to the network device according to the first codebook and the second codebook;

[0296] wherein, the first indication information is used to indicate whether to adopt the feedback manner of the AI compression model.

[0297] Please refer to Figure 10, an embodiment of the present application further provides a terminal 1000, including a processor 1001, a memory 1002, and a computer program stored on the memory 1002 and operable on the processor 1001. When the computer program is executed by the processor 1001, it implements each process of the data processing method embodiment executed by the terminal as described above, and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0298] Please refer to Figure 11 , an embodiment of the present application further provides a network device 1100, including a processor 1101, a memory 1102, and a computer program stored on the memory 1102 and operable on the processor 1101. When the computer program is executed by the processor 1101, it implements each process of the data processing method embodiment executed by the network device as described above, and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0299] An embodiment of the present application further provides 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 data processing method embodiment as described above, and can achieve the same technical effect. 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.

[0300] 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 existence of another identical element in the process, method, article or device including that element.

[0301] Through the description of the above embodiments, those skilled in the art can clearly understand that the above embodiment 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 method. Based on such an 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. The computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disc), and includes several instructions for causing a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in the various embodiments of the present application.

[0302] 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 belong to the protection scope of the present application.

Claims

1. A data processing method, applied to a terminal, characterized in that, including: receiving the first configuration information of the codebook sent by the network device; obtaining a first codebook according to the first configuration information; determining a second codebook according to the first codebook; the second codebook is the codebook corresponding to the first codebook without decomposition calculation; sending first indication information to the network device according to the first codebook and the second codebook; wherein the first indication information is used to indicate whether to adopt the feedback mode of the AI compression model.

2. The data processing method according to claim 1, characterized in that, The first configuration information includes: the number of oversampled DFT beams, the number of DFT basis vectors, and the number of precoding matrices configurable for each subband.

3. The data processing method according to claim 1, characterized in that, Obtaining a first codebook according to the first configuration information includes: performing decomposition calculation on the first configuration information according to a preset codebook format to obtain decomposition data; encoding the decomposition data to obtain the first codebook.

4. The data processing method according to claim 1, characterized in that, Sending first indication information to the network device according to the first codebook and the second codebook includes: determining a first coefficient matrix of the first codebook according to the first codebook; determining a second coefficient matrix of the second codebook according to the second codebook; calculating the difference between the first coefficient matrix and the second coefficient matrix; comparing the difference with a preset threshold to obtain a comparison result; sending the first indication information to the network device according to the comparison result.

5. The data processing method according to claim 4, characterized in that, The sending the first indication information to the network device according to the comparison result includes: when the difference is greater than the preset threshold, sending first indication information for indicating to adopt the feedback mode of the AI compression model to the network device.

6. The data processing method according to claim 1, characterized in that, After sending the first indication information to the network device according to the first codebook and the second codebook, it further includes: when the first indication information indicates to adopt the feedback mode of the AI compression model, receiving the second configuration information of the codebook and the second indication information for indicating the target compression model; determining a third codebook according to the second configuration information; determining a third coefficient matrix of the third codebook according to the third codebook; compressing the third coefficient matrix through the target compression model to obtain a fourth coefficient matrix; sending the fourth coefficient matrix to the network device.

7. The data processing method according to claim 6, characterized in that, The second indication information includes: target configuration parameters for indicating the target compression model; wherein the target configuration parameters include at least one of the following: the number of DFT basis vectors, the number of oversampled DFT beams, the number of precoding matrices configurable for each subband, and the model number.

8. The method according to claim 6, characterized in that, The method further includes: sending the first parameter and the second parameter of the third codebook to the network device; wherein the first parameter is used to report the beam group; the second parameter includes the DFT vector for frequency domain compression.

9. A data processing method, applied to a network device, characterized in that, including: determining the first configuration information of the codebook; sending the first configuration information to the terminal, so that the terminal obtains a first codebook according to the first configuration information and determines a second codebook according to the first codebook; wherein the second codebook is the codebook corresponding to the first codebook without decomposition calculation; receiving the first indication information sent by the terminal according to the first codebook and the second codebook; Among them, the first indication information is used to indicate whether to adopt the feedback method of the AI compression model.

10. The data processing method according to claim 9, characterized in that, After the first indication information sent by the receiving terminal, it further includes: In the case of receiving the first indication information for indicating to adopt the feedback method of the AI compression model, determining the second configuration information of the codebook and the second indication information for indicating the target compression model; sending the second configuration information and the second indication information to the terminal.

11. The data processing method according to claim 10, characterized in that, After sending the second configuration information and the second indication information to the terminal, it further includes: Receiving the fourth coefficient matrix sent by the terminal; wherein, the fourth coefficient matrix is obtained by the terminal compressing the third coefficient matrix of the third codebook determined according to the second configuration information through the target compression model; Using the target decompression model to decompress the fourth coefficient matrix to obtain a fifth coefficient matrix; Determining the codebook of the channel according to the fifth coefficient matrix.

12. The data processing method according to claim 11, characterized in that, After sending the second configuration information and the second indication information to the terminal, it further includes: Receiving the first parameter and the second parameter of the third codebook sent by the terminal; The determining the codebook of the channel according to the fifth coefficient matrix includes: Determining the codebook of the channel according to the fifth coefficient matrix, the first parameter, and the second parameter; Among them, the first parameter is used to report the beam group; the second parameter includes the DFT vector for frequency domain compression.

13. The data processing method according to claim 9, characterized in that, The method further includes: Collecting downlink channel estimation data; Determining the configurable data of the network device according to the downlink channel estimation data; the configurable data includes: the number of DFT basis vectors, the number of oversampled DFT beams, the number of precoding matrices configurable for each subband, and the number of frequency basis vectors; Decomposing the codebook corresponding to the downlink channel estimation data according to the configurable data to obtain a sixth coefficient matrix; Grouping the sixth coefficient matrix according to the number of oversampled DFT beams and the number of frequency basis vectors in the sixth coefficient matrix to obtain multiple groups of target data; Determining the compression model and the decompression model corresponding to each group of the target data; Training the compression model and the decompression model corresponding to each group of the target data through the target data to obtain a model database; the model database is used to store the corresponding relationship between the compression model and the model configuration parameters and the corresponding relationship between the decompression model and the compression model, and sending the model database to the terminal.

14. The method according to claim 13, characterized in that, The method further includes: Determining the target number of elements of the sample for training the compression model and the decompression model according to the number of elements of the sixth coefficient matrix; If the number of elements of the sixth coefficient matrix is less than the target number of elements, adjusting the target data by padding with zeros to obtain target sample data; Training the compression model and the decompression model through the target sample data; Among them, the number of the sixth coefficient matrices is the number of elements corresponding to the matrix composed of the number of oversampled DFT beams and the number of frequency basis vectors.

15. A data processing device, characterized in that, It includes: A first receiving module, configured to receive first configuration information of a codebook sent by a network device; A first determining module, configured to obtain a first codebook according to the first configuration information; A second determining module, configured to determine a second codebook according to the first codebook; The second codebook is the codebook corresponding to the first codebook without decomposition calculation; A first sending module, configured to send first indication information to the network device according to the first codebook and the second codebook; Wherein, the first indication information is used to indicate whether to adopt the feedback mode of the AI compression model.

16. A data processing device, characterized in that, Including: A third determining module, configured to determine first configuration information of a codebook; A second sending module, configured to send the first configuration information to a terminal, so that the terminal obtains a first codebook according to the first configuration information, and determines a second codebook according to the first codebook; wherein, the second codebook is the codebook corresponding to the first codebook without decomposition calculation; A second receiving module, configured to receive first indication information sent by the terminal according to the first codebook and the second codebook; Wherein, the first indication information is used to indicate whether to adopt the feedback mode of the AI compression model.

17. A network device, characterized in that, Including a transceiver and a processor, wherein, The processor is configured to determine first configuration information of a codebook; The transceiver is configured to send the first configuration information to a terminal, so that the terminal obtains a first codebook according to the first configuration information, and determines a second codebook according to the first codebook; wherein, the second codebook is the codebook corresponding to the first codebook without decomposition calculation; Receive first indication information sent by the terminal according to the first codebook and the second codebook; Wherein, the first indication information is used to indicate whether to adopt the feedback mode of the AI compression model.

18. A terminal, characterized in that, Including a transceiver and a processor, wherein, Receive first configuration information of a codebook sent by a network device; Obtain a first codebook according to the first configuration information; Determine a second codebook according to the first codebook; the second codebook is the codebook corresponding to the first codebook without decomposition calculation; Send first indication information to the network device according to the first codebook and the second codebook; Wherein, the first indication information is used to indicate whether to adopt the feedback mode of the AI compression model.

19. A terminal, characterized in that, 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, the steps of the method according to any one of claims 1 to 8 are implemented.

20. A network device, characterized in that, 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, the steps of the method according to any one of claims 9 to 14 are implemented.

21. 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, the steps of the method according to any one of claims 1 to 14 are implemented.

Images