WO2021244344A1 - 获取信道信息的方法及通信装置 - Google Patents

获取信道信息的方法及通信装置 Download PDF

Info

Publication number
WO2021244344A1
WO2021244344A1 PCT/CN2021/095488 CN2021095488W WO2021244344A1 WO 2021244344 A1 WO2021244344 A1 WO 2021244344A1 CN 2021095488 W CN2021095488 W CN 2021095488W WO 2021244344 A1 WO2021244344 A1 WO 2021244344A1
Authority
WO
WIPO (PCT)
Prior art keywords
reference signal
density
csi
neural network
case
Prior art date
Application number
PCT/CN2021/095488
Other languages
English (en)
French (fr)
Inventor
王坚
皇甫幼睿
徐晨
李榕
王俊
Original Assignee
华为技术有限公司
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 华为技术有限公司 filed Critical 华为技术有限公司
Publication of WO2021244344A1 publication Critical patent/WO2021244344A1/zh
Priority to US18/074,237 priority Critical patent/US20230109063A1/en

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L25/00Baseband systems
    • H04L25/02Details ; arrangements for supplying electrical power along data transmission lines
    • H04L25/0202Channel estimation
    • H04L25/0224Channel estimation using sounding signals
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04BTRANSMISSION
    • H04B7/00Radio transmission systems, i.e. using radiation field
    • H04B7/02Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas
    • H04B7/04Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
    • H04B7/0413MIMO systems
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04BTRANSMISSION
    • H04B7/00Radio transmission systems, i.e. using radiation field
    • H04B7/02Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas
    • H04B7/04Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
    • H04B7/0413MIMO systems
    • H04B7/0456Selection of precoding matrices or codebooks, e.g. using matrices antenna weighting
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04BTRANSMISSION
    • H04B7/00Radio transmission systems, i.e. using radiation field
    • H04B7/02Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas
    • H04B7/04Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
    • H04B7/06Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station
    • H04B7/0613Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission
    • H04B7/0615Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission of weighted versions of same signal
    • H04B7/0619Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission of weighted versions of same signal using feedback from receiving side
    • H04B7/0658Feedback reduction
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L25/00Baseband systems
    • H04L25/02Details ; arrangements for supplying electrical power along data transmission lines
    • H04L25/0202Channel estimation
    • H04L25/024Channel estimation channel estimation algorithms
    • H04L25/0254Channel estimation channel estimation algorithms using neural network algorithms
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/16Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using machine learning or artificial intelligence
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L5/00Arrangements affording multiple use of the transmission path
    • H04L5/003Arrangements for allocating sub-channels of the transmission path
    • H04L5/0048Allocation of pilot signals, i.e. of signals known to the receiver
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04BTRANSMISSION
    • H04B7/00Radio transmission systems, i.e. using radiation field
    • H04B7/02Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas
    • H04B7/04Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
    • H04B7/04013Intelligent reflective surfaces
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04BTRANSMISSION
    • H04B7/00Radio transmission systems, i.e. using radiation field
    • H04B7/02Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas
    • H04B7/04Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
    • H04B7/06Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station
    • H04B7/0613Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission
    • H04B7/0615Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission of weighted versions of same signal
    • H04B7/0619Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission of weighted versions of same signal using feedback from receiving side
    • H04B7/0621Feedback content
    • H04B7/0626Channel coefficients, e.g. channel state information [CSI]

Definitions

  • This application relates to the field of communication, and more specifically, to a method and communication device for acquiring channel information.
  • Massive MIMO massive multiple-input multiple-output
  • network equipment can use precoding technology to reduce the interference between multiple terminal devices and the interference between multiple signal streams of the same terminal device. interference. Thereby improving signal quality, realizing space division multiplexing, and improving spectrum utilization.
  • the terminal device may determine the precoding matrix adapted to the downlink channel through channel measurement, etc., and hope that through feedback, the network device can obtain a precoding matrix that is the same or similar to the precoding vector determined by the terminal device; or the network device
  • the precoding matrix adapted to the uplink channel can be determined through channel measurement, and it is hoped that through feedback, the terminal device can obtain a precoding matrix that is the same or similar to the precoding vector determined by the network device.
  • channel estimation is performed by placing reference signals that are known at both ends of the transceiver on the wireless transmission resources.
  • the sender needs to occupy a larger resource for transmitting the reference signal, so the sending overhead is larger.
  • the feedback overhead at the receiving end is also relatively large.
  • the present application provides a method for obtaining channel information, in order to reduce the overhead of sending reference signals at the transmitting end and/or reducing the feedback overhead of the receiving end.
  • a method for acquiring channel information may include: a first device sends a first reference signal to a second device, where the density of the first reference signal is less than or equal to the density of the second reference signal, and The second reference signal is a regular density reference signal; the first device receives first channel state information (channel state information, CSI) from the second device; the density of the first reference signal is less than the density of the second reference signal In the case that the first CSI is obtained by the second device according to the first reference signal; or, in the case that the density of the first reference signal is equal to the density of the second reference signal, the first CSI is the The second device obtains a second CSI based on a part of the first reference signal; the first device obtains a second CSI based on the first CSI and the first neural network model, and the second CSI is used to instruct the first device and the second device Channel information between.
  • CSI channel state information
  • the conventional density refers to the density of the reference signal defined in the current protocol
  • the density of the reference signal refers to the ratio of the resources used to transmit the reference signal to the total transmission resources.
  • NR new radio
  • 32-port channel state information reference signal (CSI-RS) resources account for about 20% of the total transmission resources. Therefore, it can be said that the conventional density of 32-port CSI-RS is 20%.
  • the first device can recover all channel information (second CSI) based on partial channel information (first CSI) and the first neural network model . Therefore, when the first neural network model is deployed on the first device side, the second device can only feed back part of the channel information (first CSI) to the first device, thereby reducing the feedback overhead of the second device.
  • the first device when the first neural network model is deployed in the first device, the first device can send a low-density reference signal to the second device, so that the overhead of sending the reference signal of the second device can be reduced.
  • the density of the first reference signal may be 1/2 or 1/4 of the density of the second reference signal.
  • the second reference signal and the first reference signal may be CSI-RS, or demodulation reference signal (DMRS) .
  • CSI-RS CSI-RS
  • DMRS demodulation reference signal
  • the second reference signal and the first reference signal may be channel sounding reference signals (SRS) or DMRS.
  • SRS channel sounding reference signals
  • DMRS DMRS
  • the method before the first device sends the first reference signal to the second device, the method further includes: the first device determining the first neural network model.
  • determining the first neural network model by the first device may specifically include: the first device sends the second reference signal to the second device; the first device receives the signal from the second device A third CSI, where the third CSI is obtained by the second device according to the second reference signal; the first device trains a neural network based on the third CSI to obtain the first neural network model.
  • the method further includes: when a preset trigger condition is reached, the first device updates the first neural network model.
  • the first device to update the first neural network model may specifically include: the first device sends the third reference signal to the second device, and the third reference signal is a conventional density reference Signal; the first device receives a fourth CSI from the second device, the fourth CSI is obtained by the second device according to the third reference signal; the first device trains a neural network based on the fourth CSI to obtain updates After the first neural network model.
  • the preset trigger condition may be that a first timer expires, and the first timer is started when the first device sends the first reference signal to the second device.
  • the preset trigger condition may be that the first device determines that the demodulation performance of the second device to demodulate the first data is lower than a preset threshold, and the first data is sent by the first device according to the second CSI of.
  • the preset trigger condition may be that the first device receives a first request message from the second device, and the first request message is used to request to update the first neural network model.
  • the method before the first device sends the first reference signal to the second device, the method further includes: the first device receives the first reference signal from the second device A second request message, the second request message is used to request the first reference signal, and the second request message is also used to indicate the density of the first reference signal.
  • the second request message may be carried in uplink control information (UCI).
  • UCI uplink control information
  • the second request message may be carried in downlink control information (DCI).
  • DCI downlink control information
  • the method before the first device sends the first reference signal to the second device, the method further includes: the first device determines that the first neural network is trained In the case of the model, first indication information is sent to the second device, where the first indication information is used to indicate the density of the first reference signal.
  • the first indication information may be carried in the DCI.
  • the first indication information may be carried in the UCI.
  • the method further includes: the first device sends a radio resource control (radio resource control) to the second device. , RRC) message, the RRC message includes density configuration information of the first reference signal.
  • RRC radio resource control
  • the method further includes: the first device receives an RRC message from the second device, the RRC message Includes the density configuration information of the first reference signal.
  • a method for acquiring channel information may include: a second device receiving a first reference signal from a first device, the density of the first reference signal is less than or equal to the density of the second reference signal, The second reference signal is a regular density reference signal; the second device sends a first CSI to the first device, and the first CSI uses the first neural network model to obtain the second CSI, and the second CSI is used to indicate the first CSI.
  • the first CSI is the second device according to the first reference signal Obtained; or, in the case where the density of the first reference signal is equal to the density of the second reference signal, the first CSI is obtained by the second device according to a part of the first reference signal.
  • the conventional density refers to the density of the reference signal defined in the current protocol
  • the density of the reference signal refers to the ratio of the resources used to transmit the reference signal to the total transmission resources.
  • the resources used to transmit 32-port CSI-RS defined in the current protocol account for approximately 20% of the total transmission resources. Therefore, it can be said that the normal density of 32-port CSI-RS is 20%.
  • the first device can recover all channel information (second CSI) based on partial channel information (first CSI) and the first neural network model . Therefore, when the first neural network model is deployed by the first device, the second device can only feed back part of the channel information (first CSI) to the first device, so that the feedback overhead of the second device can be reduced.
  • the first device when the first neural network model is deployed in the first device, the first device can send a low-density reference signal to the second device, so that the overhead of sending the reference signal of the second device can be reduced.
  • the density of the first reference signal may be 1/2 or 1/4 of the density of the second reference signal.
  • the second reference signal and the first reference signal may be CSI-RS or DMRS.
  • the second reference signal and the first reference signal may be SRS or DMRS.
  • the method before the second device receives the first reference signal from the first device, the method further includes: the second device receives the first reference signal from the first device A second reference signal; the second device sends a third CSI to the first device, the third CSI is obtained according to the second reference signal, and the third CSI is used to train a neural network to obtain the first neural network model .
  • the method further includes: the second device receiving the third reference signal from the first device, the third reference signal being a regular density reference signal; the The second device sends a fourth CSI to the first device, where the fourth CSI is obtained according to the third reference signal, and the fourth CSI is used to train a neural network to obtain an updated first neural network model.
  • the method before the second device receives the first reference signal from the first device, the method further includes: the second device sends the first reference signal to the first device A second request message, the second request message is used to request the first reference signal, and the second request message is also used to indicate the density of the first reference signal.
  • the second request message may be carried in UCI.
  • the second request message may be carried in the DCI.
  • the second device periodically sends a second request message to the first device
  • the second device When receiving the second instruction information from the first device, the second device sends the second request message to the first device, where the second instruction information is used to indicate that the first neural network model has been determined.
  • the method before the second device receives the first reference signal from the first device, the method further includes: the second device receives the first reference signal from the first device First indication information, where the first indication information is used to indicate the density of the first reference signal.
  • the first indication information may be carried in the DCI.
  • the first indication information may be carried in UCI.
  • the method further includes: the second device receives an RRC message from the first device, the RRC message Includes the density configuration information of the first reference signal.
  • the method further includes: the second device sends an RRC message to the first device, and the RRC message The density configuration information of the first reference signal is included.
  • a method for acquiring channel information may include: a second device receiving a first reference signal from a first device, where the density of the first reference signal is less than the density of the second reference signal, and the second device
  • the second reference signal is a conventional density reference signal
  • the second device obtains a second CSI according to the first CSI and the second neural network model, and the second CSI is used to indicate channel information between the first device and the second device,
  • the first CSI is obtained according to the first reference signal; the second device sends the second CSI to the first device.
  • the conventional density refers to the density of the reference signal defined in the current protocol
  • the density of the reference signal refers to the ratio of the resources used to transmit the reference signal to the total transmission resources.
  • the resources used to transmit 32-port CSI-RS defined in the current protocol account for approximately 20% of the total transmission resources. Therefore, it can be said that the normal density of 32-port CSI-RS is 20%.
  • the second device can recover all channel information (second CSI) based on partial channel information (first CSI) and the second neural network model . Therefore, when the second device deploys the first neural network model, the first device can send a low-density reference signal to the second device, so that the overhead of sending the reference signal can be reduced.
  • the density of the first reference signal is 1/2 or 1/4 of the density of the second reference signal.
  • the second reference signal and the first reference signal may be CSI-RS or DMRS.
  • the second reference signal and the first reference signal may be SRS or DMRS.
  • the method before the second device receives the first reference signal from the first device, the method further includes: the second device determining a second neural network model.
  • the second device determining the second neural network model may specifically include: the second device receiving the second reference signal from the first device; and the second device pairing the neural network based on the third CSI Training is performed to obtain the second neural network model, and the third CSI is obtained according to the second reference signal.
  • the method further includes: when a preset trigger condition is reached, the second device updates the second neural network model.
  • the second device updating the second neural network model may specifically include: the second device receives the third reference signal from the first device; the second device is based on the fourth CSI The neural network is trained to obtain an updated second neural network model, and the fourth CSI is obtained according to the third reference signal.
  • the preset trigger condition may be that a second timer expires, and the second timer is started when the second device receives the first reference signal from the first device.
  • the preset trigger condition may be that the second device determines that the demodulation performance of demodulating the first data is lower than a preset threshold, and the first data is sent by the first device according to the second CSI.
  • the method before the second device receives the first reference signal from the first device, the method further includes: the second device has completed training on the neural network In this case, a second request message is sent to the first device, the second request message is used to request the first reference signal, and the second request message is also used to indicate the density of the first reference signal.
  • the second request message may be carried in UCI.
  • the second request message may be carried in the DCI.
  • the method before the second device receives the first reference signal from the first device, the method further includes: the second device receives the first reference signal from the first device First indication information, where the first indication information is used to indicate the density of the first reference signal.
  • the first indication information may be carried in the DCI.
  • the first indication information may be carried in UCI.
  • the method further includes: the second device receives a radio resource control RRC message from the first device,
  • the RRC message includes density configuration information of the first reference signal.
  • the method further includes: the second device sends an RRC message to the first device, and the RRC message The density configuration information of the first reference signal is included.
  • a method for acquiring channel information may include: a first device sends a first reference signal to a second device, where the density of the first reference signal is less than the density of the second reference signal, and the second The reference signal is a conventional density reference signal.
  • the first reference signal is used to obtain a first CSI
  • the first CSI is used to obtain a second CSI through a second neural network model
  • the second CSI is used to instruct the first device and the Channel information between the second device; the first device receives the second CSI from the second device.
  • the conventional density refers to the density of the reference signal defined in the current protocol
  • the density of the reference signal refers to the ratio of the resources used to transmit the reference signal to the total transmission resources.
  • the resources used to transmit 32-port CSI-RS defined in the current protocol account for approximately 20% of the total transmission resources. Therefore, it can be said that the normal density of 32-port CSI-RS is 20%.
  • the second device can recover all channel information (second CSI) based on partial channel information (first CSI) and the second neural network model . Therefore, when the second device deploys the first neural network model, the first device can send a low-density reference signal to the second device, so that the overhead of sending the reference signal can be reduced.
  • the density of the first reference signal is 1/2 or 1/4 of the density of the second reference signal.
  • the second reference signal and the first reference signal may be CSI-RS or DMRS.
  • the second reference signal and the first reference signal may be SRS or DMRS.
  • the method before the first device sends the first reference signal to the second device, the method further includes: the first device sends the first reference signal to the second device Two reference signals, the second reference signal is used to obtain a third CSI, and the third CSI is used to train a neural network to obtain the second neural network model.
  • the method further includes: the first device sends a third reference signal to the second device, the third reference signal is used to obtain a fourth CSI, and the first device Four CSI is used to train the neural network to obtain the updated second neural network model.
  • the method before the first device sends the first reference signal to the second device, the method further includes: the first device receives the first reference signal from the second device A second request message, the second request message is used to request the first reference signal, and the second request message is also used to indicate the density of the first reference signal.
  • the second request message may be carried in UCI.
  • the second request message may be carried in the DCI.
  • the method before the first device sends the first reference signal to the second device, the method further includes: the first device sends the first reference signal to the second device. Indication information, where the first indication information is used to indicate the density of the first reference signal.
  • the first indication information may be carried in the DCI.
  • the first indication information may be carried in the UCI.
  • the first device may periodically send the first indication information to the second device; or
  • the first device may send the first instruction information to the second device when receiving the third instruction information from the second device, where the third instruction information is used to indicate that the second neural network model has been determined .
  • the method further includes: the first device sends a radio resource control RRC message to the second device, and
  • the RRC message includes density configuration information of the first reference signal.
  • the method further includes: the first device receives an RRC message from the second device, the RRC message Includes the configuration information of the density of the first reference signal.
  • a communication device which includes modules or units for executing the method in the first aspect and any one of the possible implementation manners of the first aspect.
  • a communication device which includes various modules or units used to execute the second aspect and the method in any one of the possible implementation manners of the second aspect.
  • a communication device including a transceiving unit and a processing unit: the transceiving unit is configured to receive a first reference signal from a first device, the density of the first reference signal is less than the density of the second reference signal, and The second reference signal is a conventional density reference signal; the processing unit is used to obtain a second CSI according to the first CSI and the second neural network model, and the second CSI is used to indicate the channel between the first device and the second device Information, the first CSI is obtained according to the first reference signal; the transceiver unit is further configured to send the second CSI to the first device.
  • the density of the first reference signal is 1/2 or 1/4 of the density of the second reference signal.
  • the transceiver unit is further configured to receive the second reference signal from the first device; the processing unit is further configured to train the neural network based on the third CSI To obtain the second neural network model, the third CSI is obtained according to the second reference signal.
  • the transceiver unit is further configured to receive the third reference signal from the first device; the processing unit is further configured to train the neural network based on the fourth CSI To obtain the updated second neural network model, the fourth CSI is obtained according to the third reference signal.
  • the transceiver unit is further configured to send a second request message to the first device when the neural network training is completed, and the second request message is used for The first reference signal is requested, and the second request message is also used to indicate the density of the first reference signal.
  • the second request message may be carried in the UCI.
  • the second request message may be carried in the DCI.
  • the transceiver unit is further configured to receive first indication information from the first device, where the first indication information is used to indicate the density of the first reference signal.
  • the first indication information may be carried in the DCI.
  • the first indication information may be carried in the UCI.
  • the transceiver unit is further configured to receive an RRC message from the first device, and the RRC message includes the first device. Density configuration information of a reference signal.
  • the transceiver unit when the communication device is a network device, the transceiver unit is further configured to send an RRC message to the first device, and the RRC message includes the first device. Density configuration information of the reference signal.
  • a communication device including a transceiving unit: the transceiving unit is configured to send a first reference signal to a second device, the density of the first reference signal is less than the density of the second reference signal, and the second reference signal Is a conventional density reference signal, the first reference signal is used to obtain the first CSI, the first CSI is used to obtain the second CSI through the second neural network model, and the second CSI is used to indicate the first device and the second CSI Channel information between devices; the first device receives the second CSI from the second device.
  • the density of the first reference signal is 1/2 or 1/4 of the density of the second reference signal.
  • the transceiver unit is further configured to send the second reference signal to the second device, and the second reference signal is used to obtain a third CSI. Used to train the neural network to obtain the second neural network model.
  • the transceiver unit is further configured to send a third reference signal to the second device, where the third reference signal is used to obtain a fourth CSI, and the fourth CSI is used for To train the neural network to obtain the updated second neural network model.
  • the transceiving unit is further configured to receive a second request message from the second device, the second request message being used to request the first reference signal, and the second request message The second request message is also used to indicate the density of the first reference signal.
  • the second request message may be carried in the UCI.
  • the second request message may be carried in the DCI.
  • the transceiver unit is further configured to send first indication information to the second device, where the first indication information is used to indicate the density of the first reference signal.
  • the first indication information may be carried in the DCI.
  • the first indication information may be carried in the UCI.
  • the transceiver unit may periodically send the first indication information to the second device; or
  • the transceiver unit may send the first instruction information to the second device when receiving the third instruction information from the second device, where the third instruction information is used to indicate that the second neural network model has been determined.
  • the transceiver unit when the communication device is a network device, the transceiver unit is further configured to send a radio resource control RRC message to the second device, where the RRC message includes Density configuration information of the first reference signal.
  • the transceiver unit when the communication device is a terminal device, the transceiver unit is further configured to receive an RRC message from the second device, and the RRC message includes the first device. Configuration information of the density of a reference signal.
  • a communication device including a processor.
  • the processor is coupled with the memory and can be used to execute instructions in the memory to implement the method in any one of the foregoing first aspect and the fourth aspect.
  • the communication device further includes a memory.
  • the communication device further includes a communication interface, and the processor is coupled with the communication interface.
  • the communication device is the first device.
  • the communication interface may be a transceiver, or an input/output interface.
  • the communication device is a chip configured in the first device.
  • the communication interface may be an input/output interface.
  • the transceiver may be a transceiver circuit.
  • the input/output interface may be an input/output circuit.
  • a communication device including a processor.
  • the processor is coupled with the memory and can be used to execute instructions in the memory to implement the method in any one of the foregoing second aspect and third aspect.
  • the communication device further includes a memory.
  • the communication device further includes a communication interface, and the processor is coupled with the communication interface.
  • the communication device is a second device.
  • the communication interface may be a transceiver, or an input/output interface.
  • the communication device is a chip configured in the second device.
  • the communication interface may be an input/output interface.
  • the transceiver may be a transceiver circuit.
  • the input/output interface may be an input/output circuit.
  • a processor including: an input circuit, an output circuit, and a processing circuit.
  • the processing circuit is configured to receive a signal through the input circuit and transmit a signal through the output circuit, so that the processor executes the method in any one of the possible implementation manners of the first aspect to the fourth aspect.
  • the above-mentioned processor can be one or more chips
  • the input circuit can be an input pin
  • the output circuit can be an output pin
  • the processing circuit can be a transistor, a gate circuit, a flip-flop, and various logic circuits, etc.
  • the input signal received by the input circuit may be received and input by, for example, but not limited to, a receiver
  • the signal output by the output circuit may be, for example, but not limited to, output to and transmitted by the transmitter
  • the circuit can be the same circuit, which is used as an input circuit and an output circuit at different times.
  • the embodiments of the present application do not limit the specific implementation manners of the processor and various circuits.
  • a processing device including a processor and a memory.
  • the processor is used to read instructions stored in the memory, and can receive signals through a receiver, and transmit signals through a transmitter, so as to execute the method in any one of the possible implementation manners of the first aspect to the fourth aspect.
  • processors there are one or more processors and one or more memories.
  • the memory may be integrated with the processor, or the memory and the processor may be provided separately.
  • the memory can be a non-transitory (non-transitory) memory, such as a read only memory (ROM), which can be integrated with the processor on the same chip, or can be set in different On the chip, the embodiment of the present application does not limit the type of the memory and the setting mode of the memory and the processor.
  • ROM read only memory
  • sending instruction information may be a process of outputting instruction information from the processor
  • receiving capability information may be a process of the processor receiving input capability information.
  • the data output by the processor may be output to the transmitter, and the input data received by the processor may come from the receiver.
  • the transmitter and receiver can be collectively referred to as a transceiver.
  • the processing device in the above-mentioned twelfth aspect may be one or more chips.
  • the processor in the processing device can be implemented by hardware or software.
  • the processor may be a logic circuit, integrated circuit, etc.; when implemented by software, the processor may be a general-purpose processor, which is implemented by reading software codes stored in the memory, and the memory may Integrated in the processor, can be located outside the processor, and exist independently.
  • a computer program product includes: a computer program (also called code, or instruction), which when the computer program is run, causes the computer to execute the first aspect to The method in any possible implementation of the fourth aspect.
  • a computer program also called code, or instruction
  • a computer-readable medium stores a computer program (also called code, or instruction) when it runs on a computer, so that the above-mentioned first to fourth aspects The method in any possible implementation of the aspect is executed.
  • a communication system including the aforementioned first device and second device.
  • Fig. 1 shows a schematic diagram of a suitable communication system applicable to the embodiments of the present application.
  • Fig. 2 shows a schematic diagram of the placement position of the 32-port CSI-RS on the wireless transmission resource.
  • Fig. 3 shows a schematic flowchart of a method for acquiring channel information provided by an embodiment of the present application.
  • Fig. 4 shows a schematic diagram of a method for training a neural network provided by an embodiment of the present application.
  • Figures 5 to 8 show schematic diagrams of placement positions of low-density CSI-RS on wireless transmission resources provided by embodiments of the present application.
  • Figures 9 to 11 show schematic flowcharts of methods for acquiring channel information provided by embodiments of the present application.
  • FIG. 12 shows a schematic block diagram of a communication device provided by an embodiment of the present application.
  • FIG. 13 shows a schematic structural diagram of a communication device provided by another embodiment of the present application.
  • FIG. 14 shows a schematic structural diagram of a terminal device provided by an embodiment of the present application.
  • FIG. 15 shows a schematic structural diagram of an apparatus provided by an embodiment of the present application.
  • LTE Long Term Evolution
  • FDD frequency division duplex
  • TDD time division duplex
  • UMTS universal mobile telecommunication system
  • WiMAX worldwide interoperability for microwave access
  • 5G mobile communication system fifth generation (5th Generation, 5G) mobile communication system or new wireless access Entry technology (new radio access Technology, NR).
  • the 5G mobile communication system may include non-standalone (NSA) and/or standalone (SA).
  • the technical solution provided in this application can also be applied to machine type communication (MTC), inter-machine communication long-term evolution technology (Long Term Evolution-machine, LTE-M), and device to device (device to device, D2D) networks , Machine-to-machine (M2M) network, Internet of things (IoT) network or other networks.
  • MTC machine type communication
  • LTE-M inter-machine communication long-term evolution technology
  • D2D device to device
  • M2M Machine-to-machine
  • IoT Internet of things
  • the IoT network may include, for example, the Internet of Vehicles.
  • V2X vehicle to other devices
  • V2X vehicle to other devices
  • V2X vehicle to other devices
  • V2X vehicle to other devices
  • the V2X may include: vehicle to vehicle (V2V) communication, and the vehicle communicates with Infrastructure (vehicle to infrastructure, V2I) communication, vehicle to pedestrian communication (V2P), or vehicle to network (V2N) communication, etc.
  • V2V vehicle to vehicle
  • V2I infrastructure
  • V2P vehicle to pedestrian communication
  • V2N vehicle to network
  • the technical solution provided in this application can also be applied to other communication systems, such as the 6th Generation (6G) mobile communication system. This application does not limit this.
  • 6G 6th Generation
  • the network device may be any device with a wireless transceiver function.
  • This equipment includes but is not limited to: evolved Node B (eNB), radio network controller (RNC), node B (Node B, NB), base station controller (BSC) , Base transceiver station (BTS), home base station (for example, home evolved NodeB, or home Node B, HNB), baseband unit (BBU), wireless fidelity (wireless fidelity, WiFi) system Access point (access point, AP), wireless relay node, wireless backhaul node, transmission point (transmission point, TP), or transmission and reception point (transmission and reception point, TRP), etc., can also be 5G, such as NR ,
  • the gNB may include a centralized unit (CU) and a DU.
  • the gNB may also include an active antenna unit (AAU).
  • CU implements some functions of gNB
  • DU implements some functions of gNB.
  • CU is responsible for processing non-real-time protocols and services, implementing radio resource control (RRC), and packet data convergence protocol (PDCP) The function of the layer.
  • RRC radio resource control
  • PDCP packet data convergence protocol
  • the DU is responsible for processing the physical layer protocol and real-time services, and realizes the functions of the radio link control (RLC) layer, medium access control (MAC) layer, and physical (physical, PHY) layer.
  • RLC radio link control
  • MAC medium access control
  • PHY physical layer
  • the network device may be a device including one or more of the CU node, the DU node, and the AAU node.
  • the CU can be divided into network equipment in an access network (radio access network, RAN), and the CU can also be divided into network equipment in a core network (core network, CN), which is not limited in this application.
  • the network equipment provides services for the cell, and the terminal equipment communicates with the cell through the transmission resources (for example, frequency domain resources, or spectrum resources) allocated by the network equipment.
  • the cell may belong to a macro base station (for example, a macro eNB or a macro gNB, etc.) , It can also belong to the base station corresponding to the small cell.
  • the small cell here can include: metro cell, micro cell, pico cell, femto cell, etc. , These small cells have the characteristics of small coverage and low transmit power, and are suitable for providing high-speed data transmission services.
  • terminal equipment may also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile equipment, user terminal, Terminal, wireless communication equipment, user agent or user device.
  • UE user equipment
  • the terminal device may be a device that provides users with voice/data connectivity, for example, a handheld device with a wireless connection function, a vehicle-mounted device, and so on.
  • some examples of terminals can be: mobile phones, tablets, computers with wireless transceiver functions (such as laptops, handheld computers, etc.), mobile internet devices (MID), virtual reality (virtual reality, VR) equipment, augmented reality (augmented reality, AR) equipment, wireless terminals in industrial control, wireless terminals in self-driving (self-driving), and wireless in remote medical (remote medical) Terminal, wireless terminal in smart grid, wireless terminal in transportation safety, wireless terminal in smart city, wireless terminal in smart home (smart home), cellular phone, cordless Telephone, session initiation protocol (SIP) telephone, wireless local loop (WLL) station, personal digital assistant (PDA), handheld device with wireless communication function, computing device or connection Other processing equipment to wireless modems, in-vehicle equipment, wearable equipment, terminal equipment in the 5G network, or terminal equipment in the public land mobile network
  • wearable devices can also be called wearable smart devices, which are the general term for the application of wearable technology to intelligently design daily wear and develop wearable devices, such as glasses, gloves, watches, clothing and shoes.
  • a wearable device is a portable device that is directly worn on the body or integrated into the user's clothes or accessories.
  • Wearable devices are not only a hardware device, but also realize powerful functions through software support, data interaction, and cloud interaction.
  • wearable smart devices include full-featured, large-sized, complete or partial functions that can be achieved without relying on smart phones, such as smart watches or smart glasses, and only focus on a certain type of application function, which need to cooperate with other devices such as smart phones. Use, such as all kinds of smart bracelets and smart jewelry for physical sign monitoring.
  • the terminal device may also be a terminal device in an Internet of Things (IoT) system.
  • IoT Internet of Things
  • IoT is an important part of the development of information technology in the future. Its main technical feature is to connect objects to the network through communication technology, so as to realize the intelligent network of human-machine interconnection and interconnection of things. IoT technology can achieve massive connections, deep coverage, and power saving of terminals through, for example, narrowband (narrowband, NB) technology.
  • narrowband narrowband
  • terminal equipment can also include sensors such as smart printers, train detectors, gas stations, etc.
  • the main functions include collecting data (part of the terminal equipment), receiving control information and downlink data from network equipment, and sending electromagnetic waves to transmit uplink data to network equipment. .
  • FIG. 1 shows a schematic diagram of a communication system 100 applicable to the method provided in the embodiment of the present application.
  • the communication system 100 may include at least one network device, such as the network device 101 in the 5G system shown in FIG. 1; the communication system 100 may also include at least one terminal device, as shown in FIG. Terminal equipment 102 to 107.
  • the terminal devices 102 to 107 may be mobile or fixed.
  • One or more of the network device 101 and the terminal devices 102 to 107 can communicate through a wireless link.
  • Each network device can provide communication coverage for a specific geographic area, and can communicate with terminal devices located in the coverage area. For example, the network device may send configuration information to the terminal device, and the terminal device may send uplink data to the network device based on the configuration information; for another example, the network device may send downlink data to the terminal device. Therefore, the network device 101 and the terminal devices 102 to 107 in FIG. 1 constitute a communication system.
  • the terminal devices can communicate directly.
  • D2D technology can be used to realize direct communication between terminal devices.
  • D2D technology can be used for direct communication.
  • the terminal device 106 and the terminal device 107 may communicate with the terminal device 105 individually or at the same time.
  • the terminal devices 105 to 107 may also communicate with the network device 101, respectively. For example, it can directly communicate with the network device 101, as shown in the figure, the terminal devices 105 and 106 can directly communicate with the network device 101; it can also communicate with the network device 101 indirectly, as the terminal device 107 in the figure communicates with the network device via the terminal device 106 101 communication.
  • FIG. 1 exemplarily shows a network device, multiple terminal devices, and communication links between each communication device.
  • the communication system 100 may include multiple network devices, and the coverage of each network device may include other numbers of terminal devices, for example, more or fewer terminal devices. This application does not limit this.
  • Each of the aforementioned communication devices may be configured with multiple antennas.
  • the plurality of antennas may include at least one transmitting antenna for transmitting signals and at least one receiving antenna for receiving signals.
  • each communication device additionally includes a transmitter chain and a receiver chain.
  • Those of ordinary skill in the art can understand that they can all include multiple components related to signal transmission and reception (such as processors, modulators, multiplexers, etc.). , Demodulator, demultiplexer or antenna, etc.). Therefore, multiple antenna technology can be used to communicate between network devices and terminal devices.
  • the wireless communication system 100 may also include other network entities such as a network controller and a mobility management entity, and the embodiment of the present application is not limited thereto.
  • MIMO technology is usually used to increase system capacity, that is, multiple antennas are used at the sender and receiver at the same time.
  • the use of multiple antennas combined with space division multiplexing can double the system capacity, but in fact, the use of multiple antennas also brings interference enhancement problems, so it is often necessary to perform certain processing on the signal to suppress interference The impact.
  • This method of interference suppression through signal processing can be implemented at the receiving end or at the transmitting end.
  • the signal to be sent can be pre-processed and then sent through the MIMO channel.
  • This sending method is precoding.
  • T represents the transposition operation.
  • the MIMO channel needs to be known, and therefore the MIMO channel needs to be estimated.
  • channel estimation is performed by placing a reference signal known at both ends of the transceiver on the wireless transmission resource.
  • FIG. 2 shows the placement position of the 32-port CSI-RS in the NR system. It can be seen from the figure that the CSI-RS needs to occupy nearly 20% of the transmission resources, and the overhead is relatively large.
  • an embodiment of the present application provides a method for acquiring channel information, so as to reduce the overhead of sending a reference signal at the transmitting end or reducing the feedback overhead of feeding back CSI at the receiving end.
  • the terminal device shown in the following embodiments can be replaced with a component (such as a chip or a chip system, etc.) configured in the terminal device.
  • the network device shown in the following embodiments can also be replaced with a component (such as a chip or a chip system, etc.) configured in the network device.
  • the embodiments shown below do not specifically limit the specific structure of the execution body of the method provided in the embodiments of the application, as long as the program that records the code of the method provided in the embodiments of the application can be executed according to the embodiments of the application.
  • the method only needs to communicate.
  • the execution subject of the method provided in the embodiment of the present application may be a terminal device or a network device, or a functional module in the terminal device or the network device that can call and execute the program.
  • FIG. 3 is a schematic flowchart of a method 300 for acquiring channel information according to an embodiment of the present application, shown from the perspective of device interaction.
  • the method 300 shown in FIG. 3 may include S310 to S380. The steps in the method 300 are described in detail below.
  • the first device may send configuration information of the reference signal to the second device to configure the resource for receiving the reference signal for the second device.
  • the second device may send configuration information of the reference signal to the first device to configure the resource for sending the reference signal for the first device.
  • the reference signal may be: channel state information (channel state information reference signal, CSI-RS), demodulation reference signal (demodulation reference signal, DMRS), channel sounding reference signal (sounding reference signal, SRS), etc.
  • the configuration information may include density configuration information of the reference signal and so on.
  • the configuration information of the reference signal may be carried in the RRC message.
  • the following uses an RRC message for configuring the density of CSI-RS as an example to illustrate the format of the RRC message provided in the application embodiment.
  • the RRC message used to configure the density of CSI-RS is as follows:
  • the density indicated in the density CHIOCE field is the regular density, that is, the density of the reference signal defined in the current NR protocol, that is, the density of the second reference signal or the third reference signal mentioned below.
  • the density indicated in the PortDensity field is the low density mentioned in the embodiment of this application, that is, the density of the first reference signal mentioned below.
  • each option in the PortDensity field indicates that the low density is a fraction of the regular density, for example, "one" indicates that the low density is equal to the regular density; “half” indicates that the low density is 1/2 of the regular density; “quarter” indicates The low density is 1/4 of the conventional density.
  • the above description only takes the RRC message format for configuring CSI-RS as an example, and should not constitute a limitation in the embodiment of the present application.
  • the embodiment of this application can also add the PortDensity field to the RRC message used to configure DMRS to configure low-density DMRS, or the embodiment of this application can also add the PortDensity field field to the RRC message used to configure SRS to configure low-density DMRS. Density SRS.
  • PortDensity field may also include options such as “one third” and "one eighth".
  • the embodiment of the present application does not limit the density of the low-density reference signal.
  • the network device may send different RRC messages to the terminal device to configure resources of the low-density reference signal of different densities.
  • the network device when the channel between the network device and the terminal device is relatively stable (for example, the terminal device is indoors, or the terminal device remains stationary, or the terminal device is moving slowly), the network device can be configured with a lower density and low density Reference signal.
  • the network device can configure a low-density reference signal whose density is 1/4 of the regular density.
  • the RRC message sent by the network device to the terminal device can be:
  • the network device may be configured with a relatively high-density low-density reference signal.
  • the network device may configure a low-density reference signal whose density is 1/2 of the regular density.
  • the RRC message sent by the network device to the terminal device may be:
  • S320 The first device sends a second reference signal to the second device.
  • the second device receives the second reference signal from the first device.
  • the second reference signal may be a CSI-RS or may be a DMRS.
  • the second reference signal may be a DMRS or may be an SRS.
  • the first device transmits the second reference signal at the regular density configured in the RRC message.
  • the conventional density refers to the density of the reference signal defined in the current NR protocol.
  • the density of the reference signal refers to the ratio of the resources used to transmit the reference signal to the total transmission resources.
  • the first device sends the second reference signal at a regular density, which can also mean that the number of sending ports used by the network device to send the second reference signal is equal to the number of sending ports of the reference signal defined in the current NR protocol. For example, if the second reference signal is a 32-port CSI-RS, the number of transmission ports used by the first device is 32 when the first device transmits 32-port CSI-RS at a regular density.
  • S330 The second device sends the third CSI to the first device.
  • the first device receives the third CSI from the second device.
  • the third CSI is obtained by the second device based on the second reference signal.
  • the third CSI may be a downlink CSI.
  • the third CSI may be an uplink CSI.
  • the first device trains a neural network based on the third CSI to obtain a first neural network model.
  • the embodiment of the present application does not limit the specific method for training the neural network by the first device.
  • a neural network can be trained using a method of multi-domain feature fusion and embedding of channel data and channel data.
  • the channel frequency response (CFR) (such as CFRa to CFRh shown in FIG. 4) obtained based on the reference signal is used as input data; further, the CFR value can be represented by a vector, At the same time, each channel feature of the CFR is also represented by a vector; further, the CFR and the embedding vector of the channel feature of the CFR are added together, and the fusion result is calculated in the neural network to train the neural network.
  • CFR channel frequency response
  • the input data may also have special tags, such as [channel load sensing (CLS)] and [separator (SEP)].
  • CLS channel load sensing
  • SEP separator
  • each position needs to have the embedding of the position (for example, the position embedding vectors E P0 to E P12 shown in Figure 4) , So that the neural network can learn the relationship between the position of the channel data input.
  • the multi-domain characteristics of channel data can include frequency, time, space, and so on.
  • the frequency characteristic can represent the frequency-related characteristics such as frequency and sub-carrier.
  • E F1 and E F2 as shown in FIG. 4 may respectively represent frequency embedding vectors related to two different subcarriers.
  • Time features can represent time-related features such as time and time offset.
  • E T0 and E T1 as shown in FIG. 4 may respectively represent time embedding vectors related to two different subframes.
  • the manifestation of spatial characteristics in channel data is the difference of antennas, which can represent characteristics related to antennas.
  • E A0 and E A1 in Fig. 4 can respectively represent antenna embedding vectors related to two different receiving antennas or two different transmitting antennas.
  • the first device uses part of the received CSI in the third CSI as input data for training the neural network, and the first device may determine the size of the CSI as input data according to the density of the low-density reference signal configured by the RRC message .
  • the first device uses 1/2 of the third CSI as input data for training the neural network.
  • the first device uses 1/4 of the third CSI as input data for training the neural network.
  • the first device compares the output result of the neural network with the third CSI, and when the difference between the output result and the third CSI is less than a preset threshold, it is considered that the neural network has been trained, that is, the first CSI is obtained.
  • a neural network model A neural network model.
  • the method 300 continues to execute S320 to S340 until When the difference between the output result of the neural network and the third CSI is less than the preset threshold, the method 300 executes S350 to S370.
  • S350 The first device sends the first reference signal to the second device.
  • the second device receives the first reference signal from the first device.
  • the density of the first reference signal is less than or equal to the density of the second reference signal.
  • the first reference signal may be a CSI-RS or may be a DMRS.
  • the first reference signal may be a DMRS or may be an SRS.
  • the first device transmits the first reference signal at a low density configured in the RRC message.
  • low density refers to a density lower than the conventional density.
  • the first device sends the first reference signal at a low density, which means that the number of sending ports used by the first device to send the first reference signal is less than the number of sending ports of the reference signal defined in the current NR protocol. For example, if the first reference signal is a 32-port CSI-RS, if the first device transmits a 32-port CSI-RS according to a low density, the number of transmission ports used by the first device is less than 32.
  • the embodiment of the present application does not limit the density of the first reference signal.
  • the network device may send different RRC messages to configure first reference signals of different densities.
  • the density of the first reference signal may be 1/2 of the density of the second reference signal. That is, the number of transmission ports used by the first device to transmit the first reference signal is 1/2 of the number of transmission ports used for transmitting the second reference signal.
  • the number of transmission ports used by the first device to transmit the second reference signal is 32, and the number of transmission ports used to transmit the first reference signal is 16.
  • the density of the first reference signal may be 1/4 of the density of the second reference signal. That is, the number of transmission ports used by the first device to transmit the first reference signal is 1/4 of the number of transmission ports used for transmitting the second reference signal.
  • the number of transmission ports used by the first device to transmit the second reference signal is 32, and the number of transmission ports used to transmit the first reference signal is 8.
  • the embodiment of the present application does not limit the placement position of the first reference signal on the wireless transmission resource. That is to say, the implementation of this application does not limit the sending port used by the first device to send the first reference signal.
  • the placement position of the first reference signal may be configured as a part of the placement position of the second reference signal, that is to say, the first device may use a part of the transmission ports used to transmit the second reference signal to transmit the second reference signal.
  • a reference signal For example, in the case where the second reference signal and the first reference signal are 32-port CSI-RS, if the transmission port used by the first device to transmit the second reference signal is port #1 to port #32, the first device can use Port #1 to port #32 part of the ports transmit the first reference signal. For example, if the density of the first reference signal is 1/2 of the density of the second reference signal, the first device may use 16 ports from port #1 to port #32 to transmit the first reference signal. For example, port #1 to port #16 may be used to transmit the first reference signal, or port #17 to port #32 may be used to transmit the first reference signal.
  • FIG. 5 to FIG. 8 several examples of the placement position of the first reference signal in the wireless transmission resource are given in conjunction with FIG. 5 to FIG. 8.
  • the CSI-RS of different ports are mapped and transmitted using a resource multiplexing method combining time division, frequency division and code division.
  • the grids with different filling patterns are shown in the two dimensions of time and frequency.
  • the CSI-RS placement positions of different ports on the above, combined with code division multiplexing, can obtain the required CSI-RS placement resources. Taking (a) in Figure 5 as an example, a 16-port CSI-RS needs to be carried.
  • Each filling pattern occupies two grids, that is, two resource elements (Resource Elements, RE), use two codewords of length 2 (such as [1,1] and [1,-1]) on two REs with the same filling pattern to achieve code division multiplexing, so 8 filling patterns occupy
  • the RE can carry 16 CSI-RS in total.
  • FIG. 5 and 6 show examples of the placement position of the first reference signal when the density of the first reference signal is 1/2 of the density of the second reference signal.
  • the first reference signal needs to carry 16 ports. Therefore, the placement position of the first reference signal can directly use 16 ports under the normal density.
  • the placement position of the CSI-RS is shown in Figure 5 (a) and Figure 5 (b).
  • the placement position of the first reference signal may be any half of the placement positions of the 32-port CSI-RS under the normal density.
  • the placement position of the first reference signal shown in (a) and (b) in FIG. 6 is half of the placement position of the 32-port CSI-RS shown in (a) in FIG.
  • the placement position of the first reference signal shown in (c) is half of the placement position of the 32-port CSI-RS shown in (b) in FIG. 2 and the first reference signal shown in (d) in FIG. 6
  • the signal placement position is half of the placement position of the 32-port CSI-RS shown in (c) in FIG. 2.
  • FIG. 7 to 8 show examples of the placement position of the first reference signal when the density of the first reference signal is 1/4 of the density of the second reference signal.
  • the first reference signal needs to carry 8 ports. Therefore, the placement position of the first reference signal can directly use the 8-port under normal density.
  • the placement position of the CSI-RS is shown in Figure 7 (a), (b) and (c).
  • the placement position of the first reference signal may also be any 1/4 of the placement position of the 32-port CSI-RS under the normal density.
  • the placement position of the first reference signal shown in (a) and (b) in FIG. 8 is 1/4 of the placement position of the 32-port CSI-RS shown in (a) in FIG. 2, FIG. 6
  • the placement position of the first reference signal shown in (c) in FIG. 2 is 1/4 of the placement position of the 32-port CSI-RS shown in (b) in FIG. 2
  • (d) in FIG. 6 shows The placement position of the first reference signal is 1/4 of the placement position of the 32-port CSI-RS shown in (c) in FIG. 2.
  • the first device may also send the first reference signal at the regular density configured in the RRC message.
  • the density of the first reference signal is equal to the density of the second reference signal.
  • S360 The second device sends the first CSI to the first device.
  • the first device receives the first CSI from the second device.
  • the first CSI is obtained by the second device according to the first reference signal.
  • the size of the first CSI obtained by the second device according to the first reference signal is smaller than the size of the third CSI obtained according to the second reference signal.
  • the size of the CSI That is, in the case where the third CSI obtained by the second device according to the second reference signal represents all channel information between the first device and the second device, the first CSI obtained by the second device according to the first reference signal represents Part of the channel information between the first device and the second device.
  • the first CSI is obtained by the second device according to a part of the first reference signal. Specifically, the second device obtains the first CSI according to a part of the first reference signal received on the resource for receiving the low-density reference signal. For example, taking a 32-port CSI-RS for the second reference signal and the first reference signal as an example, if the resources configured in the RRC message for transmitting regular density reference signals are shown in Figure 2(a), they are used for The resource for transmitting low-density reference signals is shown in (a) in Figure 5.
  • the first device transmits the first device at the regular density configured in the RRC message.
  • a reference signal that is, the first reference signal is sent on the resource used to transmit the second reference signal.
  • the second device obtains the first CSI according to the part of the first reference signal received on the resource for receiving the low-density reference signal, that is, the second device obtains the first CSI according to the resource shown in Figure 5(a) Part of the first reference signal received on the above obtains the first CSI.
  • the second device obtains the first CSI according to a part of the reference signals in the first reference signal
  • the size of the first CSI is smaller than the size of the third CSI. That is to say, in the case where the third CSI obtained by the second device according to the second reference signal represents all channel information between the first device and the second device, the second device obtained by the second device according to a part of the first reference signal A CSI represents part of channel information between the first device and the second device.
  • the second device sends the obtained first CSI to the first device.
  • the first device obtains the second CSI based on the first CSI and the first neural network model.
  • the second CSI is used to indicate channel information between the first device and the second device.
  • the first device may input the first CSI as input data into the first neural network model to obtain the second CSI.
  • S380 The first device performs data communication with the second device based on the second CSI.
  • the first device may calculate the precoding matrix based on the second CSI, and send the precoding matrix to the second device; further, the first device uses the precoding matrix to send the first data to the second device, and accordingly, After receiving the first data from the first device, the second device uses the precoding matrix to demodulate the first data.
  • S350, S360, and S370 may be repeated multiple times, that is, multiple times that the first device sends the first reference signal, and the second device feeds back the first CSI and the first The device obtains the three operations of the second CSI based on the first CSI and the first neural network model.
  • the neural network is deployed on the side of the first device, and the neural network is trained based on partial channel information in all channel information (third CSI) to obtain the first neural network model, so that the first device All channel information (second CSI) can be recovered based on partial channel information (first CSI) and the first neural network model. Therefore, when the first device obtains the first neural network model, the second device can only feed back part of the channel information (first CSI) to the first device, so that the feedback overhead of the second device can be reduced.
  • the first device when the first device obtains the first neural network model, the first device can send a low-density reference signal to the second device, so that the overhead of sending the reference signal of the second device can be reduced.
  • the method 300 may further include: the first device sends fourth indication information to the second device.
  • the fourth indication information is used to indicate the density of the second reference signal, that is, to indicate that the second reference signal to be sent by the first device is a reference signal of a regular density.
  • the second device receives the second reference signal on the resource used for transmitting the regular density reference signal.
  • the fourth indication information may be carried in the DCI.
  • the fourth indication information may be the RSDensityFlag field in the DCI.
  • the fourth indication information may be carried in the UCI.
  • the fourth indication information may be the RSDensityFlag field in UCI.
  • the first device may not send the fourth indication information.
  • the second device receives the reference signal from the first device on the resource used to transmit the regular density reference signal by default. Until the second device receives the first indication information from the first device, or after the second device sends a second request message to the first device, the second device receives the information from the first device on the resource used to transmit the low-density reference signal. Reference signal.
  • the first indication information is used to indicate the density of the first reference signal
  • the second request message is used to request the first reference signal
  • the second request message is also used to indicate the density of the first reference signal.
  • the method 300 may further include: when the neural network training is completed, the first device sends the first indication information to the second device. That is, when the first neural network model is determined, the first device sends the first indication information to the second device.
  • the first indication information is used to indicate the density of the first reference signal. That is, when the neural network training is completed, the first device may send first indication information to the second device to indicate that the first reference signal to be sent by the first device is a low-density reference signal. Correspondingly, after receiving the first indication information, the second device receives the first reference signal on the resource used for transmitting the low-density reference signal. As mentioned above, the density of the first reference signal may be equal to the density of the second reference signal. In this case, after the second device receives the first indication information, it will be based on the resources used to transmit low-density reference signals The received reference signal obtains the first CSI.
  • the first indication information may be carried in the DCI.
  • the first indication information may be the RSDensityFlag field in the DCI.
  • the first indication information may be carried in the UCI.
  • the first indication information may be the RSDensityFlag field in UCI.
  • the method 300 may further include: the second device sends a second request message to the first device.
  • the second request message is used to request the first reference signal, and the second request message is also used to indicate the density of the first reference signal. That is, the second device may send a second request message to the first device to request a low-density reference signal. Further, after sending the second request message, the second device receives the first reference signal on the resource used for transmitting the low-density reference signal. As mentioned above, the density of the first reference signal can be equal to the density of the second reference signal. In this case, after the second device sends the second request message, it will receive data on the resource used to transmit the low-density reference signal. The received reference signal obtains the first CSI.
  • the second device may periodically send the second request message to the first device; or, the second device may send the second request message to the first device when receiving the second indication information from the first device.
  • the second indication information is used to indicate that the first neural network model has been determined.
  • the second request message may be carried in the UCI.
  • the second request message may be the RSDensityFlag field in UCI.
  • the second request message may be carried in the DCI.
  • the second request message may be the RSDensityFlag field in the DCI.
  • the first device may periodically transmit a reference signal of regular density (second reference signal) and a low-density reference signal (first reference signal).
  • first reference signal a reference signal of regular density
  • second reference signal a low-density reference signal
  • first reference signal a reference signal of regular density
  • second reference signal a low-density reference signal
  • the first device transmits the reference signal of the regular density in the first cycle
  • the second device receives the reference signal from the first device on the resource used to transmit the reference signal of the regular density in the first cycle
  • a device sends a low-density reference signal in the second cycle, and correspondingly, the second device receives the reference signal from the first device on the resource used for transmitting the low-density reference signal in the second cycle.
  • the method 300 may further include: when a preset trigger condition is reached, the first device updates the first neural network model.
  • the step of updating the first neural network model by the first device may include:
  • the first device sends a third reference signal to the second device, where the third reference signal is a regular density reference signal;
  • the first device receives the fourth CSI from the second device, where the fourth CSI is obtained by the second device according to the third reference signal;
  • the first device trains the neural network based on the fourth CSI to obtain the updated first neural network model.
  • the method 300 may continue to repeat S350 to S370 multiple times according to the duration of the communication between the first device and the second device. Therefore, after S380, the first device updates the first neural network model, which can also be understood as: after S380, when the preset trigger condition is reached, the method 300 re-executes S320 to S370. That is, during the communication process between the first device and the second device, S320 to S370 may be periodically performed multiple times.
  • the embodiment of the present application does not limit the preset trigger condition.
  • the preset trigger condition may be that the first timer expires, and the first timer is started when the first device sends the first reference signal to the second device.
  • the first device periodically updates the first neural network model. For example, if the period for the first device to update the first neural network model is T, the first device may set the timing time of the first timer to T.
  • the preset trigger condition may be that the first device determines that the demodulation performance of the second device to demodulate the first data is lower than the preset threshold.
  • the second device demodulates the first data from the first device based on the first precoding matrix from the first device. Further, the second device may feed back the result information of the demodulation of the first data to the first device. equipment. After the first device receives the data demodulation information fed back by the second device, it can count the demodulation performance of the second device to demodulate the first data, and determine that the demodulation performance of the second device to demodulate the first data is lower than the preset demodulation performance. In the case of threshold, update the first neural network model.
  • the demodulation performance of the first data may be, for example, the packet loss rate of the first data. When the packet loss rate of the first data is higher than the preset packet loss rate threshold, it can be determined that the demodulation performance of the first data is lower than Preset threshold.
  • the first device Before updating the first neural network model, that is, before sending the third reference signal, the first device may also send fifth indication information to the second device, where the fifth indication information is used to indicate the density of the third reference signal.
  • the fifth indication information reference may be made to the above description about the fourth indication information. For brevity, details are not repeated here.
  • the preset trigger condition may be that the first device receives the first request message from the second device, and the first request message is used to request to update the first neural network model.
  • the second device demodulates the first data from the first device based on the first precoding matrix from the first device. Further, the second device can demodulate statistics based on the result information of the demodulation of the first data.
  • the first data demodulation performance and in the case where it is determined that the demodulation performance of the first data is lower than the preset threshold, a second request message is sent to the first device to request the first device to update the first neural network model. It can also be understood that the first request message is used to request a third reference signal, that is, a reference signal used to request a regular density.
  • FIG. 9 shows a schematic flowchart of a method 900 for acquiring channel information according to another embodiment of the present application.
  • the method 900 shown in FIG. 9 may include S910 to S970. The steps in the method 900 are described in detail below.
  • the first device may send configuration information of the reference signal to the second device to configure the resource for receiving the reference signal for the second device.
  • the second device may send configuration information of the reference signal to the first device to configure the resource for sending the reference signal for the first device.
  • the reference signal may be: CSI-RS, DMRS, SRS, etc.
  • the configuration information of the reference signal may include density information of the reference signal, etc.
  • the configuration information of the reference signal may be carried in the RRC message.
  • the following uses the RRC message for configuring the density of CSI-RS as an example to illustrate the RRC message format provided in the application embodiment.
  • the RRC message used to configure the density of CSI-RS is as follows:
  • the density indicated in the density CHIOCE field is the regular density, that is, the density of the reference signal defined in the current NR protocol, that is, the density of the second reference signal or the third reference signal mentioned below.
  • the density indicated in the PortDensity field is the low density mentioned in the embodiment of this application, that is, the density of the first reference signal mentioned below.
  • each option in the PortDensity field indicates that the low density is a fraction of the regular density, for example, "one" indicates that the low density is equal to the regular density; “half” indicates that the low density is 1/2 of the regular density; “quarter” indicates The low density is 1/4 of the conventional density.
  • the above description only takes the RRC message format for configuring CSI-RS as an example, and should not constitute a limitation in the embodiment of the present application.
  • the embodiment of this application can also add the PortDensity field to the RRC message used to configure DMRS to configure low-density DMRS, or the embodiment of this application can also add the PortDensity field field to the RRC message used to configure SRS to configure low-density DMRS. Density SRS.
  • PortDensity field may also include options such as “one third” and "one eighth".
  • the embodiment of the present application does not limit the density of the low-density reference signal.
  • the network device may send different RRC messages to the terminal device to configure resources of the low-density reference signal of different densities.
  • the network device when the channel between the network device and the terminal device is relatively stable (for example, the terminal device is indoors, or the terminal device remains stationary, or the terminal device is moving slowly), the network device can be configured with a lower density and low density Reference signal.
  • the network device can configure a low-density reference signal whose density is 1/4 of the regular density.
  • the RRC message sent by the network device to the terminal device can be:
  • the network device may be configured with a relatively high-density low-density reference signal.
  • the network device may configure a low-density reference signal whose density is 1/2 of the regular density.
  • the RRC message sent by the network device to the terminal device may be:
  • S920 The first device sends a second reference signal to the second device.
  • the second device receives the second reference signal from the first device.
  • the second reference signal may be a CSI-RS or may be a DMRS.
  • the second reference signal may be a DMRS or may be an SRS.
  • the first device transmits the second reference signal at the regular density configured in the RRC message.
  • the conventional density refers to the density of the reference signal defined in the current NR protocol.
  • the density of the reference signal refers to the ratio of the resources used to transmit the reference signal to the total transmission resources.
  • the first device sends the second reference signal at a regular density, which may also mean that the number of sending ports used by the network device to send the second reference signal is equal to the number of sending ports of the reference signal defined in the current NR protocol. For example, if the second reference signal is a 32-port CSI-RS, the number of transmission ports used by the first device is 32 when the first device transmits 32-port CSI-RS at a regular density.
  • the second device trains a neural network based on the third CSI to obtain a second neural network model.
  • the third CSI is obtained by the second device according to the second reference signal.
  • the embodiment of the present application does not limit the specific method for training the neural network by the second device.
  • a neural network can be trained using a method of multi-domain feature fusion and embedding of channel data and channel data.
  • the CFR obtained based on the reference signal (such as CFRa to CFRh shown in Figure 4) is used as input data; further, the CFR value can be represented by a vector, and each channel characteristic of the CFR can also be used as input data.
  • Vector representation further, the CFR and CFR channel feature embedding vectors are added together, and the fusion result is calculated in the neural network to train the neural network.
  • the input data may also have special marks, such as [CLS] and [SEP].
  • [CLS] is used to classify CFR in subsequent downstream tasks.
  • [SEP] CFR used to separate different domains.
  • each position needs to have the embedding of the position (for example, the position embedding vectors E P0 to E P12 shown in Figure 4) , So that the neural network can learn the relationship between the position of the channel data input.
  • the multi-domain characteristics of channel data can include frequency, time, space, and so on.
  • the frequency characteristic can represent the frequency-related characteristics such as frequency and sub-carrier.
  • E F1 and E F2 as shown in FIG. 4 may respectively represent frequency embedding vectors related to two different subcarriers.
  • Time features can represent time-related features such as time and time offset.
  • E T0 and E T1 as shown in FIG. 4 may respectively represent time embedding vectors related to two different subframes.
  • the manifestation of spatial characteristics in channel data is the difference of antennas, which can represent characteristics related to antennas.
  • E A0 and E A1 in Fig. 4 can respectively represent antenna embedding vectors related to two different receiving antennas or two different transmitting antennas.
  • the second device uses part of the CSI in the third CSI as input data for training the neural network, and the second device may determine the size of the CSI as the input data according to the density of the low-density reference signal configured by the RRC message.
  • the second device uses 1/2 of the third CSI as input data for training the neural network.
  • the second device uses 1/4 of the third CSI as input data for training the neural network.
  • the second device compares the output result of the neural network with the third CSI, and when the difference between the output result and the third CSI is less than a preset threshold, it is considered that the neural network has been trained, that is, the first CSI is obtained.
  • the method 900 continues to execute S920 to S930 until When the difference between the output result of the neural network and the third CSI is less than the preset threshold, the method 900 executes S940 to S960.
  • S940 The first device sends the first reference signal to the second device.
  • the second device receives the first reference signal from the first device.
  • the density of the first reference signal is less than the density of the second reference signal.
  • the first reference signal may be a CSI-RS or may be a DMRS.
  • the first reference signal may be a DMRS or may be an SRS.
  • the first device sends the first reference signal at the low density configured in the RRC message.
  • low density refers to a density lower than the conventional density.
  • the first device sends the first reference signal at a low density, which means that the number of sending ports used by the first device to send the first reference signal is less than the number of sending ports of the reference signal defined in the current NR protocol. For example, if the first reference signal is a 32-port CSI-RS, if the first device transmits a 32-port CSI-RS according to a low density, the number of transmission ports used by the first device is less than 32.
  • the embodiment of the present application does not limit the density of the first reference signal configured in the RRC message.
  • the network device may send different RRC messages to configure first reference signals of different densities.
  • the density of the first reference signal may be 1/2 of the density of the second reference signal. That is, the number of transmission ports used by the first device to transmit the first reference signal is 1/2 of the number of transmission ports used for transmitting the second reference signal.
  • the number of transmission ports used by the first device to transmit the second reference signal is 32, and the number of transmission ports used to transmit the first reference signal is 16.
  • the density of the first reference signal may be 1/4 of the density of the second reference signal. That is, the number of transmission ports used by the first device to transmit the first reference signal is 1/4 of the number of transmission ports used for transmitting the second reference signal.
  • the number of transmission ports used by the first device to transmit the second reference signal is 32, and the number of transmission ports used to transmit the first reference signal is 8.
  • the embodiment of the present application does not limit the placement position of the first reference signal on the wireless transmission resource. That is to say, the implementation of this application does not limit the sending port used by the first device to send the first reference signal.
  • the placement position of the first reference signal may be configured as a part of the placement position of the second reference signal, that is to say, the first device may use a part of the transmission ports used to transmit the second reference signal to transmit the second reference signal.
  • a reference signal For example, in the case where the second reference signal and the first reference signal are 32-port CSI-RS, if the transmission port used by the first device to transmit the second reference signal is port #1 to port #32, the first device can use Port #1 to port #32 part of the ports transmit the first reference signal. For example, if the density of the first reference signal is 1/2 of the density of the second reference signal, the first device may use 16 ports from port #1 to port #32 to transmit the first reference signal. For example, port #1 to port #16 may be used to transmit the first reference signal, or port #17 to port #32 may be used to transmit the first reference signal.
  • the CSI-RS of different ports are mapped and transmitted using a resource multiplexing method combining time division, frequency division and code division.
  • the grids with different filling patterns are shown in the two dimensions of time and frequency.
  • code division multiplexing the required CSI-RS placement resources can be obtained.
  • Each filling pattern occupies two grids, that is, two resource elements (Resource Elements, RE), use two codewords of length 2 (for example, [1,1] and [1,-1]) on two REs with the same filling pattern to achieve code division multiplexing, so all kinds of filling patterns occupy
  • the RE can carry 16 CSI-RS in total.
  • FIG. 5 and 6 show examples of the placement position of the first reference signal when the density of the first reference signal is 1/2 of the density of the second reference signal.
  • the first reference signal needs to carry 16 ports. Therefore, the placement position of the first reference signal can directly use 16 ports under the normal density.
  • the placement position of the CSI-RS is shown in Figure 5 (a) and Figure 5 (b).
  • the placement position of the first reference signal may be any half of the placement positions of the 32-port CSI-RS under the normal density.
  • the placement position of the first reference signal shown in (a) and (b) in FIG. 6 is half of the placement position of the 32-port CSI-RS shown in (a) in FIG.
  • the placement position of the first reference signal shown in (c) is half of the placement position of the 32-port CSI-RS shown in (b) in FIG. 2 and the first reference signal shown in (d) in FIG. 6
  • the signal placement position is half of the placement position of the 32-port CSI-RS shown in (c) in FIG. 2.
  • FIG. 7 to 8 show examples of the placement position of the first reference signal when the density of the first reference signal is 1/4 of the density of the second reference signal.
  • the first reference signal needs to carry 8 ports. Therefore, the placement position of the first reference signal can directly use the 8-port under normal density.
  • the placement position of the CSI-RS is shown in Figure 7 (a), (b) and (c).
  • the placement position of the first reference signal may also be any 1/4 of the placement position of the 32-port CSI-RS under the normal density.
  • the placement position of the first reference signal shown in (a) and (b) in FIG. 8 is 1/4 of the placement position of the 32-port CSI-RS shown in (a) in FIG.
  • the placement position of the first reference signal shown in (c) in FIG. 2 is 1/4 of the placement position of the 32-port CSI-RS shown in (b) in FIG. 2, and (d) in FIG.
  • the placement position of the first reference signal is 1/4 of the placement position of the 32-port CSI-RS shown in (c) in FIG. 2.
  • the second device obtains the second CSI based on the first CSI and the second neural network model.
  • the first CSI is obtained by the second device according to the first reference signal. It can be understood that, in this case, since the density of the first reference signal is smaller than the density of the second reference signal, the size of the first CSI obtained by the second device according to the first reference signal is smaller than the size of the third CSI obtained according to the second reference signal.
  • the size of the CSI That is, in the case where the third CSI obtained by the second device according to the second reference signal represents all channel information between the first device and the second device, the first CSI obtained by the second device according to the first reference signal represents Part of the channel information between the first device and the second device.
  • the second device obtains the second CSI based on the first CSI and the second neural network model. .
  • the second CSI is used to indicate channel information between the first device and the second device.
  • the second device may input the first CSI as input data into the second neural network model to obtain the second CSI.
  • S960 The second device sends the second CSI to the first device.
  • the first device receives the second CSI from the second device.
  • the first device performs data communication with the second device based on the second CSI.
  • the first device may calculate the precoding matrix based on the second CSI, and send the precoding matrix to the second device; further, the first device uses the precoding matrix to send the first data to the second device, and accordingly, After receiving the first data from the first device, the second device uses the precoding matrix to demodulate the first data.
  • S940, S950, and S960 may be repeated multiple times, that is, multiple times that the first device sends the first reference signal, and the second device is based on the first CSI and the second device.
  • the neural network model obtains the second CSI and the second device feeds back the three operations of the second CSI.
  • the neural network is deployed on the second device side, and the neural network is trained based on partial channel information in all channel information (third CSI) to obtain the second neural network model, so that the second device All channel information (second CSI) can be recovered based on partial channel information (first CSI) and a second neural network model. Therefore, when the second device obtains the first neural network model, the first device can send a low-density reference signal to the second device, so that the overhead of sending the reference signal can be reduced.
  • the method 900 may further include: the first device sends fourth indication information to the second device.
  • the fourth indication information is used to indicate the density of the second reference signal, that is, to indicate that the second reference signal to be sent by the first device is a reference signal of a regular density.
  • the second device receives the second reference signal on the resource used for transmitting the regular density reference signal.
  • the fourth indication information may be carried in the DCI.
  • the fourth indication information may be the RSDensityFlag field in the DCI.
  • the fourth indication information may be carried in the UCI.
  • the fourth indication information may be the RSDensityFlag field in UCI.
  • the first device may not send the fourth indication information.
  • the second device receives the reference signal from the first device on the resource used to transmit the regular density reference signal by default. Until the second device receives the first indication information from the first device, or after the second device sends a second request message to the first device, the second device receives the information from the first device on the resource used to transmit the low-density reference signal. Reference signal.
  • the first indication information is used to indicate the density of the first reference signal
  • the second request message is used to request the first reference signal
  • the second request message is also used to indicate the density of the first reference signal.
  • the method 900 may further include: the first device sends the first indication information to the second device.
  • the first indication information is used to indicate the density of the first reference signal. That is, when the neural network training is completed, the first device may send first indication information to the second device to indicate that the first reference signal to be sent by the first device is a low-density reference signal. Correspondingly, after receiving the first indication information, the second device receives the first reference signal on the resource used for transmitting the low-density reference signal. As mentioned above, the density of the first reference signal may be equal to the density of the second reference signal. In this case, after the second device receives the first indication information, it will be based on the resources used to transmit low-density reference signals The received reference signal obtains the first CSI.
  • the first device may periodically send the first indication information to the second device; or the first device may send the first indication information to the second device when receiving the third indication information from the second device.
  • the third indication information is used to indicate that the second neural network model has been determined.
  • the first indication information may be carried in the DCI.
  • the first indication information may be the RSDensityFlag field in the DCI.
  • the first indication information may be carried in the UCI.
  • the first indication information may be the RSDensityFlag field in UCI.
  • the method 900 may further include: the second device sends a second request message to the first device.
  • the second request message is used to request the first reference signal, and the second request message is also used to indicate the density of the first reference signal. That is, the second device may send a second request message to the first device to request a low-density reference signal. Further, after sending the second request message, the second device receives the first reference signal on the resource used for transmitting the low-density reference signal. As mentioned above, the density of the first reference signal can be equal to the density of the second reference signal. In this case, after the second device sends the second request message, it will receive data on the resource used to transmit the low-density reference signal. The received reference signal obtains the first CSI.
  • the second request message may be carried in the UCI.
  • the second request message may be the RSDensityFlag field in UCI.
  • the second request message may be carried in the DCI.
  • the second request message may be the RSDensityFlag field in the DCI.
  • the first device may periodically transmit a reference signal of regular density (second reference signal) and a low-density reference signal (first reference signal).
  • first reference signal a reference signal of regular density
  • second reference signal a low-density reference signal
  • first reference signal a reference signal of regular density
  • second reference signal a low-density reference signal
  • the first device transmits the reference signal of the regular density in the first cycle
  • the second device receives the reference signal from the first device on the resource used to transmit the reference signal of the regular density in the first cycle
  • a device transmits a low-density reference signal in the second cycle, and accordingly, the second device receives the reference signal from the first device on the resource used for transmitting the low-density reference signal in the second cycle.
  • the method 900 may further include: when a preset trigger condition is reached, the second device updates the second neural network model.
  • the step of updating the second neural network model by the second device may include:
  • the first device sends a third reference signal to the second device, where the third reference signal is a regular density reference signal;
  • the second device trains the neural network based on the fourth CSI to obtain the updated second neural network model, and the fourth CSI is obtained according to the third reference signal;
  • the method 900 may continue to execute S940 to S960 repeatedly according to the duration of the communication between the first device and the second device. Therefore, after S970, the second device updates the second neural network model, which can also be understood as: after S970, when the preset trigger condition is reached, the method 900 re-executes S920 to S960. That is, during the communication process between the first device and the second device, S920 to S960 may be periodically performed multiple times.
  • the embodiment of the present application does not limit the preset trigger condition.
  • the preset trigger condition may be that the second timer expires, and the second timer is started when the second device receives the first reference signal from the first device.
  • the second device periodically updates the second neural network model. For example, if the period for the second device to update the second neural network model is T, the second device may set the timing time of the second timer to T.
  • the preset trigger condition may be that the second device determines that the demodulation performance of demodulating the first data is lower than a preset threshold.
  • the second device demodulates the first data from the first device based on the precoding matrix from the first device. Further, the second device can demodulate the first data based on the result information of the demodulation of the first data. Data demodulation performance, and if it is determined that the demodulation performance of the first data is lower than the preset threshold, the second neural network model is updated.
  • the demodulation performance of the first data may be, for example, the packet loss rate of the first data. When the packet loss rate of the first data is higher than the preset packet loss rate threshold, it can be determined that the demodulation performance of the first data is lower than Preset threshold.
  • the second device Before updating the second neural network model, that is, before receiving the third reference signal from the first device, the second device may also send a first request message to the second device, where the first request message is used to request the third reference signal, That is, it is used to request a regular density reference signal.
  • the first device is a network device
  • the second device is a terminal device
  • the second reference signal and the first reference signal are 32-port CSI-RS as examples to illustrate the acquisition channel provided by the embodiment of the present application. Information method.
  • the neural network is deployed on the side of the network device as an example for description.
  • the method 1000 may include S1010 to S1090, and each step is described in detail below.
  • S1010 The network device sends an RRC message to the terminal device.
  • the terminal device receives the RRC message from the network device.
  • the RRC message can be used to configure resources for transmitting regular-density CSI-RS (a column of the second reference signal) and low-density CSI-RS (an example of the first reference signal), for example, it can be used to configure a regular-density CSI-RS And the density of low-density CSI-RS.
  • regular-density CSI-RS a column of the second reference signal
  • low-density CSI-RS an example of the first reference signal
  • S1020 The network device sends fourth indication information to the terminal device.
  • the terminal device receives the fourth indication information from the network device.
  • the fourth indication information is used to indicate that the CSI-RS to be sent by the network device is a regular density CSI-RS.
  • the terminal device receives the CSI-RS on the resource used to transmit the regular density CSI-RS.
  • the fourth indication information may be carried in the DCI.
  • the fourth indication information may be the RSDensityFlag field in the DCI.
  • S1030 The network device sends a regular-density CSI-RS to the terminal device.
  • the terminal device receives the regular density CSI-RS from the network device.
  • the network device transmits the regular density CSI-RS at the regular density configured in the RRC message. For example, if the CSI-RS sent by the network device is a 32-port CSI-RS, the number of transmission ports used by the network device is 32 when the network device sends 32-port CSI-RS at a regular density.
  • S1040 The terminal device sends the third CSI to the network device.
  • the network device receives the third CSI from the terminal device.
  • the third CSI is obtained by the terminal device based on the conventional density CSI-RS.
  • the way the terminal device obtains the third CSI based on the conventional density CSI-RS can refer to the prior art.
  • the embodiment of the present application will not be described in detail.
  • the network device trains a neural network based on the third CSI to obtain a first neural network model.
  • the method for training the neural network by the network device may refer to the description in S340 above. For brevity, the details are not repeated in the embodiment of the present application.
  • the network device sends first instruction information to the terminal device.
  • the terminal device receives the first indication information from the network device.
  • the first indication information is used to indicate that the CSI-RS to be sent by the network device is a low-density CSI-RS.
  • the terminal device receives the CSI-RS on the resource used to transmit the low-density CSI-RS.
  • the first indication information may be carried in the DCI.
  • the first indication information may be the RSDensityFlag field in the DCI.
  • S1070 The network device sends a low-density CSI-RS to the terminal device.
  • the terminal device receives the low-density CSI-RS from the network device.
  • the network device transmits the low-density CSI-RS at the low density configured in the RRC message. For example, if the network device sends a 32-port CSI-RS, if the network device sends a 32-port CSI-RS at a low density, the number of transmission ports used by the network device is less than 32.
  • the embodiment of the present application does not limit the density of the low-density CSI-RS and the placement position in the wireless resource. Specifically, reference may be made to the description in S350 above, and for the sake of brevity, details are not repeated in the embodiment of the present application.
  • S1080 The terminal device sends the first CSI to the network device.
  • the network device receives the first CSI from the terminal device.
  • the first CSI is obtained by the terminal device according to the low-density CSI-RS. It can be understood that in this case, since the density of the low-density CSI-RS is less than the density of the regular-density CSI-RS, the size of the first CSI obtained by the terminal device according to the low-density CSI-RS is smaller than that obtained according to the regular-density CSI-RS The size of the third CSI. That is, in the case where the third CSI obtained by the terminal device according to the regular density CSI-RS represents all downlink channel information, the first CSI obtained by the terminal device according to the low density CSI-RS represents part of the downlink channel information.
  • the terminal device sends the obtained first CSI to the network device.
  • the network device obtains a second CSI based on the first CSI and the first neural network model.
  • the second CSI is used to indicate downlink channel information between the network device and the terminal device.
  • the network device may input the first CSI as input data into the first neural network model to obtain the second CSI.
  • the neural network is deployed on the terminal device side as an example for description.
  • the method 1100 may include S1110 to S1170, and each step is described in detail below.
  • S1110 The network device sends an RRC message to the terminal device.
  • the terminal device receives the RRC message from the network device.
  • the RRC message can be used to configure resources for transmitting regular-density CSI-RS (a column of the second reference signal) and low-density CSI-RS (an example of the first reference signal), for example, it can be used to configure a regular-density CSI-RS And the density of low-density CSI-RS.
  • regular-density CSI-RS a column of the second reference signal
  • low-density CSI-RS an example of the first reference signal
  • S1120 The network device sends a regular-density CSI-RS to the terminal device.
  • the terminal device receives the regular density CSI-RS from the network device.
  • the network device transmits the regular density CSI-RS at the regular density configured in the RRC message. For example, if the CSI-RS sent by the network device is a 32-port CSI-RS, the number of transmission ports used by the network device is 32 when the network device sends 32-port CSI-RS at a regular density.
  • the terminal device trains a neural network based on the third CSI to obtain a second neural network model.
  • the third CSI is obtained by the terminal device based on the conventional density CSI-RS.
  • the way the terminal device obtains the third CSI based on the conventional density CSI-RS can refer to the prior art.
  • the embodiment of the present application will not be described in detail.
  • the method for training the neural network by the network device may refer to the description in S340 above. For brevity, the details are not repeated in the embodiment of the present application.
  • the terminal device After obtaining the second neural network model, the terminal device sends a second request message to the network device. Correspondingly, in S1140, the network device receives the second request message from the terminal device.
  • the second request message is used to request low-density CSI-RS. That is to say, after sending the second request message to the network device, the terminal device receives the low-density CSI-RS on the resource used to transmit the low-density CSI-RS.
  • the second request message can be carried in UCI.
  • the second request message may be the RSDensityFlag field in UCI.
  • S1150 The network device sends a low-density CSI-RS to the terminal device.
  • the terminal device receives the low-density CSI-RS from the network device.
  • the network device transmits the low-density CSI-RS at the low density configured in the RRC message. For example, if the network device sends a 32-port CSI-RS, if the network device sends a 32-port CSI-RS at a low density, the number of transmission ports used by the network device is less than 32.
  • the embodiment of the present application does not limit the density of the low-density CSI-RS and the placement position in the wireless resource. Specifically, reference may be made to the description in S350 above, and for the sake of brevity, the details are not repeated in the embodiment of the present application.
  • the terminal device obtains the second CSI based on the first CSI and the second neural network model.
  • the first CSI is obtained by the terminal device according to the low-density CSI-RS. It can be understood that in this case, since the density of the low-density CSI-RS is less than the density of the regular-density CSI-RS, the size of the first CSI obtained by the terminal device according to the low-density CSI-RS is smaller than that obtained according to the regular-density CSI-RS The size of the third CSI. That is, in the case where the third CSI obtained by the terminal device according to the regular density CSI-RS represents all downlink channel information, the first CSI obtained by the terminal device according to the low density CSI-RS represents part of the downlink channel information.
  • the network device may input the first CSI as input data into the first neural network model to obtain the second CSI.
  • the second CSI is used to indicate downlink channel information between the network device and the terminal device.
  • S1170 The terminal device sends the second CSI to the network device.
  • the network device receives the second CSI from the terminal device.
  • FIG. 12 is a schematic block diagram of a communication device provided by an embodiment of the present application.
  • the communication device 2000 may include a processing unit 2100 and a transceiving unit 2200.
  • the communication device 2000 may correspond to the first device in the above method embodiment, for example, it may be the first device, or a component (such as a chip or a chip system, etc.) configured in the first device. ).
  • the communication device 2000 may correspond to the first device in the method 300 and the method 900 according to the embodiments of the present application, and the communication device 2000 may include methods for executing the method 300 in FIG. 3 and the method 900 in FIG. The unit of the method executed by the first device.
  • each unit in the communication device 2000 and the other operations and/or functions described above are used to implement the corresponding process of any one of the method 300 in FIG. 3 and the method 900 in FIG. 9, respectively. It should be understood that the specific process for each unit to execute the foregoing corresponding steps has been described in detail in the foregoing method embodiment, and is not repeated here for brevity.
  • the communication device 2000 may correspond to the second device in the above method embodiment, for example, it may be the second device, or a component (such as a chip or a chip system) configured in the second device Wait).
  • the communication device 2000 may correspond to the second device in the method 300 and the method 900 according to the embodiments of the present application, and the communication device 2000 may include methods for executing the method 300 in FIG. 3 and the method 900 in FIG. The unit of the method performed by the second device.
  • each unit in the communication device 2000 and the other operations and/or functions described above are used to implement the corresponding process of any one of the method 300 in FIG. 3 and the method 900 in FIG. 9, respectively. It should be understood that the specific process for each unit to execute the foregoing corresponding steps has been described in detail in the foregoing method embodiment, and is not repeated here for brevity.
  • the communication device 2000 may correspond to the terminal device in the above method embodiment, for example, it may be a terminal device, or a component (such as a chip or a chip system, etc.) configured in the terminal device.
  • the communication device 2000 may correspond to the terminal device in the method 1000 and the method 1100 according to the embodiments of the present application, and the communication device 2000 may include a terminal device for executing the method 1000 in FIG. 10 and the method 1100 in FIG. 11 The unit of the method performed by the device.
  • each unit in the communication device 2000 and other operations and/or functions described above are used to implement the corresponding process of any one of the method 1000 in FIG. 10 and the method 1100 in FIG. 11, respectively. It should be understood that the specific process for each unit to execute the foregoing corresponding steps has been described in detail in the foregoing method embodiment, and is not repeated here for brevity.
  • the transceiver unit 2200 in the communication device 2000 can be implemented through an input/output interface, and the processing unit 2100 in the communication device 2000 can be implemented through the chip or chip.
  • the processor, microprocessor or integrated circuit integrated in the system is implemented.
  • the communication device 2000 may correspond to the network device in the above method embodiment, for example, it may be a network device, or a component (such as a chip or a chip system, etc.) configured in the network device.
  • the communication device 2000 may correspond to the network equipment in the method 1000 and the method 1100 according to the embodiments of the present application, and the communication device 2000 may include a network device for executing the method 1000 in FIG. 10 and the method 1100 in FIG. 11 The unit of the method performed by the device.
  • the units in the communication device 2000 and the other operations and/or functions described above are used to implement the corresponding process of any one of the method 1000 in FIG. 10 and the method 1100 in FIG. 11, respectively. It should be understood that the specific process for each unit to execute the foregoing corresponding steps has been described in detail in the foregoing method embodiment, and is not repeated here for brevity.
  • the transceiver unit 2200 in the communication device 2000 can be implemented through an input/output interface, and the processing unit 2100 in the communication device 2000 can be implemented through the chip or chip.
  • the processor, microprocessor or integrated circuit integrated in the system is implemented.
  • FIG. 13 is a schematic structural diagram of a communication device 3000 provided in the implementation of this application.
  • the communication device 3000 includes a processor 3100 and a communication interface 3200.
  • the communication device 3000 may further include a memory 3300.
  • the processor 3100, the communication interface 3200, and the memory 3300 may be connected through a bus.
  • processor 3100 and the memory 3300 may be combined into one processing device, and the processor 3100 is configured to execute program codes stored in the memory 3300 to implement the foregoing functions.
  • the memory 3300 may also be integrated in the processor 3100 or independent of the processor 3100.
  • the communication device 3000 may correspond to the first device in the above method embodiment.
  • the communication device 3000 may include a unit for executing the method executed by the first device in the method 300 in FIG. 3 and the method 900 in FIG. 9.
  • the units in the communication device 3000 and the other operations and/or functions described above are used to implement the corresponding processes executed by the first device in the method 300 in FIG. 3 and the method 900 in FIG. 9, respectively. It should be understood that the specific process for each unit to execute the foregoing corresponding steps has been described in detail in the foregoing method embodiment, and is not repeated here for brevity.
  • the communication device 3000 may correspond to the second device in the above method embodiment.
  • the communication device 3000 may include a unit for executing the method executed by the second device chip in the method 300 in FIG. 3 and the method 900 in FIG. 9.
  • the units in the communication device 800 and the other operations and/or functions described above are used to implement the corresponding processes executed by the second device in the method 300 in FIG. 3 and the method 900 in FIG. 9, respectively. It should be understood that the specific process for each unit to execute the foregoing corresponding steps has been described in detail in the foregoing method embodiment, and is not repeated here for brevity.
  • FIG. 14 is a schematic structural diagram of a terminal device 4000 provided by an embodiment of the present application.
  • the terminal device 4000 can be applied to the system shown in FIG. 1 to perform the functions of the terminal device in the foregoing method embodiment.
  • the antenna and radio frequency circuit with the transceiver function are denoted as the transceiver unit 4100
  • the processor with the processing function is denoted as the processing unit 4200. That is, the terminal device includes a transceiver unit 4100 and a processing unit 4200.
  • the transceiving unit 4100 may also be referred to as a transceiver, a transceiver, a transceiving device, and the like.
  • the processing unit 4200 may also be referred to as a processor, a processing board, a processing module, a processing device, and so on.
  • the device for implementing the receiving function in the transceiving unit 4100 can be regarded as the receiving unit
  • the device for implementing the sending function in the transceiving unit 4100 can be regarded as the sending unit, that is, the transceiving unit 4100 includes a receiving unit and a sending unit.
  • the transceiver unit may sometimes be referred to as a transceiver, a transceiver, or a transceiver circuit.
  • the receiving unit may sometimes be referred to as a receiver, a receiver, or a receiving circuit.
  • the sending unit may sometimes be called a transmitter, a transmitter, or a transmitting circuit.
  • the transceiving unit 4100 is also used to perform the receiving operations on the terminal device side in S1010 to S1030 and S1060 to S1070 shown in FIG. 10, and the transceiving unit 4100 is also used to perform the receiving operations shown in FIG.
  • the sending operation on the terminal device side in S1040 and S1080, and/or the transceiving unit 4100 is also used to perform other transceiving steps on the terminal device side.
  • the transceiver unit 4100 is further configured to perform the receiving operations on the terminal device side in S1110, S1120, and S1150 shown in FIG. 11, and the transceiver unit 4100 is also configured to perform S1140 shown in FIG. With the sending operation on the terminal device side in S1170, and/or the transceiving unit 4100 is also used to perform other transceiving steps on the terminal device side.
  • the processing unit 4200 is configured to execute steps S1130 and S1160 shown in FIG. 11, and/or the processing unit 4200 is further configured to execute other processing steps on the terminal device side.
  • FIG. 14 is only an example and not a limitation, and the foregoing terminal device including a transceiver unit and a processing unit may not rely on the structure shown in FIG. 14.
  • FIG. 15 shows an apparatus 5000 provided by an embodiment of the present application, which may be used to execute the method executed by the foregoing terminal device or network device.
  • the apparatus 5000 may be a communication device or a chip in a communication device.
  • the device 5000 includes: at least one input interface (Input(s)) 5100, a logic circuit 5200, and at least one output interface (Output(s)) 5300.
  • the aforementioned logic circuit 5200 may be a chip, or other integrated circuits that can implement the method of the present application.
  • the logic circuit 5200 can implement the methods executed by the terminal device or the network device in each of the foregoing embodiments;
  • the input interface 5100 is used to receive data; the output interface 5300 is used to send data.
  • the input interface 5100 can be used to receive the reference signal sent by the network device, the input interface 5100 can also be used to receive the RRC message sent by the network device; the output interface 5300 can be used to send the network device Send CSI.
  • the output interface 5300 is used to send a reference signal to the terminal device, and the output interface can also be used to send an RRC message to the terminal device; the input interface 5100 can be used to receive CSI sent by the terminal device.
  • the functions of the input interface 5100, the logic circuit 5200, or the output interface 5300 can refer to the method executed by the terminal device or the network device in the foregoing embodiments, which will not be repeated here.
  • An embodiment of the present application also provides a processing device, including a processor and an interface; the processor is configured to execute the method in any of the foregoing method embodiments.
  • the aforementioned processing device may be one or more chips.
  • the processing device may be a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), or a system on chip (SoC), or It is a central processor unit (CPU), a network processor (NP), a digital signal processing circuit (digital signal processor, DSP), or a microcontroller (microcontroller unit). , MCU), it can also be a programmable logic device (PLD) or other integrated chips.
  • FPGA field programmable gate array
  • ASIC application specific integrated circuit
  • SoC system on chip
  • CPU central processor unit
  • NP network processor
  • DSP digital signal processing circuit
  • microcontroller unit microcontroller unit
  • MCU programmable logic device
  • PLD programmable logic device
  • each step of the above method can be completed by an integrated logic circuit of hardware in the processor or instructions in the form of software.
  • the steps of the method disclosed in the embodiments of the present application may be directly embodied as being executed and completed by a hardware processor, or executed and completed by a combination of hardware and software modules in the processor.
  • the software module can be located in a mature storage medium in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, or electrically erasable programmable memory, registers.
  • the storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware. In order to avoid repetition, it will not be described in detail here.
  • the processor in the embodiment of the present application may be an integrated circuit chip with signal processing capability.
  • the steps of the foregoing method embodiments can be completed by hardware integrated logic circuits in the processor or instructions in the form of software.
  • the above-mentioned processor may be a general-purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components .
  • DSP digital signal processor
  • ASIC application specific integrated circuit
  • FPGA field programmable gate array
  • the methods, steps, and logical block diagrams disclosed in the embodiments of the present application can be implemented or executed.
  • the general-purpose processor may be a microprocessor or the processor may also be any conventional processor or the like.
  • the steps of the method disclosed in the embodiments of the present application may be directly embodied as being executed and completed by a hardware decoding processor, or executed and completed by a combination of hardware and software modules in the decoding processor.
  • the software module can be located in a mature storage medium in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, or electrically erasable programmable memory, registers.
  • the storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.
  • the memory in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memory.
  • the non-volatile memory can be read-only memory (ROM), programmable read-only memory (programmable ROM, PROM), erasable programmable read-only memory (erasable PROM, EPROM), and electrically available Erase programmable read-only memory (electrically EPROM, EEPROM) or flash memory.
  • the volatile memory may be random access memory (RAM), which is used as an external cache.
  • RAM random access memory
  • static random access memory static random access memory
  • dynamic RAM dynamic RAM
  • DRAM dynamic random access memory
  • synchronous dynamic random access memory synchronous DRAM, SDRAM
  • double data rate synchronous dynamic random access memory double data rate SDRAM, DDR SDRAM
  • enhanced synchronous dynamic random access memory enhanced SDRAM, ESDRAM
  • synchronous connection dynamic random access memory serial DRAM, SLDRAM
  • direct rambus RAM direct rambus RAM
  • the present application also provides a computer program product, the computer program product includes: computer program code, when the computer program code runs on a computer, the computer executes the steps shown in FIGS. 3 and 9 The method performed by the first device and the second device respectively in the illustrated embodiment, or the method performed by the terminal device and the network device in the embodiments shown in FIG. 10 to FIG. 11 respectively.
  • the present application also provides a computer-readable medium that stores program code, and when the program code runs on a computer, the computer executes the steps shown in FIGS. 3 and 9
  • the present application also provides a system, which includes the aforementioned one or more first devices and one or second device.
  • the first device may be a terminal device, and the second device may be a network device; or, the first device may be a network device, and the second device may be a terminal device.
  • the network equipment in the above-mentioned device embodiments completely corresponds to the network equipment or terminal equipment in the terminal equipment and method embodiments, and the corresponding modules or units execute the corresponding steps.
  • the communication unit transmits the receiving or receiving in the method embodiment.
  • the processing unit processor
  • the functions of specific units refer to the corresponding method embodiments. Among them, there may be one or more processors.
  • component used in this specification are used to denote computer-related entities, hardware, firmware, a combination of hardware and software, software, or software in execution.
  • the component may be, but is not limited to, a process, a processor, an object, an executable file, a thread of execution, a program, and/or a computer running on a processor.
  • the application running on the computing device and the computing device can be components.
  • One or more components may reside in processes and/or threads of execution, and components may be located on one computer and/or distributed between two or more computers.
  • these components can be executed from various computer readable media having various data structures stored thereon.
  • a component may be based on a signal having one or more data packets (for example, data from two components that interact with another component in a local system, a distributed system, and/or a network, such as the Internet that interacts with other systems through a signal) Communicate through local and/or remote processes.
  • data packets for example, data from two components that interact with another component in a local system, a distributed system, and/or a network, such as the Internet that interacts with other systems through a signal
  • the disclosed system, device, and method can be implemented in other ways.
  • the device embodiments described above are merely illustrative, for example, the division of the units is only a logical function division, and there may be other divisions in actual implementation, for example, multiple units or components can be combined or It can be integrated into another system, or some features can be ignored or not implemented.
  • the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may be in electrical, mechanical or other forms.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments.
  • the functional units in the various embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit.
  • each functional unit may be implemented in whole or in part by software, hardware, firmware, or any combination thereof.
  • software When implemented by software, it can be implemented in the form of a computer program product in whole or in part.
  • the computer program product includes one or more computer instructions (programs).
  • programs When the computer program instructions (programs) are loaded and executed on the computer, the processes or functions described in the embodiments of the present application are generated in whole or in part.
  • the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.
  • the computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium.
  • the computer instructions may be transmitted from a website, computer, server, or data center. Transmission to another website, computer, server, or data center via wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.).
  • the computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or a data center integrated with one or more available media.
  • the usable medium may be a magnetic medium (for example, a floppy disk, a hard disk, and a magnetic tape), an optical medium (for example, a high-density digital video disc (digital video disc, DVD)), or a semiconductor medium (for example, a solid state disk, SSD)) etc.
  • a magnetic medium for example, a floppy disk, a hard disk, and a magnetic tape
  • an optical medium for example, a high-density digital video disc (digital video disc, DVD)
  • a semiconductor medium for example, a solid state disk, SSD
  • the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium.
  • the technical solution of this application essentially or the part that contributes to the existing technology or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including Several instructions are used to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in the various embodiments of the present application.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (read-only memory, ROM), random access memory (random access memory, RAM), magnetic disk or optical disk and other media that can store program code .

Landscapes

  • Engineering & Computer Science (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Power Engineering (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Databases & Information Systems (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

本申请提供了一种获取信道信息的方法及通信装置。该方法包括:第一设备向第二设备发送第一参考信号,该第一参考信号的密度小于或等于第二参考信号的密度,该第二参考信号是常规密度参考信号;该第一设备接收来自该第二设备的第一信道状态信息CSI;该第一设备基于该第一CSI和第一神经网络模型获得第二CSI,该第二CSI用于指示该第一设备与该第二设备之间的信道信息。通过在第一设备侧部署第一神经网络模型的方式,可以减小第一设备的发送开销和/或第二设备的反馈开销。

Description

获取信道信息的方法及通信装置
本申请要求于2020年06月03日提交中国国家知识产权局、申请号为202010493592.0、申请名称为“获取信道信息的方法及通信装置”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
技术领域
本申请涉及通信领域,并且更具体地,涉及获取信道信息的方法及通信装置。
背景技术
在大规模多输入多输出(massive multiple-input multiple-output,Massive MIMO)技术中,网络设备可以通过预编码技术减小多终端设备之间的干扰以及同一终端设备的多个信号流之间的干扰。从而提高信号质量,实现空分复用,提高频谱利用率。
终端设备例如可以通过信道测量等方式确定与下行信道相适配的预编码矩阵,并希望通过反馈,使得网络设备获得与终端设备所确定的预编码向量相同或相近的预编码矩阵;或者网络设备例如可以通过信道测量等方式确定与上行信道相适配的预编码矩阵,并希望通过反馈,使得终端设备获得与网络设备所确定的预编码向量相同或相近的预编码矩阵。
通常在无线通信系统中,通过在无线传输资源上放置收发两端都已知的参考信号进行信道估计。然而为了获得准确的信道信息,发送端需要占据较大的资源用于传输参考信号,因此发送开销较大。在此基础上,接收端的反馈开销也较大。
发明内容
本申请提供一种获取信道信息的方法,以期减少发送端发送参考信号的开销和/或减小接收端的反馈开销。
第一方面,提供了一种获取信道信息的方法,该方法可以包括:第一设备向第二设备发送第一参考信号,该第一参考信号的密度小于或等于第二参考信号的密度,该第二参考信号是常规密度参考信号;该第一设备接收来自该第二设备的第一信道状态信息(channel state information,CSI);在该第一参考信号的密度小于该第二参考信号的密度的情况下,该第一CSI是该第二设备根据该第一参考信号获得的;或者,在该第一参考信号的密度等于该第二参考信号的密度的情况下,该第一CSI是该第二设备根据该第一参考信号的一部分获得的;该第一设备基于该第一CSI和第一神经网络模型获得第二CSI,该第二CSI用于指示该第一设备与该第二设备之间的信道信息。
需要说明的是,常规密度指的是目前协议中定义的参考信号的密度,参考信号的密度指的是用于传输参考信号的资源占总的传输资源的比例。例如,目前新空口(new radio,NR)协议中定义的用于传输32端口的信道状态信息参考信号(channel state information reference signal,CSI-RS)的资源大约占总的传输资源的20%,因此可以说,32端口的 CSI-RS的常规密度是20%。
基于上述技术方案,通过在第一设备侧部署第一神经网络模型的方式,使得第一设备可以基于部分信道信息(第一CSI)和第一神经网络模型恢复出全部信道信息(第二CSI)。因此,在第一设备侧部署了第一神经网络模型的情况下,第二设备可以仅向第一设备反馈部分信道信息(第一CSI),从而可以减小第二设备的反馈开销。
此外,在第一设备部署了第一神经网络模型的情况下,第一设备可以向第二设备发送低密度的参考信号,从而可以减小第二设备的发送参考信号的开销。
可选地,在该第一参考信号的密度小于该第二参考信号的密度的情况下,该第一参考信号的密度可以是该第二参考信号的密度的1/2或1/4。
可选地,在第一设备是网络设备,第二设备是终端设备的情况下,第二参考信号和第一参考信号可以是CSI-RS,或者是解调参考信号(demodulation reference signal,DMRS)。
可选地,在第一设备是终端设备,第二设备是网络设备的情况下,第二参考信号和第一参考信号可以是信道探测参考信号(sounding reference signal,SRS),或者是DMRS。
结合第一方面,在第一方面的某些实现方式中,在该第一设备向第二设备发送第一参考信号之前,该方法还包括:该第一设备确定该第一神经网络模型。
在一种实现方式中,该第一设备确定该第一神经网络模型,具体可以包括:该第一设备向该第二设备发送该第二参考信号;该第一设备接收来自该第二设备的第三CSI,该第三CSI是该第二设备根据该第二参考信号获得的;该第一设备基于该第三CSI训练神经网络以获得该第一神经网络模型。
结合第一方面,在第一方面的某些实现方式中,该方法还包括:在达到预设触发条件时,该第一设备对该第一神经网络模型进行更新。
在一种实现方式中,该第一设备对该第一神经网络模型进行更新,具体可以包括:该第一设备向该第二设备发送该第三参考信号,该第三参考信号是常规密度参考信号;该第一设备接收来自该第二设备的第四CSI,该第四CSI是该第二设备根据该第三参考信号获得的;该第一设备基于该第四CSI训练神经网络以获得更新后的第一神经网络模型。
可选地,该预设触发条件可以是第一定时器超时,该第一定时器是在该第一设备向该第二设备发送该第一参考信号时启动的。
可选地,该预设触发条件可以是该第一设备确定该第二设备解调第一数据的解调性能低于预设门限,该第一数据是该第一设备根据该第二CSI发送的。
可选地,该预设触发条件可以是该第一设备接收到来自该第二设备的第一请求消息,该第一请求消息用于请求更新该第一神经网络模型。
结合第一方面,在第一方面的某些实现方式中,在该第一设备向该第二设备发送第一参考信号之前,该方法还包括:该第一设备接收来自该第二设备的第二请求消息,该第二请求消息用于请求该第一参考信号,该第二请求消息还用于指示该第一参考信号的密度。
可选地,在该第一设备是网络设备的情况下,该第二请求消息可以携带在上行控制信息(uplink control information,UCI)中。
可选地,在该第一设备是终端设备的情况下,该第二请求消息可以携带在下行控制信息(downlink control information,DCI)中。
结合第一方面,在第一方面的某些实现方式中,在该第一设备向该第二设备发送第一 参考信号之前,该方法还包括:该第一设备在确定该第一神经网络训练模型的情况下,向该第二设备发送第一指示信息,该第一指示信息用于指示该第一参考信号的密度。
可选地,在该第一设备是网络设备的情况下,该第一指示信息可以携带在DCI中。
可选地,在该第一设备是终端设备的情况下,该第一指示信息可以携带在UCI中。
结合第一方面,在第一方面的某些实现方式中,在该第一设备是网络设备的情况下,该方法还包括:该第一设备向该第二设备发送无线资源控制(radio resource control,RRC)消息,该RRC消息中包括该第一参考信号的密度配置信息。
结合第一方面,在第一方面的某些实现方式中,在该第一设备是终端设备的情况下,该方法还包括:该第一设备接收来自该第二设备的RRC消息,该RRC消息中包括该第一参考信号的密度配置信息。
第二方面,提供了一种获取信道信息的方法,该方法可以包括:第二设备接收来自第一设备的第一参考信号,该第一参考信号的密度小于或等于第二参考信号的密度,该第二参考信号是常规密度参考信号;该第二设备向该第一设备发送第一CSI,该第一CSI用通过第一神经网络模型获得第二CSI,该第二CSI用于指示该第一设备与该第二设备之间的信道信息;其中,在该第一参考信号的密度小于该第二参考信号的密度的情况下,该第一CSI是该第二设备根据该第一参考信号获得的;或者,在该第一参考信号的密度等于该第二参考信号的密度的情况下,该第一CSI是该第二设备根据该第一参考信号的一部分获得的。
需要说明的是,常规密度指的是目前协议中定义的参考信号的密度,参考信号的密度指的是用于传输参考信号的资源占总的传输资源的比例。例如,目前协议中定义的用于传输32端口的CSI-RS的资源大约占总的传输资源的20%,因此可以说,32端口的CSI-RS的常规密度是20%。
基于上述技术方案,通过在第一设备侧部署第一神经网络模型的方式,使得第一设备可以基于部分信道信息(第一CSI)和第一神经网络模型恢复出全部信道信息(第二CSI)。因此,在第一设备部署了第一神经网络模型的情况下,第二设备可以仅向第一设备反馈部分信道信息(第一CSI),从而可以减小第二设备的反馈开销。
此外,在第一设备部署了第一神经网络模型的情况下,第一设备可以向第二设备发送低密度的参考信号,从而可以减小第二设备的发送参考信号的开销。
可选地,在该第一参考信号的密度小于该第二参考信号的密度的情况下,该第一参考信号的密度可以是该第二参考信号的密度的1/2或1/4。
可选地,在第一设备是网络设备,第二设备是终端设备的情况下,第二参考信号和第一参考信号可以是CSI-RS,或者是DMRS。
可选地,在第一设备是终端设备,第二设备是网络设备的情况下,第二参考信号和第一参考信号可以是SRS,或者是DMRS。
结合第二方面,在第二方面的某些实现方式中,在该第二设备接收来自第一设备的第一参考信号之前,该方法还包括:该第二设备接收来自该第一设备的该第二参考信号;该第二设备向该第一设备发送第三CSI,该第三CSI是根据该第二参考信号获得的,该第三CSI用于训练神经网络以获得该第一神经网络模型。
结合第二方面,在第二方面的某些实现方式中,该方法还包括:该第二设备接收来自 该第一设备的该第三参考信号,该第三参考信号是常规密度参考信号;该第二设备向该第一设备发送第四CSI,该第四CSI是根据该第三参考信号获得的,该第四CSI用于训练神经网络以获得更新后的第一神经网络模型。
结合第二方面,在第二方面的某些实现方式中,在该第二设备接收来自该第一设备的第一参考信号之前,该方法还包括:该第二设备向该第一设备发送第二请求消息,该第二请求消息用于请求该第一参考信号,该第二请求消息还用于指示该第一参考信号的密度。
可选地,在该第二设备是终端设备的情况下,该第二请求消息可以携带UCI中。
可选地,在该第二设备是网络设备的情况下,该第二请求消息可以携带在DCI中。
可选地,该第二设备周期性地向该第一设备发送第二请求消息;或者
该第二设备在接收到来自第一设备的第二指示信息的情况下,向该第一设备发送该第二请求消息,该第二指示信息用于指示已确定该第一神经网络模型。
结合第二方面,在第二方面的某些实现方式中,在该第二设备接收来自该第一设备的第一参考信号之前,该方法还包括:该第二设备接收来自该第一设备的第一指示信息,该第一指示信息用于指示该第一参考信号的密度。
可选地,在该第二设备是终端设备的情况下,该第一指示信息可以携带在DCI中。
可选地,在该第二设备是网络设备的情况下,该第一指示信息可以携带在UCI中。
结合第二方面,在第二方面的某些实现方式中,在该第二设备是终端设备的情况下,该方法还包括:该第二设备接收来自该第一设备的RRC消息,该RRC消息中包括该第一参考信号的密度配置信息。
结合第二方面,在第二方面的某些实现方式中,在该第二设备是网络设备的情况下,该方法还包括:该第二设备向该第一设备发送RRC消息,该RRC消息中包括该第一参考信号的密度配置信息。
第三方面,提供了一种获取信道信息的方法,该方法可以包括:第二设备接收来自第一设备的第一参考信号,该第一参考信号的密度小于第二参考信号的密度,该第二参考信号是常规密度参考信号;该第二设备根据第一CSI和第二神经网络模型获得第二CSI,该第二CSI用于指示该第一设备与该第二设备之间的信道信息,该第一CSI是根据该第一参考信号获得的;该第二设备向该第一设备发送该第二CSI。
需要说明的是,常规密度指的是目前协议中定义的参考信号的密度,参考信号的密度指的是用于传输参考信号的资源占总的传输资源的比例。例如,目前协议中定义的用于传输32端口的CSI-RS的资源大约占总的传输资源的20%,因此可以说,32端口的CSI-RS的常规密度是20%。
基于上述技术方案,通过在第二设备侧部署第二神经网络模型的方式,使得第二设备可以基于部分信道信息(第一CSI)和第二神经网络模型恢复出全部信道信息(第二CSI)。因此,在第二设备部署了第一神经网络模型的情况下,第一设备可以向第二设备发送低密度的参考信号,从而可以减小发送参考信号的开销。
可选地,该第一参考信号的密度是该第二参考信号的密度的1/2或1/4。
可选地,在第一设备是网络设备,第二设备是终端设备的情况下,第二参考信号和第一参考信号可以是CSI-RS,或者是DMRS。
可选地,在第一设备是终端设备,第二设备是网络设备的情况下,第二参考信号和第 一参考信号可以是SRS,或者是DMRS。
结合第三方面,在第三方面的某些实现方式中,在该第二设备接收来自第一设备的第一参考信号之前,该方法还包括:该第二设备确定第二神经网络模型。
在一种实现方式中,该第二设备确定第二神经网络模型,具体可以包括:该第二设备接收来自该第一设备的该第二参考信号;该第二设备基于第三CSI对神经网络进行训练以获得该第二神经网络模型,该第三CSI是根据该第二参考信号获得的。
结合第三方面,在第三方面的某些实现方式中,该方法还包括:在达到预设触发条件时,该第二设备对该第二神经网络模型进行更新。
在一种实现方式中,该第二设备对该第二神经网络模型进行更新,具体可以包括:该第二设备接收来自该第一设备的该第三参考信号;该第二设备基于第四CSI对神经网络进行训练以获得更新后的第二神经网络模型,该第四CSI是根据该第三参考信号获得的。
可选地,该预设触发条件可以是第二定时器超时,该第二定时器是在该第二设备接收到来自该第一设备的该第一参考信号时启动的。
可选地,该预设触发条件可以是该第二设备确定解调第一数据的解调性能低于预设门限,该第一数据是该第一设备根据该第二CSI发送的。
结合第三方面,在第三方面的某些实现方式中,在该第二设备接收来自该第一设备的第一参考信号之前,该方法还包括:该第二设备在该神经网络训练完成的情况下,向该第一设备发送第二请求消息,该第二请求消息用于请求该第一参考信号,该第二请求消息还用于指示该第一参考信号的密度。
可选地,在该第二设备是终端设备的情况下,该第二请求消息可以携带在UCI中。
可选地,在该第二设备是网络设备的情况下,该第二请求消息可以携带在DCI中。
结合第三方面,在第三方面的某些实现方式中,在该第二设备接收来自该第一设备的第一参考信号之前,该方法还包括:该第二设备接收来自该第一设备的第一指示信息,该第一指示信息用于指示该第一参考信号的密度。
可选地,在该第二设备是终端设备的情况下,该第一指示信息可以携带在DCI中。
可选地,在该第二设备是网络设备的情况下,该第一指示信息可以携带在UCI中。
结合第三方面,在第三方面的某些实现方式中,在该第二设备是终端设备的情况下,该方法还包括:该第二设备接收来自该第一设备的无线资源控制RRC消息,该RRC消息中包括该第一参考信号的密度配置信息。
结合第三方面,在第三方面的某些实现方式中,在该第二设备是网络设备的情况下,该方法还包括:该第二设备向该第一设备发送RRC消息,该RRC消息中包括该第一参考信号的密度配置信息。
第四方面,提供了一种获取信道信息的方法,该方法可以包括:第一设备向第二设备发送第一参考信号,该第一参考信号的密度小于第二参考信号的密度,该第二参考信号是常规密度参考信号,该第一参考信号用于获得第一CSI,该第一CSI用于通过第二神经网络模型获得第二CSI,该第二CSI用于指示该第一设备与该第二设备之间的信道信息;该第一设备接收来自该第二设备的第二CSI。
需要说明的是,常规密度指的是目前协议中定义的参考信号的密度,参考信号的密度指的是用于传输参考信号的资源占总的传输资源的比例。例如,目前协议中定义的用于传 输32端口的CSI-RS的资源大约占总的传输资源的20%,因此可以说,32端口的CSI-RS的常规密度是20%。
基于上述技术方案,通过在第二设备侧部署第二神经网络模型的方式,使得第二设备可以基于部分信道信息(第一CSI)和第二神经网络模型恢复出全部信道信息(第二CSI)。因此,在第二设备部署第一神经网络模型的情况下,第一设备可以向第二设备发送低密度的参考信号,从而可以减小发送参考信号的开销。
可选地,该第一参考信号的密度是该第二参考信号的密度的1/2或1/4。
可选地,在第一设备是网络设备,第二设备是终端设备的情况下,第二参考信号和第一参考信号可以是CSI-RS,或者是DMRS。
可选地,在第一设备是终端设备,第二设备是网络设备的情况下,第二参考信号和第一参考信号可以是SRS,或者是DMRS。
结合第四方面,在第四方面的某些实现方式中,在该第一设备向该第二设备发送第一参考信号之前,该方法还包括:该第一设备向该第二设备发送该第二参考信号,该第二参考信号用于获得第三CSI,该第三CSI用于训练神经网络以获得该第二神经网络模型。
结合第四方面,在第四方面的某些实现方式中,该方法还包括:该第一设备向该第二设备发送第三参考信号,该第三参考信号用于获得第四CSI,该第四CSI用于训练神经网络以获得更新后的第二神经网络模型。
结合第四方面,在第四方面的某些实现方式中,在该第一设备向该第二设备发送第一参考信号之前,该方法还包括:该第一设备接收来自该第二设备的第二请求消息,该第二请求消息用于请求该第一参考信号,该第二请求消息还用于指示该第一参考信号的密度。
可选地,在该第一设备是网络设备的情况下,该第二请求消息可以携带在UCI中。
可选地,在该第一设备是终端设备的情况下,该第二请求消息可以携带在DCI中。
结合第四方面,在第四方面的某些实现方式中,在该第一设备向该第二设备发送第一参考信号之前,该方法还包括:该第一设备向该第二设备发送第一指示信息,该第一指示信息用于指示该第一参考信号的密度。
可选地,在该第一设备是网络设备的情况下,该第一指示信息可以携带在DCI中。
可选地,在该第一设备是终端设备的情况下,该第一指示信息可以携带在UCI中。
可选地,该第一设备可以周期性地向该第二设备发送该第一指示信息;或者
该第一设备可以在接收到来自该第二设备的第三指示信息的情况下,向该第二设备发送该第一指示信息,该第三指示信息用于指示已确定该第二神经网络模型。
结合第四方面,在第四方面的某些实现方式中,在该第一设备是网络设备的情况下,该方法还包括:该第一设备向该第二设备发送无线资源控制RRC消息,该RRC消息中包括该第一参考信号的密度配置信息。
结合第四方面,在第四方面的某些实现方式中,在该第一设备是终端设备的情况下,该方法还包括:该第一设备接收来自该第二设备的RRC消息,该RRC消息中包括该第一参考信号的密度的配置信息。
第五方面,提供了一种通信装置,包括用于执行第一方面以及第一方面中任一种可能实现方式中的方法的各个模块或单元。
第六方面,提供了一种通信装置,包括用于执行第二方面以及第二方面中任一种可能 实现方式中的方法的各个模块或单元。
第七方面,提供了一种通信装置,包括收发单元和处理单元:该收发单元用于接收来自第一设备的第一参考信号,该第一参考信号的密度小于第二参考信号的密度,该第二参考信号是常规密度参考信号;该处理单元用于根据第一CSI和第二神经网络模型获得第二CSI,该第二CSI用于指示该第一设备与该第二设备之间的信道信息,该第一CSI是根据该第一参考信号获得的;该收发单元还用于向该第一设备发送该第二CSI。
可选地,该第一参考信号的密度是该第二参考信号的密度的1/2或1/4。
结合第七方面,在第七方面的某些实现方式中,该收发单元还用于接收来自该第一设备的该第二参考信号;该处理单元还用于基于第三CSI对神经网络进行训练以获得该第二神经网络模型,该第三CSI是根据该第二参考信号获得的。
结合第七方面,在第七方面的某些实现方式中,该收发单元还用于接收来自该第一设备的该第三参考信号;该处理单元还用于基于第四CSI对神经网络进行训练以获得更新后的第二神经网络模型,该第四CSI是根据该第三参考信号获得的。
结合第七方面,在第七方面的某些实现方式中,该收发单元还用于在该神经网络训练完成的情况下,向该第一设备发送第二请求消息,该第二请求消息用于请求该第一参考信号,该第二请求消息还用于指示该第一参考信号的密度。
可选地,在该通信装置是终端设备的情况下,该第二请求消息可以携带在UCI中。
可选地,在该通信装置是网络设备的情况下,该第二请求消息可以携带在DCI中。
结合第七方面,在第七方面的某些实现方式中,该收发单元还用于接收来自该第一设备的第一指示信息,该第一指示信息用于指示该第一参考信号的密度。
可选地,在该通信装置是终端设备的情况下,该第一指示信息可以携带在DCI中。
可选地,在该通信装置是网络设备的情况下,该第一指示信息可以携带在UCI中。
结合第七方面,在第七方面的某些实现方式中,在该通信装置是终端设备的情况下,该收发单元还用于接收来自该第一设备的RRC消息,该RRC消息中包括该第一参考信号的密度配置信息。
结合第七方面,在第七方面的某些实现方式中,在该通信装置是网络设备的情况下,该收发单元还用于向该第一设备发送RRC消息,该RRC消息中包括该第一参考信号的密度配置信息。
第八方面,提供了一种通信装置,包括收发单元:该收发单元用于向第二设备发送第一参考信号,该第一参考信号的密度小于第二参考信号的密度,该第二参考信号是常规密度参考信号,该第一参考信号用于获得第一CSI,该第一CSI用于通过第二神经网络模型获得第二CSI,该第二CSI用于指示该第一设备与该第二设备之间的信道信息;该第一设备接收来自该第二设备的第二CSI。
可选地,该第一参考信号的密度是该第二参考信号的密度的1/2或1/4。
结合第八方面,在第八方面的某些实现方式中,该收发单元还用于向该第二设备发送该第二参考信号,该第二参考信号用于获得第三CSI,该第三CSI用于训练神经网络以获得该第二神经网络模型。
结合第八方面,在第八方面的某些实现方式中,该收发单元还用于向该第二设备发送第三参考信号,该第三参考信号用于获得第四CSI,该第四CSI用于训练神经网络以获得 更新后的第二神经网络模型。
结合第八方面,在第八方面的某些实现方式中,该收发单元还用于接收来自该第二设备的第二请求消息,该第二请求消息用于请求该第一参考信号,该第二请求消息还用于指示该第一参考信号的密度。
可选地,在该通信装置是网络设备的情况下,该第二请求消息可以携带在UCI中。
可选地,在该通信装置是终端设备的情况下,该第二请求消息可以携带在DCI中。
结合第八方面,在第八方面的某些实现方式中,该收发单元还用于向该第二设备发送第一指示信息,该第一指示信息用于指示该第一参考信号的密度。
可选地,在该通信装置是网络设备的情况下,该第一指示信息可以携带在DCI中。
可选地,在该通信装置是终端设备的情况下,该第一指示信息可以携带在UCI中。
可选地,该收发单元可以周期性地向该第二设备发送该第一指示信息;或者
该收发单元可以在接收到来自该第二设备的第三指示信息的情况下,向该第二设备发送该第一指示信息,该第三指示信息用于指示已确定该第二神经网络模型。
结合第八方面,在第八方面的某些实现方式中,在该通信装置是网络设备的情况下,该收发单元还用于向该第二设备发送无线资源控制RRC消息,该RRC消息中包括该第一参考信号的密度配置信息。
结合第八方面,在第八方面的某些实现方式中,在该通信装置是终端设备的情况下,该收发单元还用于接收来自该第二设备的RRC消息,该RRC消息中包括该第一参考信号的密度的配置信息。
第九方面,提供了一种通信装置,包括处理器。该处理器与存储器耦合,可用于执行存储器中的指令,以实现上述第一方面及第四方面中任一种可能实现方式中的方法。可选地,该通信装置还包括存储器。可选地,该通信装置还包括通信接口,处理器与通信接口耦合。
在一种实现方式中,该通信装置为第一设备。当该通信装置为第一设备时,该通信接口可以是收发器,或,输入/输出接口。
在另一种实现方式中,该通信装置为配置于第一设备中的芯片。当该通信装置为配置于第一设备中的芯片时,该通信接口可以是输入/输出接口。
可选地,该收发器可以为收发电路。可选地,该输入/输出接口可以为输入/输出电路。
第十方面,提供了一种通信装置,包括处理器。该处理器与存储器耦合,可用于执行存储器中的指令,以实现上述第二方面及第三方面中任一种可能实现方式中的方法。可选地,该通信装置还包括存储器。可选地,该通信装置还包括通信接口,处理器与通信接口耦合。
在一种实现方式中,该通信装置为第二设备。当该通信装置为第二设备时,该通信接口可以是收发器,或,输入/输出接口。
在另一种实现方式中,该通信装置为配置于第二设备中的芯片。当该通信装置为配置于第二设备中的芯片时,该通信接口可以是输入/输出接口。
可选地,该收发器可以为收发电路。可选地,该输入/输出接口可以为输入/输出电路。
第十一方面,提供了一种处理器,包括:输入电路、输出电路和处理电路。所述处理电路用于通过所述输入电路接收信号,并通过所述输出电路发射信号,使得所述处理器执 行第一方面至第四方面中任一种可能实现方式中的方法。
在具体实现过程中,上述处理器可以为一个或多个芯片,输入电路可以为输入管脚,输出电路可以为输出管脚,处理电路可以为晶体管、门电路、触发器和各种逻辑电路等。输入电路所接收的输入的信号可以是由例如但不限于接收器接收并输入的,输出电路所输出的信号可以是例如但不限于输出给发射器并由发射器发射的,且输入电路和输出电路可以是同一电路,该电路在不同的时刻分别用作输入电路和输出电路。本申请实施例对处理器及各种电路的具体实现方式不做限定。
第十二方面,提供了一种处理装置,包括处理器和存储器。该处理器用于读取存储器中存储的指令,并可通过接收器接收信号,通过发射器发射信号,以执行第一方面至第四方面中任一种可能实现方式中的方法。
可选地,所述处理器为一个或多个,所述存储器为一个或多个。
可选地,所述存储器可以与所述处理器集成在一起,或者所述存储器与处理器分离设置。
在具体实现过程中,存储器可以为非瞬时性(non-transitory)存储器,例如只读存储器(read only memory,ROM),其可以与处理器集成在同一块芯片上,也可以分别设置在不同的芯片上,本申请实施例对存储器的类型以及存储器与处理器的设置方式不做限定。
应理解,相关的数据交互过程例如发送指示信息可以为从处理器输出指示信息的过程,接收能力信息可以为处理器接收输入能力信息的过程。具体地,处理器输出的数据可以输出给发射器,处理器接收的输入数据可以来自接收器。其中,发射器和接收器可以统称为收发器。
上述第十二方面中的处理装置可以是一个或多个芯片。该处理装置中的处理器可以通过硬件来实现也可以通过软件来实现。当通过硬件实现时,该处理器可以是逻辑电路、集成电路等;当通过软件来实现时,该处理器可以是一个通用处理器,通过读取存储器中存储的软件代码来实现,该存储器可以集成在处理器中,可以位于该处理器之外,独立存在。
第十三方面,提供了一种计算机程序产品,所述计算机程序产品包括:计算机程序(也可以称为代码,或指令),当所述计算机程序被运行时,使得计算机执行上述第一方面至第四方面中任一种可能实现方式中的方法。
第十四方面,提供了一种计算机可读介质,所述计算机可读介质存储有计算机程序(也可以称为代码,或指令)当其在计算机上运行时,使得上述第一方面至第四方面中任一种可能实现方式中的方法被执行。
第十五方面,提供了一种通信系统,包括前述的第一设备和第二设备。
附图说明
图1示出了适用于本申请实施例的适用的通信系统的示意图。
图2示出了32端口的CSI-RS在无线传输资源上的放置位置的示意图。
图3示出了本申请实施例提供的获取信道信息的方法的示意性流程图。
图4示出了本申请实施例提供的训练神经网络的方法的示意图。
图5至图8示出了本申请实施例提供的低密度CSI-RS在无线传输资源上的放置位置 的示意图。
图9至图11示出了本申请实施例提供的获取信道信息的方法的示意性流程图。
图12示出了本申请实施例提供的通信装置的示意性框图。
图13示出了本申请另一实施例提供的通信装置的示意性结构图。
图14示出了本申请实施例提供的终端设备的示意性结构图。
图15示出了本申请实施例提供的装置的示意性结构图。
具体实施方式
下面将结合附图,对本申请中的技术方案进行描述。
本申请实施例的技术方案可以应用于各种通信系统,例如:长期演进(Long Term Evolution,LTE)系统、LTE频分双工(frequency division duplex,FDD)系统、LTE时分双工(time division duplex,TDD)、通用移动通信系统(universal mobile telecommunication system,UMTS)、全球互联微波接入(worldwide interoperability for microwave access,WiMAX)通信系统、第五代(5th Generation,5G)移动通信系统或新无线接入技术(new radio access Technology,NR)。其中,5G移动通信系统可以包括非独立组网(non-standalone,NSA)和/或独立组网(standalone,SA)。
本申请提供的技术方案还可以应用于机器类通信(machine type communication,MTC)、机器间通信长期演进技术(Long Term Evolution-machine,LTE-M)、设备到设备(device to device,D2D)网络、机器到机器(machine to machine,M2M)网络、物联网(internet of things,IoT)网络或者其他网络。其中,IoT网络例如可以包括车联网。其中,车联网系统中的通信方式统称为车到其他设备(vehicle to X,V2X,X可以代表任何事物),例如,该V2X可以包括:车辆到车辆(vehicle to vehicle,V2V)通信,车辆与基础设施(vehicle to infrastructure,V2I)通信、车辆与行人之间的通信(vehicle to pedestrian,V2P)或车辆与网络(vehicle to network,V2N)通信等。
本申请提供的技术方案还可以应用于其他通信系统,如第六代(6th Generation,6G)移动通信系统等。本申请对此不作限定。
本申请实施例中,网络设备可以是任意一种具有无线收发功能的设备。该设备包括但不限于:演进型节点B(evolved Node B,eNB)、无线网络控制器(radio network controller,RNC)、节点B(Node B,NB)、基站控制器(base station controller,BSC)、基站收发台(base transceiver station,BTS)、家庭基站(例如,home evolved NodeB,或home Node B,HNB)、基带单元(baseband unit,BBU),无线保真(wireless fidelity,WiFi)系统中的接入点(access point,AP)、无线中继节点、无线回传节点、传输点(transmission point,TP)或者发送接收点(transmission and reception point,TRP)等,还可以为5G,如,NR,系统中的gNB,或,传输点(TRP或TP),5G系统中的基站的一个或一组(包括多个天线面板)天线面板,或者,还可以为构成gNB或传输点的网络节点,如基带单元(BBU),或,分布式单元(distributed unit,DU)等,或者6G通信系统中的基站等。
在一些部署中,gNB可以包括集中式单元(centralized unit,CU)和DU。gNB还可以包括有源天线单元(active antenna unit,AAU)。CU实现gNB的部分功能,DU实现gNB的部分功能,比如,CU负责处理非实时协议和服务,实现无线资源控制(radio resource  control,RRC),分组数据汇聚层协议(packet data convergence protocol,PDCP)层的功能。DU负责处理物理层协议和实时服务,实现无线链路控制(radio link control,RLC)层、介质接入控制(medium access control,MAC)层和物理(physical,PHY)层的功能。AAU实现部分物理层处理功能、射频处理及有源天线的相关功能。由于RRC层的信息最终会变成PHY层的信息,或者,由PHY层的信息转变而来,因而,在这种架构下,高层信令,如RRC层信令,也可以认为是由DU发送的,或者,由DU和AAU发送的。可以理解的是,网络设备可以为包括CU节点、DU节点、AAU节点中一项或多项的设备。此外,可以将CU划分为接入网(radio access network,RAN)中的网络设备,也可以将CU划分为核心网(core network,CN)中的网络设备,本申请对此不做限定。
网络设备为小区提供服务,终端设备通过网络设备分配的传输资源(例如,频域资源,或者说,频谱资源)与小区进行通信,该小区可以属于宏基站(例如,宏eNB或宏gNB等),也可以属于小小区(small cell)对应的基站,这里的小小区可以包括:城市小区(metro cell)、微小区(micro cell)、微微小区(pico cell)、毫微微小区(femto cell)等,这些小小区具有覆盖范围小、发射功率低的特点,适用于提供高速率的数据传输服务。
在本申请实施例中,终端设备也可以称为用户设备(user equipment,UE)、接入终端、用户单元、用户站、移动站、移动台、远方站、远程终端、移动设备、用户终端、终端、无线通信设备、用户代理或用户装置。
终端设备可以是一种向用户提供语音/数据连通性的设备,例如,具有无线连接功能的手持式设备、车载设备等。目前,一些终端的举例可以为:手机(mobile phone)、平板电脑(pad)、带无线收发功能的电脑(如笔记本电脑、掌上电脑等)、移动互联网设备(mobile internet device,MID)、虚拟现实(virtual reality,VR)设备、增强现实(augmented reality,AR)设备、工业控制(industrial control)中的无线终端、无人驾驶(self driving)中的无线终端、远程医疗(remote medical)中的无线终端、智能电网(smart grid)中的无线终端、运输安全(transportation safety)中的无线终端、智慧城市(smart city)中的无线终端、智慧家庭(smart home)中的无线终端、蜂窝电话、无绳电话、会话启动协议(session initiation protocol,SIP)电话、无线本地环路(wireless local loop,WLL)站、个人数字助理(personal digital assistant,PDA)、具有无线通信功能的手持设备、计算设备或连接到无线调制解调器的其它处理设备、车载设备、可穿戴设备,5G网络中的终端设备或者未来演进的公用陆地移动通信网络(public land mobile network,PLMN)中的终端设备等。
其中,可穿戴设备也可以称为穿戴式智能设备,是应用穿戴式技术对日常穿戴进行智能化设计、开发出可以穿戴的设备的总称,如眼镜、手套、手表、服饰及鞋等。可穿戴设备即直接穿在身上,或是整合到用户的衣服或配件的一种便携式设备。可穿戴设备不仅仅是一种硬件设备,更是通过软件支持以及数据交互、云端交互来实现强大的功能。广义穿戴式智能设备包括功能全、尺寸大、可不依赖智能手机实现完整或者部分的功能,例如:智能手表或智能眼镜等,以及只专注于某一类应用功能,需要和其它设备如智能手机配合使用,如各类进行体征监测的智能手环、智能首饰等。
此外,终端设备还可以是物联网(internet of things,IoT)系统中的终端设备。IoT是未来信息技术发展的重要组成部分,其主要技术特点是将物品通过通信技术与网络连接,从而实现人机互连,物物互连的智能化网络。IoT技术可以通过例如窄带(narrow band, NB)技术,做到海量连接,深度覆盖,终端省电。
此外,终端设备还可以包括智能打印机、火车探测器、加油站等传感器,主要功能包括收集数据(部分终端设备)、接收网络设备的控制信息与下行数据,并发送电磁波,向网络设备传输上行数据。
为便于理解本申请实施例,首先结合图1详细说明适用于本申请实施例提供的方法的通信系统。图1示出了适用于本申请实施例提供的方法的通信系统100的示意图。如图所示,该通信系统100可以包括至少一个网络设备,如图1中所示的5G系统中的网络设备101;该通信系统100还可以包括至少一个终端设备,如图1中所示的终端设备102至107。其中,该终端设备102至107可以是移动的或固定的。网络设备101和终端设备102至107中的一个或多个均可以通过无线链路通信。每个网络设备可以为特定的地理区域提供通信覆盖,并且可以与位于该覆盖区域内的终端设备通信。例如,网络设备可以向终端设备发送配置信息,终端设备可以基于该配置信息向网络设备发送上行数据;又例如,网络设备可以向终端设备发送下行数据。因此,图1中的网络设备101和终端设备102至107构成一个通信系统。
可选地,终端设备之间可以直接通信。例如可以利用D2D技术等实现终端设备之间的直接通信。如图中所示,终端设备105与106之间、终端设备105与107之间,可以利用D2D技术直接通信。终端设备106和终端设备107可以单独或同时与终端设备105通信。
终端设备105至107也可以分别与网络设备101通信。例如可以直接与网络设备101通信,如图中的终端设备105和106可以直接与网络设备101通信;也可以间接地与网络设备101通信,如图中的终端设备107经由终端设备106与网络设备101通信。
应理解,图1示例性地示出了一个网络设备和多个终端设备,以及各通信设备之间的通信链路。可选地,该通信系统100可以包括多个网络设备,并且每个网络设备的覆盖范围内可以包括其它数量的终端设备,例如更多或更少的终端设备。本申请对此不做限定。
上述各个通信设备,如图1中的网络设备101和终端设备102至107,可以配置多个天线。该多个天线可以包括至少一个用于发送信号的发射天线和至少一个用于接收信号的接收天线。另外,各通信设备还附加地包括发射机链和接收机链,本领域普通技术人员可以理解,它们均可包括与信号发送和接收相关的多个部件(例如处理器、调制器、复用器、解调器、解复用器或天线等)。因此,网络设备与终端设备之间可通过多天线技术通信。
可选地,该无线通信系统100还可以包括网络控制器、移动管理实体等其他网络实体,本申请实施例不限于此。
在无线通信系统中,通常使用MIMO技术增加系统容量,即在发送端和接收端同时使用多根天线。理论上,多天线的使用结合空分复用,能成倍增加系统容量,但是实际上由于多天线的使用,也带来了干扰增强的问题,因此往往需要对信号进行一定的处理以抑制干扰带来的影响。这种通过信号处理进行干扰抑制的方法可以在接收端实现,也可以在发送端实现。在发送端实现时,可以对待发送信号进行预处理,再经过MIMO信道发送,这种发送方式就是预编码。
为了识别MIMO信道矩阵H有用的通道,需要把多个通道转化成类似于单输入单输出(single input single output,SISO)系统的一对一模式,实现发送信号S1对应接收信号 R1,发送信号S2对应接收信号R2,……,也就是将多个MIMO交叉通道转换成多个平行的一对一信道。这个过程可以通过对H进行奇异值分解(singular value decomposition,SVD)实现,即H=U∑V T,其中U和V为正交矩阵,∑为对角矩阵,其非零元素(即对角线上的元素)即为信道矩阵H的奇异值,这些奇异值通常可以按照由大到小的顺序排列,上标“T”表示转置操作。如r=H*s+n,可以写成r=U∑V T*s+n,其中r为接收信号,s为发送信号,n为信道噪声。在待发送数据为x的情况下,可以使s=Vx。在接收端使用∑ -1U T对接收到的信号进行解码,则可以得到无干扰的多个一对一信道。在发送端的s=Vx即为预编码操作,V为预编码矩阵。
由上可知,要得到与MIMO信道匹配的预编码矩阵,需要已知MIMO信道,因此需要对MIMO信道进行估计。
通常在无线通信系统中,通过在无线传输资源上放置收发两端都已知的参考信号来进行信道估计。例如,图2中示出了NR系统中32端口CSI-RS的放置位置。从图中可以看出,CSI-RS需要占据将近20%的传输资源,开销较大。
有鉴于此,本申请实施例提供一种获取信道信息的方法,以期减小发送端发送参考信号的开销,或者减小接收端反馈CSI的反馈开销。
下面将结合附图详细说明本申请实施例提供的获取信道信息的方法。
应理解,下文仅为便于理解和说明,以终端设备与网络设备之间的交互为例详细说明本申请实施例提供的方法。但这不应对本申请提供的方法执行主体构成限定。例如,下文实施例示出的终端设备可以替换为配置于终端设备中的部件(如芯片或芯片系统等)。下文实施例示出的网络设备也可以替换为配置于网络设备中的部件(如芯片或芯片系统等)。
下文示出的实施例并未对本申请实施例提供的方法的执行主体的具体结构特别限定,只要能够通过运行记录有本申请实施例提供的方法的代码的程序,以根据本申请实施例提供的方法进行通信即可,例如,本申请实施例提供的方法的执行主体可以是终端设备或网络设备,或者,是终端设备或网络设备中能够调用程序并执行程序的功能模块。
下面结合图3至图11,详细说明本申请实施例提供的获取信道信息的方法。
图3是从设备交互的角度示出的本申请实施例提供的获取信道信息的方法300的示意性流程图。图3示出的方法300可以包括S310至S380。下面详细说明方法300中的各个步骤。
S310,参考信号资源配置。
具体地,在第一设备是网络设备,第二设备是终端设备的情况下,可以由第一设备向第二设备发送参考信号的配置信息,以为第二设备配置用于接收参考信号的资源。
在第一设备是终端设备,第二设备是网络设备的情况下,可以由第二设备向第一设备发送参考信号的配置信息,以为第一设备配置用于发送参考信号的资源。
其中,参考信号可以是:信道状态信息(channel state information reference signal,CSI-RS)、解调参考信号(demodulation reference signal,DMRS)、信道探测参考信号(sounding reference signal,SRS)等,参考信号的配置信息可以包括参考信号的密度配置信息等。
参考信号的配置信息可以承载在RRC消息中。下文以用于配置CSI-RS的密度的RRC消息为例说明申请实施例提供RRC消息格式。
用于配置CSI-RS的密度的RRC消息如下:
Figure PCTCN2021095488-appb-000001
根据本申请实施例提供的RRC消息格式,可以一次配置两种密度的CSI-RS的资源。其中,density CHIOCE字段中指示的密度是常规密度,即目前NR协议中定义的参考信号的密度,即下文中提及的第二参考信号或第三参考信号的密度。PortDensity字段中指示的密度是本申请实施例提及的低密度,即下文中提及的第一参考信号的密度。其中,PortDensity字段中的各个选项表示低密度是常规密度的几分之几,例如,“one”表示低密度等于常规密度;“half”表示低密度是常规密度的1/2;“quarter”表示低密度是常规密度的1/4。
应理解,本申请实施例将用于配置低密度参考信号的密度的字段命名为“PortDensity”仅以示例,不应对本申请实施例构成限定。
还应理解,上文仅以用于配置CSI-RS的RRC消息格式为例进行说明,不应对本申请实施例构成限定。本申请实施例也可以在用于配置DMRS的RRC消息中新增PortDensity字段以配置低密度DMRS,或者,本申请实施例也可以在用于配置SRS的RRC消息中新增PortDensity字段字段以配置低密度SRS。
还应理解,上文中仅以PortDensity字段中包括“one”、“half”、“quarter”三个选项为例进行说明,不应对本申请实施例构成限定。例如,PortDensity字段中还可以包括“one third”、“one eighth”等选项。
本申请实施例对低密度参考信号的密度不做限定,具体地,在不同的应用场景下,网络设备可以向终端设备发送不同的RRC消息,以配置不同密度的低密度参考信号的资源。
作为一个示例,在网络设备与终端设备之间的信道比较稳定(例如,终端设备在室内,或者终端设备保持静止,或者终端设备缓慢移动)的情况下,网络设备可以配置密度比较低的低密度参考信号。例如,网络设备可以配置密度是常规密度的1/4的低密度参考信号,在此情况下,网络设备向终端设备发送的RRC消息可以是:
Figure PCTCN2021095488-appb-000002
作为另一个示例,在网络设备与终端设备之间的信道不稳定(例如,终端设备快速移动)的情况下,网络设备可以配置密度比较高的低密度参考信号。例如,网络设备可以配置密度是常规密度的1/2的低密度参考信号,在此情况下,网络设备向终端设备发送的RRC消息可以是:
Figure PCTCN2021095488-appb-000003
S320,第一设备向第二设备发送第二参考信号。相应地,在S320中,第二设备接收来自第一设备的第二参考信号。
在第一设备是网络设备,第二设备是终端设备的情况下,第二参考信号可以是CSI-RS,或者可以是DMRS。
在第一设备是终端设备,第二设备是网络设备的情况下,第二参考信号可以是DMRS,或者可以是SRS。
具体地,第一设备以RRC消息中配置的常规密度发送第二参考信号。其中,常规密度指的是目前NR协议中定义的参考信号的密度。参考信号的密度指的是用于传输参考信号的资源占总的传输资源的比例。第一设备以常规密度发送第二参考信号,也可以指网络设备发送第二参考信号所使用的发送端口数等于目前NR协议中定义的参考信号的发送端 口数。例如,若第二参考信号是32端口CSI-RS,则在第一设备按照常规密度发送32端口CSI-RS的情况下,第一设备所使用的发送端口数是32。
S330,第二设备向第一设备发送第三CSI。相应地,在S330中,第一设备接收来自第二设备的第三CSI。
第三CSI是第二设备基于第二参考信号获得的。
在第一设备是网络设备,第二设备是终端设备的情况下,第三CSI可以是下行CSI。
在第一设备是终端设备,第二设备是网络设备的情况下,第三CSI可以是上行CSI。
S340,第一设备基于第三CSI训练神经网络以获得第一神经网络模型。
本申请实施例对第一设备训练神经网络的具体方式不做限定。
作为一个示例,可以采用信道数据和信道数据的多域特征融合嵌入的方法对神经网络进行训练。
如图4所示,将基于参考信号获得的信道频域响应(channel frequency response,CFR)(例如图4中示出的CFRa至CFRh)作为输入数据;进一步地,可以将CFR值用向量表示,同时将CFR的每个信道特征也用向量表示;进一步地,将CFR和CFR的信道特征的嵌入向量相加,作为融合结果在神经网络中进行计算,以对神经网络进行训练。
如图4所示,输入数据中除了CFR,还可能有特殊标记,例如[信道负载检测(channel load sensing,CLS)]和[分隔符(separator,SEP)]。[CLS]用于在后续下游任务中对CFR进行分类等。[SEP]用于分隔不同域的CFR。
除了信道数据的嵌入,还可能有位置嵌入。例如,若信道数据不是以序列的形式输入神经网络,而是并行的输入神经网络,那么每个位置都需要有该位置的嵌入(例如图4中示出的位置嵌入向量E P0至E P12),从而使得神经网络能够学习信道数据输入在位置上的关系。
信道数据的多域特征可以包括频率、时间和空间等。其中,频率特征可以表示与频率、子载波等与频率相关的特征。如图4中示出的E F1和E F2可以分别表示与两个不同的子载波相关的频率嵌入向量。时间特征可以表示时间、时间偏移量等与时间相关的特征。如图4中示出的E T0和E T1可以分别表示与两个不同子帧相关的时间嵌入向量。空间特征在信道数据上的体现就是天线的不同,可以表示和天线相关的特征。如图4中的E A0和E A1可以分别表示与两个不同接收天线或两个不同发送天线相关的天线嵌入向量。
具体地,第一设备将接收到的第三CSI中的部分CSI作为训练神经网络的输入数据,并且,第一设备可以根据RRC消息配置的低密度参考信号的密度确定作为输入数据的CSI的大小。
例如,在RRC消息配置的低密度参考信号的密度是常规密度的1/2的情况下,第一设备将第三CSI的1/2作为训练神经网络的输入数据。
又例如,在RRC消息配置的低密度参考信号的密度是常规密度的1/4的情况下,第一设备将第三CSI的1/4作为训练神经网络的输入数据。
进一步地,第一设备将神经网络的输出结果与第三CSI做比较,在输出结果与第三CSI之间的差异小于预设阈值的情况下,则认为神经网络已训练完成,即获得了第一神经网络模型。
应理解,在神经网络的输出结果与第三CSI之间的差异大于或等于预设阈值的情况 下,则认为神经网络未训练完成,在此情况下,则方法300继续执行S320至S340,直到神经网络的输出结果与第三CSI之间的差异小于预设阈值的情况下,方法300执行S350至S370。
S350,第一设备向第二设备发送第一参考信号。相应地,在S350中,第二设备接收来自第一设备的第一参考信号。
其中,第一参考信号的密度小于或等于第二参考信号的密度。
在第一设备是网络设备,第二设备是终端设备的情况下,第一参考信号可以是CSI-RS,或者可以是DMRS。
在第一设备是终端设备,第二设备是网络设备的情况下,第一参考信号可以是DMRS,或者可以是SRS。
在一些可能的实现方式中,第一设备以RRC消息中配置的低密度发送第一参考信号。其中,低密度指的是比常规密度小的密度。第一设备以低密度发送第一参考信号,指的是第一设备发送第一参考信号所使用的发送端口数小于目前NR协议中定义的参考信号的发送端口数。例如,若第一参考信号是32端口的CSI-RS,则在第一设备按照低密度发送32端口的CSI-RS的情况下,第一设备所使用的发送端口数小于32。
本申请实施例对第一参考信号的密度不做限定。如前文所述,在不同的应用场景下,网络设备可以发送不同的RRC消息以配置不同密度的第一参考信号。
作为一个示例,第一参考信号的密度可以是第二参考信号的密度的1/2。也就是说,第一设备发送第一参考信号使用的发送端口数是发送第二参考信号使用的发送端口数的1/2。例如,在第二参考信号和第一参考信号是32端口的CSI-RS的情况下,第一设备发送第二参考信号使用的发送端口数是32,发送第一参考信号使用的发送端口数是16。
作为另一个示例,第一参考信号的密度可以是第二参考信号的密度的1/4。也就是说,第一设备发送第一参考信号使用的发送端口数是发送第二参考信号使用的发送端口数的1/4。例如,在第二参考信号和第一参考信号是32端口的CSI-RS的情况下,第一设备发送第二参考信号使用的发送端口数是32,发送第一参考信号使用的发送端口数是8。
本申请实施例对第一参考信号在无线传输资源上的放置位置不做限定。也就是说,本申请实施对第一设备发送第一参考信号所使用的发送端口不做限定。
本申请实施例可以将第一参考信号的放置位置配置为第二参考信号的放置位置的一部分,也就是说第一设备可以使用发送第二参考信号所使用的发送端口中的一部分发送端口发送第一参考信号。例如,在第二参考信号和第一参考信号是32端口CSI-RS的情况下,若第一设备发送第二参考信号使用的发送端口是端口#1至端口#32,则第一设备可以使用端口#1至端口#32中的一部分端口发送第一参考信号。例如,若第一参考信号的密度是第二参考信号的密度的1/2,则第一设备可以使用端口#1至端口#32中的16个端口发送第一参考信号。例如,可以使用端口#1至端口#16发送第一参考信号,或者使用端口#17至端口#32发送第一参考信号。
下面以第二参考信号和第一参考信号是32端口的CSI-RS为例,结合图5至图8给出几种第一参考信号在无线传输资源中的放置位置的示例。其中,不同端口的CSI-RS采用时分、频分和码分相结合的资源复用方式进行映射和发送,例如,图5至图8中,不同填充图样的格子表示在时间和频率两个维度上不同端口CSI-RS的放置位置,结合码分复用, 可以获得所需的CSI-RS放置资源。以图5中的(a)为例,需要承载16端口的CSI-RS,图中共有8种填充图样不同的格子,每种填充图样占据两个格子,即占据两个资源单元(Resource Element,RE),在填充图样相同的两个RE上使用2个长度为2的码字(例如[1,1]和[1,-1]),从而实现码分复用,因此8种填充图样占据的RE总共可以承载16个CSI-RS。
图5和图6示出了第一参考信号的密度是第二参考信号的密度的1/2时,第一参考信号的放置位置的示例。在第一参考信号的密度是第二参考信号的密度的1/2的情况下,第一参考信号需要承载16个端口,因此,第一参考信号的放置位置可以直接使用常规密度下的16端口的CSI-RS的放置位置,如图5中的(a)与图5中的(b)。
如图6所示,第一参考信号的放置位置可以是常规密度下的32端口的CSI-RS的放置位置中的任意一半。例如图6中的(a)和(b)中示出的第一参考信号的放置位置是图2中的(a)示出的32端口的CSI-RS的放置位置的一半,图6中的(c)中示出的第一参考信号的放置位置是图2中的(b)示出的32端口的CSI-RS的放置位置的一半,图6中的(d)示出的第一参考信号的放置位置是图2中的(c)示出的32端口的CSI-RS的放置位置的一半。
图7至图8示出了第一参考信号的密度是第二参考信号的密度的1/4时,第一参考信号的放置位置的示例。在第一参考信号的密度是第二参考信号的密度的1/4的情况下,第一参考信号需要承载8个端口,因此,第一参考信号的放置位置可以直接使用常规密度下的8端口的CSI-RS的放置位置,如图7中的(a)、(b)和(c)。
如图8所示,第一参考信号的放置位置也可以是常规密度下的32端口的CSI-RS的放置位置的任意1/4。例如图8中的(a)和(b)中示出的第一参考信号的放置位置是图2中的(a)示出的32端口的CSI-RS的放置位置的1/4,图6中的(c)中示出的第一参考信号的放置位置是图2中的(b)示出的32端口的CSI-RS的放置位置的1/4,图6中的(d)示出的第一参考信号的放置位置是图2中的(c)示出的32端口的CSI-RS的放置位置的1/4。
在另一些可能的实现方式中,第一设备也可以以RRC消息中配置的常规密度发送第一参考信号,在此情况下,第一参考信号的密度等于第二参考信号的密度。
S360,第二设备向第一设备发送第一CSI。相应地,在S360中,第一设备接收来自第二设备的第一CSI。
在第一参考信号的密度小于第二参考信号的密度的情况下,第一CSI是第二设备根据第一参考信号获得的。可以理解,在此情况下,由于第一参考信号的密度小于第二参考信号的密度,因此,第二设备根据第一参考信号获得的第一CSI的大小小于根据第二参考信号获得的第三CSI的大小。也就是说,在第二设备根据第二参考信号获得的第三CSI表示第一设备与第二设备之间的全部信道信息的情况下,第二设备根据第一参考信号获得的第一CSI表示第一设备与第二设备之间的部分信道信息。
在第一参考信号的密度等于第二参考信号的密度的情况下,第一CSI是第二设备根据第一参考信号中的一部分获得的。具体地,第二设备根据在用于接收低密度参考信号的资源上接收到的一部分第一参考信号获得第一CSI。例如,以第二参考信号和第一参考信号是32端口的CSI-RS为例,若RRC消息中配置的用于传输常规密度参考信号的资源如图 2中的(a)所示,用于传输低密度参考信号的资源如图5中的(a)所示,则在第一参考信号的密度等于第二参考信号的密度的情况下,第一设备以RRC消息中配置的常规密度发送第一参考信号,即在用于传输第二参考信号的资源上发送第一参考信号。在此情况下,第二设备根据在用于接收低密度参考信号的资源上接收到的部分第一参考信号获得第一CSI,即第二设备根据在如图5中(a)所示的资源上接收到的部分第一参考信号获得第一CSI。
可以理解,由于第二设备是根据第一参考信号中的一部分参考信号获得第一CSI,因此,第一CSI的大小小于第三CSI的大小。也就是说,在第二设备根据第二参考信号获得的第三CSI表示第一设备与第二设备之间的全部信道信息的情况下,第二设备根据第一参考信号中的一部分获得的第一CSI表示第一设备与第二设备之间的部分信道信息。
进一步地,第二设备向第一设备发送获得的第一CSI。
S370,第一设备基于第一CSI和第一神经网络模型获得第二CSI。
第二CSI用于指示第一设备与第二设备之间的信道信息。
具体地,第一设备可以将第一CSI作为输入数据输入第一神经网络模型,以获得第二CSI。
S380,第一设备基于第二CSI,与第二设备进行数据通信。
具体地,第一设备可以基于第二CSI,计算预编码矩阵,并将预编码矩阵发送给第二设备;进一步地,第一设备使用预编码矩阵向第二设备发送第一数据,相应地,第二设备接收到来自第一设备的第一数据之后,使用预编码矩阵对第一数据进行解调。
具体地,根据第一设备和第二设备通信持续时间的长短,S350、S360和S370可能重复多次,即多次重复第一设备发送第一参考信号、第二设备反馈第一CSI和第一设备基于第一CSI和第一神经网络模型获得第二CSI三个操作。
在本申请实施例中,通过在第一设备侧部署神经网络,并基于全部信道信息(第三CSI)中的部分信道信息对神经网络进行训练获得第一神经网络模型的方式,使得第一设备可以基于部分信道信息(第一CSI)和第一神经网络模型恢复出全部信道信息(第二CSI)。因此,在第一设备获得第一神经网络模型的情况下,第二设备可以仅向第一设备反馈部分信道信息(第一CSI),从而可以减小第二设备的反馈开销。
此外,在第一设备获得第一神经网络模型的情况下,第一设备可以向第二设备发送低密度的参考信号,从而可以减小第二设备的发送参考信号的开销。
可选地,在S320之前,方法300还可以包括:第一设备向第二设备发送第四指示信息。第四指示信息用于指示第二参考信号的密度,即指示第一设备即将发送的第二参考信号是常规密度的参考信号。相应地,第二设备接收第四指示信息之后,则在用于传输常规密度参考信号的资源上接收第二参考信号。
在第一设备是网络设备,第二设备是终端设备的情况下,第四指示信息可以携带在DCI中。具体地,第四指示信息可以是DCI中的RSDensityFlag字段。RSDensityFlag字段可以是布尔(bool)型变量,例如,若RSDensityFlag=0,则指示第二参考信号的密度是常规密度。
在第一设备是终端设备,第二设备是网络设备的情况下,第四指示信息可以携带在UCI中。具体地,第四指示信息可以是UCI中的RSDensityFlag字段。RSDensityFlag字段 可以是布尔型变量,例如,若RSDensityFlag=0,则指示第二参考信号的密度是常规密度。
可选地,在S320之前,第一设备可以不发送第四指示信息,在此情况下,第二设备默认在用于传输常规密度参考信号的资源上接收来自第一设备的参考信号。直到第二设备接收到来自第一设备的第一指示信息,或者第二设备向第一设备发送第二请求消息之后,第二设备在用于传输低密度参考信号的资源上接收来自第一设备的参考信号。其中,第一指示信息用于指示第一参考信号的密度,第二请求消息用于请求第一参考信号,第二请求消息还用于指示第一参考信号的密度。
可选地,在S350之前,方法300还可以包括:第一设备在神经网络训练完成的情况下,向第二设备发送第一指示信息。即第一设备在确定第一神经网络模型的情况下,向第二设备发送第一指示信息。
第一指示信息用于指示第一参考信号的密度。即第一设备在神经网络训练完成的情况下,可以向第二设备发送第一指示信息,以指示第一设备即将发送的第一参考信号是低密度的参考信号。相应地,第二设备接收第一指示信息之后,则在用于传输低密度参考信号的资源上接收第一参考信号。如前文所述,第一参考信号的密度可以等于第二参考信号的密度,则在此情况下,第二设备接收到第一指示信息之后,则根据在用于传输低密度参考信号的资源上接收到的参考信号获得第一CSI。
在第一设备是网络设备,第二设备是终端设备的情况下,第一指示信息可以携带在DCI中。具体地,第一指示信息可以是DCI中的RSDensityFlag字段。RSDensityFlag字段可以是布尔型变量,例如,若RSDensityFlag=1,则指示第一参考信号的密度是低密度。
在第一设备是终端设备,第二设备是网络设备的情况下,第一指示信息可以携带在UCI中。具体地,第一指示信息可以是UCI中的RSDensityFlag字段。RSDensityFlag字段可以是布尔型变量,例如,若RSDensityFlag=1,则指示第一参考信号的密度是低密度。
可选地,在S350之前,方法300还可以包括:第二设备向第一设备发送第二请求消息。
第二请求消息用于请求第一参考信号,第二请求消息还用于指示第一参考信号的密度。即第二设备可以向第一设备发送第二请求消息,以请求低密度的参考信号。进一步地,第二设备在发送第二请求消息之后,则在用于传输低密度参考信号的资源上接收第一参考信号。如前文所述,第一参考信号的密度可以等于第二参考信号的密度,则在此情况下,第二设备发送第二请求消息之后,则根据在用于传输低密度参考信号的资源上接收到的参考信号获得第一CSI。
第二设备可以周期性地向第一设备发送第二请求消息;或者,第二设备可以在接收到来自第一设备的第二指示信息的情况下,向第一设备发送第二请求消息,第二指示信息用于指示已确定第一神经网络模型。
在第一设备是网络设备,第二设备是终端设备的情况下,第二请求消息可以携带在UCI中。具体地,第二请求消息可以是UCI中的RSDensityFlag字段。RSDensityFlag字段可以是布尔型变量,例如,若RSDensityFlag=1,则指示第一参考信号的密度是低密度。
在第一设备是终端设备,第二设备是网络设备的情况下,第二请求消息可以携带在DCI中。具体地,第二请求消息可以是DCI中的RSDensityFlag字段。RSDensityFlag字段可以是布尔型变量,例如,若RSDensityFlag=1,则指示第一参考信号的密度是低密度。
可选地,第一设备可以周期性地发送常规密度的参考信号(第二参考信号)和低密度参考信号(第一参考信号)。例如,第一设备在第一个周期内发送常规密度的参考信号,相应地,第二设备在第一个周期内在用于传输常规密度参考信号的资源上接收来自第一设备的参考信号;第一设备在第二个周期内发送低密度的参考信号,相应地,第二设备在第二个周期内在用于传输低密度参考信号的资源上接收来自第一设备的参考信号。
可选地,在S380之后,方法300还可以包括:在达到预设触发条件时,第一设备更新第一神经网络模型。
第一设备更新第一神经网络模型的步骤可以包括:
第一设备向第二设备发送第三参考信号,第三参考信号是常规密度参考信号;
第一设备接收来自第二设备的第四CSI,第四CSI是第二设备根据第三参考信号获得的;
第一设备基于第四CSI训练神经网络以获得更新后的第一神经网络模型。
第一设备更新第一神经网络模型的步骤的具体描述可以参考上文S320至S340中的描述,为了简洁,本申请实施例不再详述。
可以理解,在第一设备获得更新后的第一神经网络模型之后,根据第一设备和第二设备通信持续时间的长短,方法300可以继续重复执行多次S350至S370。因此在S380之后,第一设备对第一神经网络模型进行更新,也可以理解为:在S380之后,在达到预设触发条件时,方法300重新执行S320至S370。也就是说,在第一设备和第二设备的通信过程中,S320至S370可能被周期性地执行多次。
本申请实施例对预设触发条件不做限定。
作为一个示例,预设触发条件可以是第一定时器超时,第一定时器是在第一设备向第二设备发送第一参考信号时启动的。
也可以理解为,第一设备周期性地对第一神经网络模型进行更新。例如,第一设备更新第一神经网络模型的周期为T,则第一设备可以将第一定时器的定时时间设定为T。
作为另一个示例,预设触发条件可以是第一设备确定第二设备解调第一数据的解调性能低于预设门限。
如上文所述,第二设备基于来自第一设备的第一预编码矩阵解调来自第一设备的第一数据,进一步地,第二设备可以将解调第一数据的结果信息反馈给第一设备。第一设备接收到第二设备反馈的数据解调信息之后,可以统计第二设备解调第一数据的解调性能,并在确定第二设备解调第一数据的解调性能低于预设门限的情况下,更新第一神经网络模型。第一数据的解调性能例如可以是第一数据的丢包率,在第一数据的丢包率高于预设丢包率门限的情况下,则可以确定第一数据的解调性能低于预设门限。
第一设备在更新第一神经网络模型之前,即在发送第三参考信号之前,还可以向第二设备发送第五指示信息,第五指示信息用于指示第三参考信号的密度。关于第五指示信息可以参考上文中关于第四指示信息的描述,为了简洁,此处不再详述。
作为又一个示例,预设触发条件可以是第一设备接收来自第二设备的第一请求消息,第一请求消息用于请求更新第一神经网络模型。
如上文所述,第二设备基于来自第一设备的第一预编码矩阵解调来自第一设备的第一数据,进一步地,第二设备可以根据解调第一数据的结果信息,统计解调第一数据解调性 能,并在确定第一数据的解调性能低于预设门限的情况下,向第一设备发送第二请求消息,以请求第一设备更新第一神经网络模型。也可以理解为,第一请求消息用于请求第三参考信号,即用于请求常规密度的参考信号。
图9示出了本申请另一实施例提供的获取信道信息的方法900的示意性流程图。图9示出的方法900可以包括S910至S970。下面详细说明方法900中的各个步骤。
S910,参考信号资源配置。
具体地,在第一设备是网络设备,第二设备是终端设备的情况下,可以由第一设备向第二设备发送参考信号的配置信息,以为第二设备配置用于接收参考信号的资源。
在第一设备是终端设备,第二设备是网络设备的情况下,可以由第二设备向第一设备发送参考信号的配置信息,以为第一设备配置用于发送参考信号的资源。
其中,参考信号可以是:CSI-RS、DMRS、SRS等,参考信号的配置信息可以包括参考信号的密度信息等。
参考信号的配置信息可以承载在RRC消息中,下文以用于配置CSI-RS的密度的RRC消息为例说明申请实施例提供RRC消息格式。
用于配置CSI-RS的密度的RRC消息如下:
Figure PCTCN2021095488-appb-000004
Figure PCTCN2021095488-appb-000005
根据本申请实施例提供的RRC消息格式,可以一次配置两种密度的CSI-RS的资源。其中,density CHIOCE字段中指示的密度是常规密度,即目前NR协议中定义的参考信号的密度,即下文中提及的第二参考信号或第三参考信号的密度。PortDensity字段中指示的密度是本申请实施例提及的低密度,即下文中提及的第一参考信号的密度。其中,PortDensity字段中的各个选项表示低密度是常规密度的几分之几,例如,“one”表示低密度等于常规密度;“half”表示低密度是常规密度的1/2;“quarter”表示低密度是常规密度的1/4。
应理解,本申请实施例将用于配置低密度参考信号的密度的字段命名为“PortDensity”仅以示例,不应对本申请实施例构成限定。
还应理解,上文仅以用于配置CSI-RS的RRC消息格式为例进行说明,不应对本申请实施例构成限定。本申请实施例也可以在用于配置DMRS的RRC消息中新增PortDensity字段以配置低密度DMRS,或者,本申请实施例也可以在用于配置SRS的RRC消息中新增PortDensity字段字段以配置低密度SRS。
还应理解,上文中仅以PortDensity字段中包括“one”、“half”、“quarter”三个选项为例进行说明,不应对本申请实施例构成限定。例如,PortDensity字段中还可以包括“one third”、“one eighth”等选项。
本申请实施例对低密度参考信号的密度不做限定,具体地,在不同的应用场景下,网络设备可以向终端设备发送不同的RRC消息,以配置不同密度的低密度参考信号的资源。
作为一个示例,在网络设备与终端设备之间的信道比较稳定(例如,终端设备在室内,或者终端设备保持静止,或者终端设备缓慢移动)的情况下,网络设备可以配置密度比较低的低密度参考信号。例如,网络设备可以配置密度是常规密度的1/4的低密度参考信号,在此情况下,网络设备向终端设备发送的RRC消息可以是:
Figure PCTCN2021095488-appb-000006
作为另一个示例,在网络设备与终端设备之间的信道不稳定(例如,终端设备快速移动)的情况下,网络设备可以配置密度比较高的低密度参考信号。例如,网络设备可以配置密度是常规密度的1/2的低密度参考信号,在此情况下,网络设备向终端设备发送的RRC消息可以是:
Figure PCTCN2021095488-appb-000007
Figure PCTCN2021095488-appb-000008
S920,第一设备向第二设备发送第二参考信号。相应地,在S920中,第二设备接收来自第一设备的第二参考信号。
在第一设备是网络设备,第二设备是终端设备的情况下,第二参考信号可以是CSI-RS,或者可以是DMRS。
在第一设备是终端设备,第二设备是网络设备的情况下,第二参考信号可以是DMRS,或者可以是SRS。
具体地,第一设备以RRC消息中配置的常规密度发送第二参考信号。其中,常规密度指的是目前NR协议中定义的参考信号的密度。参考信号的密度指的是用于传输参考信号的资源占总的传输资源的比例。第一设备以常规密度发送第二参考信号,也可以指网络设备发送第二参考信号所使用的发送端口数等于目前NR协议中定义的参考信号的发送端口数。例如,若第二参考信号是32端口CSI-RS,则在第一设备按照常规密度发送32端口CSI-RS的情况下,第一设备所使用的发送端口数是32。
S930,第二设备基于第三CSI训练神经网络以获得第二神经网络模型。
其中,第三CSI是第二设备根据第二参考信号获得的。
本申请实施例对第二设备训练神经网络的具体方式不做限定。
作为一个示例,可以采用信道数据和信道数据的多域特征融合嵌入的方法对神经网络进行训练。
如图4所示,将基于参考信号获得的CFR(例如图4中示出的CFRa至CFRh)作为输入数据;进一步地,可以将CFR值用向量表示,同时将CFR的每个信道特征也用向量表示;进一步地,将CFR和CFR的信道特征的嵌入向量相加,作为融合结果在神经网络中进行计算,以对神经网络进行训练。
如图4所示,输入数据中除了CFR,还可能有特殊标记,例如[CLS]和[SEP]。[CLS]用于在后续下游任务中对CFR进行分类等。[SEP]用于分隔不同域的CFR。
除了信道数据的嵌入,还可能有位置嵌入。例如,若信道数据不是以序列的形式输入神经网络,而是并行的输入神经网络,那么每个位置都需要有该位置的嵌入(例如图4中示出的位置嵌入向量E P0至E P12),从而使得神经网络能够学习信道数据输入在位置上的关系。
信道数据的多域特征可以包括频率、时间和空间等。其中,频率特征可以表示与频率、子载波等与频率相关的特征。如图4中示出的E F1和E F2可以分别表示与两个不同的子载波相关的频率嵌入向量。时间特征可以表示时间、时间偏移量等与时间相关的特征。如图4中示出的E T0和E T1可以分别表示与两个不同子帧相关的时间嵌入向量。空间特征在信道数据上的体现就是天线的不同,可以表示和天线相关的特征。如图4中的E A0和E A1可以分别表示与两个不同接收天线或两个不同发送天线相关的天线嵌入向量。
具体地,第二设备将第三CSI中的部分CSI作为训练神经网络的输入数据,并且,第二设备可以根据RRC消息配置的低密度参考信号的密度确定作为输入数据的CSI的大小。
例如,在RRC消息配置的低密度参考信号的密度是常规密度的1/2的情况下,第二设备将第三CSI的1/2作为训练神经网络的输入数据。
又例如,在RRC消息配置的低密度参考信号的密度是常规密度的1/4的情况下,第二设备将第三CSI的1/4作为训练神经网络的输入数据。
进一步地,第二设备将神经网络的输出结果与第三CSI做比较,在输出结果与第三CSI之间的差异小于预设阈值的情况下,则认为神经网络已训练完成,即获得了第二神经网络模型。
应理解,在神经网络的输出结果与第三CSI之间的差异大于或等于预设阈值的情况下,则认为神经网络未训练完成,在此情况下,则方法900继续执行S920至S930,直到神经网络的输出结果与第三CSI之间的差异小于预设阈值的情况下,方法900执行S940至S960。
S940,第一设备向第二设备发送第一参考信号。相应地,在S940中,第二设备接收来自第一设备的第一参考信号。
其中,第一参考信号的密度小于第二参考信号的密度。
在第一设备是网络设备,第二设备是终端设备的情况下,第一参考信号可以是CSI-RS,或者可以是DMRS。
在第一设备是终端设备,第二设备是网络设备的情况下,第一参考信号可以是DMRS,或者可以是SRS。
具体地,第一设备以RRC消息中配置的低密度发送第一参考信号。其中,低密度指的是比常规密度小的密度。第一设备以低密度发送第一参考信号,指的是第一设备发送第一参考信号所使用的发送端口数小于目前NR协议中定义的参考信号的发送端口数。例如,若第一参考信号是32端口的CSI-RS,则在第一设备按照低密度发送32端口的CSI-RS的情况下,第一设备所使用的发送端口数小于32。
本申请实施例对RRC消息中配置的第一参考信号的密度不做限定。如前文所述,在不同的应用场景下,网络设备可以发送不同的RRC消息以配置不同密度的第一参考信号。
作为一个示例,第一参考信号的密度可以是第二参考信号的密度的1/2。也就是说,第一设备发送第一参考信号使用的发送端口数是发送第二参考信号使用的发送端口数的1/2。例如,在第二参考信号和第一参考信号是32端口的CSI-RS的情况下,第一设备发送第二参考信号使用的发送端口数是32,发送第一参考信号使用的发送端口数是16。
作为另一个示例,第一参考信号的密度可以是第二参考信号的密度的1/4。也就是说,第一设备发送第一参考信号使用的发送端口数是发送第二参考信号使用的发送端口数的1/4。例如,在第二参考信号和第一参考信号是32端口的CSI-RS的情况下,第一设备发送第二参考信号使用的发送端口数是32,发送第一参考信号使用的发送端口数是8。
本申请实施例对第一参考信号在无线传输资源上的放置位置不做限定。也就是说,本申请实施对第一设备发送第一参考信号所使用的发送端口不做限定。
本申请实施例可以将第一参考信号的放置位置配置为第二参考信号的放置位置的一部分,也就是说第一设备可以使用发送第二参考信号所使用的发送端口中的一部分发送端口发送第一参考信号。例如,在第二参考信号和第一参考信号是32端口CSI-RS的情况下,若第一设备发送第二参考信号使用的发送端口是端口#1至端口#32,则第一设备可以使用 端口#1至端口#32中的一部分端口发送第一参考信号。例如,若第一参考信号的密度是第二参考信号的密度的1/2,则第一设备可以使用端口#1至端口#32中的16个端口发送第一参考信号。例如,可以使用端口#1至端口#16发送第一参考信号,或者使用端口#17至端口#32发送第一参考信号。
下面以第二参考信号和第一参考信号是32端口的CSI-RS为例,结合图5至图8给出几种第一参考信号在无线传输资源中的放置位置的示例。其中,不同端口的CSI-RS采用时分、频分和码分相结合的资源复用方式进行映射和发送,例如,图5至图8中,不同填充图样的格子表示在时间和频率两个维度上不同端口CSI-RS的放置位置,结合码分复用,可以获得所需的CSI-RS放置资源。以图5中的(a)为例,需要承载16端口的CSI-RS,图中共有8种填充图样不同的格子,每种填充图样占据两个格子,即占据两个资源单元(Resource Element,RE),在填充图样相同的两个RE上使用2个长度为2的码字(例如[1,1]和[1,-1]),从而实现码分复用,因此种个填充图样占据的RE总共可以承载16个CSI-RS。
图5和图6示出了第一参考信号的密度是第二参考信号的密度的1/2时,第一参考信号的放置位置的示例。在第一参考信号的密度是第二参考信号的密度的1/2的情况下,第一参考信号需要承载16个端口,因此,第一参考信号的放置位置可以直接使用常规密度下的16端口的CSI-RS的放置位置,如图5中的(a)与图5中的(b)。
如图6所示,第一参考信号的放置位置可以是常规密度下的32端口的CSI-RS的放置位置中的任意一半。例如图6中的(a)和(b)中示出的第一参考信号的放置位置是图2中的(a)示出的32端口的CSI-RS的放置位置的一半,图6中的(c)中示出的第一参考信号的放置位置是图2中的(b)示出的32端口的CSI-RS的放置位置的一半,图6中的(d)示出的第一参考信号的放置位置是图2中的(c)示出的32端口的CSI-RS的放置位置的一半。
图7至图8示出了第一参考信号的密度是第二参考信号的密度的1/4时,第一参考信号的放置位置的示例。在第一参考信号的密度是第二参考信号的密度的1/4的情况下,第一参考信号需要承载8个端口,因此,第一参考信号的放置位置可以直接使用常规密度下的8端口的CSI-RS的放置位置,如图7中的(a)、(b)和(c)。
如图8所示,第一参考信号的放置位置也可以是常规密度下的32端口的CSI-RS的放置位置的任意1/4。例如图8中的(a)和(b)中示出的第一参考信号的放置位置是图2中的(a)示出的32端口的CSI-RS的放置位置的1/4,图8中的(c)中示出的第一参考信号的放置位置是图2中的(b)示出的32端口的CSI-RS的放置位置的1/4,图8中的(d)示出的第一参考信号的放置位置是图2中的(c)示出的32端口的CSI-RS的放置位置的1/4。
S950,第二设备基于第一CSI和第二神经网络模型获得第二CSI。
第一CSI是第二设备根据第一参考信号获得的。可以理解,在此情况下,由于第一参考信号的密度小于第二参考信号的密度,因此,第二设备根据第一参考信号获得的第一CSI的大小小于根据第二参考信号获得的第三CSI的大小。也就是说,在第二设备根据第二参考信号获得的第三CSI表示第一设备与第二设备之间的全部信道信息的情况下,第二设备根据第一参考信号获得的第一CSI表示第一设备与第二设备之间的部分信道信息。
进一步地,第二设备基于第一CSI和第二神经网络模型获得第二CSI。。
第二CSI用于指示第一设备与第二设备之间的信道信息。
具体地,第二设备可以将第一CSI作为输入数据输入第二神经网络模型,以获得第二CSI。
S960,第二设备向第一设备发送第二CSI。相应地,在S960中,第一设备接收来自第二设备的第二CSI。
S970,第一设备基于第二CSI,与第二设备进行数据通信。
具体地,第一设备可以基于第二CSI,计算预编码矩阵,并将预编码矩阵发送给第二设备;进一步地,第一设备使用预编码矩阵向第二设备发送第一数据,相应地,第二设备接收到来自第一设备的第一数据之后,使用预编码矩阵对第一数据进行解调。
具体地,根据第一设备和第二设备通信持续时间的长短,S940、S950和S960可能重复多次,即多次重复第一设备发送第一参考信号、第二设备基于第一CSI和第二神经网络模型获得第二CSI以及第二设备反馈第二CSI三个操作。
在本申请实施例中,通过在第二设备侧部署神经网络,并基于全部信道信息(第三CSI)中的部分信道信息对神经网络进行训练获得第二神经网络模型的方式,使得第二设备可以基于部分信道信息(第一CSI)和第二神经网络模型恢复出全部信道信息(第二CSI)。因此,在第二设备获得第一神经网络模型的情况下,第一设备可以向第二设备发送低密度的参考信号,从而可以减小发送参考信号的开销。
可选地,在S920之前,方法900还可以包括:第一设备向第二设备发送第四指示信息。第四指示信息用于指示第二参考信号的密度,即指示第一设备即将发送的第二参考信号是常规密度的参考信号。相应地,第二设备接收第四指示信息之后,则在用于传输常规密度参考信号的资源上接收第二参考信号。
在第一设备是网络设备,第二设备是终端设备的情况下,第四指示信息可以携带在DCI中。具体地,第四指示信息可以是DCI中的RSDensityFlag字段。RSDensityFlag字段可以是布尔型变量,例如,若RSDensityFlag=0,则指示第二参考信号的密度是常规密度。
在第一设备是终端设备,第二设备是网络设备的情况下,第四指示信息可以携带在UCI中。具体地,第四指示信息可以是UCI中的RSDensityFlag字段。RSDensityFlag字段可以是布尔型变量,例如,若RSDensityFlag=0,则指示第二参考信号的密度是常规密度。
可选地,在S920之前,第一设备可以不发送第四指示信息,在此情况下,第二设备默认在用于传输常规密度参考信号的资源上接收来自第一设备的参考信号。直到第二设备接收到来自第一设备的第一指示信息,或者第二设备向第一设备发送第二请求消息之后,第二设备在用于传输低密度参考信号的资源上接收来自第一设备的参考信号。其中,第一指示信息用于指示第一参考信号的密度,第二请求消息用于请求第一参考信号,第二请求消息还用于指示第一参考信号的密度。
可选地,在S940之前,方法900还可以包括:第一设备向第二设备发送第一指示信息。
第一指示信息用于指示第一参考信号的密度。即第一设备在神经网络训练完成的情况下,可以向第二设备发送第一指示信息,以指示第一设备即将发送的第一参考信号是低密度的参考信号。相应地,第二设备接收第一指示信息之后,则在用于传输低密度参考信号 的资源上接收第一参考信号。如前文所述,第一参考信号的密度可以等于第二参考信号的密度,则在此情况下,第二设备接收到第一指示信息之后,则根据在用于传输低密度参考信号的资源上接收到的参考信号获得第一CSI。
第一设备可以周期性地向第二设备发送第一指示信息;或者,第一设备可以在接收到来自第二设备的第三指示信息的情况下,向第二设备发送第一指示信息,第三指示信息用于指示已确定第二神经网络模型。
在第一设备是网络设备,第二设备是终端设备的情况下,第一指示信息可以携带在DCI中。具体地,第一指示信息可以是DCI中的RSDensityFlag字段。RSDensityFlag字段可以是布尔型变量,例如,若RSDensityFlag=1,则指示第一参考信号的密度是低密度。
在第一设备是终端设备,第二设备是网络设备的情况下,第一指示信息可以携带在UCI中。具体地,第一指示信息可以是UCI中的RSDensityFlag字段。RSDensityFlag字段可以是布尔型变量,例如,若RSDensityFlag=1,则指示第一参考信号的密度是低密度。
可选地,在S940之前,方法900还可以包括:第二设备向第一设备发送第二请求消息。
第二请求消息用于请求第一参考信号,第二请求消息还用于指示第一参考信号的密度。即第二设备可以向第一设备发送第二请求消息,以请求低密度的参考信号。进一步地,第二设备在发送第二请求消息之后,则在用于传输低密度参考信号的资源上接收第一参考信号。如前文所述,第一参考信号的密度可以等于第二参考信号的密度,则在此情况下,第二设备发送第二请求消息之后,则根据在用于传输低密度参考信号的资源上接收到的参考信号获得第一CSI。
在第一设备是网络设备,第二设备是终端设备的情况下,第二请求消息可以携带在UCI中。具体地,第二请求消息可以是UCI中的RSDensityFlag字段。RSDensityFlag字段可以是布尔型变量,例如,若RSDensityFlag=1,则指示第一参考信号的密度是低密度。
在第一设备是终端设备,第二设备是网络设备的情况下,第二请求消息可以携带在DCI中。具体地,第二请求消息可以是DCI中的RSDensityFlag字段。RSDensityFlag字段可以是布尔型变量,例如,若RSDensityFlag=1,则指示第一参考信号的密度是低密度。
可选地,第一设备可以周期性地发送常规密度的参考信号(第二参考信号)和低密度参考信号(第一参考信号)。例如,第一设备在第一个周期内发送常规密度的参考信号,相应地,第二设备在第一个周期内在用于传输常规密度参考信号的资源上接收来自第一设备的参考信号;第一设备在第二个周期内发送低密度的参考信号,相应地,第二设备在第二个周期内在用于传输低密度参考信号的资源上接收来自第一设备的参考信号。
可选地,在S970之后,方法900还可以包括:在达到预设触发条件时,第二设备更新第二神经网络模型。
第二设备更新第二神经网络模型的步骤可以包括:
第一设备向第二设备发送第三参考信号,第三参考信号是常规密度参考信号;
第二设备基于第四CSI训练神经网络以获得更新后的第二神经网络模型,第四CSI是根据第三参考信号获得的;。
第二设备更新第二神经网络模型的步骤的具体描述可以参考上文S920至S930中的描述,为了简洁,本申请实施例不再详述。
可以理解,在第二设备获得更新后的第二神经网络模型之后,根据第一设备和第二设备通信持续时间的长短,方法900可以继续重复执行多次S940至S960。因此在S970之后,第二设备对第二神经网络模型进行更新,也可以理解为:在S970之后,在达到预设触发条件时,方法900重新执行S920至S960。也就是说,在第一设备和第二设备的通信过程中,S920至S960可能被周期性地执行多次。
本申请实施例对预设触发条件不做限定。
作为一个示例,预设触发条件可以是第二定时器超时,第二定时器是在第二设备接收到来自第一设备的第一参考信号时启动的。
也可以理解为,第二设备周期性地对第二神经网络模型进行更新。例如,第二设备更新第二神经网络模型的周期为T,则第二设备可以将第二定时器的定时时间设定为T。
作为另一个示例,预设触发条件可以是第二设备确定解调第一数据的解调性能低于预设门限。
如上文所述,第二设备基于来自第一设备的预编码矩阵解调来自第一设备的第一数据,进一步地,第二设备可以根据解调第一数据的结果信息,统计解调第一数据解调性能,并在确定第一数据的解调性能低于预设门限的情况下,更新第二神经网络模型。第一数据的解调性能例如可以是第一数据的丢包率,在第一数据的丢包率高于预设丢包率门限的情况下,则可以确定第一数据的解调性能低于预设门限。
第二设备在更新第二神经网络模型之前,即在接收来自第一设备的第三参考信号之前,还可以向第二设备发送第一请求消息,第一请求消息用于请求第三参考信号,即用于请求常规密度参考信号。
下面结合图10至图11,以第一设备是网络设备、第二设备是终端设备以及第二参考信号和第一参考信号是32端口的CSI-RS为例说明本申请实施例提供的获取信道信息的方法。
图10示出的方法中,以神经网络部署在网络设备侧为例进行说明。如图10所示,方法1000可以包括S1010至S1090,下面详细说明各个步骤。
S1010,网络设备向终端设备发送RRC消息。相应地,在S1010中,终端设备接收来自网络设备的RRC消息。
RRC消息可以用于配置用于传输常规密度CSI-RS(第二参考信号的一列)和低密度CSI-RS(第一参考信号的一例)的资源,例如,可以用于配置常规密度CSI-RS和低密度CSI-RS的密度。RRC消息格式可以参考上文S310中的描述,为了简洁,本申请实施例不再赘述。
S1020,网络设备向终端设备发送第四指示信息。相应地,在S1020中,终端设备接收来自网络设备的第四指示信息。
第四指示信息用于指示网络设备即将发送的CSI-RS是常规密度CSI-RS。相应地,终端设备接收到第四指示信息之后,在用于传输常规密度CSI-RS的资源上接收CSI-RS。
第四指示信息可以携带在DCI中。具体地,第四指示信息可以是DCI中的RSDensityFlag字段。RSDensityFlag字段可以是布尔型变量,例如,若RSDensityFlag=0,则指示网络设备即将发送的CSI-RS是常规密度CSI-RS。
S1030,网络设备向终端设备发送常规密度CSI-RS。相应地,在S1030中,终端设备 接收来自网络设备的常规密度CSI-RS。
具体地,网络设备以RRC消息中配置的常规密度发送常规密度CSI-RS。例如,若网络设备发送的CSI-RS是32端口CSI-RS,则在网络设备按照常规密度发送32端口CSI-RS的情况下,网络设备所使用的发送端口数是32。
S1040,终端设备向网络设备发送第三CSI。相应地,在S1040中,网络设备接收来自终端设备的第三CSI。
第三CSI是终端设备基于常规密度CSI-RS获得的。终端设备基于常规密度CSI-RS获取第三CSI的方式可以参考现有技术,为了简洁,本申请实施例不再详述。
S1050,网络设备基于第三CSI训练神经网络以获得第一神经网络模型。
网络设备训练神经网络的方法可以参考上文S340中的描述,为了简洁,本申请实施例不再赘述。
S1060,在获得第一神经网络模型的情况下,网络设备向终端设备发送第一指示信息。相应地,在S1060中,终端设备接收来自网络设备的第一指示信息。
第一指示信息用于指示网络设备即将发送的CSI-RS是低密度CSI-RS。相应地,终端设备接收到第一指示信息之后,在用于传输低规密度CSI-RS的资源上接收CSI-RS。
第一指示信息可以携带在DCI中。具体地,第一指示信息可以是DCI中的RSDensityFlag字段。RSDensityFlag字段可以是布尔型变量,例如,若RSDensityFlag=1,则指示网络设备即将发送的CSI-RS是低密度CSI-RS。
S1070,网络设备向终端设备发送低密度CSI-RS。相应地,在S1070中,终端设备接收来自网络设备的低密度CSI-RS。
具体地,网络设备以RRC消息中配置的低密度发送低密度CSI-RS。例如,若网络设备发送的是32端口CSI-RS,则在网络设备按照低密度发送32端口CSI-RS的情况下,网络设备所使用的发送端口数小于32。
本申请实施例对低密度CSI-RS的密度和在无线资源中的放置位置不做限定。具体地,可以参考上文S350中的描述,为了简洁,本申请实施例不再赘述。
S1080,终端设备向网络设备发送第一CSI。相应地,在S1080中,网络设备接收来自终端设备的第一CSI。
第一CSI是终端设备根据低密度CSI-RS获得的。可以理解,在此情况下,由于低密度CSI-RS的密度小于常规密度CSI-RS的密度,因此,终端设备根据低密度CSI-RS获得的第一CSI的大小小于根据常规密度CSI-RS获得的第三CSI的大小。也就是说,在终端设备根据常规密度CSI-RS获得的第三CSI表示全部下行信道信息的情况下,终端设备根据低密度CSI-RS获得的第一CSI表示部分下行信道信息。
进一步地,终端设备向网络设备发送获得的第一CSI。
S1090,网络设备基于第一CSI和第一神经网络模型获得第二CSI。
第二CSI用于指示网络设备与终端设备之间的下行信道信息。
具体地,网络设备可以将第一CSI作为输入数据输入第一神经网络模型,以获得第二CSI。
图11示出的方法中,以神经网络部署在终端设备侧为例进行说明。如图11所示,方法1100可以包括S1110至S1170,下面详细说明各个步骤。
S1110,网络设备向终端设备发送RRC消息。相应地,在S1110中,终端设备接收来自网络设备的RRC消息。
RRC消息可以用于配置用于传输常规密度CSI-RS(第二参考信号的一列)和低密度CSI-RS(第一参考信号的一例)的资源,例如,可以用于配置常规密度CSI-RS和低密度CSI-RS的密度。RRC消息格式可以参考上文S310中的描述,为了简洁,本申请实施例不再赘述。
S1120,网络设备向终端设备发送常规密度CSI-RS。相应地,在S1120中,终端设备接收来自网络设备的常规密度CSI-RS。
具体地,网络设备以RRC消息中配置的常规密度发送常规密度CSI-RS。例如,若网络设备发送的CSI-RS是32端口CSI-RS,则在网络设备按照常规密度发送32端口CSI-RS的情况下,网络设备所使用的发送端口数是32。
S1130,终端设备基于第三CSI训练神经网络以获得第二神经网络模型。
第三CSI是终端设备基于常规密度CSI-RS获得的。终端设备基于常规密度CSI-RS获取第三CSI的方式可以参考现有技术,为了简洁,本申请实施例不再详述。
网络设备训练神经网络的方法可以参考上文S340中的描述,为了简洁,本申请实施例不再赘述。
S1140,在获得第二神经网络模型的情况下,终端设备向网络设备发送第二请求消息。相应地,在S1140中,网络设备接收来自终端设备的第二请求消息。
第二请求消息用于请求低密度CSI-RS。也就是说,终端设备在向网络设备发送第二请求消息之后,则在用于传输低密度CSI-RS的资源上接收低密度CSI-RS。
第二请求消息可以携带在UCI中。具体地,第二请求消息可以是UCI中的RSDensityFlag字段。RSDensityFlag字段可以是布尔型变量,例如,若RSDensityFlag=1,则指示终端设备请求的是低密度的CSI-RS。
S1150,网络设备向终端设备发送低密度CSI-RS。相应地,在S1150中,终端设备接收来自网络设备的低密度CSI-RS。
具体地,网络设备以RRC消息中配置的低密度发送低密度CSI-RS。例如,若网络设备发送的是32端口CSI-RS,则在网络设备按照低密度发送32端口CSI-RS的情况下,网络设备所使用的发送端口数小于32。
本申请实施例对低密度CSI-RS的密度和在无线资源中的放置位置不做限定。具体地,可以参考上文S350中的描述,为了简洁,本申请实施例不再赘述。
S1160,终端设备基于第一CSI和第二神经网络模型获得第二CSI。
第一CSI是终端设备根据低密度CSI-RS获得的。可以理解,在此情况下,由于低密度CSI-RS的密度小于常规密度CSI-RS的密度,因此,终端设备根据低密度CSI-RS获得的第一CSI的大小小于根据常规密度CSI-RS获得的第三CSI的大小。也就是说,在终端设备根据常规密度CSI-RS获得的第三CSI表示全部下行信道信息的情况下,终端设备根据低密度CSI-RS获得的第一CSI表示部分下行信道信息。
进一步地,网络设备可以将第一CSI作为输入数据输入第一神经网络模型,以获得第二CSI。
第二CSI用于指示网络设备与终端设备之间的下行信道信息。
S1170,终端设备向网络设备发送第二CSI。相应地,在S1170中,网络设备接收来自终端设备的第二CSI。
上文结合图3至图11详细地描述了本申请实施例的方法,下文结合图12至图15详细地描述本申请实施例的装置。需要说明的是,图12至图15所示的装置可以实现上述方法中各个步骤,为了简洁,在此不再赘述。
图12是本申请实施例提供的通信装置的示意性框图。如图12所示,该通信装置2000可以包括处理单元2100和收发单元2200。
在一种可能的设计中,该通信装置2000可对应于上文方法实施例中的第一设备,例如,可以为第一设备,或者配置于第一设备中的部件(如芯片或芯片系统等)。
应理解,该通信装置2000可对应于根据本申请实施例的方法300和方法900中的第一设备,该通信装置2000可以包括用于执行图3中的方法300和图9中的方法900中第一设备执行的方法的单元。并且,该通信装置2000中的各单元和上述其他操作和/或功能分别为了实现图3中的方法300和图9中的方法900中任一方法的相应流程。应理解,各单元执行上述相应步骤的具体过程在上述方法实施例中已经详细说明,为了简洁,在此不再赘述。
在另一种可能的设计中,该通信装置2000可对应于上文方法实施例中的第二设备,例如,可以为第二设备,或者配置于第二设备中的部件(如芯片或芯片系统等)。
应理解,该通信装置2000可对应于根据本申请实施例的方法300和方法900中的第二设备,该通信装置2000可以包括用于执行图3中的方法300和图9中的方法900中第二设备执行的方法的单元。并且,该通信装置2000中的各单元和上述其他操作和/或功能分别为了实现图3中的方法300和图9中的方法900中任一方法的相应流程。应理解,各单元执行上述相应步骤的具体过程在上述方法实施例中已经详细说明,为了简洁,在此不再赘述。
在又一种可能的设计中,该通信装置2000可对应于上文方法实施例中的终端设备,例如,可以为终端设备,或者配置于终端设备中的部件(如芯片或芯片系统等)。
应理解,该通信装置2000可对应于根据本申请实施例的方法1000和方法1100中的终端设备,该通信装置2000可以包括用于执行图10中的方法1000和图11中的方法1100中终端设备执行的方法的单元。并且,该通信装置2000中的各单元和上述其他操作和/或功能分别为了实现图10中的方法1000和图11中的方法1100中任一方法的相应流程。应理解,各单元执行上述相应步骤的具体过程在上述方法实施例中已经详细说明,为了简洁,在此不再赘述。
还应理解,该通信装置2000为配置于终端设备中的芯片时,该通信装置2000中的收发单元2200可以通过输入/输出接口实现,该通信装置2000中的处理单元2100可以通过该芯片或芯片系统上集成的处理器、微处理器或集成电路等实现。
在又一种可能的设计中,该通信装置2000可对应于上文方法实施例中的网络设备,例如,可以为网络设备,或者配置于网络设备中的部件(如芯片或芯片系统等)。
应理解,该通信装置2000可对应于根据本申请实施例的方法1000和方法1100中的网络设备,该通信装置2000可以包括用于执行图10中的方法1000和图11中的方法1100中网络设备执行的方法的单元。并且,该通信装置2000中的各单元和上述其他操作和/或 功能分别为了实现图10中的方法1000和图11中的方法1100中任一方法的相应流程。应理解,各单元执行上述相应步骤的具体过程在上述方法实施例中已经详细说明,为了简洁,在此不再赘述。
还应理解,该通信装置2000为配置于网络设备中的芯片时,该通信装置2000中的收发单元2200可以通过输入/输出接口实现,该通信装置2000中的处理单元2100可以通过该芯片或芯片系统上集成的处理器、微处理器或集成电路等实现。
图13是本申请实施提供的通信装置3000的结构示意图。如图13,通信装置3000包括处理器3100和通信接口3200。可选地,通信装置3000还可以包括存储器3300。处理器3100、通信接口3200和存储器3300可以通过总线连接。
应理解,上述处理器3100和存储器3300可以合成一个处理装置,处理器3100用于执行存储器3300中存储的程序代码来实现上述功能。具体实现时,该存储器3300也可以集成在处理器3100中,或者独立于处理器3100。
在一种可能的设计中,该通信装置3000可对应于上文方法实施例中的第一设备。
具体地,该通信装置3000可以包括用于执行图3中的方法300和图9中的方法900中的第一设备执行的方法的单元。并且,该通信装置3000中的各单元和上述其他操作和/或功能分别为了实现图3中的方法300和图9中的方法900中第一设备执行的相应流程。应理解,各单元执行上述相应步骤的具体过程在上述方法实施例中已经详细说明,为了简洁,在此不再赘述。
在一种可能的设计中,该通信装置3000可对应于上文方法实施例中的第二设备。
具体地,该通信装置3000可以包括用于执行图3中的方法300和图9中的方法900中的第二设备芯片执行的方法的单元。并且,该通信装置800中的各单元和上述其他操作和/或功能分别为了实现图3中的方法300和图9中的方法900中第二设备执行的相应流程。应理解,各单元执行上述相应步骤的具体过程在上述方法实施例中已经详细说明,为了简洁,在此不再赘述。
图14是本申请实施例提供的终端设备4000的结构示意图。该终端设备4000可应用于如图1所示的系统中,执行上述方法实施例中终端设备的功能。如图14所示,将具有收发功能的天线和射频电路记为收发单元4100,将具有处理功能的处理器记为处理单元4200。即终端设备包括收发单元4100和处理单元4200。收发单元4100也可以称为收发器、收发机、收发装置等。处理单元4200也可以称为处理器,处理单板,处理模块、处理装置等。可选地,可以将收发单元4100中用于实现接收功能的器件视为接收单元,将收发单元4100中用于实现发送功能的器件视为发送单元,即收发单元4100包括接收单元和发送单元。收发单元有时也可以称为收发机、收发器、或收发电路等。接收单元有时也可以称为接收机、接收器、或接收电路等。发送单元有时也可以称为发射机、发射器或者发射电路等。
例如,在一种实现方式中,收发单元4100还用于执行图10中所示的S1010至S1030和S1060至S1070中终端设备侧的接收操作,收发单元4100还用于执行图10中所示的S1040与S1080中终端设备侧的发送操作,和/或收发单元4100还用于执行终端设备侧的其他收发步骤。
又例如,在一种实现方式中,收发单元4100还用于执行图11中所示的S1110、S1120 与S1150中终端设备侧的接收操作,收发单元4100还用于执行图11中所示的S1140与S1170中终端设备侧的发送操作,和/或收发单元4100还用于执行终端设备侧的其他收发步骤。处理单元4200用于执行图11中所示的步骤S1130和S1160,和/或处理单元4200还用于执行终端设备侧的其他处理步骤。
应理解,图14仅为示例而非限定,上述包括收发单元和处理单元的终端设备可以不依赖于图14所示的结构。
图15给出了本申请实施例提供的一种装置5000,可以用于执行上述终端设备或网络设备所执行的方法,该装置5000可以是通信设备或者通信设备中的芯片。如图15所示,所述装置5000包括:至少一个输入接口(Input(s))5100,逻辑电路5200,至少一个输出接口(Output(s))5300。可选的,上述的逻辑电路5200可以是芯片,或其他可以实现本申请方法的集成电路。
逻辑电路5200可以实现上述各个实施例中终端设备或网络设备所执行的方法;
输入接口5100用于接收数据;输出接口5300用于发送数据。举例来说,当该装置5000为终端设备时,输入接口5100可用于接收网络设备发送的参考信号,输入接口5100还可以用于接收网络设备发送的RRC消息;输出接口5300可以用于向网络设备发送CSI。当该装置5000为网络设备时,输出接口5300用于向终端设备下发参考信号,输出接口还可以用于向终端设备下发RRC消息;输入接口5100可以用于接收终端设备发送的CSI。
输入接口5100、逻辑电路5200或输出接口5300的功能可以参考上述各个实施例中终端设备或网络设备执行的方法,此处不再赘述。
本申请实施例还提供了一种处理装置,包括处理器和接口;所述处理器用于执行上述任一方法实施例中的方法。
应理解,上述处理装置可以是一个或多个芯片。例如,该处理装置可以是现场可编程门阵列(field programmable gate array,FPGA),可以是专用集成芯片(application specific integrated circuit,ASIC),还可以是系统芯片(system on chip,SoC),还可以是中央处理器(central processor unit,CPU),还可以是网络处理器(network processor,NP),还可以是数字信号处理电路(digital signal processor,DSP),还可以是微控制器(micro controller unit,MCU),还可以是可编程控制器(programmable logic device,PLD)或其他集成芯片。
在实现过程中,上述方法的各步骤可以通过处理器中的硬件的集成逻辑电路或者软件形式的指令完成。结合本申请实施例所公开的方法的步骤可以直接体现为硬件处理器执行完成,或者用处理器中的硬件及软件模块组合执行完成。软件模块可以位于随机存储器,闪存、只读存储器,可编程只读存储器或者电可擦写可编程存储器、寄存器等本领域成熟的存储介质中。该存储介质位于存储器,处理器读取存储器中的信息,结合其硬件完成上述方法的步骤。为避免重复,这里不再详细描述。
应注意,本申请实施例中的处理器可以是一种集成电路芯片,具有信号的处理能力。在实现过程中,上述方法实施例的各步骤可以通过处理器中的硬件的集成逻辑电路或者软件形式的指令完成。上述的处理器可以是通用处理器、数字信号处理器(DSP)、专用集成电路(ASIC)、现场可编程门阵列(FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件。可以实现或者执行本申请实施例中的公开的各方法、步骤 及逻辑框图。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。结合本申请实施例所公开的方法的步骤可以直接体现为硬件译码处理器执行完成,或者用译码处理器中的硬件及软件模块组合执行完成。软件模块可以位于随机存储器,闪存、只读存储器,可编程只读存储器或者电可擦写可编程存储器、寄存器等本领域成熟的存储介质中。该存储介质位于存储器,处理器读取存储器中的信息,结合其硬件完成上述方法的步骤。
可以理解,本申请实施例中的存储器可以是易失性存储器或非易失性存储器,或可包括易失性和非易失性存储器两者。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。易失性存储器可以是随机存取存储器(random access memory,RAM),其用作外部高速缓存。通过示例性但不是限制性说明,许多形式的RAM可用,例如静态随机存取存储器(static RAM,SRAM)、动态随机存取存储器(dynamic RAM,DRAM)、同步动态随机存取存储器(synchronous DRAM,SDRAM)、双倍数据速率同步动态随机存取存储器(double data rate SDRAM,DDR SDRAM)、增强型同步动态随机存取存储器(enhanced SDRAM,ESDRAM)、同步连接动态随机存取存储器(synchlink DRAM,SLDRAM)和直接内存总线随机存取存储器(direct rambus RAM,DR RAM)。应注意,本文描述的系统和方法的存储器旨在包括但不限于这些和任意其它适合类型的存储器。
根据本申请实施例提供的方法,本申请还提供一种计算机程序产品,该计算机程序产品包括:计算机程序代码,当该计算机程序代码在计算机上运行时,使得该计算机执行图3和图9所示实施例中第一设备和第二设备分别执行的方法,或者执行图10至图11所示实施例中终端设备和网络设备分别执行的方法。
根据本申请实施例提供的方法,本申请还提供一种计算机可读介质,该计算机可读介质存储有程序代码,当该程序代码在计算机上运行时,使得该计算机执行图3和图9所示实施例中第一设备和第二设备分别执行的方法,或者执行图10至图11所示实施例中终端设备和网络设备分别执行的方法。
根据本申请实施例提供的方法,本申请还提供一种系统,其包括前述的一个或多个第一设备以及一个或第二设备。其中,第一设备可以是终端设备,第二设备可以是网络设备;或者,第一设备可以是网络设备,第二设备可以是终端设备。
上述各个装置实施例中网络设备与终端设备和方法实施例中的网络设备或终端设备完全对应,由相应的模块或单元执行相应的步骤,例如通信单元(收发器)执行方法实施例中接收或发送的步骤,除发送、接收外的其它步骤可以由处理单元(处理器)执行。具体单元的功能可以参考相应的方法实施例。其中,处理器可以为一个或多个。
在本说明书中使用的术语“部件”、“模块”、“系统”等用于表示计算机相关的实体、硬件、固件、硬件和软件的组合、软件、或执行中的软件。例如,部件可以是但不限于,在处理器上运行的进程、处理器、对象、可执行文件、执行线程、程序和/或计算机。通过图示,在计算设备上运行的应用和计算设备都可以是部件。一个或多个部件可驻留在进程和/或执行线程中,部件可位于一个计算机上和/或分布在2个或更多个计算机之间。此外,这些部件可从在上面存储有各种数据结构的各种计算机可读介质执行。部件可例如 根据具有一个或多个数据分组(例如来自与本地系统、分布式系统和/或网络间的另一部件交互的二个部件的数据,例如通过信号与其它系统交互的互联网)的信号通过本地和/或远程进程来通信。
本领域普通技术人员可以意识到,结合本文中所公开的实施例描述的各种说明性逻辑块(illustrative logical block)和步骤(step),能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行,取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能,但是这种实现不应认为超出本申请的范围。
所属领域的技术人员可以清楚地了解到,为描述的方便和简洁,上述描述的系统、装置和单元的具体工作过程,可以参考前述方法实施例中的对应过程,在此不再赘述。
在本申请所提供的几个实施例中,应该理解到,所揭露的系统、装置和方法,可以通过其它的方式实现。例如,以上所描述的装置实施例仅仅是示意性的,例如,所述单元的划分,仅仅为一种逻辑功能划分,实际实现时可以有另外的划分方式,例如多个单元或组件可以结合或者可以集成到另一个系统,或一些特征可以忽略,或不执行。另一点,所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口,装置或单元的间接耦合或通信连接,可以是电性,机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的,作为单元显示的部件可以是或者也可以不是物理单元,即可以位于一个地方,或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外,在本申请各个实施例中的各功能单元可以集成在一个处理单元中,也可以是各个单元单独物理存在,也可以两个或两个以上单元集成在一个单元中。
在上述实施例中,各功能单元的功能可以全部或部分地通过软件、硬件、固件或者其任意组合来实现。当使用软件实现时,可以全部或部分地以计算机程序产品的形式实现。所述计算机程序产品包括一个或多个计算机指令(程序)。在计算机上加载和执行所述计算机程序指令(程序)时,全部或部分地产生按照本申请实施例所述的流程或功能。所述计算机可以是通用计算机、专用计算机、计算机网络、或者其他可编程装置。所述计算机指令可以存储在计算机可读存储介质中,或者从一个计算机可读存储介质向另一个计算机可读存储介质传输,例如,所述计算机指令可以从一个网站站点、计算机、服务器或数据中心通过有线(例如同轴电缆、光纤、数字用户线(digital subscriber line,DSL))或无线(例如红外、无线、微波等)方式向另一个网站站点、计算机、服务器或数据中心进行传输。所述计算机可读存储介质可以是计算机能够存取的任何可用介质或者是包含一个或多个可用介质集成的服务器、数据中心等数据存储设备。所述可用介质可以是磁性介质,(例如,软盘、硬盘、磁带)、光介质(例如,高密度数字视频光盘(digital video disc,DVD))、或者半导体介质(例如固态硬盘(solid state disk,SSD))等。
所述功能如果以软件功能单元的形式实现并作为独立的产品销售或使用时,可以存储在一个计算机可读取存储介质中。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或者该技术方案的部分可以以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中,包括若干指令用以使得一台计算机设备(可以是个人计算机,服务器,或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而 前述的存储介质包括:U盘、移动硬盘、只读存储器(read-only memory,ROM)、随机存取存储器(random access memory,RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述,仅为本申请的具体实施方式,但本申请的保护范围并不局限于此,任何熟悉本技术领域的技术人员在本申请揭露的技术范围内,可轻易想到变化或替换,都应涵盖在本申请的保护范围之内。因此,本申请的保护范围应以所述权利要求的保护范围为准。

Claims (85)

  1. 一种获取信道信息的方法,其特征在于,包括:
    第一设备向第二设备发送第一参考信号,所述第一参考信号的密度小于或等于第二参考信号的密度,所述第二参考信号是常规密度参考信号;
    所述第一设备接收来自所述第二设备的第一信道状态信息CSI;在所述第一参考信号的密度小于所述第二参考信号的密度的情况下,所述第一CSI是所述第二设备根据所述第一参考信号获得的;或者,在所述第一参考信号的密度等于所述第二参考信号的密度的情况下,所述第一CSI是所述第二设备根据所述第一参考信号的一部分获得的;
    所述第一设备基于所述第一CSI和第一神经网络模型获得第二CSI,所述第二CSI用于指示所述第一设备与所述第二设备之间的信道信息。
  2. 根据权利要求1所述的方法,其特征在于,在所述第一设备向第二设备发送第一参考信号之前,所述方法还包括:
    所述第一设备确定所述第一神经网络模型,具体包括:
    所述第一设备向所述第二设备发送所述第二参考信号;
    所述第一设备接收来自所述第二设备的第三CSI,所述第三CSI是所述第二设备根据所述第二参考信号获得的;
    所述第一设备基于所述第三CSI训练神经网络以获得所述第一神经网络模型。
  3. 根据权利要求1或2所述的方法,其特征在于,所述方法还包括:
    在达到预设触发条件时,所述第一设备对所述第一神经网络模型进行更新,具体包括:
    所述第一设备向所述第二设备发送第三参考信号,所述第三参考信号是常规密度参考信号;
    所述第一设备接收来自所述第二设备的第四CSI,所述第四CSI是所述第二设备根据所述第三参考信号获得的;
    所述第一设备基于所述第四CSI训练神经网络以获得更新后的第一神经网络模型。
  4. 根据权利要求3所述的方法,其特征在于,
    所述预设触发条件是第一定时器超时,所述第一定时器是在所述第一设备向所述第二设备发送所述第一参考信号时启动的;或者
    所述预设触发条件是所述第一设备确定所述第二设备解调第一数据的解调性能低于预设门限,所述第一数据是所述第一设备根据所述第二CSI发送的;或者
    所述预设触发条件是所述第一设备接收到来自所述第二设备的第一请求消息,所述第一请求消息用于请求更新所述第一神经网络模型。
  5. 根据权利要求1至4中任一项所述的方法,其特征在于,在所述第一设备向第二设备发送第一参考信号之前,所述方法还包括:
    所述第一设备接收来自所述第二设备的第二请求消息,所述第二请求消息用于请求所述第一参考信号,所述第二请求消息还用于指示所述第一参考信号的密度。
  6. 根据权利要求1至4中任一项所述的方法,其特征在于,在所述第一设备向第二设备发送第一参考信号之前,所述方法还包括:
    所述第一设备在确定所述第一神经网络模型的情况下,向所述第二设备发送第一指示信息,所述第一指示信息用于指示所述第一参考信号的密度。
  7. 根据权利要求5所述的方法,其特征在于,
    在所述第一设备是网络设备的情况下,所述第二请求消息携带在上行控制信息UCI中;或者,
    在所述第一设备是终端设备的情况下,所述第二请求消息携带在下行控制信息DCI中。
  8. 根据权利要求6所述的方法,其特征在于,
    在所述第一设备是网络设备的情况下,所述第一指示信息携带在下行控制信息DCI中;或者,
    在所述第一设备是终端设备的情况下,所述第一指示信息携带在上行控制信息UCI中。
  9. 根据权利要求1至8中任一项所述的方法,其特征在于,在所述第一设备是网络设备的情况下,所述方法还包括:
    所述第一设备向所述第二设备发送无线资源控制RRC消息,所述RRC消息中包括所述第一参考信号的密度配置信息。
  10. 根据权利要求1至8中任一项所述的方法,其特征在于,在所述第一设备是终端设备的情况下,所述方法还包括:
    所述第一设备接收来自所述第二设备的RRC消息,所述RRC消息中包括所述第一参考信号的密度配置信息。
  11. 根据权利要求1至10中任一项所述的方法,其特征在于,在所述第一参考信号的密度小于所述第二参考信号的密度的情况下,所述第一参考信号的密度是所述第二参考信号的密度的1/2或1/4。
  12. 一种获取信道信息的方法,其特征在于,包括:
    第二设备接收来自第一设备的第一参考信号,所述第一参考信号的密度小于或等于第二参考信号的密度,所述第二参考信号是常规密度参考信号;
    所述第二设备向所述第一设备发送第一信道状态信息CSI,所述第一CSI用于通过第一神经网络模型获得第二CSI,所述第二CSI用于指示所述第一设备与所述第二设备之间的信道信息;
    其中,在所述第一参考信号的密度小于所述第二参考信号的密度的情况下,所述第一CSI是所述第二设备根据所述第一参考信号获得的;或者,在所述第一参考信号的密度等于所述第二参考信号的密度的情况下,所述第一CSI是所述第二设备根据所述第一参考信号的一部分获得的。
  13. 根据权利要求12所述的方法,其特征在于,在所述第二设备接收来自第一设备的第一参考信号之前,所述方法还包括:
    所述第二设备接收来自所述第一设备的所述第二参考信号;
    所述第二设备向所述第一设备发送第三CSI,所述第三CSI是根据所述第二参考信号获得的,所述第三CSI用于训练神经网络以获得所述第一神经网络模型。
  14. 根据权利要求12或13所述的方法,其特征在于,所述方法还包括:
    所述第二设备接收来自所述第一设备的第三参考信号,所述第三参考信号是常规密度参考信号;
    所述第二设备向所述第一设备发送第四CSI,所述第四CSI是根据所述第三参考信号获得的,所述第四CSI用于训练神经网络以获得更新后的第一神经网络模型。
  15. 根据权利要求12至14中任一项所述的方法,其特征在于,在所述第二设备接收来自第一设备的第一参考信号之前,所述方法还包括:
    所述第二设备向所述第一设备发送第二请求消息,所述第二请求消息用于请求所述第一参考信号,所述第二请求消息还用于指示所述第一参考信号的密度。
  16. 根据权利要求15所述的方法,其特征在于,所述第二设备向所述第一设备发送第二请求消息,包括:
    所述第二设备周期性地向所述第一设备发送第二请求消息;或者
    所述第二设备在接收到来自第一设备的第二指示信息的情况下,向所述第一设备发送所述第二请求消息,所述第二指示信息用于指示已确定所述第一神经网络模型。
  17. 根据权利要求12至14中任一项所述的方法,其特征在于,在所述第二设备接收来自所述第一设备的第一参考信号之前,所述方法还包括:
    所述第二设备接收来自所述第一设备的第一指示信息,所述第一指示信息用于指示所述第一参考信号的密度。
  18. 根据权利要求15或16所述的方法,其特征在于,
    在所述第二设备是终端设备的情况下,所述第二请求消息携带在上行控制信息UCI中;或者,
    在所述第二设备是网络设备的情况下,所述第二请求消息携带在下行控制信息DCI中。
  19. 根据权利要求17所述的方法,其特征在于,
    在所述第二设备是终端设备的情况下,所述第一指示信息携带在下行控制信息DCI中;或者,
    在所述第二设备是网络设备的情况下,所述第一指示信息携带在上行控制信息UCI中。
  20. 根据权利要求12至19中任一项所述的方法,其特征在于,在所述第二设备是终端设备的情况下,所述方法还包括:
    所述第二设备接收来自所述第一设备的无线资源控制RRC消息,所述RRC消息中包括所述第一参考信号的密度配置信息。
  21. 根据权利要求12至19中任一项所述的方法,其特征在于,在所述第二设备是网络设备的情况下,所述方法还包括:
    所述第二设备向所述第一设备发送RRC消息,所述RRC消息中包括所述第一参考信号的密度配置信息。
  22. 根据权利要求12至21中任一项所述的方法,其特征在于,在所述第一参考信号的密度小于所述第二参考信号的密度的情况下,所述第一参考信号的密度是所述第二参考信号的密度的1/2或1/4。
  23. 一种通信装置,其特征在于,包括收发单元和处理单元:
    所述收发单元用于向所述第二设备发送第一参考信号,所述第一参考信号的密度小于或等于第二参考信号的密度,所述第二参考信号是常规密度参考信号;
    所述收发单元还用于接收来自所述第二设备的第一信道状态信息CSI;在所述第一参考信号的密度小于所述第二参考信号的密度的情况下,所述第一CSI是所述第二设备根据所述第一参考信号获得的;或者,在所述第一参考信号的密度等于所述第二参考信号的密度的情况下,所述第一CSI是所述第二设备根据所述第一参考信号的一部分获得的;
    所述处理单元用于基于所述第一CSI和第一神经网络模型获得第二CSI,所述第二CSI用于指示所述通信装置与所述第二设备之间的信道信息。
  24. 根据权利要求23所述的通信装置,其特征在于,所述收发单元还用于向所述第二设备发送所述第二参考信号;
    所述收发单元还用于接收来自所述第二设备的第三CSI,所述第三CSI是所述第二设备根据所述第二参考信号获得的;
    所述处理单元还用于基于所述第三CSI对神经网络进行训练以获得所述第一神经网络模型。
  25. 根据权利要求23或24所述的通信装置,其特征在于,所述收发单元还用于向所述第二设备发送第三参考信号,所述第三参考信号是常规密度参考信号;
    所述收发单元还用于接收来自所述第二设备的第四CSI,所述第四CSI是所述第二设备根据所述第三参考信号获得的;
    所述处理单元还用于基于所述第四CSI训练神经网络以获得更新后的第一神经网络模型。
  26. 根据权利要求23至25中任一项所述的通信装置,其特征在于,所述收发单元还用于接收来自所述第二设备的第二请求消息,所述第二请求消息用于请求所述第一参考信号,所述第二请求消息还用于指示所述第一参考信号的密度。
  27. 根据权利要求23至25中任一项所述的通信装置,其特征在于,所述收发单元还用于在确定所述第一神经网络模型的情况下,向所述第二设备发送第一指示信息,所述第一指示信息用于指示所述第一参考信号的密度。
  28. 根据权利要求26所述的通信装置,其特征在于,
    在所述通信装置是网络设备的情况下,所述第二请求消息携带在上行控制信息UCI中;或者,
    在所述通信装置是终端设备的情况下,所述第二请求消息携带在下行控制信息DCI中。
  29. 根据权利要求27所述的通信装置,其特征在于,
    在所述通信装置是网络设备的情况下,所述第一指示信息携带在下行控制信息DCI中;或者,
    在所述通信装置是终端设备的情况下,所述第一指示信息携带在上行控制信息UCI中。
  30. 根据权利要求23至29中任一项所述的通信装置,其特征在于,在所述通信装置是网络设备的情况下,所述收发单元还用于向所述第二设备发送无线资源控制RRC消息,所述RRC消息中包括所述第一参考信号的密度配置信息。
  31. 根据权利要求23至29中任一项所述的通信装置,其特征在于,在所述通信装置是终端设备的情况下,所述方收发单元还用于接收来自所述第二设备的RRC消息,所述RRC消息中包括所述第一参考信号的密度配置信息。
  32. 根据权利要求23至31中任一项所述的通信装置,其特征在于,在所述第一参考信号的密度小于所述第二参考信号的密度的情况下,所述第一参考信号的密度是所述第二参考信号的密度的1/2或1/4。
  33. 一种通信装置,其特征在于,包括收发单元:
    所述收发单元用于接收来自第一设备的第一参考信号,所述第一参考信号的密度小于或等于第二参考信号的密度,所述第二参考信号是常规密度参考信号;
    所述收发单元还用于向所述第一设备发送第一信道状态信息CSI,所述第一CSI用于通过第一神经网络模型获得第二CSI,所述第二CSI用于指示所述第一设备与所述通信装置之间的信道信息;
    其中,在所述第一参考信号的密度小于所述第二参考信号的密度的情况下,所述第一CSI是所述第二设备根据所述第一参考信号获得的;或者,在所述第一参考信号的密度等于所述第二参考信号的密度的情况下,所述第一CSI是所述第二设备根据所述第一参考信号的一部分获得的。
  34. 根据权利要求33所述的方通信装置,其特征在于,所述收发单元还用于接收来自第一设备的第二参考信号;
    所述收发单元还用于向所述第一设备发送第三CSI,所述第三CSI是所述第二设备根据所述第二参考信号获得的,所述第三CSI用于对神经网络进行训练以获得所述第一神经网络模型。
  35. 根据权利要求33或34所述的通信装置,其特征在于,所述收发单元还用于接收来自第一设备的第三参考信号;
    所述收发单元还用于向所述第一设备发送第四CSI,所述第四CSI是所述第二设备根据所述第三参考信号获得的,所述第四CSI用于训练神经网络以获得更新后的第一神经网络模型。
  36. 根据权利要求33至35中任一项所述的通信装置,其特征在于,所述收发单元还用于向所述第一设备发送第二请求消息,所述第二请求消息用于请求所述第一参考信号,所述第二请求消息还用于指示所述第一参考信号的密度。
  37. 根据权利要求36所述的通信装置,其特征在于,所述收发单元具体用于:
    周期性地向所述第一设备发送第二请求消息;或者
    在接收到来自第一设备的第二指示信息的情况下,向所述第一设备发送所述第二请求消息,所述第二指示信息用于指示已确定所述第一神经网络模型。
  38. 根据权利要求33至35中任一项所述的通信装置,其特征在于,所述收发单元还用于接收来自所述第一设备的第一指示信息,所述第一指示信息用于指示所述第一参考信号的密度。
  39. 根据权利要求36或37所述的通信装置,其特征在于,
    在所述通信装置是终端设备的情况下,所述第二请求消息携带在上行控制信息UCI中;或者,
    在所述通信装置是网络设备的情况下,所述第二请求消息携带在下行控制信息DCI中。
  40. 根据权利要求38所述的通信装置,其特征在于,
    在所述通信装置是终端设备的情况下,所述第一指示信息携带在下行控制信息DCI中;或者,
    在所述通信装置是网络设备的情况下,所述第一指示信息携带在上行控制信息UCI中。
  41. 根据权利要求33至40中任一项所述的通信装置,其特征在于,在所述通信装置是终端设备的情况下,所述收发单元还用于接收来自所述第一设备的无线资源控制RRC消息,所述RRC消息中包括所述第一参考信号的密度配置信息。
  42. 根据权利要求33至40中任一项所述的通信装置,其特征在于,在所述通信装置是网络设备的情况下,所述收发单元还用于向所述第一设备发送RRC消息,所述RRC消息中包括所述第一参考信号的密度配置信息。
  43. 根据权利要求33至42中任一项所述的通信装置,其特征在于,在所述第一参考信号的密度小于所述第二参考信号的密度的情况下,所述第一参考信号的密度是所述第二参考信号的密度的1/2或1/4。
  44. 一种获取信道信息的方法,其特征在于,包括:
    第二设备接收来自第一设备的第一参考信号,所述第一参考信号的密度小于第二参考信号的密度,所述第二参考信号是常规密度参考信号;
    所述第二设备根据第一信道状态信息CSI和第二神经网络模型获得第二CSI,所述第二CSI用于指示所述第一设备与所述第二设备之间的信道信息,所述第一CSI是根据所述第一参考信号获得的;
    所述第二设备向所述第一设备发送所述第二CSI。
  45. 根据权利要求44所述的方法,其特征在于,在所述第二设备接收来自第一设备的第一参考信号之前,所述方法还包括:
    所述第二设备确定所述第二神经网络模型,具体包括:
    所述第二设备接收来自所述第一设备的所述第二参考信号;
    所述第二设备基于第三CSI对神经网络进行训练以获得所述第二神经网络模型,所述第三CSI是根据所述第二参考信号获得的。
  46. 根据权利要求44或45所述的方法,其特征在于,所述方法还包括:
    在达到预设触发条件时,所述第二设备对所述第二神经网络模型进行更新,具体包括:
    所述第二设备接收来自所述第一设备的第三参考信号;
    所述第二设备基于第四CSI对神经网络进行训练以获得更新后的第二神经网络模型,所述第四CSI是根据所述第三参考信号获得的。
  47. 根据权利要求46所述的方法,其特征在于,
    所述预设触发条件是第二定时器超时,所述第二定时器是所述第二设备接收到来自所述第一设备的所述第一参考信号时启动的;或者,
    所述预设触发条件是所述第二设备确定解调第一数据的解调性能低于预设门限,所述第一数据是所述第一设备根据所述第二CSI发送的。
  48. 根据权利要求44至47中任一项所述的方法,其特征在于,在所述第二设备接收来自第一设备的第一参考信号之前,所述方法还包括:
    所述第二设备在神经网络训练完成的情况下,向所述第一设备发送第二请求消息,所述第二请求消息用于请求所述第一参考信号,所述第二请求消息还用于指示所述第一参考信号的密度。
  49. 根据权利要求44至47中任一项所述的方法,其特征在于,在所述第二设备接收来自第一设备的第一参考信号之前,所述方法还包括:
    所述第二设备接收来自所述第一设备的第一指示信息,所述第一指示信息用于指示所述第一参考信号的密度。
  50. 根据权利要求48所述的方法,其特征在于,
    在所述第二设备是终端设备的情况下,所述第二请求消息携带在上行控制信息UCI中;或者,
    在所述第二设备是网络设备的情况下,所述第二请求消息携带在下行控制信息DCI中。
  51. 根据权利要求49所述的方法,其特征在于,
    在所述第二设备是终端设备的情况下,所述第一指示信息携带在下行控制信息DCI中;或者,
    在所述第二设备是网络设备的情况下,所述第一指示信息携带在上行控制信息UCI中。
  52. 根据权利要求44至51中任一项所述的方法,其特征在于,在所述第二设备是终端设备的情况下,所述方法还包括:
    所述第二设备接收来自所述第一设备的无线资源控制RRC消息,所述RRC消息中包括所述第一参考信号的密度配置信息。
  53. 根据权利要求44至52中任一项所述的方法,其特征在于,
    所述第一参考信号的密度是所述第二参考信号的密度的1/2或1/4。
  54. 一种获取信道信息的方法,其特征在于,包括:
    第一设备向第二设备发送第一参考信号,所述第一参考信号的密度小于第二参考信号的密度,所述第二参考信号是常规密度参考信号,所述第一参考信号用于获得第一信道状态信息CSI,所述第一CSI用于通过第二神经网络模型获得第二CSI,所述第二CSI用于指示所述第一设备与所述第二设备之间的信道信息;
    所述第一设备接收来自所述第二设备的第二CSI。
  55. 根据权利要求54所述的方法,其特征在于,在所述第一设备向第二设备发送第一参考信号之前,所述方法还包括:
    所述第一设备向所述第二设备发送所述第二参考信号,所述第二参考信号用于获得第三CSI,所述第三CSI用于训练神经网络以获得所述第二神经网络模型。
  56. 根据权利要求54或55所述的方法,其特征在于,所述方法还包括:
    所述第一设备向所述第二设备发送第三参考信号,所述第三参考信号用于获得第四CSI,所述第四CSI用于训练神经网络以获得更新后的第二神经网络模型。
  57. 根据权利要求54至56中任一项所述的方法,其特征在于,在所述第一设备向第 二设备发送第一参考信号之前,所述方法还包括:
    所述第一设备接收来自所述第二设备的第二请求消息,所述第二请求消息用于请求所述第一参考信号,所述第二请求消息还用于指示所述第一参考信号的密度。
  58. 根据权利要求54至56中任一项所述的方法,其特征在于,在所述第一设备向第二设备发送第一参考信号之前,所述方法还包括:
    所述第一设备向所述第二设备发送第一指示信息,所述第一指示信息用于指示所述第一参考信号的密度。
  59. 根据权利要求58所述的方法,其特征在于,所述第一设备向所述第二设备发送第一指示信息,包括:
    所述第一设备周期性地向所述第二设备发送所述第一指示信息;或者
    所述第一设备在接收到来自所述第二设备的第三指示信息的情况下,向所述第二设备发送所述第一指示信息,所述第三指示信息用于指示已确定所述第二神经网络模型。
  60. 根据权利要求57所述的方法,其特征在于,
    在所述第一设备是网络设备的情况下,所述第二请求消息携带在上行控制信息UCI中;或者,
    在所述第一设备是终端设备的情况下,所述第二请求消息携带在下行控制信息DCI中。
  61. 根据权利要求58或59所述的方法,其特征在于,
    在所述第一设备是网络设备的情况下,所述第一指示信息携带在下行控制信息DCI中;或者,
    在所述第一设备是终端设备的情况下,所述第一指示信息携带在上行控制信息UCI中。
  62. 根据权利要求54至61中任一项所述的方法,其特征在于,在所述第一设备是终端设备的情况下,所述方法还包括:
    所述第一设备接收来自所述第二设备的无线资源控制RRC消息,所述RRC消息中包括所述第一参考信号的密度配置信息。
  63. 根据权利要求54至62中任一项所述的方法,其特征在于,
    所述第一参考信号的密度是所述第二参考信号的密度的1/2或1/4。
  64. 一种通信装置,其特征在于,包括收发单元和处理单元:
    所述收发单元用于接收来自第一设备的第一参考信号,所述第一参考信号的密度小于第二参考信号的密度,所述第二参考信号是常规密度参考信号;
    所述处理单元用于根据第一信道状态信息CSI和第二神经网络模型获得第二CSI,所述第二CSI用于指示所述第一设备与所述第二设备之间的信道信息,所述第一CSI是根据所述第一参考信号获得的;
    所述收发单元还用于向所述第一设备发送所述第二CSI。
  65. 根据权利要求64所述的通信装置,其特征在于,
    所述收发单元还用于接收来自所述第一设备的所述第二参考信号;
    所述处理单元还用于基于第三CSI对神经网络进行训练以获得所述第二神经网络模型,所述第三CSI是根据所述第二参考信号获得的。
  66. 根据权利要求64或65所述的通信装置,其特征在于,
    所述收发单元还用于接收来自所述第一设备的第三参考信号;
    所述处理单元还用于基于第四CSI对神经网络进行训练以获得更新后的第二神经网络模型,所述第四CSI是根据所述第三参考信号获得的。
  67. 根据权利要求64至66中任一项所述的通信装置,其特征在于,
    所述收发单元还用于在神经网络训练完成的情况下,向所述第一设备发送第二请求消息,所述第二请求消息用于请求所述第一参考信号,所述第二请求消息还用于指示所述第一参考信号的密度。
  68. 根据权利要求64至66中任一项所述的通信装置,其特征在于,
    所述收发单元还用于接收来自所述第一设备的第一指示信息,所述第一指示信息用于指示所述第一参考信号的密度。
  69. 根据权利要求67所述的通信装置,其特征在于,
    在所述通信装置是终端设备的情况下,所述第二请求消息携带在上行控制信息UCI中;或者,
    在所述通信装置是网络设备的情况下,所述第二请求消息携带在下行控制信息DCI中。
  70. 根据权利要求68所述的通信装置,其特征在于,
    在所述通信装置备是终端设备的情况下,所述第一指示信息携带在下行控制信息DCI中;或者,
    在所述通信装置是网络设备的情况下,所述第一指示信息携带在上行控制信息UCI中。
  71. 根据权利要求64至70中任一项所述的通信装置,其特征在于,在所述通信装置是终端设备的情况下,所述收发单元还用于接收来自所述第一设备的无线资源控制RRC消息,所述RRC消息中包括所述第一参考信号的密度配置信息。
  72. 根据权利要求64至71中任一项所述的通信装置,其特征在于,
    所述第一参考信号的密度是所述第二参考信号的密度的1/2或1/4。
  73. 一种通信装置,其特征在于,包括收发单元:
    所述收发单元用于向第二设备发送第一参考信号,所述第一参考信号的密度小于第二参考信号的密度,所述第二参考信号是常规密度参考信号,所述第一参考信号用于获得第一信道状态信息CSI,所述第一CSI用于通过第二神经网络模型获得第二CSI,所述第二CSI用于指示所述第一设备与所述第二设备之间的信道信息;
    所述收发单元还用于接收来自所述第二设备的第二CSI。
  74. 根据权利要求73所述的通信装置,其特征在于,
    所述收发单元还用于向所述第二设备发送所述第二参考信号,所述第二参考信号用于获得第三CSI,所述第三CSI用于训练神经网络以获得所述第二神经网络模型。
  75. 根据权利要求73或74所述的通信装置,其特征在于,
    所述收发单元还用于向所述第二设备发送第三参考信号,所述第三参考信号用于获得第四CSI,所述第四CSI用于训练神经网络以获得更新后的第二神经网络模型。
  76. 根据权利要求74至75中任一项所述的通信装置,其特征在于,
    所述收发单元还用于接收来自所述第二设备的第二请求消息,所述第二请求消息用于请求所述第一参考信号,所述第二请求消息还用于指示所述第一参考信号的密度。
  77. 根据权利要求74至75中任一项所述的通信装置,其特征在于,
    所述收发单元还用于向所述第二设备发送第一指示信息,所述第一指示信息用于指示所述第一参考信号的密度。
  78. 根据权利要求76所述的通信装置,其特征在于,
    在所述通信装置是网络设备的情况下,所述第二请求消息携带在上行控制信息UCI中;或者,
    在所述通信装置是终端设备的情况下,所述第二请求消息携带在下行控制信息DCI中。
  79. 根据权利要求77所述的通信装置,其特征在于,
    在所述通信装置是网络设备的情况下,所述第一指示信息携带在下行控制信息DCI中;或者,
    在所述通信装置是终端设备的情况下,所述第一指示信息携带在上行控制信息UCI中。
  80. 根据权利要求74至79中任一项所述的通信装置,其特征在于,在所述通信装置是终端设备的情况下,所述收发单元还用于接收来自所述第二设备的无线资源控制RRC消息,所述RRC消息中包括所述第一参考信号的密度配置信息。
  81. 根据权利要求74至80中任一项所述的通信装置,其特征在于,
    所述第一参考信号的密度是所述第二参考信号的密度的1/2或1/4。
  82. 一种通信装置,其特征在于,包括至少一个处理器,所述至少一个处理器用于执行存储器中存储的计算机指令,以使得所述通信装置实现如权利要求1至22中任一项所述的方法,或者以使得所述通信装置实现如权利要求44至63中任一项所述的方法。
  83. 一种计算机可读存储介质,所述计算机可读存储介质存储有计算机指令,其特征在于,当所述计算机指令被计算设备执行时,使得如权利要求1至22中任一项所述的方法被执行,或者使得如权利要求44至63中任一项所述的方法被执行。
  84. 一种包含指令的计算机程序产品,当其在计算上运行时,使得如权利要求1至22中任一项所述的方法被执行,或者使得如权利要求44至63中任一项所述的方法被执行。
  85. 一种通信系统,包括权利要求23至32任一项所述的通信装置和权利要求33至43任一项所述的通信装置,或者包括权利要求64至72任一项所述的通信装置和权利要求73至81任一项所述的通信装置。
PCT/CN2021/095488 2020-06-03 2021-05-24 获取信道信息的方法及通信装置 WO2021244344A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US18/074,237 US20230109063A1 (en) 2020-06-03 2022-12-02 Method for obtaining channel information and communications apparatus

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010493592.0 2020-06-03
CN202010493592.0A CN113765830B (zh) 2020-06-03 2020-06-03 获取信道信息的方法及通信装置

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US18/074,237 Continuation US20230109063A1 (en) 2020-06-03 2022-12-02 Method for obtaining channel information and communications apparatus

Publications (1)

Publication Number Publication Date
WO2021244344A1 true WO2021244344A1 (zh) 2021-12-09

Family

ID=78783199

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/095488 WO2021244344A1 (zh) 2020-06-03 2021-05-24 获取信道信息的方法及通信装置

Country Status (3)

Country Link
US (1) US20230109063A1 (zh)
CN (2) CN116248446A (zh)
WO (1) WO2021244344A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2024016145A1 (en) * 2022-07-19 2024-01-25 Qualcomm Incorporated Indication of channel state information reference signal pattern for machine learning-assisted channel state information schemes

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116830466A (zh) * 2021-01-29 2023-09-29 高通股份有限公司 使用神经网络模型确定信道状态信息的技术
US12101206B2 (en) * 2021-07-26 2024-09-24 Qualcomm Incorporated Signaling for additional training of neural networks for multiple channel conditions
US20230113557A1 (en) * 2021-10-07 2023-04-13 Qualcomm Incorporated Derivation of channel features using a subset of channel ports
CN118511452A (zh) * 2022-01-14 2024-08-16 Oppo广东移动通信有限公司 基于机器学习的csi测量和报告的方法与系统
WO2024045148A1 (en) * 2022-09-02 2024-03-07 Qualcomm Incorporated Reference signal pattern association for channel estimation
CN117715106A (zh) * 2022-09-07 2024-03-15 维沃移动通信有限公司 信息传输方法、ai网络模型训练方法、装置和通信设备
CN117811627A (zh) * 2022-09-30 2024-04-02 华为技术有限公司 一种通信的方法和通信装置

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105007126A (zh) * 2014-04-23 2015-10-28 电信科学技术研究院 一种信道状态信息测量的方法、系统及设备
CN105519181A (zh) * 2013-09-25 2016-04-20 日电(中国)有限公司 用于无线通信系统中的上行链路数据传输的方法和装置
CN105850065A (zh) * 2013-09-25 2016-08-10 诺基亚通信管理国际两合公司 信道估计相关的参数的配置
US20190281660A1 (en) * 2018-05-24 2019-09-12 Jie Cui Methods to adapt a frequency density of channel state information reference signal (csi-rs) resources for beam failure detection (bfd) in new radio (nr) systems

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3429257B1 (en) * 2014-03-06 2020-05-13 Huawei Technologies Co., Ltd. Method for reporting channel state information, user equipment, and base station
US11317418B2 (en) * 2016-09-22 2022-04-26 Guangdong Oppo Mobile Telecommunications Corp., Ltd. Communication method and communication apparatus
CN112291050B (zh) * 2017-06-16 2024-06-18 华为技术有限公司 传输信息的方法和装置
CN108566257B (zh) * 2018-04-27 2020-08-18 电子科技大学 一种基于反向传播神经网络的信号恢复方法
CN111049615B (zh) * 2018-10-15 2021-01-05 华为技术有限公司 处理信号的方法和装置
CN110061946B (zh) * 2019-03-28 2021-11-16 南京邮电大学 一种面向高铁的深度信号检测方法
CN110166089B (zh) * 2019-05-24 2021-06-04 西华大学 基于深度学习的叠加编码csi反馈方法

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105519181A (zh) * 2013-09-25 2016-04-20 日电(中国)有限公司 用于无线通信系统中的上行链路数据传输的方法和装置
CN105850065A (zh) * 2013-09-25 2016-08-10 诺基亚通信管理国际两合公司 信道估计相关的参数的配置
CN105007126A (zh) * 2014-04-23 2015-10-28 电信科学技术研究院 一种信道状态信息测量的方法、系统及设备
US20190281660A1 (en) * 2018-05-24 2019-09-12 Jie Cui Methods to adapt a frequency density of channel state information reference signal (csi-rs) resources for beam failure detection (bfd) in new radio (nr) systems

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2024016145A1 (en) * 2022-07-19 2024-01-25 Qualcomm Incorporated Indication of channel state information reference signal pattern for machine learning-assisted channel state information schemes

Also Published As

Publication number Publication date
CN113765830A (zh) 2021-12-07
CN116248446A (zh) 2023-06-09
CN113765830B (zh) 2022-12-27
US20230109063A1 (en) 2023-04-06

Similar Documents

Publication Publication Date Title
WO2021244344A1 (zh) 获取信道信息的方法及通信装置
WO2021083068A1 (zh) 上报信道状态信息的方法和通信装置
CN108365997B (zh) 一种信息传输方法和装置
WO2019191932A1 (zh) 上行天线的选择方法和装置
WO2021052473A1 (zh) 通信方法和通信装置
EP4243492A1 (en) Data transmission method and apparatus
WO2021083157A1 (zh) 一种预编码矩阵的处理方法和通信装置
US20230013510A1 (en) Method for indicating channel state information csi measurement and communication apparatus
US20230078895A1 (en) Uplink reference signal sending method, uplink reference signal receiving method, and communication apparatus
WO2022227033A1 (zh) 无线通信方法、终端设备和网络设备
WO2024067244A1 (zh) 数据发送的方法和装置
US20230239028A1 (en) Channel measurement method and communication apparatus
WO2021072602A1 (zh) 链路失败检测的方法和装置
WO2022012256A1 (zh) 通信的方法及通信装置
US20200014436A1 (en) Communication Method, Network Device, and Terminal Device
WO2022193260A1 (zh) 无线通信方法、终端设备和网络设备
WO2022213328A1 (zh) 侧行链路资源配置的方法和通信装置
WO2022077142A1 (zh) 物理上行共享信道发送的方法和通信装置
WO2022056870A1 (zh) 无线通信方法、终端设备和网络设备
WO2024093646A1 (zh) 一种资源配置的方法和装置
WO2024061093A1 (zh) 一种上行预编码的指示方法及通信装置
WO2024140409A1 (zh) 一种信道状态信息csi报告的配置方法及相关装置
WO2024140774A1 (zh) 一种通信方法及装置
WO2024168716A1 (zh) 信道状态信息发送和接收方法、装置和通信系统
WO2021207895A1 (zh) 一种用于传输上行信号的方法和通信装置

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: 21817075

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21817075

Country of ref document: EP

Kind code of ref document: A1