Channel state information reporting method and apparatus, electronic device, chip, and medium

Abstract

The present disclosure relates to a channel state information reporting method and device, electronic equipment, chip and medium, wherein the method comprises: obtaining a plurality of historical channel coefficient matrices of a target channel, and a preprocessing matrix corresponding to a current Doppler position of the target channel; filtering the plurality of historical channel coefficient matrices according to the preprocessing matrix to obtain preprocessing data at a current time point; determining a predicted channel coefficient matrix at the current time point according to the preprocessing data and a channel coefficient matrix prediction model; and determining and reporting channel state information (CSI) in combination with the predicted channel coefficient matrix; wherein predicting the channel coefficient matrix at the current time point in combination with the plurality of historical channel coefficient matrices of the target channel can shorten the reporting period of the CSI information, increase the reporting frequency of the CSI information, and avoid the situation that the CSI information is out of date, thereby ensuring the channel throughput.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of communication, and particularly relates to a channel state information reporting method and device, electronic equipment, chip and medium. BACKGROUND

[0002] At present, the reporting process of channel state information (CSI) mainly includes that a terminal device receives a channel state information-reference signal (CSI-RS) configured by a network device; performs measurement processing on the CSI-RS signal to obtain a channel coefficient matrix, and then determines and reports CSI information.

[0003] In the above scheme, the reporting period of the CSI information is long, and the CSI information is likely to be out of date, which is difficult to ensure the channel throughput. SUMMARY

[0004] The present disclosure provides a channel state information reporting method and device, electronic equipment, chip and medium.

[0005] According to a first aspect of an embodiment of the present disclosure, a channel state information reporting method is provided, which includes: obtaining a plurality of historical channel coefficient matrices of a target channel, and a pre-processing matrix corresponding to a current Doppler gear of the target channel; performing filtering processing on the plurality of historical channel coefficient matrices according to the pre-processing matrix to obtain pre-processing data at a current time point; determining a predicted channel coefficient matrix at the current time point according to the pre-processing data and a channel coefficient matrix prediction model; and combining the predicted channel coefficient matrix to determine and report channel state information (CSI).

[0006] In one embodiment of the present disclosure, the obtaining of the plurality of historical channel coefficient matrices of the target channel and the pre-processing matrix corresponding to the current Doppler gear of the target channel includes: obtaining the plurality of historical channel coefficient matrices of the target channel; determining the current Doppler gear of the target channel; and querying a matrix database according to the current Doppler gear to obtain the pre-processing matrix corresponding to the current Doppler gear in the matrix database.

[0007] In an embodiment of the present disclosure, the determining manner of the matrix database comprises: determining a value of a Doppler-related parameter adapted to each Doppler bin; for each Doppler bin, determining a distribution function of a channel coefficient matrix related value in combination with the value of the Doppler-related parameter adapted to the Doppler bin; generating a plurality of reference channel coefficient matrices according to the distribution function; determining a pre-processing matrix corresponding to the Doppler bin according to the plurality of reference channel coefficient matrices; and determining the matrix database according to the pre-processing matrix corresponding to each Doppler bin.

[0008] In an embodiment of the present disclosure, the Doppler-related parameter comprises at least one of the following: a Doppler frequency, a symbol time difference value between channel coefficient matrices.

[0009] In an embodiment of the present disclosure, the distribution function comprises at least one of the following: a Bessel function, an approximate sampling function.

[0010] In an embodiment of the present disclosure, after filtering the plurality of historical channel coefficient matrices according to the pre-processing matrix to obtain pre-processed data at a current time point, the method further comprises: performing inverse fast Fourier transform processing on the pre-processed data to obtain first transformed data; performing zero processing on a first value less than or equal to a threshold value in the first transformed data to obtain processed data; performing fast Fourier transform processing on the processed data to obtain second transformed data; and updating the pre-processed data according to the second transformed data.

[0011] In an embodiment of the present disclosure, the determining the predicted channel coefficient matrix at the current time point according to the pre-processed data and a channel coefficient matrix prediction model comprises: obtaining a channel characteristic parameter of the target channel; inputting the pre-processed data and the channel characteristic parameter into the channel coefficient matrix prediction model to obtain the predicted channel coefficient matrix output by the channel coefficient matrix prediction model.

[0012] In an embodiment of the present disclosure, the channel characteristic parameter comprises at least one of the following: the current Doppler frequency offset, channel delay spread, and channel spatial correlation.

[0013] In an embodiment of the present disclosure, the channel coefficient matrix prediction model is trained in combination with a plurality of channel coefficient matrix sequences; and a number of sample channel coefficient matrices in the channel coefficient matrix sequence is greater than a number of historical channel coefficient matrices used in channel coefficient matrix prediction.

[0014] According to a second aspect of the embodiments of the present disclosure, a device for reporting channel state information is further provided. The device comprises: an acquisition module configured to acquire a plurality of historical channel coefficient matrices of a target channel and a pre-processing matrix corresponding to a current Doppler bin of the target channel; a filtering processing module configured to perform filtering processing on the plurality of historical channel coefficient matrices according to the pre-processing matrix to obtain pre-processed data at a current time point; a determination module configured to determine a predicted channel coefficient matrix at the current time point according to the pre-processed data and a channel coefficient matrix prediction model; and a reporting processing module configured to determine and report channel state information (CSI) in combination with the predicted channel coefficient matrix.

[0015] In one embodiment of the present disclosure, the acquisition module is specifically configured to acquire a plurality of historical channel coefficient matrices of the target channel; determine a current Doppler bin of the target channel; and acquire, according to the current Doppler bin, a pre-processing matrix corresponding to the current Doppler bin in a matrix database.

[0016] In one embodiment of the present disclosure, the determination manner of the matrix database comprises: determining a value of a Doppler-related parameter adapted to each Doppler bin; for each Doppler bin, determining a distribution function of a channel coefficient matrix-related value in combination with the value of the Doppler-related parameter adapted to the Doppler bin; generating a plurality of reference channel coefficient matrices according to the distribution function; determining a pre-processing matrix corresponding to the Doppler bin according to the plurality of reference channel coefficient matrices; and determining the matrix database according to the pre-processing matrix corresponding to each Doppler bin.

[0017] In one embodiment of the present disclosure, the Doppler-related parameter comprises at least one of the following: a Doppler frequency, and a symbol time difference value between channel coefficient matrices.

[0018] In one embodiment of the present disclosure, the distribution function comprises at least one of the following: a Bessel function, and an approximate sampling function.

[0019] In one embodiment of the present disclosure, the device further comprises a first transform module, a zero processing module, a second transform module, and an update processing module. The first transform module is configured to perform inverse fast Fourier transform processing on the pre-processed data to obtain first transformed data. The zero processing module is configured to perform zero processing on a first value less than or equal to a threshold value in the first transformed data to obtain processed data. The second transform module is configured to perform fast Fourier transform processing on the processed data to obtain second transformed data. The update processing module is configured to perform update processing on the pre-processed data according to the second transformed data.

[0020] In an embodiment of the present disclosure, the determining module is specifically configured to: acquire a channel characteristic parameter of the target channel; input the preprocessed data and the channel characteristic parameter into the channel coefficient matrix prediction model to acquire the predicted channel coefficient matrix output by the channel coefficient matrix prediction model.

[0021] In an embodiment of the present disclosure, the channel characteristic parameter comprises at least one of the following: the current Doppler frequency offset, channel delay spread, and channel spatial correlation.

[0022] In an embodiment of the present disclosure, the channel coefficient matrix prediction model is trained in combination with a plurality of channel coefficient matrix sequences; and the number of sample channel coefficient matrices in the channel coefficient matrix sequence is greater than the number of historical channel coefficient matrices used in channel coefficient matrix prediction.

[0023] According to a third aspect of the embodiments of the present disclosure, an electronic device is further provided, which comprises a processor, a memory for storing instructions executable by the processor, and wherein the processor is configured to implement the steps of the reporting method of channel state information as described above.

[0024] According to a fourth aspect of the embodiments of the present disclosure, a non-transitory computer-readable storage medium is further provided, which, when the instructions stored in the storage medium are executed by a processor, enables the processor to perform the reporting method of channel state information as described above.

[0025] According to a fifth aspect of the embodiments of the present disclosure, a chip is further provided, which comprises one or more interface circuits and one or more processors; the interface circuit is configured to receive a signal, and the signal comprises computer instructions, when the processor executes the computer instructions, the chip performs the reporting method of channel state information as described above.

[0026] The technical solutions provided by the embodiments of the present disclosure at least bring the following beneficial effects:

[0027] By acquiring a plurality of historical channel coefficient matrices of a target channel and a preprocessed matrix corresponding to a current Doppler shift of the target channel, performing filtering processing on the plurality of historical channel coefficient matrices according to the preprocessed matrix to obtain preprocessed data at a current time point, determining a predicted channel coefficient matrix at the current time point according to the preprocessed data and a channel coefficient matrix prediction model, and performing determination and reporting processing of channel state information (CSI) in combination with the predicted channel coefficient matrix, the reporting period of the CSI information can be shortened, the reporting frequency of the CSI information can be increased, and the situation that the CSI information is out of date can be avoided, so that the channel throughput can be ensured.

[0028] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0029] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure, and are not intended to unduly limit this disclosure.

[0030] Figure 1 This is a flowchart of a channel state information reporting method according to an embodiment of the present disclosure;

[0031] Figure 2 This is a flowchart of a channel state information reporting method according to another embodiment of the present disclosure;

[0032] Figure 3 This is a flowchart of a channel state information reporting method according to another embodiment of the present disclosure;

[0033] Figure 4 This is a schematic diagram of the structure of a channel state information reporting device according to an embodiment of the present disclosure;

[0034] Figure 5 This is a structural block diagram of an electronic device according to an exemplary embodiment of the present disclosure;

[0035] Figure 6 This is a schematic diagram of the structure of a chip according to an embodiment of the present disclosure. Detailed Implementation

[0036] To enable those skilled in the art to better understand the technical solutions of this disclosure, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0037] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0038] Currently, the reporting process of channel state information (CSI) mainly includes that a terminal device receives a channel state information-reference signal (CSI-RS) configured by a network device, performs measurement and processing on the CSI-RS signal to obtain a channel coefficient matrix, and then determines and reports the CSI information.

[0039] In the above scheme, the reporting period of the CSI information is long, and the CSI information is likely to be out of date, which makes it difficult to ensure the channel throughput.

[0040] Figure 1 A flowchart of a channel state information reporting method according to an embodiment of the present disclosure. It should be noted that the channel state information reporting method according to the present embodiment can be applied to a channel state information reporting device, which can be configured in an electronic device or a chip, so that the electronic device or the chip can perform the channel state information reporting function.

[0041] The electronic device can be any device with computing capability, such as a personal computer (PC), a mobile terminal, a terminal device, a server, etc. The mobile terminal can be, for example, a vehicle-mounted device, a mobile phone, a tablet computer, a personal digital assistant, a wearable device, etc. The mobile terminal can have various operating systems, touch screens and / or display screens.

[0042] In addition, the channel state information reporting device can also be software in the electronic device, etc. The software can be, for example, channel state information reporting software, etc. In the following embodiments, the execution subject is taken as an example of a terminal device.

[0043] As shown in FIG. 1, the method includes the following steps: Figure 1

[0044] In step 101, a plurality of historical channel coefficient matrices of a target channel and a pre-processing matrix corresponding to a current Doppler gear of the target channel are obtained.

[0045] In the present embodiment, the process of step 101 performed by the terminal device can be, for example, obtaining a plurality of historical channel coefficient matrices of a target channel; determining a current Doppler gear of the target channel; and querying a matrix database according to the current Doppler gear to obtain a pre-processing matrix corresponding to the current Doppler gear in the matrix database.

[0046] The target channel can be a channel that needs to be reported at other time points in addition to the CSI reporting in combination with the CSI-RS channel. ​

[0047] In the embodiments of the present disclosure, the interval symbol time between the historical symbol time of the plurality of historical channel coefficient matrices can be the same or different.

[0048] In an example, in the case that the interval symbol time between the historical symbol time of the plurality of historical channel coefficient matrices is different, the terminal device can determine the current Doppler gear in combination with the current Doppler frequency. Different Doppler gears can correspond to different Doppler frequencies.

[0049] In another example, in the case that the interval symbol time between the historical symbol time of the plurality of historical channel coefficient matrices is the same, the terminal device can determine the current Doppler gear in combination with the interval symbol time between the historical symbol time of the plurality of historical channel coefficient matrices and the current Doppler frequency. Different Doppler gears can correspond to different Doppler frequencies and / or different interval symbol times.

[0050] In the embodiments of the present disclosure, the matrix database can include a plurality of pre-processing matrices. Different pre-processing matrices can correspond to different Doppler gears.

[0051] In combination with the current Doppler gear of the target channel, the matrix database is queried to obtain a pre-processing matrix, and the plurality of historical channel coefficient matrices are filtered based on the pre-processing matrix, which can reduce the processing amount when the pre-processing matrix is obtained, thereby further improving the determination efficiency of the CSI information.

[0052] In step 102, the plurality of historical channel coefficient matrices are filtered based on the pre-processing matrix to obtain pre-processing data at the current time point.

[0053] In the embodiments of the present disclosure, it is assumed that the plurality of historical channel coefficient matrices are historical channel coefficient matrices at symbol time in a plurality of consecutive time slots. That is, in the plurality of consecutive time slots, a historical channel coefficient matrix is determined at the symbol time in each time slot. The current time point can be a symbol time in a time slot after the plurality of consecutive time slots. Based on the above assumption, the determination formula of the pre-processing data at the current time point can be as shown in the following formula (1).

[0054]

[0055] Wherein, x0(t), x1(t),..., x N-1 (t) represents the historical channel coefficient matrix at the symbol time in the consecutive N time slots. G bessel represents the pre-processing matrix. represents the pre-processing data.

[0056] In step 103, a predicted channel coefficient matrix at the current time point is determined according to the preprocessed data and the channel coefficient matrix prediction model.

[0057] In the embodiments of the present disclosure, the process performed by the terminal device in step 103 may, for example, be that: a channel characteristic parameter of the target channel is acquired; the preprocessed data and the channel characteristic parameter are input into the channel coefficient matrix prediction model, and a predicted channel coefficient matrix output by the channel coefficient matrix prediction model is acquired.

[0058] In the embodiments of the present disclosure, the channel characteristic parameter may include at least one of: a current Doppler frequency offset, a channel delay spread, and a channel spatial correlation. The current Doppler frequency offset may refer to a Doppler frequency offset at the current time point. The Doppler frequency offset refers to a change in phase and frequency caused by a difference in propagation distance when a mobile station moves at a constant speed in a certain direction.

[0059] The channel delay spread refers to a difference in signal arrival time caused by multipath propagation. The channel spatial correlation refers to a correlation between channel values corresponding to different transmit antennas.

[0060] The channel coefficient matrix prediction model has a large number of parameters and high accuracy. Inputting the preprocessed data and the channel characteristic parameter into the channel coefficient matrix prediction model and acquiring a predicted channel coefficient matrix output by the channel coefficient matrix prediction model can improve the accuracy of the determined predicted channel coefficient matrix, thereby further improving the accuracy of the reported CSI information and further improving the channel throughput.

[0061] In the embodiments of the present disclosure, the channel coefficient matrix prediction model is trained in combination with a plurality of channel coefficient matrix sequences. The number of sample channel coefficient matrices in the channel coefficient matrix sequence is greater than the number of historical channel coefficient matrices used in channel coefficient matrix prediction.

[0062] Specifically, the channel coefficient matrix prediction model may be trained in combination with a plurality of channel coefficient matrix sequences and related channel characteristic parameters. The N+1 channel coefficient matrices in the channel coefficient matrix sequence may be acquired. The first N channel coefficient matrices and related channel characteristic parameters are input into an initial channel coefficient matrix prediction model, and an N+1 predicted channel coefficient matrix output by the channel coefficient matrix prediction model is acquired. A loss function value is determined according to the N+1 predicted channel coefficient matrix, the N+1 channel coefficient matrix, and a loss function of the channel coefficient matrix prediction model. The channel coefficient matrix prediction model is adjusted in parameter according to the loss function value, and training is realized.

[0063] The channel coefficient matrix prediction model can be trained in combination with a plurality of channel coefficient matrix sequences and related channel characteristic parameters. The plurality of channel coefficient matrices in the channel coefficient matrix sequence can be a plurality of consecutive channel coefficient matrices of the target channel or other channels, which can reflect the change trend of the channel coefficient matrix, so that the channel coefficient matrix prediction model can learn the change trend, thereby further improving the prediction accuracy of the channel coefficient matrix prediction model.

[0064] In step 104, the channel state information (CSI) is determined and reported in combination with the predicted channel coefficient matrix.

[0065] In the embodiments of the present disclosure, the terminal device can determine the CSI information in combination with the predicted channel coefficient matrix, and perform reporting processing on the determined CSI information.

[0066] The CSI information can include at least one of the following: a predicted channel coefficient matrix, a channel quality indicator (CQI), a rank indicator (RI), a precoding matrix indicator (PMI), and the like.

[0067] In the reporting method of the channel state information according to the embodiments of the present disclosure, a plurality of historical channel coefficient matrices of a target channel and a pre-processing matrix corresponding to a current Doppler position of the target channel are obtained; the plurality of historical channel coefficient matrices are filtered according to the pre-processing matrix to obtain pre-processing data at a current time point; a predicted channel coefficient matrix at the current time point is determined according to the pre-processing data and a channel coefficient matrix prediction model; the channel state information (CSI) is determined and reported in combination with the predicted channel coefficient matrix; the channel coefficient matrix at the current time point is predicted in combination with the plurality of historical channel coefficient matrices of the target channel, which can shorten the reporting period of the CSI information, increase the reporting frequency of the CSI information, and avoid the situation that the CSI information is out of date, thereby ensuring the channel throughput.

[0068] Figure 2 A flowchart of the reporting method of the channel state information according to another embodiment of the present disclosure is shown. It should be noted that the reporting method of the channel state information according to the present embodiment can be applied to a reporting device of the channel state information. The device can be configured in an electronic device or a chip, so that the electronic device or the chip can perform the reporting function of the channel state information.

[0069] Among them, electronic devices can be any device with computing capabilities, such as personal computers (PCs), mobile terminals, terminal devices, servers, etc. Mobile terminals can be, for example, in-vehicle devices, mobile phones, tablets, personal digital assistants, wearable devices, and other hardware devices with various operating systems, touch screens, and / or displays.

[0070] In addition, the channel state information reporting device can also be software in electronic devices. For example, software can be used to report channel state information. The following embodiments use a terminal device as an example for explanation.

[0071] like Figure 2 As shown, the method includes the following steps:

[0072] Step 201: Determine the values ​​of the Doppler-related parameters that are compatible with each Doppler setting.

[0073] In this embodiment of the disclosure, the Doppler-related parameters may include at least one of the following: Doppler frequency and symbol time difference between the channel coefficient matrix. Different Doppler frequencies and / or different symbol time differences correspond to different Doppler levels.

[0074] Step 202: For each Doppler level, determine the distribution function of the channel coefficient matrix correlation value by combining the values ​​of the Doppler correlation parameters adapted to the Doppler level.

[0075] In this embodiment of the disclosure, the correlation value of the channel coefficient matrix refers to the degree of correlation between the elements in the channel coefficient matrix. This degree of correlation reflects the regularity or similarity of the channel's changes under different time, frequency, spatial and other dimensions.

[0076] The distribution function may include at least one of the following: a Bessel function or an approximate sampling function. The Bessel function can be expressed as J0(2πf d Δt). Where, f d Let represent the Doppler frequency; Δt represents the symbol time difference between the channel coefficient matrices. The approximate sampling function can be expressed as sinc(2πf). d Δt).

[0077] The ability to set multiple distribution functions allows terminal devices to flexibly select the distribution function according to actual needs for determining the preprocessing matrix.

[0078] Step 203: Generate multiple reference channel coefficient matrices based on the distribution function.

[0079] Step 204, determining the pre-processing matrix corresponding to the Doppler bin according to the plurality of reference channel coefficient matrices.

[0080] In the embodiments of the present disclosure, it should be noted that the number of generated reference channel coefficient matrices can be greater than the number of historical channel coefficient matrices used in channel coefficient matrix prediction, that is, the number of historical channel coefficient matrices in step 206. For example, if the number of historical channel coefficient matrices used in channel coefficient matrix prediction is N, then the number of reference channel coefficient matrices can be N+1.

[0081] In the embodiments of the present disclosure, the interval symbol time between each adjacent reference channel coefficient matrix in the plurality of generated reference channel coefficient matrices can be the same, which is the symbol time difference in the distribution function.

[0082] Wherein, it is assumed that the number of the plurality of reference channel coefficient matrices is N+1, which corresponds to the channel coefficient matrices on the symbol time in the continuous N+1 time slots. Based on the above assumption, the determination formula of the pre-processing matrix can be, for example, as shown in the following formula (2).

[0083] G bessel = x N (t)[x0(t)x1(t)...x N-1 (t)] T |x0(t)x1(t)...x N-1 (t) -2 (2)

[0084] Wherein, G bessel represents the pre-processing matrix; x N (t) represents the N+1th reference channel coefficient matrix; x0(t)x1(t)...x N-1 (t) represents the first N reference channel coefficient matrices.

[0085] Step 205, determining the matrix database according to the pre-processing matrix corresponding to each Doppler bin.

[0086] In the embodiments of the present disclosure, the terminal device can perform combination processing on each Doppler bin and the corresponding pre-processing matrix to obtain the matrix database.

[0087] Step 206, obtaining a plurality of historical channel coefficient matrices of a target channel and a current Doppler bin of the target channel.

[0088] Step 207, querying the matrix database according to the current Doppler bin to obtain the pre-processing matrix corresponding to the current Doppler bin in the matrix database.

[0089] Step 208, filtering processing is performed on the plurality of historical channel coefficient matrices according to the preprocessing matrix, to obtain preprocessing data at the current time point.

[0090] Step 209, a predicted channel coefficient matrix at the current time point is determined according to the preprocessing data and a channel coefficient matrix prediction model.

[0091] Step 210, channel state information (CSI) determination and reporting processing is performed in combination with the predicted channel coefficient matrix.

[0092] It should be noted that the detailed description of steps 206 to 210 can refer to steps 101 to 104 in the embodiment shown in Figure 1 and will not be described in detail here.

[0093] In the channel state information reporting method of the embodiment of the present disclosure, the value of the Doppler-related parameter adapted to each Doppler bin is determined; for each Doppler bin, the distribution function of the channel coefficient matrix related value is determined in combination with the value of the Doppler-related parameter adapted to the Doppler bin; the plurality of reference channel coefficient matrices is generated according to the distribution function; the preprocessing matrix corresponding to the Doppler bin is determined according to the plurality of reference channel coefficient matrices; the matrix database is determined according to the preprocessing matrix corresponding to each Doppler bin; the plurality of historical channel coefficient matrices of the target channel and the current Doppler bin of the target channel are obtained; the preprocessing matrix corresponding to the current Doppler bin in the matrix database is obtained by querying the matrix database according to the current Doppler bin; the preprocessing data at the current time point is obtained by performing filtering processing on the plurality of historical channel coefficient matrices according to the preprocessing matrix; the predicted channel coefficient matrix at the current time point is determined according to the preprocessing data and the channel coefficient matrix prediction model; the channel state information (CSI) determination and reporting processing is performed in combination with the predicted channel coefficient matrix; wherein the distribution function of the channel coefficient matrix related value is determined in combination with the value of the Doppler-related parameter adapted to the Doppler bin; and then the plurality of reference channel coefficient matrices is generated for preprocessing matrix generation processing, so that the terminal device can directly query and obtain the preprocessing matrix in combination with the current Doppler bin, and perform channel coefficient matrix prediction processing, which can determine the preprocessing matrix in advance, thereby shortening the prediction time of the channel coefficient matrix, improving the prediction efficiency of the coefficient matrix, and further improving the reporting speed of the CSI information, and further avoiding the out-of-date situation of the CSI information.

[0094] Figure 3 The flowchart of the channel state information reporting method of another embodiment of the present disclosure is shown. It should be noted that the channel state information reporting method of the present embodiment can be applied to a channel state information reporting device, which can be configured in an electronic device or a chip, so that the electronic device or the chip can perform the channel state information reporting function.

[0095] The electronic device can be any device with computing capability, such as a personal computer (PC), a mobile terminal, a terminal device, a server, and the like. The mobile terminal can be, for example, a vehicle-mounted device, a mobile phone, a tablet computer, a personal digital assistant, a wearable device, and the like, which are hardware devices with various operating systems, touch screens, and / or display screens.

[0096] In addition, the channel state information reporting device can also be software in the electronic device, such as channel state information reporting software, and the like. In the following embodiments, the execution subject is taken as an example of a terminal device.

[0097] As shown in FIG. 1, the method includes the following steps: Figure 3

[0098] In step 301, a plurality of historical channel coefficient matrices of a target channel and a pre-processing matrix corresponding to a current Doppler bin of the target channel are obtained.

[0099] In step 302, the plurality of historical channel coefficient matrices are filtered according to the pre-processing matrix to obtain pre-processed data at a current time point.

[0100] In step 303, inverse fast Fourier transform processing is performed on the pre-processed data to obtain first transformed data.

[0101] In the embodiments of the present disclosure, the inverse fast Fourier transform formula of the pre-processed data can be as shown in the following formula (3).

[0102]

[0103] wherein, represents the pre-processed data; IFFT represents inverse fast Fourier transform processing; represents the first transformed data.

[0104] It should be noted that the inverse fast Fourier transform processing is a transformation processing from frequency domain data to time domain data, that is, each frequency component in the data is converted into a time domain signal.

[0105] In step 304, the first values in the first transformed data that are less than or equal to a threshold value are set to zero to obtain processed data.

[0106] In the embodiments of the present disclosure, as an alternative to step 304, the terminal device can perform deletion processing and the like on the first values in the first transformed data that are less than or equal to the threshold value.

[0107] ​In the embodiments of the present disclosure, the formula for performing the first numerical zero processing on the first transformed data can be as shown in the following formula (4).

[0108]

[0109] wherein TH represents a threshold value; Find represents finding a value greater than the threshold value in the first transformed data, that is, performing the zero processing or the deletion processing on the first value less than or equal to the threshold value; represents the processed data.

[0110] In step 305, the fast Fourier transform processing is performed on the processed data to obtain second transformed data.

[0111] wherein the zero processing or the deletion processing on the first value in the first transformed data can reduce the data amount in the first transformed data, and the fast Fourier transform processing can reduce the data amount in the second transformed data.

[0112] wherein it is to be noted that the fast Fourier transform processing is a transform processing from time domain data to frequency domain data, that is, each time domain signal in the data is converted into a frequency domain component. The zero processing or the deletion processing on the first value in the first transformed data can reduce the number of time domain signals in the time domain data, and further reduce the number of frequency domain components in the frequency domain data, that is, reduce the data amount of the second transformed data.

[0113] In step 306, the update processing is performed on the preprocessed data according to the second transformed data.

[0114] In the embodiments of the present disclosure, the terminal device can take the second transformed data as the updated preprocessed data. The data amount in the second transformed data is reduced, and further the data amount in the preprocessed data is reduced, so that when the preprocessed data is input into the channel coefficient matrix prediction model, the processing amount of the channel coefficient matrix prediction model on the preprocessed data can be reduced, and the accuracy of the determined predicted channel coefficient matrix can be improved.

[0115] In step 307, the predicted channel coefficient matrix at the current time point is determined according to the preprocessed data and the channel coefficient matrix prediction model.

[0116] In the embodiments of the present disclosure, the process performed by the terminal device in step 307 can be, for example, acquiring the channel characteristic parameter of the target channel; inputting the preprocessed data and the channel characteristic parameter into the channel coefficient matrix prediction model to acquire the predicted channel coefficient matrix output by the channel coefficient matrix prediction model.

[0117] The channel characteristic parameters can include at least one of the following: a current Doppler frequency offset, a channel delay spread, and a channel spatial correlation.

[0118] In the embodiments of the present disclosure, the channel coefficient matrix prediction model can include an input layer, a hidden layer, and an output layer. The data input by the input layer can include preprocessed data, a current Doppler frequency offset, a channel delay spread, and a channel spatial correlation. The data output by the output layer can be a predicted channel coefficient matrix at a current time point.

[0119] The hidden layer can be provided with an activation function and a loss function, etc. The activation function can include at least one of the following: a logistic function Sigmoid, a hyperbolic tangent function Tanh, a linear rectifier function ReLU, etc. The Sigmoid function can map a real number to the interval (0, 1) and can be used for binary classification. The Tanh function is a symmetric function centered at zero. The ReLU function refers to a nonlinear function represented by a ramp function and its variants.

[0120] The loss function can include at least one of the following: a mean square error function, a cross-entropy function, etc.

[0121] Step 308, in combination with the predicted channel coefficient matrix, determining and reporting the channel state information (CSI).

[0122] It should be noted that the detailed description of steps 301 to 302 and steps 307 to 308 can refer to steps 101 to 104 in the embodiment shown in Figure 1 The detailed description of steps 101 to 104 in the embodiment shown in

[0123] In the channel state information reporting method of the embodiments of the present disclosure, a plurality of historical channel coefficient matrices of a target channel and a preprocessing matrix corresponding to a current Doppler position of the target channel are obtained; the plurality of historical channel coefficient matrices are filtered according to the preprocessing matrix to obtain preprocessing data at a current time point; inverse fast Fourier transform processing is performed on the preprocessing data to obtain first transformed data; zero processing is performed on first values in the first transformed data that are less than or equal to a threshold value to obtain processed data; fast Fourier transform processing is performed on the processed data to obtain second transformed data; the preprocessing data is updated according to the second transformed data; a predicted channel coefficient matrix at the current time point is determined according to the preprocessing data and a channel coefficient matrix prediction model; and the determination and reporting of channel state information (CSI) are performed in combination with the predicted channel coefficient matrix; wherein the inverse fast Fourier transform processing, the first value zero processing and the fast Fourier transform processing of the preprocessing data can reduce the data amount of the preprocessing data, thereby reducing the processing amount of the preprocessing data by the channel coefficient matrix prediction model, further accelerating the prediction speed of the channel coefficient matrix, further avoiding the out-of-date situation of the CSI information, and thus ensuring the channel throughput.

[0124] Figure 4 FIG. 1 is a structural schematic diagram of a channel state information reporting device according to an embodiment of the present disclosure.

[0125] As shown in FIG. 1, the channel state information reporting device can include an obtaining module 401, a filtering processing module 402, a determining module 403 and a reporting processing module 404. Figure 4

[0126] The obtaining module 401 is configured to obtain a plurality of historical channel coefficient matrices of a target channel and a preprocessing matrix corresponding to a current Doppler position of the target channel; the filtering processing module 402 is configured to perform filtering processing on the plurality of historical channel coefficient matrices according to the preprocessing matrix to obtain preprocessing data at a current time point; the determining module 403 is configured to determine a predicted channel coefficient matrix at the current time point according to the preprocessing data and a channel coefficient matrix prediction model; and the reporting processing module 404 is configured to perform determination and reporting of channel state information (CSI) in combination with the predicted channel coefficient matrix.

[0127] In an embodiment of the present disclosure, the obtaining module 401 is specifically configured to obtain a plurality of historical channel coefficient matrices of the target channel; determine a current Doppler position of the target channel; and query a matrix database according to the current Doppler position to obtain a preprocessing matrix corresponding to the current Doppler position in the matrix database.

[0128] ​In an embodiment of the present disclosure, the determination manner of the matrix database comprises: determining a value of a Doppler-related parameter adapted to each Doppler bin; for each Doppler bin, determining a distribution function of a channel coefficient matrix related value in combination with the value of the Doppler-related parameter adapted to the Doppler bin; generating a plurality of reference channel coefficient matrices according to the distribution function; determining a pre-processing matrix corresponding to the Doppler bin according to the plurality of reference channel coefficient matrices; and determining the matrix database according to the pre-processing matrix corresponding to each Doppler bin.

[0129] In an embodiment of the present disclosure, the Doppler-related parameter comprises at least one of the following: a Doppler frequency, a symbol time difference value between channel coefficient matrices.

[0130] In an embodiment of the present disclosure, the distribution function comprises at least one of the following: a Bessel function, an approximate sampling function.

[0131] In an embodiment of the present disclosure, the apparatus further comprises a first transform module, a zero processing module, a second transform module, and an update processing module; the first transform module is configured to perform inverse fast Fourier transform processing on the pre-processed data to obtain first transformed data; the zero processing module is configured to perform zero processing on a first value less than or equal to a threshold value in the first transformed data to obtain processed data; the second transform module is configured to perform fast Fourier transform processing on the processed data to obtain second transformed data; and the update processing module is configured to perform update processing on the pre-processed data according to the second transformed data.

[0132] In an embodiment of the present disclosure, the determination module 403 is specifically configured to: obtain a channel characteristic parameter of the target channel; and input the pre-processed data and the channel characteristic parameter into the channel coefficient matrix prediction model to obtain the predicted channel coefficient matrix output by the channel coefficient matrix prediction model.

[0133] In an embodiment of the present disclosure, the channel characteristic parameter comprises at least one of the following: the current Doppler frequency offset, channel delay spread, and channel spatial correlation.

[0134] In an embodiment of the present disclosure, the channel coefficient matrix prediction model is trained in combination with a plurality of channel coefficient matrix sequences; and a number of sample channel coefficient matrices in the channel coefficient matrix sequence is greater than a number of historical channel coefficient matrices used in channel coefficient matrix prediction.

[0135] In the channel state information reporting apparatus of the embodiments of the present disclosure, a plurality of historical channel coefficient matrices of a target channel and a pre-processing matrix corresponding to a current Doppler bin of the target channel are obtained; the plurality of historical channel coefficient matrices are filtered according to the pre-processing matrix to obtain pre-processed data at a current time point; a predicted channel coefficient matrix at the current time point is determined according to the pre-processed data and a channel coefficient matrix prediction model; and the predicted channel coefficient matrix is combined to determine and report channel state information (CSI). The predicted channel coefficient matrix at the current time point is predicted by combining the plurality of historical channel coefficient matrices of the target channel, which can shorten the reporting period of the CSI information, increase the reporting frequency of the CSI information, and avoid the situation that the CSI information is out of date, thereby ensuring the channel throughput.

[0136] According to a third aspect of the embodiments of the present disclosure, an electronic device is provided, which includes a processor and a memory for storing processor-executable instructions, wherein the processor is configured to implement the steps of the channel state information reporting method as described above.

[0137] To implement the above-mentioned embodiments, the present disclosure further provides a non-transitory computer-readable storage medium.

[0138] When the instructions in the storage medium are executed by the processor, the processor can execute the channel state information reporting method as described above.

[0139] To implement the above-mentioned embodiments, the present disclosure further provides a computer program product.

[0140] When the computer program product is executed by the processor of the electronic device, the electronic device can execute the method as described above.

[0141] Figure 5 FIG. 1 shows a structural block diagram of an electronic device according to an example embodiment. Figure 5 The electronic device shown is merely an example, and should not impose any limitation on the functions and use range of the embodiments of the present disclosure.

[0142] As Figure 5As shown, the electronic device 1000 includes a processor 111, which can perform various appropriate actions and processes according to a program stored in a read only memory (ROM) 112 or a program loaded into a random access memory (RAM) 113 from a memory 116. In the RAM 113, various programs and data required for the operation of the electronic device 1000 are also stored. The processor 111, the ROM 112, and the RAM 113 are connected to each other through a bus 114. An input / output (I / O) interface 115 is also connected to the bus 114.

[0143] Connected to the I / O interface 115 are a memory 116 including a hard disk or the like, and a communication section 117 including a network interface card such as a local area network (LAN) card, a modem, or the like, which performs communication processing via a network such as the Internet; and a drive 118 is also connected to the I / O interface 115 as necessary.

[0144] In particular, according to embodiments of the present disclosure, the processes described above with reference to the flowcharts can be implemented as a computer software program. For example, embodiments of the present disclosure include a computer program carrying on a computer readable medium, which contains program codes for executing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network by the communication section 117. When the computer program is executed by the processor 111, the above-described functions defined in the methods of the present disclosure are performed.

[0145] In an exemplary embodiment, a storage medium including instructions, such as a memory including instructions, is also provided, which can be executed by the processor 111 of the electronic device 1000 to complete the above-described methods. Optionally, the storage medium can be a non-transitory computer readable storage medium, for example, the non-transitory computer readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, and an optical data storage device, and the like.

[0146] In this disclosure, a computer readable storage medium can be any tangible medium that contains or stores a program used by or in connection with an instruction execution system, apparatus, or device. In this disclosure, a computer readable signal medium can include a propagated data signal with computer readable program code embodied therein, for use by or in connection with an instruction execution system, apparatus, or device. The propagated data signal can take any number of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium can be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable storage medium can be transmitted using any appropriate medium, including but not limited to wireless, wire line, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0147] Figure 6 A structural schematic diagram of a chip for an embodiment of the disclosure. As shown in the figure, the chip includes a processor 601 and an interface circuit 602. Among them, the number of processors 601 can be one or more, and the number of interface circuits 602 can be one or more. Figure 6

[0148] Optionally, the interface circuit 602 is configured to receive a signal, and the signal includes computer instructions, when the processor 601 executes the computer instructions, so that the chip executes the channel state information reporting method described in the above embodiments of the disclosure.

[0149] The collection, storage, use, processing, transmission, provision and disclosure of user personal information involved in the present application comply with the relevant legal regulations and do not violate public order and good customs.

[0150] In addition, the word "exemplary" is used herein to mean serving as an example, instance, or illustration. Any aspect or design described herein as "exemplary" is not necessarily to be construed as advantageous over other aspects or designs. Rather, use of the word exemplary is intended to present concepts in a concrete manner. As used in this document, the term "or" is intended to mean an inclusive "or" rather than an exclusive "or". That is, unless specified otherwise, or clear from context, "X employs A or B" is intended to mean any of the natural inclusive permutations. That is, if X employs A; X employs B; or X employs both A and B, then "X employs A or B" is satisfied under any of the foregoing instances. In addition, the articles "a" and "an" as used in this application and the appended claims should generally be construed to mean "one or more" unless specified otherwise or clear from context to be directed to a singular form. Thus, use of the articles in this application and the following claims is not limiting.

[0151] ​Likewise, although the present disclosure has been described and illustrated with respect to one or more implementations, equivalent alterations and modifications will become apparent to those skilled in the art in view of the description and illustrations. The present disclosure includes all such modifications and alterations and is only limited by the scope of the claims. In particular regard to the various functions performed by the above described components (e.g., elements, resources, etc.), the terms used to describe such components are intended to correspond, unless otherwise indicated, to any component which performs the specified function of the described component (e.g., a functional equivalent), even though not structurally equivalent to the disclosed structure. In addition, although a particular feature of the disclosure can have been disclosed with respect to only one of several implementations, such feature can be combined with one or more other features of the other implementations as can be desired and advantageous for any given or particular application. Furthermore, to the extent that the terms "includes", "including", "has", "have", "has", "having", or variants thereof are used in either the detailed description or the claims, such terms are intended to be inclusive in a manner similar to the term "comprising".

[0152] Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the features of the disclosure disclosed herein. It is intended that the present disclosure be considered as including any variations, uses, or adaptations of the disclosure and generic equivalents of the components described herein as covered by the appended claims. The specification and examples are to be construed as exemplary only, with the true scope and spirit of the disclosure being indicated by the following claims.

[0153] It is to be understood that the present disclosure is not limited to the precise construction described and illustrated above and that various modifications and changes can be made therein without departing from the scope of the present disclosure. The scope of the present disclosure is limited only by the claims appended hereto.

Claims

1. A method for reporting channel state information, characterized in that, The method includes: Obtain multiple historical channel coefficient matrices for the target channel; Determine the current Doppler level of the target channel; Based on the current Doppler level, query the matrix database to obtain the preprocessing matrix corresponding to the current Doppler level in the matrix database; The multiple historical channel coefficient matrices are filtered according to the preprocessing matrix to obtain the preprocessed data at the current time point; Based on the preprocessed data and the channel coefficient matrix prediction model, the predicted channel coefficient matrix at the current time point is determined; Based on the predicted channel coefficient matrix, the Channel State Information (CSI) is determined and reported.

2. The method according to claim 1, characterized in that, The methods for determining the matrix database include: Determine the values ​​of the Doppler-related parameters that are compatible with each Doppler setting; For each Doppler level, the distribution function of the channel coefficient matrix correlation value is determined by combining the values ​​of the Doppler correlation parameters adapted to the Doppler level. Based on the distribution function, generate multiple reference channel coefficient matrices; Based on the plurality of reference channel coefficient matrices, determine the preprocessing matrix corresponding to the Doppler range; The matrix database is determined based on the preprocessing matrix corresponding to each of the Doppler levels.

3. The method according to claim 2, characterized in that, The Doppler-related parameters include at least one of the following: Doppler frequency and symbol time difference between the channel coefficient matrix.

4. The method according to claim 2, characterized in that, The distribution function includes at least one of the following: Bessel function, approximate sampling function.

5. The method according to claim 1, characterized in that, After filtering the plurality of historical channel coefficient matrices according to the preprocessing matrix to obtain the preprocessed data at the current time point, the method further includes: The preprocessed data is subjected to inverse fast Fourier transform to obtain the first transformed data; The first value in the first transformed data that is less than or equal to the threshold value is set to zero to obtain the processed data. The processed data is subjected to a Fast Fourier Transform to obtain the second transformed data; The preprocessed data is updated based on the second transformed data.

6. The method according to claim 1, characterized in that, The step of determining the predicted channel coefficient matrix at the current time point based on the preprocessed data and the channel coefficient matrix prediction model includes: Obtain the channel characteristic parameters of the target channel; The preprocessed data and the channel characteristic parameters are input into the channel coefficient matrix prediction model to obtain the predicted channel coefficient matrix output by the channel coefficient matrix prediction model.

7. The method according to claim 6, characterized in that, The channel characteristic parameters include at least one of the following: current Doppler frequency offset, channel delay spread, and channel spatial correlation.

8. The method according to claim 1 or 6, characterized in that, The channel coefficient matrix prediction model is trained by combining multiple channel coefficient matrix sequences; the number of sample channel coefficient matrices in the channel coefficient matrix sequence is greater than the number of historical channel coefficient matrices used in the channel coefficient matrix prediction.

9. A channel state information reporting device, characterized in that, The device includes: The acquisition module is used to acquire multiple historical channel coefficient matrices of the target channel, as well as the preprocessing matrix corresponding to the current Doppler level of the target channel; The filtering module is used to filter the plurality of historical channel coefficient matrices according to the preprocessing matrix to obtain the preprocessed data at the current time point; The determination module is used to determine the predicted channel coefficient matrix at the current time point based on the preprocessed data and the channel coefficient matrix prediction model. The reporting processing module is used to determine and report Channel State Information (CSI) by combining the predicted channel coefficient matrix. The acquisition module is specifically used for: Obtain multiple historical channel coefficient matrices of the target channel; Determine the current Doppler level of the target channel; Based on the current Doppler level query matrix database, obtain the preprocessing matrix corresponding to the current Doppler level in the matrix database.

10. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured as follows: The steps of implementing the channel state information reporting method as described in any one of claims 1 to 8.

11. A non-transitory computer-readable storage medium, wherein when instructions in the storage medium are executed by a processor, the processor is able to perform a method for reporting channel state information as described in any one of claims 1 to 8.

12. A chip, characterized in that, It includes one or more interface circuits and one or more processors; the interface circuits are used to receive signals, the signals including computer instructions, and when the processor executes the computer instructions, it causes the chip to perform the channel state information reporting method according to any one of claims 1 to 8.

Images