WO2021142836A1 - 通信方法及装置 - Google Patents

通信方法及装置 Download PDF

Info

Publication number
WO2021142836A1
WO2021142836A1 PCT/CN2020/073020 CN2020073020W WO2021142836A1 WO 2021142836 A1 WO2021142836 A1 WO 2021142836A1 CN 2020073020 W CN2020073020 W CN 2020073020W WO 2021142836 A1 WO2021142836 A1 WO 2021142836A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
terminal device
channel state
sent
channel
Prior art date
Application number
PCT/CN2020/073020
Other languages
English (en)
French (fr)
Inventor
田杰娇
田文强
陈文洪
Original Assignee
Oppo广东移动通信有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Oppo广东移动通信有限公司 filed Critical Oppo广东移动通信有限公司
Priority to CN202080092149.0A priority Critical patent/CN115280682A/zh
Priority to EP20913745.4A priority patent/EP4092918A4/en
Priority to PCT/CN2020/073020 priority patent/WO2021142836A1/zh
Publication of WO2021142836A1 publication Critical patent/WO2021142836A1/zh
Priority to US17/812,695 priority patent/US20220352952A1/en

Links

Images

Classifications

    • 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]
    • 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
    • H04B7/0417Feedback systems
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04BTRANSMISSION
    • H04B17/00Monitoring; Testing
    • H04B17/30Monitoring; Testing of propagation channels
    • H04B17/391Modelling the propagation channel
    • 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
    • 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
    • H04B7/0636Feedback format
    • H04B7/0645Variable feedback
    • 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
    • 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
    • H04L5/00Arrangements affording multiple use of the transmission path
    • H04L5/0001Arrangements for dividing the transmission path
    • H04L5/0014Three-dimensional division
    • H04L5/0023Time-frequency-space
    • 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
    • H04L5/0053Allocation of signaling, i.e. of overhead other than pilot signals
    • 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
    • H04L5/0053Allocation of signaling, i.e. of overhead other than pilot signals
    • H04L5/0057Physical resource allocation for CQI
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/04Architecture, e.g. interconnection topology
    • G06N3/045Combinations of networks
    • 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
    • H04L5/005Allocation of pilot signals, i.e. of signals known to the receiver of common pilots, i.e. pilots destined for multiple users or terminals

Definitions

  • the present invention relates to the field of communication technology, and in particular to a communication method and device.
  • the feedback of channel state information can determine the performance of multiple-in multiple-out (MIMO) transmission.
  • MIMO multiple-in multiple-out
  • network devices usually pre-configure some configuration parameters for channel state information measurement, such as synchronization signal block (Synchronization Signal block, SSB) or channel state information configuration parameters (Channel-State Information Reference Signal, CSI-RS) ), the terminal device measures the channel state according to the configuration parameters sent by the network device, determines the current channel state information, and feeds back the current channel state information to the network device, so that the network device can configure a reasonable and efficient data transmission method based on the current channel state information.
  • synchronization signal block Synchronation Signal block
  • CSI-RS Channel State Information Reference Signal
  • the embodiments of the present invention provide a communication method and device to solve the problem that channel resources cannot be accurately scheduled in a communication system in the prior art.
  • the first aspect of the present invention provides a communication method, including:
  • the first information is used to indicate whether the network device obtains downlink channel information through the artificial intelligence algorithm model, the artificial intelligence algorithm model is based on historical uplink channel information and historical downlink channel information for sample training establishment of.
  • the method further includes:
  • the method further includes:
  • the types of the channel state information include a first type and a second type, and the amount of information reported for the first type is less than or equal to the amount of information reported for the second type.
  • the second information is used to instruct the terminal device to use the first type to report the channel state information
  • the second information is used to instruct the terminal device to use the second type to report the channel state information.
  • the method further includes:
  • the method further includes:
  • a downlink precoding matrix is generated according to the downlink channel information.
  • the method further includes:
  • the uplink channel information is input into the artificial intelligence algorithm model, and the downlink channel information output by the artificial intelligence algorithm model is obtained.
  • the first information is sent to the terminal device through broadcast information
  • the first information is sent to the terminal device through a random access process
  • the first information is sent to the terminal device through radio resource control RRC dedicated signaling;
  • the first information is sent to the terminal device through a media access control control unit MAC-CE;
  • the first information is sent to the terminal device through downlink control information DCI.
  • the at least one channel state configuration parameter is sent to the terminal device through broadcast information or radio resource control RRC dedicated signaling.
  • the second information is sent to the terminal device through a random access process
  • the second information is sent to the terminal device through radio resource control RRC dedicated signaling;
  • the second information is sent to the terminal device through a media access control control unit MAC-CE;
  • the artificial intelligence algorithm model includes: a deep learning model and/or a machine learning model.
  • the deep learning model includes a convolutional neural network module
  • the machine learning model includes at least one of the following models: a classification algorithm model, a regression algorithm model, a clustering algorithm model, and a dimensionality reduction algorithm model .
  • Receive first information sent by a network device the first information is used to indicate whether the network device obtains downlink channel information through an artificial intelligence algorithm model, the artificial intelligence algorithm model is based on historical uplink channel information and historical downlink channel information as sample training built;
  • the measuring the channel state according to the first information to obtain channel state information includes:
  • the types of the channel state information include a first type and a second type, and the amount of information reported for the first type is less than or equal to the amount of information reported for the second type.
  • the second information is used to instruct the terminal device to use the first type to report the channel state information
  • the second information is used to instruct the terminal device to use the second type to report the channel state information.
  • the first information is also used to indicate whether the network device has channel reciprocity.
  • the first information is sent to the terminal device through broadcast information
  • the first information is sent to the terminal device through a random access process
  • the first information is sent to the terminal device through radio resource control RRC dedicated signaling;
  • the first information is sent to the terminal device through a media access control control unit MAC-CE;
  • the first information is sent to the terminal device through downlink control information DCI.
  • the at least one channel state configuration parameter is sent to the terminal device through broadcast information or radio resource control RRC dedicated signaling.
  • the second information is sent to the terminal device through broadcast information
  • the second information is sent to the terminal device through a random access process
  • the second information is sent to the terminal device through radio resource control RRC dedicated signaling;
  • the second information is sent to the terminal device through a media access control control unit MAC-CE;
  • the second information is sent to the terminal device through downlink control information DCI.
  • the artificial intelligence algorithm model includes: a deep learning model and/or a machine learning model.
  • the deep learning model includes a convolutional neural network module
  • the machine learning model includes at least one of the following models: a classification algorithm model, a regression algorithm model, a clustering algorithm model, and a dimensionality reduction algorithm model .
  • a third aspect of the present invention provides a communication device, including:
  • the sending module is configured to send first information to the terminal device, the first information is used to indicate whether the network device obtains downlink channel information through an artificial intelligence algorithm model, the artificial intelligence algorithm model is based on historical uplink channel information and historical downlink channel Information is established for sample training.
  • the sending module is further configured to send at least one channel state information configuration parameter to the terminal device, and the at least one channel state information configuration parameter is used for the terminal device according to the The first information determines the target configuration parameters, performs channel state measurement, and obtains channel state information;
  • the configuration parameters of different channel states have different time-frequency resources and/or different port densities.
  • the sending module is further configured to send second information to the terminal device, and the second information is used to indicate the type of channel state information reported by the terminal device.
  • the types of the channel state information include a first type and a second type, and the amount of information reported for the first type is less than or equal to the amount of information reported for the second type.
  • the second information is used to instruct the terminal device to use the first type to report the channel state information
  • the second information is used to instruct the terminal device to use the second type to report the channel state information.
  • the device further includes: a receiving module and a processing module;
  • the receiving module is configured to receive the channel state information reported by the terminal device according to the second information
  • the sending module is also used to transmit the encoded data to the terminal device.
  • the processing module is further configured to, if the downlink channel information is obtained through the artificial intelligence algorithm model and the downlink channel information is complete, generate downlink precoding according to the downlink channel information matrix.
  • the receiving module is further configured to receive uplink channel information sent by the terminal device;
  • the processing module is further configured to input the uplink channel information into the artificial intelligence algorithm model, and obtain downlink channel information output by the artificial intelligence algorithm model.
  • the first information is also used to indicate whether the network device has channel reciprocity.
  • the first information is sent to the terminal device through broadcast information
  • the first information is sent to the terminal device through a random access process
  • the first information is sent to the terminal device through radio resource control RRC dedicated signaling;
  • the first information is sent to the terminal device through a media access control control unit MAC-CE;
  • the first information is sent to the terminal device through downlink control information DCI.
  • the at least one channel state configuration parameter is sent to the terminal device through broadcast information or radio resource control RRC dedicated signaling.
  • the second information is sent to the terminal device through broadcast information
  • the second information is sent to the terminal device through a random access process
  • the second information is sent to the terminal device through radio resource control RRC dedicated signaling;
  • the second information is sent to the terminal device through a media access control control unit MAC-CE;
  • the second information is sent to the terminal device through downlink control information DCI.
  • the artificial intelligence algorithm model includes: a deep learning model and/or a machine learning model.
  • the deep learning model includes a convolutional neural network module
  • the machine learning model includes at least one of the following models: a classification algorithm model, a regression algorithm model, a clustering algorithm model, and a dimensionality reduction algorithm model .
  • a fourth aspect of the present invention provides a communication device, including:
  • the receiving module is configured to receive first information sent by a network device, the first information is used to indicate whether the network device obtains downlink channel information through an artificial intelligence algorithm model, which is based on historical uplink channel information and history Downlink channel information is established for sample training;
  • the processing module is configured to measure the channel state according to the first information, and obtain channel state information.
  • the receiving module is further configured to receive at least one configuration parameter of channel state information sent by the network device, where the configuration parameters of different channel states have different time-frequency resources and/or port densities. different;
  • the processing module is specifically configured to determine a target configuration parameter from the configuration parameters of the at least one channel state information according to the first information, perform channel state measurement, and obtain channel state information.
  • the receiving module is specifically configured to receive second information sent by the network device, and the second information is used to indicate the type of channel state information reported by the terminal device;
  • the device also includes: a sending module
  • the sending module is configured to report the channel state information to the network device according to the type of the channel state information indicated by the second information.
  • the types of channel state information include a first type and a second type, and the amount of information reported for the first type is less than or equal to the amount of information reported for the second type.
  • the second information is used to instruct the terminal device to use the first type to report the channel state information
  • the first information is also used to indicate whether the network device has channel reciprocity.
  • the first information is sent to the terminal device through broadcast information
  • the first information is sent to the terminal device through a random access process
  • the first information is sent to the terminal device through radio resource control RRC dedicated signaling;
  • the first information is sent to the terminal device through a media access control control unit MAC-CE;
  • the first information is sent to the terminal device through downlink control information DCI.
  • the at least one channel state configuration parameter is sent to the terminal device through broadcast information or radio resource control RRC dedicated signaling.
  • the second information is sent to the terminal device through broadcast information
  • the second information is sent to the terminal device through a random access process
  • the second information is sent to the terminal device through radio resource control RRC dedicated signaling;
  • the second information is sent to the terminal device through a media access control control unit MAC-CE;
  • the second information is sent to the terminal device through downlink control information DCI.
  • the artificial intelligence algorithm model includes: a deep learning model and/or a machine learning model.
  • the deep learning model includes a convolutional neural network module
  • the machine learning model includes at least one of the following models: a classification algorithm model, a regression algorithm model, a clustering algorithm model, and a dimensionality reduction algorithm model .
  • a fifth aspect of the present invention provides a network device.
  • the terminal device includes a processor, a memory, a transmitter, and a receiver; the transmitter and the receiver are coupled to the processor, and the processor controls The sending action of the transmitter, and the processor controlling the receiving action of the receiver;
  • the memory is used to store computer executable program code, and the program code includes information; when the processor executes the information, the information causes the terminal device to execute the communication provided in the first aspect and the possible implementation manners of the first aspect. method.
  • a sixth aspect of the present invention provides a terminal device.
  • the terminal device includes a processor, a memory, a transmitter, and a receiver; the transmitter and the receiver are coupled to the processor, and the processor controls The sending action of the transmitter, and the processor controlling the receiving action of the receiver;
  • the memory is used to store computer executable program code, and the program code includes information; when the processor executes the information, the information causes the network device to execute the communication method provided in the second aspect and the possible implementation manners of the second aspect .
  • a seventh aspect of the present invention provides a chip, including: a processor, configured to call and run a computer program from a memory, so that the device installed with the chip executes the possible implementation manners of the first aspect and the first aspect The communication method provided.
  • An eighth aspect of the present invention provides a chip, including: a processor, configured to call and run a computer program from a memory, so that the device installed with the chip executes the possible implementation manners of the second aspect and the second aspect The communication method provided.
  • a ninth aspect of the present invention provides a computer-readable storage medium for storing a computer program that enables a computer to execute the communication method provided in the first aspect and each possible implementation manner of the first aspect.
  • a tenth aspect of the present invention provides a computer-readable storage medium for storing a computer program that enables a computer to execute the communication method provided in each possible implementation manner of the second aspect and the third aspect.
  • the eleventh aspect of the present invention provides a computer program product, including computer program information, which enables a computer to execute the communication method provided in the first aspect and each possible implementation manner of the first aspect.
  • the twelfth aspect of the present invention provides a computer program product, including computer program information, which enables a computer to execute the communication method provided by the second aspect and each possible implementation manner of the second aspect.
  • the thirteenth aspect of the present invention provides a computer program that enables a computer to execute the communication method provided in the first aspect and each possible implementation manner of the first aspect.
  • the fourteenth aspect of the present invention provides a computer program that enables a computer to execute the communication method provided in the second aspect and each possible implementation manner of the second aspect.
  • a network device sends first information to a terminal device.
  • the first information is used to indicate whether the network device obtains downlink channel information through an artificial intelligence algorithm model.
  • the artificial intelligence algorithm model is based on historical uplink channel information.
  • historical downlink channel information is established for sample training.
  • the terminal device measures the channel state according to the first information, and obtains the channel state information. In this way, the terminal device can learn the way the network device obtains the downlink channel information, and the terminal device can use the corresponding parameters to measure the channel state according to the different ways the network device obtains the downlink channel information, reducing the number of channels obtained by the measurement.
  • the error of the state information can realize the accurate scheduling of channel resources in the communication system.
  • FIG. 1 is a schematic diagram of a scenario of a communication method provided by an embodiment of this application.
  • FIG. 2 is a signaling interaction diagram of a communication method provided by an embodiment of this application.
  • Figure 3 is a signaling interaction diagram of another communication method provided by an embodiment of the application.
  • FIG. 4 is a signaling interaction diagram of still another communication method provided by an embodiment of this application.
  • FIG. 5 is a signaling interaction diagram of another communication method provided by an embodiment of this application.
  • FIG. 6 is a schematic structural diagram of a communication device provided by an embodiment of this application.
  • FIG. 7 is a schematic structural diagram of another communication device provided by an embodiment of this application.
  • FIG. 8 is a schematic structural diagram of a network device provided by an embodiment of this application.
  • FIG. 9 is a schematic structural diagram of a terminal device provided by an embodiment of the application.
  • the feedback of channel state information can determine the performance of multiple-in multiple-out (MIMO) transmission.
  • MIMO multiple-in multiple-out
  • network devices usually pre-configure some configuration parameters for channel state information measurement, such as synchronization signal block (Synchronization Signal block, SSB) or channel state information configuration parameters (Channel-State Information Reference Signal, CSI-RS) ), the terminal device measures the channel state according to the configuration parameters sent by the network device, determines the current channel state information, and feeds back the current channel state information to the network device, so that the network device can configure a reasonable and efficient data transmission method based on the current channel state information.
  • synchronization signal block Synchronation Signal block
  • CSI-RS Channel State Information Reference Signal
  • the network device informs the terminal device whether to obtain downlink channel information through the artificial intelligence algorithm model by sending the first information to the terminal device, so that the terminal device can measure the channel state according to the first information, thereby reducing the measured value.
  • the error of the channel state information can realize the accurate scheduling of channel resources in the communication system.
  • FIG. 1 is a schematic diagram of a scenario of a communication method provided by an embodiment of the application.
  • the terminal device 101 and the network device 102 communicate with each other.
  • the network device 102 After the network device 102 obtains the downlink channel information, it can send information to the terminal device 101 to instruct the network device 102 to obtain the downlink channel information.
  • the embodiment of the present application does not limit the number of terminal devices 101 and network devices 102 included in the communication system.
  • the terminal device 101 may also be called a terminal, a user equipment (UE), a mobile station (mobile station, MS), a mobile terminal (mobile terminal, MT), and so on.
  • the terminal device 101 may be a mobile phone (mobile phone), a tablet computer (pad), a computer with wireless transceiver function, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, and an industrial control (industrial control) terminal device.
  • Wireless terminal in control wireless terminal in self-driving (self-driving), wireless terminal in remote medical surgery, wireless terminal in smart grid (smart grid), smart home (smart home) Wireless terminal, etc.
  • the network device 102 may, for example, be a base station, or various wireless access points, or may refer to a device that communicates with user equipment through one or more sectors on the air interface in the network.
  • the base station can be used to convert received air frames and IP packets into each other, and act as a router between the wireless terminal and the rest of the network, where the rest of the network can include an Internet Protocol (IP) network.
  • IP Internet Protocol
  • the base station can also coordinate the attribute management of the air interface.
  • the base station can be a base station (BTS) in global system of mobile communication (GSM) or code division multiple access (CDMA), or it can be a broadband code division multiple access (BTS).
  • GSM global system of mobile communication
  • CDMA code division multiple access
  • BTS broadband code division multiple access
  • the base station (NodeB, NB) in wideband code division multiple Access (WCDMA) can also be an evolved base station (evolutional nodeB, eNB or eNodeB) in long term evolution (LTE), or a relay station or access point. Or the base station gNB in the future 5G network, etc., is not limited here.
  • Figure 2 is a signaling interaction diagram of a communication method provided by an embodiment of the application. This embodiment relates to the process of how the terminal device and the network device interact. As shown in Figure 2, the method includes:
  • the network device sends first information to the terminal device.
  • the first information is used to indicate whether the network device obtains downlink channel information through the artificial intelligence algorithm model.
  • the artificial intelligence algorithm model is based on historical uplink channel information and historical downlink channel information as a sample training establishment. of.
  • the network device may send the first information to the terminal device according to whether the downlink channel information is obtained through the artificial intelligence algorithm model.
  • the embodiment of the present application does not limit the types of artificial intelligence algorithm models, and the artificial intelligence algorithm models may include: deep learning models and/or machine learning models.
  • the deep learning model may include a convolutional neural network module
  • the machine learning model may include at least one of the following models: a classification algorithm model, a regression algorithm model, a clustering algorithm model, and a dimensionality reduction algorithm model.
  • the downlink channel information is acquired through the artificial intelligence algorithm model, and the network device can take the uplink channel information as input, and output the downlink channel information through the trained artificial intelligence algorithm model.
  • the uplink channel information can be obtained from channel sounding configuration parameters (sounding reference signal, SRS).
  • the use of artificial intelligence algorithm model to obtain downlink channel information can better avoid the problem of large errors between the CSI information after restoration and the real CSI information in the traditional model and codebook-based CSI feedback mechanism.
  • manual The intelligent algorithm model can achieve the purpose of saving uplink signaling overhead and downlink resource overhead.
  • the network device can receive the uplink channel information sent by the terminal device, and input the uplink channel information into the artificial intelligence algorithm model, thereby Obtain the downlink channel information output by the artificial intelligence algorithm model.
  • the first information may be sent to the terminal device through broadcast information.
  • the broadcast information may include a master information block (Master information block, MIB), a system information block (system information block, SIB) 1, and other SIB messages.
  • the first information may be sent to the terminal device through a random access procedure.
  • a random access procedure such as a message sent by a network device in a two-step random access process, or a random access response or contention resolution message sent by a network device in a four-step random access process.
  • the first information may be sent to the terminal device through radio resource control (radio resource control, RRC) dedicated signaling.
  • radio resource control radio resource control
  • the first information may be sent to the terminal device through a media access control control element (MAC-CE).
  • MAC-CE media access control control element
  • the first information may be sent to the terminal device through downlink control information (DCI).
  • DCI downlink control information
  • the first information may also be used to indicate whether the network device has channel reciprocity, that is, whether the channel fading experienced by the uplink and downlink transmission signals is the same.
  • S202 The terminal device measures the channel state according to the first information, and obtains channel state information.
  • the terminal device after the terminal device receives the first information sent from the network device, it can measure the channel state according to the first information to obtain channel state information.
  • the network device may send at least one channel state configuration parameter (channel-state information reference signal, CSI-RS) to the terminal device in advance, and there is a mapping relationship between the CSI-RS and the manner of acquiring downlink channel information.
  • the terminal device may select a target CSI-RS from multiple CSI-RSs to perform channel state according to the first information, and obtain channel state information.
  • the terminal device may be preset with two channel state measurement methods, and the two measurement methods respectively correspond to the demonstration of obtaining downlink channel information through the artificial intelligence algorithm model. After receiving the first information, the terminal device can select one of the two measurement methods to perform channel state measurement through the indication of the first information, and the measurement parameters of the two measurement methods are different.
  • first information can not only be used to measure the channel state, but also can be used in any scenario where the manner in which the network device obtains the downlink channel information needs to be learned, and the embodiment without application will not restrict this.
  • a network device sends first information to a terminal device.
  • the first information is used to indicate whether the network device obtains downlink channel information through an artificial intelligence algorithm model.
  • the artificial intelligence algorithm model is based on historical uplink channel information and history.
  • Downlink channel information is established for sample training.
  • the terminal device measures the channel state according to the first information, and obtains the channel state information. In this way, the terminal device can learn the way the network device obtains the downlink channel information, and the terminal device can use the corresponding parameters to measure the channel state according to the different ways the network device obtains the downlink channel information, reducing the number of channels obtained by the measurement.
  • the error of the state information can realize the accurate scheduling of channel resources in the communication system.
  • Figure 3 is a signaling interaction diagram of another communication method provided by an embodiment of the application. As shown in Figure 3, the communication method includes:
  • the network device sends first information to the terminal device.
  • the first information is used to indicate whether the network device obtains downlink channel information through the artificial intelligence algorithm model.
  • the artificial intelligence algorithm model is based on historical uplink channel information and historical downlink channel information as a sample training establishment. of.
  • the network device sends at least one channel state information configuration parameter to the terminal device, where the at least one channel state information configuration parameter is used for the terminal device to determine the target configuration parameter according to the first information to perform channel state measurement and obtain channel state information;
  • the configuration parameters of different channel states have different time-frequency resources and/or different port densities.
  • the network device may send at least one channel state information configuration parameter when the terminal device first accesses. In some embodiments, the network device may send at least one configuration parameter of channel state information after sending the first information to the terminal device. In other embodiments, the network device may send at least one configuration parameter of channel state information before sending the first information to the terminal device.
  • the embodiment of the present application also does not limit the number of configuration parameters of the channel state information, and can be specifically set according to actual conditions.
  • At least one channel state configuration parameter is sent to the terminal device through broadcast information or RRC dedicated signaling.
  • the broadcast information may include master information block (Master information block, MIB), system information block (system information block, SIB) 1, and other SIB messages;
  • RRC dedicated signaling is used to transmit configuration parameters , Such as RRC reconfiguration message.
  • S303 According to the first information, determine the target configuration parameter from the configuration parameters of the at least one channel state information, perform channel state measurement, and obtain channel state information.
  • the terminal device determines that the current CSI-RS transmission adopts the configuration parameters of the first CSI-RS.
  • the configuration parameters may adopt a lower granularity to achieve the purpose of saving downlink signal overhead. For example, a CSI-RS configuration parameter with a longer period, a lower density, or a smaller number of ports may be used.
  • the terminal device determines that the current CSI-RS transmission adopts the configuration parameters of the second CSI-RS, and the configuration parameters of the second CSI-RS are configured Higher granularity can be used to improve the accuracy of CSI measurement, for example, a shorter period, higher density, or more port number of CSI-RS configuration parameters can be used.
  • a network device sends at least one configuration parameter of channel state information to a terminal device, and determines the target configuration parameter from the configuration parameter of the at least one channel state information according to the first information, performs channel state measurement, and obtains the channel state information.
  • the corresponding state measurement method can be adopted according to the specific method of obtaining the downlink channel information, so that when the artificial intelligence algorithm model is used to obtain the downlink channel information, the downlink signal overhead can be saved, and the artificial intelligence algorithm model is not used to obtain the downlink channel.
  • Information improve the accuracy of CSI measurement, thereby reducing the signal overhead while reducing the error of the measured channel state information, so as to achieve accurate scheduling of channel resources in the communication system.
  • FIG. 4 is a signaling interaction diagram of yet another communication method provided by an embodiment of the application. As shown in Figure 4, the communication method includes:
  • the network device sends first information to the terminal device.
  • the first information is used to indicate whether the network device obtains downlink channel information through the artificial intelligence algorithm model.
  • the artificial intelligence algorithm model is based on historical uplink channel information and historical downlink channel information as a sample training establishment. of.
  • the terminal device measures the channel state according to the first information, and obtains channel state information.
  • S401-S402 can be understood with reference to S201-S202 shown in FIG. 2, and the repeated content will not be repeated here.
  • the network device sends second information to the terminal device, where the second information is used to indicate the type of channel state information reported by the terminal device.
  • the network device may also send second information to the terminal device to instruct the terminal device to report the type of channel state information.
  • the types of channel state information include a first type and a second type, and the amount of information reported for the first type is less than or equal to the amount of information reported for the second type.
  • the first type may be a reduced CSI report type
  • the second type may be a conventional CSI report type, the CSI report amount of the reduced CSI report method and the conventional CSI report method, the periodic configuration used, the bearer channel, etc.
  • the configuration is different.
  • the reported amount of the reduced CSI reporting method is one of the following combinations: channel quality indicator (CQI); CRI (CSI-RS); rank indicator (rank indicator, RI); CRI (CSI-RS)+CQI; CRI +RI; CQI+RI.
  • the reported amount of the conventional CSI reporting method is one of the following combinations: CRI+RI+precoding matrix indicator (PMI)+CQI; CRI+RI+i1; CRI+RI+i1+CQI; CRI+RI+CQI; CRI+ configuration parameter receiving power (Reference Signal Receiving Power, RSRP); SSB RI+RSRP; CRI+RI+LI+PMI+CQI.
  • PMI precoding matrix indicator
  • CRI+i1 CRI+RI+i1
  • CRI+RI+i1+CQI CRI+RI+CQI
  • CRI+ configuration parameter receiving power Reference Signal Receiving Power, RSRP
  • SSB RI+RSRP CRI+RI+LI+PMI+CQI.
  • the reduced CSI report type may use periodic physical uplink control channels to report channel state information.
  • the conventional CSI report type may use a physical uplink control channel or a physical uplink shared channel to report channel state information.
  • the second information is used to instruct the terminal device to use the first type to report channel state information; if the artificial intelligence algorithm model is not used to obtain the downlink channel information , The second information is used to instruct the terminal device to use the second type to report channel state information.
  • the integrity of the downlink channel information can also be verified. If the integrity exceeds the threshold, the terminal device is instructed to use the first type to report channel state information. Correspondingly, if the downlink channel information is obtained through the artificial intelligence algorithm model and the downlink channel information is complete, then the downlink precoding matrix is directly generated according to the downlink channel information to perform information transmission.
  • the second information may be sent to the terminal device through broadcast information.
  • the broadcast information may include a master information block (Master information block, MIB), a system information block (system information block, SIB) 1, and other SIB messages.
  • the second information may be sent to the terminal device through a random access procedure.
  • a random access procedure such as a message sent by a network device in a two-step random access process, or a random access response or contention resolution message sent by a network device in a four-step random access process.
  • the second information may be sent to the terminal device through radio resource control (radio resource control, RRC) dedicated signaling.
  • radio resource control radio resource control
  • the second information may be sent to the terminal device through a media access control control element (MAC-CE)
  • MAC-CE media access control control element
  • the second information may be sent to the terminal device through downlink control information (DCI).
  • DCI downlink control information
  • S404 The terminal device reports the channel state information to the network device according to the type of the channel state information indicated by the second information.
  • the communication method provided in the embodiments of the present application sends second information to the terminal device through the network device.
  • the second information is used to indicate the type of channel state information reported by the terminal device, so that the terminal device uses the artificial intelligence algorithm model to obtain the downlink channel information.
  • the channel state information is reported in a reporting mode with a small amount of reporting, so that the purpose of saving signaling overhead can be achieved.
  • Figure 5 is a signaling interaction diagram of yet another communication method provided by an embodiment of the application. As shown in Figure 5, the communication method includes:
  • the network sends first information to the terminal device.
  • the first information is used to indicate whether the network device obtains downlink channel information through an artificial intelligence algorithm model.
  • the artificial intelligence algorithm model is established for sample training based on historical uplink channel information and historical downlink channel information.
  • S502 The terminal device measures the channel state according to the first information, and obtains channel state information.
  • S503 The network device sends second information to the terminal device, where the second information is used to indicate the type of channel state information reported by the terminal device.
  • S504 The terminal device reports the channel state information to the network device according to the type of the channel state information indicated by the second information.
  • S501-S504 can be understood with reference to S401-S404 shown in FIG. 4, and the repeated content will not be repeated here.
  • the network device generates a downlink precoding matrix according to the channel state information and the downlink channel information.
  • the downlink channel information and channel state information obtained by the artificial intelligence algorithm model can be sorted to obtain a complete And generate the downlink precoding matrix based on the complete downlink channel information.
  • the network device can verify the integrity of the downlink channel information after determining to obtain the downlink channel information through the artificial intelligence algorithm model. If the complete downlink channel information can be obtained through the artificial intelligence algorithm, no subsequent follow-up is required.
  • the downlink precoding matrix can be designed directly from the downlink channel information recovered by the artificial intelligence algorithm model.
  • the downlink precoding matrix is generated according to the downlink channel information.
  • S506 The network device encodes the data according to the downlink precoding matrix.
  • the data may be encoded according to the current encoding method.
  • the network device transmits the encoded data to the terminal device.
  • FIG. 6 is a schematic structural diagram of a communication device provided by an embodiment of the application.
  • the communication device may be implemented by software, hardware, or a combination of the two, and may be the network device or the chip of the network device in the foregoing embodiment.
  • the communication device 600 includes: a processing model 601, a sending module 602, and a receiving module 603.
  • the sending module 602 is used to send first information to the terminal device.
  • the first information is used to indicate whether the network device obtains downlink channel information through the artificial intelligence algorithm model.
  • the artificial intelligence algorithm model is based on historical uplink channel information and historical downlink channel information as samples Established by training.
  • the sending module 602 is further configured to send at least one channel state information configuration parameter to the terminal device, and the at least one channel state information configuration parameter is used for the terminal device to determine the target configuration parameter according to the first information.
  • Channel state measurement to obtain channel state information;
  • the configuration parameters of different channel states have different time-frequency resources and/or different port densities.
  • the sending module 602 is further configured to send second information to the terminal device, and the second information is used to indicate the type of channel state information reported by the terminal device.
  • the types of channel state information include a first type and a second type, and the amount of information reported for the first type is less than or equal to the amount of information reported for the second type.
  • the second information is used to instruct the terminal device to use the first type to report channel state information
  • the second information is used to instruct the terminal device to use the second type to report channel state information.
  • the receiving module 603 is configured to receive the channel state information reported by the terminal device according to the second information
  • the processing module 601 is configured to generate a downlink precoding matrix according to channel state information and downlink channel information; to encode data according to the downlink precoding matrix;
  • the sending module 602 is also used to transmit the encoded data to the terminal device.
  • the processing module 601 is further configured to generate a downlink precoding matrix according to the downlink channel information if the downlink channel information is obtained through the artificial intelligence algorithm model and the downlink channel information is complete.
  • the receiving module 603 is further configured to receive uplink channel information sent by the terminal device;
  • the processing module 601 is also used to input the uplink channel information into the artificial intelligence algorithm model, and obtain the downlink channel information output by the artificial intelligence algorithm model.
  • the first information is also used to indicate whether the network device has channel reciprocity.
  • the first information is sent to the terminal device through broadcast information
  • the first information is sent to the terminal device through a random access process
  • the first information is sent to the terminal device through radio resource control RRC dedicated signaling;
  • the first information is sent to the terminal device through a media access control control unit MAC-CE;
  • the first information is sent to the terminal device through downlink control information DCI.
  • At least one channel state configuration parameter is sent to the terminal device through broadcast information or radio resource control RRC dedicated signaling.
  • the second information is sent to the terminal device through broadcast information
  • the second information is sent to the terminal device through a random access process
  • the second information is sent to the terminal device through radio resource control RRC dedicated signaling;
  • the second information is sent to the terminal device through a media access control control unit MAC-CE;
  • the second information is sent to the terminal device through downlink control information DCI.
  • the artificial intelligence algorithm model includes: a deep learning model and/or a machine learning model.
  • the deep learning model includes a convolutional neural network module
  • the machine learning model includes at least one of the following models: a classification algorithm model, a regression algorithm model, a clustering algorithm model, and a dimensionality reduction algorithm model.
  • the communication device provided in the embodiment of the present application can execute the actions of the communication method on the network device side in the foregoing method embodiment, and its implementation principles and technical effects are similar, and will not be repeated here.
  • FIG. 7 is a schematic structural diagram of another communication device provided by an embodiment of this application.
  • the communication device may be implemented by software, hardware, or a combination of the two, and may be the terminal device or the chip of the terminal device in the foregoing embodiment.
  • the communication device 700 includes: a receiving module 701, a processing module 702, and a sending module 703.
  • the receiving module 701 is used to receive the first information sent by the network device.
  • the first information is used to indicate whether the network device obtains downlink channel information through the artificial intelligence algorithm model.
  • the artificial intelligence algorithm model is based on historical uplink channel information and historical downlink channel information as samples Established by training
  • the processing module 702 is configured to measure the channel state according to the first information, and obtain channel state information.
  • the receiving module 701 is further configured to receive at least one configuration parameter of channel state information sent by the network device, where the configuration parameters of different channel states have different time-frequency resources and/or different port densities;
  • the processing module 702 is specifically configured to determine a target configuration parameter from the configuration parameters of at least one channel state information according to the first information, perform channel state measurement, and obtain channel state information.
  • the receiving module 701 is specifically configured to receive the second information sent by the network device, and the second information is used to indicate the type of channel state information reported by the terminal device;
  • the sending module 703 is configured to report the channel state information to the network device according to the type of the channel state information indicated by the second information.
  • the types of channel state information include a first type and a second type, and the amount of information reported for the first type is less than or equal to the amount of information reported for the second type.
  • the second information is used to instruct the terminal device to use the first type to report channel state information
  • the second information is used to instruct the terminal device to use the second type to report channel state information.
  • the first information is also used to indicate whether the network device has channel reciprocity.
  • the first information is sent to the terminal device through broadcast information
  • the first information is sent to the terminal device through a random access process
  • the first information is sent to the terminal device through radio resource control RRC dedicated signaling;
  • the first information is sent to the terminal device through a media access control control unit MAC-CE;
  • the first information is sent to the terminal device through downlink control information DCI.
  • At least one channel state configuration parameter is sent to the terminal device through broadcast information or radio resource control RRC dedicated signaling.
  • the second information is sent to the terminal device through broadcast information
  • the second information is sent to the terminal device through a random access process
  • the second information is sent to the terminal device through radio resource control RRC dedicated signaling;
  • the second information is sent to the terminal device through a media access control control unit MAC-CE;
  • the second information is sent to the terminal device through downlink control information DCI.
  • the artificial intelligence algorithm model includes: a deep learning model and/or a machine learning model.
  • the deep learning model includes a convolutional neural network module
  • the machine learning model includes at least one of the following models: a classification algorithm model, a regression algorithm model, a clustering algorithm model, and a dimensionality reduction algorithm model.
  • the communication device provided in the embodiment of the present application can execute the actions of the communication method on the terminal device side in the foregoing method embodiment, and its implementation principles and technical effects are similar, and will not be repeated here.
  • FIG. 8 is a schematic structural diagram of a network device provided by an embodiment of this application.
  • the network device may include: a processor 81 (such as a CPU) and a memory 82; the memory 82 may include a high-speed RAM memory, or may also include a non-volatile memory NVM, such as at least one disk memory, the memory 82 Various information can be stored in it to complete various processing functions and implement the method steps of the embodiments of the present application.
  • the network device involved in the embodiment of the present application may further include: a power supply 85, a communication bus 86, and a communication port 87.
  • the communication bus 86 is used to implement communication connections between components.
  • the aforementioned communication port 87 is used to implement connection and communication between the network device and other peripherals.
  • the above-mentioned memory 82 is used to store computer executable program code, and the program code includes information; when the processor 81 executes the information, the information causes the processor 81 to perform the processing actions of the network device in the above-mentioned method embodiment, which The realization principle and technical effect are similar, so I won't repeat them here.
  • FIG. 9 is a schematic structural diagram of a terminal device provided by an embodiment of the application.
  • the terminal device may include: a processor 91 (for example, a CPU), a memory 92, a receiver 93, and a transmitter 94; the receiver 93 and the transmitter 94 are coupled to the processor 91, and the processor 91 controls the receiver In the receiving operation of 93, the processor 91 controls the transmitting operation of the transmitter 94.
  • the memory 92 may include a high-speed RAM memory, or may also include a non-volatile memory NVM, such as at least one disk memory.
  • the memory 92 may store various information for completing various processing functions and implementing the methods of the embodiments of the present application. step.
  • the terminal device involved in the embodiment of the present application may further include: a power supply 95, a communication bus 96, and a communication port 97.
  • the receiver 93 and the transmitter 94 may be integrated in the transceiver of the terminal device, or may be independent transceiver antennas on the terminal device.
  • the communication bus 96 is used to implement communication connections between components.
  • the aforementioned communication port 97 is used to implement connection and communication between the terminal device and other peripherals.
  • the above-mentioned memory 92 is used to store computer executable program code, and the program code includes information; when the processor 91 executes the information, the information causes the processor 91 to perform the processing actions of the terminal device in the above-mentioned method embodiment, so that The transmitter 94 executes the sending action of the terminal device in the foregoing method embodiment, and causes the receiver 93 to execute the receiving action of the terminal device in the foregoing method embodiment.
  • the implementation principles and technical effects are similar, and will not be repeated here.
  • An embodiment of the present application also provides a communication system including a terminal device and a network device.
  • the terminal device executes the above-mentioned communication method on the terminal device side
  • the network device executes the above-mentioned communication method on the network device side.
  • the embodiment of the present application also provides a chip including a processor and an interface.
  • the interface is used to input and output data or instructions processed by the processor.
  • the processor is used to execute the method provided in the above method embodiment.
  • the chip can be used in terminal equipment can also be used in network equipment.
  • the present invention also provides a computer-readable storage medium.
  • the computer-readable storage medium may include: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), and a random access memory (RAM, Random Access Memory). ), magnetic disks or optical disks, and other media that can store program codes.
  • the computer-readable storage medium stores program information.
  • the program information is used for the communication method on the terminal device side or used for the network device side. Communication method.
  • the embodiment of the present application also provides a program, which is used to execute the communication method on the terminal device side or the communication method on the network device side provided in the above method embodiment when the program is executed by the processor.
  • the embodiments of the present application also provide a program product, such as a computer-readable storage medium, in which instructions are stored, which when run on a computer, cause the computer to execute the communication method on the terminal device side provided by the foregoing method embodiments, Or the communication method on the network device side.
  • a program product such as a computer-readable storage medium, in which instructions are stored, which when run on a computer, cause the computer to execute the communication method on the terminal device side provided by the foregoing method embodiments, Or the communication method on the network device side.
  • the above-mentioned embodiments it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof.
  • 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.
  • the computer program instructions When the computer program instructions are loaded and executed on the computer, the processes or functions according to the embodiments of the present invention are generated in whole or in part.
  • the computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.
  • 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.
  • computer instructions may be transmitted from a website, computer, server, or data center through a cable (such as Coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) to transmit to another website site, computer, server or data center.
  • 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 DVD), or a semiconductor medium (for example, a solid state disk (SSD)).

Landscapes

  • Engineering & Computer Science (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Power Engineering (AREA)
  • Physics & Mathematics (AREA)
  • Electromagnetism (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

本发明提供一种通信方法及装置,方法包括:网络设备向终端设备发送第一信息,第一信息用于指示网络设备是否通过人工智能算法模型获取下行信道信息,人工智能算法模型是基于历史上行信道信息和历史下行信道信息为样本训练建立的。终端设备根据第一信息测量信道状态,获取信道状态信息。通过该方式,终端设备可以获知网络设备获取下行信道信息的方式,进而终端设备可以根据网络设备获取下行信道信息的方式的不同,采用与之对应的参数进行信道状态测量,减少了测量得到的信道状态信息的误差,从而实现在通信系统中对信道资源的准确调度。

Description

通信方法及装置 技术领域
本发明涉及通信技术领域,尤其涉及一种通信方法及装置。
背景技术
在长期演进(long term evolution,LTE)系统、5G(new radio,NR)系统中,信道状态信息的反馈可以决定多进多出(multiple-in multiple-out,MIMO)传输的性能。
相关技术中,网络设备通常会预先配置一些供信道状态信息测量用的配置参数,例如同步信号块(Synchronization Signal block,SSB)或者信道状态信息的配置参数(Channel-State Information Reference Signal,CSI-RS),终端设备根据网络设备发送的配置参数测量信道状态,进而确定当前信道状态信息,并向网络设备反馈当前信道状态信息,供网络设备基于当前信道状态信息配置出合理高效的数据传输方式。
然而,在测量信道状态时,仅仅考虑反馈开销及量化等因素,往往并不能非常准确地反映出当前的信道实际状态信息,由此产生的误差并不利于未来通信系统中对信道资源的准确调度。
发明内容
本发明实施例提供一种通信方法及装置,以解决现有技术中无法在通信系统中对信道资源的准确调度的问题。
本发明的第一个方面提供一种通信方法,包括:
向终端设备发送第一信息,所述第一信息用于指示网络设备是否通过人工智能算法模型获取下行信道信息,所述人工智能算法模型是基于历史上行信道信息和历史下行信道信息为样本训练建立的。
一种可选的实施方式中,所述方法还包括:
向所述终端设备发送至少一个信道状态信息的配置参数,所述至少一个信道状态信息的配置参数用于供所述终端设备根据所述第一信息确定目标配置参数进行信道状态测量,获取信道状态信息;
其中,不同信道状态的配置参数的时频资源不同和/或端口密度不同。
一种可选的实施方式中,所述方法还包括:
向所述终端设备发送第二信息,所述第二信息用于指示所述终端设备上报信道状态信息的类型。
一种可选的实施方式中,不同的信道状态信息的类型的上报的信息量不同。
一种可选的实施方式中,所述信道状态信息的类型,包括有第一类型和第二类型,上报所述第一类型的信息量少于或等于上报所述第二类型的信息量。
一种可选的实施方式中,若通过所述人工智能算法模型获取所述下行信道信息,则所述第二信息用于指示所述终端设备使用所述第一类型上报所述信道状态信息;
若未通过所述人工智能算法模型获取所述下行信道信息,则所述第二信息用于指 示所述终端设备使用所述第二类型上报所述信道状态信息。
一种可选的实施方式中,所述方法还包括:
接收所述终端设备根据所述第二信息上报的所述信道状态信息;
根据所述信道状态信息和所述下行信道信息,生成下行预编码矩阵;
根据所述下行预编码矩阵对数据进行编码;
向所述终端设备传输编码后的数据。
一种可选的实施方式中,所述方法还包括:
若所述下行信道信息通过所述人工智能算法模型获取且所述下行信道信息完整,则根据所述下行信道信息,生成下行预编码矩阵。
一种可选的实施方式中,所述方法还包括:
接收终端设备发送的上行信道信息;
将所述上行信道信息输入所述人工智能算法模型,并获取所述人工智能算法模型输出的下行信道信息。
一种可选的实施方式中,所述第一信息还用于指示所述网络设备是否具备信道互易性。
一种可选的实施方式中,所述第一信息通过广播信息发送给所述终端设备;
或者,所述第一信息通过随机接入过程发送给所述终端设备;
或者,所述第一信息通过无线资源控制RRC专有信令发送给所述终端设备;
或者,所述第一信息通过媒体接入控制控制单元MAC-CE发送给所述终端设备;
或者,所述第一信息通过下行控制信息DCI发送给所述终端设备。
一种可选的实施方式中,所述至少一个信道状态配置参数通过广播信息或无线资源控制RRC专有信令发送给所述终端设备。
一种可选的实施方式中,所述第二信息通过广播信息发送给所述终端设备;
或者,所述第二信息通过随机接入过程发送给所述终端设备;
或者,所述第二信息通过无线资源控制RRC专有信令发送给所述终端设备;
或者,所述第二信息通过媒体接入控制控制单元MAC-CE发送给所述终端设备;
或者,所述第二信息通过下行控制信息DCI发送给所述终端设备。
一种可选的实施方式中,所述人工智能算法模型包括:深度学习模型和/或机器学习模型。
一种可选的实施方式中,所述深度学习模型包括卷积神经网络模块,所述机器学习模型包括以下至少一种模型:分类算法模型、回归算法模型、聚类算法模型和降维算法模型。
本发明的第二个方面提供一种通信方法,包括:
接收网络设备发送的第一信息,所述第一信息用于指示网络设备是否通过人工智能算法模型获取下行信道信息,所述人工智能算法模型是基于历史上行信道信息和历史下行信道信息为样本训练建立的;
根据所述第一信息测量信道状态,获取信道状态信息。
一种可选的实施方式中,所述方法还包括:
接收所述网络设备发送的至少一个信道状态信息的配置参数,其中,不同信道状态的配置参数的时频资源不同和/或端口密度不同;
所述根据所述第一信息测量信道状态,获取信道状态信息,包括:
根据所述第一信息从所述至少一个信道状态信息的配置参数中确定目标配置参数进行信道状态测量,获取信道状态信息。
一种可选的实施方式中,所述方法还包括:
接收所述网络设备发送的第二信息,所述第二信息用于指示终端设备上报信道状 态信息的类型;
通过所述第二信息指示的信道状态信息的类型,向所述网络设备上报所述信道状态信息。
一种可选的实施方式中,不同的信道状态信息的类型的上报的信息量不同。
一种可选的实施方式中,所述信道状态信息的类型,包括有第一类型和第二类型,上报所述第一类型的信息量少于或等于上报所述第二类型的信息量。
一种可选的实施方式中,若通过所述人工智能算法模型获取所述下行信道信息,则所述第二信息用于指示所述终端设备使用所述第一类型上报所述信道状态信息;
若未通过所述人工智能算法模型获取所述下行信道信息,则所述第二信息用于指示所述终端设备使用所述第二类型上报所述信道状态信息。
一种可选的实施方式中,所述第一信息还用于指示所述网络设备是否具备信道互易性。
一种可选的实施方式中,所述第一信息通过广播信息发送给终端设备;
或者,所述第一信息通过随机接入过程发送给所述终端设备;
或者,所述第一信息通过无线资源控制RRC专有信令发送给所述终端设备;
或者,所述第一信息通过媒体接入控制控制单元MAC-CE发送给所述终端设备;
或者,所述第一信息通过下行控制信息DCI发送给所述终端设备。
一种可选的实施方式中,所述至少一个信道状态配置参数通过广播信息或无线资源控制RRC专有信令发送给终端设备。
一种可选的实施方式中,所述第二信息通过广播信息发送给所述终端设备;
或者,所述第二信息通过随机接入过程发送给所述终端设备;
或者,所述第二信息通过无线资源控制RRC专有信令发送给所述终端设备;
或者,所述第二信息通过媒体接入控制控制单元MAC-CE发送给所述终端设备;
或者,所述第二信息通过下行控制信息DCI发送给所述终端设备。
一种可选的实施方式中,所述人工智能算法模型包括:深度学习模型和/或机器学习模型。
一种可选的实施方式中,所述深度学习模型包括卷积神经网络模块,所述机器学习模型包括以下至少一种模型:分类算法模型、回归算法模型、聚类算法模型和降维算法模型。
本发明第三个方面提供一种通信装置,包括:
发送模块,用于向终端设备发送第一信息,所述第一信息用于指示网络设备是否通过人工智能算法模型获取下行信道信息,所述人工智能算法模型是基于历史上行信道信息和历史下行信道信息为样本训练建立的。
一种可选的实施方式中,所述发送模块还用于向所述终端设备发送至少一个信道状态信息的配置参数,所述至少一个信道状态信息的配置参数用于供所述终端设备根据所述第一信息确定目标配置参数进行信道状态测量,获取信道状态信息;
其中,不同信道状态的配置参数的时频资源不同和/或端口密度不同。
一种可选的实施方式中,所述发送模块还用于向所述终端设备发送第二信息,所述第二信息用于指示所述终端设备上报信道状态信息的类型。
一种可选的实施方式中,不同的信道状态信息的类型的上报的信息量不同。
一种可选的实施方式中,所述信道状态信息的类型,包括有第一类型和第二类型,上报所述第一类型的信息量少于或等于上报所述第二类型的信息量。
一种可选的实施方式中,若通过所述人工智能算法模型获取所述下行信道信息,则所述第二信息用于指示所述终端设备使用所述第一类型上报所述信道状态信息;
若未通过所述人工智能算法模型获取所述下行信道信息,则所述第二信息用于指 示所述终端设备使用所述第二类型上报所述信道状态信息。
一种可选的实施方式中,所述装置还包括:接收模块和处理模块;
所述接收模块用于接收所述终端设备根据所述第二信息上报的所述信道状态信息;
处理模块用于根据所述信道状态信息和所述下行信道信息,生成下行预编码矩阵;根据所述下行预编码矩阵对数据进行编码;
所述发送模块还用于向所述终端设备传输编码后的数据。
一种可选的实施方式中,所述处理模块还用于若所述下行信道信息通过所述人工智能算法模型获取且所述下行信道信息完整,则根据所述下行信道信息,生成下行预编码矩阵。
一种可选的实施方式中,所述接收模块还用于接收终端设备发送的上行信道信息;
所述处理模块还用于将所述上行信道信息输入所述人工智能算法模型,并获取所述人工智能算法模型输出的下行信道信息。
一种可选的实施方式中,所述第一信息还用于指示所述网络设备是否具备信道互易性。
一种可选的实施方式中,所述第一信息通过广播信息发送给所述终端设备;
或者,所述第一信息通过随机接入过程发送给所述终端设备;
或者,所述第一信息通过无线资源控制RRC专有信令发送给所述终端设备;
或者,所述第一信息通过媒体接入控制控制单元MAC-CE发送给所述终端设备;
或者,所述第一信息通过下行控制信息DCI发送给所述终端设备。
一种可选的实施方式中,所述至少一个信道状态配置参数通过广播信息或无线资源控制RRC专有信令发送给所述终端设备。
一种可选的实施方式中,所述第二信息通过广播信息发送给所述终端设备;
或者,所述第二信息通过随机接入过程发送给所述终端设备;
或者,所述第二信息通过无线资源控制RRC专有信令发送给所述终端设备;
或者,所述第二信息通过媒体接入控制控制单元MAC-CE发送给所述终端设备;
或者,所述第二信息通过下行控制信息DCI发送给所述终端设备。
一种可选的实施方式中,所述人工智能算法模型包括:深度学习模型和/或机器学习模型。
一种可选的实施方式中,所述深度学习模型包括卷积神经网络模块,所述机器学习模型包括以下至少一种模型:分类算法模型、回归算法模型、聚类算法模型和降维算法模型。
本发明第四个方面提供一种通信装置,包括:
所述接收模块用于接收网络设备发送的第一信息,所述第一信息用于指示网络设备是否通过人工智能算法模型获取下行信道信息,所述人工智能算法模型是基于历史上行信道信息和历史下行信道信息为样本训练建立的;
所述处理模块用于根据所述第一信息测量信道状态,获取信道状态信息。
一种可选的实施方式中,所述接收模块还用于接收所述网络设备发送的至少一个信道状态信息的配置参数,其中,不同信道状态的配置参数的时频资源不同和/或端口密度不同;
所述处理模块具体用于根据所述第一信息从所述至少一个信道状态信息的配置参数中确定目标配置参数进行信道状态测量,获取信道状态信息。
一种可选的实施方式中,所述接收模块具体用于接收所述网络设备发送的第二信息,所述第二信息用于指示终端设备上报信道状态信息的类型;
所述装置还包括:发送模块;
所述发送模块用于通过所述第二信息指示的信道状态信息的类型,向所述网络设备上报所述信道状态信息。
一种可选的实施方式中,不同的信道状态信息的类型的上报的信息量不同。
一种可选的实施方式中,所述信道状态信息的类型,包括有第一类型和第二类型,上报所述第一类型的信息量少于或等于上报所述第二类型的信息量。
一种可选的实施方式中,若通过所述人工智能算法模型获取所述下行信道信息,则所述第二信息用于指示所述终端设备使用所述第一类型上报所述信道状态信息;
若未通过所述人工智能算法模型获取所述下行信道信息,则所述第二信息用于指示所述终端设备使用所述第二类型上报所述信道状态信息。
一种可选的实施方式中,所述第一信息还用于指示所述网络设备是否具备信道互易性。
一种可选的实施方式中,所述第一信息通过广播信息发送给终端设备;
或者,所述第一信息通过随机接入过程发送给所述终端设备;
或者,所述第一信息通过无线资源控制RRC专有信令发送给所述终端设备;
或者,所述第一信息通过媒体接入控制控制单元MAC-CE发送给所述终端设备;
或者,所述第一信息通过下行控制信息DCI发送给所述终端设备。
一种可选的实施方式中,所述至少一个信道状态配置参数通过广播信息或无线资源控制RRC专有信令发送给终端设备。
一种可选的实施方式中,所述第二信息通过广播信息发送给所述终端设备;
或者,所述第二信息通过随机接入过程发送给所述终端设备;
或者,所述第二信息通过无线资源控制RRC专有信令发送给所述终端设备;
或者,所述第二信息通过媒体接入控制控制单元MAC-CE发送给所述终端设备;
或者,所述第二信息通过下行控制信息DCI发送给所述终端设备。
一种可选的实施方式中,所述人工智能算法模型包括:深度学习模型和/或机器学习模型。
一种可选的实施方式中,所述深度学习模型包括卷积神经网络模块,所述机器学习模型包括以下至少一种模型:分类算法模型、回归算法模型、聚类算法模型和降维算法模型。
本发明第五个方面提供一种网络设备,所述终端设备包括:处理器、存储器、发送器和接收器;所述发送器和所述接收器耦合至所述处理器,所述处理器控制所述发送器的发送动作,所述处理器控制所述接收器的接收动作;
其中,存储器用于存储计算机可执行程序代码,程序代码包括信息;当处理器执行信息时,信息使所述终端设备设备执行如第一方面和第一方面的各可能的实施方式所提供的通信方法。
本发明第六个方面提供一种终端设备,所述终端设备包括:处理器、存储器、发送器和接收器;所述发送器和所述接收器耦合至所述处理器,所述处理器控制所述发送器的发送动作,所述处理器控制所述接收器的接收动作;
其中,存储器用于存储计算机可执行程序代码,程序代码包括信息;当处理器执行信息时,信息使所述网络设备执行如第二方面和第二方面的各可能的实施方式所提供的通信方法。
本发明第七个方面提供一种芯片,包括:处理器,用于从存储器中调用并运行计算机程序,使得安装有所述芯片的设备执行如第一方面和第一方面的各可能的实施方式所提供的通信方法。
本发明第八个方面提供一种芯片,包括:处理器,用于从存储器中调用并运行计算机程序,使得安装有所述芯片的设备执行如第二方面和第二方面的各可能的实施方 式所提供的通信方法。
本发明第九个方面提供一种计算机可读存储介质,用于存储计算机程序,所述计算机程序使得计算机执行如第一方面和第一方面的各可能的实施方式所提供的通信方法。
本发明第十个方面提供一种计算机可读存储介质,用于存储计算机程序,所述计算机程序使得计算机执行如第二方面和第人方面的各可能的实施方式所提供的通信方法。
本发明第十一个方面提供一种计算机程序产品,包括计算机程序信息,该计算机程序信息使得计算机执行如第一方面和第一方面的各可能的实施方式所提供的通信方法。
本发明第十二个方面提供一种计算机程序产品,包括计算机程序信息,该计算机程序信息使得计算机执行如第二方面和第二方面的各可能的实施方式所提供的通信方法。
本发明第十三个方面提供一种计算机程序,所述计算机程序使得计算机执行如第一方面和第一方面的各可能的实施方式所提供的通信方法。
本发明第十四个方面提供一种计算机程序,所述计算机程序使得计算机执行如第二方面和第二方面的各可能的实施方式所提供的通信方法。
本发明实施例提供的通信方法及装置,网络设备向终端设备发送第一信息,第一信息用于指示网络设备是否通过人工智能算法模型获取下行信道信息,人工智能算法模型是基于历史上行信道信息和历史下行信道信息为样本训练建立的。终端设备根据第一信息测量信道状态,获取信道状态信息。通过该方式,终端设备可以获知网络设备获取下行信道信息的方式,进而终端设备可以根据网络设备获取下行信道信息的方式的不同,采用与之对应的参数进行信道状态测量,减少了测量得到的信道状态信息的误差,从而实现在通信系统中对信道资源的准确调度。
附图说明
为了更清楚地说明本发明或现有技术中的技术方案,下面将对实施例或现有技术描述中所需要使用的附图作一简单地介绍,显而易见地,下面描述中的附图是本发明的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动性的前提下,还可以根据这些附图获得其他的附图。
图1为本申请实施例提供的一种通信方法的场景示意图;
图2为本申请实施例提供的一种通信方法的信令交互图;
图3为本申请实施例提供的另一种通信方法的信令交互图;
图4为本申请实施例提供的再一种通信方法的信令交互图;
图5为本申请实施例提供的又一种通信方法的信令交互图;
图6为本申请实施例提供的一种通信装置的结构示意图;
图7为本申请实施例提供的另一种通信装置的结构示意图;
图8为本申请实施例提供的一种网络设备的结构示意图;
图9为本申请实施例提供的一种终端设备的结构示意图。
具体实施方式
为使本发明的目的、技术方案和优点更加清楚,下面将结合本发明实施例中的附图,对本发明实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例是本发明一 部分实施例,而不是全部的实施例。基于本发明中的实施例,本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例,都属于本发明保护的范围。
在长期演进(long term evolution,LTE)系统、5G(new radio,NR)系统中,信道状态信息的反馈可以决定多进多出(multiple-in multiple-out,MIMO)传输的性能。
相关技术中,网络设备通常会预先配置一些供信道状态信息测量用的配置参数,例如同步信号块(Synchronization Signal block,SSB)或者信道状态信息的配置参数(Channel-State Information Reference Signal,CSI-RS),终端设备根据网络设备发送的配置参数测量信道状态,进而确定当前信道状态信息,并向网络设备反馈当前信道状态信息,供网络设备基于当前信道状态信息配置出合理高效的数据传输方式。
然而,在测量信道状态时,仅仅考虑反馈开销及量化等因素,往往并不能非常准确地反映出当前的信道实际状态信息,由此产生的误差并不利于未来通信系统中对信道资源的准确调度。
为解决上述问题,实现在通信系统中对信道资源的准确调度,需要提高信道状态信息的精度。由于不同的下行信道信息获取方法获取到的下行信息的完整度不同,一些网络设备采用人工智能算法模型获取下行信道信息,另一些网络设备不采用人工智能算法模型获取下行信道信息。终端设备选择与下行信道信息的完整度对应的参数进行信道状态测量,其测得的信道状态信息误差较小。因此,本申请中,网络设备通过向终端设备发送第一信息来告知终端设备是否通过人工智能算法模型获取下行信道信息,从而使终端设备根据第一信息进行信道状态测量,以此来减少测得的信道状态信息的误差,进而实现在通信系统中对信道资源的准确调度。
图1为本申请实施例提供的一种通信方法的场景示意图。如图1所示,终端设备101和网络设备102之间进行通信。当网络设备102获取到下行信道信息后,可以向终端设备101发送信息,指示网络设备102获取下行信道信息的方式。
其中,本申请实施例对该通信系统中包括的终端设备101和网络设备102的数量不做限定。
终端设备101,也可以称为终端Terminal、用户设备(user equipment,UE)、移动台(mobile station,MS)、移动终端(mobile terminal,MT)等。终端设备101可以是手机(mobile phone)、平板电脑(pad)、带无线收发功能的电脑、虚拟现实(virtual reality,VR)终端设备、增强现实(augmented reality,AR)终端设备、工业控制(industrial control)中的无线终端、无人驾驶(self driving)中的无线终端、远程手术(remote medical surgery)中的无线终端、智能电网(smart grid)中的无线终端、智慧家庭(smart home)中的无线终端等。
网络设备102,可例如基站,或者各种无线接入点,或者可以是指网络中在空中接口上通过一个或多个扇区与用户设备进行通信的设备。基站可用于将收到的空中帧与IP分组进行相互转换,作为无线终端与网络的其余部分之间的路由器,其中网络的其余部分可包括网际协议(IP)网络。基站还可协调对空中接口的属性管理。例如,基站可以是全球移动通讯(global system of mobile communication,GSM)或码分多址(code division multiple access,CDMA)中的基站(base transceiver station,BTS),也可以是宽带码分多址(wideband code division multiple Access,WCDMA)中的基站(NodeB,NB),还可以是长期演进(long term evolution,LTE)中的演进型基站(evolutional nodeB,eNB或eNodeB),或者中继站或接入点,或者未来5G网络中的基站gNB等,在此并不限定。
需要说明的是,本申请实施例中涉及的通信方法可以运用于多种通信系统中,本申请实施对于可运用的通信系统不做限制,可以是NR通信系统,也可以是其他通信系统。
需要说明的是,图1所示的应用场景仅仅为本申请的一个可用场景,本申请还可以运用于其他任何需要测量信道状态的场景。
下面以终端设备和网络设备为例,以具体地实施例对本申请实施例的技术方案进行详细说明。下面这几个具体的实施例可以相互结合,对于相同或相似的概念或过程可能在某些实施例不再赘述。
图2为本申请实施例提供的一种通信方法的信令交互图。本实施例涉及的是终端设备和网络设备如何进行交互的过程。如图2所示,该方法包括:
S201、网络设备向终端设备发送第一信息,第一信息用于指示网络设备是否通过人工智能算法模型获取下行信道信息,人工智能算法模型是基于历史上行信道信息和历史下行信道信息为样本训练建立的。
在本步骤中,网络设备在获取下行信道信息后,可以根据是否通过人工智能算法模型获取下行信道信息,向终端设备发送第一信息。
其中,本申请实施例对于人工智能算法模型的类型不做限制,人工智能算法模型可以包括:深度学习模型和/或机器学习模型。
示例性的,深度学习模型可以包括卷积神经网络模块,机器学习模型可以包括以下至少一种模型:分类算法模型、回归算法模型、聚类算法模型和降维算法模型。
在一些实施例中,通过人工智能算法模型获取下行信道信息,可以由网络设备将上行信道信息作为输入,通过训练好的人工智能算法模型,输出下行信道信息。该上行信道信息可以由信道探测配置参数(sounding reference signal,SRS)中获取。
在本申请中,通过人工智能算法模型获取下行信道信息,可以较好地规避传统基于模型、码本的CSI反馈机制中存在的CSI信息还原后与真实CSI信息误差较大的问题,同时,人工智能算法模型可以达到节省上行信令开销与下行资源开销的目的。
需要说明的是,本申请对于如何对人工智能算法模型进行训练不做限制,其训练样本的选取均可以根据实际情况具体设置。
在一些可选的实施方式中,若网络设备采用人工智能算法模型获取下行信道信息,则具体的,网络设备可以接收终端设备发送的上行信道信息,并将上行信道信息输入人工智能算法模型,从而获取人工智能算法模型输出的下行信道信息。
本申请实施例对于如何发送第一信息不做限制,在一些可选的实施方式中,第一信息可以通过广播信息发送给终端设备。示例性的,该广播信息可以包括主信息块(Master information block,MIB)、系统信息块(system information block,SIB)1,以及其他SIB消息。
在一些可选的实施方式中,第一信息可以通过随机接入过程发送给终端设备。示例性的,比如两步随机接入过程中的网络设备发送的消息,或者四步随机接入过程中的网络设备发送的随机接入相应或者竞争解决消息。
在一些可选的实施方式中,第一信息可以通过无线资源控制(radio resource control,RRC)专有信令发送给终端设备。
在一些可选的实施方式中,第一信息可以通过媒体接入控制控制单元(media access control-control element,MAC-CE)发送给终端设备。
在一些可选的实施方式中,第一信息可以通过下行控制信息(downlink control information,DCI)发送给终端设备。
需要说明的是,在一些实施例中,第一信息还可以用于指示网络设备是否具备信道互易性,即上行链路和下行链路的传输信号所经历的信道衰落是否是相同的。
S202、终端设备根据第一信息测量信道状态,获取信道状态信息。
在本步骤中,当终端设备接收到来自网络设备发送的第一信息后,可以根据第一信息测量信道状态,获取信道状态信息。
在一些实施例中,网络设备可以预先向终端设备发送至少一个信道状态的配置参数(channel-state information reference signal,CSI-RS),CSI-RS与获取下行信道信息 的方式存在映射关系。终端设备可以根据第一信息可以从多个CSI-RS选择目标CSI-RS进行信道状态,获取信道状态信息。
在另一些实施例中,终端设备可以预先设置有两种信道状态的测量方式,两种测量方式分别与示范通过人工智能算法模型获取下行信道信息相对应。终端设备在接收到第一信息后,可以通过第一信息的指示从两种测量方式中选择一种进行信道状态测量,两种测量方式的测量参数不同。
需要说明的是,上述第一信息不仅可以用于测量信道状态,还可以用于任何需要获知网络设备获取下行信道信息的方式的场景中,不申请实施例对此不做限制。
本申请实施例提供的通信方法,网络设备向终端设备发送第一信息,第一信息用于指示网络设备是否通过人工智能算法模型获取下行信道信息,人工智能算法模型是基于历史上行信道信息和历史下行信道信息为样本训练建立的。终端设备根据第一信息测量信道状态,获取信道状态信息。通过该方式,终端设备可以获知网络设备获取下行信道信息的方式,进而终端设备可以根据网络设备获取下行信道信息的方式的不同,采用与之对应的参数进行信道状态测量,减少了测量得到的信道状态信息的误差,从而实现在通信系统中对信道资源的准确调度。
在上述实施例的基础上,下面对于网络设备通过向终端设备发送至少一个信道状态配置参数来测量信道状态进行具体说明。图3为本申请实施例提供的另一种通信方法的信令交互图。如图3所示,该通信方法包括:
S301、网络设备向终端设备发送第一信息,第一信息用于指示网络设备是否通过人工智能算法模型获取下行信道信息,人工智能算法模型是基于历史上行信道信息和历史下行信道信息为样本训练建立的。
S301的技术名词、技术效果、技术特征,以及可选实施方式,可参照图2所示的S201理解,对于重复的内容,在此不再累述。
S302、网络设备向终端设备发送至少一个信道状态信息的配置参数,至少一个信道状态信息的配置参数用于供终端设备根据第一信息确定目标配置参数进行信道状态测量,获取信道状态信息;
其中,不同信道状态的配置参数的时频资源不同和/或端口密度不同。
本申请实施例对于网络设备何时向终端设备发送至少一个信道状态信息的配置参数不做限制,在一些实施例中,网络设备可以在终端设备初次接入时发送至少一个信道状态信息的配置参数,在一些实施例中,网络设备可以在向终端设备发送第一信息后,发送至少一个信道状态信息的配置参数。在另一些实施例中,网络设备可以在向终端设备发送第一信息之前,发送至少一个信道状态信息的配置参数。
本申请实施例对于信道状态信息的配置参数的数量也不做限制,可以根据实际情况具体设置。
在一些可选的实施方式中,至少一个信道状态配置参数通过广播信息或RRC专有信令发送给终端设备。示例性的,该广播信息可以包括主信息块(Master information block,MIB)、系统信息块(system information block,SIB)1,以及其他SIB消息;示例性的,利用RRC专有信令传输配置参数,可例如RRC重配置消息。
S303、根据第一信息,从至少一个信道状态信息的配置参数中确定目标配置参数进行信道状态测量,获取信道状态信息。
示例性的,若网络设备采用基于人工智能算法模型由上行信道信息转换获取下行信道信息,则终端设备确定当前的CSI-RS传输采用第一CSI-RS的配置参数,该第一CSI-RS的配置参数可以采用较低的颗粒度以达到节省下行信号开销的目的,可例如,采用较长的周期、较小的密度或者较少的端口数的CSI-RS的配置参数。若网络设备不采用基人工智能算法模型由上行信道信息转换获取下行信道信息,则终端设备确定 当前的CSI-RS传输采用第二CSI-RS的配置参数,该第二CSI-RS的配置参数配置可以采用较高的颗粒度以提高CSI测量的准确性,例如,采用较短的周期、较大的密度或者较多的端口数的CSI-RS的配置参数。
本申请实施例提供的通信方法,网络设备向终端设备发送至少一个信道状态信息的配置参数,根据第一信息从至少一个信道状态信息的配置参数中确定目标配置参数进行信道状态测量,获取信道状态信息。通过该方式,可以根据具体的获取下行信道信息的方式采用对应的状态测量方法,使得在采用人工智能算法模型获取下行信道信息时,可以节省下行信号开销,在不采用人工智能算法模型获取下行信道信息时,提高CSI测量的准确性,进而在减少信号开销的同时减少了测量得到的信道状态信息的误差,从而实现在通信系统中对信道资源的准确调度。
在上述实施例的基础上,在完成信道状态测量后,网络设备还可以向终端设备发送第二信息,以指示终端设备上报信道状态信息的类型。图4为本申请实施例提供的再一种通信方法的信令交互图。如图4所示,该通信方法包括:
S401、网络设备向终端设备发送第一信息,第一信息用于指示网络设备是否通过人工智能算法模型获取下行信道信息,人工智能算法模型是基于历史上行信道信息和历史下行信道信息为样本训练建立的。
S402、终端设备根据第一信息测量信道状态,获取信道状态信息。
S401-S402的技术名词、技术效果、技术特征,以及可选实施方式,可参照图2所示的S201-S202理解,对于重复的内容,在此不再累述。
S403、网络设备向终端设备发送第二信息,第二信息用于指示终端设备上报信道状态信息的类型。
在本步骤中,在终端设备测量信道状态,获取信道状态信息后,网络设备还可以向终端设备发送第二信息,指示终端设备上报信道状态信息的类型。
其中,不同的信道状态信息的类型的上报的信息量不同。
在一种可选的实施方式中,信道状态信息的类型,包括有第一类型和第二类型,上报第一类型的信息量少于或等于上报第二类型的信息量。
示例性的,第一类型可以为缩减CSI上报类型,第二类型可以为常规CSI上报类型,缩减CSI上报方式和常规CSI上报方式的CSI上报量、使用的周期性配置、承载的信道等CSI上报配置不同。缩减CSI上报方式的上报量为以下组合之一:信道质量指示(channel quality indicator,CQI);CRI(CSI-RS);秩指示(rank indicator,RI);CRI(CSI-RS)+CQI;CRI+RI;CQI+RI。常规CSI上报方式的上报量为以下组合之一:CRI+RI+预编码矩阵指示(precoding matrix indicator,PMI)+CQI;CRI+RI+i1;CRI+RI+i1+CQI;CRI+RI+CQI;CRI+配置参数接收功率(Reference Signal Receiving Power,RSRP);SSB RI+RSRP;CRI+RI+LI+PMI+CQI。
其中,缩减CSI上报类型可以采用周期性物理上行控制信道上报信道状态信息。常规CSI上报类型可以采用物理上行控制信道或者物理上行共享信道上报信道状态信息。
在一种可选的实施方式中,若通过人工智能算法模型获取下行信道信息,则第二信息用于指示终端设备使用第一类型上报信道状态信息;若未通过人工智能算法模型获取下行信道信息,则第二信息用于指示终端设备使用第二类型上报信道状态信息。
在一些实施例中,在确定通过人工智能算法模型获取下行信道信息后,还可以验证下行信道信息的完整度,若完整度超过阈值,才指示终端设备使用第一类型上报信道状态信息。相应的,若下行信道信息通过人工智能算法模型获取且下行信道信息完整,则根据下行信道信息,直接生成下行预编码矩阵,进行信息传输。
本申请实施例对于如何发送第二信息不做限制,在一些可选的实施方式中,第二 信息可以通过广播信息发送给终端设备。示例性的,该广播信息可以包括主信息块(Master information block,MIB)、系统信息块(system information block,SIB)1,以及其他SIB消息。
在一些可选的实施方式中,第二信息可以通过随机接入过程发送给终端设备。示例性的,比如两步随机接入过程中的网络设备发送的消息,或者四步随机接入过程中的网络设备发送的随机接入相应或者竞争解决消息。
在一些可选的实施方式中,第二信息可以通过无线资源控制(radio resource control,RRC)专有信令发送给终端设备。
在一些可选的实施方式中,第二信息可以通过媒体接入控制控制单元(media access control-control element,MAC-CE)发送给终端设备
在一些可选的实施方式中,第二信息可以通过下行控制信息(downlink control information,DCI)发送给终端设备。
S404、终端设备通过第二信息指示的信道状态信息的类型,向网络设备上报信道状态信息。
本申请实施例提供的通信方法,通过网络设备向终端设备发送第二信息,第二信息用于指示终端设备上报信道状态信息的类型,从而使终端设备在使用人工智能算法模型获取下行信道信息后,采用上报量较小的上报方式上报信道状态信息,从而可以达到节省信令开销的目的。
在上述实施例的基础上,下面对网络设备接收到信道状态信息后如何与终端设备传输数据进行说明。图5为本申请实施例提供的又一种通信方法的信令交互图。如图5所示,该通信方法包括:
S501网络向终端设备发送第一信息,第一信息用于指示网络设备是否通过人工智能算法模型获取下行信道信息,人工智能算法模型是基于历史上行信道信息和历史下行信道信息为样本训练建立的。
S502、终端设备根据第一信息测量信道状态,获取信道状态信息。
S503、网络设备向终端设备发送第二信息,第二信息用于指示终端设备上报信道状态信息的类型。
S504、终端设备通过第二信息指示的信道状态信息的类型,向网络设备上报信道状态信息。
S501-S504的技术名词、技术效果、技术特征,以及可选实施方式,可参照图4所示的S401-S404理解,对于重复的内容,在此不再累述。
S505、网络设备根据信道状态信息和下行信道信息,生成下行预编码矩阵。
在本步骤中,由于通过人工智能算法模型获取的下行信道信息存在一定的缺失,因此在网络设备接收到信道状态信息后,可以将人工智能算法模型获取的下行信道信息和信道状态信息整理获得完整的下行信道信息,并基于完整的下行信道信息生成下行预编码矩阵。
在一些实施例中,网络设备在确定通过人工智能算法模型获取下行信道信息后,可以对下行信道信息的完整度进行验证,若通过人工智能算法够得到完整的下行信道信息,则不需要后续的信道状态信息反馈过程,可以直接由人工智能算法模型恢复出的下行信道信息来设计下行的预编码矩阵。
在一种可选的实施方式中,若下行信道信息通过人工智能算法模型获取且下行信道信息完整,则根据下行信道信息,生成下行预编码矩阵。
S506、网络设备根据下行预编码矩阵对数据进行编码。
本申请实施例对于如何根据下行预编码矩阵对数据进行编码,可以根据现在的编码方式对数据进行编码。
S507、网络设备向终端设备传输编码后的数据。
本领域普通技术人员可以理解:实现上述方法实施例的全部或部分步骤可以通过程序信息相关的硬件来完成,前述的程序可以存储于一计算机可读取存储介质中,该程序在执行时,执行包括上述方法实施例的步骤;而前述的存储介质包括:ROM、RAM、磁碟或者光盘等各种可以存储程序代码的介质。
图6为本申请实施例提供的一种通信装置的结构示意图。该通信装置可以通过软件、硬件或者两者的结合实现,可以为上述实施例中的网络设备或网络设备的芯片。如图6所示,该通信装置600包括:处理模型601、发送模块602和接收模块603。
发送模块602,用于向终端设备发送第一信息,第一信息用于指示网络设备是否通过人工智能算法模型获取下行信道信息,人工智能算法模型是基于历史上行信道信息和历史下行信道信息为样本训练建立的。
一种可选的实施方式中,发送模块602还用于向终端设备发送至少一个信道状态信息的配置参数,至少一个信道状态信息的配置参数用于供终端设备根据第一信息确定目标配置参数进行信道状态测量,获取信道状态信息;
其中,不同信道状态的配置参数的时频资源不同和/或端口密度不同。
一种可选的实施方式中,发送模块602还用于向终端设备发送第二信息,第二信息用于指示终端设备上报信道状态信息的类型。
一种可选的实施方式中,不同的信道状态信息的类型的上报的信息量不同。
一种可选的实施方式中,信道状态信息的类型,包括有第一类型和第二类型,上报第一类型的信息量少于或等于上报第二类型的信息量。
一种可选的实施方式中,若通过人工智能算法模型获取下行信道信息,则第二信息用于指示终端设备使用第一类型上报信道状态信息;
若未通过人工智能算法模型获取下行信道信息,则第二信息用于指示终端设备使用第二类型上报信道状态信息。
一种可选的实施方式中,接收模块603用于接收终端设备根据第二信息上报的信道状态信息;
处理模块601用于根据信道状态信息和下行信道信息,生成下行预编码矩阵;根据下行预编码矩阵对数据进行编码;
发送模块602还用于向终端设备传输编码后的数据。
一种可选的实施方式中,处理模块601还用于若下行信道信息通过人工智能算法模型获取且下行信道信息完整,则根据下行信道信息,生成下行预编码矩阵。
一种可选的实施方式中,接收模块603还用于接收终端设备发送的上行信道信息;
处理模块601还用于将上行信道信息输入人工智能算法模型,并获取人工智能算法模型输出的下行信道信息。
一种可选的实施方式中,第一信息还用于指示网络设备是否具备信道互易性。
一种可选的实施方式中,第一信息通过广播信息发送给终端设备;
或者,第一信息通过随机接入过程发送给终端设备;
或者,第一信息通过无线资源控制RRC专有信令发送给终端设备;
或者,第一信息通过媒体接入控制控制单元MAC-CE发送给终端设备;
或者,第一信息通过下行控制信息DCI发送给终端设备。
一种可选的实施方式中,至少一个信道状态配置参数通过广播信息或无线资源控制RRC专有信令发送给终端设备。
一种可选的实施方式中,第二信息通过广播信息发送给终端设备;
或者,第二信息通过随机接入过程发送给终端设备;
或者,第二信息通过无线资源控制RRC专有信令发送给终端设备;
或者,第二信息通过媒体接入控制控制单元MAC-CE发送给终端设备;
或者,第二信息通过下行控制信息DCI发送给终端设备。
一种可选的实施方式中,人工智能算法模型包括:深度学习模型和/或机器学习模型。
一种可选的实施方式中,深度学习模型包括卷积神经网络模块,机器学习模型包括以下至少一种模型:分类算法模型、回归算法模型、聚类算法模型和降维算法模型。
本申请实施例提供的通信装置,可以执行上述方法实施例中网络设备侧的通信方法的动作,其实现原理和技术效果类似,在此不再赘述。
图7为本申请实施例提供的另一种通信装置的结构示意图。该通信装置可以通过软件、硬件或者两者的结合实现,可以为上述实施例中的终端设备或终端设备的芯片。如图7所示,该通信装置700包括:接收模块701和处理模块702和发送模块703。
接收模块701用于接收网络设备发送的第一信息,第一信息用于指示网络设备是否通过人工智能算法模型获取下行信道信息,人工智能算法模型是基于历史上行信道信息和历史下行信道信息为样本训练建立的;
处理模块702用于根据第一信息测量信道状态,获取信道状态信息。
一种可选的实施方式中,接收模块701还用于接收网络设备发送的至少一个信道状态信息的配置参数,其中,不同信道状态的配置参数的时频资源不同和/或端口密度不同;
处理模块702具体用于根据第一信息从至少一个信道状态信息的配置参数中确定目标配置参数进行信道状态测量,获取信道状态信息。
一种可选的实施方式中,接收模块701具体用于接收网络设备发送的第二信息,第二信息用于指示终端设备上报信道状态信息的类型;
发送模块703用于通过第二信息指示的信道状态信息的类型,向网络设备上报信道状态信息。
一种可选的实施方式中,不同的信道状态信息的类型的上报的信息量不同。
一种可选的实施方式中,信道状态信息的类型,包括有第一类型和第二类型,上报第一类型的信息量少于或等于上报第二类型的信息量。
一种可选的实施方式中,若通过人工智能算法模型获取下行信道信息,则第二信息用于指示终端设备使用第一类型上报信道状态信息;
若未通过人工智能算法模型获取下行信道信息,则第二信息用于指示终端设备使用第二类型上报信道状态信息。
一种可选的实施方式中,第一信息还用于指示网络设备是否具备信道互易性。
一种可选的实施方式中,第一信息通过广播信息发送给终端设备;
或者,第一信息通过随机接入过程发送给终端设备;
或者,第一信息通过无线资源控制RRC专有信令发送给终端设备;
或者,第一信息通过媒体接入控制控制单元MAC-CE发送给终端设备;
或者,第一信息通过下行控制信息DCI发送给终端设备。
一种可选的实施方式中,至少一个信道状态配置参数通过广播信息或无线资源控制RRC专有信令发送给终端设备。
一种可选的实施方式中,第二信息通过广播信息发送给终端设备;
或者,第二信息通过随机接入过程发送给终端设备;
或者,第二信息通过无线资源控制RRC专有信令发送给终端设备;
或者,第二信息通过媒体接入控制控制单元MAC-CE发送给终端设备;
或者,第二信息通过下行控制信息DCI发送给终端设备。
一种可选的实施方式中,人工智能算法模型包括:深度学习模型和/或机器学习模 型。
一种可选的实施方式中,深度学习模型包括卷积神经网络模块,机器学习模型包括以下至少一种模型:分类算法模型、回归算法模型、聚类算法模型和降维算法模型。
本申请实施例提供的通信装置,可以执行上述方法实施例中终端设备侧的通信方法的动作,其实现原理和技术效果类似,在此不再赘述。
图8为本申请实施例提供的一种网络设备的结构示意图。如图8所示,该网络设备可以包括:处理器81(例如CPU)和存储器82;存储器82可能包含高速RAM存储器,也可能还包括非易失性存储器NVM,例如至少一个磁盘存储器,存储器82中可以存储各种信息,以用于完成各种处理功能以及实现本申请实施例的方法步骤。可选的,本申请实施例涉及的网络设备还可以包括:电源85、通信总线86以及通信端口87。通信总线86用于实现元件之间的通信连接。上述通信端口87用于实现网络设备与其他外设之间进行连接通信。
在本申请实施例中,上述存储器82用于存储计算机可执行程序代码,程序代码包括信息;当处理器81执行信息时,信息使处理器81执行上述方法实施例中网络设备的处理动作,其实现原理和技术效果类似,在此不再赘述。
图9为本申请实施例提供的一种终端设备的结构示意图。如图9所示,该终端设备可以包括:处理器91(例如CPU)、存储器92、接收器93和发送器94;接收器93和发送器94耦合至处理器91,处理器91控制接收器93的接收动作、处理器91控制发送器94的发送动作。存储器92可能包含高速RAM存储器,也可能还包括非易失性存储器NVM,例如至少一个磁盘存储器,存储器92中可以存储各种信息,以用于完成各种处理功能以及实现本申请实施例的方法步骤。可选的,本申请实施例涉及的终端设备还可以包括:电源95、通信总线96以及通信端口97。接收器93和发送器94可以集成在终端设备的收发信机中,也可以为终端设备上独立的收发天线。通信总线96用于实现元件之间的通信连接。上述通信端口97用于实现终端设备与其他外设之间进行连接通信。
在本申请实施例中,上述存储器92用于存储计算机可执行程序代码,程序代码包括信息;当处理器91执行信息时,信息使处理器91执行上述方法实施例中终端设备的处理动作,使发送器94执行上述方法实施例中终端设备的发送动作,使接收器93执行上述方法实施例中终端设备的接收动作,其实现原理和技术效果类似,在此不再赘述。
本申请实施例还提供一种通信系统,包括终端设备和网络设备,终端设备执行上述终端设备侧的通信方法,网络设备执行上述网络设备侧的通信方法。
本申请实施例还提供了一种芯片,包括处理器和接口。其中接口用于输入输出处理器所处理的数据或指令。处理器用于执行以上方法实施例中提供的方法。该芯片可以应用于终端设备中也可以应用于网络设备中。
本发明还提供了一种计算机可读存储介质,该计算机可读存储介质可以包括:U盘、移动硬盘、只读存储器(ROM,Read-Only Memory)、随机存取存储器(RAM,Random Access Memory)、磁盘或者光盘等各种可以存储程序代码的介质,具体的,该计算机可读存储介质中存储有程序信息,程序信息用于上述终端设备侧的通信方法,或者用于上述网络设备侧的通信方法。
本申请实施例还提供一种程序,该程序在被处理器执行时用于执行以上方法实施例提供的终端设备侧的通信方法,或者网络设备侧的通信方法。
本申请实施例还提供一种程序产品,例如计算机可读存储介质,该程序产品中存储有指令,当其在计算机上运行时,使得计算机执行上述方法实施例提供的终端设备侧的通信方法,或者网络设备侧的通信方法。
在上述实施例中,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。计算机程序产品包 括一个或多个计算机指令。在计算机上加载和执行计算机程序指令时,全部或部分地产生按照本发明实施例的流程或功能。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。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,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(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。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。可用介质可以是磁性介质,(例如,软盘、硬盘、磁带)、光介质(例如,DVD)、或者半导体介质(例如固态硬盘Solid State Disk(SSD))等。
最后应说明的是:以上各实施例仅用以说明本发明的技术方案,而非对其限制;尽管参照前述各实施例对本发明进行了详细的说明,本领域的普通技术人员应当理解:其依然可以对前述各实施例所记载的技术方案进行修改,或者对其中部分或者全部技术特征进行等同替换;而这些修改或者替换,并不使相应技术方案的本质脱离本发明各实施例技术方案的范围。

Claims (60)

  1. 一种通信方法,其特征在于,包括:
    向终端设备发送第一信息,所述第一信息用于指示网络设备是否通过人工智能算法模型获取下行信道信息,所述人工智能算法模型是基于历史上行信道信息和历史下行信道信息为样本训练建立的。
  2. 根据权利要求1所述的方法,其特征在于,所述方法还包括:
    向所述终端设备发送至少一个信道状态信息的配置参数,所述至少一个信道状态信息的配置参数用于供所述终端设备根据所述第一信息确定目标配置参数进行信道状态测量,获取信道状态信息;
    其中,不同信道状态的配置参数的时频资源不同和/或端口密度不同。
  3. 根据权利要求1所述的方法,其特征在于,所述方法还包括:
    向所述终端设备发送第二信息,所述第二信息用于指示所述终端设备上报信道状态信息的类型。
  4. 根据权利要求3所述的方法,其特征在于,不同的信道状态信息的类型的上报的信息量不同。
  5. 根据权利要求4所述的方法,其特征在于,所述信道状态信息的类型,包括有第一类型和第二类型,上报所述第一类型的信息量少于或等于上报所述第二类型的信息量。
  6. 根据权利要求5所述的方法,其特征在于,若通过所述人工智能算法模型获取所述下行信道信息,则所述第二信息用于指示所述终端设备使用所述第一类型上报所述信道状态信息;
    若未通过所述人工智能算法模型获取所述下行信道信息,则所述第二信息用于指示所述终端设备使用所述第二类型上报所述信道状态信息。
  7. 根据权利要求3所述的方法,其特征在于,所述方法还包括:
    接收所述终端设备根据所述第二信息上报的所述信道状态信息;
    根据所述信道状态信息和所述下行信道信息,生成下行预编码矩阵;
    根据所述下行预编码矩阵对数据进行编码;
    向所述终端设备传输编码后的数据。
  8. 根据权利要求1所述的方法,其特征在于,所述方法还包括:
    若所述下行信道信息通过所述人工智能算法模型获取且所述下行信道信息完整,则根据所述下行信道信息,生成下行预编码矩阵。
  9. 根据权利要求1所述的方法,其特征在于,所述方法还包括:
    接收终端设备发送的上行信道信息;
    将所述上行信道信息输入所述人工智能算法模型,并获取所述人工智能算法模型输出的下行信道信息。
  10. 根据权利要求1-9任一项所述的方法,其特征在于,所述第一信息还用于指示所述网络设备是否具备信道互易性。
  11. 根据权利要求1-9任一项所述的方法,其特征在于,所述第一信息通过广播信息发送给所述终端设备;
    或者,所述第一信息通过随机接入过程发送给所述终端设备;
    或者,所述第一信息通过无线资源控制RRC专有信令发送给所述终端设备;
    或者,所述第一信息通过媒体接入控制控制单元MAC-CE发送给所述终端设备;
    或者,所述第一信息通过下行控制信息DCI发送给所述终端设备。
  12. 根据权利要求2所述的方法,其特征在于,所述至少一个信道状态配置参数通过广播信息或无线资源控制RRC专有信令发送给所述终端设备。
  13. 根据权利要求3-6任一项所述的方法,其特征在于,所述第二信息通过广播信息发送给所述终端设备;
    或者,所述第二信息通过随机接入过程发送给所述终端设备;
    或者,所述第二信息通过无线资源控制RRC专有信令发送给所述终端设备;
    或者,所述第二信息通过媒体接入控制控制单元MAC-CE发送给所述终端设备;
    或者,所述第二信息通过下行控制信息DCI发送给所述终端设备。
  14. 根据权利要求1-9任一项所述的方法,其特征在于,所述人工智能算法模型包括:深度学习模型和/或机器学习模型。
  15. 根据权利要求14所述的方法,其特征在于,所述深度学习模型包括卷积神经网络模块,所述机器学习模型包括以下至少一种模型:分类算法模型、回归算法模型、聚类算法模型和降维算法模型。
  16. 一种通信方法,其特征在于,包括:
    接收网络设备发送的第一信息,所述第一信息用于指示网络设备是否通过人工智能算法模型获取下行信道信息,所述人工智能算法模型是基于历史上行信道信息和历史下行信道信息为样本训练建立的;
    根据所述第一信息测量信道状态,获取信道状态信息。
  17. 根据权利要求16所述的方法,其特征在于,所述方法还包括:
    接收所述网络设备发送的至少一个信道状态信息的配置参数,其中,不同信道状态的配置参数的时频资源不同和/或端口密度不同;
    所述根据所述第一信息测量信道状态,获取信道状态信息,包括:
    根据所述第一信息从所述至少一个信道状态信息的配置参数中确定目标配置参数进行信道状态测量,获取信道状态信息。
  18. 根据权利要求16所述的方法,其特征在于,所述方法还包括:
    接收所述网络设备发送的第二信息,所述第二信息用于指示终端设备上报信道状态信息的类型;
    通过所述第二信息指示的信道状态信息的类型,向所述网络设备上报所述信道状态信息。
  19. 根据权利要求18所述的方法,其特征在于,不同的信道状态信息的类型的上报的信息量不同。
  20. 根据权利要求19所述的方法,其特征在于,所述信道状态信息的类型,包括有第一类型和第二类型,上报所述第一类型的信息量少于或等于上报所述第二类型的信息量。
  21. 根据权利要求20所述的方法,其特征在于,若通过所述人工智能算法模型获取所述下行信道信息,则所述第二信息用于指示所述终端设备使用所述第一类型上报所述信道状态信息;
    若未通过所述人工智能算法模型获取所述下行信道信息,则所述第二信息用于指示所述终端设备使用所述第二类型上报所述信道状态信息。
  22. 根据权利要求16-21任一项所述的方法,其特征在于,所述第一信息还用于指示所述网络设备是否具备信道互易性。
  23. 根据权利要求16-21任一项所述的方法,其特征在于,所述第一信息通过广播信息发送给终端设备;
    或者,所述第一信息通过随机接入过程发送给所述终端设备;
    或者,所述第一信息通过无线资源控制RRC专有信令发送给所述终端设备;
    或者,所述第一信息通过媒体接入控制控制单元MAC-CE发送给所述终端设备;
    或者,所述第一信息通过下行控制信息DCI发送给所述终端设备。
  24. 根据权利要求17所述的方法,其特征在于,所述至少一个信道状态配置参数通过广播信息或无线资源控制RRC专有信令发送给终端设备。
  25. 根据权利要求18-21任一项所述的方法,其特征在于,所述第二信息通过广播信息发送给所述终端设备;
    或者,所述第二信息通过随机接入过程发送给所述终端设备;
    或者,所述第二信息通过无线资源控制RRC专有信令发送给所述终端设备;
    或者,所述第二信息通过媒体接入控制控制单元MAC-CE发送给所述终端设备;
    或者,所述第二信息通过下行控制信息DCI发送给所述终端设备。
  26. 根据权利要求16-21任一项所述的方法,其特征在于,所述人工智能算法模型包括:深度学习模型和/或机器学习模型。
  27. 根据权利要求26所述的方法,其特征在于,所述深度学习模型包括卷积神经网络模块,所述机器学习模型包括以下至少一种模型:分类算法模型、回归算法模型、聚类算法模型和降维算法模型。
  28. 一种通信装置,其特征在于,包括:
    发送模块,用于向终端设备发送第一信息,所述第一信息用于指示网络设备是否通过人工智能算法模型获取下行信道信息,所述人工智能算法模型是基于历史上行信道信息和历史下行信道信息为样本训练建立的。
  29. 根据权利要求28所述的装置,其特征在于,所述发送模块还用于向所述终端设备发送至少一个信道状态信息的配置参数,所述至少一个信道状态信息的配置参数用于供所述终端设备根据所述第一信息确定目标配置参数进行信道状态测量,获取信道状态信息;
    其中,不同信道状态的配置参数的时频资源不同和/或端口密度不同。
  30. 根据权利要求28所述的装置,其特征在于,所述发送模块还用于向所述终端设备发送第二信息,所述第二信息用于指示所述终端设备上报信道状态信息的类型。
  31. 根据权利要求30所述的装置,其特征在于,不同的信道状态信息的类型的上报的信息量不同。
  32. 根据权利要求31所述的装置,其特征在于,所述信道状态信息的类型,包括有第一类型和第二类型,上报所述第一类型的信息量少于或等于上报所述第二类型的信息量。
  33. 根据权利要求32所述的装置,其特征在于,若通过所述人工智能算法模型获取所述下行信道信息,则所述第二信息用于指示所述终端设备使用所述第一类型上报所述信道状态信息;
    若未通过所述人工智能算法模型获取所述下行信道信息,则所述第二信息用于指示所述终端设备使用所述第二类型上报所述信道状态信息。
  34. 根据权利要求30所述的装置,其特征在于,所述装置还包括:接收模块和处理模块;
    所述接收模块用于接收所述终端设备根据所述第二信息上报的所述信道状态信息;
    处理模块用于根据所述信道状态信息和所述下行信道信息,生成下行预编码矩阵;根据所述下行预编码矩阵对数据进行编码;
    所述发送模块还用于向所述终端设备传输编码后的数据。
  35. 根据权利要求34所述的装置,其特征在于,所述处理模块还用于若所述下行信道信息通过所述人工智能算法模型获取且所述下行信道信息完整,则根据所述下 行信道信息,生成下行预编码矩阵。
  36. 根据权利要求34所述的装置,其特征在于,所述接收模块还用于接收终端设备发送的上行信道信息;
    所述处理模块还用于将所述上行信道信息输入所述人工智能算法模型,并获取所述人工智能算法模型输出的下行信道信息。
  37. 根据权利要求28-36任一项所述的装置,其特征在于,所述第一信息还用于指示所述网络设备是否具备信道互易性。
  38. 根据权利要求28-36任一项所述的装置,其特征在于,所述第一信息通过广播信息发送给所述终端设备;
    或者,所述第一信息通过随机接入过程发送给所述终端设备;
    或者,所述第一信息通过无线资源控制RRC专有信令发送给所述终端设备;
    或者,所述第一信息通过媒体接入控制控制单元MAC-CE发送给所述终端设备;
    或者,所述第一信息通过下行控制信息DCI发送给所述终端设备。
  39. 根据权利要求29所述的装置,其特征在于,所述至少一个信道状态配置参数通过广播信息或无线资源控制RRC专有信令发送给所述终端设备。
  40. 根据权利要求30-33任一项所述的装置,其特征在于,所述第二信息通过广播信息发送给所述终端设备;
    或者,所述第二信息通过随机接入过程发送给所述终端设备;
    或者,所述第二信息通过无线资源控制RRC专有信令发送给所述终端设备;
    或者,所述第二信息通过媒体接入控制控制单元MAC-CE发送给所述终端设备;
    或者,所述第二信息通过下行控制信息DCI发送给所述终端设备。
  41. 根据权利要求28-36任一项所述的装置,其特征在于,所述人工智能算法模型包括:深度学习模型和/或机器学习模型。
  42. 根据权利要求41所述的装置,其特征在于,所述深度学习模型包括卷积神经网络模块,所述机器学习模型包括以下至少一种模型:分类算法模型、回归算法模型、聚类算法模型和降维算法模型。
  43. 一种通信装置,其特征在于,包括:接收模块和处理模块;
    所述接收模块用于接收网络设备发送的第一信息,所述第一信息用于指示网络设备是否通过人工智能算法模型获取下行信道信息,所述人工智能算法模型是基于历史上行信道信息和历史下行信道信息为样本训练建立的;
    所述处理模块用于根据所述第一信息测量信道状态,获取信道状态信息。
  44. 根据权利要求43所述的装置,其特征在于,所述接收模块还用于接收所述网络设备发送的至少一个信道状态信息的配置参数,其中,不同信道状态的配置参数的时频资源不同和/或端口密度不同;
    所述处理模块具体用于根据所述第一信息从所述至少一个信道状态信息的配置参数中确定目标配置参数进行信道状态测量,获取信道状态信息。
  45. 根据权利要求43所述的装置,其特征在于,所述接收模块具体用于接收所述网络设备发送的第二信息,所述第二信息用于指示终端设备上报信道状态信息的类型;
    所述装置还包括:发送模块;
    所述发送模块用于通过所述第二信息指示的信道状态信息的类型,向所述网络设备上报所述信道状态信息。
  46. 根据权利要求45所述的装置,其特征在于,不同的信道状态信息的类型的上报的信息量不同。
  47. 根据权利要求46所述的装置,其特征在于,所述信道状态信息的类型,包 括有第一类型和第二类型,上报所述第一类型的信息量少于或等于上报所述第二类型的信息量。
  48. 根据权利要求47所述的装置,其特征在于,若通过所述人工智能算法模型获取所述下行信道信息,则所述第二信息用于指示所述终端设备使用所述第一类型上报所述信道状态信息;
    若未通过所述人工智能算法模型获取所述下行信道信息,则所述第二信息用于指示所述终端设备使用所述第二类型上报所述信道状态信息。
  49. 根据权利要求43-48任一项所述的装置,其特征在于,所述第一信息还用于指示所述网络设备是否具备信道互易性。
  50. 根据权利要求43-48任一项所述的装置,其特征在于,所述第一信息通过广播信息发送给终端设备;
    或者,所述第一信息通过随机接入过程发送给所述终端设备;
    或者,所述第一信息通过无线资源控制RRC专有信令发送给所述终端设备;
    或者,所述第一信息通过媒体接入控制控制单元MAC-CE发送给所述终端设备;
    或者,所述第一信息通过下行控制信息DCI发送给所述终端设备。
  51. 根据权利要求44所述的装置,其特征在于,所述至少一个信道状态配置参数通过广播信息或无线资源控制RRC专有信令发送给终端设备。
  52. 根据权利要求45-48任一项所述的装置,其特征在于,所述第二信息通过广播信息发送给所述终端设备;
    或者,所述第二信息通过随机接入过程发送给所述终端设备;
    或者,所述第二信息通过无线资源控制RRC专有信令发送给所述终端设备;
    或者,所述第二信息通过媒体接入控制控制单元MAC-CE发送给所述终端设备;
    或者,所述第二信息通过下行控制信息DCI发送给所述终端设备。
  53. 根据权利要求43-48任一项所述的装置,其特征在于,所述人工智能算法模型包括:深度学习模型和/或机器学习模型。
  54. 根据权利要求53所述的装置,其特征在于,所述深度学习模型包括卷积神经网络模块,所述机器学习模型包括以下至少一种模型:分类算法模型、回归算法模型、聚类算法模型和降维算法模型。
  55. 一种网络设备,其特征在于,包括:处理器和存储器;
    所述存储器用于存储计算机程序,所述处理器用于调用并运行所述存储器中存储的计算机程序,执行如权利要求1至15中任一项所述的通信方法。
  56. 一种终端设备,其特征在于,包括:处理器、存储器、发送器和接收器;
    所述存储器用于存储计算机程序,所述处理器用于调用并运行所述存储器中存储的计算机程序,执行如权利要求16至27中任一项所述的通信方法;
    所述发送器用于执行所述终端设备的发送动作,所述接收器用于执行所述终端设备的接收动作。
  57. 一种芯片,其特征在于,包括:处理器,用于从存储器中调用并运行计算机程序,使得安装有所述芯片的设备执行如权利要求1至15或16-27中任一项所述的方法。
  58. 一种计算机可读存储介质,其特征在于,用于存储计算机程序,所述计算机程序使得计算机执行如权利要求1至27中任一项所述的方法。
  59. 一种计算机程序产品,其特征在于,包括计算机程序信息,该计算机程序信息使得计算机执行如权利要求1至27中任一项所述的方法。
  60. 一种计算机程序,其特征在于,所述计算机程序使得计算机执行如权利要求1至27中任一项所述的方法。
PCT/CN2020/073020 2020-01-19 2020-01-19 通信方法及装置 WO2021142836A1 (zh)

Priority Applications (4)

Application Number Priority Date Filing Date Title
CN202080092149.0A CN115280682A (zh) 2020-01-19 2020-01-19 通信方法及装置
EP20913745.4A EP4092918A4 (en) 2020-01-19 2020-01-19 METHOD AND DEVICE FOR COMMUNICATION
PCT/CN2020/073020 WO2021142836A1 (zh) 2020-01-19 2020-01-19 通信方法及装置
US17/812,695 US20220352952A1 (en) 2020-01-19 2022-07-14 Method and device for communication

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/073020 WO2021142836A1 (zh) 2020-01-19 2020-01-19 通信方法及装置

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/812,695 Continuation US20220352952A1 (en) 2020-01-19 2022-07-14 Method and device for communication

Publications (1)

Publication Number Publication Date
WO2021142836A1 true WO2021142836A1 (zh) 2021-07-22

Family

ID=76863454

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/073020 WO2021142836A1 (zh) 2020-01-19 2020-01-19 通信方法及装置

Country Status (4)

Country Link
US (1) US20220352952A1 (zh)
EP (1) EP4092918A4 (zh)
CN (1) CN115280682A (zh)
WO (1) WO2021142836A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113922936A (zh) * 2021-08-31 2022-01-11 中国信息通信研究院 一种ai技术信道状态信息反馈方法和设备
WO2023125951A1 (zh) * 2021-12-31 2023-07-06 维沃移动通信有限公司 通信模型配置方法、装置和通信设备

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11838782B2 (en) * 2020-01-31 2023-12-05 Qualcomm Incorporated Measurements on a first band applicable to procedures on a second band
CN117998602A (zh) * 2022-11-04 2024-05-07 华为技术有限公司 信道状态信息确定方法、装置及可读存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108390706A (zh) * 2018-01-30 2018-08-10 东南大学 一种基于深度学习的大规模mimo信道状态信息反馈方法
WO2018236932A1 (en) * 2017-06-19 2018-12-27 Oshea Timothy James ENCODING AND DECODING INFORMATION FOR WIRELESS TRANSMISSION USING MULTIPLE ANTENNA TRANSMITTERS
CN109450830A (zh) * 2018-12-26 2019-03-08 重庆大学 一种高速移动环境下基于深度学习的信道估计方法
CN110383710A (zh) * 2017-03-09 2019-10-25 三星电子株式会社 高级无线通信系统中的协方矩阵反馈的方法和装置

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10484064B2 (en) * 2016-09-01 2019-11-19 Samsung Electronics Co., Ltd. Method and apparatus for downlink and uplink CSI acquisition
EP3729677B1 (en) * 2017-12-22 2023-08-09 Telefonaktiebolaget LM Ericsson (publ) A wireless communications system, a radio network node, a machine learning unt and methods therein for transmission of a downlink signal in a wireless communications network supporting beamforming

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110383710A (zh) * 2017-03-09 2019-10-25 三星电子株式会社 高级无线通信系统中的协方矩阵反馈的方法和装置
WO2018236932A1 (en) * 2017-06-19 2018-12-27 Oshea Timothy James ENCODING AND DECODING INFORMATION FOR WIRELESS TRANSMISSION USING MULTIPLE ANTENNA TRANSMITTERS
CN108390706A (zh) * 2018-01-30 2018-08-10 东南大学 一种基于深度学习的大规模mimo信道状态信息反馈方法
CN109450830A (zh) * 2018-12-26 2019-03-08 重庆大学 一种高速移动环境下基于深度学习的信道估计方法

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113922936A (zh) * 2021-08-31 2022-01-11 中国信息通信研究院 一种ai技术信道状态信息反馈方法和设备
CN113922936B (zh) * 2021-08-31 2023-04-28 中国信息通信研究院 一种ai技术信道状态信息反馈方法和设备
WO2023125951A1 (zh) * 2021-12-31 2023-07-06 维沃移动通信有限公司 通信模型配置方法、装置和通信设备

Also Published As

Publication number Publication date
CN115280682A (zh) 2022-11-01
US20220352952A1 (en) 2022-11-03
EP4092918A1 (en) 2022-11-23
EP4092918A4 (en) 2022-12-28

Similar Documents

Publication Publication Date Title
US11863252B2 (en) Terminal device capability transmission method, apparatus, and system
WO2021142836A1 (zh) 通信方法及装置
US10951332B2 (en) Method and apparatus for coordinated multipoint (CoMP) communication using quasi-co-location
WO2020057383A1 (zh) 数据传输的方法和装置
JP2021534602A (ja) 複数のtrp送信/パネルに用いられるcsiレポーティング
US10419094B2 (en) Channel state information measurement method, channel state information acquisition method, terminal and network device
KR20210095700A (ko) 채널 상태 정보의 측정 목적을 표시하기 위한 방법 및 디바이스와 시스템
US20210266926A1 (en) Channel state information transmission method and apparatus
US10362505B2 (en) Method and terminal for handling channel state information
US11088738B2 (en) Communication method and network device
CN106888062B (zh) Cqi估计、sinr确定方法及相关设备
CN113271671A (zh) 波束管理方法及相关装置
WO2016082224A1 (zh) 一种资源配置的方法、用户设备及基站
WO2017050213A1 (zh) 一种链路自适应的方法及装置
JP7143898B2 (ja) 基地局、及び方法
US20220038154A1 (en) Csi calculation method, user terminal and computer-readable storage medium
US20220360309A1 (en) Cqi saturation mitigation in downlink massive mu-mimo systems
WO2020233500A1 (zh) 一种通信方法及通信装置
WO2013123850A1 (zh) 一种信息反馈方法及装置、终端
WO2014198032A1 (zh) 信道状态信息测量的方法及设备
US20230308234A1 (en) Signal transmission method and apparatus, and storage medium
WO2021155659A1 (zh) 一种上行参考信号发射方式确定方法、装置及系统
WO2023082154A1 (zh) Csi反馈方案的更新方法、装置、设备及存储介质
TWI837873B (zh) 用於無線通訊的方法
WO2024051564A1 (zh) 信息传输方法、ai网络模型训练方法、装置和通信设备

Legal Events

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

Ref document number: 20913745

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2020913745

Country of ref document: EP

Effective date: 20220816

NENP Non-entry into the national phase

Ref country code: DE