WO2022105913A1 - 通信方法、装置及通信设备 - Google Patents

通信方法、装置及通信设备 Download PDF

Info

Publication number
WO2022105913A1
WO2022105913A1 PCT/CN2021/132073 CN2021132073W WO2022105913A1 WO 2022105913 A1 WO2022105913 A1 WO 2022105913A1 CN 2021132073 W CN2021132073 W CN 2021132073W WO 2022105913 A1 WO2022105913 A1 WO 2022105913A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
sub
network
communication
pieces
Prior art date
Application number
PCT/CN2021/132073
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 EP21894060.9A priority Critical patent/EP4250663A4/en
Publication of WO2022105913A1 publication Critical patent/WO2022105913A1/zh
Priority to US18/200,546 priority patent/US20230291517A1/en

Links

Images

Classifications

    • 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
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L5/00Arrangements affording multiple use of the transmission path
    • H04L5/003Arrangements for allocating sub-channels of the transmission path
    • H04L5/0044Arrangements for allocating sub-channels of the transmission path allocation of payload
    • H04L5/0046Determination of how many bits are transmitted on different sub-channels
    • 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
    • H04L41/08Configuration management of networks or network elements
    • H04L41/0803Configuration setting
    • H04L41/0823Configuration setting characterised by the purposes of a change of settings, e.g. optimising configuration for enhancing reliability
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/04Architecture, e.g. interconnection topology
    • G06N3/045Combinations of networks
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/14Network analysis or design
    • H04L41/145Network analysis or design involving simulating, designing, planning or modelling of a network
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L5/00Arrangements affording multiple use of the transmission path
    • H04L5/0001Arrangements for dividing the transmission path
    • H04L5/0014Three-dimensional division
    • H04L5/0016Time-frequency-code
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L5/00Arrangements affording multiple use of the transmission path
    • H04L5/003Arrangements for allocating sub-channels of the transmission path
    • H04L5/0058Allocation criteria
    • H04L5/0073Allocation arrangements that take into account other cell interferences
    • 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

Definitions

  • the present application belongs to the field of wireless communication technologies, and in particular relates to a communication method, apparatus and communication device.
  • AI networks also called neural networks
  • neural networks have been widely used in various fields.
  • the input size of an AI network is generally fixed. If inputs of different sizes are required, an AI network needs to be constructed for each input size. In a practical application environment, the input of the AI network may change at any time. For example, in the field of communication technology, when the original information to be sent is generated through an AI network into a data stream that can be transmitted through a wireless network, the size of the original information to be sent is usually not fixed. An AI network, which leads to an excessive number of AI networks stored in communication devices, increasing the storage pressure of communication devices.
  • Embodiments of the present application provide a method, an apparatus, and a communication device for sending communication information, which can solve the problem of too many AI networks stored in the communication device.
  • a method for sending communication information including: a first communication device divides the first communication information into n pieces of first target subband information; A first sub-AI network of an artificial intelligence AI network model, wherein the maximum input amount of the first sub-AI network is N sub-band information, the maximum input amount of the first AI network is M sub-band information, n, Both M and N are integers greater than 0, and n ⁇ N ⁇ M; the second communication information output by the first sub-AI network is sent.
  • a device for sending communication information comprising: a division module for dividing the first communication information into n pieces of first target subband information; an input module for dividing the n pieces of first target subband information
  • the sub-band information is input to the first sub-AI network of the first artificial intelligence AI network model, wherein the maximum input amount of the first sub-AI network is N sub-band information, and the maximum input amount of the first AI network is M pieces of subband information, where n, M, and N are all integers greater than 0, and n ⁇ N ⁇ M;
  • a sending module configured to send the second communication information output by the first sub-AI network.
  • a communication device 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 processor When executed, the steps of the method as described in the first aspect are implemented.
  • a readable storage medium is provided, and a program or an instruction is stored on the readable storage medium, and when the program or instruction is executed by a processor, the steps of the method according to the first aspect are implemented.
  • a chip in a fifth aspect, includes a processor and a communication interface, the communication interface is coupled to the processor, and the processor is configured to run a terminal program or instruction to implement the first aspect method steps.
  • 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 The processor implements the steps of the method as described in the first aspect when executed.
  • the first communication device divides the first communication information into n pieces of first target subband information, and inputs the n pieces of first target subband information into the first sub AI of the first AI network model network, wherein the maximum input amount of the first sub-AI network is N sub-band information, and the maximum input amount of the first AI network is M sub-band information, n ⁇ N ⁇ M, and then send the first sub-AI network output second communication information.
  • the first AI network module includes multiple sub-AI networks, and the multiple sub-AI networks can be laid out in a nested manner, and each sub-AI network corresponds to a different maximum input amount, so that the actual input information can be
  • the size of the AI network can be selected and input to the corresponding sub-AI network, which reduces the number of stored AI network models, simplifies the complexity of the AI network, and improves the performance of the communication system.
  • FIG. 1 shows a schematic diagram of a wireless communication system to which an embodiment of the present application can be applied
  • FIG. 2 shows a schematic flowchart of a method for sending communication information provided by an embodiment of the present application
  • FIG. 3 shows a schematic structural diagram of an AI network model provided by an embodiment of the present application
  • FIG. 4 shows a schematic structural diagram of another AI network model provided by an embodiment of the present application.
  • FIG. 5 shows a schematic structural diagram of another AI network model provided by an embodiment of the present application.
  • FIG. 6 shows a schematic structural diagram of another AI network model provided by an embodiment of the present application.
  • FIG. 7 shows a schematic structural diagram of another AI network model provided by an embodiment of the present application.
  • FIG. 8 shows a schematic structural diagram of another AI network model provided by an embodiment of the present application.
  • FIG. 9 shows a schematic structural diagram of another AI network model provided by an embodiment of the present application.
  • FIG. 10 shows a schematic structural diagram of another AI network model provided by an embodiment of the present application.
  • FIG. 11a shows a schematic structural diagram of another AI network model provided by an embodiment of the present application.
  • FIG. 11b shows a schematic structural diagram of another AI network model provided by an embodiment of the present application.
  • FIG. 12 shows a schematic structural diagram of an apparatus for sending communication information provided by an embodiment of the present application.
  • FIG. 13 shows a schematic structural diagram of a communication device provided by an embodiment of the present application.
  • FIG. 14 shows a schematic diagram of the hardware structure of a terminal provided by an embodiment of the present application.
  • FIG. 15 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 schematic diagram of a wireless communication system to which an embodiment 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 computer Assistant (Personal Digital Assistant, PDA), handheld computer, 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, headphones, glasses, etc.
  • PDA Personal Digital Assistant
  • 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 apparatus 200 may be executed by a first communication device.
  • the apparatus may be executed by software or hardware installed on the first communication device.
  • the method may include the following steps.
  • the first communication device divides the first communication information into n pieces of first target 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 manner, S210 may include: dividing the first communication information into one or more first target subband information according to the target resource of the first communication information, wherein the target The resources include at least one of the following: frequency domain resources, time domain resources, spatial domain resources, code domain resources, time delay domain resources, Doppler domain resources, Fourier transform domain resources, S domain resources, Z domain resources, and others Resource of type transform domain.
  • the S-domain means that in the frequency domain analysis, the imaginary exponent exp(j ⁇ t) is used as the basic signal, and any signal can be decomposed into many imaginary exponent components of different frequencies.
  • the Z domain is the domain resulting from the Z transform. Among them, the Z transformation is a classical transformation in mathematics.
  • 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 (1) to (4).
  • 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: subcarriers: , Resource Block (Resource Block, RB), Physical Resource Block (Physical Resource Block, PRB, subband, Precoding Resource Block Group (PRG), and Bandwidth Part (Bandwidth Part, BWP). That is to say , in this possible implementation manner, the first communication information may be divided according to RBs, PRBs, PRGs, subbands or BWPs, and each one or more RBs, PRBs, PRGs, subbands or BWPs of the first communication information The information on is divided into a subband.
  • subcarriers includes at least one of the following: subcarriers: , Resource Block (Resource Block, RB), Physical Resource Block (Physical Resource Block, PRB, subband, Precoding Resource Block Group (PRG), and Bandwidth Part (Bandwidth Part, BWP). That is to say , in
  • 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: a symbol, a A slot, half-slot, frame, subframe, radio frame, millisecond, second, or other unit of time. That is to say, in this possible implementation manner, the first communication information may be divided according to symbols, time slots, half-slots, frames, subframes, radio frames, milliseconds, seconds or other time units, and the first communication Information over each symbol, slot, half-slot, frame, subframe, radio frame, millisecond, second, or other unit of time of information is divided into a subband.
  • the symbols include but are not limited to orthogonal frequency division multiplex (Orthogonal frequency division multiplex, OFDM) symbols.
  • 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 according to orthogonal codes, quasi-orthogonal codes, and semi-orthogonal codes.
  • S212 Input the n pieces of first target subband information into the first sub-AI network of the first artificial intelligence AI network model, wherein the maximum input amount of the first sub-AI network is N pieces of subband information, and the The maximum input quantity of the first AI network is M subband information, where n, M, and N are all integers greater than 0, and n ⁇ N ⁇ M.
  • the first artificial intelligence network (or it may also be called a neural network) model is used to process the input subband information to output the second communication information corresponding to the first communication information, that is, the waiting information 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 maximum input amount of the first AI network model is M subband information
  • the first AI network model can input information of different sizes
  • the first AI network model can include multiple sub-AI networks, wherein the large The sub-AI network when the information is input can include the sub-AI network when the small information is input, or it can be said that a sub-AI network when the large information is input can be constructed based on the sub-AI network when the small information is input.
  • each sub-AI network may correspond to a maximum input amount, and each sub-AI network may be set in a nested manner.
  • the maximum input amount of the first-layer sub-AI network of the first AI network model is M
  • the sub-AI network can nest a sub-AI network with a maximum input of i and a sub-AI network with a maximum input of (M-i)
  • a sub-AI network with a maximum input of (M-i) which can be nested
  • a sub-AI network with a maximum input size of i and a sub-AI network with an input size of (M-2i) are set up in such a loop nesting.
  • S214 Send the second communication information output by the first sub-AI network.
  • the first AI network module includes multiple sub-AI networks, and the multiple sub-AI networks can be laid out in a nested manner, and each sub-AI network corresponds to a different maximum input amount, so that the actual input information can be
  • the size of the AI network can be selected and input to the corresponding sub-AI network, which reduces the number of stored AI network models, simplifies the complexity of the AI network, and improves the performance of the communication system.
  • the n pieces of the first target subbands when the n pieces of the first target subband information are input into the first sub-AI network of the first artificial intelligence AI network model, the n pieces of the first target subbands may be The band information is arranged and input to the first sub-AI network in a predetermined order, wherein the predetermined order includes: an order in which the identifiers of the n pieces of the first target sub-band information are from large to small or from small to large.
  • n pieces of the first target subband information when inputting n pieces of the first target subband information into the first sub-AI network of the first artificial intelligence AI network model, if the first sub-AI The input amount of the network is fixed as N sub-band information, then n pieces of the first target sub-band information and N-n invalid sub-band information are input into the first sub-AI network, wherein, the n pieces of the first target sub-band information are Band information is located at the specified location. For example, if the input of the first sub-AI network is fixed 10 sub-bands, but currently there are only 4 valid sub-bands, the input is 123xxxxxx4, where x indicates that the sub-band has no valid input. When a certain subband has no valid input, default information (such as all-zero information), a mathematical combination of at least one valid subband information, or other information can be used as the input of the subband.
  • the size of the second communication information is a fixed value, or the size of the second communication information is determined by the quantity of the input first target subband information. That is to say, in this possible implementation manner, the overhead of the second communication information may be fixed, or may be changed according to the change of the input amount.
  • the size of the second communication information is proportional to the amount of the inputted first target subband information.
  • the inputted number of subbands X1 corresponds to the overhead of the second communication information is Y1
  • the overhead of the second communication information is Y1*N.
  • the increment of the size of the second communication information is proportional to the increment of the quantity of the inputted first target subband information.
  • the number of input subbands X1+X2 corresponds to the overhead of the second communication information is Y1+Y2.
  • the overhead of the second communication information is Y1+Y2*N.
  • X1 is the base output/number of base subbands
  • X2 is the additional input using the nested structure.
  • the first AI network model may also be trained, so that each network parameter of the first AI network model is determined. Therefore, in this possible implementation, before S210, the method may further include: using a plurality of training samples to train the first AI network model, wherein one of the training samples includes: m pieces of subband information And the size of the output information corresponding to the m subband information, m ⁇ M. For example, if the training sample includes the number of subbands X1, X2, X3, . The overhead of the second communication information is Y2, . . .
  • the number of subbands Xn corresponds to the overhead of the second communication information Yn; these samples are used as training samples of the first AI network model and input to the first AI network model for training.
  • the number of subbands and/or the overhead of the second communication information is notified by other communication devices or communication modules, or notified by the first communication device to other communication devices or communication modules.
  • the first communication device may also need to send third communication information. Therefore, in this possible implementation manner, after S214, the method may further include:
  • Step 1 the first communication device divides the third communication information into (n+p) pieces of second target subband information, where p is an integer greater than or equal to 0; that is, in this possible implementation , the third communication information is greater than or equal to the first communication information.
  • Step 2 input the n pieces of second target subband information into the first sub-AI network, and input the other p second target subband information in the (n+p) second target subband information into the first subband information.
  • the second sub-AI network of the AI network model wherein the maximum input quantity of the second sub-AI network is P sub-band information, P is an integer greater than 0, and p ⁇ P ⁇ M; that is, in this possible
  • the n second target subband information and the other p second target subband information in the (n+p) second target subband information are respectively input into the two sub AI networks, wherein one subband
  • the AI network is the same as the sub AI network to which the first communication information is input, for example, the first sub AI network is the same as the sub AI network to which the first communication information is input.
  • Step 3 Send the fourth communication information output by the first AI network.
  • the input information of the first sub-AI network may further include at least one of the following: other p pieces of the second target sub-band information, the second sub-AI network’s input information Intermediate information, and output information of the second sub-AI network; the input information of the second sub-AI network further includes at least one of the following: n pieces of the target sub-band information, the middle of the first sub-AI network information, and output information of the first sub-AI network.
  • n subband information is represented by input A
  • p subband information is represented by input B
  • the first output information corresponding to n subband information is output A
  • P subband information is output A
  • the second output information corresponding to the information is output B
  • the first sub-AI network is sub-module A
  • the second sub-AI network is sub-module B
  • the first output information is the second communication information
  • Mathematical operations can include a combination of various common mathematical operations such as addition and subtraction multipliers, K-th power, K-th root, logarithm, derivation, and partial derivation.
  • K is an arbitrary number.
  • K 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 input information of the first sub-AI network further includes other p pieces of the second target sub-band information
  • the input information of the second sub-AI network further includes n pieces of the target sub-band information.
  • the input information of the second sub-AI network includes n pieces of the target sub-band information and intermediate information of the first sub-AI network.
  • the input information of the first sub-AI network further includes other p pieces of the second target sub-band information and the intermediate information of the second sub-AI network, and the input information of the second sub-AI network also includes n the target subband information and the intermediate information of the first sub AI network.
  • the fourth communication information includes at least one of the following: first output information, second output information, and the first output information and the second output information are calculated according to a preset algorithm results obtained later.
  • the fourth communication information includes the first output information, or includes the first output information and the second output information.
  • the fourth communication information is a one-dimensional vector or a two-dimensional matrix or a multi-dimensional matrix obtained by combining the first output information and the second output information.
  • the fourth communication information includes a result obtained by calculating the first output information and the second output information 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, K-th power, K-th root, logarithm, derivation, and partial derivation.
  • K is an arbitrary number.
  • K 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 output information may be determined by the output of the first sub-AI network and/or the output of the second sub-AI network; and/or, the second output Information may be determined from the output of the first sub-AI network and/or the output of the second sub-AI network.
  • the first output information is determined by the output of the first sub-AI network and the output of the second sub-AI network
  • the second output information is determined by the output of the first sub-AI network and the output of the second sub-AI network is determined.
  • the first output information is determined by the output of the first sub-AI network
  • the second output information is determined by the output of the first sub-AI network and the output of the second sub-AI network, or is determined by the output of the first sub-AI network and the output of the second sub-AI network.
  • the output of the second sub-AI network is determined.
  • the first output information is determined by the output of the first sub-AI network and the output of the second sub-AI network, or is determined by the output of the first sub-AI network
  • the second output information is determined by the output of the first sub-AI network.
  • the output of the second sub-AI network is determined.
  • the size of the fourth communication information is greater than or equal to the size of the second communication information.
  • n pieces of subband information are input, and first output information and second output information are output, wherein the size of the first output information and the second communication information are the same.
  • the fourth communication information may include more information.
  • the size of the fourth communication information is smaller than or equal to the size of the second communication information.
  • n pieces of second target subband information may also be input to the first sub-AI network and the second sub-AI network.
  • n pieces of second target subband information are input as input A to the first sub-AI network and the second sub-AI network respectively, the first output information and the second output information can be obtained at the same time, so that the obtained
  • the size of the fourth communication information (including the first output information and the second output information) is larger than that of the second communication information, so that the n pieces of second target subband information can be better processed to obtain higher quality output information.
  • the input of the first sub-AI network may include the intermediate information of the second sub-AI network, or not include the intermediate information of the second sub-AI network, and the second sub-AI network
  • the input of the first sub AI network may include the intermediate information of the first sub AI network, or not include the intermediate information of the first sub AI network
  • the first output information may be determined by the output of the first sub AI network, or may be determined by the output of the first sub AI network.
  • the second output information may be determined by the output of the second sub-AI network, or may be determined by the output of the second sub-AI network and the output of the first sub-AI network, specific embodiments of the present application is not limited.
  • Step 1 the first communication device divides the third communication information into (n+p) pieces of second target subband information, where p is an integer greater than or equal to 0; that is, the third communication information is greater than or equal to the first communication information.
  • Step 2 input n pieces of second target subband information into the first sub-AI network, and input other p second target subband information in the (n+p) second target subband information into the first sub-AI network.
  • the first sub-AI network where p ⁇ N.
  • all (n+p) pieces of second target subband information are input into the first sub-AI network, wherein, (n+p) pieces of second target subband information can be simultaneously used as The input information of the first sub-AI network is input.
  • (n+p) pieces of second target sub-band information are simultaneously input as the input information of the first sub-AI network.
  • n pieces of second target sub-band information and p pieces of second target sub-band information may also be input as input information of the first sub-AI network, for example, in the case of n+p>N, n
  • the pieces of second target subband information and the p pieces of second target subband information are respectively input as input information of the first sub-AI network.
  • first sub-AI network may use intermediate information or output information when the n pieces of second target sub-band information are input.
  • Step 3 Send the fourth communication information output by the first sub-AI network.
  • n pieces of second target subband information are input as input A to the first sub-AI network
  • p pieces of second target subband information are input as input B to the first sub-AI network
  • the output A of the first sub-AI network is used as the fourth communication information.
  • n pieces of second target subband information are input to the first sub-AI network as input A, and p pieces of second target subband information are input to the first sub-AI network as input B,
  • the output A and the output B of the first sub-AI network are used as the fourth communication information.
  • the fourth communication information includes first output information and/or second output information, optionally, the size of the first output information and the second communication information of the same size.
  • the size of the fourth communication information is the same as the size of the second communication information. That is to say, in this possible implementation, the output dimensions may be the same for different input dimensions, but the information contained in the output is different (that is, the size of the second communication information and the fourth communication information are the same, but the information actually contained is different. ), with different effects on subsequent modules. , compared with the second communication information, the amount of information represented by the fourth communication information is larger and more accurate, resulting in better performance.
  • the second communication information and/or the fourth communication information includes one of the following (1) to (10).
  • 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.
  • the channels include but are not limited to Physical Downlink Control Channel (PDCCH), Physical Downlink Shared Channel (PDSCH), Physical Uplink Control Channel (PUCCH), Physical Uplink Shared Channel (Physical Uplink Shared Channel, PUSCH), Physical Random Access Channel (Physical Random Access Channel, PRACH), Physical Broadcast Channel (Physical Broadcast Channel, PBCH), etc.
  • PDCCH Physical Downlink Control Channel
  • PDSCH Physical Downlink Shared Channel
  • PUCCH Physical Uplink Control Channel
  • PUCCH Physical Uplink Shared Channel
  • PUSCH Physical Uplink Shared Channel
  • Physical Random Access Channel Physical Random Access Channel
  • PRACH Physical Broadcast Channel
  • PBCH Physical Broadcast Channel
  • it can include at least one of the following:
  • 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 Prediction of channel state information, beam prediction, etc. may be included.
  • Interference information Including but not limited to information such as intra-cell interference, inter-cell interference, out-of-band interference, and intermodulation interference.
  • 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 business and parameters and management information of high-level business and parameters. Including but not limited to: throughput, required packet size, business requirements, moving speed, noise information, etc.
  • Control signaling For example, related signaling of power control and related signaling of beam management, etc.
  • the communication peer (ie, the second communication device) of the first communication device may use a matching AI network to process the received second communication information and/or fourth communication information, or may use a non-AI network to process the received second communication information and/or the fourth communication information.
  • the method processes the second communication and/or the fourth communication, or the second communication and/or the fourth communication can be used directly.
  • 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 transmitting communication information provided by the embodiments of the present application is described by taking the method for transmitting communication information performed by a device for transmitting communication information as an example.
  • FIG. 12 shows a schematic structural diagram of an apparatus for sending communication information provided by an embodiment of the present application.
  • the sending apparatus 1200 may include: a dividing module 1201 for dividing the first communication information into nth a target sub-band information; the input module 1202 is configured to input n pieces of the first target sub-band information into the first sub-AI network of the first artificial intelligence AI network model, wherein the maximum value of the first sub-AI network
  • the input quantity is N subband information
  • the maximum input quantity of the first AI network is M subband information
  • n, M and N are all integers greater than 0, and n ⁇ N ⁇ M;
  • the sending module 1203 is used for sending The second communication information output by the first sub-AI network.
  • the dividing module 1201 divides the first communication information into one or more first target subband information, including: dividing the first communication information according to the target resource of the first communication information The information is divided into one or more first target subband information, wherein the target resources include at least one of the following: frequency domain resources, time domain resources, space domain resources, code domain resources, time delay domain resources, Doppler domain resources resource, Fourier transform domain resource, S domain resource and Z domain resource.
  • the dividing module 1201 divides the first communication information into one or more first target subband information, including at least one of the following:
  • the first communication information is divided into one or more first target subband information on the frequency domain resource, wherein the frequency domain unit resource includes at least one of the following: carrier, resource block RB, physical resource block PRB, subband, precoding resource block group PRG, and bandwidth part BWP;
  • time domain unit resource dividing the first communication information into one or more first target subband information on the time domain resource, wherein the time domain unit resource includes at least one of the following: a symbol (eg, OFDM symbols), slots, half-slots, frames, subframes, radio frames, milliseconds, and seconds;
  • the first communication information is divided into one or more first target subband information on the airspace resource, wherein the airspace unit resource includes at least one of the following: an antenna, an antenna element , antenna panel, transmitting and receiving unit, beam, layer, rank, and antenna angle;
  • the first communication information is divided into one or more first target subband information on the code domain resource, wherein the code domain unit resource includes at least one of the following: positive Interleaved, quasi-orthogonal, and semi-orthogonal codes.
  • the input module 1202 inputs the n pieces of first target subband information into the first sub-AI network of the first artificial intelligence AI network model, including:
  • the predetermined order includes: the identifiers of the n pieces of first target subband information from large to small or In ascending order; or,
  • the input quantity of the first sub-AI network is fixed as N sub-band information, then n pieces of the first target sub-band information and N-n pieces of invalid sub-band information are input to the first sub-AI network, where n The first target subband information is located at a specified position.
  • the size of the second communication information is a fixed value, or the size of the second communication information is determined by the quantity of the input first target subband information.
  • the size of the second communication information is determined by the quantity of the inputted first target subband information, including:
  • the size of the second communication information is proportional to the quantity of the inputted first target subband information; or,
  • the increment of the size of the second communication information is proportional to the increment of the quantity of the inputted first target subband information.
  • the apparatus may further include: a training module 1204, configured to use a plurality of training samples to train the first AI network model, wherein one of the training samples The sample includes: m pieces of subband information and the size of the output information corresponding to the m pieces of subband information, where m ⁇ M.
  • a training module 1204 configured to use a plurality of training samples to train the first AI network model, wherein one of the training samples The sample includes: m pieces of subband information and the size of the output information corresponding to the m pieces of subband information, where m ⁇ M.
  • the second communication information includes one of the following:
  • the dividing module 1201 is further configured to divide the third communication information into (n+p) pieces of second target subband information by the first communication device, where p is greater than or equal to an integer of 0;
  • the input module 1202 is further configured to input the n pieces of second target subband information into the first sub-AI network, and input the other p in the (n+p) pieces of second target subband information
  • the second target sub-band information is input into the second sub-AI network of the first AI network model, wherein the maximum input amount of the second sub-AI network is P sub-band information, P is an integer greater than 0, and p ⁇ P ⁇ M;
  • the sending module 1203 is further configured to send the fourth communication information output by the first AI network.
  • the input information of the first sub-AI network further includes at least one of the following: other p pieces of the second target sub-band information, intermediate information of the second sub-AI network, and all The output information of the second sub-AI network; the input information of the second sub-AI network also includes at least one of the following: n pieces of the target sub-band information, the intermediate information of the first sub-AI network, and the The output information of the first sub-AI network.
  • the fourth communication information includes at least one of the following: first output information, second output information, and the first output information and the second output information are calculated according to a preset algorithm The result obtained later; wherein, the first output information is determined by the output of the first sub-AI network and/or the output of the second sub-AI network; and/or, the second output information is determined by the first sub-AI network The output of the sub-AI network and/or the output of the second sub-AI network is determined.
  • the size of the fourth communication information is greater than or equal to the size of the second communication information.
  • the size of the fourth communication information is smaller than or equal to the size of the second communication information.
  • the dividing module 1201 is further configured to divide the third communication information into (n+p) pieces of second target subband information, where p is an integer greater than or equal to 0; the The input module 1202 is further configured to input the n pieces of second target subband information into the first sub-AI network, and input the other p second target subbands in the (n+p) pieces of second target subband information The information is input to the first sub-AI network, where p ⁇ N; the sending module 1203 is further configured to send the fourth communication information output by the first sub-AI network.
  • the fourth communication information includes first output information and/or second output information, wherein the size of the first output information is the same as the size of the second communication information.
  • 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 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 embodiments in FIG. 2 to FIG. 11 , and achieve the same technical effect, which is not repeated here to avoid repetition.
  • an embodiment of the present application further provides a communication device 1300, including a processor 1301, a memory 1302, a program or instruction stored in the memory 1302 and executable on the processor 1301, During execution, each process of the above-mentioned embodiment of the method for sending communication information is implemented, and the same technical effect can be achieved. In order to avoid repetition, details are not repeated here.
  • FIG. 14 is a schematic diagram of a hardware structure of a terminal implementing an embodiment of the present application.
  • the terminal 1400 includes but is not limited to: a radio frequency unit 1401, a network module 1402, an audio output unit 1403, an input unit 1404, a sensor 1405, a display unit 1406, a user input unit 1407, an interface unit 1408, a memory 1409, a processor 1410 and other components .
  • the terminal 1400 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 1410 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. 14 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 1404 may include a graphics processor (Graphics Processing Unit, GPU) 14041 and a microphone 14042. Such as camera) to obtain still pictures or video image data for processing.
  • the display unit 1406 may include a display panel 14061, which may be configured in the form of a liquid crystal display, an organic light emitting diode, or the like.
  • the user input unit 1407 includes a touch panel 14071 and other input devices 14072 .
  • the touch panel 14071 is also called a touch screen.
  • the touch panel 14071 may include two parts, a touch detection device and a touch controller.
  • Other input devices 14072 may include, but are not limited to, physical keyboards, function keys (such as volume control keys, switch keys, etc.), trackballs, mice, and joysticks, which will not be described herein again.
  • the radio frequency unit 1401 receives the downlink data from the network side device, and then processes it to the processor 1410; in addition, sends the uplink data to the network side device.
  • the radio frequency unit 1401 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 1409 may be used to store software programs or instructions as well as various data.
  • the memory 1409 may mainly include a storage 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 1409 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 1410 may include one or more processing units; optionally, the processor 1410 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 1410.
  • the processor 1410 is configured to divide the first communication information into n pieces of first target sub-band information; input the n pieces of first target sub-band information into the first sub-AI network of the first artificial intelligence AI network model , wherein the maximum input amount of the first sub-AI network is N sub-band information, the maximum input amount of the first AI network is M sub-band information, n, M and N are all integers greater than 0, and n ⁇ N ⁇ M;
  • the radio frequency unit 1401 is configured to send the second communication information output by the first sub-AI network.
  • the above-mentioned terminal provided in this embodiment of the present application can implement the method performed by the first communication device in the above-mentioned method 200, and achieve the same technical effect. To avoid repetition, details are not described here.
  • the network device 1500 includes: an antenna 1501 , a radio frequency device 1502 , and a baseband device 1503 .
  • the antenna 1501 is connected to the radio frequency device 1502 .
  • the radio frequency device 1502 receives information through the antenna 1501, and sends the received information to the baseband device 1503 for processing.
  • the baseband device 1503 processes the information to be sent and sends it to the radio frequency device 1502
  • the radio frequency device 1502 processes the received information and sends it out through the antenna 1501 .
  • the above-mentioned frequency band processing apparatus may be located in the baseband apparatus 1503 , and the method performed by the network side device in the above embodiments may be implemented in the baseband apparatus 1503 .
  • the baseband apparatus 1503 includes a processor 1504 and a memory 1505 .
  • the baseband device 1503 may include, for example, at least one baseband board on which multiple chips are arranged, as shown in FIG. 15 , one of the chips is, for example, the processor 1504 , which is connected to the memory 1505 to call the program in the memory 1505 to execute
  • the network-side device shown in the above method embodiments operates.
  • the baseband device 1503 may further include a network interface 1506 for exchanging information with the radio frequency device 1502, and the interface is, for example, a common public radio interface (CPRI for short).
  • CPRI common public radio interface
  • the network-side device in the embodiment of the present invention further includes: instructions or programs stored in the memory 1505 and executable on the processor 1504, and the processor 1504 invokes the instructions or programs in the memory 1505 to execute the modules shown in FIG. 12 .
  • the above-mentioned network side device provided in this embodiment of the present application can implement the method performed by the first communication device in the above-mentioned method 200, and achieve the same technical effect. To avoid repetition, details are not described here.
  • the embodiments of the present application further provide 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, each process of the above-mentioned embodiment of the method for sending communication information is implemented, and can To achieve the same technical effect, in order to avoid repetition, details are not repeated here.
  • the processor is the processor in the terminal or the network side device 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 to realize the above-mentioned communication information.
  • the various processes of the embodiments of the sending method can achieve the same technical effect, and are not repeated here in order to avoid repetition.
  • a computer program product comprising a processor, a memory, and a program or instruction stored on the memory and executable on the processor, when the program or instruction is executed by the processor , realizes each process of the above-mentioned embodiment of the method for sending communication information, and can achieve the same technical effect. 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)
  • Data Mining & Analysis (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

本申请公开了一种通信方法、装置及通信设备,属于无线通信技术领域。其中,该方法包括:第一通信设备将第一通信信息划分为n个第一目标子带信息;将n个所述第一目标子带信息输入到第一人工智能AI网络模型的第一子AI网络,其中,所述第一子AI网络的最大输入量为N个子带信息,所述第一AI网络的最大输入量为M个子带信息,n、M和N均为大于0的整数,且n≤N≤M;发送所述第一子AI网络输出的第二通信信息。

Description

通信方法、装置及通信设备
交叉引用
本发明要求在2020年11月23日提交中国专利局、申请号为202011324299.8、发明名称为“通信方法、装置及通信设备”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,具体涉及一种通信方法、装置及通信设备。
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。
在相关技术中,一个AI网络的输入大小一般是固定的,如果需要有不同大小的输入,则需要针对每个输入大小构建一个AI网络。而在实际应用环境中,AI网络的输入可能随时变化。例如,在通信技术领域,在通过AI网络将待发送的原始信息生成可以通过无线网络传输的数据流时,待发送的原始信息的大小通常是不固定的,因此,需要针对每个输入大小构建一个AI网络,从而导致通信设备中存储的AI网络数量过多,增加了通信设备的存储压力。
发明内容
本申请实施例提供一种通信信息的发送方法、装置及通信设备,能够解 决通信设备中存储的AI网络数量过多的问题。
第一方面,提供了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n个第一目标子带信息;将n个所述第一目标子带信息输入到第一人工智能AI网络模型的第一子AI网络,其中,所述第一子AI网络的最大输入量为N个子带信息,所述第一AI网络的最大输入量为M个子带信息,n、M和N均为大于0的整数,且n≤N≤M;发送所述第一子AI网络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:划分模块,用于将第一通信信息划分为n个第一目标子带信息;输入模块,用于将n个所述第一目标子带信息输入到第一人工智能AI网络模型的第一子AI网络,其中,所述第一子AI网络的最大输入量为N个子带信息,所述第一AI网络的最大输入量为M个子带信息,n、M和N均为大于0的整数,且n≤N≤M;发送模块,用于发送所述第一子AI网络输出的第二通信信息。
第三方面,提供了一种通信设备,该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第一方面所述的方法的步骤。
第四方面,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。
第五方面,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终端程序或指令,实现如第一方面所述的方法步骤。
第六方面,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。
在本申请实施例中,第一通信设备将第一通信信息划分为n个第一目标子带信息,将n个所述第一目标子带信息输入到第一AI网络模型的第一子 AI网络,其中,所述第一子AI网络的最大输入量为N个子带信息,所述第一AI网络的最大输入量为M个子带信息,n≤N≤M,然后发送第一子AI网络输出的第二通信信息。在本申请实施例中,第一AI网络模块包括多个子AI网络,多个子AI网络之间可以采用嵌套的方式布局,每个子AI网络对应不同的最大输入量,从而可以根据实际的输入信息的大小,选择输入到对应的子AI网络,降低了存储的AI网络模型的数量,简化了AI网络的复杂度,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示意图;
图2示出本申请实施例提供的通信信息的发送方法的一种流程示意图;
图3示出本申请实施例提供的一种AI网络模型的结构示意图;
图4示出本申请实施例提供的另一种AI网络模型的结构示意图;
图5示出本申请实施例提供的又一种AI网络模型的结构示意图;
图6示出本申请实施例提供的又一种AI网络模型的结构示意图;
图7示出本申请实施例提供的又一种AI网络模型的结构示意图;
图8示出本申请实施例提供的又一种AI网络模型的结构示意图;
图9示出本申请实施例提供的又一种AI网络模型的结构示意图;
图10示出本申请实施例提供的又一种AI网络模型的结构示意图;
图11a示出本申请实施例提供的又一种AI网络模型的结构示意图;
图11b示出本申请实施例提供的又一种AI网络模型的结构示意图;
图12示出本申请实施例提供的通信信息的发送装置的一种结构示意图;
图13示出本申请实施例提供的一种通信设备的结构示意图;
图14示出本申请实施例提供的一种终端的硬件结构示意图;
图15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示意图。无线通信 系统包括终端11和网络侧设备12。其中,终端11也可以称作终端设备或者用户终端(User Equipment,UE),终端11可以是手机、平板电脑(Tablet Personal Computer)、膝上型电脑(Laptop Computer)或称为笔记本电脑、个人数字助理(Personal Digital Assistant,PDA)、掌上电脑、上网本、超级移动个人计算机(ultra-mobile personal computer,UMPC)、移动上网装置(Mobile Internet Device,MID)、可穿戴式设备(Wearable Device)或车载设备(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案进行详细地说明。
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,该装置200可以由第一通信设备执行。换言之,所述装置可以由安装在第一通信设备上的软件或硬件来执行。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n个第一目标子带信息。
在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第一目标子带信息,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、码域资源、时延域资源、多普勒域资源、傅里叶变换域资源、S域资源、Z域资源,和其它类型变换域的资源。
在上述可能的实现方式中,S域是指在频域分析中以虚指数exp(jωt)为基本信号,任意信号可分解为众多不同频率的虚指数分量。Z域是Z变换得到的域。其中,Z变换为数学中经典的变换。
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(1)至(4)中的至少之一。
(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:子载波、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:符号、时隙、半时隙、帧、子帧、无线帧、毫秒、秒或其它时间单位。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符号、时隙、半时隙、帧、子帧、无线帧、毫秒、秒或其它时间单位进行划分,将第一通信信息的每一个或多个符号、时隙、半时隙、帧、子帧、无线帧、毫秒、秒或其它时间单位上的信息划分为一个子带。其中,所述符号包括但不限于正交频分复用(Orthogonal frequency division multiplex,OFDM)符号。
(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n个所述第一目标子带信息输入到第一人工智能AI网络模型的第一子AI网络,其中,所述第一子AI网络的最大输入量为N个子带信息,所述第一AI网络的最大输入量为M个子带信息,n、M和N均为大于0的整数,且n≤N≤M。
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。
在本申请实施例中,第一AI网络模型的最大输入量为M个子带信息,第一AI网络模型可以输入不同的大小的信息,第一AI网络模型可以包括多个子AI网络,其中,大信息输入时的子AI网络可以包含小信息输入时的子AI网络,或者也可以说基于小信息输入时的子AI网络可以构造出大信息输入时的子AI网络。
在本申请实施例,每个子AI网络可以对应一个最大输入量,各个子AI 网络之间可以采用嵌套的方式设置,例如,第一AI网络模型的第一层子AI网络的最大输入量为M,该子AI网络可以嵌套一个最大输入量为i的子AI网络和一个最大输入量为(M-i)的子AI网络,而最大输入量为(M-i)的子AI网络,又可以嵌套一个最大输入量为i的子AI网络和一个输入大小为(M-2i)的子AI网络,如此循环嵌套设置。当然,并不限于此,在实际应用中,还可以采用其它类似的网络结构。
S214,发送所述第一子AI网络输出的第二通信信息。
在本申请实施例中,第一AI网络模块包括多个子AI网络,多个子AI网络之间可以采用嵌套的方式布局,每个子AI网络对应不同的最大输入量,从而可以根据实际的输入信息的大小,选择输入到对应的子AI网络,降低了存储的AI网络模型的数量,简化了AI网络的复杂度,提升了通信系统的性能。
在一个可能的实现方式中,在S212中,将n个所述第一目标子带信息输入到第一人工智能AI网络模型的第一子AI网络时,可以将n个所述第一目标子带信息按照预定顺序排列输入到所述第一子AI网络,其中,所述预定顺序包括:n个所述第一目标子带信息的标识从大到小或从小到大的顺序。
或者,在另一个可能的实现方式中,在S212中,将n个所述第一目标子带信息输入到第一人工智能AI网络模型的第一子AI网络时,若所述第一子AI网络的输入量固定为N个子带信息,则将n个所述第一目标子带信息和N-n个无效子带信息输入到所述第一子AI网络,其中,n个所述第一目标子带信息位于指定位置。例如,若第一子AI网络的输入为固定10个子带,但目前只有4个有效子带,则输入为123xxxxxx4,其中x表示该子带无有效输入。当某个子带无有效输入时,可以将默认信息(如全零信息)、至少一个有效子带信息的数学组合或其它信息作为该子带的输入。
在一个可能的实现方式中,所述第二通信信息的大小为固定值,或所述第二通信信息的大小由输入的所述第一目标子带信息的数量确定。也就是说, 在该可能的实现方式中,第二通信信息的开销可以是固定的,也可以是根据输入量的变化而变化。
例如,第二通信信息的大小与输入的所述第一目标子带信息的数量成正比。比如,输入的子带数目X1,对应第二通信信息的开销为Y1,当输入的子带数目为X1*N,则第二通信信息的开销为Y1*N。
另外,第二通信信息的大小的增量与输入的所述第一目标子带信息的数量的增量成正比。例如,输入的子带数目X1+X2,对应第二通信信息的开销为Y1+Y2,当输入的子带数目为X1+X2*N,则第二通信信息的开销为Y1+Y2*N。其中X1为基础输出量/基础子带数目,X2为使用嵌套结构的额外输入。
在本申请实施例的一个可能的实现方式中,在S210之前,还可以对第一AI网络模型进行训练,以使得确定第一AI网络模型的各个网络参数。因此,在该可能的实现方式中,在S210之前,该方法还可以包括:使用多个训练样本,对所述第一AI网络模型进行训练,其中,一个所述训练样本包括:m个子带信息以及m个子带信息对应的输出信息的大小,m≤M。例如,训练样本包含第一AI网络模型输入的子带数目X1、X2、X3、….、Xn,则样本中,子带数目X1对应第二通信信息的开销为Y1,子带数目X2对应第二通信信息的开销为Y2,…,子带数目Xn对应第二通信信息的开销为Yn;将这些样本都作为第一AI网络模型的训练样本,输入到第一AI网络模型进行训练。可选地,子带数目和/或第二通信信息的开销,由其它通信设备或通信模块告知,或由第一通信设备告知其它通信设备或通信模块。
在一个可能的实现方式中,在S214之后,第一通信设备可能还需要发送第三通信信息,因此,在该可能的实现方式中,在S214之后,该方法还可以包括:
步骤1,所述第一通信设备将第三通信信息划分为(n+p)个第二目标子带信息,其中,p为大于或等于0的整数;也就是说,在该可能的实现方式 中,第三通信信息大于或等于第一通信信息。
步骤2,将n个所述第二目标子带信息输入所述第一子AI网络,将(n+p)个第二目标子带信息中的其它p个第二目标子带信息输入第一AI网络模型的第二子AI网络,其中,所述第二子AI网络的最大输入量为P个子带信息,P为大于0的整数,且p≤P≤M;也就是说,在该可能的实现方式中,将n个第二目标子带信息和(n+p)个第二目标子带信息中的其它p个第二目标子带信息分别输入到两个子AI网络,其中,一个子AI网络与第一通信信息输入的子AI网络相同,例如,所述第一子AI网络与第一通信信息输入的子AI网络相同。
步骤3,发送所述第一AI网络输出的第四通信信息。
在上述可能的实现方式中,如图3所示,第一子AI网络的输入信息还可以包括以下至少之一:其它p个所述第二目标子带信息、所述第二子AI网络的中间信息、以及所述第二子AI网络的输出信息;所述第二子AI网络的输入信息还包括以下至少之一:n个所述目标子带信息、所述第一子AI网络的中间信息、以及所述第一子AI网络的输出信息。
需要说明的是,在本申请中的各个附图中,n个子带信息用输入A表示,p个子带信息用输入B表示,n个子带信息对应的第一输出信息为输出A,P个子带信息对应的第二输出信息为输出B,第一子AI网络为子模块A,第二子AI网络为子模块B。可选地,第一输出信息为第二通信信息,或通过第一输出信息经过信号处理和/或数学操作后可以得到第二通信信息。数学操作可以包括加减乘数、K次方、K次开根号、对数、求导、求偏导等各种常见数学操作的组合。K为任意数。例如,K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。
例如,在图4中,第一子AI网络的输入信息还包括其它p个所述第二目标子带信息,第二子AI网络的输入信息还包括n个所述目标子带信息。
或者,在图5中,第二子AI网络的输入信息包括n个所述目标子带信息 和第一子AI网络的中间信息。
又或者,在图6中,第一子AI网络的输入信息还包括其它p个所述第二目标子带信息和第二子AI网络的中间信息,第二子AI网络的输入信息还包括n个所述目标子带信息和第一子AI网络的中间信息。
在上述可能的实现方式中,所述第四通信信息包括以下至少之一:第一输出信息、第二输出信息、以及所述第一输出信息和所述第二输出信息按照预设算法进行计算后得到的结果。
例如,在图3至图5中,第四通信信息包括第一输出信息,或者,包括第一输出信息和第二输出信息。例如,第四通信信息为第一输出信息与第二输出信息合并后得到的一维向量或二维矩阵或多维矩阵.
又例如,在图6中,第四通信信息包括所述第一输出信息和所述第二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、K次方、K次开根号、对数、求导、求偏导等各种常见数学操作的组合。K为任意数。例如,K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。
在上述可能的实现方式中,可选的,第一输出信息可以由所述第一子AI网络的输出和/或所述第二子AI网络的输出确定;和/或,所述第二输出信息可以由所述第一子AI网络的输出和/或所述第二子AI网络的输出确定。例如,在图7和图4中,第一输出信息由所述第一子AI网络的输出和所述第二子AI网络的输出确定,第二输出信息由所述第一子AI网络的输出和所述第二子AI网络的输出确定。在图5中,第一输出信息由所述第一子AI网络的输出确定,第二输出信息由所述第一子AI网络的输出和所述第二子AI网络的输出确定、或由所述第二子AI网络的输出确定。而在图8中,第一输出信息由所述第一子AI网络的输出和所述第二子AI网络的输出确定、或由所述第一子AI网络的输出,第二输出信息由所述第二子AI网络的输出确定。
在上述可能的实现方式中,在p等于0的情况下,所述第四通信信息的大小大于或等于所述第二通信信息的大小。例如,在图9中,输入n个子带信息,输出为第一输出信息和第二输出信息,其中,第一输出信息与第二通信信息的大小相同。相对于第二通信信息,第四通信信息中可以包括更多的信息。
在另一个可能的实现方式中,在p等于0的情况下,所述第四通信信息的大小小于或等于所述第二通信信息的大小。
在上述可能的实现方式中,在p等于0的情况下,也可以将n个第二目标子带信息输入到第一子AI网络和第二子AI网络。例如,在图10中,将n个第二目标子带信息作为输入A分别输入第一子AI网络和第二子AI网络,可以同时得到第一输出信息和第二输出信息,从而使得得到的第四通信信息(包括第一输出信息和第二输出信息)的大小比第二通信信息更大,从而可以更好的处理n个第二目标子带信息,以获得更高质量的输出信息。
如图10所示,在上述可能的实现方式中,第一子AI网络的输入可以包括第二子AI网络的中间信息、或不包括第二子AI网络的中间信息,而第二子AI网络的输入可以包括第一子AI网络的中间信息、或不包括第一子AI网络的中间信息,第一输出信息可以由第一子AI网络的输出确定,也可以由第一子AI网络的输出和第二子AI网络的输出确定,第二输出信息可以由第二子AI网络的输出确定,也可以由第二子AI网络的输出和第一子AI网络的输出确定,具体本申请实施例中不作限定。
或者,在另一个可能的实现方式中,在第一通信设备在发送第三通信信息时,还可以采用下面的步骤:
步骤1,所述第一通信设备将第三通信信息划分为(n+p)个第二目标子带信息,其中,p为大于或等于0的整数;即第三通信信息大于或等于第一通信信息。
步骤2,将n个所述第二目标子带信息输入所述第一子AI网络,将(n+p) 个第二目标子带信息中的其它p个第二目标子带信息输入所述第一子AI网络,其中,p≤N。
即在该可能的实现方式中,将(n+p)个第二目标子带信息均输入到第一子AI网络中,其中,可以将(n+p)个第二目标子带信息同时作为第一子AI网络的输入信息输入,例如,在n+p≤N时,将(n+p)个第二目标子带信息同时作为第一子AI网络的输入信息输入。或者,也可以将n个第二目标子带信息和p个所述第二目标子带信息分别作为第一子AI网络的输入信息输入,例如,在n+p>N的情况下,将n个第二目标子带信息和p个所述第二目标子带信息分别作为第一子AI网络的输入信息输入。例如,先将n个第二目标子带信息输入第一子AI网络,然后将p个所述第二目标子带信息输入第一子AI网络;可选地,将p个所述第二目标子带信息输入第一子AI网络时,第一子AI网络可以利用n个第二目标子带信息输入时的中间信息或输出信息。
步骤3,发送所述第一子AI网络输出的第四通信信息。
例如,在图11a中,将n个第二目标子带信息作为输入A输入到第一子AI网络,将p个所述第二目标子带信息作为输入B输入到第一子AI网络,将第一子AI网络的输出A作为第四通信信息。
又例如,在图11b中,将n个第二目标子带信息作为输入A输入到第一子AI网络,将p个所述第二目标子带信息作为输入B输入到第一子AI网络,将第一子AI网络的输出A和输出B作为第四通信信息。
在上述可能的实现方式中,可选的,所述第四通信信息包括第一输出信息和/或第二输出信息,可选地,所述第一输出信息的大小与所述第二通信信息的大小相同。
可选地,在第四通信信息只包括第一输出信息的情况下,第四通信信息的大小与第二通信信息的大小相同。也就是说,在该可能的实现方式中,不同的输入维度,输出维度可以相同,但输出中包含的信息不同(即第二通信信息与第四通信信息的大小相同,但实际包含的信息不同),对后续模块的影 响不同。,相比于第二通信信息,第四通信信息表征的信息量更大、更精确,带来更好的性能。
在本申请实施例的一个可能的实现方式中,所述第二通信信息和/或第四通信信息包括以下(1)至(10)的的之一。
(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,可以包括以下至少之一:
(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,第一通信设备的通信对端(即第二通信设备)可能用相匹配的AI网络处理接收到的第二通信信息和/或第四通信信息,也可能用非AI的方法处理第二通信信息和/或第四通信信息,或第二通信信息和/或第四通信信息可以直接使用。
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12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12所示,该发送装置1200可以包括:划分模块1201,用于将第一通信信息划分为n个第一目标子带信息;输入模块1202,用于将n个所述第一目标子带信息输入到第一人工智能AI网络模型的第一子AI网络,其中,所述第一子AI网络的最大输入量为N个子带信息,所述第一AI网络的最大输入量为M个子带信息,n、M和N均为大于0的整数,且n≤N≤M;发送模块1203,用于发送所述第一子AI网络输出的第二通信信息。
在一个可能的实现方式中,所述划分模块1201将第一通信信息划分为一个或多个第一目标子带信息,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第一目标子带信息,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、码域资源、时延域资源、多普勒域资源、傅里叶变换域资源、S域资源和Z域资源。
在一个可能的实现方式中,所述划分模块1201将第一通信信息划分为一个或多个第一目标子带信息,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第一目标子带信息,其中,所述频域单位资源包括以下至少之一:子载波、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第一目标子带信息,其中,所述时域单位资源包括以下至少之一:符号(例如,OFDM符号)、时隙、半时隙、帧、子帧、无线帧、毫秒、以及秒;
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第一目标子带信息,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第一目标子带信息,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,所述输入模块1202将n个所述第一目标子带信息输入到第一人工智能AI网络模型的第一子AI网络,包括:
将n个所述第一目标子带信息按照预定顺序排列输入到所述第一子AI网络,其中,所述预定顺序包括:n个所述第一目标子带信息的标识从大到小或从小到大的顺序;或者,
若所述第一子AI网络的输入量固定为N个子带信息,则将n个所述第一目标子带信息和N-n个无效子带信息输入到所述第一子AI网络,其中,n个所述第一目标子带信息位于指定位置。
在一个可能的实现方式中,所述第二通信信息的大小为固定值,或所述第二通信信息的大小由输入的所述第一目标子带信息的数量确定。
在一个可能的实现方式中,所述第二通信信息的大小由输入的所述第一目标子带信息的数量确定,包括:
第二通信信息的大小与输入的所述第一目标子带信息的数量成正比;或,
第二通信信息的大小的增量与输入的所述第一目标子带信息的数量的增量成正比。
在一个可能的实现方式中,如图12所示,所述装置还可以包括:训练模块1204,用于使用多个训练样本,对所述第一AI网络模型进行训练,其中,一个所述训练样本包括:m个子带信息以及m个子带信息对应的输出信息的大小,m≤M。
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。
在一个可能的实现方式中,所述划分模块1201,还用于所述第一通信设备将第三通信信息划分为(n+p)个第二目标子带信息,其中,p为大于或等于0的整数;所述输入模块1202,还用于将n个所述第二目标子带信息输入所述第一子AI网络,将(n+p)个第二目标子带信息中的其它p个第二目标子带信息输入第一AI网络模型的第二子AI网络,其中,所述第二子AI网络的最大输入量为P个子带信息,P为大于0的整数,且p≤P≤M;所述发送模块1203,还用于发送所述第一AI网络输出的第四通信信息。
在一个可能的实现方式中,所述第一子AI网络的输入信息还包括以下至少之一:其它p个所述第二目标子带信息、所述第二子AI网络的中间信息、以及所述第二子AI网络的输出信息;所述第二子AI网络的输入信息还包括以下至少之一:n个所述目标子带信息、所述第一子AI网络的中间信息、以及所述第一子AI网络的输出信息。
在一个可能的实现方式中,所述第四通信信息包括以下至少之一:第一输出信息、第二输出信息、以及所述第一输出信息和所述第二输出信息按照预设算法进行计算后得到的结果;其中,第一输出信息由所述第一子AI网络的输出和/或所述第二子AI网络的输出确定;和/或,所述第二输出信息由所述第一子AI网络的输出和/或所述第二子AI网络的输出确定。
在一个可能的实现方式中,在p等于0的情况下,所述第四通信信息的 大小大于或等于所述第二通信信息的大小。
在一个可能的实现方式中,在p等于0的情况下,所述第四通信信息的大小小于或等于所述第二通信信息的大小。
在一个可能的实现方式中,所述划分模块1201,还用于将第三通信信息划分为(n+p)个第二目标子带信息,其中,p为大于或等于0的整数;所述输入模块1202,还用于将n个所述第二目标子带信息输入所述第一子AI网络,将(n+p)个第二目标子带信息中的其它p个第二目标子带信息输入所述第一子AI网络,其中,p≤N;所述发送模块1203,还用于发送所述第一子AI网络输出的第四通信信息。
在一个可能的实现方式中,所述第四通信信息包括第一输出信息和/或第二输出信息,其中,所述第一输出信息的大小与所述第二通信信息的大小相同。
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至图11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13所示,本申请实施例还提供一种通信设备1300,包括处理器1301,存储器1302,存储在存储器1302上并可在所述处理器1301上运行的程序或指令,执行时实现上述通信信息的发送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14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1400包括但不限于:射频单元1401、网络模块1402、音频输出单元1403、输入单元1404、传感器1405、显示单元1406、用户输入单元1407、接口单元1408、存储器1409、以及处理器1410等部件。
本领域技术人员可以理解,终端1400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1410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14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1404可以包括图形处理器(Graphics Processing Unit,GPU)14041和麦克风14042,图形处理器14041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1406可包括显示面板14061,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14061。用户输入单元1407包括触控面板14071以及其他输入设备14072。触控面板14071,也称为触摸屏。触控面板14071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14072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1401将来自网络侧设备的下行数据接收后,给处理器1410处理;另外,将上行的数据发送给网络侧设备。通常,射频单元1401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1409可用于存储软件程序或指令以及各种数据。存储器1409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1409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1410可包括一个或多个处理单元;可选的,处理器1410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1410中。
其中,处理器1410,用于将第一通信信息划分为n个第一目标子带信息;将n个所述第一目标子带信息输入到第一人工智能AI网络模型的第一子AI网络,其中,所述第一子AI网络的最大输入量为N个子带信息,所述第一AI网络的最大输入量为M个子带信息,n、M和N均为大于0的整数,且n≤N≤M;
射频单元1401,用于发送所述第一子AI网络输出的第二通信信息。
本申请实施例提供的上述终端,可以实现上述方法200中第一通信设备所执行的方法,并达到相同的技术效果,为避免重复,故不在此赘述。
具体地,本申请实施例还提供了一种网络侧设备。如图15所示,该网络设备1500包括:天线1501、射频装置1502、基带装置1503。天线1501与射频装置1502连接。在上行方向上,射频装置1502通过天线1501接收信息,将接收的信息发送给基带装置1503进行处理。在下行方向上,基带装置1503对要发送的信息进行处理,并发送给射频装置1502,射频装置1502对收到的信息进行处理后经过天线1501发送出去。
上述频带处理装置可以位于基带装置1503中,以上实施例中网络侧设备执行的方法可以在基带装置1503中实现,该基带装置1503包括处理器1504 和存储器1505。
基带装置1503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15所示,其中一个芯片例如为处理器1504,与存储器1505连接,以调用存储器1505中的程序,执行以上方法实施例中所示的网络侧设备操作。
该基带装置1503还可以包括网络接口1506,用于与射频装置1502交互信息,该接口例如为通用公共无线接口(common public radio interface,简称CPRI)。
具体地,本发明实施例的网络侧设备还包括:存储在存储器1505上并可在处理器1504上运行的指令或程序,处理器1504调用存储器1505中的指令或程序执行图12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。
本申请实施例提供的上述网络侧设备,可以实现上述方法200中第一通信设备所执行的方法,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通信信息的发送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或网络侧设备中的处理器。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,实现上述通信信息的发送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。
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,实现上述通信信息的发送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 (32)

  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n个第一目标子带信息;
    将n个所述第一目标子带信息输入到第一人工智能AI网络模型的第一子AI网络,其中,所述第一子AI网络的最大输入量为N个子带信息,所述第一AI网络的最大输入量为M个子带信息,n、M和N均为大于0的整数,且n≤N≤M;
    发送所述第一子AI网络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第一目标子带信息,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第一目标子带信息,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、码域资源、时延域资源、多普勒域资源、傅里叶变换域资源、S域资源和Z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第一目标子带信息,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第一目标子带信息,其中,所述频域单位资源包括以下至少之一:子载波、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第一目标子带信息,其中,所述时域单位资源包括以下至少之一:符号、时隙、半时隙、帧、子帧、无线帧、毫秒、以及秒;
    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第一目标子带信息,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 一个或多个第一目标子带信息,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,将n个所述第一目标子带信息输入到第一人工智能AI网络模型的第一子AI网络,包括:
    将n个所述第一目标子带信息按照预定顺序排列输入到所述第一子AI网络,其中,所述预定顺序包括:n个所述第一目标子带信息的标识从大到小或从小到大的顺序;或者,
    若所述第一子AI网络的输入量固定为N个子带信息,则将n个所述第一目标子带信息和N-n个无效子带信息输入到所述第一子AI网络,其中,n个所述第一目标子带信息位于指定位置。
  5. 根据权利要求1所述的方法,其中,所述第二通信信息的大小为固定值,或所述第二通信信息的大小由输入的所述第一目标子带信息的数量确定。
  6. 根据权利要求5所述的方法,其中,所述第二通信信息的大小由输入的所述第一目标子带信息的数量确定,包括:
    第二通信信息的大小与输入的所述第一目标子带信息的数量成正比;或,
    第二通信信息的大小的增量与输入的所述第一目标子带信息的数量的增量成正比。
  7. 根据权利要求1至6任一项所述的方法,其中,在第一通信设备将第一通信信息划分为一个或多个第一目标子带信息之前,所述方法还包括:
    使用多个训练样本,对所述第一AI网络模型进行训练,其中,一个所述训练样本包括:m个子带信息以及m个子带信息对应的输出信息的大小,m≤M。
  8. 根据权利要求1至6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。
  9. 根据权利要求1至6任一项所述的方法,其中,在发送所述第二通信信息之后,所述方法还包括:
    所述第一通信设备将第三通信信息划分为(n+p)个第二目标子带信息,其中,p为大于或等于0的整数;
    将n个所述第二目标子带信息输入所述第一子AI网络,将(n+p)个第二目标子带信息中的其它p个第二目标子带信息输入第一AI网络模型的第二子AI网络,其中,所述第二子AI网络的最大输入量为P个子带信息,P为大于0的整数,且p≤P≤M;
    发送所述第一AI网络输出的第四通信信息。
  10. 根据权利要求9所述的方法,其中,
    所述第一子AI网络的输入信息还包括以下至少之一:其它p个所述第二目标子带信息、所述第二子AI网络的中间信息、以及所述第二子AI网络的输出信息;
    所述第二子AI网络的输入信息还包括以下至少之一:n个所述目标子带信息、所述第一子AI网络的中间信息、以及所述第一子AI网络的输出信息。
  11. 根据权利要求9所述的方法,其中,所述第四通信信息包括以下至少之一:第一输出信息、第二输出信息、以及所述第一输出信息和所述第二输出信息按照预设算法进行计算后得到的结果;其中,
    第一输出信息由所述第一子AI网络的输出和/或所述第二子AI网络的输 出确定;和/或,
    所述第二输出信息由所述第一子AI网络的输出和/或所述第二子AI网络的输出确定。
  12. 根据权利要求9所述的方法,其中,在p等于0的情况下,所述第四通信信息的大小大于或等于所述第二通信信息的大小。
  13. 根据权利要求9所述的方法,其中,在p等于0的情况下,所述第四通信信息的大小小于或等于所述第二通信信息的大小。
  14. 根据权利要求1至6任一项所述的方法,其中,在发送所述第二通信信息之后,所述方法还包括:
    所述第一通信设备将第三通信信息划分为(n+p)个第二目标子带信息,其中,p为大于或等于0的整数;
    将n个所述第二目标子带信息输入所述第一子AI网络,将(n+p)个第二目标子带信息中的其它p个第二目标子带信息输入所述第一子AI网络,其中,p≤N;
    发送所述第一子AI网络输出的第四通信信息。
  15. 根据权利要求14所述的方法,其中,所述第四通信信息包括第一输出信息和/或第二输出信息,其中,所述第一输出信息的大小与所述第二通信信息的大小相同。
  16. 一种通信信息的发送装置,包括:
    划分模块,用于将第一通信信息划分为n个第一目标子带信息;
    输入模块,用于将n个所述第一目标子带信息输入到第一人工智能AI网络模型的第一子AI网络,其中,所述第一子AI网络的最大输入量为N个子带信息,所述第一AI网络的最大输入量为M个子带信息,n、M和N均为大于0的整数,且n≤N≤M;
    发送模块,用于发送所述第一子AI网络输出的第二通信信息。
  17. 根据权利要求16所述的装置,其中,所述划分模块将第一通信信息划分为一个或多个第一目标子带信息,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第一目标子带信息,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、码域资源、时延域资源、多普勒域资源、傅里叶变换域资源、S域资源和Z域资源。
  18. 根据权利要求17所述的装置,其中,所述划分模块将第一通信信息划分为一个或多个第一目标子带信息,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第一目标子带信息,其中,所述频域单位资源包括以下至少之一:子载波、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第一目标子带信息,其中,所述时域单位资源包括以下至少之一:符号、时隙、半时隙、帧、子帧、无线帧、毫秒、以及秒;
    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第一目标子带信息,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第一目标子带信息,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。
  19. 根据权利要求16所述的装置,其中,所述输入模块将n个所述第一目标子带信息输入到第一人工智能AI网络模型的第一子AI网络,包括:
    将n个所述第一目标子带信息按照预定顺序排列输入到所述第一子AI网络,其中,所述预定顺序包括:n个所述第一目标子带信息的标识从大到小或从小到大的顺序;或者,
    若所述第一子AI网络的输入量固定为N个子带信息,则将n个所述第一目标子带信息和N-n个无效子带信息输入到所述第一子AI网络,其中,n个所述第一目标子带信息位于指定位置。
  20. 根据权利要求16所述的装置,其中,所述第二通信信息的大小为固定值,或所述第二通信信息的大小由输入的所述第一目标子带信息的数量确定。
  21. 根据权利要求20所述的装置,其中,所述第二通信信息的大小由输入的所述第一目标子带信息的数量确定,包括:
    第二通信信息的大小与输入的所述第一目标子带信息的数量成正比;或,
    第二通信信息的大小的增量与输入的所述第一目标子带信息的数量的增量成正比。
  22. 根据权利要求16至21任一项所述的装置,其中,所述装置还包括:
    训练模块,用于使用多个训练样本,对所述第一AI网络模型进行训练,其中,一个所述训练样本包括:m个子带信息以及m个子带信息对应的输出信息的大小,m≤M。
  23. 根据权利要求16至21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。
  24. 根据权利要求16至21任一项所述的装置,其中,
    所述划分模块,还用于所述第一通信设备将第三通信信息划分为(n+p) 个第二目标子带信息,其中,p为大于或等于0的整数;
    所述输入模块,还用于将n个所述第二目标子带信息输入所述第一子AI网络,将(n+p)个第二目标子带信息中的其它p个第二目标子带信息输入第一AI网络模型的第二子AI网络,其中,所述第二子AI网络的最大输入量为P个子带信息,P为大于0的整数,且p≤P≤M;
    所述发送模块,还用于发送所述第一AI网络输出的第四通信信息。
  25. 根据权利要求24所述的装置,其中,
    所述第一子AI网络的输入信息还包括以下至少之一:其它p个所述第二目标子带信息、所述第二子AI网络的中间信息、以及所述第二子AI网络的输出信息;
    所述第二子AI网络的输入信息还包括以下至少之一:n个所述目标子带信息、所述第一子AI网络的中间信息、以及所述第一子AI网络的输出信息。
  26. 根据权利要求24所述的装置,其中,所述第四通信信息包括以下至少之一:第一输出信息、第二输出信息、以及所述第一输出信息和所述第二输出信息按照预设算法进行计算后得到的结果;其中,
    第一输出信息由所述第一子AI网络的输出和/或所述第二子AI网络的输出确定;和/或,
    所述第二输出信息由所述第一子AI网络的输出和/或所述第二子AI网络的输出确定。
  27. 根据权利要求24所述的装置,其中,在p等于0的情况下,所述第四通信信息的大小大于或等于所述第二通信信息的大小。
  28. 根据权利要求24所述的装置,其中,在p等于0的情况下,所述第四通信信息的大小小于或等于所述第二通信信息的大小。
  29. 根据权利要求16至21任一项所述的装置,其中,
    所述划分模块,还用于将第三通信信息划分为(n+p)个第二目标子带信息,其中,p为大于或等于0的整数;
    所述输入模块,还用于将n个所述第二目标子带信息输入所述第一子AI 网络,将(n+p)个第二目标子带信息中的其它p个第二目标子带信息输入所述第一子AI网络,其中,p≤N;
    所述发送模块,还用于发送所述第一子AI网络输出的第四通信信息。
  30. 根据权利要求29所述的装置,所述第四通信信息包括第一输出信息和/或第二输出信息,其中,所述第一输出信息的大小与所述第二通信信息的大小相同。
  31. 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15任一项所述的通信方法的步骤。
  32. 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15任一项所述的通信方法。
PCT/CN2021/132073 2020-11-23 2021-11-22 通信方法、装置及通信设备 WO2022105913A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP21894060.9A EP4250663A4 (en) 2020-11-23 2021-11-22 COMMUNICATION METHOD AND DEVICE AND COMMUNICATION DEVICE
US18/200,546 US20230291517A1 (en) 2020-11-23 2023-05-22 Communication method, communications apparatus, and communications device

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202011324299.8A CN114531355B (zh) 2020-11-23 2020-11-23 通信方法、装置及通信设备
CN202011324299.8 2020-11-23

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US18/200,546 Continuation US20230291517A1 (en) 2020-11-23 2023-05-22 Communication method, communications apparatus, and communications device

Publications (1)

Publication Number Publication Date
WO2022105913A1 true WO2022105913A1 (zh) 2022-05-27

Family

ID=81619216

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/132073 WO2022105913A1 (zh) 2020-11-23 2021-11-22 通信方法、装置及通信设备

Country Status (4)

Country Link
US (1) US20230291517A1 (zh)
EP (1) EP4250663A4 (zh)
CN (1) CN114531355B (zh)
WO (1) WO2022105913A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2024027582A1 (zh) * 2022-08-01 2024-02-08 维沃移动通信有限公司 模型更新方法、装置、通信设备及可读存储介质

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117997484A (zh) * 2022-10-27 2024-05-07 维沃移动通信有限公司 信息传输方法、信息处理方法、装置和通信设备

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1178017A (zh) * 1995-03-14 1998-04-01 西门子公司 设计神经网络的设备及神经网络
US20080120260A1 (en) * 2006-11-16 2008-05-22 Yancey Jerry W Reconfigurable neural network systems and methods utilizing FPGAs having packet routers
CN107203807A (zh) * 2016-03-16 2017-09-26 中国科学院计算技术研究所 神经网络的计算方法、系统及其装置
CN110020722A (zh) * 2017-11-08 2019-07-16 梁平 用于神经网络和逻辑推理的可扩展及实时可重构硬件

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8271336B2 (en) * 1999-11-22 2012-09-18 Accenture Global Services Gmbh Increased visibility during order management in a network-based supply chain environment
JP6164639B2 (ja) * 2013-05-23 2017-07-19 国立研究開発法人情報通信研究機構 ディープ・ニューラルネットワークの学習方法、及びコンピュータプログラム
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
CN110300444B (zh) * 2018-03-23 2021-02-09 维沃移动通信有限公司 信息传输方法、终端及网络设备
CN110830187B (zh) * 2018-08-07 2021-08-17 维沃移动通信有限公司 信息的传输指示方法、网络设备及终端
GB2576499A (en) * 2018-08-15 2020-02-26 Imperial College Sci Tech & Medicine Joint source channel coding for noisy channels using neural networks
CN110972193B (zh) * 2018-09-28 2021-12-03 华为技术有限公司 一种切片信息处理方法及装置
CN111436141A (zh) * 2019-03-25 2020-07-21 维沃移动通信有限公司 信息传输、接收方法、终端及网络侧设备
CN111866953B (zh) * 2019-04-26 2023-05-09 中国移动通信有限公司研究院 一种网络资源分配方法、装置和存储介质
CN110196668B (zh) * 2019-05-31 2021-01-08 维沃移动通信有限公司 信息处理方法和终端设备
KR20190119548A (ko) * 2019-10-02 2019-10-22 엘지전자 주식회사 이미지 노이즈 처리방법 및 처리장치

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1178017A (zh) * 1995-03-14 1998-04-01 西门子公司 设计神经网络的设备及神经网络
US20080120260A1 (en) * 2006-11-16 2008-05-22 Yancey Jerry W Reconfigurable neural network systems and methods utilizing FPGAs having packet routers
CN107203807A (zh) * 2016-03-16 2017-09-26 中国科学院计算技术研究所 神经网络的计算方法、系统及其装置
CN110020722A (zh) * 2017-11-08 2019-07-16 梁平 用于神经网络和逻辑推理的可扩展及实时可重构硬件

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4250663A4

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2024027582A1 (zh) * 2022-08-01 2024-02-08 维沃移动通信有限公司 模型更新方法、装置、通信设备及可读存储介质

Also Published As

Publication number Publication date
EP4250663A1 (en) 2023-09-27
EP4250663A4 (en) 2024-05-08
CN114531355B (zh) 2023-07-18
CN114531355A (zh) 2022-05-24
US20230291517A1 (en) 2023-09-14

Similar Documents

Publication Publication Date Title
WO2022078276A1 (zh) Ai网络参数的配置方法和设备
WO2022105913A1 (zh) 通信方法、装置及通信设备
EP4336738A1 (en) Beam control method and apparatus for intelligent surface device, and electronic device
WO2022184009A1 (zh) 量化的方法、装置、设备及可读存储介质
US20230291658A1 (en) Method for Processing Partial Input Missing of AI Network, and Device
WO2023040887A1 (zh) 信息上报方法、装置、终端及可读存储介质
WO2022073496A1 (zh) 神经网络信息传输方法、装置、通信设备和存储介质
US20230299910A1 (en) Communications data processing method and apparatus, and communications device
US20240088970A1 (en) Method and apparatus for feeding back channel information of delay-doppler domain, and electronic device
US20230261815A1 (en) Communication Information Sending Method, Communication Information Receiving Method, and Communication Device
JP2023527056A (ja) チャネル情報の処理方法及び装置
WO2023198058A1 (zh) 信息传输方法、装置、终端及网络侧设备
WO2023066307A1 (zh) 信道估计方法、装置、终端及网络侧设备
WO2022184011A1 (zh) 信息处理方法、装置、通信设备及可读存储介质
CN115843021A (zh) 数据传输方法及装置
WO2023198094A1 (zh) 模型输入的确定方法及通信设备
WO2023072239A1 (zh) 信道预测方法、装置、网络侧设备及终端
CN117997457A (zh) 参考信号确定方法、终端及网络侧设备
CN118828554A (zh) 信号配置发送方法、接收方法、装置及通信设备
CN115776359A (zh) 导频的发送、接收方法和设备
CN114866381A (zh) 信号处理方法、装置、通信设备及存储介质

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: 21894060

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2021894060

Country of ref document: EP

Ref document number: 202317041972

Country of ref document: IN

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2021894060

Country of ref document: EP

Effective date: 20230623