Prediction method and apparatus for channel state information (CSI), and storage medium

Abstract

The present disclosure relates to the technical field of communications, and relates to a prediction method and apparatus for channel state information (CSI), and a storage medium. The method is applied to a UE, and comprises: receiving a downlink reference signal sent by a base station, and performing estimation on the basis of the downlink reference signal to obtain a first downlink CSI and a downlink communication environment parameter; on the basis of the first downlink CSI, the downlink communication environment parameter, and a pre-trained CSI prediction model, performing prediction to obtain a second downlink CSI corresponding to a moment when the base station sends a PDSCH; and sending the second downlink CSI to the base station. According to the present disclosure, the timeliness of the downlink CSI can be improved.

Description

Channel State Information (CSI) prediction method, device, and storage medium

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This disclosure claims priority to a Chinese patent application filed with the Patent Office of China on January 26, 2024, with application number 202410116631.3 and application name “Method, device and storage medium for prediction of channel state information CSI”, the entire contents of which are incorporated by reference into this disclosure. Technical Field

[0003] The present disclosure relates to the field of communication technology, and in particular to a CSI prediction method, device, and storage medium. Background Art

[0004] Currently, in scenarios where UEs (User Equipment) are moving at high speed, the downlink CSI (Channel State Information) reported by the UE suffers from poor timeliness. Specifically, when a base station performs downlink scheduling based on the downlink CSI reported by the UE, the downlink communication environment in which the UE is located has significantly changed due to the UE's high-speed movement. Therefore, the downlink CSI reported by the UE no longer reflects the current UE's downlink communication environment.

[0005] The poor timeliness of downlink CSI fed back by the UE will lead to a series of problems such as inaccurate base station scheduling and reduced data rate. Therefore, a downlink CSI prediction method is urgently needed to improve the timeliness of downlink CSI. Summary of the Invention

[0006] Based on this, in order to address the above technical issues, a CSI prediction method, device and storage medium are provided.

[0007] In a first aspect, a method for predicting channel state information (CSI) is provided. The method is applied to a user equipment (UE), and the method includes:

[0008] receiving a downlink reference signal sent by a base station, and estimating a first downlink CSI and a downlink communication environment parameter based on the downlink reference signal;

[0009] Predicting, according to the first downlink CSI, the downlink communication environment parameter, and a pre-trained CSI prediction model, a second downlink CSI corresponding to a time instant at which the base station transmits a physical downlink shared channel (PDSCH);

[0010] Send the second downlink CSI to the base station.

[0011] As an optional implementation manner, predicting the second downlink CSI corresponding to the PDSCH transmission time of the base station according to the first downlink CSI, the downlink communication environment parameter, and the pre-trained CSI prediction model includes:

[0012] Determining a predicted time interval according to the downlink communication environment parameter, a pre-stored first time parameter provided by the UE, and a second time parameter provided by the base station;

[0013] According to the first downlink CSI, the prediction time interval and the pre-trained CSI prediction model, a second downlink CSI corresponding to the PDSCH sending moment of the base station is predicted.

[0014] As an optional implementation manner, determining the predicted time interval according to the downlink communication environment parameter, the pre-stored first time parameter provided by the UE, and the second time parameter provided by the base station includes:

[0015] determining a transmission time of the downlink reference signal according to the downlink communication environment parameter;

[0016] determining a transmission time of the second downlink CSI according to the downlink communication environment parameter and the first time parameter;

[0017] The prediction time interval is determined according to the transmission time of the downlink reference signal, the transmission time of the second downlink CSI, the first time parameter, and the second time parameter.

[0018] As an optional implementation manner, the downlink communication environment parameter includes at least one or more of a moving speed v of the UE, a moving azimuth angle θ of the UE relative to the base station, and a relative distance between the UE and the base station;

[0019] The step of determining a transmission time T1 of the downlink reference signal according to the downlink communication environment parameter:

[0020] T1=S0 / c;

[0021] Wherein, T1 represents the transmission time of the downlink reference signal, S0 represents the relative distance between the UE and the base station when the base station sends the downlink reference signal, and c represents the speed of light; or,

[0022] determining, according to the downlink communication environment parameter and the first time parameter, a transmission time T2 of the second downlink CSI:

[0023] Wherein, T2 represents the transmission time of the second downlink CSI, v represents the moving speed of the UE, θ represents the moving azimuth angle of the UE relative to the base station, and t1 represents the first time parameter.

[0024] As an optional implementation manner, the sending the second downlink CSI to the base station includes:

[0025] Obtaining compressed second downlink CSI according to the second downlink CSI, a preset compression ratio, and a pre-trained CSI compression model;

[0026] Sending the compressed second downlink CSI and the compression ratio to the base station.

[0027] As an optional implementation manner, the first time parameter is the time interval between receiving the last symbol of the physical downlink shared channel PDCCH that triggers CSI reporting and reporting the second downlink CSI; the second time parameter includes the time for scheduling PDSCH and preparing PDSCH; or,

[0028] The first time parameter is the time interval from receiving the last symbol of the PDCCH that triggers CSI reporting to reporting the compressed second downlink CSI; the second time parameter includes the decompression time of the compressed second downlink CSI and the time for scheduling PDSCH and preparing PDSCH.

[0029] As an optional implementation, the method further includes:

[0030] The time interval level corresponding to the predicted time interval is determined according to the correspondence between the time interval sent by the base station and the time interval level.

[0031] As an optional implementation, the method further includes:

[0032] Sending time indication information to the base station; the time indication information is the predicted time interval, or the time indication information is the time interval level corresponding to the predicted time interval.

[0033] As an optional implementation manner, predicting and obtaining the second downlink CSI corresponding to the PDSCH transmission time instant of the base station according to the first downlink CSI, the prediction time interval, and the pre-trained CSI prediction model includes:

[0034] Get a preset number of historical downlink CSIs;

[0035] A second downlink CSI corresponding to a PDSCH transmission moment of the base station is predicted based on the first downlink CSI, each of the historical downlink CSIs, the prediction time interval, and a pre-trained CSI prediction model.

[0036] As an optional implementation manner, the CSI prediction model is obtained by the following method, including:

[0037] Acquire a basic data set, where the basic data set includes historical downlink CSI of the UE;

[0038] Determine the training data set and the label data set corresponding to each prediction time interval in the basic data set respectively;

[0039] Based on each of the training data sets, each of the label data sets, and each of the prediction time intervals, an initial CSI prediction model is trained to obtain a trained CSI prediction model.

[0040] As an optional implementation manner, determining the training data set and the label data set corresponding to each prediction time interval includes:

[0041] Determine multiple first historical downlink CSI groups corresponding to each prediction time interval, wherein each of the first historical downlink CSI groups includes a first historical downlink CSI and a second historical downlink CSI, and a difference between channel estimation times of the first historical downlink CSI and the second historical downlink CSI is the prediction time interval;

[0042] The plurality of first historical downlink CSIs are determined as a training data set, and the plurality of second historical downlink CSIs are determined as a label data set.

[0043] As an optional implementation manner, determining the training data set and the label data set corresponding to each prediction time interval includes:

[0044] Determining multiple second historical downlink CSI groups corresponding to each prediction time interval, wherein each of the second historical downlink CSI groups includes a third historical downlink CSI, a fourth historical downlink CSI, and a preset number of fifth historical downlink CSIs, the difference between the channel estimation times of the third historical downlink CSI and the fourth historical downlink CSI is the prediction time interval, and the channel estimation times of the preset number of the fifth historical downlink CSIs are earlier than the channel estimation time of the third historical downlink CSI;

[0045] The plurality of third historical downlink CSIs and the fifth historical downlink CSIs respectively corresponding to the third historical downlink CSIs are determined as a training data set, and the plurality of fourth historical downlink CSIs are determined as a label data set.

[0046] As an optional implementation manner, the CSI compression model is obtained by training in the following manner, including:

[0047] Determining the historical downlink CSI of the UE as a third training data set;

[0048] The historical downlink CSI compressed and quantized using the compressed sensing measurement matrix is ​​determined as the third label data set;

[0049] Based on the third training data set and the third label data set, the initial CSI compression model is trained to obtain a trained CSI compression model.

[0050] In a second aspect, a method for predicting channel state information (CSI) is provided. The method is applied to a base station and includes:

[0051] Sending a downlink reference signal to a user equipment UE;

[0052] Obtaining downlink CSI predicted by the UE;

[0053] Scheduling is performed according to the downlink CSI, and a physical downlink shared channel PDSCH is sent to the UE.

[0054] As an optional implementation manner, obtaining the downlink CSI predicted by the UE includes:

[0055] receiving compressed downlink CSI and compression ratio sent by the UE;

[0056] The downlink CSI is obtained according to the compressed downlink CSI, the compression ratio, and a pre-trained CSI decompression model.

[0057] As an optional implementation, the method further includes:

[0058] Receive time indication information sent by the UE; the time indication information is a predicted time interval determined by the UE, or the time indication information is a time interval level corresponding to the predicted time interval determined by the UE.

[0059] As an optional implementation manner, when the time indication information is a time interval level corresponding to the predicted time interval determined by the UE, the method further includes:

[0060] In the correspondence between the time interval and the time interval level, the time interval corresponding to the time indication information is determined, and the predicted time interval is determined by randomly selecting a value or taking the median in the time interval corresponding to the time indication information.

[0061] As an optional implementation, the method further includes:

[0062] Determining a predicted time interval range according to a pre-stored downlink communication environment parameter range of the UE, a first time parameter range provided by the UE, and a second time parameter range provided by the base station;

[0063] Dividing the predicted time interval range according to a preset level division rule to obtain a corresponding relationship between time intervals and time interval levels;

[0064] The correspondence between the time interval and the time interval level is sent to the UE.

[0065] As an optional implementation manner, the CSI decompression model is trained by the following method, including:

[0066] Obtaining historical downlink CSI of the UE;

[0067] The historical downlink CSI compressed and quantized using the compressed sensing measurement matrix is ​​determined as a training data set;

[0068] Determine the historical downlink CSI decompressed by the compressed sensing recovery algorithm as a label data set;

[0069] Based on the training data set and the label data set, an initial CSI decompression model is trained to obtain a trained CSI decompression model.

[0070] In a third aspect, a user equipment (UE) is provided, including a memory, a transceiver, and a processor;

[0071] The memory is used to store a computer program; the transceiver is used to send and receive data under the control of the processor; and the processor is used to read the computer program in the memory and perform the following operations:

[0072] receiving a downlink reference signal sent by a base station, and estimating a first downlink CSI and a downlink communication environment parameter based on the downlink reference signal;

[0073] Predicting, according to the first downlink CSI, the downlink communication environment parameter, and a pre-trained CSI prediction model, a second downlink CSI corresponding to a time instant at which the base station transmits a physical downlink shared channel (PDSCH);

[0074] Send the second downlink CSI to the base station.

[0075] As an optional implementation manner, predicting the second downlink CSI corresponding to the PDSCH transmission time of the base station according to the first downlink CSI, the downlink communication environment parameter, and the pre-trained CSI prediction model includes:

[0076] Determining a predicted time interval according to the downlink communication environment parameter, a pre-stored first time parameter provided by the UE, and a second time parameter provided by the base station;

[0077] According to the first downlink CSI, the prediction time interval and the pre-trained CSI prediction model, a second downlink CSI corresponding to the PDSCH sending moment of the base station is predicted.

[0078] As an optional implementation manner, determining the predicted time interval according to the downlink communication environment parameter, the pre-stored first time parameter provided by the UE, and the second time parameter provided by the base station includes:

[0079] determining a transmission time of the downlink reference signal according to the downlink communication environment parameter;

[0080] determining a transmission time of the second downlink CSI according to the downlink communication environment parameter and the first time parameter;

[0081] The prediction time interval is determined according to the transmission time of the downlink reference signal, the transmission time of the second downlink CSI, the first time parameter, and the second time parameter.

[0082] As an optional implementation manner, the downlink communication environment parameter includes at least one or more of a moving speed v of the UE, a moving azimuth angle θ of the UE relative to the base station, and a relative distance between the UE and the base station;

[0083] The step of determining a transmission time T1 of the downlink reference signal according to the downlink communication environment parameter:

[0084] T1=S0 / c;

[0085] Wherein, T1 represents the transmission time of the downlink reference signal, S0 represents the relative distance between the UE and the base station when the base station sends the downlink reference signal, and c represents the speed of light; or,

[0086] determining, according to the downlink communication environment parameter and the first time parameter, a transmission time T2 of the second downlink CSI:

[0087] Wherein, T2 represents the transmission time of the second downlink CSI, v represents the moving speed of the UE, θ represents the moving azimuth angle of the UE relative to the base station, and t1 represents the first time parameter.

[0088] As an optional implementation manner, the sending the second downlink CSI to the base station includes:

[0089] Obtaining compressed second downlink CSI according to the second downlink CSI, a preset compression ratio, and a pre-trained CSI compression model;

[0090] Sending the compressed second downlink CSI and the compression ratio to the base station.

[0091] As an optional implementation manner, the first time parameter is the time interval between receiving the last symbol of the physical downlink shared channel PDCCH that triggers CSI reporting and reporting the second downlink CSI; the second time parameter includes the time for scheduling PDSCH and preparing PDSCH; or,

[0092] The first time parameter is the time interval from receiving the last symbol of the PDCCH that triggers CSI reporting to reporting the compressed second downlink CSI; the second time parameter includes the decompression time of the compressed second downlink CSI and the time for scheduling PDSCH and preparing PDSCH.

[0093] As an optional implementation manner, the processor is further configured to read the computer program in the memory and perform the following operations:

[0094] The time interval level corresponding to the predicted time interval is determined according to the correspondence between the time interval sent by the base station and the time interval level.

[0095] As an optional implementation manner, the processor is further configured to read the computer program in the memory and perform the following operations:

[0096] Sending time indication information to the base station; the time indication information is the predicted time interval, or the time indication information is the time interval level corresponding to the predicted time interval.

[0097] As an optional implementation manner, predicting and obtaining the second downlink CSI corresponding to the PDSCH transmission time instant of the base station according to the first downlink CSI, the prediction time interval, and the pre-trained CSI prediction model includes:

[0098] Get a preset number of historical downlink CSIs;

[0099] A second downlink CSI corresponding to a PDSCH transmission moment of the base station is predicted based on the first downlink CSI, each of the historical downlink CSIs, the prediction time interval, and a pre-trained CSI prediction model.

[0100] As an optional implementation manner, the CSI prediction model is obtained by the following method, including:

[0101] Acquire a basic data set, where the basic data set includes historical downlink CSI of the UE;

[0102] Determine the training data set and the label data set corresponding to each prediction time interval in the basic data set respectively;

[0103] Based on each of the training data sets, each of the label data sets, and each of the prediction time intervals, an initial CSI prediction model is trained to obtain a trained CSI prediction model.

[0104] As an optional implementation manner, determining the training data set and the label data set corresponding to each prediction time interval includes:

[0105] Determine multiple first historical downlink CSI groups corresponding to each prediction time interval, wherein each of the first historical downlink CSI groups includes a first historical downlink CSI and a second historical downlink CSI, and a difference between channel estimation times of the first historical downlink CSI and the second historical downlink CSI is the prediction time interval;

[0106] The plurality of first historical downlink CSIs are determined as a training data set, and the plurality of second historical downlink CSIs are determined as a label data set.

[0107] As an optional implementation manner, determining the training data set and the label data set corresponding to each prediction time interval includes:

[0108] Determining multiple second historical downlink CSI groups corresponding to each prediction time interval, wherein each of the second historical downlink CSI groups includes a third historical downlink CSI, a fourth historical downlink CSI, and a preset number of fifth historical downlink CSIs, the difference between the channel estimation times of the third historical downlink CSI and the fourth historical downlink CSI is the prediction time interval, and the channel estimation times of the preset number of the fifth historical downlink CSIs are earlier than the channel estimation time of the third historical downlink CSI;

[0109] The plurality of third historical downlink CSIs and the fifth historical downlink CSIs respectively corresponding to the third historical downlink CSIs are determined as a training data set, and the plurality of fourth historical downlink CSIs are determined as a label data set.

[0110] As an optional implementation manner, the CSI compression model is obtained by training in the following manner, including:

[0111] Determining the historical downlink CSI of the UE as a third training data set;

[0112] The historical downlink CSI compressed and quantized using the compressed sensing measurement matrix is ​​determined as the third label data set;

[0113] Based on the third training data set and the third label data set, the initial CSI compression model is trained to obtain a trained CSI compression model.

[0114] In a fourth aspect, a base station is provided, comprising a memory, a transceiver, and a processor;

[0115] The memory is used to store a computer program; the transceiver is used to send and receive data under the control of the processor; and the processor is used to read the computer program in the memory and perform the following operations:

[0116] Sending a downlink reference signal to a user equipment UE;

[0117] Obtaining downlink CSI predicted by the UE;

[0118] Scheduling is performed according to the downlink CSI, and a physical downlink shared channel PDSCH is sent to the UE.

[0119] As an optional implementation manner, obtaining the downlink CSI predicted by the UE includes:

[0120] receiving compressed downlink CSI and compression ratio sent by the UE;

[0121] The downlink CSI is obtained according to the compressed downlink CSI, the compression ratio, and a pre-trained CSI decompression model.

[0122] As an optional implementation manner, the processor is further configured to read the computer program in the memory and perform the following operations:

[0123] Receive time indication information sent by the UE; the time indication information is a predicted time interval determined by the UE, or the time indication information is a time interval level corresponding to the predicted time interval determined by the UE.

[0124] As an optional implementation manner, when the time indication information is a time interval level corresponding to the predicted time interval determined by the UE, the processor is further configured to read the computer program in the memory and perform the following operations:

[0125] In the correspondence between the time interval and the time interval level, the time interval corresponding to the time indication information is determined, and the predicted time interval is determined by randomly selecting a value or taking the median in the time interval corresponding to the time indication information.

[0126] As an optional implementation manner, the processor is further configured to read the computer program in the memory and perform the following operations:

[0127] Determining a predicted time interval range according to a pre-stored downlink communication environment parameter range of the UE, a first time parameter range provided by the UE, and a second time parameter range provided by the base station;

[0128] Dividing the predicted time interval range according to a preset level division rule to obtain a corresponding relationship between time intervals and time interval levels;

[0129] The correspondence between the time interval and the time interval level is sent to the UE.

[0130] As an optional implementation manner, the CSI decompression model is trained by the following method, including:

[0131] Obtaining historical downlink CSI of the UE;

[0132] The historical downlink CSI compressed and quantized using the compressed sensing measurement matrix is ​​determined as a training data set;

[0133] Determine the historical downlink CSI decompressed by the compressed sensing recovery algorithm as a label data set;

[0134] Based on the training data set and the label data set, an initial CSI decompression model is trained to obtain a trained CSI decompression model.

[0135] In a fifth aspect, a device for predicting channel state information (CSI) is provided. The device is applied to a user equipment (UE), and includes:

[0136] an estimating unit, configured to receive a downlink reference signal sent by a base station, and estimate and obtain a first downlink CSI and a downlink communication environment parameter based on the downlink reference signal;

[0137] A prediction unit, configured to predict, based on the first downlink CSI, the downlink communication environment parameter, and a pre-trained CSI prediction model, a second downlink CSI corresponding to a moment when the base station transmits a physical downlink shared channel PDSCH;

[0138] The first sending unit is configured to send the second downlink CSI to the base station.

[0139] In a sixth aspect, a device for predicting channel state information (CSI) is provided. The device is applied to a base station and includes:

[0140] A first sending unit, configured to send a downlink reference signal to a user equipment UE;

[0141] An acquiring unit, configured to acquire the downlink CSI predicted by the UE;

[0142] The second sending unit is configured to perform scheduling according to the downlink CSI and send a physical downlink shared channel PDSCH to the UE.

[0143] In a seventh aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method steps described in the first aspect or the second aspect are implemented.

[0144] The present disclosure provides a CSI prediction method, device and storage medium. The technical solution provided by the embodiments of the present disclosure brings at least the following beneficial effects: the UE receives a downlink reference signal sent by the base station, and estimates the first downlink CSI and downlink communication environment parameters based on the downlink reference signal. Then, the UE predicts the second downlink CSI corresponding to the moment when the base station sends PDSCH based on the first downlink CSI, the downlink communication environment parameters and the pre-trained CSI prediction model, and sends the second downlink CSI to the base station. In this way, the second downlink CSI used by the base station when sending PDSCH to the UE at the moment of sending PDSCH can better match the downlink communication environment where the UE is at the moment of sending PDSCH, thereby ensuring the timeliness of the downlink CSI.

[0145] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0146] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0147] FIG1 is a flowchart of a CSI prediction method provided by an embodiment of the present disclosure;

[0148] FIG2 is a flowchart of a CSI prediction method provided by an embodiment of the present disclosure;

[0149] FIG3 is a flowchart of a CSI prediction method provided by an embodiment of the present disclosure;

[0150] FIG4 is a schematic structural diagram of a UE provided in an embodiment of the present disclosure;

[0151] FIG5 is a schematic structural diagram of a base station provided by an embodiment of the present disclosure;

[0152] FIG6 is a schematic structural diagram of a CSI prediction device provided by an embodiment of the present disclosure;

[0153] FIG7 is a schematic structural diagram of a CSI prediction device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0154] In embodiments of the present invention, the term "and / or" describes the association relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally indicates that the associated objects are in an "or" relationship.

[0155] In the embodiments of the present disclosure, the term "plurality" refers to two or more than two, and other quantifiers are similar thereto.

[0156] The following will be combined with the accompanying drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. Obviously, the embodiments described are only part of the embodiments of the present disclosure and not all of the embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present disclosure.

[0157] FIG1 is a flowchart of a CSI prediction method provided by an embodiment of the present disclosure. The CSI prediction method is applied to a UE. As shown in FIG1 , the specific steps are as follows:

[0158] Step 101: Receive a downlink reference signal sent by a base station, and estimate and obtain a first downlink CSI and a downlink communication environment parameter based on the downlink reference signal.

[0159] In the embodiments provided herein, a base station transmits a PDCCH (Physical Downlink Control Channel) and downlink reference information to a UE, triggering CSI reporting. Accordingly, the UE receives the PDCCH and downlink reference signal transmitted by the base station, triggering CSI reporting. The UE can perform channel estimation based on the downlink reference signal and obtain first downlink CSI corresponding to the downlink reference signal. Furthermore, the UE can also perform communication environment estimation based on the downlink reference signal and obtain downlink communication environment parameters corresponding to the downlink reference signal.

[0160] Step 102 : Predict and obtain a second downlink CSI corresponding to the time when the base station sends the PDSCH based on the first downlink CSI, downlink communication environment parameters, and a pre-trained CSI prediction model.

[0161] In the embodiments provided in the present disclosure, in order to make the downlink CSI used by the base station better match the downlink communication environment in which the UE is located when sending PDSCH, the UE can predict the second downlink CSI corresponding to the moment when the base station sends PDSCH based on the first downlink CSI, downlink communication environment parameters and a pre-trained CSI prediction model.

[0162] As an optional implementation, in step 102 above, the UE predicts the second downlink CSI corresponding to the base station's PDSCH transmission time based on the first downlink CSI, downlink communication environment parameters, and a pre-trained CSI prediction model. The prediction process includes, but is not limited to, the following method, as shown in Figure 2.

[0163] Step 201: Determine a predicted time interval according to a downlink communication environment parameter, a pre-stored first time parameter provided by the UE, and a second time parameter provided by the base station.

[0164] In the embodiments provided in the present disclosure, when a base station sends a PDSCH to a UE, in order to better match the downlink CSI used by the base station with the downlink communication environment in which the UE is located at the time of sending the PDSCH, the UE may determine a predicted time interval based on a downlink communication environment parameter, a pre-stored first time parameter provided by the UE, and a second time parameter provided by the base station.

[0165] It should be noted that the first time parameter and the second time parameter of the embodiment of the present disclosure can be obtained in different ways, including but not limited to:

[0166] First way:

[0167] The first time parameter may be the time interval between receiving the last symbol of the PDCCH triggering CSI reporting and reporting the second downlink CSI. The first time parameter includes the estimation time of the first downlink CSI, the estimation time of the downlink communication environment parameter, the calculation time of the prediction time interval, the prediction time of the second downlink CSI, etc.

[0168] The second time parameter includes at least the time for scheduling the PDSCH and preparing the PDSCH.

[0169] Second way:

[0170] The first time parameter may be the time interval between receiving the last symbol of the PDCCH triggering CSI reporting and reporting the compressed second downlink CSI. The first time parameter includes the estimation time of the first downlink CSI, the estimation time of the downlink communication environment parameter, the calculation time of the prediction time interval, the prediction time of the second downlink CSI, and the compression time of the second downlink CSI.

[0171] The second time parameter includes at least the decompression time of the compressed second downlink CSI and the time of scheduling and preparing the PDSCH.

[0172] In order to improve the accuracy of predicting the second CSI, when the current downlink CSI (ie, the first downlink CSI) is used as an input parameter, the first parameter and the second parameter obtained in the first manner may be preferentially selected as input parameters to predict the second CSI.

[0173] When determining to predict the second CSI using the CSI compression model, the first parameter and the second parameter obtained in the second manner may be preferentially selected as input parameters.

[0174] Optionally, the downlink communication environment parameter includes at least one or more of a UE's moving speed, a moving azimuth angle relative to the base station, and a relative distance from the base station. The UE's moving azimuth angle relative to the base station is the angle formed by a line connecting the UE and the base station and the UE's moving direction.

[0175] In the above step 201, the specific process of the UE determining the predicted time interval according to the downlink communication environment parameter, the pre-stored first time parameter provided by the UE, and the second time parameter provided by the base station is as follows:

[0176] Step 1: Determine the transmission time of the downlink reference signal according to the downlink communication environment parameters.

[0177] In the embodiments provided in the present disclosure, the UE may determine the transmission time of the downlink reference signal according to downlink communication environment parameters.

[0178] As an optional implementation manner, the UE determines the transmission time T1 of the downlink reference signal according to the downlink communication environment parameter: T1 = S0 / c;

[0179] Wherein, T1 represents the transmission time of the downlink reference signal, S0 represents the relative distance between the UE and the base station when the base station sends the downlink reference signal, and c represents the speed of light.

[0180] Step 2: Determine the transmission time of the second downlink CSI according to the downlink communication environment parameter and the first time parameter.

[0181] In the embodiments provided herein, in a UE high-speed mobility scenario, the UE will move at high speed over time, the distance of the UE from the base station will also change over time, and the transmission time it takes for the UE to transmit the second downlink CSI to the base station will also change over time. Based on this, the UE can determine the transmission time of the second downlink CSI based on the downlink communication environment parameters and the first time parameter. The downlink predicted transmission time is the transmission time it takes for the UE to transmit the second downlink CSI to the base station at the target location after moving from the current location to the target location within the first time parameter.

[0182] As an optional implementation manner, the UE determines the transmission time T2 of the compressed second downlink CSI according to the downlink communication environment parameter and the first time parameter:

[0183] Wherein, T2 represents the transmission time of the second downlink CSI, v represents the moving speed of the UE, θ represents the moving azimuth of the UE relative to the base station, and t1 represents the first time parameter.

[0184] Step three: determine a prediction time interval according to the transmission time of the downlink reference signal, the transmission time of the second downlink CSI and the first time parameter.

[0185] In the embodiments provided in the present disclosure, the UE determines the predicted time interval as the sum of the transmission time of the downlink reference signal, the transmission time of the second downlink CSI, the first time parameter provided by the UE, and the second time parameter provided by the base station. The predicted time interval is the time from the last symbol of the PDCCH that triggers the CSI reporting to the time when the base station sends the PDSCH to the UE (excluding the transmission time of the PDSCH from the base station to the UE).

[0186] Step 202: According to the first downlink CSI, the prediction time interval and the pre-trained CSI prediction model, a second downlink CSI corresponding to the time when the base station sends the PDSCH is predicted.

[0187] In the embodiment provided by the present disclosure, the UE inputs the first downlink CSI and the predicted time interval into the pre-trained CSI prediction model. Accordingly, the CSI prediction model outputs the second downlink CSI corresponding to the moment when the base station sends PDSCH. Since the current moment is delayed by the predicted time interval, it is the moment when the base station sends PDSCH. Therefore, based on the first downlink CSI and the predicted time interval, the second downlink CSI obtained by the CSI prediction model is the second downlink CSI corresponding to the moment when the base station sends PDSCH. In this way, the second downlink CSI used by the base station when sending PDSCH to the UE at the moment of sending PDSCH can better match the downlink communication environment of the UE at the moment of sending PDSCH, thereby ensuring the timeliness of the second downlink CSI. Optionally, the CSI prediction model can adopt an LSTM (Long-Short Term Memory) neural network model, or a GRU (Gated Recurrent Unit) neural network model, or other types of neural network models, which are not limited in the embodiments of the present disclosure.

[0188] As an optional implementation, in order to further improve the accuracy of the second downlink CSI, the UE can obtain a preset number of historical downlink CSIs, and predict the second downlink CSI corresponding to the moment when the base station sends the PDSCH based on the first downlink CSI, each historical downlink CSI, the prediction time interval and the pre-trained CSI prediction model.

[0189] In the embodiments provided in the present disclosure, the UE can obtain a preset number of historical downlink CSIs. The preset number of historical downlink CSIs is a preset number of historical downlink CSIs whose channel estimation time is earlier than the channel estimation time of the first downlink CSI and closest to the channel estimation time of the first downlink CSI. The UE then inputs the first downlink CSI, each historical downlink CSI, and the prediction time interval into a pre-trained CSI prediction model. Accordingly, the CSI prediction model outputs the second downlink CSI corresponding to the time when the base station transmits the PDSCH.

[0190] Step 103: Send the second downlink CSI to the base station.

[0191] In the embodiment provided in the present disclosure, after obtaining the second downlink CSI, the UE may send the second downlink CSI to the base station.

[0192] As an optional implementation, the UE can compress the second downlink CSI and send it to the base station. The specific processing process is: obtain the compressed second downlink CSI based on the second downlink CSI, a preset compression ratio and a pre-trained CSI compression model; and send the compressed second downlink CSI and compression ratio to the base station.

[0193] In the embodiments provided in the present disclosure, the UE may input the second downlink CSI and a preset compression ratio into a pre-trained CSI compression model. Accordingly, the CSI compression model outputs compressed second downlink CSI. The CSI compression model may employ an RNN (Recurrent Neural Network) neural network model or other types of neural network models, which are not limited in the embodiments of the present disclosure.

[0194] To ensure that the base station can decompress the data normally, the UE can send the compressed second downlink CSI and compression ratio to the base station through the PUSCH (Physical Uplink Shared Channel). In this way, the second downlink CSI used by the base station when sending the PDSCH to the UE at the time of sending the PDSCH can better match the downlink communication environment in which the UE is located at the time of sending the PDSCH, thereby solving the problem of poor timeliness of the second downlink CSI and ensuring the accuracy of the second downlink CSI.

[0195] As an optional implementation, to reduce signaling overhead, the time indication information sent by the UE to the base station may be the time interval level corresponding to the predicted time interval. Accordingly, the UE may determine the time interval level corresponding to the predicted time interval based on the correspondence between the time interval sent by the base station and the time interval level.

[0196] As an optional implementation, the UE may also send time indication information to the base station, wherein the time indication information is a predicted time interval, or the time indication information is a time interval level corresponding to the predicted time interval.

[0197] In the embodiments provided herein, directly reporting the predicted time interval results in significant signaling overhead. Therefore, the UE can determine the index of the time interval level corresponding to the predicted time interval from the correspondence between the time interval range and the time interval level transmitted by the base station. This reduces signaling overhead by transmitting the time interval level corresponding to the predicted time interval to the base station. The base station's process for determining the correspondence between the time interval range and the time interval level will be described in detail later and will not be further elaborated here.

[0198] As an optional implementation, in step 201 above, the UE can obtain the second downlink CSI using the CSI prediction model in two ways: Method 1: Input the first downlink CSI and the prediction time interval into a pre-trained CSI prediction model to obtain the second downlink CSI. Method 2: Input the first downlink CSI, historical downlink CSI, and the prediction time interval into a pre-trained CSI prediction model to obtain the second downlink CSI. Accordingly, the UE obtains the CSI prediction model in the following manner.

[0199] Step 1: Obtain a basic data set. The basic data set includes the historical downlink CSI of the UE.

[0200] In the embodiments provided herein, each time a UE performs channel estimation based on downlink reference information sent by a base station and obtains downlink CSI (i.e., historical downlink CSI), the UE can record the historical downlink CSI and the channel estimation time to obtain a basic data set. When the UE needs to train an initial CSI prediction model, the UE can obtain this basic data set.

[0201] Step 2: Determine the training dataset and label dataset corresponding to each prediction time interval in the basic dataset.

[0202] In the embodiment provided in the present disclosure, the UE may determine, in the basic data set, a training data set and a label data set corresponding to each prediction time interval.

[0203] For the above-mentioned method 1, the UE determines multiple first historical downlink CSI groups corresponding to each prediction time interval, wherein each first historical downlink CSI group includes a first historical downlink CSI and a second historical downlink CSI, and the difference between the channel estimation moments of the first historical downlink CSI and the second historical downlink CSI is the prediction time interval. The UE determines the multiple first historical downlink CSIs as training data sets and determines the multiple second historical downlink CSIs as label data sets.

[0204] In the embodiment provided in the present disclosure, for different prediction time intervals, the UE can determine multiple first historical downlink CSI groups corresponding to each prediction time interval in the basic data set. Each first historical downlink CSI group includes a first historical downlink CSI and a second historical downlink CSI. The difference between the channel estimation moment of the first historical downlink CSI and the channel estimation moment of the second historical downlink CSI is the prediction time interval. For example, the prediction time interval is Δt, the channel estimation moment of the first historical downlink CSI is t, and the channel estimation moment of the second historical downlink CSI is t+Δt. Optionally, a prediction time interval can be selected from a time interval range corresponding to a prediction time interval level. Then, the UE can determine the first historical downlink CSI as a training data set, and determine the second historical downlink CSI as a label data set.

[0205] For the above-mentioned method 2, the UE determines multiple second historical downlink CSI groups corresponding to each prediction time interval, wherein each second historical downlink CSI group includes the third historical downlink CSI, the fourth historical downlink CSI and a preset number of fifth historical downlink CSIs, the difference between the channel estimation time of the third historical downlink CSI and the fourth historical downlink CSI is the prediction time interval, and the channel estimation time of the preset number of fifth historical downlink CSIs is earlier than the channel estimation time of the third historical downlink CSI; the UE determines the multiple third historical downlink CSIs and the fifth historical downlink CSIs corresponding to the third historical downlink CSIs as training data sets, and determines the multiple fourth historical downlink CSIs as label data sets.

[0206] In an embodiment provided in the present disclosure, for different prediction time intervals, the UE may determine, in a basic data set, multiple second historical downlink CSI groups corresponding to each prediction time interval. Each second historical downlink CSI group includes a third historical downlink CSI, a fourth historical downlink CSI, and a preset number of fifth historical downlink CSIs. The difference between the channel estimation time of the third historical downlink CSI and the channel estimation time of the fourth historical downlink CSI is the prediction time interval, and the channel estimation time of the preset number of fifth historical downlink CSIs is earlier than and close to the channel estimation time of the third historical downlink CSI. For example, if the prediction time interval is Δt and the channel estimation time of the third historical downlink CSI is t, then the channel estimation time of the fourth historical downlink CSI is t+Δt, and the channel estimation time of the fifth historical downlink CSI is earlier than t. Optionally, a prediction time interval may be selected from a time interval range corresponding to a prediction time interval level. The UE may then determine the multiple third historical downlink CSIs and the fifth historical downlink CSIs corresponding to the third historical downlink CSIs as a training data set, and determine the multiple fourth historical downlink CSIs as a label data set.

[0207] Step 3: Based on each training data set, each label data set, and each prediction time interval, the initial CSI prediction model is trained to obtain a trained CSI prediction model.

[0208] In the embodiments provided herein, the UE trains an initial CSI prediction model based on a training dataset, a labeled dataset, and each prediction time interval until the model converges, thereby obtaining a trained CSI prediction model. This trained CSI prediction model can output different second downlink CSIs for different prediction time intervals and different first downlink CSIs.

[0209] As an optional implementation manner, the UE obtains a CSI compression model through training in the following manner:

[0210] Step 1: determine the historical downlink CSI of the UE as the third training data set.

[0211] In the embodiment provided in the present disclosure, each time the UE performs channel estimation based on the downlink reference information sent by the base station and obtains downlink CSI (ie, historical downlink CSI), the UE may determine the historical downlink CSI as the third training data set.

[0212] Step 2: The historical downlink CSI compressed and quantized using the compressed sensing measurement matrix is ​​determined as the third label data set.

[0213] In the embodiments provided herein, the UE may determine, as a third labeled data set, historical downlink CSI compressed and quantized using a compressed sensing measurement matrix. The measurement matrix is ​​composed of randomly selected rows from an orthogonal Fourier transform matrix; quantization may be uniform or non-uniform, which is not limited in the embodiments of this disclosure.

[0214] Step three: Based on the third training data set and the third label data set, the initial CSI compression model is trained to obtain a trained CSI compression model.

[0215] In the embodiments provided herein, the UE may train an initial CSI compression model based on the third training dataset and the third labeled dataset until the model converges, thereby obtaining a trained CSI compression model. Alternatively, the UE may train CSI compression models corresponding to different compression ratios, or design the CSI compression model as an extensible model by connecting corresponding upsampling modules or downsampling modules according to different compression ratios to accommodate different compression ratios.

[0216] It should be noted that the training process of the above-mentioned CSI prediction model and CSI compression model can be performed by the terminal manufacturer and directly deployed on the UE after training. It can also be trained separately by different UEs themselves, but this will increase the computational burden and energy consumption of the UE.

[0217] The present disclosure also provides a CSI prediction method. FIG3 is a flowchart of the CSI prediction method provided by the present disclosure. The CSI prediction method is applied to a base station. As shown in FIG3 , the specific steps are as follows:

[0218] Step 301: Send a downlink reference signal to the UE.

[0219] In the embodiment provided in the present disclosure, when the base station requires the UE to perform downlink CSI prediction, the base station may send a PDCCH and downlink reference information for triggering CSI reporting to the UE.

[0220] Step 302: Obtain the downlink CSI predicted by the UE.

[0221] In the embodiment provided in the present disclosure, the UE may send the predicted downlink CSI to the base station via the PUSCH channel. Correspondingly, the base station may receive the second downlink CSI sent by the UE.

[0222] Step 303: Perform scheduling according to the downlink CSI and send PDSCH to the UE.

[0223] In the embodiment provided in the present disclosure, the base station obtains downlink CSI, performs scheduling according to the downlink predicted CSI, and sends PDSCH to the UE.

[0224] As an optional implementation manner, the base station receives compressed downlink CSI and a compression ratio sent by the UE; and obtains the downlink CSI according to the compressed downlink CSI, the compression ratio, and a pre-trained CSI decompression model.

[0225] In the embodiments provided in the present disclosure, the UE can send compressed downlink CSI and compression ratio to the base station through the PUSCH channel. Accordingly, the base station can receive the compressed downlink CSI and compression ratio sent by the UE. After the base station receives the compressed downlink CSI and compression ratio sent by the UE, it can input the compressed downlink CSI and compression ratio into a pre-trained CSI decompression model. Accordingly, the CSI decompression model outputs downlink CSI. Among them, the CSI decompression model can adopt a CNN (Convolutional Neural Network) neural network model, or an MLP (Multi-Layer Perceptron) neural network model, or other types of neural network models, which are not limited in the embodiments of the present disclosure.

[0226] As an optional implementation manner, the base station receives time indication information sent by the UE, wherein the time indication information is a predicted time interval determined by the UE, or the time indication information is a time interval level corresponding to the predicted time interval determined by the UE.

[0227] As an optional implementation, to reduce signaling overhead, the time indication information sent by the UE to the base station is the time interval level corresponding to the predicted time interval. Accordingly, the base station can determine the time interval corresponding to the time indication information based on the correspondence between time intervals and time interval levels, and determine the predicted time interval by randomly selecting a value or taking the median of the time intervals corresponding to the time indication information.

[0228] In the embodiments provided herein, after receiving the time indication information, the base station may determine the time interval corresponding to the time indication information based on the correspondence between time intervals and time interval levels. The base station may then determine a predicted time interval within the time intervals corresponding to the time indication information. Alternatively, the base station may randomly select a time interval from the time intervals corresponding to the time indication information as the predicted time interval, or may select the median of the time intervals from the time indication information as the predicted time interval, although this embodiment is not limiting.

[0229] As an optional implementation manner, the base station determines the corresponding relationship between the time interval and the time interval level in the following process:

[0230] Step 1: Determine a predicted time interval range based on a pre-stored downlink communication environment parameter range of the UE, a first time parameter range provided by the UE, and a second time parameter range provided by the base station.

[0231] In the embodiments provided herein, the base station may determine a predicted time interval range based on a pre-stored downlink communication environment parameter range of the UE, a first time parameter range provided by the UE, and a second time parameter range provided by the base station. The process by which the base station determines the predicted time interval range is similar to the process by which the UE determines the predicted time interval, and is not further described herein.

[0232] Step 2: Divide the prediction time interval range according to the preset level division rule to obtain the corresponding relationship between the time interval and the time interval level.

[0233] In the embodiments provided herein, a base station may divide the predicted time interval range according to a preset classification rule to obtain a correspondence between time intervals and time interval levels. The time intervals corresponding to each time interval level may be uniform or non-uniform. For example, the base station may divide the predicted time interval range into time interval levels with non-uniform time intervals based on the UE's moving speed. For example, the greater the UE's moving speed, the smaller the time interval corresponding to the time interval level.

[0234] Step 3: Send the correspondence between the time interval and the time interval level to the UE.

[0235] In the embodiment provided by the present disclosure, after the base station obtains the correspondence between the time interval and the time interval level, it can send the correspondence between the time interval and the time interval level to the UE by broadcasting, so that after the UE determines the predicted time interval, it can determine the time interval level corresponding to the predicted time interval based on the correspondence between the time interval and the time interval level.

[0236] As an optional implementation manner, the base station obtains a CSI decompression model through training in the following manner:

[0237] Step 1: Obtain the historical downlink CSI of the UE.

[0238] In the embodiment provided in the present disclosure, each time the UE performs channel estimation based on the downlink reference information sent by the base station and obtains downlink CSI (ie, historical downlink CSI), the base station may record the historical downlink CSI.

[0239] Step 2: The historical downlink CSI compressed and quantized using the compressed sensing measurement matrix is ​​determined as a training data set.

[0240] In the embodiments provided herein, a base station may determine historical downlink CSI, compressed and quantized using a compressed sensing measurement matrix, as a training dataset. The measurement matrix is ​​constructed by randomly extracting rows from an orthogonal Fourier transform matrix. Quantization may be uniform or non-uniform, which is not limited in the embodiments provided herein.

[0241] Step 3: Determine the historical downlink CSI decompressed by the compressed sensing recovery algorithm as a label data set.

[0242] In the embodiments provided herein, a base station may use historical downlink CSI compressed and quantized using a compressed sensing measurement matrix, and then decompress the historical downlink CSI using a compressed sensing recovery algorithm to determine it as a label dataset. The compressed sensing recovery algorithm may use an OMP (Orthogonal Matching Pursuit) algorithm or other types of compressed sensing recovery algorithms, which are not limited in the embodiments of the present disclosure.

[0243] Step 4: Based on the training data set and the label data set, the initial CSI decompression model is trained to obtain a trained CSI decompression model.

[0244] In the embodiments provided herein, a base station may train an initial CSI decompression model based on a training dataset and a labeled dataset until the model converges, thereby obtaining a trained CSI decompression model. Alternatively, the base station may train CSI decompression models corresponding to different compression ratios. Alternatively, the base station may design the CSI decompression model as a scalable model, i.e., connecting corresponding upsampling modules or downsampling modules according to different compression ratios to accommodate different compression ratios.

[0245] It should be noted that the compression and decompression of downlink CSI can also be implemented using an Auto-Encoder bilateral model (an unsupervised learning model). Using the Auto-Encoder bilateral model to compress and decompress downlink CSI requires deploying an encoder on the UE side and a decoder on the base station side. Accordingly, the training and deployment methods of the encoder and decoder can include the following methods. Method 1: The UE trains the encoder and decoder and sends the trained decoder to the base station. The advantage of Method 1 is that the machine learning models trained by each UE can better adapt to their respective UEs. The disadvantage is that the computational burden of the UE is relatively heavy, and the base station needs to maintain more decoders. Method 2: The terminal manufacturer trains the encoder and decoder, deploys the trained encoder to the UE, and sends the trained decoder to the base station. When using the encoder for compression, the UE also needs to send an identifier of the decoder corresponding to the encoder to the base station so that the base station can perform decompression. The advantage of method 2 is that it reduces the training burden of the UE, but the disadvantage is that the terminal manufacturer cannot train different machine learning models according to the different environments in which the UE is located. Method 3: The base station trains the encoder and decoder, and broadcasts the trained encoder to each UE. The advantage of method 3 is that it reduces the training burden of the UE, but the disadvantage is that the base station cannot train different machine learning models according to the different environments in which the UE is located. Method 4: The base station and UE jointly train the encoder and decoder, that is, in each training loop, forward propagation and backward propagation training processes need to be performed between the UE side and the base station side, and the data sets used by the two sides must be consistent. The disadvantage of method 4 is that the overhead is very high, and since quantization is required during the transmission process, the training performance may be affected. Regardless of which of the above training and deployment methods is adopted, since the training data of the Auto-Encoder is the same as the label data, data collection only requires the UE, terminal manufacturer or base station to obtain historical downlink CSI over a period of time. Common training data uses the downlink CSI channel matrix or the eigenvector of the precoding matrix. The commonly used machine learning model is based on the transformer learning model.

[0246] The present disclosure provides a CSI prediction method, in which a UE receives a downlink reference signal sent by a base station and estimates a first downlink CSI and a downlink communication environment parameter based on the downlink reference signal. Then, the UE predicts a second downlink CSI corresponding to the moment when the base station sends the PDSCH based on the first downlink CSI, the downlink communication environment parameter, and a pre-trained CSI prediction model, and sends the second downlink CSI to the base station. In this way, the second downlink CSI used by the base station when sending the PDSCH to the UE at the moment of sending the PDSCH can better match the downlink communication environment in which the UE is located at the moment of sending the PDSCH, thereby ensuring the timeliness of the downlink CSI.

[0247] It can be understood that the same / similar parts between the various embodiments of the above method in this specification can be referred to each other, and each embodiment focuses on the differences from other embodiments. For related parts, please refer to the description of other method embodiments.

[0248] The embodiment of the present disclosure further provides a UE, as shown in FIG4 , including a memory 410 , a transceiver 420 , and a processor 430 ;

[0249] The memory 410 is used to store computer programs; the transceiver 420 is used to send and receive data under the control of the processor 430; the processor 430 is used to read the computer program in the memory 410 and perform the following operations:

[0250] receiving a downlink reference signal sent by a base station, and estimating a first downlink CSI and a downlink communication environment parameter based on the downlink reference signal;

[0251] Predicting, based on the first downlink CSI, downlink communication environment parameters, and a pre-trained CSI prediction model, a second downlink CSI corresponding to a PDSCH transmission time of the base station;

[0252] Send the second downlink CSI to the base station.

[0253] As an optional implementation manner, predicting and obtaining a second downlink CSI corresponding to a PDSCH transmission time of a base station based on the first downlink CSI, downlink communication environment parameters, and a pre-trained CSI prediction model includes:

[0254] Determining a predicted time interval according to a downlink communication environment parameter, a pre-stored first time parameter provided by the UE, and a second time parameter provided by the base station;

[0255] According to the first downlink CSI, the prediction time interval and the pre-trained CSI prediction model, the second downlink CSI corresponding to the time when the base station sends the PDSCH is predicted.

[0256] As an optional implementation manner, determining the predicted time interval according to the downlink communication environment parameter, the pre-stored first time parameter provided by the UE, and the second time parameter provided by the base station includes:

[0257] Determining a transmission time of a downlink reference signal according to downlink communication environment parameters;

[0258] determining a transmission time of a second downlink CSI according to the downlink communication environment parameter and the first time parameter;

[0259] A prediction time interval is determined according to the transmission time of the downlink reference signal, the transmission time of the second downlink CSI, the first time parameter and the second time parameter.

[0260] As an optional implementation manner, the downlink communication environment parameter includes at least one or more of a moving speed v of the UE, a moving azimuth angle θ of the UE relative to the base station, and a relative distance between the UE and the base station;

[0261] Determine the transmission time T1 of the downlink reference signal based on the downlink communication environment parameters:

[0262] T1=S0 / c;

[0263] Wherein, T1 represents the transmission time of the downlink reference signal, S0 represents the relative distance between the UE and the base station when the base station sends the downlink reference signal, and c represents the speed of light; or,

[0264] Determine the transmission time T2 of the second downlink CSI according to the downlink communication environment parameter and the first time parameter:

[0265] Wherein, T2 represents the transmission time of the second downlink CSI, v represents the moving speed of the UE, θ represents the moving azimuth of the UE relative to the base station, and t1 represents the first time parameter.

[0266] As an optional implementation manner, sending the second downlink CSI to the base station includes:

[0267] Obtaining compressed second downlink CSI according to the second downlink CSI, a preset compression ratio, and a pre-trained CSI compression model;

[0268] The compressed second downlink CSI and the compression ratio are sent to the base station.

[0269] As an optional implementation manner, the first time parameter is the time interval from receiving the last symbol of the PDCCH triggering CSI reporting to reporting the second downlink CSI; the second time parameter includes the time for scheduling PDSCH and preparing PDSCH; or,

[0270] The first time parameter is the time interval from receiving the last symbol of the PDCCH that triggers CSI reporting to reporting the compressed second downlink CSI; the second time parameter includes the decompression time of the compressed second downlink CSI and the time for scheduling PDSCH and preparing PDSCH.

[0271] As an optional implementation manner, the processor 430 is further configured to read the computer program in the memory 410 and perform the following operations:

[0272] The time interval level corresponding to the predicted time interval is determined according to the correspondence between the time interval sent by the base station and the time interval level.

[0273] As an optional implementation manner, the processor 430 is further configured to read the computer program in the memory 410 and perform the following operations:

[0274] Sending time indication information to the base station; the time indication information is a predicted time interval, or the time indication information is a time interval level corresponding to the predicted time interval.

[0275] As an optional implementation manner, predicting and obtaining the second downlink CSI corresponding to the PDSCH transmission time instant of the base station according to the first downlink CSI, the prediction time interval, and the pre-trained CSI prediction model includes:

[0276] Get a preset number of historical downlink CSIs;

[0277] According to the first downlink CSI, each historical downlink CSI, the prediction time interval and the pre-trained CSI prediction model, the second downlink CSI corresponding to the time when the base station sends the PDSCH is predicted.

[0278] As an optional implementation, the CSI prediction model is obtained by the following method, including:

[0279] Obtain a basic data set, which includes the historical downlink CSI of the UE;

[0280] Determine the training dataset and label dataset corresponding to each prediction time interval in the basic dataset respectively;

[0281] Based on each training data set, each label data set, and each prediction time interval, an initial CSI prediction model is trained to obtain a trained CSI prediction model.

[0282] As an optional implementation, determining the training dataset and label dataset corresponding to each prediction time interval includes:

[0283] Determine multiple first historical downlink CSI groups corresponding to each prediction time interval, where each first historical downlink CSI group includes a first historical downlink CSI and a second historical downlink CSI, and a difference between channel estimation times of the first historical downlink CSI and the second historical downlink CSI is the prediction time interval;

[0284] A plurality of first historical downlink CSIs are determined as a training data set, and a plurality of second historical downlink CSIs are determined as a label data set.

[0285] As an optional implementation, determining the training dataset and label dataset corresponding to each prediction time interval includes:

[0286] Determining multiple second historical downlink CSI groups corresponding to each prediction time interval, where each second historical downlink CSI group includes a third historical downlink CSI, a fourth historical downlink CSI, and a preset number of fifth historical downlink CSIs, the difference between the channel estimation times of the third historical downlink CSI and the fourth historical downlink CSI is the prediction time interval, and the channel estimation times of the preset number of fifth historical downlink CSIs are earlier than the channel estimation time of the third historical downlink CSI;

[0287] The plurality of third historical downlink CSIs and the fifth historical downlink CSIs respectively corresponding to the third historical downlink CSIs are determined as a training data set, and the plurality of fourth historical downlink CSIs are determined as a label data set.

[0288] As an optional implementation, the CSI compression model is trained by the following method, including:

[0289] Determine the historical downlink CSI of the UE as a third training data set;

[0290] The historical downlink CSI compressed and quantized using the compressed sensing measurement matrix is ​​determined as the third label data set;

[0291] Based on the third training data set and the third label data set, the initial CSI compression model is further trained to obtain a trained CSI compression model.

[0292] The embodiment of the present disclosure further provides a base station, as shown in FIG5 , including a memory 510 , a transceiver 520 , and a processor 530 ;

[0293] The memory 510 is used to store computer programs; the transceiver 520 is used to send and receive data under the control of the processor 530; the processor 530 is used to read the computer program in the memory 510 and perform the following operations:

[0294] Sending a downlink reference signal to the UE;

[0295] Get the downlink CSI predicted by the UE;

[0296] Schedule according to the downlink CSI and send PDSCH to the UE.

[0297] As an optional implementation manner, obtaining the downlink CSI predicted by the UE includes:

[0298] receiving compressed downlink CSI and compression ratio sent by the UE;

[0299] The downlink CSI is obtained according to the compressed downlink CSI, the compression ratio, and the pre-trained CSI decompression model.

[0300] As an optional implementation manner, the processor 530 is further configured to read the computer program in the memory 510 and perform the following operations:

[0301] Receive time indication information sent by the UE; the time indication information is a predicted time interval determined by the UE, or the time indication information is a time interval level corresponding to the predicted time interval determined by the UE.

[0302] As an optional implementation manner, when the time indication information is a time interval level corresponding to the predicted time interval determined by the UE, the processor 530 is further configured to read the computer program in the memory 510 and perform the following operations:

[0303] In the correspondence between the time interval and the time interval level, the time interval corresponding to the time indication information is determined, and the predicted time interval is determined by randomly selecting a value or taking the median in the time interval corresponding to the time indication information.

[0304] As an optional implementation manner, the processor 530 is further configured to read the computer program in the memory 510 and perform the following operations:

[0305] Determining a predicted time interval range according to a pre-stored downlink communication environment parameter range of the UE, a first time parameter range provided by the UE, and a second time parameter range provided by the base station;

[0306] According to the preset grade division rules, the prediction time interval range is divided to obtain the corresponding relationship between the time interval and the time interval grade;

[0307] The correspondence between the time interval and the time interval level is sent to the UE.

[0308] As an optional implementation, the CSI decompression model is trained by the following method, including:

[0309] Get the historical downlink CSI of the UE;

[0310] The historical downlink CSI compressed and quantized using the compressed sensing measurement matrix is ​​determined as a training data set;

[0311] Determine the historical downlink CSI decompressed by the compressed sensing recovery algorithm as a label data set;

[0312] Based on the training dataset and the label dataset, the initial CSI decompression model is trained to obtain a trained CSI decompression model.

[0313] The present disclosure also provides a CSI prediction device, as shown in FIG6 , which is applied to a UE and includes:

[0314] The estimation unit 610 is configured to receive a downlink reference signal sent by a base station, and estimate and obtain a first downlink CSI and a downlink communication environment parameter based on the downlink reference signal;

[0315] The prediction unit 620 is configured to predict and obtain a second downlink CSI corresponding to a PDSCH transmission time of the base station based on the first downlink CSI, downlink communication environment parameters, and a pre-trained CSI prediction model;

[0316] The first sending unit 630 is configured to send the second downlink CSI to the base station.

[0317] As an optional implementation, the prediction unit 620 is specifically configured to:

[0318] Determining a predicted time interval according to a downlink communication environment parameter, a pre-stored first time parameter provided by the UE, and a second time parameter provided by the base station;

[0319] According to the first downlink CSI, the prediction time interval and the pre-trained CSI prediction model, the second downlink CSI corresponding to the time when the base station sends the PDSCH is predicted.

[0320] As an optional implementation, the prediction unit 620 is specifically configured to:

[0321] Determining a transmission time of a downlink reference signal according to downlink communication environment parameters;

[0322] determining a transmission time of a second downlink CSI according to the downlink communication environment parameter and the first time parameter;

[0323] A prediction time interval is determined according to the transmission time of the downlink reference signal, the transmission time of the second downlink CSI, the first time parameter and the second time parameter.

[0324] As an optional implementation manner, the downlink communication environment parameter includes at least one or more of a moving speed v of the UE, a moving azimuth angle θ of the UE relative to the base station, and a relative distance between the UE and the base station;

[0325] Determine the transmission time T1 of the downlink reference signal based on the downlink communication environment parameters:

[0326] T1=S0 / c;

[0327] Wherein, T1 represents the transmission time of the downlink reference signal, S0 represents the relative distance between the UE and the base station when the base station sends the downlink reference signal, and c represents the speed of light; or,

[0328] Determine the transmission time T2 of the second downlink CSI according to the downlink communication environment parameter and the first time parameter:

[0329] Wherein, T2 represents the transmission time of the second downlink CSI, v represents the moving speed of the UE, θ represents the moving azimuth of the UE relative to the base station, and t1 represents the first time parameter.

[0330] As an optional implementation manner, the first sending unit 630 is specifically configured to:

[0331] Obtaining compressed second downlink CSI according to the second downlink CSI, a preset compression ratio, and a pre-trained CSI compression model;

[0332] The compressed second downlink CSI and the compression ratio are sent to the base station.

[0333] As an optional implementation manner, the first time parameter is the time interval from receiving the last symbol of the PDCCH triggering CSI reporting to reporting the second downlink CSI; the second time parameter includes the time for scheduling PDSCH and preparing PDSCH; or,

[0334] The first time parameter is the time interval from receiving the last symbol of the PDCCH that triggers CSI reporting to reporting the compressed second downlink CSI; the second time parameter includes the decompression time of the compressed second downlink CSI and the time for scheduling PDSCH and preparing PDSCH.

[0335] As an optional embodiment, the device further includes:

[0336] The determining unit is configured to determine the time interval level corresponding to the predicted time interval according to the correspondence between the time interval sent by the base station and the time interval level.

[0337] As an optional embodiment, the device further includes:

[0338] The second sending unit is configured to send time indication information to the base station; the time indication information is a predicted time interval, or the time indication information is a time interval level corresponding to the predicted time interval.

[0339] As an optional implementation, the prediction unit 620 is specifically configured to:

[0340] Get a preset number of historical downlink CSIs;

[0341] According to the first downlink CSI, each historical downlink CSI, the prediction time interval and the pre-trained CSI prediction model, the second downlink CSI corresponding to the time when the base station sends the PDSCH is predicted.

[0342] As an optional implementation manner, the first model training unit is specifically configured to:

[0343] Obtain a basic data set, which includes the historical downlink CSI of the UE;

[0344] Determine the training dataset and label dataset corresponding to each prediction time interval in the basic dataset respectively;

[0345] Based on each training data set, each label data set, and each prediction time interval, an initial CSI prediction model is trained to obtain a trained CSI prediction model.

[0346] As an optional implementation manner, the first model training unit is specifically configured to:

[0347] Determine multiple first historical downlink CSI groups corresponding to each prediction time interval, where each first historical downlink CSI group includes a first historical downlink CSI and a second historical downlink CSI, and a difference between channel estimation times of the first historical downlink CSI and the second historical downlink CSI is the prediction time interval;

[0348] A plurality of first historical downlink CSIs are determined as a training data set, and a plurality of second historical downlink CSIs are determined as a label data set.

[0349] As an optional implementation manner, the first model training unit is specifically configured to:

[0350] Determining multiple second historical downlink CSI groups corresponding to each prediction time interval, where each second historical downlink CSI group includes a third historical downlink CSI, a fourth historical downlink CSI, and a preset number of fifth historical downlink CSIs, the difference between the channel estimation times of the third historical downlink CSI and the fourth historical downlink CSI is the prediction time interval, and the channel estimation times of the preset number of fifth historical downlink CSIs are earlier than the channel estimation time of the third historical downlink CSI;

[0351] The plurality of third historical downlink CSIs and the fifth historical downlink CSIs respectively corresponding to the third historical downlink CSIs are determined as a training data set, and the plurality of fourth historical downlink CSIs are determined as a label data set.

[0352] As an optional implementation manner, the second model training unit is specifically configured to:

[0353] Determine the historical downlink CSI of the UE as a third training data set;

[0354] The historical downlink CSI compressed and quantized using the compressed sensing measurement matrix is ​​determined as the third label data set;

[0355] Based on the third training data set and the third label data set, the initial CSI compression model is further trained to obtain a trained CSI compression model.

[0356] The present disclosure also provides a CSI prediction device, as shown in FIG7 , which is applied to a base station and includes:

[0357] A first sending unit 710 is configured to send a downlink reference signal to a UE;

[0358] An acquiring unit 720 is configured to acquire downlink CSI predicted by the UE;

[0359] The second sending unit 730 is configured to perform scheduling according to the downlink CSI and send the PDSCH to the UE.

[0360] As an optional implementation manner, the acquiring unit 720 is specifically configured to:

[0361] receiving compressed downlink CSI and compression ratio sent by the UE;

[0362] The downlink CSI is obtained according to the compressed downlink CSI, the compression ratio, and the pre-trained CSI decompression model.

[0363] As an optional embodiment, the device further includes:

[0364] The receiving unit is configured to receive time indication information sent by the UE; the time indication information is a predicted time interval determined by the UE, or the time indication information is a time interval level corresponding to the predicted time interval determined by the UE.

[0365] As an optional implementation manner, when the time indication information is a time interval level corresponding to the predicted time interval determined by the UE, the apparatus further includes:

[0366] The first determining unit is configured to determine the time interval corresponding to the time indication information in the correspondence between the time interval and the time interval level, and determine the predicted time interval by randomly selecting a value or taking the median within the time interval corresponding to the time indication information.

[0367] As an optional embodiment, the device further includes:

[0368] A second determining unit is configured to determine a predicted time interval range according to a pre-stored downlink communication environment parameter range of the UE, a first time parameter range provided by the UE, and a second time parameter range provided by the base station;

[0369] A division unit, configured to divide the prediction time interval range according to a preset level division rule, and obtain a corresponding relationship between the time interval and the time interval level;

[0370] The third sending unit is configured to send the correspondence between the time interval and the time interval level to the UE.

[0371] As an optional implementation, the model training unit is specifically configured to:

[0372] Get the historical downlink CSI of the UE;

[0373] The historical downlink CSI compressed and quantized using the compressed sensing measurement matrix is ​​determined as a training data set;

[0374] Determine the historical downlink CSI decompressed by the compressed sensing recovery algorithm as a label data set;

[0375] Based on the training dataset and the label dataset, the initial CSI decompression model is trained to obtain a trained CSI decompression model.

[0376] It should be noted that the division of units in the embodiments of the present disclosure is schematic and is merely a logical functional division. In actual implementation, other division methods may be used. Furthermore, the functional units in the various embodiments of the present disclosure may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0377] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a processor-readable storage medium. Based on this understanding, the technical solution of the present disclosure, or the part that contributes to the relevant technology, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the method described in each embodiment of the present disclosure.

[0378] It should be noted here that the above-mentioned device provided by the embodiment of the present invention can implement all the method steps implemented by the above-mentioned method embodiment and can achieve the same technical effect. The parts and beneficial effects that are the same as the method embodiment in this embodiment will not be described in detail here.

[0379] An embodiment of the present disclosure provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the above-mentioned CSI prediction method are implemented.

[0380] The processor-readable storage medium can be any available medium or data storage device that can be accessed by the processor, including but not limited to magnetic storage (such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO)), optical storage (such as CDs, DVDs, BDs, HVDs, etc.), and semiconductor storage (such as ROMs, EPROMs, EEPROMs, non-volatile memories (NAND FLASH), solid-state drives (SSDs)), etc.

[0381] Those skilled in the art will appreciate that the embodiments of the present disclosure may be provided as methods, systems, or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present disclosure may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage and optical storage, etc.) containing computer-usable program code.

[0382] The present disclosure is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present disclosure. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer-executable instructions. These computer-executable instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0383] These processor-executable instructions may also be stored in a processor-readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the processor-readable memory produce a product including an instruction device that implements the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0384] Obviously, those skilled in the art may make various changes and modifications to the present disclosure without departing from the spirit and scope of the present disclosure. Thus, if these modifications and variations of the present disclosure fall within the scope of the claims of the present disclosure and their equivalents, the present disclosure is intended to include these modifications and variations.

Claims

1. A method for predicting channel state information (CSI), wherein, The method is applied to a user equipment UE, and the method includes: Receiving a downlink reference signal sent by a base station, and estimating a first downlink CSI and downlink communication environment parameters based on the downlink reference signal; Predicting a second downlink CSI corresponding to a time when the base station transmits a physical downlink shared channel PDSCH according to the first downlink CSI, the downlink communication environment parameters, and a pre-trained CSI prediction model; Sending the second downlink CSI to the base station.

2. The method according to claim 1, wherein The predicting the second downlink CSI corresponding to the time when the base station transmits the PDSCH according to the first downlink CSI, the downlink communication environment parameters, and a pre-trained CSI prediction model includes: Determining a prediction time interval according to the downlink communication environment parameters, a first time parameter provided by the UE stored in advance, and a second time parameter provided by the base station; Predicting a second downlink CSI corresponding to the time when the base station transmits the PDSCH according to the first downlink CSI, the prediction time interval, and a pre-trained CSI prediction model.

3. The method according to claim 1, wherein The determining the prediction time interval according to the downlink communication environment parameters, a first time parameter provided by the UE stored in advance, and a second time parameter provided by the base station includes: Determining a transmission time of the downlink reference signal according to the downlink communication environment parameters; Determining a transmission time of the second downlink CSI according to the downlink communication environment parameters and the first time parameter; Determining the prediction time interval according to the transmission time of the downlink reference signal, the transmission time of the second downlink CSI, the first time parameter, and the second time parameter.

4. The method according to claim 3, wherein, The downlink communication environment parameters at least include at least one or more of a moving speed v of the UE, a moving azimuth angle θ of the UE relative to the base station, and a relative distance S0 between the UE and the base station; The determining the transmission time T1 of the downlink reference signal according to the downlink communication environment parameters: T1 = S0 / c; wherein, T1 represents the transmission time of the downlink reference signal, S0 represents the relative distance between the UE and the base station when the base station transmits the downlink reference signal, and c represents the speed of light; or, Determine the transmission time T2 of the second downlink CSI according to the downlink communication environment parameters and the first time parameter: wherein, T2 represents the transmission time of the second downlink CSI, v represents the moving speed of the UE, θ represents the moving azimuth angle of the UE relative to the base station, and t1 represents the first time parameter.

5. The method according to claim 1, wherein, The sending the second downlink CSI to the base station includes: Obtaining a compressed second downlink CSI according to the second downlink CSI, a preset compression ratio, and a pre-trained CSI compression model; Sending the compressed second downlink CSI and the compression ratio to the base station.

6. The method according to claim 1 or 5, wherein The first time parameter is the time interval from the last symbol of a physical downlink control channel PDCCH that triggers CSI reporting to the reporting of the second downlink CSI; the second time parameter includes the time for scheduling the PDSCH and preparing the PDSCH; Or, The first time parameter is the time interval from the last symbol of the PDCCH that triggers CSI reporting to the reporting of the compressed second downlink CSI; the second time parameter includes the decompression time of the compressed second downlink CSI and the time for scheduling and preparing the PDSCH.

7. The method according to claim 2, wherein, The method further includes: Determining the time interval level corresponding to the predicted time interval according to the correspondence between the time interval and the time interval level sent by the base station.

8. The method according to claim 2 or 7, wherein The method further includes: Sending time indication information to the base station; the time indication information is the predicted time interval, or the time indication information is the time interval level corresponding to the predicted time interval.

9. The method according to claim 2, wherein The predicting the second downlink CSI corresponding to the PDSCH transmission moment of the base station according to the first downlink CSI, the predicted time interval, and a pre-trained CSI prediction model includes: Obtaining a preset number of historical downlink CSIs; Predicting the second downlink CSI corresponding to the PDSCH transmission moment of the base station according to the first downlink CSI, each of the historical downlink CSIs, the predicted time interval, and a pre-trained CSI prediction model.

10. The method according to claim 1, wherein, Obtaining the CSI prediction model through the following manner, including: Obtaining a basic data set, where the basic data set contains the historical downlink CSIs of the UE; Respectively determining the training data set and the label data set corresponding to each predicted time interval in the basic data set; Training an initial CSI prediction model based on each of the training data sets, each of the label data sets, and each of the predicted time intervals to obtain a trained CSI prediction model.

11. The method according to claim 10, wherein, The determining the training data set and the label data set corresponding to each predicted time interval includes: Determining a plurality of first historical downlink CSI groups corresponding to each predicted time interval, where each of the first historical downlink CSI groups includes a first historical downlink CSI and a second historical downlink CSI, and the difference in the channel estimation moments of the first historical downlink CSI and the second historical downlink CSI is the predicted time interval; Determining the plurality of first historical downlink CSIs as the training data set and determining the plurality of second historical downlink CSIs as the label data set.

12. The method according to claim 10, wherein, The determining the training data set and the label data set corresponding to each predicted time interval includes: Determining a plurality of second historical downlink CSI groups corresponding to each predicted time interval, where each of the second historical downlink CSI groups includes a third historical downlink CSI, a fourth historical downlink CSI, and a preset number of fifth historical downlink CSIs, the difference in the channel estimation moments of the third historical downlink CSI and the fourth historical downlink CSI is the predicted time interval, and the channel estimation moments of the preset number of fifth historical downlink CSIs are earlier than the channel estimation moment of the third historical downlink CSI; Determining the plurality of third historical downlink CSIs and each of the fifth historical downlink CSIs corresponding to the third historical downlink CSI as the training data set and determining the plurality of fourth historical downlink CSIs as the label data set.

13. The method according to claim 5, wherein The CSI compression model is trained in the following manner, including: Determine the historical downlink CSI of the UE as the third training data set; Determine the compressed and quantized historical downlink CSI using a measurement matrix based on compressive sensing as the third label data set; Based on the third training data set and the third label data set, train the initial CSI compression model to obtain the trained CSI compression model.

14. A method for predicting channel state information (CSI), wherein, The method is applied to a base station and includes: Send a downlink reference signal to a user equipment (UE); Obtain the predicted downlink CSI of the UE; Perform scheduling based on the downlink CSI and send a physical downlink shared channel (PDSCH) to the UE.

15. The method according to claim 14, wherein, The obtaining of the predicted downlink CSI of the UE includes: Receive the compressed downlink CSI and the compression ratio sent by the UE; Obtain the downlink CSI according to the compressed downlink CSI, the compression ratio, and a pre-trained CSI decompression model.

16. The method according to claim 14, wherein, The method further includes: Receive time indication information sent by the UE; the time indication information is a predicted time interval determined by the UE, or the time indication information is a time interval level corresponding to the predicted time interval determined by the UE.

17. The method according to claim 16, wherein, In the case where the time indication information is a time interval level corresponding to the predicted time interval determined by the UE, the method further includes: In the correspondence between time intervals and time interval levels, determine the time interval corresponding to the time indication information, and within the time interval corresponding to the time indication information, determine the predicted time interval by randomly selecting a value or taking the median.

18. The method according to claim 14, wherein The method further includes: Determine a predicted time interval range according to a pre-stored range of downlink communication environment parameters of the UE, a first time parameter range provided by the UE, and a second time parameter range provided by the base station; Divide the predicted time interval range according to a preset level division rule to obtain the correspondence between time intervals and time interval levels; Send the correspondence between time intervals and time interval levels to the UE.

19. A user equipment UE, wherein, Includes a memory, a transceiver, and a processor; Wherein, the memory is used to store a computer program; the transceiver is used to transmit and receive data under the control of the processor, and the processor is used to read the computer program in the memory and perform the following operations: Receive a downlink reference signal sent by the base station and, based on the downlink reference signal, estimate a first downlink CSI and downlink communication environment parameters; According to the first downlink CSI, the downlink communication environment parameters, and a pre-trained CSI prediction model, predict a second downlink CSI corresponding to the time when the base station sends a physical downlink shared channel (PDSCH); Send the second downlink CSI to the base station.

20. The UE according to claim 19, wherein The predicting of the second downlink CSI corresponding to the time when the base station sends a PDSCH according to the first downlink CSI, the downlink communication environment parameters, and a pre-trained CSI prediction model includes: Determine a prediction time interval according to the downlink communication environment parameters, the first time parameter provided by the UE and stored in advance, and the second time parameter provided by the base station. Predict a second downlink CSI corresponding to the PDSCH transmission time of the base station according to the first downlink CSI, the prediction time interval, and a pre-trained CSI prediction model.

21. The UE according to claim 19, wherein The determining the prediction time interval according to the downlink communication environment parameters, the first time parameter provided by the UE and stored in advance, and the second time parameter provided by the base station includes: Determine the transmission time of the downlink reference signal according to the downlink communication environment parameters. Determine the transmission time of the second downlink CSI according to the downlink communication environment parameters and the first time parameter. Determine the prediction time interval according to the transmission time of the downlink reference signal, the transmission time of the second downlink CSI, the first time parameter, and the second time parameter.

22. The UE according to claim 21, wherein, The downlink communication environment parameters include at least one or more of the moving speed v of the UE, the moving azimuth angle θ of the UE relative to the base station, and the relative distance between the UE and the base station. The determining the transmission time T1 of the downlink reference signal according to the downlink communication environment parameters: T1 = S0 / c; Wherein, T1 represents the transmission time of the downlink reference signal, S0 represents the relative distance between the UE and the base station when the base station transmits the downlink reference signal, and c represents the speed of light; alternatively, determining the transmission time T2 of the second downlink CSI according to the downlink communication environment parameter and the first time parameter: where T2 represents the transmission time of the second downlink CSI, v represents the moving speed of the UE, θ represents the moving azimuth angle of the UE relative to the base station, and t1 represents the first time parameter.

23. The UE according to claim 19, wherein The sending the second downlink CSI to the base station includes: Obtain a compressed second downlink CSI according to the second downlink CSI, a preset compression ratio, and a pre-trained CSI compression model. Send the compressed second downlink CSI and the compression ratio to the base station.

24. The UE according to claim 19 or 23, wherein The first time parameter is the time interval between the last symbol of the physical downlink shared channel PDCCH that triggers CSI reporting and the reporting of the second downlink CSI; the second time parameter includes the time for scheduling the PDSCH and preparing the PDSCH. Or, The first time parameter is the time interval between the last symbol of the PDCCH that triggers CSI reporting and the reporting of the compressed second downlink CSI; the second time parameter includes the decompression time of the compressed second downlink CSI and the time for scheduling the PDSCH and preparing the PDSCH.

25. The UE according to claim 20, wherein, The processor is further configured to read a computer program in the memory and perform the following operations: Determine the time interval level corresponding to the prediction time interval according to the correspondence between the time interval sent by the base station and the time interval level.

26. The UE according to claim 20 or 25, wherein, The processor is further configured to read a computer program in the memory and perform the following operations: Send time indication information to the base station; the time indication information is the prediction time interval, or the time indication information is the time interval level corresponding to the prediction time interval.

27. The UE according to claim 20, wherein Predicting a second downlink CSI corresponding to the PDSCH transmission time of the base station according to the first downlink CSI, the predicted time interval, and a pre-trained CSI prediction model includes: Obtaining a preset number of historical downlink CSIs; Predicting a second downlink CSI corresponding to the PDSCH transmission time of the base station according to the first downlink CSI, each of the historical downlink CSIs, the predicted time interval, and a pre-trained CSI prediction model.

28. A base station, wherein, Including a memory, a transceiver, and a processor; Wherein, the memory is used for storing a computer program; the transceiver is used for transceiving data under the control of the processor, and the processor is used for reading the computer program in the memory and performing the following operations: Sending a downlink reference signal to a user equipment UE; Obtaining the downlink CSI predicted by the UE; Performing scheduling according to the downlink CSI and sending a physical downlink shared channel PDSCH to the UE.

29. A prediction device for channel state information (CSI), wherein, The device is applied to a user equipment UE, and the device includes: An estimation unit, configured to receive a downlink reference signal sent by a base station, and estimate a first downlink CSI and downlink communication environment parameters based on the downlink reference signal; A prediction unit, configured to predict a second downlink CSI corresponding to the PDSCH transmission time of the base station according to the first downlink CSI, the downlink communication environment parameters, and a pre-trained CSI prediction model; A first sending unit, configured to send the second downlink CSI to the base station.

30. A prediction device for channel state information (CSI), wherein, The device is applied to a base station, and the device includes: A first sending unit, configured to send a downlink reference signal to a user equipment UE; An obtaining unit, configured to obtain the downlink CSI predicted by the UE; A second sending unit, configured to perform scheduling according to the downlink CSI and send a physical downlink shared channel PDSCH to the UE.

31. A computer-readable storage medium having a computer program stored thereon, wherein, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 13, or 14 to 19 are implemented.

Images