WO2022083619A1 - 通信信息的发送、接收方法及通信设备 - Google Patents

通信信息的发送、接收方法及通信设备 Download PDF

Info

Publication number
WO2022083619A1
WO2022083619A1 PCT/CN2021/124911 CN2021124911W WO2022083619A1 WO 2022083619 A1 WO2022083619 A1 WO 2022083619A1 CN 2021124911 W CN2021124911 W CN 2021124911W WO 2022083619 A1 WO2022083619 A1 WO 2022083619A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
sub
module
level
communication
Prior art date
Application number
PCT/CN2021/124911
Other languages
English (en)
French (fr)
Inventor
杨昂
孙鹏
Original Assignee
维沃移动通信有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 维沃移动通信有限公司 filed Critical 维沃移动通信有限公司
Priority to JP2023524933A priority Critical patent/JP2023550690A/ja
Priority to EP21882034.8A priority patent/EP4220486A4/en
Publication of WO2022083619A1 publication Critical patent/WO2022083619A1/zh
Priority to US18/137,807 priority patent/US20230261815A1/en

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04BTRANSMISSION
    • H04B17/00Monitoring; Testing
    • H04B17/30Monitoring; Testing of propagation channels
    • H04B17/391Modelling the propagation channel
    • H04B17/3913Predictive models, e.g. based on neural network models
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W4/00Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/18Information format or content conversion, e.g. adaptation by the network of the transmitted or received information for the purpose of wireless delivery to users or terminals
    • 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
    • G06N3/044Recurrent networks, e.g. Hopfield networks
    • 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
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/08Learning methods
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/16Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using machine learning or artificial intelligence
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L5/00Arrangements affording multiple use of the transmission path
    • H04L5/0001Arrangements for dividing the transmission path
    • H04L5/0003Two-dimensional division
    • H04L5/0005Time-frequency
    • H04L5/0007Time-frequency the frequencies being orthogonal, e.g. OFDM(A), DMT
    • H04L5/001Time-frequency the frequencies being orthogonal, e.g. OFDM(A), DMT the frequencies being arranged in component carriers
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L5/00Arrangements affording multiple use of the transmission path
    • H04L5/0091Signaling for the administration of the divided path
    • H04L5/0094Indication of how sub-channels of the path are allocated
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W24/00Supervisory, monitoring or testing arrangements
    • H04W24/02Arrangements for optimising operational condition
    • 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
    • G06N3/0464Convolutional networks [CNN, ConvNet]
    • 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
    • H04B7/0617Diversity 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 for beam forming
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W24/00Supervisory, monitoring or testing arrangements
    • H04W24/10Scheduling measurement reports ; Arrangements for measurement reports

Definitions

  • the present invention claims the priority of the Chinese patent application with the application number of 202011149923.5 and the invention titled “Communication Information Transmission and Reception Method and Communication Equipment” filed with the China Patent Office on October 23, 2020, the entire content of which is by reference Incorporated in the present invention.
  • the present application belongs to the technical field of wireless communication, and in particular relates to a method for sending and receiving communication information and a communication device.
  • AI networks also called neural networks
  • neural networks have been widely used in various fields.
  • Embodiments of the present application provide a method and a communication device for sending and receiving communication information, which can solve the problem of how to use an AI network in the transmission of communication information.
  • a method for sending communication information comprising: dividing the first communication information into one or more subband information by a first communication device; The one or more subband information is input to the first artificial intelligence network model, and the second communication information output by the first artificial intelligence network model is sent.
  • a device for sending communication information including: a preprocessing module for dividing the first communication information into one or more subband information; a first input module for dividing the first communication information The broadband information and/or the one or more subband information are input to the first artificial intelligence network model; the sending module is configured to send the second communication information output by the first artificial intelligence network model.
  • a method for receiving communication information comprising: a second communication device receiving second communication information sent by a first communication device; inputting the second communication information into a second artificial intelligence network model, to obtain broadband information and/or one or more subband information of the first communication information.
  • a device for receiving communication information comprising: a receiving module for receiving second communication information sent by a first communication device; a second input module for inputting the second communication information into a first communication device.
  • An artificial intelligence network model to obtain broadband information and/or one or more sub-band information of the first communication information.
  • a communication device in a fifth aspect, includes a processor, a memory, and a program or instruction stored on the memory and executable on the processor, the program or instruction being executed by the processor
  • the terminal includes a processor, a memory, and a program or instruction stored on the memory and executable on the processor, the program or instruction being executed by the processor
  • a readable storage medium on which a program or an instruction is stored, and when the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented, or the steps as described in the first aspect are implemented. The steps of the method described in the third aspect.
  • a chip in a seventh aspect, includes a processor and a communication interface, the communication interface is coupled to the processor, and the processor is configured to run a communication device program or instruction, and the implementation is as described in the first aspect method, or implement the method described in the third aspect.
  • a computer program product comprising a processor, a memory, and a program or instruction stored on the memory and executable on the processor, the program or instruction being executed by the When executed by the processor, the steps of the method described in the first aspect or the steps of the method described in the third aspect are realized.
  • the first communication device divides the first communication information into one or more subband information, and uses the broadband information and/or the one or more subband information of the first communication information as the first communication information.
  • the input information of the artificial intelligence network model is input to the first artificial intelligence network model, so as to obtain the second communication information to be sent, and send the second communication information. Therefore, the first artificial intelligence network model is used to convert the original first communication information into the second communication information to be sent, and the performance of the communication system is improved.
  • FIG. 1 shows a block diagram of a wireless communication system to which an embodiment of the present application can be applied
  • FIG. 2 shows a flowchart of a method for sending communication information provided by an embodiment of the present application
  • FIG. 3 shows a schematic structural diagram of a first artificial intelligence network model in an embodiment of the present application
  • FIG. 4 shows a schematic structural diagram of another first artificial intelligence network model in an embodiment of the present application.
  • FIG. 5 shows a schematic structural diagram of yet another first artificial intelligence network model in an embodiment of the present application.
  • FIG. 6 shows a schematic structural diagram of yet another first artificial intelligence network model in an embodiment of the present application.
  • FIG. 7 shows a flowchart of a method for receiving communication information provided by an embodiment of the present application.
  • FIG. 8 shows a schematic structural diagram of a second artificial intelligence network model in an embodiment of the present application.
  • FIG. 9 shows a schematic structural diagram of an apparatus for sending communication information provided by an embodiment of the present application.
  • FIG. 10 shows a schematic structural diagram of an apparatus for receiving communication information provided by an embodiment of the present application.
  • FIG. 11 shows a schematic structural diagram of a communication device provided by an embodiment of the present application.
  • FIG. 12 shows a schematic diagram of a hardware structure of a terminal provided by an embodiment of the present application.
  • FIG. 13 shows a schematic diagram of a hardware structure of a network-side device provided by an embodiment of the present application.
  • first, second and the like in the description and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It is to be understood that the data so used are interchangeable under appropriate circumstances so that the embodiments of the present application can be practiced in sequences other than those illustrated or described herein, and "first”, “second” distinguishes Usually it is a class, and the number of objects is not limited.
  • the first object may be one or multiple.
  • “and/or” in the description and claims indicates at least one of the connected objects, and the character “/" generally indicates that the associated objects are in an "or” relationship.
  • LTE Long Term Evolution
  • LTE-Advanced LTE-Advanced
  • LTE-A Long Term Evolution-Advanced
  • CDMA Code Division Multiple Access
  • TDMA Time Division Multiple Access
  • FDMA Frequency Division Multiple Access
  • OFDMA Orthogonal Frequency Division Multiple Access
  • SC-FDMA Single-carrier Frequency-Division Multiple Access
  • system and “network” in the embodiments of the present application are often used interchangeably, and the described technology can be used not only for the above-mentioned systems and radio technologies, but also for other systems and radio technologies.
  • NR New Radio
  • the following description describes a New Radio (NR) system for example purposes, and uses NR terminology in most of the description below, but these techniques can also be applied to applications other than NR system applications, such as 6th Generation , 6G) communication system.
  • NR New Radio
  • FIG. 1 shows a block diagram of a wireless communication system to which the embodiments of the present application can be applied.
  • the wireless communication system includes a terminal 11 and a network-side device 12 .
  • the terminal 11 may also be called a terminal device or a user terminal (User Equipment, UE), and the terminal 11 may be a mobile phone, a tablet computer (Tablet Personal Computer), a laptop computer (Laptop Computer) or a notebook computer, a personal digital assistant (Personal Digital Assistant, PDA), PDA, netbook, ultra-mobile personal computer (ultra-mobile personal computer, UMPC), mobile Internet Device (Mobile Internet Device, MID), wearable device (Wearable Device) or vehicle-mounted device ( VUE), pedestrian terminal (PUE) and other terminal-side devices, wearable devices include: bracelets, earphones, glasses, etc.
  • the network side device 12 may be a base station or a core network, wherein the base station may be referred to as a Node B, an evolved Node B, an access point, a Base Transceiver Station (BTS), a radio base station, a radio transceiver, a basic service Set (Basic Service Set, BSS), Extended Service Set (Extended Service Set, ESS), Node B, Evolved Node B (eNB), Home Node B, Home Evolved Node B, WLAN Access Point, WiFi Node, Send Transmitting Receiving Point (TRP) or some other suitable term in the field, as long as the same technical effect is achieved, the base station is not limited to a specific technical vocabulary. It should be noted that in the embodiment of this application, only the NR system is used. The base station in the example is taken as an example, but the specific type of the base station is not limited.
  • FIG. 2 shows a schematic flowchart of a method for sending communication information in an embodiment of the present application, and the method 200 may be executed by a communication device.
  • the method may be performed by software or hardware installed on the communication device.
  • the communication device may be a terminal or a network side device.
  • the method may include the following steps.
  • the first communication device divides the first communication information into one or more subband information.
  • the subband division may be based on frequency domain resource division, time domain resource division, spatial domain resource division, code domain resource division, and the like. Therefore, in this possible implementation, S210 may include: dividing the first communication information into one or more subband information according to a target resource of the first communication information, where the target resource includes at least the following One: frequency domain resources, time domain resources, space domain resources and code domain resources.
  • a predetermined resource size may be used as a unit, with reference to dividing the first communication information into one or more subband information. Therefore, in a possible implementation manner, the first communication device divides the first communication information into one or more subband information, including at least one of the following:
  • the first communication information is divided into one or more subband information on the frequency domain resource, wherein the frequency domain unit resource includes at least one of the following: a resource block (Resource Block, RB), physical resource block (Physical Resource Block, PRB, subband, precoding resource block group (Precoding Resource block Group, PRG), and bandwidth part (Bandwidth Part, BWP). That is to say, in this In a possible implementation manner, the first communication information may be divided according to RBs, PRBs, PRGs, subbands or BWPs, and information on each or more RBs, PRBs, PRGs, subbands or BWPs of the first communication information may be divided. divided into a subband.
  • RB resource block
  • PRB Physical Resource Block
  • PRG Physical Resource Block Group
  • BWP bandwidth part
  • the time domain unit resource dividing the first communication information into one or more subband information on the time domain resource, wherein the time domain unit resource includes at least one of the following: subcarriers: , Orthogonal Frequency Division Multiplex (OFDM) symbols, time slots, and half-slots. That is to say, in this possible implementation manner, the first communication information may be divided according to subcarriers, OFDM symbols, time slots or half time slots, and each or more carriers, OFDM symbols, Information on a slot or half-slot is divided into a subband.
  • OFDM Orthogonal Frequency Division Multiplex
  • the space unit resource includes at least one of the following: an antenna, an antenna element, Antenna panel, transmitting and receiving unit, beam (including analog beam and digital beam), layer (Layer), rank (Rank), and antenna angle (eg, tilt angle). That is to say, in this possible implementation manner, the first communication information can be classified into antennas, antenna elements, antenna panels, transmitting and receiving units, beams (including analog beams and digital beams), layers, and ranks. , and the antenna angle (eg, tilt angle) is divided.
  • the code domain unit resource dividing the first communication information into one or more subband information on the code domain resource, wherein the code domain unit resource includes at least one of the following: orthogonal codes, quasi-orthogonal codes, and semi-orthogonal codes. That is to say, in this possible implementation manner, the first communication information may be divided into orthogonal codes, quasi-orthogonal codes, and semi-orthogonal codes.
  • S212 Input the broadband information and/or the one or more subband information of the first communication information into the first artificial intelligence network model, and send the second communication information output by the first artificial intelligence network model.
  • the first artificial intelligence network (or may also be referred to as a neural network) model is used to process the broadband information and/or the one or more subband information of the input first communication information to Output the second communication information corresponding to the first communication information, that is, the information to be sent.
  • the first artificial intelligence network model may encode one or more subband information according to the broadband information of the first communication information, and output a subband encoded data stream (ie, the second communication information), wherein the first communication information may be the original signal .
  • the broadband information of the first communication information may be information representing the overall characteristics of the first communication information.
  • the first artificial intelligence network model may be a pre-established network model, and through training, a data stream corresponding to the input information may be output.
  • the first artificial intelligence network model may include at least one level of submodules, and each level of submodules may include one or more submodules.
  • the first artificial intelligence network model includes a first-level sub-module, and the first-level sub-module includes N sub-modules, that is, sub-modules A-1 to A-N, wherein , N is the input broadband information and/or the number of subbands, specifically, in FIG. 3, the input is N subbands, of course, it is not limited to this, in practical applications, the input can also be a broadband information and N-1 subband information.
  • the first artificial intelligence network model includes two-level sub-modules, wherein the first-level sub-module includes N modules, that is, sub-modules A-1 to A-N , the second-level sub-module includes one sub-module, that is, sub-module B.
  • the first artificial intelligence network model includes multi-level sub-modules, for example, the sub-module B is followed by a sub-module C, a sub-module D, and the like.
  • the submodule may include at least one of the following:
  • Fully connected neural network module that is, the artificial intelligence network type adopted by the sub-module is a fully connected neural network.
  • Convolutional neural network module that is, the type of artificial intelligence network adopted by the sub-module is a convolutional neural network.
  • Recurrent neural network module that is, the artificial intelligence network type adopted by the sub-module is a recurrent neural network.
  • Residual neural network module that is, the type of artificial intelligence network adopted by the sub-module is a residual neural network.
  • Preset algorithm module For example, algorithm modules for finding time correlation and/or frequency correlation, decomposition of eigenvalues, finding eigenvalues, finding eigenvectors, calculating channel capacity, filtering, equalization, etc. according to the input information.
  • a sub-module may include multiple small networks, each small network may use one of the above modules, and different small networks may use different modules above, which are not specifically limited in this embodiment of the present application.
  • some submodules in the first artificial intelligence network model may adopt the same artificial intelligence network structure and/or adopt the same artificial intelligence network parameters.
  • sub-module A-i and sub-module A-j use the same AI network structure, but the specific weights and bias values are different.
  • the sub-module A-i and the sub-module A-j use the same AI network structure, and the specific weights and bias values are the same.
  • the artificial intelligence network structure adopted by the sub-module is determined by at least one of the following:
  • Type of artificial intelligence network for example, fully connected neural network, convolutional neural network, recurrent neural network, or residual network.
  • the combination mode of the included multiple sub-networks that is, the combination mode of each small network when a sub-module includes multiple small networks. For example, fully connected + convolution, convolution + residual, etc.
  • connection method between the hidden layer and the input layer
  • the number of neurons in each layer is generally different or may be the same.
  • the input information of a target submodule of the first artificial intelligence network model this time includes at least one of the following:
  • the input information of other sub-modules at the same level as the target sub-module; that is, the input information of the target sub-module may include the input information of other sub-modules at the same level except the target sub-module. , that is, the input information is the input of the target sub-module and one or more other sub-modules at the same level as the target sub-module at the same time.
  • other sub-modules of the same level are M sub-modules adjacent to the target sub-module, where M is a positive integer.
  • other submodules at the same level are M submodules that skip some submodules and are adjacent to the target submodule. For example, if the target submodule is A-5, the other submodules at the same level are A-7 and A-3, or A-1 and A-3 and A-7 and A-9 and A-11, M is a positive integer.
  • other sibling submodules include all other sibling submodules except the target submodule.
  • the input information of the sub-module A-i includes the last intermediate information of the sub-module A-j of the current stage, or also includes the current input information of the sub-module A-j of the current stage.
  • the second communication information may be the last level of the first artificial intelligence network model.
  • the combination of the output information of the multiple sub-modules may include: a one-dimensional vector or a two-dimensional matrix or a multi-dimensional matrix obtained by combining the output information of the multiple sub-modules; for example, In Figure 3, the output information of multiple sub-modules A-i can be combined into a large one-dimensional vector, or a two-dimensional matrix, or a multi-dimensional matrix for direct input. For another example, in Figure 4, the output information of multiple submodules A-i can be combined into a large one-dimensional vector, or a two-dimensional matrix, or a multi-dimensional matrix directly input as the input of the next level, for example, as the input of the submodule B enter.
  • the combination of the output information of the multiple sub-modules may include: a result obtained after the output information of the multiple sub-modules is calculated according to a preset algorithm.
  • the preset algorithm includes, but is not limited to, weighting and/or other mathematical operations.
  • weighting may include a combination of linear averaging, multiplicative averaging, and other common averaging methods.
  • Mathematical operations can include a combination of various common mathematical operations such as addition and subtraction multipliers, n-th power, n-th root square, logarithm, derivation, and partial derivation.
  • n is any number.
  • n may be a positive number or a negative number or 0, or may also be a real number or a complex number, which is not specifically limited in this embodiment.
  • the first artificial intelligence network model includes a first-level submodule and a second-level submodule, wherein the first-level submodule includes one or more first submodules, and the second The first-level sub-module is located at the previous stage of the first-level sub-module, and the second-level sub-module includes N second sub-modules, wherein N is the broadband information input to the first artificial intelligence network model and/ or the number of subbands.
  • the first artificial intelligence network model includes a first-level sub-module (including sub-module B) and a second-level sub-module (including sub-modules A-1, A-2, ..., A-N).
  • the first artificial intelligence network model includes first-level submodules (including submodules B-1 and B-2) and second-level submodules (including submodules A-1, A-2 ,...,A-N).
  • the first-level sub-module includes a plurality of first sub-modules, at least one of the plurality of first sub-modules represents bandwidth information, and a plurality of the first sub-modules
  • the other first submodules in the module represent subband information, wherein the other first submodules are part or all of the first submodules except the at least one first submodule in the plurality of first submodules module.
  • the second communication information is a precoding matrix indicator (Precoding matrix indicator, PMI)
  • PMI precoding matrix indicator
  • the PMI is divided into a wideband PMI and a subband PMI, or may also be called wideband information or wideband part of PMI, subband information of PMI or subband section.
  • sub-module B-1 represents broadband information
  • sub-module B-2 represents sub-band information
  • the sub-module B-2 can be further divided into multiple sub-modules.
  • submodule B-2-1, submodule B-2-2, ..., submodule B-2-L where L is a positive integer.
  • L is equal to the number N of subbands.
  • the broadband information of the second communication information is obtained through the at least one first submodule.
  • the full-bandwidth information of the second communication information can be obtained. That is, the full-bandwidth feature of the second communication information.
  • the subband information of the second communication information is obtained through the at least one first submodule and the other first submodules. That is to say, without the output of the at least one first submodule, the subband information of the second communication information cannot be obtained only by the other first submodules. For example, in FIG. 5 , there is no output from the submodule B-1, and only the submodule B-2 cannot obtain the subband information of the second communication information.
  • the subband information of the second communication information is obtained through the other first submodule. That is, the subband information of the second communication information can be obtained only by the other first submodules. For example, in FIG. 5, there is no output of the sub-module B-1, and only the sub-module B-2 can obtain the sub-band information of the second communication information.
  • the input information of the at least one first submodule is part or all of the output information of the second submodule; the input information of the other first submodules is part or all of the first submodule.
  • the input information of the at least one first submodule may be different from the input information of the other first submodules.
  • the input information of the sub-module B-1 may be the output information of part of the sub-module A (that is, some of the sub-modules in A-1 to A-N), and the input information of the sub-module B-2 may be part of the output information of the sub-module A-1 to A-N.
  • Output information of module A (ie some submodules in A-1 to A-N).
  • the input information of the sub-module B-1 and the input information of the sub-module B-2 may be the same or different.
  • the optional first artificial intelligence network model further includes a third-level sub-module, and the third-level sub-module is located at a level before the second-level sub-module.
  • the first artificial intelligence network model further includes a sub-module C, and the sub-module C is located at the previous level of the sub-modules A-1 to A-N.
  • the third-level sub-module includes a third sub-module
  • the input information of the third sub-module is the broadband information of the first communication information and/or the one or more sub-band information.
  • the input information of the sub-module C is the N sub-band information of the first communication information). That is to say, in this possible implementation manner, the broadband information of the first communication information and/or the one or more sub-band information first enters the third sub-module for unified processing, and then is output into the second-level sub-module. module.
  • the input information of each second sub-module in the second-level sub-module may be the same or different.
  • the input information of a second sub-module in the second-level sub-module may be all output information of the third sub-module, or the input information of a second sub-module in the second-level sub-module may be the third sub-module. Part of the output information of the module.
  • the input information of one of the second sub-modules is all output information of the third sub-module. That is, the output information of the third sub-module is used as the input information of each second sub-module at the next stage.
  • the input information of one of the second sub-modules is part of the output information of the third sub-module, and the input information of different second sub-modules is different.
  • the input information of sub-module C includes N parts, and each part is used as the input information of one sub-module A-i.
  • one submodule A-i corresponds to one subband information i.
  • the first artificial intelligence network model in FIG. 6 may also not include the first-level sub-module, that is, not include sub-module B, or not include sub-module B-1 and sub-module B-2 ).
  • the second communication information includes one of the following:
  • Reference signal that is, a reference signal used for signal processing.
  • reference signals for signal detection, filtering, equalization, etc. may be included.
  • the reference signal includes but is not limited to: demodulation reference signal (Demodulation Reference Signal, DMRS), sounding reference signal (Sounding Reference Signal, SRS), synchronization signal/physical broadcast channel signal block (or synchronization signal block) (Synchronization Signal and PBCH block, SSB), tracking reference signal (Tracking Reference Signal, TRS), phase TRS (Phase-TRS, PTRS), channel state information (Channel State Information, CSI) reference signal (CSI Reference Signal, CSI-RS) and so on.
  • channels include but are not limited to Physical Downlink Control Channel (PDCCH), Physical Downlink Shared Channel (PDSCH), Physical Uplink Control Channel (Physical Uplink Control Channel) , PUCCH), Physical Uplink Shared Channel (PUSCH), Physical Random Access Channel (PRACH), Physical Broadcast Channel (PBCH), etc.
  • PUCCH Physical Downlink Control Channel
  • PDSCH Physical Downlink Shared Channel
  • PUSCH Physical Uplink Shared Channel
  • PRACH Physical Broadcast Channel
  • PBCH Physical Broadcast Channel
  • channel state information may include:
  • channel state information feedback information Including but not limited to channel related information, channel matrix related information, channel feature information, channel matrix feature information, PMI, Rank indicator (RI), CSI-RS Resource Indicator (CRI), channel quality Indicator (Channel quality indicator, CQI), layer indicator (Layer Indicator, LI), etc.
  • the base station obtains the angle and delay information according to the uplink channel, and can notify the UE of the angle information and delay information through CSI-RS precoding or direct indication method, and the UE according to the base station's instructions Report or select and report within the range indicated by the base station, thereby reducing the calculation amount of the UE and the overhead of CSI reporting.
  • Beam information including but not limited to: beam quality, beam indication information (eg, reference signal ID), beam failure indication information, and new beam indication information in beam failure recovery.
  • Beam information that can also be used for beam management, including: beam measurement, beam reporting, beam prediction, beam failure detection, beam failure recovery, and new beam indication in beam failure recovery.
  • Channel prediction information may include prediction of channel state information, beam prediction, and the like.
  • Interference information including but not limited to intra-cell interference, inter-cell interference, out-of-band interference, intermodulation interference and other information.
  • the network side device can estimate the specific position of the UE (including the horizontal position and/or the vertical position) or the possible future trajectory through the reference signal (eg SRS), or information to assist the position estimation or the trajectory estimation.
  • the reference signal eg SRS
  • Prediction information of high-level services and parameters, and management information of high-level services and parameters including but not limited to: throughput, required data packet size, service requirements, moving speed, noise information, etc.
  • Control signaling For example, related signaling of power control and related signaling of beam management, etc.
  • the second communication information to be sent can be obtained through the first artificial intelligence network model, and the structure of the first artificial intelligence network model is relatively simple, which can effectively reduce the complexity of the AI network, thereby improving the communication system performance.
  • FIG. 7 shows a schematic flowchart of a method for receiving communication information in an embodiment of the present application, and the method 700 may be executed by a communication device.
  • the method may be performed by software or hardware installed on the communication device.
  • the communication device may be a terminal or a network side device.
  • the method may include the following steps.
  • the second communication device receives the second communication information sent by the first communication device.
  • the first communication device may use the foregoing method 200 to send the second communication information, or the first communication device may also use other methods to send the second communication information, which is not specifically limited in this embodiment.
  • the second communication information may be an encoded data stream.
  • S712 Input the second communication information into the second artificial intelligence network model to obtain broadband information and/or one or more subband information of the first communication information.
  • the second artificial intelligence network model is used to decode the received second communication information to obtain broadband information and/or one or more subband information of the first communication information.
  • the second artificial intelligence network model may be pre-trained, so that the second artificial intelligence network model can output broadband information and/or one or more subband information corresponding to the input second communication information.
  • the second communication device may further restore the subbands according to the broadband information and/or one or more subband information
  • the distribution state of information, through time-frequency conversion, restores the original information, that is, the first communication information.
  • the second artificial intelligence network model may adopt an artificial intelligence network model similar to the first artificial intelligence network model.
  • Part of the content of the second artificial intelligence network model is mainly described below, and other parts are similar to or correspond to the first artificial intelligence network model.
  • the second artificial intelligence network model includes at least one level of submodules, and each level includes one or more submodules.
  • the second artificial intelligence network model includes two-level sub-modules, wherein the first-level sub-module includes one sub-module B, and the second-level sub-module includes N sub-modules A, namely A-1 to A-N, where N is the number of broadband information and/or one or more subband information of the first communication information.
  • the submodule may include at least one of the following:
  • some of the sub-modules of the second artificial intelligence network model may adopt the same artificial intelligence network structure and/or adopt the same artificial intelligence network parameters.
  • the artificial intelligence network structure adopted by the sub-module is determined by at least one of the following:
  • connection method between the hidden layer and the input layer
  • the input information of a target submodule of the second artificial intelligence network model this time includes at least one of the following:
  • the combination of the outputs of the multiple sub-modules includes:
  • the second artificial intelligence network model may include a first-level submodule and a second-level submodule, wherein the first-level submodule includes at least one first submodule, and the second-level submodule The sub-module is located at a level after the first-level sub-module, and the second-level sub-module includes N second sub-modules, where N is the broadband information and/or the output of the second artificial intelligence network model The number of subband information.
  • the first-level sub-module includes a plurality of first sub-modules, and at least one first sub-module in the plurality of first sub-modules represents bandwidth information, and a plurality of all the first sub-modules represent bandwidth information.
  • the other first submodules in the first submodule represent subband information, wherein the other first submodules are the part of the plurality of first submodules other than the at least one first submodule or All first submodules.
  • the input information of at least one first sub-module may be full-bandwidth information of the second communication information, that is, all broadband characteristics, and the input information of the other first sub-modules may include the full-bandwidth information of the second communication information and all broadband features. Subband information of the second communication information.
  • the input information of one of the second submodules includes output information of the at least one first submodule and/or output information of the other first submodules.
  • the output information of the at least one first sub-module is N parts, which are respectively input to each second sub-module
  • the output information of the other first sub-modules is N parts, which are respectively input to each second sub-module .
  • the second artificial intelligence network model further includes a third-level sub-module, and the third-level sub-module is located at a subsequent level of the second-level sub-module.
  • the output information of each second sub-module in the second-level sub-module can be uniformly processed and then output.
  • the third-level sub-module may include a third sub-module, and the output information of the third sub-module is the broadband information of the first communication information and/or a or multiple subband information.
  • the input information of the third sub-module is a combination of output information of a plurality of the second sub-modules.
  • the input information of the third sub-module may be a one-dimensional vector, a two-dimensional matrix or a multi-dimensional matrix obtained by merging the output information of each of the second sub-modules, or the output information of each second sub-module may be weighted and averaged. information.
  • the second communication information includes one of the following:
  • the execution subject may be a device for sending communication information, or a control module in the device for sending communication information for executing the method for sending communication information.
  • the device for sending communication information provided by the embodiments of the present application is described by taking the method for sending communication information performed by a device for sending communication information as an example.
  • FIG. 9 shows a schematic structural diagram of an apparatus for sending communication information provided by an embodiment of the present application.
  • the apparatus 900 for sending communication information may include: a preprocessing module 901 configured to divide the first communication information into One or more subband information; the first input module 902 is used for inputting the broadband information of the first communication information and/or the one or more subband information into the first artificial intelligence network model; the sending module 903 is used for inputting for sending the second communication information output by the first artificial intelligence network model.
  • the preprocessing module 901 divides the first communication information into one or more subband information, including
  • the first communication information is divided into one or more subband information, wherein the target resource includes at least one of the following: frequency domain resources, time domain resources, space domain resources and Code domain resources.
  • the preprocessing module 901 divides the first communication information into one or more subband information, including at least one of the following:
  • the first communication information is divided into one or more subband information on the frequency domain resource, wherein the frequency domain unit resource includes at least one of the following: resource block RB, physical resource block PRB, subband, precoding resource block group PRG, and bandwidth part BWP;
  • the first communication information is divided into one or more subband information on the time domain resource, wherein the time domain unit resource includes at least one of the following: subcarrier, OFDM symbol , slot, and half slot;
  • airspace unit resources as a unit, dividing the first communication information into one or more subband information on the airspace resources, wherein the airspace unit resources include at least one of the following: an antenna, an antenna element, an antenna panel, Transmitting and receiving units, beams, layers, ranks, and antenna angles;
  • the first communication information is divided into one or more subband information on the code domain resource, wherein the code domain unit resource includes at least one of the following: an orthogonal code, a quasi- Orthogonal codes, and semi-orthogonal codes.
  • the first artificial intelligence network model includes at least one level of sub-modules, and each level includes one or more sub-modules.
  • the sub-module includes at least one of the following: a fully connected neural network module; a convolutional neural network module; a recurrent neural network module; a residual neural network module; a preset algorithm module.
  • some of the sub-modules adopt the same artificial intelligence network structure and/or adopt the same artificial intelligence network parameters.
  • the artificial intelligence network structure adopted by the sub-module is determined by at least one of the following:
  • connection method between the input layer and the hidden layer The connection method between the input layer and the hidden layer
  • connection method between multiple hidden layers The connection method between multiple hidden layers
  • connection method between the hidden layer and the input layer is the connection method between the hidden layer and the input layer
  • the number of neurons in each layer is the number of neurons in each layer.
  • the input information of a target submodule of the first artificial intelligence network model this time includes at least one of the following:
  • the second communication information includes: output information of sub-modules of the last level of the first artificial intelligence network model; or multiple data of the last level of the first artificial intelligence network model The combination of output information of each submodule.
  • the combination of the output information of the multiple submodules includes:
  • the output information of the multiple sub-modules is the result obtained after the calculation is performed according to the preset algorithm.
  • the first artificial intelligence network model includes a first-level submodule and a second-level submodule, wherein the first-level submodule includes one or more first submodules, and the second The first-level sub-module is located at the previous stage of the first-level sub-module, and the second-level sub-module includes N second sub-modules, wherein N is the broadband information input to the first artificial intelligence network model and/ or the number of subbands.
  • the first-level sub-module includes a plurality of first sub-modules, at least one of the plurality of first sub-modules represents bandwidth information, and a plurality of the first sub-modules
  • the other first submodules in the module represent subband information, wherein the other first submodules are part or all of the first submodules except the at least one first submodule in the plurality of first submodules module.
  • the broadband information of the second communication information is obtained through the at least one first submodule; and/or, the broadband information of the second communication information is obtained through the at least one first submodule and the other first submodules Subband information of the second communication information.
  • the input information of the at least one first submodule is part or all of the output information of the second submodule; the input information of the other first submodules is part or all of the first submodule.
  • the output information of the second submodule is part or all of the first submodule.
  • the first artificial intelligence network model further includes a third-level sub-module, and the third-level sub-module is located at a level before the second-level sub-module.
  • the third-level sub-module includes a third sub-module
  • the input information of the third sub-module is broadband information of the first communication device and/or the one or more sub-modules with information.
  • the input information of one of the second sub-modules is all the output information of the third sub-module.
  • the input information of one of the second sub-modules is part of the output information of the third sub-module, and the input information of different second sub-modules is different.
  • the second communication information includes one of the following:
  • the apparatus for sending communication information in this embodiment of the present application may be an apparatus, or may be a component, an integrated circuit, or a chip in a terminal or a network-side device.
  • the device may be a mobile terminal or a non-mobile terminal.
  • the mobile terminal may include, but is not limited to, the types of terminals 11 listed above, and the non-mobile terminal may be a server, a network attached storage (NAS), a personal computer (personal computer, PC), a television ( television, TV), teller machine, or self-service machine, etc., which are not specifically limited in the embodiments of the present application.
  • the apparatus for sending communication information in this embodiment of the present application may be an apparatus having an operating system.
  • the operating system may be an Android (Android) operating system, an ios operating system, or other possible operating systems, which are not specifically limited in the embodiments of the present application.
  • the apparatus for sending communication information provided by the embodiment of the present application can implement each process implemented by the method embodiment in FIG. 2 and achieve the same technical effect. To avoid repetition, details are not repeated here.
  • FIG. 10 shows a schematic structural diagram of an apparatus for receiving communication information provided by an embodiment of the present application.
  • the apparatus 1000 for receiving communication information may include: a receiving module 1001, configured to receive data sent by a first communication device. second communication information; a second input module 1002, configured to input the second communication information into a second artificial intelligence network model to obtain broadband information and/or one or more subband information of the first communication information.
  • the second artificial intelligence network model includes at least one level of sub-modules, and each level includes one or more sub-modules.
  • the submodule includes at least one of the following:
  • some of the sub-modules use the same artificial intelligence network structure and/or use the same artificial intelligence network parameters.
  • the artificial intelligence network structure adopted by the sub-module is determined by at least one of the following:
  • connection method between the input layer and the hidden layer The connection method between the input layer and the hidden layer
  • connection method between multiple hidden layers The connection method between multiple hidden layers
  • connection method between the hidden layer and the input layer is the connection method between the hidden layer and the input layer
  • the number of neurons in each layer is the number of neurons in each layer.
  • the input information of a target submodule of the second artificial intelligence network model this time includes at least one of the following:
  • the combination of the output information of the multiple submodules includes:
  • the output information of the multiple sub-modules is the result obtained after the calculation is performed according to the preset algorithm.
  • the second artificial intelligence network model includes a first-level submodule and a second-level submodule, wherein the first-level submodule includes at least one first submodule, and the second-level submodule
  • the module is located at the next level of the first-level sub-module, and the second-level sub-module includes N second sub-modules, where N is the broadband information and/or sub-modules output by the second artificial intelligence network model. Quantity with information.
  • the first-level sub-module includes a plurality of first sub-modules, at least one of the plurality of first sub-modules represents bandwidth information, and a plurality of the first sub-modules
  • the other first submodules in the module represent subband information, wherein the other first submodules are part or all of the first submodules except the at least one first submodule in the plurality of first submodules module.
  • the input information of one of the second submodules includes output information of the at least one first submodule and/or output information of the other first submodules.
  • the second artificial intelligence network model further includes a third-level sub-module, and the third-level sub-module is located at a subsequent level of the second-level sub-module.
  • the third-level sub-module includes a third sub-module, and the output information of the third sub-module is broadband information and/or one or more sub-band information of the first communication information .
  • the input of the third sub-module is a combination of output information of a plurality of the second sub-modules.
  • the second communication information includes one of the following:
  • the apparatus for receiving communication information in this embodiment of the present application may be an apparatus, or may be a component, an integrated circuit, or a chip in a terminal or a network-side device.
  • the device may be a mobile terminal or a non-mobile terminal.
  • the mobile terminal may include, but is not limited to, the types of terminals 11 listed above, and the non-mobile terminal may be a server, a network attached storage (NAS), a personal computer (personal computer, PC), a television ( television, TV), teller machine, or self-service machine, etc., which are not specifically limited in the embodiments of the present application.
  • the apparatus for receiving the communication information in the embodiment of the present application may be an apparatus having an operating system.
  • the operating system may be an Android (Android) operating system, an ios operating system, or other possible operating systems, which are not specifically limited in the embodiments of the present application.
  • the apparatus for receiving communication information provided by the embodiment of the present application can implement each process implemented by the method embodiment in FIG. 2 and achieve the same technical effect. To avoid repetition, details are not repeated here.
  • an embodiment of the present application further provides a communication device 1100, including a processor 1101, a memory 1102, a program or instruction stored in the memory 1102 and executable on the processor 1101,
  • a communication device 1100 including a processor 1101, a memory 1102, a program or instruction stored in the memory 1102 and executable on the processor 1101,
  • the communication device 1100 is a terminal or a network-side device
  • the program or instruction is executed by the processor 1101
  • each process of the above-mentioned embodiment of the method for sending communication information is realized, or the above-mentioned embodiment of the method for receiving communication information is realized. and can achieve the same technical effect, in order to avoid repetition, it will not be repeated here.
  • FIG. 12 is a schematic diagram of a hardware structure of a terminal implementing an embodiment of the present application.
  • the terminal 1200 includes but is not limited to: a radio frequency unit 1201, a network module 1202, an audio output unit 1203, an input unit 1204, a sensor 1205, a display unit 1206, a user input unit 1207, an interface unit 1208, a memory 1209, a processor 1210 and other components .
  • the terminal 1200 may also include a power source (such as a battery) for supplying power to various components, and the power source may be logically connected to the processor 1210 through a power management system, so as to manage charging, discharging, and power consumption through the power management system management and other functions.
  • a power source such as a battery
  • the terminal structure shown in FIG. 12 does not constitute a limitation on the terminal, and the terminal may include more or less components than shown, or combine some components, or arrange different components, which will not be repeated here.
  • the input unit 1204 may include a graphics processor (Graphics Processing Unit, GPU) 12041 and a microphone 12042. Such as camera) to obtain still pictures or video image data for processing.
  • the display unit 1206 may include a display panel 12061, which may be configured in the form of a liquid crystal display, an organic light emitting diode, or the like.
  • the user input unit 1207 includes a touch panel 12071 and other input devices 12072 .
  • the touch panel 12071 is also called a touch screen.
  • the touch panel 12071 may include two parts, a touch detection device and a touch controller.
  • Other input devices 12072 may include, but are not limited to, physical keyboards, function keys (such as volume control keys, switch keys, etc.), trackballs, mice, and joysticks, which are not described herein again.
  • the radio frequency unit 1201 receives the downlink data from the network side device, and then processes it to the processor 1210; in addition, sends the uplink data to the network side device.
  • the radio frequency unit 1201 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, and the like.
  • Memory 1209 may be used to store software programs or instructions as well as various data.
  • the memory 1209 may mainly include a stored program or instruction area and a storage data area, wherein the stored program or instruction area may store an operating system, an application program or instruction required for at least one function (such as a sound playback function, an image playback function, etc.) and the like.
  • the memory 1209 may include a high-speed random access memory, and may also include a non-volatile memory, wherein the non-volatile memory may be a read-only memory (Read-Only Memory, ROM), a programmable read-only memory (Programmable ROM, PROM) ), erasable programmable read-only memory (ErasablePROM, EPROM), electrically erasable programmable read-only memory (Electrically EPROM, EEPROM) or flash memory.
  • ROM Read-Only Memory
  • PROM programmable read-only memory
  • ErasablePROM ErasablePROM
  • EPROM electrically erasable programmable read-only memory
  • EEPROM electrically erasable programmable read-only memory
  • flash memory for example at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device.
  • the processor 1210 may include one or more processing units; optionally, the processor 1210 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs or instructions, etc. Modem processors mainly deal with wireless communications, such as baseband processors. It can be understood that, the above-mentioned modulation and demodulation processor may not be integrated into the processor 1210.
  • the processor 1210 is configured for the first communication device to divide the first communication information into one or more sub-band information, and input the broadband information and/or the one or more sub-band information of the first communication information to the first artificial Smart network model.
  • the radio frequency unit 1201 is configured to send the second communication information output by the first artificial intelligence network model.
  • the radio frequency unit 1201 is configured to receive the second communication information sent by the first communication device.
  • the processor 1210 is configured to input the second communication information into the second artificial intelligence network model to obtain broadband information and/or one or more subband information of the first communication information.
  • the network device 1300 includes: an antenna 1301 , a radio frequency device 1302 , and a baseband device 1303 .
  • the antenna 1301 is connected to the radio frequency device 1302 .
  • the radio frequency device 1302 receives information through the antenna 1301, and sends the received information to the baseband device 1303 for processing.
  • the baseband device 1303 processes the information to be sent and sends it to the radio frequency device 1302
  • the radio frequency device 1302 processes the received information and sends it out through the antenna 1301 .
  • the above-mentioned frequency band processing apparatus may be located in the baseband apparatus 1303 , and the method performed by the network side device in the above embodiments may be implemented in the baseband apparatus 1303 .
  • the baseband apparatus 1303 includes a processor 1304 and a memory 1305 .
  • the baseband device 1303 may include, for example, at least one baseband board on which a plurality of chips are arranged, as shown in FIG. 13 , one of the chips is, for example, the processor 1304 , which is connected to the memory 1305 to call a program in the memory 1305 to execute
  • the network devices shown in the above method embodiments operate.
  • the baseband device 1303 may further include a network interface 1306 for exchanging information with the radio frequency device 1302, and the interface is, for example, a common public radio interface (CPRI for short).
  • CPRI common public radio interface
  • the network-side device in this embodiment of the present application further includes: an instruction or program stored in the memory 1305 and executable on the processor 1304 , and the processor 1304 invokes the instruction or program in the memory 1305 to execute the instructions or programs shown in FIG. 9 or 10 .
  • the method executed by each module achieves the same technical effect. To avoid repetition, it is not repeated here.
  • An embodiment of the present application further provides a readable storage medium, where a program or an instruction is stored on the readable storage medium, and when the program or instruction is executed by a processor, the above-mentioned methods for sending communication information shown in FIG. 2 to FIG. 8 are implemented.
  • Each process of the embodiment, or each process of the above-mentioned embodiment of the method for receiving communication information shown in FIG. 2 to FIG. 8 will not be repeated here in order to avoid repetition.
  • the processor is the processor in the terminal described in the foregoing embodiment.
  • the readable storage medium includes a computer-readable storage medium, such as a computer read-only memory (Read-Only Memory, ROM), a random access memory (Random Access Memory, RAM), a magnetic disk or an optical disk, and the like.
  • An embodiment of the present application further provides a chip, where the chip includes a processor and a communication interface, the communication interface is coupled to the processor, and the processor is used to run a network-side device program or instruction, and implement the above-mentioned FIG. 2 to
  • the chip includes a processor and a communication interface
  • the communication interface is coupled to the processor
  • the processor is used to run a network-side device program or instruction, and implement the above-mentioned FIG. 2 to
  • the chip mentioned in the embodiments of the present application may also be referred to as a system-on-chip, a system-on-chip, a system-on-chip, or a system-on-a-chip, or the like.
  • An embodiment of the present application further provides a computer program product, the computer program product includes a processor, a memory, and a program or instruction stored on the memory and executable on the processor, the program or instruction being When the processor executes, each process of the above-mentioned embodiment of the method for sending communication information shown in FIG. 2 to FIG. 8 is realized, or each process of the embodiment of the above-mentioned method for receiving communication information shown in FIG. To achieve the same technical effect, in order to avoid repetition, details are not repeated here.
  • the chip mentioned in the embodiments of the present application may also be referred to as a system-on-chip, a system-on-chip, a system-on-chip, or a system-on-a-chip, or the like.

Landscapes

  • Engineering & Computer Science (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Software Systems (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Databases & Information Systems (AREA)
  • Medical Informatics (AREA)
  • Electromagnetism (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

本申请公开了一种通信信息的发送、接收方法及通信设备,属于无线通信技术领域。其中,一种通信信息的发送方法包括:第一通信设备将第一通信信息划分为一个或多个子带信息;将所述第一通信信息的宽带信息和/或所述一个或多个子带信息输入到第一人工智能网络模型,发送所述第一人工智能网络模型输出的第二通信信息。

Description

通信信息的发送、接收方法及通信设备
交叉引用
本发明要求在2020年10月23日提交中国专利局、申请号为202011149923.5、发明名称为“通信信息的发送、接收方法及通信设备”的中国专利申请的优先权,该申请的全部内容通过引用结合在本发明中。
技术领域
本申请属于无线通信技术领域,具体涉及一种通信信息的发送、接收方法及通信设备。
背景技术
目前,人工智能(Artificial Intelligence,AI)网络(也可以称为神经网络)在各个领域获得了广泛的应用。
然而,关于在通信信息的传输中使用AI网络,目前尚未给出比较好的解决方案。
发明内容
本申请实施例提供一种通信信息的发送、接收方法及通信设备,能够解决如何在通信信息的传输中使用AI网络的问题。
第一方面,提供了一种通信信息的发送方法,该方法包括:第一通信设备将第一通信信息划分为一个或多个子带信息;将所述第一通信信息的宽带信息和/或所述一个或多个子带信息输入到第一人工智能网络模型,并发送所 述第一人工智能网络模型输出的第二通信信息。
第二方面,提供了一种通信信息的发送装置,包括:预处理模块,用于将第一通信信息划分为一个或多个子带信息;第一输入模块,用于将所述第一通信信息的宽带信息和/或所述一个或多个子带信息输入到第一人工智能网络模型;发送模块,用于发送所述第一人工智能网络模型输出的第二通信信息。
第三方面,提供了一种通信信息的接收方法,该方法包括:第二通信设备接收第一通信设备发送的第二通信信息;将所述第二通信信息输入到第二人工智能网络模型,以得到第一通信信息的宽带信息和/或一个或多个子带信息。
第四方面,提供了一种通信信息的接收装置,包括:接收模块,用于接收第一通信设备发送的第二通信信息;第二输入模块,用于将所述第二通信信息输入到第二人工智能网络模型,以得到第一通信信息的宽带信息和/或一个或多个子带信息。
第五方面,提供了一种通信设备,该终端包括处理器、存储器及存储在所述存储器上并可在所述处理器上运行的程序或指令,所述程序或指令被所述处理器执行时实现如第一方面所述的方法的步骤,或者实现如第三方面所述的方法的步骤。
第六方面,提供了一种可读存储介质,所述可读存储介质上存储程序或指令,所述程序或指令被处理器执行时实现如第一方面所述的方法的步骤,或者实现如第三方面所述的方法的步骤。
第七方面,提供了一种芯片,所述芯片包括处理器和通信接口,所述通信接口和所述处理器耦合,所述处理器用于运行通信设备程序或指令,实现如第一方面所述的方法,或实现如第三方面所述的方法。
第八方面,提供了一种计算机程序产品,该计算机程序产品包括处理器、存储器及存储在所述存储器上并可在所述处理器上运行的程序或指令,所述 程序或指令被所述处理器执行时实现如第一方面所述的方法的步骤,或实现如第三方面所述的方法的步骤。
在本申请实施例中,第一通信设备在将第一通信信息划分为一个或多个子带信息,将所述第一通信信息的宽带信息和/或所述一个或多个子带信息作为第一人工智能网络模型的输入信息,输入到第一人工智能网络模型,从而得到待发送的第二通信信息,并发送第二通信信息。从而实现利用第一人工智能网络模型将原始的第一通信信息转换为待发送的第二通信信息,提升了通信系统的性能。
附图说明
图1示出本申请实施例可应用的一种无线通信系统的框图;
图2示出本申请实施例提供的一种通信信息的发送方法的流程图;
图3示出本申请实施例中的一种第一人工智能网络模型的结构示意图;
图4示出本申请实施例中的另一种第一人工智能网络模型的结构示意图;
图5示出本申请实施例中的又一种第一人工智能网络模型的结构示意图;
图6示出本申请实施例中的又一种第一人工智能网络模型的结构示意图;
图7示出本申请实施例提供的一种通信信息的接收方法的流程图;
图8示出本申请实施例中的一种第二人工智能网络模型的结构示意图;
图9示出本申请实施例提供的一种通信信息的发送装置的结构示意图;
图10示出本申请实施例提供的一种通信信息的接收装置的结构示意图;
图11示出本申请实施例提供的一种通信设备的结构示意图;
图12示出本申请实施例提供的一种终端的硬件结构示意图;
图13示出本申请实施例提供的一种网络侧设备的硬件结构示意图。
具体实施方式
下面将结合本申请实施例中的附图,对本申请实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例是本申请一部分实施例,而不是全部的实施例。基于本申请中的实施例,本领域普通技术人员所获得的所有其他实施例,都属于本申请保护的范围。
本申请的说明书和权利要求书中的术语“第一”、“第二”等是用于区别类似的对象,而不用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换,以便本申请的实施例能够以除了在这里图示或描述的那些以外的顺序实施,且“第一”、“第二”所区别的对象通常为一类,并不限定对象的个数,例如第一对象可以是一个,也可以是多个。此外,说明书以及权利要求中“和/或”表示所连接对象的至少其中之一,字符“/”一般表示前后关联对象是一种“或”的关系。
值得指出的是,本申请实施例所描述的技术不限于长期演进型(Long Term Evolution,LTE)/LTE的演进(LTE-Advanced,LTE-A)系统,还可用于其他无线通信系统,诸如码分多址(Code Division Multiple Access,CDMA)、时分多址(Time Division Multiple Access,TDMA)、频分多址(Frequency Division Multiple Access,FDMA)、正交频分多址(Orthogonal Frequency Division Multiple Access,OFDMA)、单载波频分多址(Single-carrier Frequency-Division Multiple Access,SC-FDMA)和其他系统。本申请实施例中的术语“系统”和“网络”常被可互换地使用,所描述的技术既可用于以上提及的系统和无线电技术,也可用于其他系统和无线电技术。以下描述出于示例目的描述了新空口(NewRadio,NR)系统,并且在以下大部分描述中使用NR术语,但是这些技术也可应用于NR系统应用以外的应用,如第6代(6 thGeneration,6G)通信系统。
图1示出本申请实施例可应用的一种无线通信系统的框图。无线通信系统包括终端11和网络侧设备12。其中,终端11也可以称作终端设备或者用户终端(User Equipment,UE),终端11可以是手机、平板电脑(Tablet  PersonalComputer)、膝上型电脑(Laptop Computer)或称为笔记本电脑、个人数字助理(Personal Digital Assistant,PDA)、掌上电脑、上网本、超级移动个人计算机(ultra-mobile personal computer,UMPC)、移动上网装置(Mobile Internet Device,MID)、可穿戴式设备(Wearable Device)或车载设备(VUE)、行人终端(PUE)等终端侧设备,可穿戴式设备包括:手环、耳机、眼镜等。需要说明的是,在本申请实施例并不限定终端11的具体类型。网络侧设备12可以是基站或核心网,其中,基站可被称为节点B、演进节点B、接入点、基收发机站(Base Transceiver Station,BTS)、无线电基站、无线电收发机、基本服务集(Basic Service Set,BSS)、扩展服务集(Extended Service Set,ESS)、B节点、演进型B节点(eNB)、家用B节点、家用演进型B节点、WLAN接入点、WiFi节点、发送接收点(TransmittingReceivingPoint,TRP)或所述领域中其他某个合适的术语,只要达到相同的技术效果,所述基站不限于特定技术词汇,需要说明的是,在本申请实施例中仅以NR系统中的基站为例,但是并不限定基站的具体类型。
下面结合附图,通过具体的实施例及其应用场景对本申请实施例提供的通信信息的发送方法进行详细地说明。
图2示出本申请实施例中的通信信息的发送方法的一种流程示意图,该方法200可以由通信设备执行。换言之,所述方法可以由安装在通信设备上的软件或硬件来执行。在本申请实施例中,通信设备可以为终端也可以为网络侧设备。如图2所示,该方法可以包括以下步骤。
S210,第一通信设备将第一通信信息划分为一个或多个子带信息。
在本申请实施例的一个可能的实现方式中,子带划分可以根据频域资源划分、时域资源划分、空域资源划分、码域资源划分等。因此,在该可能的实现方式中,S210可以包括:根据所述第一通信信息的目标资源,将所述第一通信信息划分为一个或多个子带信息,其中,所述目标资源包括以下至少之一:频域资源、时域资源、空域资源和码域资源。
在具体应用中,可选的,可以以预定的资源大小为单位,参考将第一通信信息划分为一个或多个子带信息。因此,在一个可能的实现方式中,第一通信设备将第一通信信息划分为一个或多个子带信息,包括以下至少之一:
(1)以频域单位资源为单位,在所述频域资源上将所述第一通信信息划分为一个或多个子带信息,其中,所述频域单位资源包括以下至少之一:资源块(Resource Block,RB)、物理资源块(Physical Resource Block,PRB、子带、预编码资源块组(Precoding Resource block Group,PRG)、以及带宽部分(Bandwidth Part,BWP)。也就是说,在该可能的实现方式中,可以将第一通信信息按照RB、PRB、PRG、子带或BWP进行划分,将第一通信信息的每一个或多个RB、PRB、PRG、子带或BWP上的信息划分为一个子带。
(2)以时域单位资源为单位,在所述时域资源上将所述第一通信信息划分为一个或多个子带信息,其中,所述时域单位资源包括以下至少之一:子载波、正交频分复用(Orthogonal frequency division multiplex,OFDM)符号、时隙、以及半时隙。也就是说,在该可能的实现方式中,可以将第一通信信息按照子载波、OFDM符号、时隙或半时隙进行划分,将第一通信信息的每一个或多个载波、OFDM符号、时隙或半时隙上的信息划分为一个子带。
(3)以空域单位资源为单位,在所述空域资源上将所述第一通信信息划分为一个或多个子带信息,其中,所述空域单位资源包括以下至少之一:天线、天线元、天线面板、发送接收单元、波束(包括模拟波束和数字波束)、层(Layer)、秩(Rank)、以及天线角度(例如,倾角)。也就是说,在该可能的实现方式中,可以将第一通信信息按照天线、天线元、天线面板、发送接收单元、波束(包括模拟波束和数字波束)、层(Layer)、秩(Rank)、以及天线角度(例如,倾角)进行划分。
(4)以码域单位资源为单位,在所述码域资源上将所述第一通信信息划分为一个或多个子带信息,其中,所述码域单位资源包括以下至少之一:正交码、准正交码、以及半正交码。也就是说,在该可能的实现方式中,可以 将第一通信信息按照正交码、准正交码、以及半正交码进行划分。
S212,将所述第一通信信息的宽带信息和/或所述一个或多个子带信息输入到第一人工智能网络模型,并发送所述第一人工智能网络模型输出的第二通信信息。
在本申请实施例中,第一人工智能网络(或者也可以称之为神经网络)模型用于对输入的第一通信信息的宽带信息和/或所述一个或多个子带信息进行处理,以输出与第一通信信息对应的第二通信信息,即待发送的信息。例如,第一人工智能网络模型可以根据第一通信信息的宽带信息对一个或多个子带信息编码,输出子带编码数据流(即第二通信信息),其中,第一通信信息可以为原始信号。其中,第一通信信息的宽带信息可以为表征第一通信信息的整体特征的信息。
在具体应用中,第一人工智能网络模型可以是预先建立好的网络模型,并通过训练可以输出与输入信息对应的数据流。
在一个可能的实现方式中,第一人工智能网络模型可以包括至少一级子模块,每一级子模块可以包括一个或多个子模块。
例如,在图3所示的第一人工智能网络模型的结构中,第一人工智能网络模型包括一级子模块,该级子模块中包括N个子模块,即子模块A-1至A-N,其中,N为输入的宽带信息和/或子带的数量,具体的,在图3中,输入的为N个子带,当然,并不限于此,在实际应用中,输入的还可以为一个宽带信息和N-1个子带信息。
或者,在图4所示的第一人工智能网络模型的结构中,第一人工智能网络模型包括两级子模块,其中,第一级子模块包括N个模块,即子模块A-1至A-N,第二级子模块包括一个子模块,即子模块B。可选地,第一人工智能网络模型包括多级子模块,比如子模块B后面还有子模块C、子模块D等。
在一个可能的实现方式,所述子模块可以包括以下至少之一:
(1)全连接神经网络模块;也就是说,子模块采用的人工智能网络类型 为全连接神经网络。
(2)卷积神经网络模块;也就是说,子模块采用的人工智能网络类型为卷积神经网络。
(3)循环神经网络模块;也就是说,子模块采用的人工智能网络类型为循环神经网络。
(4)残差神经网络模块;也就是说,子模块采用的人工智能网络类型为残差神经网络。
(5)预设算法模块。例如,根据输入信息求时间相关性和/或频率相关性、特征值分解、求特征值、求特征向量、计算信道容量、滤波、均衡等的算法模块。
在具体应用中,一个子模块可以包括多个小网络,每个小网络均可以采用上述之一的模块,不同小网络可以采用上述不同的模块,具体本申请实施例中不作限定。
在具体应用中,第一人工智能网络模型中的部分子模块可以采用相同的人工智能网络结构和/或采用相同的人工智能网络参数。
例如,在图4中,子模块A-i和子模块A-j采用相同的AI网络结构,但具体的权值、偏置的数值不同。或者,子模块A-i和子模块A-j采用相同的AI网络结构,并且具体的权值、偏置的数值相同。又或者,子模块A-i和子模块B,AI网络结构不同,而且具体的权值、偏置的数值也不同。其中,i=1,2,3,…,N,j=1,2,3,…,N,且i≠j。
在本申请实施例中,所述子模块采用的人工智能网络结构由以下至少之一确定:
(1)人工智能网络类型;例如,全连接神经网络、卷积神经网络、循环神经网络、或残差网络。
(2)包括的多个子网络的组合方式;即一个子模块包括多个小网络的情况下,各个小网络的组合方式。例如,全连接+卷积,卷积+残差等。
(3)隐藏层的层数;
(4)输入层与隐藏层的连接方式;
(5)多个隐藏层之间的连接方式;
(6)隐藏层与输入层的连接方式;
(7)每层神经元的数目。其中,不同层的神经元数目一般不同,也可能相同。
在一个可能的实现方式中,所述第一人工智能网络模型的一个目标子模块本次的输入信息包括以下至少之一:
(1)与所述目标子模块同级的其它子模块本次的输入信息;即目标子模块的输入信息可以包括同级的除所述目标子模块之外的其它子模块本次的输入信息,也就是说,该输入信息同时为目标子模块和与目标子模块同级的其它一个或多个子模块的输入。
(2)与所述目标子模块同级的其它子模块之前时刻的输入信息;其中,之前时刻的输入信息是指本次之前的输入信息,例如,上一次的输入信息。
(3)与所述目标子模块同级的其它子模块本次的中间信息。
(4)与所述目标子模块同级的其它子模块之前时刻的中间信息;
(5)与所述目标子模块同级的其它子模块的本次的输出信息;
(6)与所述目标子模块同级的其它子模块的之前时刻的输出信息;其中,之前时刻的输出信息是指本次之前的输出信息,例如,上一次的输出信息。
(7)所述目标子模块上一级的多个子模块输出信息的组合。
在上述可能的实现方式中,其他同级子模块为与目标子模块相邻的M个子模块,M为正整数。或者,其他同级子模块为跳过部分子模块与目标子模块相邻的M个子模块,例如,目标子模块为A-5,则其它同级子模块为A-7和A-3,或A-1和A-3和A-7和A-9和A-11,M为正整数。或者其他同级子模块包括除了目标子模块的所有其它同级子模块。
例如,在图4中,子模块A-i的输入信息包括本级子模块A-j的上次的 中间信息,或还包括本级子模块A-j的本次的输入信息。其中,i=1,2,3,…,N,j=1,2,3,…,N,且i≠j。
在本申请实施例中,可选的,第一人工智能网络模型的最后一级的子模块可以为一个或多个,对应的,第二通信信息可以为所述第一人工智能网络模型的最后一级的子模块的输出信息;或所述第一人工智能网络模型的最后一级的多个子模块输出信息的组合。
在本申请实施例的一个可选实施方式中,所述多个子模块输出信息的组合可以包括:所述多个子模块的输出信息合并后得到的一维向量或二维矩阵或多维矩阵;例如,在图3中,可以将多个子模块A-i的输出信息,合并为一个大的一维向量,或者二维矩阵,或者多维矩阵直接输入。又例如,在图4中,可以将多个子模块A-i的输出信息,合并为一个大的一维向量,或者二维矩阵,或者多维矩阵直接输入作为下一级的输入,例如作为子模块B的输入。
在本申请实施例的另一个可选实施方式中,所述多个子模块输出信息的组合可以包括:所述多个子模块的输出信息按照预设算法进行计算后得到的结果。其中,预设算法包括但不限于加权和/或其它数学操作。例如,加权可以包括线性平均、乘性平均及其它常见平均方法的组合。数学操作可以包括加减乘数、N次方、n次开根号、对数、求导、求偏导等各种常见数学操作的组合。n为任意数。例如,n可以为正数或负数或0,或者也可以为实数或复数,具体本实施例中不作限定。
在一个可能的实现方式中,所述第一人工智能网络模型包括第一级子模块和第二级子模块,其中,第一级子模块包括一个或多个第一子模块,所述第二级子模块位于所述第一级子模块的前一级,且所述第二级子模块包括N个第二子模块,其中,N为输入所述第一人工智能网络模型的宽带信息和/或子带的数量。
例如,在图4中,所述第一人工智能网络模型包括第一级子模块(包括 子模块B)和第二级子模块(包括子模块A-1,A-2,…,A-N)。
或者,在图5中,所述第一人工智能网络模型包括第一级子模块(包括子模块B-1和B-2)和第二级子模块(包括子模块A-1,A-2,…,A-N)。
在一个可能的实现方式中,所述第一级子模块包括多个第一子模块,多个所述第一子模块中的至少一个第一子模块表示带宽信息,多个所述第一子模块中的其它第一子模块表示子带信息,其中,所述其它第一子模块为所述多个第一子模块中除所述至少一个第一子模块之外的部分或全部第一子模块。
例如,若第二通信信息是预编码矩阵指示(Precoding matrix indicator,PMI),则PMI分为宽带PMI和子带PMI,或者,也可以称为PMI的宽带信息或宽带部分、PMI的子带信息或子带部分。
例如,在图5中,子模块B-1表示宽带信息,子模块B-2表示子带信息。可选地,子模块B-2可以继续划分为多个子模块。例如,子模块B-2-1、子模块B-2-2、….、子模块B-2-L,其中L为正整数。可选地,L等于子带数目N。
可选地,通过所述至少一个第一子模块得到所述第二通信信息的宽带信息。例如,在图5中,通过子模块B-1的输出(不需要子模块B-2的输出),可以得到第二通信信息的全宽带信息。即第二通信信息的全宽带特征。
可选的,通过所述至少一个第一子模块和所述其它第一子模块得到所述第二通信信息的子带信息。也就是说,没有所述至少一个第一子模块的输出,仅靠所述其它第一子模块,无法得到第二通信信息的子带信息。例如,在图5中,没有子模块B-1的输出,仅靠子模块B-2,无法得到第二通信信息的子带信息。
可选地,通过所述其它第一子模块得到所述第二通信信息的子带信息。也就是说,仅靠所述其它第一子模块,可以得到第二通信信息的子带信息。例如,在图5中,没有子模块B-1的输出,仅靠子模块B-2,可以得到第二通信信息的子带信息。
在一个可能的实现方式中,所述至少一个第一子模块的输入信息为部分 或全部所述第二子模块的输出信息;所述其它第一子模块的输入信息为部分或全部所述第二子模块的输出信息。可选的,所述至少一个第一子模块的输入信息与所述其它第一子模块的输入信息可以不同。例如,在图5中,子模块B-1的输入信息可以为部分子模块A(即A-1至A-N中的部分子模块)的输出信息,子模块B-2的输入信息可以为部分子模块A(即A-1至A-N中的部分子模块)的输出信息。其中,子模块B-1的输入信息与子模块B-2的输入信息可以相同,也可以不同。例如,子模块B-1的输入信息可以为全部子模块A(即A-1至A-N中的全部子模块)的输出信息,而当子模块B-2可以继续划分为多个子模块时,例如子模块B-2-1、子模块B-2-2、….、子模块B-2-L,子模块B-2-i的输入信息为子模块A-i,其中i=1,2,3,…,N。
在上述可能的实现方式中,可选的所述第一人工智能网络模型还包括第三级子模块,所述第三级子模块位于所述第二级子模块的前一级。
例如,在图6中,所述第一人工智能网络模型还包括子模块C,子模块C位于子模块A-1至A-N的前一级。
可选的,所述第三级子模块包括一个第三子模块,所述第三子模块的输入信息为所述第一通信信息的宽带信息和/或所述一个或多个子带信息。例如,在图6中,子模块C的输入信息为第一通信信息的N个子带信息)。也就是说,在该可能的实现方式中,所述第一通信信息的宽带信息和/或所述一个或多个子带信息先进入第三子模块进行统一处理,然后再输出进入第二级子模块。
在该可能的实现方式中,第二级子模块中的各个第二子模块的输入信息可以相同,也可以不同。或者,第二级子模块中的一个第二子模块的输入信息可以为第三子模块的全部输出信息,或者,第二级子模块中的一个第二子模块的输入信息可以为第三子模块的部分输出信息。
可选的,一个所述第二子模块的输入信息为所述第三子模块全部输出信息。也就是说,第三子模块的输出信息作为其后一级的各个第二子模块的输 入信息。
或者,一个所述第二子模块的输入信息为所述第三子模块部分输出信息,且不同所述第二子模块的输入信息不同。例如,在图6中,子模块C的输入信息包括N部分,每部分作为一个子模块A-i的输入信息。可选的,一个子模块A-i对应一个子带信息i。
或者,在另一个可能的实现方式中,在图6第一人工智能网络模型也可以不包括第一级子模块,即不包括子模块B,或不包括子模块B-1和子模块B-2)。
在本申请实施例的一个可能的实现方式中,所述第二通信信息包括以下之一:
(1)参考信号;即用于信号处理的参考信号。例如,可以包括用于信号检测、滤波、均衡等的参考信号。所述参考信号包括但不限于:解调参考信号(Demodulation Reference Signal,DMRS)、探测参考信号(Sounding Reference Signal,SRS)、同步信号/物理广播信道信号块(或同步信号块)(Synchronization Signal and PBCH block,SSB)、跟踪参考信号(Tracking Reference Signal,TRS)、相位TRS(Phase-TRS,PTRS)、信道状态信息(Channel State Information,CSI)参考信号(CSI Reference Signal,CSI-RS)等。
(2)信道承载的信号;其中,信道包括但不限于物理下行控制信道(Physical downlink control channel,PDCCH)、物理下行共享信道(Physical downlink shared channel,PDSCH)、物理上行控制信道(Physical Uplink Control Channel,PUCCH)、物理上行共享信道(Physical Uplink Shared Channel,PUSCH)、物理随机接入信道(Physical Random Access Channel,PRACH)、物理广播信道(Physical broadcast channel,PBCH)等。
(3)信道状态信息。
例如,信道状态信息可以包括:
(3-1)、信道状态信息反馈信息。包括但不限于信道相关信息、信道矩 阵相关信息、信道特征信息、信道矩阵特征信息、PMI、秩指示(Rank indicator,RI)、CSI-RS资源指示(CSI-RS Resource Indicator,CRI)、信道质量指示(Channel quality indicator,CQI)、层指示(Layer Indicator,LI)等。
(3-2)、频分复用(Frequency Division Duplex,FDD)上下行部分互易性的信道状态信息。
其中,对于FDD系统,根据部分互异性,基站根据上行信道获取角度和时延信息,可以通过CSI-RS预编码或者直接指示的方法,将角度信息和时延信息通知UE,UE根据基站的指示上报或者在基站的指示范围内选择并上报,从而减少UE的计算量和CSI上报的开销。
(4)波束信息;包括但不限于:波束质量、波束的指示信息(例如,参考信号ID)、波束失败指示信息、波束失败恢复中的新波束指示信息。还可以用于波束管理的波束信息,包括:波束测量、波束上报、波束预测、波束失败检测、波束失败恢复、波束失败恢复中的新波束指示。
(5)信道预测信息;可以包括信道状态信息的预测、波束预测等。
(6)干扰信息;包括但不限于小区内干扰、小区间干扰、带外干扰、交调干扰等信息。
(7)定位信息;
(8)轨迹信息;
网络侧设备可以通过参考信号(例如SRS),估计出的UE的具体位置(包括水平位置和/或垂直位置)或未来可能的轨迹,或辅助位置估计或轨迹估计的信息。
(9)高层业务和参数的预测信息,以及高层业务和参数的管理信息;包括但不限于:吞吐量、所需数据包大小、业务需求、移动速度、噪声信息等。
(10)控制信令。例如,功率控制的相关信令以及波束管理的相关信令等。
在本申请实施例中,可以通过第一人工智能网络模型获取待发送的第二 通信信息,并且,第一人工智能网络模型的结构比较简单,能够有效降低AI网络的复杂度,从而提升通信系统的性能。
图7示出本申请实施例中的通信信息的接收方法的一种流程示意图,该方法700可以由通信设备执行。换言之,所述方法可以由安装在通信设备上的软件或硬件来执行。在本申请实施例中,通信设备可以为终端也可以为网络侧设备。如图7所示,该方法可以包括以下步骤。
S710,第二通信设备接收第一通信设备发送的第二通信信息。
在本申请实施例中,第一通信设备可以采用上述方法200发送第二通信信息,或者,第一通信设备也可以采用其它的方式发送第二通信信息,具体本实施例中不作限定。
在本申请实施例中,第二通信信息可以为编码数据流。
S712,将所述第二通信信息输入到第二人工智能网络模型,以得到第一通信信息的宽带信息和/或一个或多个子带信息。
在本申请实施例中,第二人工智能网络模型用于对接收到的第二通信信息进行解码,以得到第一通信信息的宽带信息和/或一个或多个子带信息。第二人工智能网络模型可以预先进行训练,从而使得第二人工智能网络模型可以输出与输入的第二通信信息对应的宽带信息和/或一个或多个子带信息。
在一个可能的实现方式中,在得到第一通信信息的宽带信息和/或一个或多个子带信息之后,第二通信设备还可以根据宽带信息和/或一个或多个子带信息,恢复子带信息的分布状态,通过时频转换,恢复原始信息,即第一通信信息。
在本申请实施例中,第二人工智能网络模型可以采用与第一人工智能网络模型相似的人工智能网络模型。下面主要对第二人工智能网络模型的部分内容进行描述,其它部分与第一人工智能网络模型相似或对应,具体可以参见方法200中对第一人工智能网络模型的描述,在此不再赘述。
在一个可能的实现方式中,所述第二人工智能网络模型包括至少一级子 模块,每级包括一个或多个子模块。
例如,在图8中,所述第二人工智能网络模型包括两级子模块,其中,第一级子模块包括一个子模块B,第二级子模块包括N个子模块A,即A-1至A-N,其中,N为第一通信信息的宽带信息和/或一个或多个子带信息的数量。
在一个可能的实现方式中,所述子模块可以包括以下至少之一:
(1)全连接神经网络模块;
(2)卷积神经网络模块;
(3)循环神经网络模块;
(4)残差神经网络模块;
(5)预设算法模块。
在一个可能的实现方式中,所述第二人工智能网络模型的部分所述子模块可以采用相同的人工智能网络结构和/或采用相同的人工智能网络参数。
在一个可能的实现方式中,所述子模块采用的人工智能网络结构由以下至少之一确定:
(1)人工智能网络类型;
(2)包括的多个子网络的组合方式;
(3)隐藏层的层数;
(4)输入层与隐藏层的连接方式;
(5)多个隐藏层之间的连接方式;
(6)隐藏层与输入层的连接方式;
(7)每层神经元的数目。
在一个可能的实现方式中,所述第二人工智能网络模型的一个目标子模块本次的输入信息包括以下至少之一:
(1)与所述目标子模块同级的其它子模块本次的输入信息;
(2)与所述目标子模块同级的其它子模块之前时刻的输入信息;
(3)与所述目标子模块同级的其它子模块本次的中间信息;
(4)与所述目标子模块同级的其它子模块之前时刻的中间信息;
(5)与所述目标子模块同级的其它子模块的本次的输出信息;
(6)与所述目标子模块同级的其它子模块的之前时刻的输出信息;
(7)所述目标子模块上一级的多个子模块输出信息的组合。
在一个可能的实现方式中,所述多个子模块输出的组合包括:
(1)所述多个子模块的输出信息合并后得到的一维向量或二维矩阵或多维矩阵;或,
(2)所述多个子模块的输出信息按照预设算法进行计算后得到的结果。具体可以参见方法200中的相关描述。
在一个可能的实现方式中,所述第二人工智能网络模型可以包括第一级子模块和第二级子模块,其中,第一级子模块包括至少一个第一子模块,所述第二级子模块位于所述第一级子模块的后一级,且所述第二级子模块包括N个第二子模块,其中,N为所述第二人工智能网络模型输出的宽带信息和/或子带信息的数量。
在上述可能的实现方式中,可选的,所述第一级子模块包括多个第一子模块,多个所述第一子模块中的至少一个第一子模块表示带宽信息,多个所述第一子模块中的其它第一子模块表示子带信息,其中,所述其它第一子模块为所述多个第一子模块中除所述至少一个第一子模块之外的部分或全部第一子模块。
例如,至少一个第一子模块的输入信息可以为第二通信信息的全宽带信息,即全部的宽带特征,所述其它第一子模块的输入信息可以包括第二通信信息的全宽带信息以及所述第二通信信息的子带信息。
在一个可能的实现方式中,一个所述第二子模块的输入信息包括所述至少一个第一子模块的输出信息和/或所述其它第一子模块的输出信息。
例如,所述至少一个第一子模块的输出信息为N个部分,分别输入到各 个第二子模块,所述其它第一子模块的输出信息为N个部分,分别输入到各个第二子模块。
在一个可能的实现方式,所述第二人工智能网络模型还包括第三级子模块,所述第三级子模块位于所述第二级子模块的后一级。通过第三级子模块,可以对第二级子模块中的各个第二子模块的输出信息进行统一处理后输出。
在上述可能的实现方式中,可选的,所述第三级子模块可以包括一个第三子模块,所述第三子模块的输出信息为所述第一通信信息的宽带信息和/或一个或多个子带信息。
在上述可能的实现方式中,可选的,所述第三子模块的输入信息为多个所述第二子模块输出信息的组合。例如,第三子模块的输入信息可以为各个第二子模块的输出信息合并后得到的一维向量或二维矩阵或多维矩阵,或者,各个第二子模块的输出信息进行加权平均后得到的信息。
在一个可能的实现方式中,与方法200相似,所述第二通信信息包括以下之一:
参考信号;
信道承载的信号;
信道状态信息;
波束信息;
信道预测信息;
干扰信息;
定位信息;
轨迹信息;
高层业务和参数的预测信息;
高层业务和参数的管理信息;
控制信令。
具体可以参见方法200中的相关描述。
需要说明的是,本申请实施例提供的通信信息的发送方法,执行主体可以为通信信息的发送装置,或者,该通信信息的发送装置中的用于执行通信信息的发送方法的控制模块。本申请实施例中以通信信息的发送装置执行通信信息的发送方法为例,说明本申请实施例提供的通信信息的发送装置。
图9示出本申请实施例提供的一种通信信息的发送装置的结构示意图,如图9所示,该通信信息的发送装置900可以包括:预处理模块901用于将第一通信信息划分为一个或多个子带信息;第一输入模块902,用于将所述第一通信信息的宽带信息和/或所述一个或多个子带信息输入到第一人工智能网络模型;发送模块903,用于发送所述第一人工智能网络模型输出的第二通信信息。
在一个可能的实现方式中,所述预处理模块901将第一通信信息划分为一个或多个子带信息,包括
根据所述第一通信信息的目标资源,将所述第一通信信息划分为一个或多个子带信息,其中,所述目标资源包括以下至少之一:频域资源、时域资源、空域资源和码域资源。
在一个可能的实现方式中,所述预处理模块901将第一通信信息划分为一个或多个子带信息,包括以下至少之一:
以频域单位资源为单位,在所述频域资源上将所述第一通信信息划分为一个或多个子带信息,其中,所述频域单位资源包括以下至少之一:资源块RB、物理资源块PRB、子带、预编码资源块组PRG、以及带宽部分BWP;
以时域单位资源为单位,在所述时域资源上将所述第一通信信息划分为一个或多个子带信息,其中,所述时域单位资源包括以下至少之一:子载波、OFDM符号、时隙、以及半时隙;
以空域单位资源为单位,在所述空域资源上将所述第一通信信息划分为一个或多个子带信息,其中,所述空域单位资源包括以下至少之一:天线、天线元、天线面板、发送接收单元、波束、层、秩、以及天线角度;
以码域单位资源为单位,在所述码域资源上将所述第一通信信息划分为一个或多个子带信息,其中,所述码域单位资源包括以下至少之一:正交码、准正交码、以及半正交码。
在一个可能的实现方式中,所述第一人工智能网络模型包括至少一级子模块,每级包括一个或多个子模块。
在一个可能的实现方式中,所述子模块包括以下至少之一:全连接神经网络模块;卷积神经网络模块;循环神经网络模块;残差神经网络模块;预设算法模块。
在一个可能的实现方式中,部分所述子模块采用相同的人工智能网络结构和/或采用相同的人工智能网络参数。
在一个可能的实现方式中,所述子模块采用的人工智能网络结构由以下至少之一确定:
人工智能网络类型;
包括的多个子网络的组合方式;
隐藏层的层数;
输入层与隐藏层的连接方式;
多个隐藏层之间的连接方式;
隐藏层与输入层的连接方式;
每层神经元的数目。
在一个可能的实现方式中,所述第一人工智能网络模型的一个目标子模块本次的输入信息包括以下至少之一:
与所述目标子模块同级的其它子模块本次的输入信息;
与所述目标子模块同级的其它子模块之前时刻的输入信息;
与所述目标子模块同级的其它子模块本次的中间信息;
与所述目标子模块同级的其它子模块之前时刻的中间信息;
与所述目标子模块同级的其它子模块的本次的输出信息;
与所述目标子模块同级的其它子模块的之前时刻的输出信息;
所述目标子模块上一级的多个子模块输出信息的组合。
在一个可能的实现方式中,所述第二通信信息包括:所述第一人工智能网络模型的最后一级的子模块的输出信息;或所述第一人工智能网络模型的最后一级的多个子模块输出信息的组合。
在一个可能的实现方式中,所述多个子模块输出信息的组合包括:
所述多个子模块的输出信息合并后得到的一维向量或二维矩阵或多维矩阵;或,
所述多个子模块的输出信息按照预设算法进行计算后得到的结果。
在一个可能的实现方式中,所述第一人工智能网络模型包括第一级子模块和第二级子模块,其中,第一级子模块包括一个或多个第一子模块,所述第二级子模块位于所述第一级子模块的前一级,且所述第二级子模块包括N个第二子模块,其中,N为输入所述第一人工智能网络模型的宽带信息和/或子带的数量。
在一个可能的实现方式中,所述第一级子模块包括多个第一子模块,多个所述第一子模块中的至少一个第一子模块表示带宽信息,多个所述第一子模块中的其它第一子模块表示子带信息,其中,所述其它第一子模块为所述多个第一子模块中除所述至少一个第一子模块之外的部分或全部第一子模块。
在一个可能的实现方式中,通过所述至少一个第一子模块得到所述第二通信信息的宽带信息;和/或,通过所述至少一个第一子模块和所述其它第一子模块得到所述第二通信信息的子带信息。
在一个可能的实现方式中,所述至少一个第一子模块的输入信息为部分或全部所述第二子模块的输出信息;所述其它第一子模块的输入信息为部分或全部所述第二子模块的输出信息。
在一个可能的实现方式中,所述第一人工智能网络模型还包括第三级子模块,所述第三级子模块位于所述第二级子模块的前一级。
在一个可能的实现方式中,所述第三级子模块包括一个第三子模块,所述第三子模块的输入信息为所述第一通信设备的宽带信息和/或所述一个或多个子带信息。
在一个可能的实现方式中,一个所述第二子模块的输入信息为所述第三子模块全部输出信息。
在一个可能的实现方式中,一个所述第二子模块的输入信息为所述第三子模块部分输出信息,且不同所述第二子模块的输入信息不同。
在一个可能的实现方式中,所述第二通信信息包括以下之一:
参考信号;
信道承载的信号;
信道状态信息;
波束信息;
信道预测信息;
干扰信息;
定位信息;
轨迹信息;
高层业务和参数的预测信息;
高层业务和参数的管理信息;
控制信令。
本申请实施例中的通信信息的发送装置可以是装置,也可以是终端或网络侧设备中的部件、集成电路、或芯片。该装置可以是移动终端,也可以为非移动终端。示例性的,移动终端可以包括但不限于上述所列举的终端11的类型,非移动终端可以为服务器、网络附属存储器(Network Attached Storage,NAS)、个人计算机(personal computer,PC)、电视机(television,TV)、柜员机或者自助机等,本申请实施例不作具体限定。
本申请实施例中的通信信息的发送装置可以为具有操作系统的装置。该 操作系统可以为安卓(Android)操作系统,可以为ios操作系统,还可以为其他可能的操作系统,本申请实施例不作具体限定。
本申请实施例提供的通信信息的发送装置能够实现图2的方法实施例实现的各个过程,并达到相同的技术效果,为避免重复,这里不再赘述。
图10示出本申请实施例提供的一种通信信息的接收装置的结构示意图,如图10所示,该通信信息的接收装置1000可以包括:接收模块1001,用于接收第一通信设备发送的第二通信信息;第二输入模块1002,用于将所述第二通信信息输入到第二人工智能网络模型,以得到第一通信信息的宽带信息和/或一个或多个子带信息。
在一个可能的实现方式中,所述第二人工智能网络模型包括至少一级子模块,每级包括一个或多个子模块。
在一个可能的实现方式中,所述子模块包括以下至少之一:
全连接神经网络模块;
卷积神经网络模块;
循环神经网络模块;
残差神经网络模块;
预设算法模块。
在一个可能的实现方式中,部分所述子模块采用相同的人工智能网络结构和/或采用相同的人工智能网络参数。
在一个可能的实现方式中,所述子模块采用的人工智能网络结构由以下至少之一确定:
人工智能网络类型;
包括的多个子网络的组合方式;
隐藏层的层数;
输入层与隐藏层的连接方式;
多个隐藏层之间的连接方式;
隐藏层与输入层的连接方式;
每层神经元的数目。
在一个可能的实现方式中,所述第二人工智能网络模型的一个目标子模块本次的输入信息包括以下至少之一:
与所述目标子模块同级的其它子模块本次的输入信息;
与所述目标子模块同级的其它子模块之前时刻的输入信息;
与所述目标子模块同级的其它子模块本次的中间信息;
与所述目标子模块同级的其它子模块之前时刻的中间信息;
与所述目标子模块同级的其它子模块的本次的输出信息;
与所述目标子模块同级的其它子模块的之前时刻的输出信息;
所述目标子模块上一级的多个子模块输出信息的组合。
在一个可能的实现方式中,所述多个子模块输出信息的组合包括:
所述多个子模块的输出信息合并后得到的一维向量或二维矩阵或多维矩阵;或,
所述多个子模块的输出信息按照预设算法进行计算后得到的结果。
在一个可能的实现方式中,所述第二人工智能网络模型包括第一级子模块和第二级子模块,其中,第一级子模块包括至少一个第一子模块,所述第二级子模块位于所述第一级子模块的后一级,且所述第二级子模块包括N个第二子模块,其中,N为所述第二人工智能网络模型输出的宽带信息和/或子带信息的数量。
在一个可能的实现方式中,所述第一级子模块包括多个第一子模块,多个所述第一子模块中的至少一个第一子模块表示带宽信息,多个所述第一子模块中的其它第一子模块表示子带信息,其中,所述其它第一子模块为所述多个第一子模块中除所述至少一个第一子模块之外的部分或全部第一子模块。
在一个可能的实现方式中,一个所述第二子模块的输入信息包括所述至少一个第一子模块的输出信息和/或所述其它第一子模块的输出信息。
在一个可能的实现方式中,所述第二人工智能网络模型还包括第三级子模块,所述第三级子模块位于所述第二级子模块的后一级。
在一个可能的实现方式中,所述第三级子模块包括一个第三子模块,所述第三子模块的输出信息为所述第一通信信息的宽带信息和/或一个或多个子带信息。
在一个可能的实现方式中,所述第三子模块的输入为多个所述第二子模块输出信息的组合。
在一个可能的实现方式中,所述第二通信信息包括以下之一:
参考信号;
信道承载的信号;
信道状态信息;
波束信息;
信道预测信息;
干扰信息;
定位信息;
轨迹信息;
高层业务和参数的预测信息;
高层业务和参数的管理信息;
控制信令。
本申请实施例中的通信信息的接收装置可以是装置,也可以是终端或网络侧设备中的部件、集成电路、或芯片。该装置可以是移动终端,也可以为非移动终端。示例性的,移动终端可以包括但不限于上述所列举的终端11的类型,非移动终端可以为服务器、网络附属存储器(Network Attached Storage,NAS)、个人计算机(personal computer,PC)、电视机(television,TV)、柜员机或者自助机等,本申请实施例不作具体限定。
本申请实施例中的通信信息的接收装置可以为具有操作系统的装置。该 操作系统可以为安卓(Android)操作系统,可以为ios操作系统,还可以为其他可能的操作系统,本申请实施例不作具体限定。
本申请实施例提供的通信信息的接收装置能够实现图2的方法实施例实现的各个过程,并达到相同的技术效果,为避免重复,这里不再赘述。
可选的,如图11所示,本申请实施例还提供一种通信设备1100,包括处理器1101,存储器1102,存储在存储器1102上并可在所述处理器1101上运行的程序或指令,例如,该通信设备1100为终端或网络侧设备时,该程序或指令被处理器1101执行时实现上述的通信信息的发送方法实施例的各个过程,或者,实现上述的通信信息的接收方法实施例的各个过程,且能达到相同的技术效果,为避免重复,这里不再赘述。
图12为实现本申请实施例的一种终端的硬件结构示意图。
该终端1200包括但不限于:射频单元1201、网络模块1202、音频输出单元1203、输入单元1204、传感器1205、显示单元1206、用户输入单元1207、接口单元1208、存储器1209、以及处理器1210等部件。
本领域技术人员可以理解,终端1200还可以包括给各个部件供电的电源(比如电池),电源可以通过电源管理系统与处理器1210逻辑相连,从而通过电源管理系统实现管理充电、放电、以及功耗管理等功能。图 12中示出的终端结构并不构成对终端的限定,终端可以包括比图示更多或更少的部件,或者组合某些部件,或者不同的部件布置,在此不再赘述。
应理解的是,本申请实施例中,输入单元1204可以包括图形处理器(Graphics Processing Unit,GPU)12041和麦克风12042,图形处理器12041对在视频捕获模式或图像捕获模式中由图像捕获装置(如摄像头)获得的静态图片或视频的图像数据进行处理。显示单元1206可包括显示面板12061,可以采用液晶显示器、有机发光二极管等形式来配置显示面板12061。用户输入单元1207包括触控面板12071以及其他输入设备12072。触控面板12071,也称为触摸屏。触控面板12071可包括触摸检测装置和触摸控制器两个部分。 其他输入设备12072可以包括但不限于物理键盘、功能键(比如音量控制按键、开关按键等)、轨迹球、鼠标、操作杆,在此不再赘述。
本申请实施例中,射频单元1201将来自网络侧设备的下行数据接收后,给处理器1210处理;另外,将上行的数据发送给网络侧设备。通常,射频单元1201包括但不限于天线、至少一个放大器、收发信机、耦合器、低噪声放大器、双工器等。
存储器1209可用于存储软件程序或指令以及各种数据。存储器1209可主要包括存储程序或指令区和存储数据区,其中,存储程序或指令区可存储操作系统、至少一个功能所需的应用程序或指令(比如声音播放功能、图像播放功能等)等。此外,存储器1209可以包括高速随机存取存储器,还可以包括非易失性存储器,其中,非易失性存储器可以是只读存储器(Read-OnlyMemory,ROM)、可编程只读存储器(ProgrammableROM,PROM)、可擦除可编程只读存储器(ErasablePROM,EPROM)、电可擦除可编程只读存储器(ElectricallyEPROM,EEPROM)或闪存。例如至少一个磁盘存储器件、闪存器件、或其他非易失性固态存储器件。
处理器1210可包括一个或多个处理单元;可选的,处理器1210可集成应用处理器和调制解调处理器,其中,应用处理器主要处理操作系统、用户界面和应用程序或指令等,调制解调处理器主要处理无线通信,如基带处理器。可以理解的是,上述调制解调处理器也可以不集成到处理器1210中。
处理器1210,用于第一通信设备将第一通信信息划分为一个或多个子带信息,将所述第一通信信息的宽带信息和/或所述一个或多个子带信息输入到第一人工智能网络模型。
射频单元1201,用于发送所述第一人工智能网络模型输出的第二通信信息。
或者,
射频单元1201,用于接收第一通信设备发送的第二通信信息。
处理器1210,用于将所述第二通信信息输入到第二人工智能网络模型,以得到第一通信信息的宽带信息和/或一个或多个子带信息。
具体地,本申请实施例还提供了一种网络侧设备。如图13所示,该网络设备1300包括:天线1301、射频装置1302、基带装置1303。天线1301与射频装置1302连接。在上行方向上,射频装置1302通过天线1301接收信息,将接收的信息发送给基带装置1303进行处理。在下行方向上,基带装置1303对要发送的信息进行处理,并发送给射频装置1302,射频装置1302对收到的信息进行处理后经过天线1301发送出去。
上述频带处理装置可以位于基带装置1303中,以上实施例中网络侧设备执行的方法可以在基带装置1303中实现,该基带装置1303包括处理器1304和存储器1305。
基带装置1303例如可以包括至少一个基带板,该基带板上设置有多个芯片,如图13所示,其中一个芯片例如为处理器1304,与存储器1305连接,以调用存储器1305中的程序,执行以上方法实施例中所示的网络设备操作。
该基带装置1303还可以包括网络接口1306,用于与射频装置1302交互信息,该接口例如为通用公共无线接口(common public radio interface,简称CPRI)。
具体地,本申请实施例的网络侧设备还包括:存储在存储器1305上并可在处理器1304上运行的指令或程序,处理器1304调用存储器1305中的指令或程序执行图9或10所示各模块执行的方法,并达到相同的技术效果,为避免重复,故不在此赘述。
本申请实施例还提供一种可读存储介质,所述可读存储介质上存储有程序或指令,该程序或指令被处理器执行时实现上述图2至图8所示的通信信息的发送方法实施例的各个过程,或实现上述图2至图8所示的通信信息的接收方法实施例的各个过程,且能达到相同的技术效果,为避免重复,这里不再赘述。
其中,所述处理器为上述实施例中所述的终端中的处理器。所述可读存储介质,包括计算机可读存储介质,如计算机只读存储器(Read-Only Memory,ROM)、随机存取存储器(Random Access Memory,RAM)、磁碟或者光盘等。
本申请实施例另提供了一种芯片,所述芯片包括处理器和通信接口,所述通信接口和所述处理器耦合,所述处理器用于运行网络侧设备程序或指令,实现上述图2至图8所示的通信信息的发送方法实施例的各个过程,或实现上述图2至图8所示的通信信息的接收方法实施例的各个过程,且能达到相同的技术效果,为避免重复,这里不再赘述。
应理解,本申请实施例提到的芯片还可以称为系统级芯片,系统芯片,芯片系统或片上系统芯片等。
本申请实施例另提供了一种计算机程序产品,该计算机程序产品包括处理器、存储器及存储在所述存储器上并可在所述处理器上运行的程序或指令,所述程序或指令被所述处理器执行时实现上述图2至图8所示的通信信息的发送方法实施例的各个过程,或实现上述图2至图8所示的通信信息的接收方法实施例的各个过程,且能达到相同的技术效果,为避免重复,这里不再赘述。
应理解,本申请实施例提到的芯片还可以称为系统级芯片,系统芯片,芯片系统或片上系统芯片等。
需要说明的是,在本文中,术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含,从而使得包括一系列要素的过程、方法、物品或者装置不仅包括那些要素,而且还包括没有明确列出的其他要素,或者是还包括为这种过程、方法、物品或者装置所固有的要素。在没有更多限制的情况下,由语句“包括一个……”限定的要素,并不排除在包括该要素的过程、方法、物品或者装置中还存在另外的相同要素。此外,需要指出的是,本申请实施方式中的方法和装置的范围不限按示出或讨论的顺序来执行功能,还 可包括根据所涉及的功能按基本同时的方式或按相反的顺序来执行功能,例如,可以按不同于所描述的次序来执行所描述的方法,并且还可以添加、省去、或组合各种步骤。另外,参照某些示例所描述的特征可在其他示例中被组合。
通过以上的实施方式的描述,本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现,当然也可以通过硬件,但很多情况下前者是更佳的实施方式。基于这样的理解,本申请的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来,该计算机软件产品存储在一个存储介质(如ROM/RAM、磁碟、光盘)中,包括若干指令用以使得一台终端(可以是手机,计算机,服务器,或者网络设备等)执行本申请各个实施例所述的方法。
上面结合附图对本申请的实施例进行了描述,但是本申请并不局限于上述的具体实施方式,上述的具体实施方式仅仅是示意性的,而不是限制性的,本领域的普通技术人员在本申请的启示下,在不脱离本申请宗旨和权利要求所保护的范围情况下,还可做出很多形式,均属于本申请的保护之内。

Claims (44)

  1. 一种通信信息的发送方法,包括:
    第一通信设备将第一通信信息划分为一个或多个子带信息;
    将所述第一通信信息的宽带信息和/或所述一个或多个子带信息输入到第一人工智能网络模型,并发送所述第一人工智能网络模型输出的第二通信信息。
  2. 根据权利要求1所述的方法,其中,第一通信设备将第一通信信息划分为一个或多个子带信息,包括:
    根据所述第一通信信息的目标资源,将所述第一通信信息划分为一个或多个子带信息,其中,所述目标资源包括以下至少之一:频域资源、时域资源、空域资源和码域资源。
  3. 根据权利要求2所述的方法,其中,第一通信设备将第一通信信息划分为一个或多个子带信息,包括以下至少之一:
    以频域单位资源为单位,在所述频域资源上将所述第一通信信息划分为一个或多个子带信息,其中,所述频域单位资源包括以下至少之一:资源块RB、物理资源块PRB、子带、预编码资源块组PRG、以及带宽部分BWP;
    以时域单位资源为单位,在所述时域资源上将所述第一通信信息划分为一个或多个子带信息,其中,所述时域单位资源包括以下至少之一:子载波、正交频分复用OFDM符号、时隙、以及半时隙;
    以空域单位资源为单位,在所述空域资源上将所述第一通信信息划分为一个或多个子带信息,其中,所述空域单位资源包括以下至少之一:天线、天线元、天线面板、发送接收单元、波束、层、秩、以及天线角度;
    以码域单位资源为单位,在所述码域资源上将所述第一通信信息划分为一个或多个子带信息,其中,所述码域单位资源包括以下至少之一:正交码、准正交码、以及半正交码。
  4. 根据权利要求1所述的方法,其中,所述第一人工智能网络模型包括至少一级子模块,每级包括一个或多个子模块。
  5. 根据权利要求4所述的方法,其中,所述子模块包括以下至少之一:
    全连接神经网络模块;
    卷积神经网络模块;
    循环神经网络模块;
    残差神经网络模块;
    预设算法模块。
  6. 根据权利要求4所述的方法,其中,部分所述子模块采用相同的人工智能网络结构和/或采用相同的人工智能网络参数。
  7. 根据权利要求4所述的方法,其中,所述子模块采用的人工智能网络结构由以下至少之一确定:
    人工智能网络类型;
    包括的多个子网络的组合方式;
    隐藏层的层数;
    输入层与隐藏层的连接方式;
    多个隐藏层之间的连接方式;
    隐藏层与输入层的连接方式;
    每层神经元的数目。
  8. 根据权利要求4所述的方法,其中,所述第一人工智能网络模型的一个目标子模块本次的输入信息包括以下至少之一:
    与所述目标子模块同级的其它子模块本次的输入信息;
    与所述目标子模块同级的其它子模块之前时刻的输入信息;
    与所述目标子模块同级的其它子模块本次的中间信息;
    与所述目标子模块同级的其它子模块之前时刻的中间信息;
    与所述目标子模块同级的其它子模块的本次的输出信息;
    与所述目标子模块同级的其它子模块的之前时刻的输出信息;
    所述目标子模块上一级的多个子模块输出信息的组合。
  9. 根据权利要求4所述的方法,其中,所述第二通信信息包括:所述第 一人工智能网络模型的最后一级的子模块的输出信息;或所述第一人工智能网络模型的最后一级的多个子模块输出信息的组合。
  10. 根据权利要求8或9所述的方法,其中,所述多个子模块输出信息的组合包括:
    所述多个子模块的输出信息合并后得到的一维向量或二维矩阵或多维矩阵;或,
    所述多个子模块的输出信息按照预设算法进行计算后得到的结果。
  11. 根据权利要求4所述的方法,其中,所述第一人工智能网络模型包括第一级子模块和第二级子模块,其中,第一级子模块包括一个或多个第一子模块,所述第二级子模块位于所述第一级子模块的前一级,且所述第二级子模块包括N个第二子模块,其中,N为输入所述第一人工智能网络模型的宽带信息和/或子带的数量。
  12. 根据权利要求11所述的方法,其中,所述第一级子模块包括多个第一子模块,多个所述第一子模块中的至少一个第一子模块表示带宽信息,多个所述第一子模块中的其它第一子模块表示子带信息,其中,所述其它第一子模块为所述多个第一子模块中除所述至少一个第一子模块之外的部分或全部第一子模块。
  13. 根据权利要求12所述的方法,其中,
    通过所述至少一个第一子模块得到所述第二通信信息的宽带信息;和/或,
    通过所述至少一个第一子模块和所述其它第一子模块得到所述第二通信信息的子带信息。
  14. 根据权利要求12所述的方法,其中,所述至少一个第一子模块的输入信息为部分或全部所述第二子模块的输出信息;所述其它第一子模块的输入信息为部分或全部所述第二子模块的输出信息。
  15. 根据权利要求11所述的方法,其中,所述第一人工智能网络模型还包括第三级子模块,所述第三级子模块位于所述第二级子模块的前一级。
  16. 根据权利要求15所述的方法,其中,所述第三级子模块包括一个第三子模块,所述第三子模块的输入信息为所述第一通信设备的宽带信息和/或所述一个或多个子带信息。
  17. 根据权利要求16所述的方法,其中,一个所述第二子模块的输入信息为所述第三子模块全部输出信息。
  18. 根据权利要求17所述的方法,其中,一个所述第二子模块的输入信息为所述第三子模块部分输出信息,且不同所述第二子模块的输入信息不同。
  19. 根据权利要求1至18任一项所述的方法,其中,所述第二通信信息包括以下之一:
    参考信号;
    信道承载的信号;
    信道状态信息;
    波束信息;
    信道预测信息;
    干扰信息;
    定位信息;
    轨迹信息;
    高层业务和参数的预测信息;
    高层业务和参数的管理信息;
    控制信令。
  20. 根据权利要求1至18任一项所述的方法,其中,所述第一通信设备为终端或网络侧设备。
  21. 一种通信信息的接收方法,包括:
    第二通信设备接收第一通信设备发送的第二通信信息;
    将所述第二通信信息输入到第二人工智能网络模型,以得到第一通信信息的宽带信息和/或一个或多个子带信息。
  22. 根据权利要求21所述的方法,其中,所述第二人工智能网络模型包 括至少一级子模块,每级包括一个或多个子模块。
  23. 根据权利要求22所述的方法,其中,所述子模块包括以下至少之一:
    全连接神经网络模块;
    卷积神经网络模块;
    循环神经网络模块;
    残差神经网络模块;
    预设算法模块。
  24. 根据权利要求22所述的方法,其中,部分所述子模块采用相同的人工智能网络结构和/或采用相同的人工智能网络参数。
  25. 根据权利要求22所述的方法,其中,所述子模块采用的人工智能网络结构由以下至少之一确定:
    人工智能网络类型;
    包括的多个子网络的组合方式;
    隐藏层的层数;
    输入层与隐藏层的连接方式;
    多个隐藏层之间的连接方式;
    隐藏层与输入层的连接方式;
    每层神经元的数目。
  26. 根据权利要求22所述的方法,其中,所述第二人工智能网络模型的一个目标子模块本次的输入信息包括以下至少之一:
    与所述目标子模块同级的其它子模块本次的输入信息;
    与所述目标子模块同级的其它子模块之前时刻的输入信息;
    与所述目标子模块同级的其它子模块本次的中间信息;
    与所述目标子模块同级的其它子模块之前时刻的中间信息;
    与所述目标子模块同级的其它子模块的本次的输出信息;
    与所述目标子模块同级的其它子模块的之前时刻的输出信息;
    所述目标子模块上一级的多个子模块输出信息的组合。
  27. 根据权利要求26所述的方法,其中,所述多个子模块输出信息的组合包括:
    所述多个子模块的输出信息合并后得到的一维向量或二维矩阵或多维矩阵;或,
    所述多个子模块的输出信息按照预设算法进行计算后得到的结果。
  28. 根据权利要求22所述的方法,其中,所述第二人工智能网络模型包括第一级子模块和第二级子模块,其中,第一级子模块包括至少一个第一子模块,所述第二级子模块位于所述第一级子模块的后一级,且所述第二级子模块包括N个第二子模块,其中,N为所述第二人工智能网络模型输出的宽带信息和/或子带信息的数量。
  29. 根据权利要求28所述的方法,其中,所述第一级子模块包括多个第一子模块,多个所述第一子模块中的至少一个第一子模块表示带宽信息,多个所述第一子模块中的其它第一子模块表示子带信息,其中,所述其它第一子模块为所述多个第一子模块中除所述至少一个第一子模块之外的部分或全部第一子模块。
  30. 根据权利要求28所述的方法,其中,一个所述第二子模块的输入信息包括所述至少一个第一子模块的输出信息和/或所述其它第一子模块的输出信息。
  31. 根据权利要求28所述的方法,其中,所述第二人工智能网络模型还包括第三级子模块,所述第三级子模块位于所述第二级子模块的后一级。
  32. 根据权利要求31所述的方法,其中,所述第三级子模块包括一个第三子模块,所述第三子模块的输出信息为所述第一通信信息的宽带信息和/或一个或多个子带信息。
  33. 根据权利要求31所述的方法,其中,所述第三子模块的输入为多个所述第二子模块输出信息的组合。
  34. 根据权利要求21至33任一项所述的方法,其中,所述第二通信信息包括以下之一:
    参考信号;
    信道承载的信号;
    信道状态信息;
    波束信息;
    信道预测信息;
    干扰信息;
    定位信息;
    轨迹信息;
    高层业务和参数的预测信息;
    高层业务和参数的管理信息;
    控制信令。
  35. 根据权利要求21至33任一项所述的方法,其中,所述第二通信设备为终端或网络侧设备。
  36. 一种通信信息的发送装置,包括:
    预处理模块,用于将第一通信信息划分为一个或多个子带信息;
    第一输入模块,用于将所述第一通信信息的宽带信息和/或所述一个或多个子带信息输入到第一人工智能网络模型;
    发送模块,用于发送所述第一人工智能网络模型输出的第二通信信息。
  37. 根据权利要求36所述的装置,其中,所述预处理模块将第一通信信息划分为一个或多个子带信息,包括:
    根据所述第一通信信息的目标资源,将所述第一通信信息划分为一个或多个子带信息,其中,所述目标资源包括以下至少之一:频域资源、时域资源、空域资源和码域资源。
  38. 根据权利要求37所述的装置,其中,所述预处理模块将第一通信信息划分为一个或多个子带信息,包括以下至少之一:
    以频域单位资源为单位,在所述频域资源上将所述第一通信信息划分为一个或多个子带信息,其中,所述频域单位资源包括以下至少之一:资源块 RB、物理资源块PRB、子带、预编码资源块组PRG、以及带宽部分BWP;
    以时域单位资源为单位,在所述时域资源上将所述第一通信信息划分为一个或多个子带信息,其中,所述时域单位资源包括以下至少之一:子载波、OFDM符号、时隙、以及半时隙;
    以空域单位资源为单位,在所述空域资源上将所述第一通信信息划分为一个或多个子带信息,其中,所述空域单位资源包括以下至少之一:天线、天线元、天线面板、发送接收单元、波束、层、秩、以及天线角度;
    以码域单位资源为单位,在所述码域资源上将所述第一通信信息划分为一个或多个子带信息,其中,所述码域单位资源包括以下至少之一:正交码、准正交码、以及半正交码。
  39. 一种通信信息的接收装置,包括:
    接收模块,用于接收第一通信设备发送的第二通信信息;
    第二输入模块,用于将所述第二通信信息输入到第二人工智能网络模型,以得到第一通信信息的宽带信息和/或一个或多个子带信息。
  40. 根据权利要求39所述的装置,其中,所述第二人工智能网络模型包括至少一级子模块,每级包括一个或多个子模块。
  41. 根据权利要求40所述的装置,其中,所述第二人工智能网络模型的一个目标子模块本次的输入信息包括以下至少之一:
    与所述目标子模块同级的其它子模块本次的输入信息;
    与所述目标子模块同级的其它子模块之前时刻的输入信息;
    与所述目标子模块同级的其它子模块本次的中间信息;
    与所述目标子模块同级的其它子模块之前时刻的中间信息;
    与所述目标子模块同级的其它子模块的本次的输出信息;
    与所述目标子模块同级的其它子模块的之前时刻的输出信息;
    所述目标子模块上一级的多个子模块输出信息的组合。
  42. 根据权利要求39至41任一项所述的装置,其中,所述第二通信信息包括以下之一:
    参考信号;
    信道承载的信号;
    信道状态信息;
    波束信息;
    信道预测信息;
    干扰信息;
    定位信息;
    轨迹信息;
    高层业务和参数的预测信息;
    高层业务和参数的管理信息;
    控制信令。
  43. 一种通信设备,包括处理器,存储器及存储在所述存储器上并可在所述处理器上运行的程序或指令,所述程序或指令被所述处理器执行时实现如权利要求1至20任一项所述的通信信息的发送方法的步骤,或者实现如权利要求21至35任一项所述的通信信息的接收方法的步骤。
  44. 一种可读存储介质,所述可读存储介质上存储程序或指令,所述程序或指令被所述处理器执行时实现如权利要求1至20任一项所述的通信信息的发送方法的步骤,或者实现如权利要求21至35任一项所述的通信信息的接收方法的步骤。
PCT/CN2021/124911 2020-10-23 2021-10-20 通信信息的发送、接收方法及通信设备 WO2022083619A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
JP2023524933A JP2023550690A (ja) 2020-10-23 2021-10-20 通信情報の送信、受信方法及び通信機器
EP21882034.8A EP4220486A4 (en) 2020-10-23 2021-10-20 METHOD FOR SENDING COMMUNICATION INFORMATION, METHOD FOR RECEIVING COMMUNICATION INFORMATION, AND COMMUNICATION DEVICE
US18/137,807 US20230261815A1 (en) 2020-10-23 2023-04-21 Communication Information Sending Method, Communication Information Receiving Method, and Communication Device

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202011149923.5A CN114501353B (zh) 2020-10-23 2020-10-23 通信信息的发送、接收方法及通信设备
CN202011149923.5 2020-10-23

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US18/137,807 Continuation US20230261815A1 (en) 2020-10-23 2023-04-21 Communication Information Sending Method, Communication Information Receiving Method, and Communication Device

Publications (1)

Publication Number Publication Date
WO2022083619A1 true WO2022083619A1 (zh) 2022-04-28

Family

ID=81291585

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/124911 WO2022083619A1 (zh) 2020-10-23 2021-10-20 通信信息的发送、接收方法及通信设备

Country Status (5)

Country Link
US (1) US20230261815A1 (zh)
EP (1) EP4220486A4 (zh)
JP (1) JP2023550690A (zh)
CN (1) CN114501353B (zh)
WO (1) WO2022083619A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117674926A (zh) * 2022-08-12 2024-03-08 大唐移动通信设备有限公司 信道状态信息处理方法及装置

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109245861A (zh) * 2018-10-29 2019-01-18 广州海格通信集团股份有限公司 一种采用深层人工神经网络的物理层通信方法
US20190274108A1 (en) * 2018-03-02 2019-09-05 DeepSig Inc. Learning communication systems using channel approximation
WO2020035683A1 (en) * 2018-08-15 2020-02-20 Imperial College Of Science, Technology And Medicine Joint source channel coding for noisy channels using neural networks
CN111614439A (zh) * 2020-05-20 2020-09-01 北京邮电大学 一种信息传输方法、系统、装置及电子设备
CN112446463A (zh) * 2019-08-31 2021-03-05 安徽寒武纪信息科技有限公司 一种神经网络全连接层运算方法、装置以及相关产品

Family Cites Families (23)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
BRPI0717890B1 (pt) * 2006-11-01 2021-01-12 Qualcomm Incorporated método e sistema para facilitar gerenciamento de recursos de célula e memória legível por computador
CN102243140B (zh) * 2011-04-18 2013-01-23 杨彦利 一种基于子带信号分析的机械设备状态监测方法
CN104954142B (zh) * 2015-06-11 2017-06-20 哈尔滨工程大学 一种子带拼接的宽带数据采集装置
CN105070293B (zh) * 2015-08-31 2018-08-21 武汉大学 基于深度神经网络的音频带宽扩展编码解码方法及装置
CN107203807B (zh) * 2016-03-16 2020-10-02 中国科学院计算技术研究所 神经网络加速器的片上缓存带宽均衡方法、系统及其装置
AU2016410568B2 (en) * 2016-06-21 2022-03-24 Intrinsic Innovation Llc System and method for a recursive cortical network
CN108347776B (zh) * 2017-01-25 2023-11-10 华为技术有限公司 一种通信系统中资源分配的方法及设备
CN108811098B (zh) * 2017-05-02 2021-05-04 华为技术有限公司 确定时隙格式的方法、终端设备和网络设备
CN107347208B (zh) * 2017-06-27 2020-02-07 阳光凯讯(北京)科技有限公司 基于人工智能技术的基站对终端高效定时调整方法及系统
CN109275190B (zh) * 2017-07-17 2021-10-26 华为技术有限公司 一种通信方法及装置
US10853977B2 (en) * 2017-08-30 2020-12-01 Korea Advanced Institute Of Science And Technology Apparatus and method for reconstructing image using extended neural network
US20200372412A1 (en) * 2018-01-03 2020-11-26 Signify Holding B.V. System and methods to share machine learning functionality between cloud and an iot network
US10283140B1 (en) * 2018-01-12 2019-05-07 Alibaba Group Holding Limited Enhancing audio signals using sub-band deep neural networks
CN108449286B (zh) * 2018-03-01 2020-07-03 北京邮电大学 网络带宽资源分配方法及装置
CN111461296B (zh) * 2018-12-29 2023-09-22 中科寒武纪科技股份有限公司 数据处理方法、电子设备和可读存储介质
CN111524536B (zh) * 2019-02-01 2023-09-08 富士通株式会社 信号处理方法和信息处理设备
CN109919315B (zh) * 2019-03-13 2021-10-01 科大讯飞股份有限公司 一种神经网络的前向推理方法、装置、设备及存储介质
CN110995327B (zh) * 2019-12-17 2021-05-04 电子科技大学 一种多载波mimo系统的混合波束成形优化方法及系统
CN111223493B (zh) * 2020-01-08 2022-08-02 北京声加科技有限公司 语音信号降噪处理方法、传声器和电子设备
CN115242365A (zh) * 2020-01-14 2022-10-25 北京紫光展锐通信技术有限公司 探测参考信号传输方法及相关产品
CN111458676B (zh) * 2020-03-05 2022-03-29 北京邮电大学 一种基于级联神经网络的波达方向估计方法及装置
CN111508519B (zh) * 2020-04-03 2022-04-26 北京达佳互联信息技术有限公司 一种音频信号人声增强的方法及装置
CN111582461B (zh) * 2020-05-21 2023-04-14 中国人民解放军国防科技大学 神经网络训练方法、装置、终端设备和可读存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190274108A1 (en) * 2018-03-02 2019-09-05 DeepSig Inc. Learning communication systems using channel approximation
WO2020035683A1 (en) * 2018-08-15 2020-02-20 Imperial College Of Science, Technology And Medicine Joint source channel coding for noisy channels using neural networks
CN109245861A (zh) * 2018-10-29 2019-01-18 广州海格通信集团股份有限公司 一种采用深层人工神经网络的物理层通信方法
CN112446463A (zh) * 2019-08-31 2021-03-05 安徽寒武纪信息科技有限公司 一种神经网络全连接层运算方法、装置以及相关产品
CN111614439A (zh) * 2020-05-20 2020-09-01 北京邮电大学 一种信息传输方法、系统、装置及电子设备

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4220486A4 *

Also Published As

Publication number Publication date
EP4220486A4 (en) 2024-04-17
CN114501353A (zh) 2022-05-13
CN114501353B (zh) 2024-01-05
US20230261815A1 (en) 2023-08-17
EP4220486A1 (en) 2023-08-02
JP2023550690A (ja) 2023-12-05

Similar Documents

Publication Publication Date Title
CN114363921B (zh) Ai网络参数的配置方法和设备
US20230262506A1 (en) Beam reporting method, beam information determining method, and related device
US11290171B2 (en) Method and apparatus for signal detection in a MIMO communication system
CN108141777A (zh) 基于通信系统的干扰特性控制用户设备操作的装置和方法
WO2022105913A1 (zh) 通信方法、装置及通信设备
US20230244911A1 (en) Neural network information transmission method and apparatus, communication device, and storage medium
WO2022199664A1 (zh) 信息发送方法和设备
US20230261815A1 (en) Communication Information Sending Method, Communication Information Receiving Method, and Communication Device
CN115378769B (zh) 数据传输方法、装置、通信设备及存储介质
US20240088970A1 (en) Method and apparatus for feeding back channel information of delay-doppler domain, and electronic device
US20230291658A1 (en) Method for Processing Partial Input Missing of AI Network, and Device
US11411600B2 (en) Processing of uplink data streams
US20230299910A1 (en) Communications data processing method and apparatus, and communications device
WO2023198058A1 (zh) 信息传输方法、装置、终端及网络侧设备
WO2023198094A1 (zh) 模型输入的确定方法及通信设备
US20230388158A1 (en) Ai-augmented channel estimation
WO2022184011A1 (zh) 信息处理方法、装置、通信设备及可读存储介质
WO2024041421A1 (zh) 测量反馈处理方法、装置、终端及网络侧设备

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: 21882034

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2023524933

Country of ref document: JP

ENP Entry into the national phase

Ref document number: 2021882034

Country of ref document: EP

Effective date: 20230424

NENP Non-entry into the national phase

Ref country code: DE