WO2023066307A1 - 信道估计方法、装置、终端及网络侧设备 - Google Patents

信道估计方法、装置、终端及网络侧设备 Download PDF

Info

Publication number
WO2023066307A1
WO2023066307A1 PCT/CN2022/126226 CN2022126226W WO2023066307A1 WO 2023066307 A1 WO2023066307 A1 WO 2023066307A1 CN 2022126226 W CN2022126226 W CN 2022126226W WO 2023066307 A1 WO2023066307 A1 WO 2023066307A1
Authority
WO
WIPO (PCT)
Prior art keywords
transmission unit
domain transmission
time
channel estimation
neural network
Prior art date
Application number
PCT/CN2022/126226
Other languages
English (en)
French (fr)
Inventor
李建军
宋扬
孙鹏
杨昂
Original Assignee
维沃移动通信有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 维沃移动通信有限公司 filed Critical 维沃移动通信有限公司
Publication of WO2023066307A1 publication Critical patent/WO2023066307A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B7/00—Radio transmission systems, i.e. using radiation field
    • H04B7/02—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas
    • H04B7/04—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
    • H04B7/0413—MIMO systems
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L25/00—Baseband systems
    • H04L25/02—Details ; arrangements for supplying electrical power along data transmission lines

Definitions

  • the present application relates to the field of communication technologies, and in particular to a channel estimation method, device, terminal and network side equipment.
  • a large-scale antenna array formed by using massive multiple input multiple output (MIMO) technology can support more users to send and receive signals at the same time, thereby increasing the channel capacity and data flow of the mobile network by dozens of times or more At the same time, it can achieve a sharp reduction in interference between multiple users.
  • MIMO massive multiple input multiple output
  • CSI-RS Channel State Information Reference Signal
  • Resource Block Resource Block
  • OFDM Orthogonal Frequency Division Multiplex
  • Embodiments of the present application provide a channel estimation method, device, terminal and network side equipment, which can reduce pilot overhead and improve communication system performance.
  • the embodiment of the present application provides a channel estimation method, including:
  • the terminal receives the pilot signal sent by the network side device, and the resource blocks RB occupied by the pilot signal in the first time domain transmission unit and the second time domain transmission unit are at least partially different;
  • the embodiment of the present application provides a channel estimation method, including:
  • the network side device sends the pilot signal, and the resource blocks RB occupied by the pilot signal in the first time domain transmission unit and the second time domain transmission unit are at least partially different.
  • an embodiment of the present application provides a channel estimation device, which is applied to a terminal, and the device includes:
  • the receiving module is configured to receive the pilot signal sent by the network side device, and the resource blocks RB occupied by the pilot signal in the first time domain transmission unit and the second time domain transmission unit are at least partially different;
  • a channel estimation module configured to perform channel estimation on the third time domain transmission unit according to the pilot signals on the first time domain transmission unit and the second time domain transmission unit.
  • an embodiment of the present application provides a channel estimation device, which is applied to a network side device, and the device includes:
  • the sending module is configured to send a pilot signal, and resource blocks RB occupied by the pilot signal in the first time domain transmission unit and the second time domain transmission unit are at least partially different.
  • a terminal includes a processor, a memory, and a program or instruction stored in the memory and operable on the processor.
  • the program or instruction is executed by the processor The steps of the method described in the first aspect are realized.
  • a terminal including a processor and a communication interface, wherein the communication interface is used to receive a pilot signal sent by a network side device, and the first time domain transmission unit and the second time domain transmission unit
  • the resource blocks RB occupied by the pilot signals are at least partly different;
  • the unit performs channel estimation.
  • a network-side device includes a processor, a memory, and a program or instruction stored in the memory and operable on the processor, and the program or instruction is executed by the The processor implements the steps of the method described in the second aspect when executed.
  • a network side device including a processor and a communication interface, wherein the communication interface is used to send a pilot signal, and the pilot signal in the first time domain transmission unit and the second time domain transmission unit Resource blocks RB occupied by frequency signals are at least partially different.
  • a readable storage medium is provided, and programs or instructions are stored on the readable storage medium, and when the programs or instructions are executed by a processor, the steps of the method described in the first aspect are realized, or the steps of the method described in the first aspect are realized, or The steps of the method described in the second aspect.
  • a chip in a tenth aspect, includes a processor and a communication interface, the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the method as described in the first aspect , or implement the method described in the second aspect.
  • a computer program product is provided, the computer program product is stored in a non-transitory storage medium, and the computer program product is executed by at least one processor to implement the first aspect or the second aspect The steps of the method.
  • the network-side device sends a pilot signal to the terminal, and the resource blocks RB occupied by the pilot signal in the first time domain transmission unit and the second time domain transmission unit are at least partially different, so that only when Pilot signals are sent on some RBs, which can reduce pilot overhead and improve communication system performance.
  • FIG. 1 shows a schematic diagram of a wireless communication system
  • FIG. 2 shows a schematic flow diagram of a channel estimation method performed by a terminal according to an embodiment of the present application
  • FIG. 3 shows a schematic flow diagram of a channel estimation method performed by a network side device according to an embodiment of the present application
  • FIG. 4 and FIG. 5 show schematic diagrams of sending CSI-RS according to an embodiment of the present application
  • FIG. 6 shows a schematic structural diagram of a channel estimation device applied to a terminal according to an embodiment of the present application
  • FIG. 7 shows a schematic structural diagram of a channel estimation device applied to a network side device according to an embodiment of the present application
  • FIG. 8 shows a schematic diagram of the composition of a communication device in an embodiment of the present application.
  • FIG. 9 shows a schematic diagram of the composition of a terminal in an embodiment of the present application.
  • FIG. 10 shows a schematic diagram of the composition of the network side equipment in the embodiment of the present application.
  • Figure 11 shows the informer network structure diagram
  • Figure 12 shows a schematic diagram of a multi-head attention mechanism
  • Figure 13 shows a schematic diagram of the masked multi-head attention mechanism.
  • first, second and the like in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific sequence or sequence. It is to be understood that the terms so used are interchangeable under appropriate circumstances such that the embodiments of the application are capable of operation in sequences other than those illustrated or described herein and that "first" and “second” distinguish objects. It is usually one category, and the number of objects is not limited. For example, there may be one or more first objects.
  • “and/or” in the description and claims means at least one of the connected objects, and the character “/” generally means that the related objects are an "or” relationship.
  • LTE Long Term Evolution
  • LTE-Advanced LTE-Advanced
  • LTE-A Long Term Evolution-Advanced
  • CDMA Code Division Multiple Access
  • TDMA Time Division Multiple Access
  • FDMA Frequency Division Multiple Access
  • OFDMA Orthogonal Frequency Division Multiple Access
  • SC-FDMA Single-carrier Frequency-Division Multiple Access
  • system and “network” in the embodiments of the present application are often used interchangeably, and the described technology can be used for the above-mentioned system and radio technology, and can also be used for other systems and radio technologies.
  • the following description describes the New Radio (New Radio, NR) system for example purposes, and uses NR terminology in most of the following descriptions, but these techniques can also be applied to applications other than NR system applications, such as the 6th Generation (6th Generation , 6G) communication system.
  • 6th Generation 6th Generation
  • Fig. 1 shows a block diagram of a wireless communication system to which the embodiment of the present application is applicable.
  • the wireless communication system includes a terminal 11 and a network side device 12 .
  • the terminal 11 can also be called a terminal device or a user terminal (User Equipment, UE), and the terminal 11 can be a mobile phone, a tablet computer (Tablet Personal Computer), a laptop computer (Laptop Computer) or a notebook computer, a personal digital Assistant (Personal Digital Assistant, PDA), handheld computer, netbook, ultra-mobile personal computer (UMPC), mobile Internet device (Mobile Internet Device, MID), wearable device (Wearable Device) or vehicle-mounted device (Vehicle User Equipment, VUE), pedestrian terminal (Pedestrian User Equipment, PUE) and other terminal-side equipment, wearable devices include: smart watches, bracelets, earphones, glasses, etc.
  • the network side device 12 may be a base station or a core network, where a base station may be called a node B, an evolved node B, an access point, a base transceiver station (Base Transceiver Station, BTS), a radio base station, a radio transceiver, a basic service Basic Service Set (BSS), Extended Service Set (ESS), Node B, Evolved Node B (eNB), Home Node B, Home Evolved Node B, Wireless Local Area Network (WLAN) ) access point, wireless fidelity (Wireless Fidelity, WiFi) node, transmitting and receiving point (Transmitting Receiving Point, TRP) or some other suitable term in the field, as long as the same technical effect is achieved, the base station is not limited to Specific technical vocabulary.
  • the core network device may be a location management device, for example, a location management Functions (Location Management Function (LMF), Evolutionary-Service Mobile Location Center (E-SMLC)), etc.
  • LMF Location Management Function
  • E-SMLC Evolutionary-Service Mobile Location Center
  • the large-scale antenna array formed by massive MIMO technology can support more users to send and receive signals at the same time, thereby increasing the channel capacity and data flow of the mobile network by dozens of times or more, and at the same time, it can realize the interference between multiple users. dropped sharply. Therefore, it has been continuously and highly concerned by researchers since it was proposed.
  • OFDM has become the underlying technology of mobile communication since 4G. This technology can effectively fight against multipath interference, and divides frequency-domain frequency-selective channels into multiple flat-fading sub-channels to support wireless transmission.
  • OFDM combined with massive MIMO is already the basic framework of present and future wireless communication.
  • the transmission of pilot channel state information-reference signal CSI-RS is based on resource block RB.
  • Each resource block RB contains 12 subcarriers in the frequency domain and 6-7 OFDM symbols in the time domain.
  • the pilot signal CSI-RS is not sent every Transmission Time Interval (Transmission Time Interval, TTI), but is sent every few TTIs. Therefore, in the TTI where no CSI-RS is sent, the real massive MIMO channel cannot be known. For this reason, the related technologies generally use the channel estimated by the TTI of the latest CSI-RS transmission as the channel of the current TTI, thereby searching for the optimal precoding from the codebook.
  • An embodiment of the present application provides a channel estimation method, which is executed by a terminal, as shown in FIG. 2 , the method includes:
  • Step 101 The terminal receives the pilot signal sent by the network side device, and the resource blocks RB occupied by the pilot signal in the first time domain transmission unit and the second time domain transmission unit are at least partially different;
  • Step 102 Perform channel estimation on a third time domain transmission unit according to the pilot signals on the first time domain transmission unit and the second time domain transmission unit.
  • the third time domain transmission unit may be the same as the first time domain transmission unit or may be different; the third time domain transmission unit may be the same as the second time domain transmission unit or may be different; the first time domain transmission unit and the first time domain transmission unit The two time domain transmission units are different time domain transmission units.
  • the terminal receives the pilot signal sent by the network side equipment, and the resource blocks RB occupied by the pilot signal in the first time domain transmission unit and the second time domain transmission unit are at least partially different, that is, the network
  • the side device only sends pilot signals on some RBs, which can reduce the pilot overhead; in addition, if the number of RBs sending pilot signals remains unchanged, since the pilot signals are only sent on some RBs in the time domain transmission unit, it can The number of time-domain transmission units for sending pilot signals increases, and the interval between time-domain transmission units for sending pilot signals decreases, which can improve the accuracy of channel estimation and improve the performance of the communication system.
  • the performing channel estimation on the third time domain transmission unit according to the pilot signals on the first time domain transmission unit and the second time domain transmission unit includes:
  • the channel on the RB that does not transmit the pilot signal can be obtained, because the transmission pilot
  • the RB of the signal and the RB of the untransmitted pilot signal can be located in the same time-domain transmission unit, and the correlation is strong, so the accuracy of channel estimation can be improved, and the performance of the communication system can be improved.
  • the performing channel estimation on the third time domain transmission unit according to the pilot signals on the first time domain transmission unit and the second time domain transmission unit includes:
  • Channel estimation is performed according to the pilot signal on the first time domain transmission unit, the pilot signal on the second time domain transmission unit and the pre-trained neural network model, and L time domains after the current time domain transmission unit are obtained Channels on all RBs in the transmission unit, L is a positive integer.
  • the pilot signal on the first time-domain transmission unit and the pilot signal on the second time-domain transmission unit can be used to predict subsequent channels, and it is possible to predict channels without pilots in the future, Therefore, the large pilot overhead is greatly reduced, and the performance of the system is also improved.
  • all the RBs are RBs determined according to a predefined rule or a pre-configuration manner.
  • the RBs determined according to a predefined rule or a pre-configuration manner include at least RBs occupied by the pilot signal in the transmission unit of the first time slot and RBs occupied by the pilot signal in the transmission unit of the second time slot.
  • channel estimation is performed by using the pilot signals on the nearest K time-domain transmission units that send pilot signals, and K is a positive integer. That is, channel estimation is performed by using the current time-domain transmission unit and K-1 time-domain transmission units that send pilot signals before the current time-domain transmission unit.
  • the pilot signal is sent on half of the RBs
  • the terminal receiving the pilot signal sent by the network side device includes:
  • the terminal receives the pilot signal sent by the network side device on the first RB of the first time domain transmission unit
  • the terminal receives the pilot signal sent by the network side device on the second RB of the second time domain transmission unit;
  • the first RB is different from the second RB
  • the second time-domain transmission unit is the nearest time-domain transmission unit after the first time-domain transmission unit that sends the pilot signal
  • the second time-domain transmission unit There is at least one time domain transmission unit between the second time domain transmission unit and the first time domain transmission unit.
  • pilot signals are sent at intervals of one or more time domain transmission units. If the number of RBs for sending pilot signals on each time domain transmission unit unchanged, the pilot overhead can be reduced.
  • the sequence number of the first RB is an even number, and the sequence number of the second RB is an odd number;
  • the sequence number of the first RB is an odd number
  • the sequence number of the second RB is an even number
  • pilot signal sending time domain transmission unit For example, on a certain pilot signal sending time domain transmission unit, select to receive the pilot signal on the RB with an odd number, then on the next pilot signal sending time domain transmission unit, choose to receive the pilot signal on the RB with an even number Or, on a certain pilot signal sending time domain transmission unit, choose to receive the pilot signal on the RB whose serial number is even, then on the next pilot signal sending time domain transmission unit, select the serial number to be odd The pilot signal is received on the RB.
  • This embodiment also includes the step of training the neural network model, and the step of training the neural network model includes at least one of the following:
  • the training step is to use the training data to train the neural network initial model to obtain the trained neural network initial model; wherein, the training data includes the input data of the neural network initial model and corresponding actual channel data, and the input data is the channel estimation result of K consecutive time-domain transmission units sending pilot signals, the length of the channel estimation result of each time-domain transmission unit is M ⁇ N, and the output of the neural network initial model is the Kth transmission pilot
  • the time-domain transmission unit of the signal and the channel estimation results of N antennas on all M RBs in the subsequent L consecutive time-domain transmission units, M, N, K, and L are positive integers;
  • Judging step if the mean square error between the output of the neural network initial model after training and the corresponding actual channel data is greater than or equal to the preset threshold or the preset number of iterations has not been reached, turn to the training step; if the training The mean square error between the output of the final neural network initial model and the corresponding actual channel data is less than a preset threshold or reaches a preset number of iterations, and the trained neural network initial model is used as the neural network model.
  • the step of training to obtain the neural network model includes at least one of the following:
  • the training step is to use the training data to train the neural network model obtained in the previous training to obtain the trained neural network model; wherein, the training data includes input data and corresponding actual channel data of the neural network model obtained in the previous training , the input data is the channel estimation results of K consecutive time-domain transmission units sending pilot signals, the length of the channel estimation results of each time-domain transmission unit is M ⁇ N, and the neural network model obtained from the previous training The output is the Kth time-domain transmission unit sending the pilot signal and the channel estimation results of N antennas on all M RBs in the subsequent L consecutive time-domain transmission units, M, N, K, and L are positive integers;
  • Judging step if the mean square error between the output of the trained neural network model and the corresponding actual channel data is greater than or equal to the preset threshold or does not reach the preset number of iterations, turn to the training step; if after the training The mean square error between the output of the neural network model and the corresponding actual channel data is less than a preset threshold or reaches a preset number of iterations, and the trained neural network model is used as the neural network model.
  • the neural network model includes a first neural network model and a second neural network model, and among the input data for training the first neural network model, the first of the K consecutive time-domain transmission units sending pilot signals The pilot signals in the time-domain transmission units are sent on the RBs with even numbers; in the input data for training the second neural network model, the first of the K consecutive time-domain transmission units sending pilot signals The pilot signal in the time domain transmission unit is sent on the first RB whose sequence number is odd.
  • the two neural network models can be used alternately for channel estimation and prediction.
  • performing channel estimation according to the neural network model includes:
  • the received pilot signal in the first time-domain transmission unit is sent on the RB with an even number, use the first neural network model to perform channel estimation; if the received first time-domain transmission unit Pilot signals are sent on RBs with odd numbers, and channel estimation is performed by using the second neural network model.
  • the pilot signal includes at least one of the following:
  • the time domain transmission unit includes any of the following: transmission time interval TTI, subframe, millisecond, time slot and symbol.
  • the embodiment of the present application also provides a channel estimation method, which is executed by a network side device, as shown in FIG. 3 , the method includes:
  • Step 201 The network side device sends a pilot signal, and the resource blocks RB occupied by the pilot signal in the first time domain transmission unit and the second time domain transmission unit are at least partially different.
  • the network side device in order to save pilot overhead, does not send pilot signals on RBs of each time-domain transmission unit, but sends pilot signals on some RBs.
  • the transmission of the pilot signal is based on the resource block RB as the basic unit.
  • the number of RBs for sending pilot signals remains unchanged, since pilot signals are only sent on some RBs in the time-domain transmission unit, more time-domain transmission units for sending pilot signals can be made, and the number of time-domain transmission units for sending pilot signals can be increased.
  • the reduced interval between time-domain transmission units can improve the accuracy of channel estimation and improve the performance of the communication system.
  • the network side device may also send a pilot signal at intervals of several time domain transmission units.
  • the sending of the pilot signal by the network side device includes:
  • the first RB is different from the second RB
  • the second time-domain transmission unit is the nearest time-domain transmission unit after the first time-domain transmission unit that sends the pilot signal
  • the second time-domain transmission unit There is at least one time domain transmission unit between the second time domain transmission unit and the first time domain transmission unit.
  • the sequence number of the first RB is an even number, and the sequence number of the second RB is an odd number;
  • the sequence number of the first RB is an odd number
  • the sequence number of the second RB is an even number
  • the network side device alternately selects the RB with an odd number and the RB with an even number to send the pilot signal.
  • the pilot signal includes at least one of the following:
  • the time domain transmission unit includes any of the following: transmission time interval TTI, subframe, millisecond, time slot and symbol.
  • the network side device sends pilot CSI-RSs of N ports.
  • the pilot signal CSI-RS is not sent every TTI, but is sent every S TTIs.
  • the basic unit of pilot CSI-RS transmission is RB.
  • Each RB includes 12 subcarriers in the frequency domain and multiple OFDM symbols in the time domain (equal to the OFDM symbols included in each TTI).
  • each TTI has M RBs, and each RB has a sequence number, and pilot design and resource allocation are performed based on RBs.
  • the pilot CSI-RS is not sent on every RB, but is only sent on half of the RBs. If the CSI-RS is selected to be sent on the odd-numbered RB in a certain CSI-RS sending TTI, then the CSI-RS is selected to be sent on the even-numbered RB in the next CSI-RS sending TTI.
  • the network side device alternately selects the RB with an odd number and the RB with an even number to transmit the CSI-RS.
  • the receiving end After receiving the signal on the TTI of the CSI-RS sent by the network side equipment, the receiving end (that is, the terminal) can use the CSI-RS to estimate the channel of the N antennas on the corresponding RB, but it cannot accurately know that no CSI is sent on the TTI. -The channel on the RB of the RS.
  • the channels of the N antennas on all RBs cannot be accurately known.
  • the channel on each RB estimated by K TTIs sending CSI-RS in the past, and the neural network model based on the attention mechanism can not only estimate that no CSI-RS is sent on the current TTI (indicated by the Kth TTI).
  • the channels of the N antennas on the RB of the RS can also predict the channels of all RBs on the next L TTIs where no CSI-RS is sent, as shown in FIG. 5 .
  • the neural network model adopts an informer network structure based on an attention mechanism, and the neural network model adopts an encoder-decoder architecture, as shown in FIG. 11 .
  • the encoder consists of multi-layer multi-head ProbSparse Self-attention and Self-attention Distilling.
  • Q, V, and K are respectively transformed through n times of linear transformation to obtain n groups of Q, K, and V, where n corresponds to n-head.
  • the encoder's feature maps lead to redundant combinations, exploit distilling to privilege dominant features with dominant features, and generate focus self-attention feature maps in the next layer.
  • the "distilling" process here advances from layer j to j+1 as follows:
  • the decoder consists of a single layer of multi-head ProbSparse Self-attention and Masked multi-head attention.
  • the input of multi-head attention is three vectors Q, V and K, and the calculation process is as follows:
  • Q, V, and K are respectively transformed through n times of linear transformation to obtain n groups of Q, K, and V, where n corresponds to n-head.
  • Masked multi-head attention is applied to ProbSparse self-attention calculation. It prevents each position from focusing on future positions, thus avoiding autoregression.
  • the principle is shown in Figure 13, where the result of the dot product is set to negative infinity.
  • the input of the neural network model in this embodiment is K sequences X t , the length of each sequence is M ⁇ N, and the value of the element is the channel of N antennas on M RBs estimated by CSI-RS, and no CSI-RS is sent.
  • the channel value on the RB of the RS is replaced with 0. Therefore X t is a matrix of MN ⁇ K.
  • X t can be expressed as:
  • x t i is the i-th column of X t , that is, the channel estimation result on the i-th TTI.
  • X t can be expressed as:
  • the output of the neural network model is L+1 sequences Y t , which are the estimated and predicted values of channels of N antennas on all M RBs on the Kth TTI and subsequent L consecutive TTIs.
  • the channel vector sequence X t estimated by the CSI-RS on K TTIs is input to the encoder, and the encoder includes a multi-layer attention mechanism composite Network, each layer is composed of multi-header ProbSparse self-attention and Self-attention Distilling.
  • the output B t of the encoder is generated. Then Bt is input to the decoder.
  • the decoder has only one layer, consisting of Masked ProbSparse multi-head attention and multi-head attention, where the input of Masked ProbSparse multi-head attention is a vector sequence X t of length K/2+L+1, its former K/ The two sequences are the second half of X t , and the last L+1 vector sequences are all 0 vectors.
  • the output of the multi-head attention is generated.
  • the prediction result Y t is output.
  • the network parameters of the informer network need to be trained.
  • X t in the training data comes from CSI-RS channel estimation on each TTI, and the matching target is the actual channel H t of K to K+L TTI.
  • Each set of training data includes the input data of the informer network (CSI-RS channel estimation results on each TTI) and the corresponding actual channel data H t .
  • the goal of training optimization is to minimize the mean square error between the output Y t of the neural network model and the actual channel H t .
  • the goal of training optimization may be that the number of iterations reaches a preset number, such as 100.
  • the pilot signal in the first TTI can be sent on RBs with even numbers or odd RBs, in order to improve the accuracy of signal estimation and channel prediction, it is necessary to train the neural network separately for these two cases After the neural network model is trained, the two neural network models can be used alternately for channel estimation and prediction.
  • This embodiment can be applied to the application scenarios where LTE, GSM, and CDMA technologies adopt massive MIMO.
  • the channel estimation method provided in the embodiment of the present application may be executed by a channel estimation device, or a module in the channel estimation device for executing the loading channel estimation method.
  • the channel estimation method provided in the embodiment of the present application is described by taking the method for channel estimation performed by the channel estimation device as an example.
  • An embodiment of the present application provides a channel estimation device, which is applied to a terminal 300. As shown in FIG. 6, the device includes:
  • the receiving module 310 is configured to receive the pilot signal sent by the network side equipment, and the resource blocks RB occupied by the pilot signal in the first time domain transmission unit and the second time domain transmission unit are at least partially different;
  • the channel estimation module 320 is configured to perform channel estimation on the third time domain transmission unit according to the pilot signals on the first time domain transmission unit and the second time domain transmission unit.
  • the terminal receives the pilot signal sent by the network side equipment, and the resource blocks RB occupied by the pilot signal in the first time domain transmission unit and the second time domain transmission unit are at least partially different, that is, the network
  • the side device only sends pilot signals on some RBs, which can reduce pilot overhead and improve the performance of the communication system.
  • the channel estimation module is specifically configured to perform channel estimation according to the pilot signal on the first time domain transmission unit, the pilot signal on the second time domain transmission unit and the pre-trained neural network model. Estimating and obtaining channels on all RBs in the third time domain transmission unit.
  • the channel estimation module is specifically configured to perform channel estimation according to the pilot signal on the first time domain transmission unit, the pilot signal on the second time domain transmission unit and the pre-trained neural network model. Estimated to obtain channels on all RBs within L time-domain transmission units after the current time-domain transmission unit, where L is a positive integer.
  • all the RBs are RBs determined according to a predefined rule or a pre-configuration manner.
  • the RBs determined according to a predefined rule or a pre-configuration manner include at least RBs occupied by the pilot signal in the transmission unit of the first time slot and RBs occupied by the pilot signal in the transmission unit of the second time slot.
  • the channel estimation module is specifically configured to perform channel estimation using pilot signals on the latest K time-domain transmission units that send pilot signals, where K is a positive integer.
  • the receiving module is specifically configured to receive the pilot signal sent by the network side device on the first RB of the first time domain transmission unit; receive the pilot signal sent by the network side device on the second RB of the second time domain transmission unit the transmitted pilot signal;
  • the first RB is different from the second RB
  • the second time-domain transmission unit is the nearest time-domain transmission unit after the first time-domain transmission unit that sends the pilot signal
  • the second time-domain transmission unit There is at least one time domain transmission unit between the second time domain transmission unit and the first time domain transmission unit.
  • the sequence number of the first RB is an even number, and the sequence number of the second RB is an odd number;
  • the sequence number of the first RB is an odd number
  • the sequence number of the second RB is an even number
  • a training module is also included for training to obtain the neural network model
  • the step of obtaining the neural network model through training includes at least one of the following:
  • the training step is to use the training data to train the neural network initial model to obtain the trained neural network initial model; wherein, the training data includes the input data of the neural network initial model and corresponding actual channel data, and the input data is the channel estimation result of K consecutive time-domain transmission units sending pilot signals, the length of the channel estimation result of each time-domain transmission unit is M ⁇ N, and the output of the neural network initial model is the Kth transmission pilot
  • the time-domain transmission unit of the signal and the channel estimation results of N antennas on all M RBs in the subsequent L consecutive time-domain transmission units, M, N, K, and L are positive integers;
  • Judging step if the mean square error between the output of the neural network initial model after training and the corresponding actual channel data is greater than or equal to the preset threshold or the preset number of iterations has not been reached, turn to the training step; if the training The mean square error between the output of the final neural network initial model and the corresponding actual channel data is less than a preset threshold or reaches a preset number of iterations, and the trained neural network initial model is used as the neural network model.
  • the training module is specifically configured to perform at least one of the following:
  • the training step is to use the training data to train the neural network model obtained in the previous training to obtain the trained neural network model; wherein, the training data includes input data and corresponding actual channel data of the neural network model obtained in the previous training , the input data is the channel estimation results of K consecutive time-domain transmission units sending pilot signals, the length of the channel estimation results of each time-domain transmission unit is M ⁇ N, and the neural network model obtained from the previous training The output is the Kth time-domain transmission unit sending the pilot signal and the channel estimation results of N antennas on all M RBs in the subsequent L consecutive time-domain transmission units, M, N, K, and L are positive integers;
  • Judging step if the mean square error between the output of the trained neural network model and the corresponding actual channel data is greater than or equal to the preset threshold or does not reach the preset number of iterations, turn to the training step; if after the training The mean square error between the output of the neural network model and the corresponding actual channel data is less than a preset threshold or reaches a preset number of iterations, and the trained neural network model is used as the neural network model.
  • the neural network model includes a first neural network model and a second neural network model, and in the input data for training the first neural network model, the K consecutive time-domain transmission units that send pilot signals In the first time-domain transmission unit, the pilot signal is sent on the even-numbered RB; in the input data for training the second neural network model, in the K consecutive time-domain transmission units that send pilot signals The pilot signal in the first time domain transmission unit is sent on the first RB whose sequence number is odd.
  • the channel estimation module is specifically configured to use the first neural network model to perform channel estimation if the received pilot signal in the first time domain transmission unit is sent on an RB with an even number; If the received pilot signal in the first time-domain transmission unit is sent on the RB whose sequence number is odd, use the second neural network model to perform channel estimation.
  • the pilot signal includes at least one of the following:
  • Channel State Information Reference Signal CSI-RS Sounding Reference Signal SRS, and Demodulation Reference Signal DMRS.
  • the time domain transmission unit includes any one of the following: transmission time interval TTI, subframe, millisecond, time slot and symbol.
  • the channel estimation apparatus in the embodiment of the present application may be an apparatus, an apparatus having an operating system or an electronic device, or may be a component, an integrated circuit, or a chip in a terminal.
  • the apparatus or electronic equipment may be a mobile terminal or a non-mobile terminal.
  • the mobile terminal may include but not limited to the types of terminals 11 listed above, and the non-mobile terminal may be a server, a network attached storage (Network Attached Storage, NAS), a personal computer (personal computer, PC), a television ( television, TV), teller machines or self-service machines, etc., are not specifically limited in this embodiment of the present application.
  • the channel estimation device provided by the embodiment of the present application can realize each process realized by the method embodiment in FIG. 2 and achieve the same technical effect. To avoid repetition, details are not repeated here.
  • An embodiment of the present application provides a channel estimation device, which is applied to a network side device 400. As shown in FIG. 7, the device includes:
  • the sending module 410 is configured to send a pilot signal, and resource blocks RB occupied by the pilot signal in the first time domain transmission unit and the second time domain transmission unit are at least partially different.
  • the network side device in order to save pilot overhead, does not send pilot signals on RBs of each time-domain transmission unit, but sends pilot signals on some RBs.
  • the transmission of the pilot signal is based on the resource block RB as the basic unit.
  • the network side device may also send a pilot signal at intervals of several time domain transmission units.
  • the sending module is specifically configured to send a pilot signal on the first RB of the first time domain transmission unit; send a pilot signal on the second RB of the second time domain transmission unit;
  • the first RB is different from the second RB
  • the second time-domain transmission unit is the nearest time-domain transmission unit after the first time-domain transmission unit that sends the pilot signal
  • the second time-domain transmission unit There is at least one time domain transmission unit between the second time domain transmission unit and the first time domain transmission unit.
  • the sequence number of the first RB is an even number, and the sequence number of the second RB is an odd number;
  • the sequence number of the first RB is an odd number
  • the sequence number of the second RB is an even number
  • the pilot signal includes at least one of the following:
  • the time domain transmission unit includes any of the following: transmission time interval TTI, subframe, millisecond, time slot and symbol.
  • the channel estimation device provided by the embodiment of the present application can realize each process realized by the method embodiment in FIG. 3 and achieve the same technical effect. To avoid repetition, details are not repeated here.
  • this embodiment of the present application further provides a communication device 500, including a processor 501, a memory 502, and programs or instructions stored in the memory 502 and operable on the processor 501,
  • a communication device 500 including a processor 501, a memory 502, and programs or instructions stored in the memory 502 and operable on the processor 501
  • the communication device 500 is a terminal
  • the program or instruction is executed by the processor 501
  • each process of the above embodiments of the channel estimation method applied to the terminal can be implemented, and the same technical effect can be achieved.
  • the communication device 500 is a network-side device
  • the program or instruction is executed by the processor 501
  • each process of the above-mentioned embodiment of the channel estimation method applied to the network-side device can be achieved, and the same technical effect can be achieved. To avoid repetition, here No longer.
  • the embodiment of the present application also provides a terminal, including a processor and a communication interface, wherein the communication interface is used to receive the pilot signal sent by the network side equipment, and the first time domain transmission unit and the second time domain transmission unit
  • the resource blocks RB occupied by the pilot signals are at least partly different;
  • the unit performs channel estimation.
  • FIG. 9 is a schematic diagram of a hardware structure of a terminal implementing an embodiment of the present application.
  • the terminal 1000 includes but not limited to: a radio frequency unit 1001, a network module 1002, an audio output unit 1003, an input unit 1004, a sensor 1005, a display unit 1006, a user input unit 1007, an interface unit 1008, a memory 1009, and a processor 1010, etc. at least some of the components.
  • the terminal 1000 can also include a power supply (such as a battery) for supplying power to various components, and the power supply can be logically connected to the processor 1010 through the power management system, so as to manage charging, discharging, and power consumption through the power management system. Management and other functions.
  • a power supply such as a battery
  • the terminal structure shown in FIG. 9 does not constitute a limitation on the terminal, and the terminal may include more or fewer components than shown in the figure, or combine some components, or arrange different components, which will not be repeated here.
  • the input unit 1004 may include a graphics processor (Graphics Processing Unit, GPU) 10041 and a microphone 10042, and the graphics processor 10041 is used for the image capture device (such as the image data of the still picture or video obtained by the camera) for processing.
  • the display unit 1006 may include a display panel 10061, and the display panel 10061 may be configured in the form of a liquid crystal display, an organic light emitting diode, or the like.
  • the user input unit 1007 includes a touch panel 10071 and other input devices 10072 .
  • the touch panel 10071 is also called a touch screen.
  • the touch panel 10071 may include two parts, a touch detection device and a touch controller.
  • Other input devices 10072 may include, but are not limited to, physical keyboards, function keys (such as volume control buttons, switch buttons, etc.), trackballs, mice, and joysticks, which will not be repeated here.
  • the radio frequency unit 1001 receives the downlink data from the network side device, and processes it to the processor 1010; in addition, estimates the uplink channel to the network side device.
  • the radio frequency unit 1001 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, and the like.
  • the memory 1009 can be used to store software programs or instructions as well as various data.
  • the memory 1009 may mainly include a program or instruction storage area and a data storage area, wherein the program or instruction storage area may store an operating system, at least one application program or instruction required by a function (such as a sound playback function, an image playback function, etc.) and the like.
  • the memory 1009 may include a high-speed random access memory, and may also include a nonvolatile memory, wherein the nonvolatile memory may be a read-only memory (Read-Only Memory, ROM), a programmable read-only memory (Programmable ROM) , PROM), erasable programmable read-only memory (Erasable PROM, EPROM), electrically erasable programmable read-only memory (Electrically EPROM, EEPROM) or flash memory.
  • ROM Read-Only Memory
  • PROM programmable read-only memory
  • PROM erasable programmable read-only memory
  • Erasable PROM Erasable PROM
  • EPROM electrically erasable programmable read-only memory
  • EEPROM electrically erasable programmable read-only memory
  • flash memory for example at least one disk storage device, flash memory device, or other non-volatile solid-state storage device.
  • the processor 1010 may include one or more processing units; optionally, the processor 1010 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, application programs or instructions, etc., Modem processors mainly handle wireless communications, such as baseband processors. It can be understood that the foregoing modem processor may not be integrated into the processor 1010 .
  • the processor 1010 is configured to receive the pilot signal sent by the network side device, and the resource blocks RB occupied by the pilot signal in the first time domain transmission unit and the second time domain transmission unit are at least partially different; according to the performing channel estimation on the third time domain transmission unit based on the pilot signals on the first time domain transmission unit and the second time domain transmission unit.
  • the processor 1010 is configured to perform channel estimation according to the pilot signal on the first time-domain transmission unit, the pilot signal on the second time-domain transmission unit, and a pre-trained neural network model, Channels on all RBs in the third time domain transmission unit are obtained.
  • the processor 1010 is configured to perform channel estimation according to the pilot signal on the first time-domain transmission unit, the pilot signal on the second time-domain transmission unit, and a pre-trained neural network model, Channels on all RBs within L time-domain transmission units after the current time-domain transmission unit are obtained, where L is a positive integer.
  • all the RBs are RBs determined according to a predefined rule or a pre-configuration manner.
  • the RBs determined according to a predefined rule or a pre-configuration manner include at least RBs occupied by the pilot signal in the transmission unit of the first time slot and RBs occupied by the pilot signal in the transmission unit of the second time slot.
  • the processor 1010 is specifically configured to perform channel estimation using pilot signals on the latest K time-domain transmission units that send pilot signals, where K is a positive integer.
  • the processor 1010 is configured to receive the pilot signal sent by the network side device on the first RB of the first time domain transmission unit; receive the pilot signal sent by the network side device on the second RB of the second time domain transmission unit the pilot signal;
  • the first RB is different from the second RB
  • the second time-domain transmission unit is the nearest time-domain transmission unit after the first time-domain transmission unit that sends the pilot signal
  • the second time-domain transmission unit There is at least one time domain transmission unit between the second time domain transmission unit and the first time domain transmission unit.
  • the sequence number of the first RB is an even number, and the sequence number of the second RB is an odd number;
  • the sequence number of the first RB is an odd number
  • the sequence number of the second RB is an even number
  • the processor 1010 is configured to train the neural network model, wherein the step of training the neural network model includes at least one of the following:
  • the training step is to use the training data to train the neural network initial model to obtain the trained neural network initial model; wherein, the training data includes the input data of the neural network initial model and corresponding actual channel data, and the input data is the channel estimation result of K consecutive time-domain transmission units sending pilot signals, the length of the channel estimation result of each time-domain transmission unit is M ⁇ N, and the output of the neural network initial model is the Kth transmission pilot
  • the time-domain transmission unit of the signal and the channel estimation results of N antennas on all M RBs in the subsequent L consecutive time-domain transmission units, M, N, K, and L are positive integers;
  • Judging step if the mean square error between the output of the neural network initial model after training and the corresponding actual channel data is greater than or equal to the preset threshold or the preset number of iterations has not been reached, turn to the training step; if the training The mean square error between the output of the final neural network initial model and the corresponding actual channel data is less than a preset threshold or reaches a preset number of iterations, and the trained neural network initial model is used as the neural network model.
  • the step of training the neural network model includes one of the following:
  • the training step is to use the training data to train the neural network model obtained in the previous training to obtain the trained neural network model; wherein, the training data includes input data and corresponding actual channel data of the neural network model obtained in the previous training , the input data is the channel estimation results of K consecutive time-domain transmission units sending pilot signals, the length of the channel estimation results of each time-domain transmission unit is M ⁇ N, and the neural network model obtained from the previous training The output is the Kth time-domain transmission unit sending the pilot signal and the channel estimation results of N antennas on all M RBs in the subsequent L consecutive time-domain transmission units, M, N, K, and L are positive integers;
  • Judging step if the mean square error between the output of the trained neural network model and the corresponding actual channel data is greater than or equal to the preset threshold or does not reach the preset number of iterations, turn to the training step; if after the training The mean square error between the output of the neural network model and the corresponding actual channel data is less than a preset threshold or reaches a preset number of iterations, and the trained neural network model is used as the neural network model.
  • the neural network model includes a first neural network model and a second neural network model, and in the input data for training the first neural network model, the K consecutive time-domain transmission units that send pilot signals In the first time-domain transmission unit, the pilot signal is sent on the even-numbered RB; in the input data for training the second neural network model, in the K consecutive time-domain transmission units that send pilot signals The pilot signal in the first time domain transmission unit is sent on the first RB whose sequence number is odd.
  • the processor 1010 is configured to use the first neural network model to perform channel estimation if the received pilot signal in the first time-domain transmission unit is sent on an even-numbered RB; The received pilot signal in the first time-domain transmission unit is sent on the RB whose sequence number is odd, and the channel estimation is performed by using the second neural network model.
  • the pilot signal includes at least one of the following:
  • Channel State Information Reference Signal CSI-RS Sounding Reference Signal SRS, and Demodulation Reference Signal DMRS.
  • the time domain transmission unit includes any one of the following: transmission time interval TTI, subframe, millisecond, time slot and symbol.
  • the embodiment of the present application also provides a network side device, including a processor and a communication interface, the communication interface is used to send pilot signals, and the pilot signals in the first time domain transmission unit and the second time domain transmission unit occupy
  • the resource blocks RB of are at least partially different.
  • the network-side device embodiment corresponds to the above-mentioned network-side device method embodiment, and each implementation process and implementation mode of the above-mentioned method embodiment can be applied to this network-side device embodiment, and can achieve the same technical effect.
  • the embodiment of the present application also provides a network side device.
  • the network device 700 includes: an antenna 71 , a radio frequency device 72 , and a baseband device 73 .
  • the antenna 71 is connected to a radio frequency device 72 .
  • the radio frequency device 72 receives information through the antenna 71, and sends the received information to the baseband device 73 for processing.
  • the baseband device 73 processes the information to be sent and sends it to the radio frequency device 72
  • the radio frequency device 72 processes the received information and sends it out through the antenna 71 .
  • the above-mentioned frequency band processing device may be located in the baseband device 73, and the method performed by the network side device in the above embodiment may be implemented in the baseband device 73, and the baseband device 73 includes a processor 74 and a memory 75.
  • the baseband device 73 may include at least one baseband board, on which a plurality of chips are arranged, as shown in FIG.
  • the baseband device 73 may also include a network interface 76 for exchanging information with the radio frequency device 72, such as a common public radio interface (CPRI for short).
  • a network interface 76 for exchanging information with the radio frequency device 72, such as a common public radio interface (CPRI for short).
  • CPRI common public radio interface
  • the network-side device in the embodiment of the present invention also includes: instructions or programs stored in the memory 75 and operable on the processor 74, and the processor 74 calls the instructions or programs in the memory 75 to execute the modules shown in FIG. 7 To avoid duplication, the method of implementation and to achieve the same technical effect will not be repeated here.
  • the embodiment of the present application also provides a readable storage medium.
  • the readable storage medium stores programs or instructions.
  • the program or instructions are executed by the processor, the various processes of the above-mentioned channel estimation method embodiments can be achieved, and the same To avoid repetition, the technical effects will not be repeated here.
  • the processor is the processor in the terminal described in the foregoing embodiments.
  • the readable storage medium includes computer readable storage medium, such as computer read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk, etc.
  • the embodiment of the present application further provides a chip, the chip includes a processor and a communication interface, the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the above channel estimation method embodiment
  • the chip includes a processor and a communication interface
  • the communication interface is coupled to the processor
  • the processor is used to run programs or instructions to implement the above channel estimation method embodiment
  • the chip mentioned in the embodiment of the present application may also be called a system-on-chip, a system-on-chip, a system-on-a-chip, or a system-on-a-chip.
  • the term “comprising”, “comprising” or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article or apparatus comprising a set of elements includes not only those elements, It also includes other elements not expressly listed, or elements inherent in the process, method, article, or device. Without further limitations, an element defined by the phrase “comprising a " does not preclude the presence of additional identical elements in the process, method, article, or apparatus comprising that element.
  • the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved. Functions are performed, for example, the described methods may be performed in an order different from that described, and various steps may also be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.
  • the methods of the above embodiments can be implemented by means of software plus a necessary general-purpose hardware platform, and of course also by hardware, but in many cases the former is better implementation.
  • the technical solution of the present application can be embodied in the form of computer software products, which are stored in a storage medium (such as ROM/RAM, magnetic disk, etc.) , CD-ROM), including several instructions to make a terminal (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) execute the methods described in the various embodiments of the present application.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Power Engineering (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

本申请公开一种信道估计方法、装置、终端及网络侧设备，属于通信技术领域。信道估计方法，包括：终端接收网络侧设备发送的导频信号，第一时域传输单元与第二时域传输单元中所述导频信号所占的资源块RB至少部分不同；根据所述第一时域传输单元和所述第二时域传输单元上的导频信号，对第三时域传输单元进行信道估计。本申请实施例的技术方案能够减少导频开销，提高信道估计和预测的精度，提高通信系统的性能。

Description

信道估计方法、装置、终端及网络侧设备
相关申请的交叉引用
本申请主张在2021年10月22日在中国提交的中国专利申请No.202111234895.1的优先权，其全部内容通过引用包含于此。
技术领域
本申请涉及通信技术领域，具体涉及一种信道估计方法、装置、终端及网络侧设备。
背景技术
利用大规模多输入多输出(Multiple Input Multiple Output，MIMO)技术形成的大规模天线阵列，可以同时支持更多用户发送和接收信号，从而将移动网络的信道容量以及数据流量提升数十倍或更大，同时能实现多用户之间干扰的急剧降低。
然而在大规模MIMO系统中，随着天线规模的急剧增加，导频开销和信道估计的复杂度都有数量级的增加。这已经成为制约大规模MIMO走向大规模商用的关键瓶颈问题之一。
现有通信系统中，导频信道状态信息-参考信号(Channel State Information Reference Signal，CSI-RS)发送是以资源块(Resource Block，RB)为基本单位。每个资源块RB在频域包含12个子载波，在时域包含6-7个正交频分复用(Orthogonal Frequency Division Multiplex，OFDM)符号。在每个RB上都有CSI-RS发送，将会导致导频开销较大，影响通信系统的性能。
发明内容
本申请实施例提供了一种信道估计方法、装置、终端及网络侧设备，能够减少导频开销，提高通信系统的性能。
第一方面，本申请实施例提供了一种信道估计方法，包括：
终端接收网络侧设备发送的导频信号，第一时域传输单元与第二时域传 输单元中的所述导频信号所占的资源块RB至少部分不同；
根据所述第一时域传输单元和所述第二时域传输单元上的导频信号，对第三时域传输单元进行信道估计。
第二方面，本申请实施例提供了一种信道估计方法，包括：
网络侧设备发送导频信号，第一时域传输单元与第二时域传输单元中的所述导频信号所占的资源块RB至少部分不同。
第三方面，本申请实施例提供了一种信道估计装置，应用于终端，所述装置包括：
接收模块，用于接收网络侧设备发送的导频信号，第一时域传输单元与第二时域传输单元中的所述导频信号所占的资源块RB至少部分不同；
信道估计模块，用于根据所述第一时域传输单元和所述第二时域传输单元上的导频信号，对第三时域传输单元进行信道估计。
第四方面，本申请实施例提供了一种信道估计装置，应用于网络侧设备，所述装置包括：
发送模块，用于发送导频信号，第一时域传输单元与第二时域传输单元中的所述导频信号所占的资源块RB至少部分不同。
第五方面，提供了一种终端，该终端包括处理器、存储器及存储在所述存储器上并可在所述处理器上运行的程序或指令，所述程序或指令被所述处理器执行时实现如第一方面所述的方法的步骤。
第六方面，提供了一种终端，包括处理器及通信接口，其中，所述通信接口用于接收网络侧设备发送的导频信号，第一时域传输单元与第二时域传输单元中的所述导频信号所占的资源块RB至少部分不同；所述处理器用于根据所述第一时域传输单元和所述第二时域传输单元上的导频信号，对第三时域传输单元进行信道估计。
第七方面，提供了一种网络侧设备，该网络侧设备包括处理器、存储器及存储在所述存储器上并可在所述处理器上运行的程序或指令，所述程序或指令被所述处理器执行时实现如第二方面所述的方法的步骤。
第八方面，提供了一种网络侧设备，包括处理器及通信接口，其中，所述通信接口用于发送导频信号，第一时域传输单元与第二时域传输单元中的 所述导频信号所占的资源块RB至少部分不同。
第九方面，提供了一种可读存储介质，所述可读存储介质上存储程序或指令，所述程序或指令被处理器执行时实现如第一方面所述的方法的步骤，或者实现如第二方面所述的方法的步骤。
第十方面，提供了一种芯片，所述芯片包括处理器和通信接口，所述通信接口和所述处理器耦合，所述处理器用于运行程序或指令，实现如第一方面所述的方法，或实现如第二方面所述的方法。
第十一方面，提供了一种计算机程序产品，所述计算机程序产品被存储在非瞬态的存储介质中，所述计算机程序产品被至少一个处理器执行以实现如第一方面或第二方面所述的方法的步骤。
在本申请实施例中，网络侧设备向终端发送导频信号，第一时域传输单元与第二时域传输单元中的所述导频信号所占的资源块RB至少部分不同，这样仅在部分RB上发送导频信号，能够减少导频开销，提高通信系统的性能。
附图说明
图1表示无线通信系统的示意图；
图2表示本申请实施例由终端执行的信道估计方法的流程示意图；
图3表示本申请实施例由网络侧设备执行的信道估计方法的流程示意图；
图4和图5表示本申请实施例发送CSI-RS的示意图；
图6表示本申请实施例应用于终端的信道估计装置的结构示意图；
图7表示本申请实施例应用于网络侧设备的信道估计装置的结构示意图；
图8表示本申请实施例的通信设备的组成示意图；
图9表示本申请实施例的终端的组成示意图；
图10表示本申请实施例的网络侧设备的组成示意图；
图11表示informer网络结构图；
图12表示多头注意(multi-head attention)机制的示意图；
图13表示标记多头注意(masked multi-head attention)机制的示意图。
具体实施方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚描述，显然，所描述的实施例是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员所获得的所有其他实施例，都属于本申请保护的范围。
本申请的说明书和权利要求书中的术语“第一”、“第二”等是用于区别类似的对象，而不用于描述特定的顺序或先后次序。应该理解这样使用的术语在适当情况下可以互换，以便本申请的实施例能够以除了在这里图示或描述的那些以外的顺序实施，且“第一”、“第二”所区别的对象通常为一类，并不限定对象的个数，例如第一对象可以是一个，也可以是多个。此外，说明书以及权利要求中“和/或”表示所连接对象的至少其中之一，字符“/”一般表示前后关联对象是一种“或”的关系。
值得指出的是，本申请实施例所描述的技术不限于长期演进型(Long Term Evolution，LTE)/LTE的演进(LTE-Advanced，LTE-A)系统，还可用于其他无线通信系统，诸如码分多址(Code Division Multiple Access，CDMA)、时分多址(Time Division Multiple Access，TDMA)、频分多址(Frequency Division Multiple Access，FDMA)、正交频分多址(Orthogonal Frequency Division Multiple Access，OFDMA)、单载波频分多址(Single-carrier Frequency-Division Multiple Access，SC-FDMA)和其他系统。本申请实施例中的术语“系统”和“网络”常被可互换地使用，所描述的技术既可用于以上提及的系统和无线电技术，也可用于其他系统和无线电技术。以下描述出于示例目的描述了新空口(New Radio，NR)系统，并且在以下大部分描述中使用NR术语，但是这些技术也可应用于NR系统应用以外的应用，如第6代(6th Generation，6G)通信系统。
图1示出本申请实施例可应用的一种无线通信系统的框图。无线通信系统包括终端11和网络侧设备12。其中，终端11也可以称作终端设备或者用户终端(User Equipment，UE)，终端11可以是手机、平板电脑(Tablet Personal Computer)、膝上型电脑(Laptop Computer)或称为笔记本电脑、个人数字助理(Personal Digital Assistant，PDA)、掌上电脑、上网本、超级移动个人计 算机(ultra-mobile personal computer，UMPC)、移动上网装置(Mobile Internet Device，MID)、可穿戴式设备(Wearable Device)或车载设备(Vehicle User Equipment，VUE)、行人终端(Pedestrian User Equipment，PUE)等终端侧设备，可穿戴式设备包括：智能手表、手环、耳机、眼镜等。需要说明的是，在本申请实施例并不限定终端11的具体类型。网络侧设备12可以是基站或核心网，其中，基站可被称为节点B、演进节点B、接入点、基收发机站(Base Transceiver Station，BTS)、无线电基站、无线电收发机、基本服务集(Basic Service Set，BSS)、扩展服务集(Extended Service Set，ESS)、B节点、演进型B节点(eNB)、家用B节点、家用演进型B节点、无线局域网(Wireless Local Area Network，WLAN)接入点、无线保真(Wireless Fidelity，WiFi)节点、发送接收点(Transmitting Receiving Point，TRP)或所述领域中其他某个合适的术语，只要达到相同的技术效果，所述基站不限于特定技术词汇，需要说明的是，在本申请实施例中仅以NR系统中的基站为例，但是并不限定基站的具体类型，所述核心网设备可以是位置管理设备，例如，所位置管理功能(本地管理功能(Location Management Function，LMF)、演进型服务移动位置中心(Evolutionary-Service Mobile Location Center E-SMLC))等。
利用大规模MIMO技术形成的大规模天线阵列，可以同时支持更多用户发送和接收信号，从而将移动网络的信道容量以及数据流量提升数十倍或更大，同时能实现多用户之间干扰的急剧降低。因此从它被提出就一直受到广大研究人员的持续高度关注。为了支持宽带无线通信，从4G开始OFDM就成为移动通信的底层技术。该技术可以有效的对抗多径干扰，将频域频率选择性信道划分为多个平衰落的子信道来支持无线传输。OFDM结合大规模MIMO已经是现在和未来无线通信的基本框架。
然而在大规模MIMO系统中，随着天线规模的急剧增加，导频开销和信道估计的复杂度都有数量级的增加。这已经成为制约大规模MIMO走向大规模商用的关键瓶颈问题之一。
现有通信系统中，导频信道状态信息-参考信号CSI-RS发送是以资源块RB为基本单位。每个资源块RB在频域包含12个子载波，在时域包含6-7个OFDM符号。在每个RB上都有CSI-RS发送。为了减少导频开销，导频 信号CSI-RS不是在每个传输时间间隔(Transmission Time Interval，TTI)都发送的，而是间隔几个TTI发送一次。因此在没有发送CSI-RS的TTI，其真实的大规模MIMO的信道是无法知道的。为此，相关技术一般采用最近发送CSI-RS的TTI估计的信道作为当前TTI的信道，由此来从码本里寻找最优的预编码。由于信道是变化的，最近发送CSI-RS的TTI估计的信道与当前TTI的信道存在偏差，并且运动速度越快，偏差越大，进而导致信道反馈和发送端预编码的操作发生偏差，引起系统性能的下降。
本申请实施例提供一种信道估计方法，由终端执行，如图2所示，所述方法包括：
步骤101：终端接收网络侧设备发送的导频信号，第一时域传输单元与第二时域传输单元中的所述导频信号所占的资源块RB至少部分不同；
步骤102：根据所述第一时域传输单元和所述第二时域传输单元上的导频信号，对第三时域传输单元进行信道估计。
其中，第三时域传输单元可以与第一时域传输单元相同，也可以不同；第三时域传输单元可以与第二时域传输单元相同，也可以不同；第一时域传输单元与第二时域传输单元为不同的时域传输单元。
在本申请实施例中，终端接收网络侧设备发送的导频信号，第一时域传输单元与第二时域传输单元中的所述导频信号所占的资源块RB至少部分不同，即网络侧设备仅在部分RB上发送导频信号，能够减少导频开销；另外，若发送导频信号的RB的数量不变，由于仅在时域传输单元中的部分RB上发送导频信号，能够使得发送导频信号的时域传输单元变多，发送导频信号的时域传输单元之间的间隔减小，能够提高信道估计的精度，提高通信系统的性能。
一些实施例中，所述根据所述第一时域传输单元和所述第二时域传输单元上的导频信号，对第三时域传输单元进行信道估计包括：
根据所述第一时域传输单元上的导频信号、所述第二时域传输单元上的导频信号和预先训练的神经网络模型进行信道估计，得到所述第三时域传输单元内所有RB上的信道。
本实施例中，利用所述第一时域传输单元上的导频信号、所述第二时域 传输单元上的导频信号可以得到没有发送导频信号的RB上的信道，由于发送导频信号的RB与未发送导频信号的RB可以位于同一时域传输单元，相关性很强，因此能够提高信道估计的精度，提高通信系统的性能。
一些实施例中，所述根据所述第一时域传输单元和所述第二时域传输单元上的导频信号，对第三时域传输单元进行信道估计包括：
根据所述第一时域传输单元上的导频信号、所述第二时域传输单元上的导频信号和预先训练的神经网络模型进行信道估计，得到当前时域传输单元之后L个时域传输单元内所有RB上的信道，L为正整数。
本实施例还可以利用所述第一时域传输单元上的导频信号、所述第二时域传输单元上的导频信号对之后的信道进行预测，能够预测未来没有导频情况的信道，从而极大的减少了大导频开销，也提高了系统的性能。
一些实施例中，所述所有RB为按照预定义规则或预配置方式确定的RB。
一些实施例中，所述按照预定义规则或预配置方式确定的RB至少包括第一时隙传输单元中导频信号所占用的RB和第二时隙传输单元中导频信号所占用的RB。
为了保证信道估计和信道预测的精度，利用最近的K个发送导频信号的时域传输单元上的导频信号进行信道估计，K为正整数。也就是利用当前时域传输单元及当前时域传输单元之前K-1个发送导频信号的时域传输单元进行信道估计。
一些实施例中，导频信号在一半的RB上发送，所述终端接收网络侧设备发送的导频信号包括：
所述终端接收网络侧设备在第一时域传输单元的第一RB上发送的导频信号；
所述终端接收网络侧设备在第二时域传输单元的第二RB上发送的导频信号；
其中，所述第一RB与所述第二RB不同，所述第二时域传输单元为所述第一时域传输单元之后最近的发送所述导频信号的时域传输单元，所述第二时域传输单元与所述第一时域传输单元之间间隔至少一个时域传输单元。
本实施例中，不是在所有的时域传输单元上发送导频信号，而是间隔一 个或多个时域传输单元发送导频信号，若每个时域传输单元上发送导频信号的RB数量不变，可以降低导频开销。
一些实施例中，所述第一RB的序号为偶数，所述第二RB的序号为奇数；或
所述第一RB的序号为奇数，所述第二RB的序号为偶数。
比如，在某一个导频信号发送时域传输单元上，选择在序号为奇数的RB上接收导频信号，则在下一个导频信号发送时域传输单元上，选择在序号为偶数的RB上接收导频信号；或者，在某一个导频信号发送时域传输单元上，选择在序号为偶数的RB上接收导频信号，则在下一个导频信号发送时域传输单元上，选择在序号为奇数的RB上接收导频信号。
本实施例还包括训练得到神经网络模型的步骤，所述训练得到所述神经网络模型的步骤包括至少如下之一：
建立步骤，建立神经网络初始模型；
训练步骤，利用训练数据对所述神经网络初始模型进行训练，得到训练后的神经网络初始模型；其中，所述训练数据包括神经网络初始模型的输入数据和对应的实际信道数据，所述输入数据为连续K个发送导频信号的时域传输单元的信道估计结果，每个时域传输单元的信道估计结果的长度为M×N，所述神经网络初始模型的输出为第K个发送导频信号的时域传输单元及之后连续L个时域传输单元内所有M个RB上N个天线的信道估计结果，M，N，K，L为正整数；
判断步骤，若所述训练后的神经网络初始模型的输出与对应的实际信道数据的均方误差大于或等于预设阈值或未达到预设的迭代次数，转向所述训练步骤；若所述训练后的神经网络初始模型的输出与对应的实际信道数据的均方误差小于预设阈值或达到预设的迭代次数，将所述训练后的神经网络初始模型作为所述神经网络模型。
一些实施例中，所述训练得到所述神经网络模型的步骤包括至少如下之一：
训练步骤，利用训练数据对上一次训练得到的神经网络模型进行训练，得到训练后的神经网络模型；其中，所述训练数据包括上一次训练得到的神 经网络模型的输入数据和对应的实际信道数据，所述输入数据为连续K个发送导频信号的时域传输单元的信道估计结果，每个时域传输单元的信道估计结果的长度为M×N，所述上一次训练得到神经网络模型的输出为第K个发送导频信号的时域传输单元及之后连续L个时域传输单元内所有M个RB上N个天线的信道估计结果，M，N，K，L为正整数；
判断步骤，若所述训练后的神经网络模型的输出与对应的实际信道数据的均方误差大于或等于预设阈值或未达到预设的迭代次数，转向所述训练步骤；若所述训练后的神经网络模型的输出与对应的实际信道数据的均方误差小于预设阈值或达到预设的迭代次数，将所述训练后的神经网络模型作为所述神经网络模型。
其中，所述神经网络模型包括第一神经网络模型和第二神经网络模型，训练所述第一神经网络模型的输入数据中，所述连续K个发送导频信号的时域传输单元中第一个时域传输单元中的导频信号在序号为偶数的RB上发送；训练所述第二神经网络模型的输入数据中，所述连续K个发送导频信号的时域传输单元中第一个时域传输单元中的导频信号在序号为奇数的第一RB上发送。
由于第一个时域传输单元中导频信号可以在序号为偶数的RB上发送，还可以在序号为奇数的RB上发送，为了提高信号估计和信道预测的精度，需要为这两种情况分别训练神经网络模型，训练神经网络模型之后，就可以交替使用这两个神经网络模型，进行信道估计和预测。
一些实施例中，根据所述神经网络模型进行信道估计包括：
若接收到的第一个时域传输单元中的导频信号在序号为偶数的RB上发送，利用所述第一神经网络模型进行信道估计；若接收到的第一个时域传输单元中的导频信号在序号为奇数的RB上发送，利用所述第二神经网络模型进行信道估计。
本实施例中，所述导频信号包括以下至少一项：
信道状态信息参考信号CSI-RS，探测参考信号(Sounding Reference Signal，SRS)，解调参考信号(Demodulation Reference Signal，DMRS)。所述时域传输单元包括以下任一项：传输时间间隔TTI，子帧，毫秒，时隙和符号。
本申请实施例还提供了一种信道估计方法，由网络侧设备执行，如图3所示，所述方法包括：
步骤201：网络侧设备发送导频信号，第一时域传输单元与第二时域传输单元中的所述导频信号所占的资源块RB至少部分不同。
本申请实施例中，为了节省导频开销，网络侧设备并不是在每个时域传输单元的RB上都发送导频信号，而是在部分RB上发送导频信号。在每个时域传输单元内，导频信号的发送是以资源块RB为基本单位。另外，若发送导频信号的RB的数量不变，由于仅在时域传输单元中的部分RB上发送导频信号，能够使得发送导频信号的时域传输单元变多，发送导频信号的时域传输单元之间的间隔减小，能够提高信道估计的精度，提高通信系统的性能。
另外，为了进一步节省导频开销，网络侧设备还可以间隔几个时域传输单元发送一次导频信号。所述网络侧设备发送导频信号包括：
在第一时域传输单元的第一RB上发送导频信号；
在第二时域传输单元的第二RB上发送导频信号；
其中，所述第一RB与所述第二RB不同，所述第二时域传输单元为所述第一时域传输单元之后最近的发送所述导频信号的时域传输单元，所述第二时域传输单元与所述第一时域传输单元之间间隔至少一个时域传输单元。
一些实施例中，所述第一RB的序号为偶数，所述第二RB的序号为奇数；或
所述第一RB的序号为奇数，所述第二RB的序号为偶数。
即如果在某一个导频信号发送时域传输单元上，选择在序号为奇数的RB上发送导频信号，则在下一个导频信号发送时域传输单元上，选择在序号为偶数的RB上发送导频信号。依次类推，在各个不同的导频信号发送时域传输单元上，网络侧设备交替选择在序号为奇数的RB和序号为偶数的RB上，发送导频信号。
本实施例中，所述导频信号包括以下至少一项：
信道状态信息参考信号CSI-RS，探测参考信号SRS，解调参考信号DMRS。所述时域传输单元包括以下任一项：传输时间间隔TTI，子帧，毫秒，时隙和符号。
以导频信号为CSI-RS，时域传输单元为TTI为例，本实施例基于OFDM的大规模MIMO系统，在发送端有N个天线。为了能使终端用户获得下行大规模MIMO的信道信息，网络侧设备发送N个端口的导频CSI-RS。为了减少导频开销，导频信号CSI-RS不是在每个TTI都发送的，而是间隔S个TTI发送一次。在每个TTI内，导频CSI-RS发送是以RB为基本单位。每个RB在频域包含12个子载波，在时域包含多个OFDM符号(等于每个TTI包含的OFDM符号)。假定每个TTI有M个RB，每个RB都有一个序号，导频设计和资源分配都是以RB为基本单位进行的。本实施例中，如图4所示，导频CSI-RS不是在每个RB上都发送的，而是只在一半的RB上发送。如果在某一个CSI-RS发送TTI，选择在序号为奇数的RB上发送CSI-RS，则在下一个CSI-RS发送TTI上，选择在序号为偶数的RB上发送CSI-RS。依次类推，在各个不同的CSI-RS发送TTI上，网络侧设备交替选择在序号为奇数的RB和序号为偶数的RB上，发送CSI-RS。
接收端(即终端)接收到网络侧设备发送CSI-RS的TTI上的信号后，可以利用其中的CSI-RS估计出相应RB上N个天线的信道，但是无法精确知道该TTI上没有发送CSI-RS的RB上的信道，另外，该TTI和下一次发送CSI-RS TTI之间的S个TTI上，所有RB上的N个天线的信道也是无法精确知道的。本实施例利用以往K个发送CSI-RS的TTI估计到的各个RB上的信道，基于注意力机制的神经网络模型，不仅可以估计出当前TTI(用第K个TTI表示)上没有发送CSI-RS的RB上的N个天线的信道，还可以预测出接下来的L个没有发送CSI-RS的TTI上所有RB上的信道，如图5所示。
本实施例中，神经网络模型采用基于注意力机制的informer网络结构，该神经网络模型是采用编码器-解码器架构，如图11所示。
其中，编码器由多层的多头概率稀疏自注意(multi-head ProbSparse Self-attention)和自注意浓缩(Self-attention Distilling)构成。
对于multi-head ProbSparse Self-attention，如图12所示，它的输入为Q、V和K三个向量，其计算过程如下：
1、Q，V，K分别通过n次线性变换得到n组Q，K，V，这里n对应着n-head。
2、对于每一组Q,K,V，通过Attetion(缩放点积注意(scaled Dot-product Attention))得到相应输出头Head。计算方法如下：
Figure PCTCN2022126226-appb-000001
3、拼接所有的Head，并将其线性映射为最终输出。
对于Self-attention Distilling，self-attention浓缩是发现随着编码器(Encoder)层数的加深，由于序列中每个位置的输出已经包含了序列中其他元素的信息(self-attention的职责)，可以缩短输入序列的长度。所以Encoder有类似于金字塔结构。
作为ProbSparse Self-attention的自然结果，encoder的特征映射会带来冗余组合，利用distilling对具有支配特征的优势特征进行特权化，并在下一层生成集中自注意(focus self-attention)特征映射。受扩展卷积的启发，这里的“distilling”过程从第j层往j+1推进的方法如下:
Figure PCTCN2022126226-appb-000002
其中在[.]AB包含多头ProbSparse自注意和注意块中的基本操作，Conv1d(·)利用ELU(·)激活函数在时间维度上执行一维卷积滤波器(核宽度＝3)，这里添加了一个具有步长(stride)2和向下取样(down-sample)的最大池化层。
解码器由单层的multi-head ProbSparse Self-attention和标记多头注意力(Masked multi-head attention)构成。
如图12所示，multi-head attention的输入为Q、V和K三个向量，其计算过程如下：
1、Q，V，K分别通过n次线性变换得到n组Q，K，V，这里n对应着n-head。
2、对于每一组Q,K,V，通过Attetion(scaled Dot-product Attention)得到相应输出Head。计算方法如下：
Figure PCTCN2022126226-appb-000003
3、拼接所有的Head，并将其线性映射为最终输出。
Masked multi-head attention应用于ProbSparse自注意计算。它可以防止 每个位置都关注未来的位置，从而避免了自回归。原理如图13所示，这里将点积的结果设置为负无穷。
本实施例的神经网络模型的输入为K个序列X t，每个序列长度为M×N，元素的值为由CSI-RS估计得到的M个RB上N个天线的信道，没有发送CSI-RS的RB上的信道值用0代替。因此X t为一个MN×K的矩阵。
如果用于预测的K个TTI中，第一个TTI中CSI-RS在序号为奇数RB上发送，X t可以表示为：
Figure PCTCN2022126226-appb-000004
其中
Figure PCTCN2022126226-appb-000005
表示第k个TTI上，第i个RB上第j个天线的信道。x t i为X t的第i列，即第i个TTI上的信道估计结果。
如果用于预测的K个TTI中，第一个TTI中CSI-RS在序号为偶数RB上发送，X t可以表示为：
Figure PCTCN2022126226-appb-000006
神经网络模型的输出为L+1个序列Y t，为第K个TTI及之后的连续L个TTI上所有M个RB上N个天线的信道的估计值和预测值。
Figure PCTCN2022126226-appb-000007
其中
Figure PCTCN2022126226-appb-000008
表示第k个TTI上，第i个RB上第j个天线的信道的预测值。
本实施例中，在利用神经网络模型进行信道估计和预测时，首先，将K个TTI上的CSI-RS估计的信道向量序列X t输入到编码器，编码器包括多层的注意力机制复合网络，每一层都由multi-header ProbSparse self-attention和Self-attention Distilling构成。经过多层的注意力机制复合网络后，产生编码器的输出B t。然后B t输入到解码器。解码器只有一层，由Masked ProbSparse multi-head attention和multi-head attention构成，其中Masked ProbSparse multi-head attention的输入为一个K/2+L+1长度的向量序列X t，它的前K/2个序列为X t的后半段，后L+1个向量序列全为0向量。即
Figure PCTCN2022126226-appb-000009
Masked ProbSparse multi-head attention的输出和编码器的输出一同传递给multi-head attention后，产生multi-head attention的输出。multi-head attention的输出再经过一个全连接网络后，输出预测结果Y t。
为了使用基于注意力机制的informer网络结构进行信道估计和预测，informer网络的网络参数需要进行训练。训练时，训练数据中X t来自各个TTI上CSI-RS信道估计，匹配的目标为K到K+L TTI的实际信道H t。利用多组训练数据对informer网络进行训练，每组训练数据包括informer网络的输入数据(各个TTI上CSI-RS信道估计结果)和对应的实际信道数据H t，利用连续K个TTI的信道估计结果进行训练，训练优化的目标为神经网络模型的输出Y t和实际信道H t之间的均方误差最小。即
Figure PCTCN2022126226-appb-000010
或者，训练优化的目标可以为迭代次数达到预设次数，比如100次。
Figure PCTCN2022126226-appb-000011
由于第一个TTI中导频信号可以在序号为偶数的RB上发送，还可以在序号为奇数的RB上发送，为了提高信号估计和信道预测的精度，需要为这两种情况分别训练神经网络模型，训练神经网络模型之后，就可以交替使用这两个神经网络模型，进行信道估计和预测。
本实施例可以应用于LTE、GSM和CDMA技术采用大规模MIMO的应用场景，利用本实施例的基于注意力机制的信道估计和预测方法，利用已知的信道信息，能够预测未来没有导频信号的信道，从而极大的减少了导频开销，也提高了系统的性能。
需要说明的是，本申请实施例提供的信道估计方法，执行主体可以为信道估计装置，或者该信道估计装置中的用于执行加载信道估计方法的模块。本申请实施例中以信道估计装置执行加载信道估计方法为例，说明本申请实施例提供的信道估计方法。
本申请实施例提供了一种信道估计装置，应用于终端300，如图6所示，所述装置包括：
接收模块310，用于接收网络侧设备发送的导频信号，第一时域传输单 元与第二时域传输单元中所述导频信号所占的资源块RB至少部分不同；
信道估计模块320，用于根据所述第一时域传输单元和所述第二时域传输单元上的导频信号，对第三时域传输单元进行信道估计。
在本申请实施例中，终端接收网络侧设备发送的导频信号，第一时域传输单元与第二时域传输单元中的所述导频信号所占的资源块RB至少部分不同，即网络侧设备仅在部分RB上发送导频信号，能够减少导频开销，提高通信系统的性能。
一些实施例中，所述信道估计模块具体用于根据所述第一时域传输单元上的导频信号、所述第二时域传输单元上的导频信号和预先训练的神经网络模型进行信道估计，得到所述第三时域传输单元内所有RB上的信道。
一些实施例中，所述信道估计模块具体用于根据所述第一时域传输单元上的导频信号、所述第二时域传输单元上的导频信号和预先训练的神经网络模型进行信道估计，得到当前时域传输单元之后L个时域传输单元内所有RB上的信道，L为正整数。
一些实施例中，所述所有RB为按照预定义规则或预配置方式确定的RB。
一些实施例中，所述按照预定义规则或预配置方式确定的RB至少包括第一时隙传输单元中导频信号所占用的RB和第二时隙传输单元中导频信号所占用的RB。
一些实施例中，所述信道估计模块具体用于利用最近的K个发送导频信号的时域传输单元上的导频信号进行信道估计，K为正整数。
一些实施例中，所述接收模块具体用于接收网络侧设备在第一时域传输单元的第一RB上发送的导频信号；接收网络侧设备在第二时域传输单元的第二RB上发送的导频信号；
其中，所述第一RB与所述第二RB不同，所述第二时域传输单元为所述第一时域传输单元之后最近的发送所述导频信号的时域传输单元，所述第二时域传输单元与所述第一时域传输单元之间间隔至少一个时域传输单元。
一些实施例中，所述第一RB的序号为偶数，所述第二RB的序号为奇数；或
所述第一RB的序号为奇数，所述第二RB的序号为偶数。
一些实施例中，还包括训练模块，用于训练得到所述神经网络模型；
其中，所述训练得到所述神经网络模型的步骤包括至少如下之一：
建立步骤，建立神经网络初始模型；
训练步骤，利用训练数据对所述神经网络初始模型进行训练，得到训练后的神经网络初始模型；其中，所述训练数据包括神经网络初始模型的输入数据和对应的实际信道数据，所述输入数据为连续K个发送导频信号的时域传输单元的信道估计结果，每个时域传输单元的信道估计结果的长度为M×N，所述神经网络初始模型的输出为第K个发送导频信号的时域传输单元及之后连续L个时域传输单元内所有M个RB上N个天线的信道估计结果，M，N，K，L为正整数；
判断步骤，若所述训练后的神经网络初始模型的输出与对应的实际信道数据的均方误差大于或等于预设阈值或未达到预设的迭代次数，转向所述训练步骤；若所述训练后的神经网络初始模型的输出与对应的实际信道数据的均方误差小于预设阈值或达到预设的迭代次数，将所述训练后的神经网络初始模型作为所述神经网络模型。
一些实施例中，所述训练模块具体用于执行至少如下之一：
训练步骤，利用训练数据对上一次训练得到的神经网络模型进行训练，得到训练后的神经网络模型；其中，所述训练数据包括上一次训练得到的神经网络模型的输入数据和对应的实际信道数据，所述输入数据为连续K个发送导频信号的时域传输单元的信道估计结果，每个时域传输单元的信道估计结果的长度为M×N，所述上一次训练得到神经网络模型的输出为第K个发送导频信号的时域传输单元及之后连续L个时域传输单元内所有M个RB上N个天线的信道估计结果，M，N，K，L为正整数；
判断步骤，若所述训练后的神经网络模型的输出与对应的实际信道数据的均方误差大于或等于预设阈值或未达到预设的迭代次数，转向所述训练步骤；若所述训练后的神经网络模型的输出与对应的实际信道数据的均方误差小于预设阈值或达到预设的迭代次数，将所述训练后的神经网络模型作为所述神经网络模型。
一些实施例中，所述神经网络模型包括第一神经网络模型和第二神经网 络模型，训练所述第一神经网络模型的输入数据中，所述连续K个发送导频信号的时域传输单元中第一个时域传输单元中的导频信号在序号为偶数的RB上发送；训练所述第二神经网络模型的输入数据中，所述连续K个发送导频信号的时域传输单元中第一个时域传输单元中的导频信号在序号为奇数的第一RB上发送。
一些实施例中，所述信道估计模块具体用于若接收到的第一个时域传输单元中的导频信号在序号为偶数的RB上发送，利用所述第一神经网络模型进行信道估计；若接收到的第一个时域传输单元中的导频信号在序号为奇数的RB上发送，利用所述第二神经网络模型进行信道估计。
一些实施例中，所述导频信号包括以下至少一项：
信道状态信息参考信号CSI-RS，探测参考信号SRS，解调参考信号DMRS。
一些实施例中，所述时域传输单元包括以下任一项：传输时间间隔TTI，子帧，毫秒，时隙和符号。
本申请实施例中的信道估计装置可以是装置，具有操作系统的装置或电子设备，也可以是终端中的部件、集成电路、或芯片。该装置或电子设备可以是移动终端，也可以为非移动终端。示例性的，移动终端可以包括但不限于上述所列举的终端11的类型，非移动终端可以为服务器、网络附属存储器(Network Attached Storage，NAS)、个人计算机(personal computer，PC)、电视机(television，TV)、柜员机或者自助机等，本申请实施例不作具体限定。
本申请实施例提供的信道估计装置能够实现图2的方法实施例实现的各个过程，并达到相同的技术效果，为避免重复，这里不再赘述。
本申请实施例提供了一种信道估计装置，应用于网络侧设备400，如图7所示，所述装置包括：
发送模块410，用于发送导频信号，第一时域传输单元与第二时域传输单元中的所述导频信号所占的资源块RB至少部分不同。
本申请实施例中，为了节省导频开销，网络侧设备并不是在每个时域传输单元的RB上都发送导频信号，而是在部分RB上发送导频信号。在每个时域传输单元内，导频信号的发送是以资源块RB为基本单位。
另外，为了进一步节省导频开销，网络侧设备还可以间隔几个时域传输单元发送一次导频信号。一些实施例中，所述发送模块具体用于在第一时域传输单元的第一RB上发送导频信号；在第二时域传输单元的第二RB上发送导频信号；
其中，所述第一RB与所述第二RB不同，所述第二时域传输单元为所述第一时域传输单元之后最近的发送所述导频信号的时域传输单元，所述第二时域传输单元与所述第一时域传输单元之间间隔至少一个时域传输单元。
一些实施例中，所述第一RB的序号为偶数，所述第二RB的序号为奇数；或
所述第一RB的序号为奇数，所述第二RB的序号为偶数。
一些实施例中，所述导频信号包括以下至少一项：
信道状态信息参考信号CSI-RS，探测参考信号SRS，解调参考信号DMRS。所述时域传输单元包括以下任一项：传输时间间隔TTI，子帧，毫秒，时隙和符号。
本申请实施例提供的信道估计装置能够实现图3的方法实施例实现的各个过程，并达到相同的技术效果，为避免重复，这里不再赘述。
可选的，如图8所示，本申请实施例还提供一种通信设备500，包括处理器501，存储器502，存储在存储器502上并可在所述处理器501上运行的程序或指令，例如，该通信设备500为终端时，该程序或指令被处理器501执行时实现上述应用于终端的信道估计方法实施例的各个过程，且能达到相同的技术效果。该通信设备500为网络侧设备时，该程序或指令被处理器501执行时实现上述应用于网络侧设备的信道估计方法实施例的各个过程，且能达到相同的技术效果，为避免重复，这里不再赘述。
本申请实施例还提供一种终端，包括处理器和通信接口，其中，所述通信接口用于接收网络侧设备发送的导频信号，第一时域传输单元与第二时域传输单元中的所述导频信号所占的资源块RB至少部分不同；所述处理器用于根据所述第一时域传输单元和所述第二时域传输单元上的导频信号，对第三时域传输单元进行信道估计。
具体地，图9为实现本申请实施例的一种终端的硬件结构示意图。
该终端1000包括但不限于：射频单元1001、网络模块1002、音频输出单元1003、输入单元1004、传感器1005、显示单元1006、用户输入单元1007、接口单元1008、存储器1009、以及处理器1010等中的至少部分部件。
本领域技术人员可以理解，终端1000还可以包括给各个部件供电的电源(比如电池)，电源可以通过电源管理系统与处理器1010逻辑相连，从而通过电源管理系统实现管理充电、放电、以及功耗管理等功能。图9中示出的终端结构并不构成对终端的限定，终端可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件布置，在此不再赘述。
应理解的是，本申请实施例中，输入单元1004可以包括图形处理器(Graphics Processing Unit，GPU)10041和麦克风10042，图形处理器10041对在视频捕获模式或图像捕获模式中由图像捕获装置(如摄像头)获得的静态图片或视频的图像数据进行处理。显示单元1006可包括显示面板10061，可以采用液晶显示器、有机发光二极管等形式来配置显示面板10061。用户输入单元1007包括触控面板10071以及其他输入设备10072。触控面板10071，也称为触摸屏。触控面板10071可包括触摸检测装置和触摸控制器两个部分。其他输入设备10072可以包括但不限于物理键盘、功能键(比如音量控制按键、开关按键等)、轨迹球、鼠标、操作杆，在此不再赘述。
本申请实施例中，射频单元1001将来自网络侧设备的下行数据接收后，给处理器1010处理；另外，将上行的信道估计给网络侧设备。通常，射频单元1001包括但不限于天线、至少一个放大器、收发信机、耦合器、低噪声放大器、双工器等。
存储器1009可用于存储软件程序或指令以及各种数据。存储器1009可主要包括存储程序或指令区和存储数据区，其中，存储程序或指令区可存储操作系统、至少一个功能所需的应用程序或指令(比如声音播放功能、图像播放功能等)等。此外，存储器1009可以包括高速随机存取存储器，还可以包括非易失性存储器，其中，非易失性存储器可以是只读存储器(Read-Only Memory，ROM)、可编程只读存储器(Programmable ROM，PROM)、可擦除可编程只读存储器(Erasable PROM，EPROM)、电可擦除可编程只读存储器(Electrically EPROM，EEPROM)或闪存。例如至少一个磁盘存储器件、闪存 器件、或其他非易失性固态存储器件。
处理器1010可包括一个或多个处理单元；可选的，处理器1010可集成应用处理器和调制解调处理器，其中，应用处理器主要处理操作系统、用户界面和应用程序或指令等，调制解调处理器主要处理无线通信，如基带处理器。可以理解的是，上述调制解调处理器也可以不集成到处理器1010中。
其中，处理器1010，用于接收网络侧设备发送的导频信号，第一时域传输单元与第二时域传输单元中的所述导频信号所占的资源块RB至少部分不同；根据所述第一时域传输单元和所述第二时域传输单元上的导频信号，对第三时域传输单元进行信道估计。
一些实施例中，处理器1010，用于根据所述第一时域传输单元上的导频信号、所述第二时域传输单元上的导频信号和预先训练的神经网络模型进行信道估计，得到所述第三时域传输单元内所有RB上的信道。
一些实施例中，处理器1010，用于根据所述第一时域传输单元上的导频信号、所述第二时域传输单元上的导频信号和预先训练的神经网络模型进行信道估计，得到当前时域传输单元之后L个时域传输单元内所有RB上的信道，L为正整数。
一些实施例中，所述所有RB为按照预定义规则或预配置方式确定的RB。
一些实施例中，所述按照预定义规则或预配置方式确定的RB至少包括第一时隙传输单元中导频信号所占用的RB和第二时隙传输单元中导频信号所占用的RB。
一些实施例中，所述处理器1010具体用于利用最近的K个发送导频信号的时域传输单元上的导频信号进行信道估计，K为正整数。
一些实施例中，处理器1010，用于接收网络侧设备在第一时域传输单元的第一RB上发送的导频信号；接收网络侧设备在第二时域传输单元的第二RB上发送的导频信号；
其中，所述第一RB与所述第二RB不同，所述第二时域传输单元为所述第一时域传输单元之后最近的发送所述导频信号的时域传输单元，所述第二时域传输单元与所述第一时域传输单元之间间隔至少一个时域传输单元。
一些实施例中，所述第一RB的序号为偶数，所述第二RB的序号为奇数； 或
所述第一RB的序号为奇数，所述第二RB的序号为偶数。
一些实施例中，处理器1010，用于训练得到所述神经网络模型，其中，所述训练得到所述神经网络模型的步骤包括至少如下之一：
建立步骤，建立神经网络初始模型；
训练步骤，利用训练数据对所述神经网络初始模型进行训练，得到训练后的神经网络初始模型；其中，所述训练数据包括神经网络初始模型的输入数据和对应的实际信道数据，所述输入数据为连续K个发送导频信号的时域传输单元的信道估计结果，每个时域传输单元的信道估计结果的长度为M×N，所述神经网络初始模型的输出为第K个发送导频信号的时域传输单元及之后连续L个时域传输单元内所有M个RB上N个天线的信道估计结果，M，N，K，L为正整数；
判断步骤，若所述训练后的神经网络初始模型的输出与对应的实际信道数据的均方误差大于或等于预设阈值或未达到预设的迭代次数，转向所述训练步骤；若所述训练后的神经网络初始模型的输出与对应的实际信道数据的均方误差小于预设阈值或达到预设的迭代次数，将所述训练后的神经网络初始模型作为所述神经网络模型。
一些实施例中，训练神经网络模型的步骤包括如下之一：
训练步骤，利用训练数据对上一次训练得到的神经网络模型进行训练，得到训练后的神经网络模型；其中，所述训练数据包括上一次训练得到的神经网络模型的输入数据和对应的实际信道数据，所述输入数据为连续K个发送导频信号的时域传输单元的信道估计结果，每个时域传输单元的信道估计结果的长度为M×N，所述上一次训练得到神经网络模型的输出为第K个发送导频信号的时域传输单元及之后连续L个时域传输单元内所有M个RB上N个天线的信道估计结果，M，N，K，L为正整数；
判断步骤，若所述训练后的神经网络模型的输出与对应的实际信道数据的均方误差大于或等于预设阈值或未达到预设的迭代次数，转向所述训练步骤；若所述训练后的神经网络模型的输出与对应的实际信道数据的均方误差小于预设阈值或达到预设的迭代次数，将所述训练后的神经网络模型作为所 述神经网络模型。
一些实施例中，所述神经网络模型包括第一神经网络模型和第二神经网络模型，训练所述第一神经网络模型的输入数据中，所述连续K个发送导频信号的时域传输单元中第一个时域传输单元中的导频信号在序号为偶数的RB上发送；训练所述第二神经网络模型的输入数据中，所述连续K个发送导频信号的时域传输单元中第一个时域传输单元中的导频信号在序号为奇数的第一RB上发送。
一些实施例中，处理器1010，用于若接收到的第一个时域传输单元中的导频信号在序号为偶数的RB上发送，利用所述第一神经网络模型进行信道估计；若接收到的第一个时域传输单元中的导频信号在序号为奇数的RB上发送，利用所述第二神经网络模型进行信道估计。
一些实施例中，所述导频信号包括以下至少一项：
信道状态信息参考信号CSI-RS，探测参考信号SRS，解调参考信号DMRS。
一些实施例中，所述时域传输单元包括以下任一项：传输时间间隔TTI，子帧，毫秒，时隙和符号。
本申请实施例还提供一种网络侧设备，包括处理器和通信接口，通信接口用于发送导频信号，第一时域传输单元与第二时域传输单元中的所述导频信号所占的资源块RB至少部分不同。
该网络侧设备实施例是与上述网络侧设备方法实施例对应的，上述方法实施例的各个实施过程和实现方式均可适用于该网络侧设备实施例中，且能达到相同的技术效果。
具体地，本申请实施例还提供了一种网络侧设备。如图10所示，该网络设备700包括：天线71、射频装置72、基带装置73。天线71与射频装置72连接。在上行方向上，射频装置72通过天线71接收信息，将接收的信息发送给基带装置73进行处理。在下行方向上，基带装置73对要发送的信息进行处理，并发送给射频装置72，射频装置72对收到的信息进行处理后经过天线71发送出去。
上述频带处理装置可以位于基带装置73中，以上实施例中网络侧设备执行的方法可以在基带装置73中实现，该基带装置73包括处理器74和存储器 75。
基带装置73例如可以包括至少一个基带板，该基带板上设置有多个芯片，如图10所示，其中一个芯片例如为处理器74，与存储器75连接，以调用存储器75中的程序，执行以上方法实施例中所示的网络设备操作。
该基带装置73还可以包括网络接口76，用于与射频装置72交互信息，该接口例如为通用公共无线接口(common public radio interface，简称CPRI)。
具体地，本发明实施例的网络侧设备还包括：存储在存储器75上并可在处理器74上运行的指令或程序，处理器74调用存储器75中的指令或程序执行图7所示各模块执行的方法，并达到相同的技术效果，为避免重复，故不在此赘述。
本申请实施例还提供一种可读存储介质，所述可读存储介质上存储有程序或指令，该程序或指令被处理器执行时实现上述信道估计方法实施例的各个过程，且能达到相同的技术效果，为避免重复，这里不再赘述。
其中，所述处理器为上述实施例中所述的终端中的处理器。所述可读存储介质，包括计算机可读存储介质，如计算机只读存储器(Read-Only Memory，ROM)、随机存取存储器(Random Access Memory，RAM)、磁碟或者光盘等。
本申请实施例另提供了一种芯片，所述芯片包括处理器和通信接口，所述通信接口和所述处理器耦合，所述处理器用于运行程序或指令，实现上述信道估计方法实施例的各个过程，且能达到相同的技术效果，为避免重复，这里不再赘述。
应理解，本申请实施例提到的芯片还可以称为系统级芯片，系统芯片，芯片系统或片上系统芯片等。
需要说明的是，在本文中，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者装置不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者装置所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括该要素的过程、方法、物品或者装置中还存在另外的相同要素。此外，需要指出的是，本申请实施方式中的方法和装置的范围不限按示出或讨论的顺序来执行功能，还 可包括根据所涉及的功能按基本同时的方式或按相反的顺序来执行功能，例如，可以按不同于所描述的次序来执行所描述的方法，并且还可以添加、省去、或组合各种步骤。另外，参照某些示例所描述的特征可在其他示例中被组合。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分可以以计算机软件产品的形式体现出来，该计算机软件产品存储在一个存储介质(如ROM/RAM、磁碟、光盘)中，包括若干指令用以使得一台终端(可以是手机，计算机，服务器，空调器，或者网络设备等)执行本申请各个实施例所述的方法。
上面结合附图对本申请的实施例进行了描述，但是本申请并不局限于上述的具体实施方式，上述的具体实施方式仅仅是示意性的，而不是限制性的，本领域的普通技术人员在本申请的启示下，在不脱离本申请宗旨和权利要求所保护的范围情况下，还可做出很多形式，均属于本申请的保护之内。

Claims (41)

  1. 一种信道估计方法，包括：
    终端接收网络侧设备发送的导频信号，第一时域传输单元与第二时域传输单元中所述导频信号所占的资源块RB至少部分不同；
    根据所述第一时域传输单元和所述第二时域传输单元上的导频信号，对第三时域传输单元进行信道估计。
  2. 根据权利要求1所述的信道估计方法，其中，所述根据所述第一时域传输单元和所述第二时域传输单元上的导频信号，对第三时域传输单元进行信道估计包括：
    根据所述第一时域传输单元上的导频信号、所述第二时域传输单元上的导频信号和预先训练的神经网络模型进行信道估计，得到所述第三时域传输单元内所有RB上的信道。
  3. 根据权利要求1所述的信道估计方法，其中，所述根据所述第一时域传输单元和所述第二时域传输单元上的导频信号，对第三时域传输单元进行信道估计包括：
    根据所述第一时域传输单元上的导频信号、所述第二时域传输单元上的导频信号和预先训练的神经网络模型进行信道估计，得到当前时域传输单元之后L个时域传输单元内所有RB上的信道，L为正整数。
  4. 根据权利要求2或3所述的信道估计方法，其中，所述所有RB为按照预定义规则或预配置方式确定的RB。
  5. 根据权利要求4所述的信道估计方法，其中，所述按照预定义规则或预配置方式确定的RB至少包括第一时隙传输单元中导频信号所占用的RB和第二时隙传输单元中导频信号所占用的RB。
  6. 根据权利要求2或3所述的信道估计方法，其中，利用最近的K个发送导频信号的时域传输单元上的导频信号进行信道估计，K为正整数。
  7. 根据权利要求1所述的信道估计方法，其中，所述终端接收网络侧设备发送的导频信号包括：
    所述终端接收网络侧设备在第一时域传输单元的第一RB上发送的导频信 号；
    所述终端接收网络侧设备在第二时域传输单元的第二RB上发送的导频信号；
    其中，所述第一RB与所述第二RB不同，所述第二时域传输单元为所述第一时域传输单元之后最近的发送所述导频信号的时域传输单元，所述第二时域传输单元与所述第一时域传输单元之间间隔至少一个时域传输单元。
  8. 根据权利要求7所述的信道估计方法，其中，
    所述第一RB的序号为偶数，所述第二RB的序号为奇数；或
    所述第一RB的序号为奇数，所述第二RB的序号为偶数。
  9. 根据权利要求2或3所述的信道估计方法，其中，还包括：
    训练得到所述神经网络模型；
    其中，所述训练得到所述神经网络模型的步骤包括至少如下之一：
    建立步骤，建立神经网络初始模型；
    训练步骤，利用训练数据对所述神经网络初始模型进行训练，得到训练后的神经网络初始模型；其中，所述训练数据包括神经网络初始模型的输入数据和对应的实际信道数据，所述输入数据为连续K个发送导频信号的时域传输单元的信道估计结果，每个时域传输单元的信道估计结果的长度为M×N，所述神经网络初始模型的输出为第K个发送导频信号的时域传输单元及之后连续L个时域传输单元内所有M个RB上N个天线的信道估计结果，M，N，K，L为正整数；
    判断步骤，若所述训练后的神经网络初始模型的输出与对应的实际信道数据的均方误差大于或等于预设阈值或未达到预设的迭代次数，转向所述训练步骤；若所述训练后的神经网络初始模型的输出与对应的实际信道数据的均方误差小于预设阈值或达到预设的迭代次数，将所述训练后的神经网络初始模型作为所述神经网络模型。
  10. 根据权利要求9所述的信道估计方法，其中，所述训练得到所述神经网络模型的步骤包括至少如下之一：
    训练步骤，利用训练数据对上一次训练得到的神经网络模型进行训练，得到训练后的神经网络模型；其中，所述训练数据包括上一次训练得到的神 经网络模型的输入数据和对应的实际信道数据，所述输入数据为连续K个发送导频信号的时域传输单元的信道估计结果，每个时域传输单元的信道估计结果的长度为M×N，所述上一次训练得到神经网络模型的输出为第K个发送导频信号的时域传输单元及之后连续L个时域传输单元内所有M个RB上N个天线的信道估计结果，M，N，K，L为正整数；
    判断步骤，若所述训练后的神经网络模型的输出与对应的实际信道数据的均方误差大于或等于预设阈值或未达到预设的迭代次数，转向所述训练步骤；若所述训练后的神经网络模型的输出与对应的实际信道数据的均方误差小于预设阈值或达到预设的迭代次数，将所述训练后的神经网络模型作为所述神经网络模型。
  11. 根据权利要求9所述的信道估计方法，其中，所述神经网络模型包括第一神经网络模型和第二神经网络模型，训练所述第一神经网络模型的输入数据中，所述连续K个发送导频信号的时域传输单元中第一个时域传输单元中的导频信号在序号为偶数的RB上发送；训练所述第二神经网络模型的输入数据中，所述连续K个发送导频信号的时域传输单元中第一个时域传输单元中的导频信号在序号为奇数的第一RB上发送。
  12. 根据权利要求11所述的信道估计方法，其中，根据所述神经网络模型进行信道估计包括：
    若接收到的第一个时域传输单元中的导频信号在序号为偶数的RB上发送，利用所述第一神经网络模型进行信道估计；若接收到的第一个时域传输单元中的导频信号在序号为奇数的RB上发送，利用所述第二神经网络模型进行信道估计。
  13. 根据权利要求1所述的信道估计方法，其中，所述导频信号包括以下至少一项：
    信道状态信息参考信号CSI-RS，探测参考信号SRS，解调参考信号DMRS。
  14. 根据权利要求1所述的信道估计方法，其中，所述时域传输单元包括以下任一项：传输时间间隔TTI，子帧，毫秒，时隙和符号。
  15. 一种信道估计方法，包括：
    网络侧设备发送导频信号，第一时域传输单元与第二时域传输单元中的 所述导频信号所占的资源块RB至少部分不同。
  16. 根据权利要求15所述的信道估计方法，其中，所述网络侧设备发送导频信号包括：
    在所述第一时域传输单元的第一RB上发送导频信号；
    在所述第二时域传输单元的第二RB上发送导频信号；
    其中，所述第一RB与所述第二RB不同，所述第二时域传输单元为所述第一时域传输单元之后最近的发送所述导频信号的时域传输单元，所述第二时域传输单元与所述第一时域传输单元之间间隔至少一个时域传输单元。
  17. 根据权利要求16所述的信道估计方法，其中，
    所述第一RB的序号为偶数，所述第二RB的序号为奇数；或
    所述第一RB的序号为奇数，所述第二RB的序号为偶数。
  18. 根据权利要求15所述的信道估计方法，其中，所述导频信号包括以下至少一项：
    信道状态信息参考信号CSI-RS，探测参考信号SRS，解调参考信号DMRS。
  19. 根据权利要求15所述的信道估计方法，其中，所述时域传输单元包括以下任一项：传输时间间隔TTI，子帧，毫秒，时隙和符号。
  20. 一种信道估计装置，包括：
    接收模块，用于接收网络侧设备发送的导频信号，第一时域传输单元与第二时域传输单元中所述导频信号所占的资源块RB至少部分不同；
    信道估计模块，用于根据所述第一时域传输单元和所述第二时域传输单元上的导频信号，对第三时域传输单元进行信道估计。
  21. 根据权利要求20所述的信道估计装置，其中，所述信道估计模块具体用于根据所述第一时域传输单元上的导频信号、所述第二时域传输单元上的导频信号和预先训练的神经网络模型进行信道估计，得到所述第三时域传输单元内所有RB上的信道。
  22. 根据权利要求20所述的信道估计装置，其中，所述信道估计模块具体用于根据所述第一时域传输单元上的导频信号、所述第二时域传输单元上的导频信号和预先训练的神经网络模型进行信道估计，得到当前时域传输单元之后L个时域传输单元内所有RB上的信道，L为正整数。
  23. 根据权利要求21或22所述的信道估计装置，其中，所述所有RB为按照预定义规则或预配置方式确定的RB。
  24. 根据权利要求23所述的信道估计装置，其中，所述按照预定义规则或预配置方式确定的RB至少包括第一时隙传输单元中导频信号所占用的RB和第二时隙传输单元中导频信号所占用的RB。
  25. 根据权利要求21或22所述的信道估计装置，其中，所述信道估计模块具体用于利用最近的K个发送导频信号的时域传输单元上的导频信号进行信道估计，K为正整数。
  26. 根据权利要求20所述的信道估计装置，其中，所述接收模块具体用于接收网络侧设备在第一时域传输单元的第一RB上发送的导频信号；接收网络侧设备在第二时域传输单元的第二RB上发送的导频信号；
    其中，所述第一RB与所述第二RB不同，所述第二时域传输单元为所述第一时域传输单元之后最近的发送所述导频信号的时域传输单元，所述第二时域传输单元与所述第一时域传输单元之间间隔至少一个时域传输单元。
  27. 根据权利要求26所述的信道估计装置，其中，
    所述第一RB的序号为偶数，所述第二RB的序号为奇数；或
    所述第一RB的序号为奇数，所述第二RB的序号为偶数。
  28. 根据权利要求21或22所述的信道估计装置，其中，还包括训练模块，用于训练得到所述神经网络模型；
    其中，所述训练得到所述神经网络模型的步骤包括至少如下之一：
    建立步骤，建立神经网络初始模型；
    训练步骤，利用训练数据对所述神经网络初始模型进行训练，得到训练后的神经网络初始模型；其中，所述训练数据包括神经网络初始模型的输入数据和对应的实际信道数据，所述输入数据为连续K个发送导频信号的时域传输单元的信道估计结果，每个时域传输单元的信道估计结果的长度为M×N，所述神经网络初始模型的输出为第K个发送导频信号的时域传输单元及之后连续L个时域传输单元内所有M个RB上N个天线的信道估计结果，M，N，K，L为正整数；
    判断步骤，若所述训练后的神经网络初始模型的输出与对应的实际信道 数据的均方误差大于或等于预设阈值或未达到预设的迭代次数，转向所述训练步骤；若所述训练后的神经网络初始模型的输出与对应的实际信道数据的均方误差小于预设阈值或达到预设的迭代次数，将所述训练后的神经网络初始模型作为所述神经网络模型。
  29. 根据权利要求28所述的信道估计装置，其中，所述训练模块具体用于执行至少如下之一：
    训练步骤，利用训练数据对上一次训练得到的神经网络模型进行训练，得到训练后的神经网络模型；其中，所述训练数据包括上一次训练得到的神经网络模型的输入数据和对应的实际信道数据，所述输入数据为连续K个发送导频信号的时域传输单元的信道估计结果，每个时域传输单元的信道估计结果的长度为M×N，所述上一次训练得到神经网络模型的输出为第K个发送导频信号的时域传输单元及之后连续L个时域传输单元内所有M个RB上N个天线的信道估计结果，M，N，K，L为正整数；
    判断步骤，若所述训练后的神经网络模型的输出与对应的实际信道数据的均方误差大于或等于预设阈值或未达到预设的迭代次数，转向所述训练步骤；若所述训练后的神经网络模型的输出与对应的实际信道数据的均方误差小于预设阈值或达到预设的迭代次数，将所述训练后的神经网络模型作为所述神经网络模型。
  30. 根据权利要求28所述的信道估计装置，其中，所述神经网络模型包括第一神经网络模型和第二神经网络模型，训练所述第一神经网络模型的输入数据中，所述连续K个发送导频信号的时域传输单元中第一个时域传输单元中的导频信号在序号为偶数的RB上发送；训练所述第二神经网络模型的输入数据中，所述连续K个发送导频信号的时域传输单元中第一个时域传输单元中的导频信号在序号为奇数的第一RB上发送。
  31. 根据权利要求30所述的信道估计装置，其中，所述信道估计模块具体用于若接收到的第一个时域传输单元中的导频信号在序号为偶数的RB上发送，利用所述第一神经网络模型进行信道估计；若接收到的第一个时域传输单元中的导频信号在序号为奇数的RB上发送，利用所述第二神经网络模型进行信道估计。
  32. 根据权利要求20所述的信道估计装置，其中，所述导频信号包括以下至少一项：
    信道状态信息参考信号CSI-RS，探测参考信号SRS，解调参考信号DMRS。
  33. 根据权利要求20所述的信道估计装置，其中，所述时域传输单元包括以下任一项：传输时间间隔TTI，子帧，毫秒，时隙和符号。
  34. 一种信道估计装置，包括：
    发送模块，用于发送导频信号，第一时域传输单元与第二时域传输单元中的所述导频信号所占的资源块RB至少部分不同。
  35. 根据权利要求34所述的信道估计装置，其中，所述发送模块具体用于在所述第一时域传输单元的第一RB上发送导频信号；在所述第二时域传输单元的第二RB上发送导频信号；
    其中，所述第一RB与所述第二RB不同，所述第二时域传输单元为所述第一时域传输单元之后最近的发送所述导频信号的时域传输单元，所述第二时域传输单元与所述第一时域传输单元之间间隔至少一个时域传输单元。
  36. 根据权利要求35所述的信道估计装置，其中，
    所述第一RB的序号为偶数，所述第二RB的序号为奇数；或
    所述第一RB的序号为奇数，所述第二RB的序号为偶数。
  37. 根据权利要求34所述的信道估计装置，其中，所述导频信号包括以下至少一项：
    信道状态信息参考信号CSI-RS，探测参考信号SRS，解调参考信号DMRS。
  38. 根据权利要求34所述的信道估计装置，其中，所述时域传输单元包括以下任一项：传输时间间隔TTI，子帧，毫秒，时隙和符号。
  39. 一种终端，包括处理器，存储器及存储在所述存储器上并可在所述处理器上运行的程序或指令，其中，所述程序或指令被所述处理器执行时实现如权利要求1至14任一项所述的信道估计方法的步骤。
  40. 一种网络侧设备，包括处理器，存储器及存储在所述存储器上并可在所述处理器上运行的程序或指令，其中，所述程序或指令被所述处理器执行时实现如权利要求15至19任一项所述的信道估计方法的步骤。
  41. 一种可读存储介质，所述可读存储介质上存储程序或指令，其中，所 述程序或指令被处理器执行时实现如权利要求1-19任一项所述的信道估计方法的步骤。
PCT/CN2022/126226 2021-10-22 2022-10-19 信道估计方法、装置、终端及网络侧设备 WO2023066307A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111234895.1A CN116016045A (zh) 2021-10-22 2021-10-22 信道估计方法、装置、终端及网络侧设备
CN202111234895.1 2021-10-22

Publications (1)

Publication Number Publication Date
WO2023066307A1 true WO2023066307A1 (zh) 2023-04-27

Family

ID=86028559

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/126226 WO2023066307A1 (zh) 2021-10-22 2022-10-19 信道估计方法、装置、终端及网络侧设备

Country Status (2)

Country Link
CN (1) CN116016045A (zh)
WO (1) WO2023066307A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116915555B (zh) * 2023-08-28 2023-12-29 中国科学院声学研究所 一种基于自监督学习的水声信道估计方法及装置

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105812113A (zh) * 2007-01-05 2016-07-27 高通股份有限公司 用于改进信道估计和干扰估计的导频设计
CN109565433A (zh) * 2016-07-28 2019-04-02 Oppo广东移动通信有限公司 传输导频信号的方法、终端设备和网络侧设备
CN112204898A (zh) * 2018-07-06 2021-01-08 华为技术有限公司 用于自适应调节mimo传输方案的设备和方法
WO2021175444A1 (en) * 2020-03-06 2021-09-10 Nokia Technologies Oy Classes of nn parameters for channel estimation

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105812113A (zh) * 2007-01-05 2016-07-27 高通股份有限公司 用于改进信道估计和干扰估计的导频设计
CN109565433A (zh) * 2016-07-28 2019-04-02 Oppo广东移动通信有限公司 传输导频信号的方法、终端设备和网络侧设备
CN112204898A (zh) * 2018-07-06 2021-01-08 华为技术有限公司 用于自适应调节mimo传输方案的设备和方法
WO2021175444A1 (en) * 2020-03-06 2021-09-10 Nokia Technologies Oy Classes of nn parameters for channel estimation

Also Published As

Publication number Publication date
CN116016045A (zh) 2023-04-25

Similar Documents

Publication Publication Date Title
EP4231693A1 (en) Configuration method for ai network parameter and device
CN113922848B (zh) 信号发送方法、信道估计方法、发送端设备及接收端设备
CN113708855B (zh) 基于深度学习的otfs数据驱动接收方法、系统及介质
WO2023066307A1 (zh) 信道估计方法、装置、终端及网络侧设备
US20230291517A1 (en) Communication method, communications apparatus, and communications device
CN103378896A (zh) 用于确定信道状态信息的方法和设备
WO2021238850A1 (zh) 信道信息的处理方法及装置
US20240088970A1 (en) Method and apparatus for feeding back channel information of delay-doppler domain, and electronic device
CN114531696A (zh) Ai网络部分输入缺失的处理方法和设备
CN115913486A (zh) 信息上报方法、装置、终端及可读存储介质
WO2023072239A1 (zh) 信道预测方法、装置、网络侧设备及终端
WO2023061277A1 (zh) 导频信号发送方法、信道估计方法、装置及设备
TW201941553A (zh) 用於進行通道預估的方法及相關之積體電路與通信裝置
WO2022166882A1 (zh) 信号处理方法、装置、通信设备及存储介质
CN115333581B (zh) 终端天线面板信息的传输方法、终端及网络侧设备
CN115208526B (zh) 信号传输方法、装置及终端
WO2023179540A1 (zh) 信道预测方法、装置及无线通信设备
CN115396262B (zh) 信道估计方法、装置、设备及可读存储介质
WO2023051539A1 (zh) 上行预编码信息确定方法、终端及网络侧设备
WO2024083072A1 (zh) 感知配置方法、感知方法、装置、网络侧设备及感知设备
WO2023001143A1 (zh) 信息传输、信息接收方法、装置、终端及网络侧设备
EP4293969A1 (en) Method and apparatus for processing data sending and receiving, and device
WO2022166880A1 (zh) 信号处理方法、装置、通信设备及存储介质
WO2024032694A1 (zh) Csi预测处理方法、装置、通信设备及可读存储介质
CN115987465A (zh) 信息映射方法及通信设备

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22882912

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2022882912

Country of ref document: EP

ENP Entry into the national phase

Ref document number: 2022882912

Country of ref document: EP

Effective date: 20240522