WO2022042523A1 - 一种通信方法及装置 - Google Patents

一种通信方法及装置 Download PDF

Info

Publication number
WO2022042523A1
WO2022042523A1 PCT/CN2021/114246 CN2021114246W WO2022042523A1 WO 2022042523 A1 WO2022042523 A1 WO 2022042523A1 CN 2021114246 W CN2021114246 W CN 2021114246W WO 2022042523 A1 WO2022042523 A1 WO 2022042523A1
Authority
WO
WIPO (PCT)
Prior art keywords
constellation
communication device
communication
constellation diagram
diagram
Prior art date
Application number
PCT/CN2021/114246
Other languages
English (en)
French (fr)
Inventor
皇甫幼睿
王坚
李榕
王俊
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Priority to EP21860358.7A priority Critical patent/EP4192086A4/en
Priority to BR112023003355A priority patent/BR112023003355A2/pt
Publication of WO2022042523A1 publication Critical patent/WO2022042523A1/zh
Priority to US18/173,221 priority patent/US20230198826A1/en

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L27/00—Modulated-carrier systems
    • H04L27/32—Carrier systems characterised by combinations of two or more of the types covered by groups H04L27/02, H04L27/10, H04L27/18 or H04L27/26
    • H04L27/34—Amplitude- and phase-modulated carrier systems, e.g. quadrature-amplitude modulated carrier systems
    • H04L27/345—Modifications of the signal space to allow the transmission of additional information
    • H04L27/3461—Modifications of the signal space to allow the transmission of additional information in order to transmit a subchannel
    • H04L27/3472—Modifications of the signal space to allow the transmission of additional information in order to transmit a subchannel by switching between alternative constellations
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/06—Testing, supervising or monitoring using simulated traffic
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B17/00—Monitoring; Testing
    • H04B17/30—Monitoring; Testing of propagation channels
    • H04B17/391—Modelling the propagation channel
    • H04B17/3912—Simulation models, e.g. distribution of spectral power density or received signal strength indicator [RSSI] for a given geographic region
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L27/00—Modulated-carrier systems
    • H04L27/32—Carrier systems characterised by combinations of two or more of the types covered by groups H04L27/02, H04L27/10, H04L27/18 or H04L27/26
    • H04L27/34—Amplitude- and phase-modulated carrier systems, e.g. quadrature-amplitude modulated carrier systems
    • H04L27/3405—Modifications of the signal space to increase the efficiency of transmission, e.g. reduction of the bit error rate, bandwidth, or average power
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00—Arrangements for monitoring or testing data switching networks
    • H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W76/00—Connection management
    • H04W76/20—Manipulation of established connections
    • H04W76/27—Transitions between radio resource control [RRC] states

Definitions

  • the present application relates to the field of communication technologies, and in particular, to a communication method and device.
  • a digital communication system is a system that uses digital signals to transmit information.
  • the information to be sent is transmitted on a carrier.
  • the information to be sent and the information transmitted on the carrier are usually mapped by digital modulation.
  • Digital modulation can differentiate signals in amplitude and phase, and each combination of amplitude and phase can be represented as a point in two-dimensional space. All points combined with amplitude and phase can be regarded as a constellation diagram on a two-dimensional plane, that is, the constellation diagram includes multiple constellation points, and each constellation point is obtained by combining amplitude and phase.
  • the information to be sent is encoded and then mapped onto a constellation diagram (or a corresponding constellation point in the constellation diagram) to realize digital modulation.
  • Embodiments of the present application provide a communication method and device, which are used to design a constellation diagram matching a communication scenario, which can adapt to different communication scenarios and communication performance requirements, and improve network performance.
  • an embodiment of the present application provides a communication method, including: a first communication device sends a constellation diagram design parameter; the constellation diagram design parameter includes a communication scenario design parameter and a communication device design parameter; the first communication device receives Information about a second constellation map, where the second constellation map corresponds to the constellation map design parameter; the first communication device uses the second constellation map to communicate.
  • the two communicating parties use the constellation diagram for modulation and demodulation during the communication process.
  • the fixed constellation diagram can no longer meet the communication requirements. Therefore, the first communication device sends a message to the second communication device.
  • Constellation diagram design parameters the second communication device generates a second constellation diagram based on the constellation diagram design parameters, and sends the second constellation diagram to the first communication device, and the first communication device communicates with the second
  • the devices may communicate using the new said second constellation. It can be seen that in this method, the constellation diagrams used by both parties in the communication process can be adaptively changed according to different communication scenarios. By designing a constellation diagram that better matches the current communication scenario, the network performance can be improved and the maximum network performance can be ensured.
  • the first communication device may also use the first constellation map for communication.
  • the first communication apparatus may use the first constellation diagram to send the constellation diagram design parameters
  • the second communication apparatus may use the first constellation diagram to receive the constellation diagram design parameters
  • the first communication apparatus may further update the first constellation diagram to the second constellation diagram, so The first constellation diagram is different from the second constellation diagram.
  • the second constellation diagram may be generated by the second communication apparatus according to the constellation diagram design parameters.
  • the number of constellation points in the first constellation diagram and the second constellation diagram are the same, and the coordinates of the corresponding at least one constellation point are different, and the corresponding at least one constellation point may refer to a constellation point located in the same quadrant. At least one constellation point.
  • the communication scenario design parameters include at least one of the following information: channel characteristics, environment visualization information; wherein, the channel characteristics include at least one of the following information: channel environment type indication, channel model indication, A channel model; the environment visualization information includes at least one of the following information: images collected in the environment, depth pictures, point cloud data, and three-dimensional pictures.
  • the communication device design parameters include at least one of the following information: user behavior portrait, constellation diagram designer reporting parameters; wherein, the user behavior portrait includes at least one of the following information: location distribution of communication devices, service type distribution of communication devices, The mobility distribution of the communication device, the code rate distribution of the communication device, and the hardware parameter distribution of the radio frequency link of the communication device; the parameters reported by the constellation designer include at least one of the following information: the performance fed back by the communication device, and the information obtained by the constellation designer , the formula used to evaluate the performance of constellation diagrams.
  • the communication device includes a first communication device and/or a second communication device.
  • the location distribution of the communication devices may include the location distribution of the first communication device and/or the location distribution of the second communication device
  • the communication device service type distribution may include the service type distribution of the first communication device and/or the location distribution of the second communication device.
  • the mobility distribution of the communication device includes the mobility distribution of the first communication device and/or the mobility distribution of the second communication device
  • the code rate distribution of the communication device includes The code rate distribution of the first communication device and/or the code rate distribution of the second communication device
  • the radio frequency link hardware parameter distribution of the communication device includes the radio frequency link hardware parameter distribution of the first communication device and /or the hardware parameter distribution of the radio frequency link of the second communication device
  • the performance fed back by the communication device includes the performance fed back by the first communication device and/or the performance fed back by the second communication device.
  • the first communication apparatus may further transform the second constellation into a third constellation, where the third constellation The figure shows the constellation diagram closest to the second constellation diagram in the preset constellation diagram.
  • the demodulation complexity of the third constellation is lower than the demodulation complexity of the second constellation.
  • the third constellation diagram may be a regular constellation diagram, that is, the distribution of the positions of constellation points in the third constellation diagram has regularity, for example, the constellation diagrams in the third constellation diagram are symmetrically distributed.
  • the method further includes:
  • the first communication apparatus receives indication information, where the indication information is used to indicate that a fallback mechanism is used, and the fallback mechanism is used to instruct to transform the second constellation map into the first constellation map; or
  • the first communication apparatus sends a first request message, where the first request message is used to request a fallback mechanism, and the fallback mechanism is used to instruct to transform the second constellation map into the first constellation map.
  • a fallback mechanism transforms the second constellation into the first constellation, and the fallback mechanism may be initiated by the first communication device or may be initiated by the second communication device.
  • the first communication apparatus may further store the correspondence between the constellation design parameters and the second constellation.
  • the first communication apparatus may further search for the second constellation map corresponding to the constellation map design parameter in the corresponding relationship according to the constellation map design parameter.
  • the constellation diagram designer can generate the same constellation diagram based on the same or similar communication scenarios, so the first communication device can save the corresponding relationship between the constellation diagram design parameters and the constellation diagram, so as to facilitate the subsequent quick acquisition of the constellation diagram corresponding to the same communication scene .
  • an embodiment of the present application provides a communication method, including: a second communication device receives a constellation design parameter; the constellation design parameter includes a communication scenario design parameter and a communication device design parameter; the second communication device sends Information about a second constellation map, where the second constellation map corresponds to the constellation map design parameters; the second communication device uses the second constellation map to communicate.
  • the second communication device may also use the first constellation map for communication.
  • the communication scenario design parameters include at least one of the following information: channel characteristics, environment visualization information; wherein, the channel characteristics include at least one of the following information: channel environment type indication, channel model indication, channel model; the environment visualization information includes at least one of the following information: images, depth pictures, point cloud data or three-dimensional pictures collected in the environment.
  • the communication device design parameters include at least one of the following information: user behavior portrait, constellation diagram designer reporting parameters; wherein, the user behavior portrait includes at least one of the following information: location distribution of communication devices, service type distribution of communication devices, The mobility distribution of the communication device, the code rate distribution of the communication device, and the hardware parameter distribution of the radio frequency link of the communication device; the parameters reported by the constellation designer include at least one of the following information: the performance fed back by the communication device, and the information obtained by the constellation designer , or a formula for evaluating the performance of a constellation diagram.
  • the second communication apparatus may further update the first constellation diagram to the first constellation diagram according to the constellation diagram design parameter Two constellation diagrams, the first constellation diagram is different from the second constellation diagram.
  • the second communication apparatus updates the first constellation diagram to the second constellation diagram according to the constellation diagram design parameters, including: the second communication apparatus may update the constellation diagram The map design parameters are input into the constellation map designer; the second communication device updates the first constellation map to the second constellation map based on the constellation map designer.
  • the constellation diagram designer may generate a second constellation diagram according to the constellation diagram design parameters.
  • the process of generating the second constellation map from the constellation map design may be regarded as a process of deep reinforcement learning.
  • the second communication apparatus updates the first constellation diagram to the second constellation diagram based on the constellation diagram designer, including: the agent determining the second constellation diagram to be generated. modulation level, and determine the number of constellation points N corresponding to the modulation level, where N is a positive integer; the agent determines the constellation point coordinates of the N constellation points; the evaluator determines the scene state and The constellation diagram design parameter determines the decoding results of the N constellation points; the agent adjusts the coordinates of the N constellation points according to the decoding results of the N constellation points until the constellation Graph Designer converges.
  • the modulation level of the second constellation map to be generated may be the same as the modulation level of the first constellation map, or the modulation level of the second constellation map to be generated may be the first communication device and the second constellation map.
  • the communication device is agreed/negotiated in advance during communication.
  • the convergence condition of the constellation diagram designer may be the number of rounds of deep reinforcement learning, or when the reward no longer increases/changes, it is determined that the constellation diagram designer converges.
  • the return is used to evaluate the communication performance of the generated constellation, and can include one or more of the following metrics: throughput, bit error ratio (BER), block error rate (BLER), spectral efficiency and other parameters.
  • the state in deep reinforcement learning includes the constellation map generated by the agent
  • the action in deep reinforcement learning includes adjustment of the coordinates of constellation points by the agent
  • the reward in deep reinforcement learning includes the translation determined by the evaluator. code result.
  • the constellation designer is located in a communication link, ie the constellation designer is included in the communication link of the first communication device and the second communication device.
  • the constellation diagram designer includes the agent and the evaluator; or optionally, the constellation diagram designer includes the agent, and the evaluator is located in the constellation diagram outside the designer.
  • the decoding result may also be a bit error rate, that is, the bit error rate is fed back to the agent as a reward.
  • the agent adjusts the coordinates of the N constellation points according to the decoding results of the N constellation points, including: the agent can adjust the coordinates of the N constellation points according to the decoding results of the N constellation points. According to the code result, the coordinates of some constellation points in the N constellation points are modulated.
  • the agent can design only a part of the constellation diagram. For example, there are 8 constellation points in the constellation diagram.
  • the reinforcement learning can explore and design only two of the constellation points, and the coordinates of the remaining constellation points remain unchanged.
  • the time step of constellation design is greatly reduced, which is equivalent to local correction and fine-tuning of the constellation diagram, which can reduce the resource consumption caused by deep reinforcement learning exploration, and can ensure that the performance of the constellation diagram obtained by exploration is lower than that of the constellation diagram in the current standard. will drop too much, which can guarantee the reliable transmission of the system.
  • the constellation diagram designer determining the constellation point coordinates of the N constellation points includes: the constellation diagram designer may determine the constellation point coordinates of the N constellation points within a set coordinate range .
  • the coordinate value of the constellation point is sampled from the Gaussian distribution, and the value range of the coordinate value of the constellation point is theoretically infinite.
  • the exploration constellation point When the coordinate value of the exploration output exceeds the coordinate value range, you can set the coordinates of the constellation point to this coordinate value range to ensure that the performance of the exploration constellation map will not be too bad.
  • the evaluator can also determine the decoding results of the N constellation point coordinates after each adjustment; the agent selects the N constellation point coordinates with the best decoding results to generate the second constellation picture.
  • the goal of the agent is to maximize the decoding performance, that is, to optimize the decoding performance and gradually converge. After a period of training, the decoding performance almost no longer increases. At this time, you can select a round with the best performance, record the actions/actions at each time step, and form a complete constellation diagram in sequence, so as to obtain the current scene. Design of the second constellation diagram.
  • the network device may also determine the Constellation point obtained by signal demodulation of service data. For example, the constellation point with the smallest distance may be determined as the constellation point obtained by demodulating the signal of the service data.
  • the network device may also decode the service data signal according to the distance between the received service data signal and each constellation point in the second constellation diagram, An evaluation result of the business data is determined. For example, a decoding method may be used to calculate the evaluation result of the service data, that is, soft information.
  • the agent will also output other parameters in the communication link, such as filter parameters in the communication link, pilot signal configuration parameters, soft information processing configuration parameters, precoding configuration parameters, etc. Adjust and optimize these parameters and constellations to obtain the best decoding performance.
  • the second communication apparatus may further transform the second constellation diagram into a third constellation diagram, and the third constellation diagram
  • the constellation diagram is the constellation diagram closest to the second constellation diagram in the preset constellation diagram.
  • the demodulation complexity of the third constellation is lower than the demodulation complexity of the second constellation, and converting the third constellation into the third constellation is easier for modulation and demodulation in the communication process It is beneficial to improve the communication performance.
  • the method further includes:
  • indication information where the indication information is used to indicate that a fallback mechanism is used, and the fallback mechanism is used to instruct to transform the second constellation map into the first constellation map;
  • the second communication apparatus receives a first request message, where the first request message is used to request a fallback mechanism, and the fallback mechanism is used to instruct to transform the second constellation map into the first constellation map.
  • the first constellation diagram prevents the communication between the communication devices from being affected, and can ensure the normal communication between the communication devices.
  • the second communication apparatus may further store the correspondence between the constellation design parameters and the second constellation.
  • the second communication apparatus may further search for the second constellation map corresponding to the constellation map design parameter in the corresponding relationship according to the constellation map design parameter.
  • the constellation diagram designer can generate the same constellation diagram based on the same or similar communication scenarios, so the corresponding relationship between the constellation diagram design parameters and the constellation diagram can be saved in the second communication device, so as to facilitate the subsequent quick acquisition of the constellation diagram corresponding to the same communication scene , to improve network performance.
  • an embodiment of the present application further provides a communication device, where the communication device has the function of implementing the first communication device or the second communication device in the above method embodiments.
  • These functions can be implemented by hardware or by executing corresponding software by hardware.
  • the hardware or software includes one or more functional modules corresponding to the above-mentioned functions.
  • an embodiment of the present application further provides a communication device, and the communication device may be the first communication device or the second communication device in the above method embodiments, or the first communication device or the second communication device provided in the first communication device or the second communication device.
  • the communication device includes a transceiver and a processor, and optionally, also includes a memory, wherein the memory is used to store computer programs or instructions, and the processor is respectively coupled with the memory and the transceiver, and when the processor executes the described When a computer program or instruction is used, the communication device is made to execute the method executed by the first communication device or the second communication device in the above method embodiments.
  • an embodiment of the present application further provides a computer program product, the computer program product includes: computer program code, when the computer program code is run on a computer, the computer program code enables the computer to execute any one of the above-mentioned aspects. method.
  • an embodiment of the present application further provides a chip system, the chip system includes a processor and a memory, and the processor and the memory are electrically coupled; the memory is used to store computer program instructions; The processor is configured to execute part or all of the computer program instructions in the memory, and when the part or all of the computer program instructions are executed, is used to implement the method described in any one of the above aspects.
  • the chip system further includes a transceiver, and the transceiver is configured to send a signal processed by the processor, or receive a signal input to the processor.
  • the chip system may be composed of chips, or may include chips and other discrete devices.
  • an embodiment of the present application further provides a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, and when the computer program is executed, the method described in any one of the foregoing aspects is implemented.
  • an embodiment of the present application further provides a communication system, and the system may include a first communication device that executes the method described in the first aspect and any possible implementation of the first aspect, and executes the first communication device described above.
  • FIG. 1 is an architectural diagram of a network system applicable in the embodiment of the application
  • FIG. 2, FIG. 3b, and FIG. 6 are schematic diagrams of a communication flow applicable in the embodiment of the application;
  • Fig. 3a, Fig. 3c, Fig. 4a, Fig. 4b are schematic diagrams of a constellation diagram design applicable in the embodiment of the present application;
  • 5a and 5b are schematic diagrams of a constellation diagram applicable in the embodiment of the present application.
  • FIG. 7 and FIG. 8 are structural diagrams of a communication device applicable to the embodiments of the present application.
  • the word "exemplary” is used to mean serving as an example, illustration or illustration. Any embodiment or design described in this application as "exemplary” should not be construed as preferred or advantageous over other embodiments or designs. Rather, the use of the word example is intended to present a concept in a concrete way.
  • the network architecture and service scenarios described in the embodiments of the present application are for the purpose of illustrating the technical solutions of the embodiments of the present application more clearly, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application.
  • the evolution of the architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.
  • Terminal devices including devices that provide users with voice and/or data connectivity, specifically, include devices that provide users with voice, or include devices that provide users with data connectivity, or include devices that provide users with voice and data connectivity sexual equipment.
  • it may include a handheld device with wireless connectivity, or a processing device connected to a wireless modem.
  • the terminal equipment can communicate with the core network via a radio access network (RAN), exchange voice or data with the RAN, or exchange voice and data with the RAN.
  • RAN radio access network
  • the terminal equipment may include user equipment (UE), wireless terminal equipment, mobile terminal equipment, device-to-device (D2D) terminal equipment, vehicle to everything (V2X) terminal equipment , machine-to-machine/machine-type communications (M2M/MTC) terminal equipment, Internet of things (IoT) terminal equipment, light terminal equipment (light UE), subscriber units ( subscriber unit), subscriber station (subscriber station), mobile station (mobile station), remote station (remote station), access point (access point, AP), remote terminal (remote terminal), access terminal (access terminal), User terminal, user agent, or user device, etc.
  • UE user equipment
  • D2D device-to-device
  • V2X vehicle to everything
  • M2M/MTC machine-to-machine/machine-type communications
  • IoT Internet of things
  • light UE light UE
  • subscriber units subscriber unit
  • subscriber station subscriber station
  • mobile station mobile station
  • remote station remote station
  • access point access point
  • AP remote terminal
  • these may include mobile telephones (or "cellular" telephones), computers with mobile terminal equipment, portable, pocket-sized, hand-held, computer-embedded mobile devices, and the like.
  • mobile telephones or "cellular" telephones
  • PCS personal communication service
  • SIP session initiation protocol
  • WLL wireless local loop
  • PDA personal digital assistant
  • constrained devices such as devices with lower power consumption, or devices with limited storage capacity, or devices with limited computing power, etc.
  • it includes information sensing devices such as barcodes, radio frequency identification (RFID), sensors, global positioning system (GPS), and laser scanners.
  • RFID radio frequency identification
  • GPS global positioning system
  • the terminal device may also be a wearable device.
  • Wearable devices can also be called wearable smart devices or smart wearable devices, etc. It is a general term for the application of wearable technology to intelligently design daily wear and develop wearable devices, such as glasses, gloves, watches, clothing and shoes. Wait.
  • a wearable device is a portable device that is worn directly on the body or integrated into the user's clothing or accessories. Wearable device is not only a hardware device, but also realizes powerful functions through software support, data interaction, and cloud interaction.
  • wearable smart devices include full-featured, large-scale, complete or partial functions without relying on smart phones, such as smart watches or smart glasses, and only focus on a certain type of application function, which needs to cooperate with other devices such as smart phones.
  • Use such as all kinds of smart bracelets, smart helmets, smart jewelry, etc. for physical sign monitoring.
  • the various terminal devices described above if they are located on the vehicle (for example, placed in the vehicle or installed in the vehicle), can be considered as on-board terminal equipment.
  • the on-board terminal equipment is also called on-board unit (OBU). ).
  • the terminal device may further include a relay (relay).
  • a relay relay
  • any device capable of data communication with the base station can be regarded as a terminal device.
  • the apparatus for implementing the function of the terminal device may be the terminal device, or may be an apparatus capable of supporting the terminal device to implement the function, such as a chip system, and the apparatus may be installed in the terminal device.
  • the chip system may be composed of chips, or may include chips and other discrete devices.
  • Network equipment including, for example, access network (AN) equipment, such as a base station (for example, an access point), which may refer to a device in the access network that communicates with wireless terminal equipment over the air interface through one or more cells , or, for example, a network device in a vehicle-to-everything (V2X) technology is a roadside unit (RSU).
  • the base station may be used to interconvert the received air frames and IP packets, acting as a router between the terminal equipment and the rest of the access network, which may include the IP network.
  • the RSU can be a fixed infrastructure entity supporting V2X applications and can exchange messages with other entities supporting V2X applications.
  • the network device can also coordinate the attribute management of the air interface.
  • the network equipment may include an evolved base station (NodeB or eNB or e-NodeB, evolutional Node B) in a long term evolution (long term evolution, LTE) system or long term evolution-advanced (LTE-A), Alternatively, it may also include the next generation node B (gNB) in the 5th generation mobile communication technology (the 5th generation, 5G) NR system (also referred to as the NR system for short), or may also include a cloud access network (cloud access network).
  • gNB next generation node B
  • 5G 5th generation mobile communication technology
  • 5G 5th generation NR system
  • cloud access network cloud access network
  • CU central unit
  • DU distributed unit
  • the network equipment may also include core network equipment.
  • the core network equipment includes, for example, an access and mobility management function (AMF) or a user plane function (UPF) and the like.
  • AMF access and mobility management function
  • UPF user plane function
  • the network device may also be a device for carrying network device functions in a device-to-device (Device to Device, D2D) communication, a machine-to-machine (Machine to Machine, M2M) communication, a vehicle networking, or a satellite communication system.
  • D2D Device to Device
  • M2M Machine to Machine
  • the constellation diagram is used for the modulation of the signal by the communication device when it is sent, and also for the demodulation of the signal when the communication device is received.
  • constellation diagrams can be used to define the amplitude and phase of signal elements, and digital modulation can differentiate signals in amplitude and phase.
  • a signal element can be represented by a constellation point, and each combination of magnitude and phase can be represented as a constellation point.
  • the horizontal X-axis of the constellation diagram is related to the in-phase carrier
  • the vertical Y-axis of the constellation diagram is related to the quadrature carrier.
  • the number and coordinates of the constellation points in the constellation diagrams of different modulation and demodulation methods may be different.
  • the modulation and demodulation methods include quadrature phase shift keying (QPSK), 16 quadrature amplitude modulation (quadrature amplitude modulation, QAM) ) or 64QAM, etc.
  • QPSK quadrature phase shift keying
  • QAM quadrature amplitude modulation
  • 64QAM 64QAM
  • each constellation point can represent 2-bit binary information, and each point can also be regarded as a code with 2-bit binary information, and the codes corresponding to the four constellation points are 00 and 01 respectively.
  • the coordinates of these four constellation points can be designed as [1,1], [-1,1], [1,-1] and [-1,-1] respectively.
  • the abscissa and ordinate of each constellation point can also be divided by ⁇ 2.
  • the binary information to be sent is encoded and then mapped to the constellation points in the constellation diagram, so as to realize digital modulation (also called constellation modulation).
  • demodulation according to the distance between the received signal and each constellation point in the constellation diagram, it is determined which signal is sent by the transmitting end, so as to correctly demodulate the data. For example, when demodulating the received QPSK signal, according to the distance between the QPSK signal and the four constellation points in the constellation diagram, if the distance to the 00 point is the closest, it can be determined that the received QPSK signal is 00, or another example is the QPSK constellation.
  • the four constellations in the figure are distributed symmetrically in four quadrants, and the receiver can complete the demodulation of the signal by judging which quadrant the received signal is in.
  • the codes represented by adjacent constellation points in the constellation diagram differ by only 1 bit as far as possible. This can ensure that when a constellation point is misjudged as its adjacent code, the number of misjudged bits is the least, that is to say, the BER can be as small as possible.
  • the communication performance is affected by the modulation method.
  • the design of the modulation method includes: a. Based on the channel assumption of random bit random equal probability and additive white gaussian noise (AWGN), the design of the modulation constellation points makes the adjacent constellations Points conform to the characteristics of Gray code; b Use methods such as constellation shaping and probability shaping to improve communication performance.
  • Mode a is a constellation diagram designed under ideal conditions, which cannot be well adapted to actual communication scenarios.
  • Mode b is to design a constellation mapping with unequal probability when the designed constellation diagram is in use. The positions of the constellation points do not change, but only the mapping probability is changed.
  • the existing communication system adopts a fixed constellation diagram design, that is, the positions of the constellation points in the constellation diagram are fixed, both parties in the communication store the fixed constellation diagram, and can use the fixed constellation diagram to complete the modulation and demodulation of the communication .
  • the constellation diagram used by the communication device for communication can be adaptively changed according to different communication scenarios, that is to say, different constellation diagrams have different performances in different scenarios, and a constellation diagram that better matches the current scene can be designed, so that the The performance of the network is maximized.
  • a constellation diagram designer can be used for constellation diagram design based on different scenarios. The constellation diagram designer takes the relevant information of the current scene as the most basic input, and outputs a constellation diagram adapted to this scene. The process of designing the constellation diagram by the constellation diagram designer can be implemented based on deep reinforcement learning.
  • DRL Deep reinforcement learning
  • a deep neural network has an input layer and an output layer, and has at least one hidden layer between the input layer and the output layer, and may have nonlinear activation function processing after the hidden layer, such as a rectified linear unit (ReLU) function or the tanh function, etc.
  • the input layer, output layer, and hidden layer can be collectively referred to as network layers, or simply referred to as layers.
  • the layers are connected to each other by the nodes on each layer, and a pair of connected nodes has a weight value and a bias value.
  • a deep neural network can be viewed as a nonlinear transformation from input to output.
  • the output can also calculate the loss through a loss function, and the gradient generated by the calculation can be passed back from the output layer to the input layer using the back-propagation algorithm to update the weight value and bias of each layer. set value to minimize the loss.
  • Reinforcement learning is a process in which an agent interacts with the environment and learns the optimal strategy through trial and error (or exploration). Especially for problems with a series of decisions, reinforcement learning can provide a solution when theoretical modeling cannot be done or the solution is difficult. Reinforcement learning may also include the following concepts: state (or observation), policy, reward (also called reward), time step, round, and value function. Among them, the agent can act/act on the environment according to the state of the environment feedback, so as to obtain the reward and the state of the next moment. return). The policy determines what action the agent will take given a state, that is, a policy can be thought of as a mapping from states to actions.
  • observations can be the input of the deep neural network, and actions correspond to the output of the deep neural network.
  • the reward is the value of the environment feedback after the agent takes a certain action in the current environment, that is, the evaluation of the quality of the action taken by the agent.
  • the agent takes an action, and the environment feeds back a reward value.
  • the problems usually encountered are not problems that can be solved by optimizing a single action, but the final results or comprehensive results brought about by optimizing a series of decisions.
  • Each round contains multiple time steps.
  • the environment can return a reward value at the time step at the end of each round, in which case the reward value at each time step before the end of the round can be replaced by zero.
  • the value function is also a kind of mapping.
  • the input of the value function can be a state, or a collection of states and actions.
  • the output of the value function is a value, which represents the estimated value of the total reward that the agent can accumulate in the future. The currently selected action is better.
  • the value function can also be represented by a deep neural network, the input of the value function is the input of the deep neural network, and the output of the value function is the output of the deep neural network.
  • At least one item(s) below or similar expressions thereof refer to any combination of these items, including any combination of single item(s) or plural items(s).
  • at least one item (a) of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple .
  • the ordinal numbers such as “first” and “second” mentioned in the embodiments of the present application are used to distinguish multiple objects, and are not used to limit the order, sequence, priority or priority of multiple objects. Importance.
  • the first data packet and the second data packet are only for distinguishing different data packets, but do not indicate the difference in content, priority, sending order, or importance of the two data packets.
  • the communication methods provided in the embodiments of the present application can be applied to various communication systems, for example, satellite communication systems, Internet of things (Internet of things, IoT), narrow-band Internet of things (NB-IoT) systems, global Mobile communication system (global system for mobile communications, GSM), enhanced data rate for GSM evolution (enhanced data rate for GSM evolution, EDGE), wideband code division multiple access system (wideband code division multiple access, WCDMA), code division multiple access 2000 system (code division multiple access, CDMA2000), time division synchronization code division multiple access system (time division-synchronization code division multiple access, TD-SCDMA), long term evolution system (long term evolution, LTE), fifth generation (5G) ) communication systems, such as 5G new radio (NR), and three major application scenarios of 5G mobile communication systems: enhanced mobile broadband (eMBB), ultra-reliable, low-latency communications (ultra reliable low latency communications) , uRLLC) and massive machine type communications (mMTC), or other or future communication systems.
  • enhanced mobile broadband
  • the network architecture shown in FIG. 1 includes a network device and a terminal device, and the network device and the terminal device communicate using a constellation diagram.
  • the number of the network devices may be one or more, and the number of the terminal devices may be one or more (as shown in FIG. 1, two terminal devices).
  • the type and quantity are not limited.
  • the constellation diagram design used in the current communication standard is fixed. For example, when the modulation and demodulation mode is QPSK, the agreed and fixed first constellation diagram is adopted, and when the modulation and demodulation mode is 16QAM, the agreed and fixed second constellation diagram is adopted. Constellation. With the development of communication technology and communication scenarios, the performance requirements of communication systems are getting higher and higher, and many vertical application scenarios (such as industrial Internet, Internet of Vehicles, etc.) have appeared, and fixed constellation diagrams cannot adapt to changing communication scenarios and Communication performance requirements, resulting in poor communication performance in the actual communication process.
  • an embodiment of the present application provides a communication method, and the communication method provided by the embodiment of the present application is applicable to the communication system shown in FIG. 1 .
  • the communication device can adaptively design the constellation diagram used in communication based on the relevant information of the current scene, which can ensure the design of the constellation diagram more matching with the current scene and improve the performance of the communication network.
  • the scene-related information can be understood as the constellation diagram design parameters of the constellation diagram designer.
  • the specific flow of the communication method may include:
  • the first communication device sends a constellation design parameter
  • the second communication device receives the constellation design parameter, where the constellation design parameter includes a communication scenario design parameter and a communication device design parameter.
  • the first communication device may be a terminal device or a network device, for example, the first communication device is a terminal device.
  • the second communication device may be a terminal device or a network device, for example, the second communication device is a network device (eg, a base station).
  • the first communication apparatus may actively send the constellation design parameters.
  • the first communication apparatus may periodically acquire the constellation design parameters, and then send the acquired constellation design parameters to the second communication apparatus.
  • RRC radio resource control
  • the first communication device acquires the constellation design parameters, and then uses the acquired parameters.
  • the constellation design parameters are sent to the second communication device.
  • the second communication device may send a first message to the first communication device, where the first message is used to inquire whether the first communication device supports updating the constellation map, that is, to inquire the first communication device Whether a communication device has the capability to update the constellation, or the first message is used to notify/instruct/request the first communication device to send constellation design parameters.
  • the first communication apparatus may also actively request the second communication apparatus to update the constellation map.
  • the first communication device may feed back capability information to the second communication device to indicate whether the first communication device supports Update the constellation chart. For example, a newly added updateConstellation field can be used to indicate whether the first communication device supports updating the constellation diagram. When the value of the updateConstellation field is true, it means that the first communication device supports updating the constellation diagram, and when the value of the updateConstellation field is false , it indicates that the first communication device does not support updating the constellation map. If the first communication apparatus supports updating the constellation diagram, the first communication apparatus may subsequently send the constellation diagram design parameters in the uplink.
  • the first communication device supports updating a constellation diagram, for example, the first communication device supports updating a constellation diagram used for communication in hardware, or the first communication device supports acquiring a constellation diagram design in hardware parameter.
  • the core network device may further authenticate the capability information of the first communication apparatus.
  • the first communication device sends the second communication to the second communication device according to the notification/instruction/request of the first message The device sends the constellation diagram design parameters.
  • the first constellation diagram may be used for communication between the first communication device and the second communication device.
  • the first constellation diagram may be a fixed constellation diagram specified in the current standard, or the first constellation diagram may be a constellation diagram generated according to a constellation diagram design parameter.
  • the first communication device uses the first constellation map to send the constellation map design parameters; the second communication device uses the first constellation map to receive the constellation map Design Parameters.
  • the constellation diagram design parameters may be mainly related to the first communication device, such as communication scenario design.
  • the communication device involved in the parameters and communication device design parameters mainly refers to the first communication device. However, this does not mean that the influence of the design parameters related to the second communication device on the design of the constellation diagram is not considered.
  • the communication scene design parameters include at least one of the following information: channel characteristics, environment visualization information, time, weather and other context-related information.
  • the channel feature is a description of the channel environment where the communication device is located, and may be a statistical result within a period of time.
  • the channel characteristics may include indications of channel environment types, such as city, country, office A, street B, and home C, which can reflect indication information of different channel characteristics. Use the information of home, 0.5, office, and 0.5 as the channel environment type indication.
  • the channel feature may include a channel model indication, multiple channel models may be stored in the communication system, and each channel model may correspond to a different scenario. By providing the channel model indication, the constellation diagram designer can be informed of the channel characteristics of the current scene, and in order to save signaling overhead, part of the replacement parameters in the known channel model can also be sent.
  • the channel feature may be a statistically obtained channel model, or may be a channel model determined based on methods such as ray tracing, or may be a channel model implemented by a neural network. It can be understood that the communication device involved in the embodiments of the present application includes the first communication device and/or the second communication device.
  • the channel environment type indication can give a general understanding of the channel characteristics, and the environment visualization information can provide a further description of the scene, making the constellation diagram designed by the constellation diagram designer more accurate.
  • Providing environment visualization information helps communication systems to model the environment through ray tracing to build channel models or as inputs to channel models.
  • Environment visualization information is used to describe the size and position of objects in space, and may include one or more of images collected in the environment, depth images, point cloud data, or three-dimensional images.
  • the designed constellation diagrams are also different. Therefore, the optimal constellation diagram can be explored for different scenarios to ensure that the performance of the constellation diagram can be further improved. Design a constellation diagram that best matches the current scene.
  • the communication device design parameters include at least one of the following information: user behavior portraits, constellation diagram designer reward parameters, and constellation diagram designer training parameters.
  • User behavioral profile represents the behavioral preferences of users over a period of time, so it can be represented by distribution, which is statistical information over a period of time.
  • the user behavior profile may include the location distribution of the communication device, and the location distribution may be a statistic of changes in the geographic location of the communication device over a period of time.
  • the user behavior portrait may include the service type of the communication device, and the service type refers to the statistics of the service type used by the communication device within a period of time, such as voice service, data service, etc., and the data service can be divided into high latency requirements. games, virtual reality (VR), and/or web pages with lower latency requirements.
  • the type of service may affect the distribution of received data, ie the distribution of sources.
  • the user behavior profile may include a mobility distribution of the communication device, where the mobility distribution is a statistic of the mobility of the communication device over a period of time.
  • the mobility refers to the speed at which the communication device moves, such as stationary, low mobility or high mobility, or the mobility can also be a specific moving speed.
  • the user behavior profile may include physical layer configuration information.
  • the physical layer configuration information may be obtained by statistics within a period of time, and the physical layer configuration information may include code rate, codec type, filter type, waveform information, pilot frequency information, antenna configuration, precoding information, etc. one or more.
  • the user behavior profile includes the hardware parameter distribution of the radio frequency link of the communication device, which refers to the statistical hardware parameter changes within a period of time.
  • the radio frequency link hardware parameters include the device unique identification code used by the communication device, the international mobile subscriber identity (IMSI), the device model, the antenna model, and the digital-to-analog converter (digital-to-analog converter) in the radio frequency link.
  • IMSI international mobile subscriber identity
  • DAC digital-to-digital converter
  • ADC analog-to-digital converter
  • the constellation designer report parameter includes at least one of the following information: information fed back by the communication device, performance calculated by the constellation designer, or a formula for evaluating the constellation performance.
  • Performance refers to throughput, bit error rate, data rate, peak to average power ratio (PAPR) and other indicators that have an impact on the performance of the communication system.
  • the performance can also be the key performance indicator (key performance indicator) feedback from the communication device. , KPI), such as capacity, service quality, delay, call dropped statistics and other indicators.
  • KPI key performance indicator
  • the formula for evaluating the performance of the constellation map may be a formula for calculating whether the constellation map satisfies the Gray code, a formula for calculating the code distance of the constellation map, or other performance evaluation formulas that can reflect the use of the constellation map in the communication system.
  • the constellation designer training parameters include at least one of the following information: training convergence conditions, training rounds, time steps included in each round, training iterations, coordinate range of constellation points, or the number of training constellation points.
  • the convergence condition of the training may be the number of iterations for training, or the number of rounds for training, or the decoding performance no longer increases, or the like.
  • the convergence condition of the training may be the number of iterations for training, or the number of rounds for training, or the decoding performance no longer increases, or the like.
  • the constellation diagram designer can predict the scenarios, for example, based on historical scenarios, infer possible future scenarios, and design constellation diagrams according to possible future scenarios.
  • the second communication device updates the first constellation map to a second constellation map according to the constellation map design parameters, where the second constellation map corresponds to the constellation map design parameters.
  • the second constellation map is used for the first communication device and the second communication device to communicate using the second constellation map, or the second constellation map is used to implement the first communication device and the second constellation map. the modulation and demodulation between the second communication devices.
  • the second constellation diagram is different from the first constellation diagram.
  • the number of constellation points in the second constellation diagram and the first constellation diagram are the same, and the coordinates of the constellation points are different.
  • the constellation points in the second constellation diagram may be distributed randomly or symmetrically.
  • a constellation diagram designer exists in the communication link, for example, the second communication device may be provided with a constellation diagram designer.
  • the constellation diagram designer may adopt a deep reinforcement learning method, the input of the constellation diagram designer is scene-related information, that is, constellation diagram design parameters, and the output of the constellation diagram designer is the second constellation diagram. This method of determining the constellation diagram according to the scene can be regarded as a targeted design of the constellation diagram.
  • the first communication apparatus sends the constellation diagram design parameters to the first and second communication apparatuses.
  • the second communication apparatus inputs the constellation diagram design parameters into a constellation diagram designer, the second communication apparatus may generate the second constellation diagram based on the constellation diagram designer, and then the second communication
  • the apparatus may update the first constellation map to the second constellation map, and the second constellation map is the constellation map suitable for the current scene.
  • the second communication device may send the second constellation to the first communication device.
  • the process of generating the second constellation diagram based on the constellation diagram designer may refer to the following detailed description.
  • S203 The second communication apparatus sends the information of the second constellation, and the first communication apparatus receives the information of the second constellation.
  • the information of the second constellation diagram may be identification information of the second constellation diagram, or may be the coordinates of each constellation point in the second constellation diagram, or the like.
  • the first communication device may send a second message to the second communication device, where the second message is used to request to switch to the updated constellation map (that is, the first constellation map). two constellations) to communicate.
  • the second communication device initiates RRC connection reconfiguration, and after the RRC connection reconfiguration is completed, the updated constellation diagram can be used for communication between the first communication device and the second communication device.
  • S204 The first communication apparatus and the second communication apparatus communicate using the second constellation.
  • the process of using the updated second constellation for communication is shown in Figure 3b.
  • the sender performs channel coding on the information bits to be sent, modulates the coded signal using the second constellation, and transmits the modulated signal through the channel.
  • Sent to the receiver the second constellation diagram is generated based on the constellation diagram designer.
  • the receiver uses the second constellation diagram to demodulate the received signal, and performs channel decoding on the demodulated signal to obtain decoded bits, which can be regarded as information sent by the sender.
  • the designed constellation diagrams are highly likely to be irregular, and the demodulation complexity of the irregular constellation diagrams is higher than that of the regular constellation diagrams.
  • the distribution/position/coordinates of the constellation points in the irregular constellation diagram do not have regularity, while the distribution/position/coordinates of the constellation points in the regular constellation diagram have regularity (for example, the constellation points are distributed symmetrically). Therefore, the first communication device may further transform the second constellation into a third constellation, and the second communication device may also transform the second constellation into the third constellation, and the first constellation
  • the three constellation diagrams are the constellation diagrams closest to the second constellation diagram in the preset constellation diagram.
  • the preset constellation diagram may be a regular constellation diagram.
  • the third constellation diagram may be a regular constellation diagram that has the same number of constellation points as the second constellation diagram, and the coordinates of the constellation points are the closest. Constellation. After the first communication device and the second communication device are transformed into the third constellation map, the third constellation map may also be used for communication.
  • the fallback mechanism may be adopted, and the The new second constellation diagram returns to the original first constellation diagram, the first threshold is used to indicate the degree of performance degradation of the communication system, and the value of the first threshold is not limited in this embodiment of the present application.
  • the fallback mechanism may be initiated by a second communication apparatus, and the second communication apparatus sends indication information to the first communication apparatus, where the indication information is used to indicate that a fallback mechanism is adopted, and the fallback mechanism is used.
  • the fallback mechanism may be initiated by a first communication apparatus, and the first communication apparatus sends a first request message to the second communication apparatus, where the first request message is used to request a fallback mechanism, the fallback mechanism is used to instruct to transform the second constellation map into the first constellation map.
  • the first communication device and the second communication device may use the first constellation for communication.
  • the design process of the constellation diagram may occur online during the use of the communication device, that is, the communication device designs and updates the constellation diagram online when working in a changed environment or scene where the communication device is located.
  • a targeted constellation diagram can be designed offline according to a specific scenario. For example, when a communication device is in production, it is already clear that it will be applied in a certain scenario, and the scenario will basically not change. Pre-design a constellation diagram for this scenario.
  • offline design is generally not as flexible as online design. Most communication devices work in changing environments and scenarios. Online design and updating of constellation diagrams can provide higher flexibility and keep communication devices in a high-performance operating state. According to actual needs, choose online design constellation diagram or offline design constellation diagram.
  • a mapping table can be stored, which will be The constellation diagram obtained by deep reinforcement learning is saved in the mapping table.
  • the corresponding constellation diagram can be directly determined by looking up the table, wherein the first communication device and the second communication device can both save the mapping table, and the first communication device can store the mapping table.
  • the apparatus and the second communication apparatus may update the mapping table regularly, or select and update the corresponding constellation diagram through the constellation diagram serial number in the table.
  • the mapping table may be as shown in Table 1.
  • Table 1 stores the correspondence between some constellation design parameters and the constellation, and assigns serial numbers/identification information to each correspondence.
  • the design parameters of the constellation diagram include the source distribution as the source distribution x, the channel feature as the high-frequency indoor channel, the physical layer configuration as the code rate 0.5, the hardware parameter as 3bit ADC, and the constellation diagram as the constellation diagram A.
  • the design parameters of the constellation diagram include the source distribution as the source distribution y, the channel feature as the low-frequency urban channel, the physical layer configuration as the code rate 0.75, the hardware parameter as full duplex, and the constellation diagram as the constellation diagram B.
  • the first communication apparatus and the second communication apparatus may store the correspondence between the constellation design parameters and the second constellation.
  • the first communication apparatus and the second communication apparatus may assign identification information (eg, assign first identification information) to the corresponding relationship.
  • the first communication device and the second communication device may further search for the second constellation map corresponding to the constellation map design parameter in the corresponding relationship according to the constellation map design parameter .
  • the first communication device and the second communication device can preferentially search in the mapping table
  • the constellation diagram corresponding to the constellation diagram design parameter if the mapping table does not include the constellation diagram corresponding to a certain constellation diagram design parameter, the second communication device may design the parameter for the constellation diagram to generate the corresponding constellation diagram.
  • the process of generating the second constellation diagram based on the constellation diagram designer will be described in detail below.
  • the process of generating the second constellation diagram based on the constellation diagram designer can be regarded as a learning and training process for the constellation diagram design, and the constellation diagram design parameters in this process may include the constellation diagram designer reward parameters and/or the constellation diagram design training parameters .
  • the agent can try to generate a constellation diagram based on the constellation diagram design parameters obtained from the outside, and the evaluator can evaluate the performance of the constellation diagram that the agent tries to generate, and determine the agent's attempt to generate a constellation diagram. Whether the generated constellation diagram is the constellation diagram that best matches the current scene. Specifically, the design parameters of the constellation diagram and the constellation diagram that the agent tries to generate are used as the input of the evaluator, which changes the evaluation conditions of the evaluator. The evaluator recalculates the reward according to the changed evaluation conditions, and the agent can aim to increase the reward.
  • the agent when the reward no longer increases, the agent is considered to converge, and the constellation map output in the convergent state is the final constellation map, that is, the second constellation map.
  • the state is a possible constellation diagram
  • the action is the change to this constellation diagram
  • the reward is the value of the new constellation diagram after the action is taken, that is, the performance of the constellation diagram.
  • the estimator can be a link-level simulator, a system-level simulator, a theoretical calculation formula, or a table look-up method, or a statistics and combination of actual communication conditions.
  • the evaluator can evaluate corresponding reward values for different constellation diagrams. For example, the constellation diagram generated by the agent is input into the evaluator, and the evaluator determines that the constellation diagram is contrary to the known and reliable design rules of the constellation diagram. If it deviates from the characteristics of the Gray code, the evaluator can directly be The constellation diagram outputs a small reward value, which can save time consumption caused by a lot of unreasonable exploration without going through the Monte Carlo simulation method. Another example is that multiple network devices can share the evaluation experience.
  • the evaluator can query the historical evaluation results of the device or other network devices. If the evaluation result of the constellation diagram is the same or similar to the constellation diagram, the previous evaluation result can be directly reused, and the Monte Carlo simulation time and time consumption can also be saved.
  • the two communicating parties use the constellation diagram generated by the agent to communicate, and the evaluator counts the performance indicators (such as throughput, BER, BLER, spectral efficiency, etc.) after the communication parties use the new constellation diagram to communicate, and feeds them back to the intelligence in return.
  • the agent adjusts the previously generated constellation diagram according to the reward until the agent converges.
  • the interaction process between the agent and the evaluator is shown in Figure 3c, the agent outputs the designed constellation diagram as an action, and the link simulator (ie the evaluator) determines the constellation diagram The bit error rate is fed back to the agent as a reward.
  • the agent first determines the modulation level of the constellation diagram to be generated.
  • the state in the elements related to deep reinforcement learning in the agent can be a vector of 1*16 dimensions (or any dimension with a total number of elements greater than or equal to 16), or it can be a vector of 4*4 dimensions (or with a total number of elements greater than or equal to 16)
  • a matrix of any dimension) the value of the vector or the element in the matrix can be any real number, and represents the position coordinates of each constellation point in the constellation diagram.
  • the action in the elements of the deep reinforcement learning is the distribution of the coordinates of the constellation points determined at each time step.
  • each time step is set to determine a constellation point, which involves the distribution of two coordinate values, and the distribution of the coordinate values can be Gaussian. Distribution, Gaussian distribution contains two real numbers, expectation and variance.
  • the real number can be any real number, but the space of any real number is too large, which is not conducive to the convergence of the agent.
  • the constellation map will eventually be normalized, and it is not necessary to explore the space with too large real numbers.
  • the tanh activation function can be added before the output of the deep neural network, so that the real number output of the neural network takes the value of [-1, 1] between.
  • the expectation of the constellation point coordinate distribution is feasible between [-1, 1], but the variance of the distribution still needs to be processed.
  • the variance output of the deep neural network is w, 2 ⁇ (10*w)
  • the value of is used as the variance of the distribution.
  • the variance is greater than 0, and the variance can be a small value or a large value.
  • This setting can ensure that both The diversity of exploration (the variance is relatively large at the beginning), and the final convergence of the exploration (the variance will become smaller and smaller), these four distribution values form two Gaussian distributions, from which two real values can be sampled, and two real values can be obtained by sampling.
  • the value is the coordinate value finally obtained at this time step.
  • the state may be all zeros or any initial value.
  • the agent outputs the coordinates of a constellation point according to the input state.
  • the coordinates of the constellation point cause the state to change, that is, the constellation point in the state vector
  • the value set at the position of the constellation point changes from the initial value to the coordinates of the constellation point output by the action.
  • the final state that is, the complete constellation diagram, and the constellation Graph design parameters are input to the estimator.
  • the estimator is a link simulator, and the link simulator outputs the constellation diagram and the decoding result of the constellation diagram design parameters as a return, and the decoding result can be BLER (the value may be converted, Such as log10(BLER)) or BER, whether the design of the constellation diagram conforms to the characteristics of the Gray code is related to the BER, so the BER can be used as a return.
  • BLER the value may be converted, Such as log10(BLER)
  • BER whether the design of the constellation diagram conforms to the characteristics of the Gray code is related to the BER, so the BER can be used as a return.
  • the coordinates of all constellation points can also be output in one time step, such that one round is one time step.
  • only one coordinate value (the coordinate value of a constellation point on the horizontal axis or the coordinate value on the vertical axis) can be output in one time step, so that in this example, one round needs to go through 16 time steps to design Complete constellation chart. It can be understood that the specific design process can be changed according to different needs of deep reinforcement learning.
  • the goal of the agent is to maximize the sum of the decoding performance, that is, to optimize the decoding performance and gradually converge. After a period of training, the decoding performance almost no longer increases. At this time, you can choose a round with the best decoding performance, record the actions of each time step in this round, and output each time step in order.
  • the coordinate values form a complete constellation diagram, which can be regarded as a constellation diagram designed by deep reinforcement learning for the current scene.
  • the constellation diagram designer includes an agent and an evaluator, that is, the second communication device includes both an agent and an evaluator.
  • the estimator may include a channel simulator.
  • the channel simulator inside the estimator can simulate the channel characteristics and output channel values under the channel characteristics. , provided to the link emulator in the estimator.
  • Channel characteristics may include channel strength, channel distribution, multipath distribution, delay, and the like.
  • the second communication device only needs to obtain the constellation diagram design parameters from the outside, and can try to generate a constellation diagram, and can evaluate the constellation diagram that is attempted to be generated.
  • the constellation diagram designer includes an intelligent body, that is, an intelligent body is included in the second communication device, and the evaluator is located outside the second communication device.
  • the second communication device includes the agent
  • the first communication device includes an evaluator.
  • the second communication apparatus obtains the constellation diagram design parameters from the outside, attempts to generate a constellation diagram, and sends the constellation diagram that is attempted to be generated to the first communication apparatus, and the first communication apparatus evaluates the constellation diagram.
  • the second communication device adjusts the constellation diagram according to the evaluation result/reward until the agent converges.
  • the agent may send a constellation diagram to the multiple evaluators at the same time, and receive evaluation results from the multiple evaluators.
  • the agent and the evaluator are located in different communication devices
  • the agent when the agent is set on the modulation side/sender, the information of the new constellation can be sent to the demodulation side/receiver through the channel.
  • the information of the new constellation can be sent to the modulation side/transmitter through the channel.
  • the demodulation method of the irregular constellation diagram may be different from the demodulation method of the regular constellation diagram. If there is no need to output soft information when the new constellation is modulated, the distance between the received signal and each constellation point can be judged, and the constellation point with the smallest distance can be determined as the constellation point obtained by demodulation. If the soft information needs to be output during the modulation of the new constellation, the distance information between the received signal and each constellation point can be calculated, and then combined with the commonly used decoding algorithm to calculate the soft information. For example, the max-log decoding method can be used to calculate the soft information.
  • FIG. 5 a and FIG. 5 b Different information bit lengths generate different constellation diagrams, and schematic diagrams of constellation diagrams generated according to the deep reinforcement learning shown in the embodiments of the present application are shown in FIG. 5 a and FIG. 5 b .
  • the following 8QAM constellation diagram is obtained through reinforcement learning under the link using 2bit ADC.
  • the coordinate values of each constellation point in the constellation diagram are shown in Table 2. It can be understood that the order of the constellation points in the above constellation diagram is still within the protection scope of the present invention, and the scaling or fine-tuning of the coordinate values of the constellation points within a certain range is still within the protection scope of the present invention.
  • the following 8QAM constellation diagram is obtained through reinforcement learning under the link using 3bit ADC.
  • the coordinate values of each constellation point in the constellation diagram are shown in Table 3. It can be understood that the order of the constellation points in the above constellation diagram is still within the protection scope of the present invention, and the scaling or fine-tuning of the coordinate values of the constellation points within a certain range is still within the protection scope of the present invention.
  • the base station inquires whether the terminal device has the ability to update the constellation map.
  • S602 The terminal device feeds back information about the capability of the terminal device to update the constellation map.
  • fields/signaling messages may also be newly added in this embodiment of the present application.
  • IE update constellation identification bit
  • updateConstellationFlag update constellation identification bit
  • updateConstellation update constellation
  • ConstellationRelatedParameters constellation related parameters
  • the value of the updateConstellation field is an integer in the range of [0, 1024], which is used to indicate the updated constellation diagram, that is, the updateConstellation field may include the coordinates of the constellation points in the updated constellation diagram.
  • the ConstellationRelatedParameters field is a set set, which is a set of parameters related to constellation diagrams, that is, the ConstellationRelatedParameters field may include constellation diagram design parameters.
  • the terminal device may indicate whether the terminal device has the ability to update the constellation map through the newly added updateConstellationFlag field in Table 4, and the value range of the updateConstellationFlag field may be a Boolean value of 0 or 1. If the value of the updateConstellationFlag field is 1, it indicates that the terminal device has the ability to update the constellation diagram, and if the value of the updateConstellationFlag field is 0, it indicates that the terminal device does not have the ability to update the constellation diagram. Generally, in this embodiment of the present application, the terminal device has the capability of updating the constellation map.
  • the base station can send the updated coordinates of the constellation points in the constellation diagram to the terminal device through the newly added updateConstellation field in Table 4, where the value of the updateConstellation field can be any real number, such as shown in Figure 5a or Figure 5b, The value is any real number in the range [-1.5, 1.5], or as shown in Table 4, the value is an integer in the range [0, 1024]. It can be understood that if the communication device that generates the constellation is the terminal device, the terminal device can also send the updated coordinates of the constellation points in the constellation to the base station through the updateConstellation field.
  • the updateConstellation field may be sent through RRC signaling.
  • the terminal device can send the parameter set related to the constellation diagram, that is, the constellation diagram design parameters, through the newly added ConstellationRelated Parameters field in Table 4, and the ConstellationRelated Parameters is a set collection.
  • the core network device authenticates the capability information of the terminal device for updating the constellation map.
  • S604 The terminal device requests to update the constellation map.
  • S605 The base station starts the process of updating the constellation diagram, and inquires the terminal device about the parameters required for updating the constellation diagram.
  • S606 The terminal device sends parameters required for updating the constellation diagram (ie, constellation diagram design parameters) according to the local statistical information.
  • the terminal device may send the constellation diagram design parameters through the newly added ConstellationRelated Parameters field.
  • the base station generates a new constellation diagram based on the constellation diagram designer according to the parameters.
  • the base station sends the information of the new constellation to the terminal device.
  • the terminal device After receiving the new constellation, the terminal device requests the base station to switch the new constellation.
  • S609 Perform RRC connection reconfiguration between the base station and the terminal device, and after the RRC connection reconfiguration is completed, switch between the base station and the terminal device to a new constellation.
  • Optional S610a the base station determines that the new constellation cannot work, or the performance drops significantly after working, and the base station initiates a fallback standard constellation (ie, the original constellation) indication.
  • the terminal device confirms a fallback to the standard constellation.
  • Optional S610b The terminal device determines that the new constellation diagram cannot work, or the performance drops significantly after operation, and the terminal device requests to fall back to the standard constellation diagram.
  • the process of rolling back the standard constellation map may be initiated by the base station (eg S610a), or may be initiated by the terminal device (eg S610b), and S610a and S610b may be used alternatively.
  • S611 Perform RRC connection reconfiguration between the base station and the terminal device, and after the RRC connection reconfiguration is completed, switch between the base station and the terminal device to a standard constellation.
  • the communication device can generate a constellation diagram based on the relevant parameters of the current scene through deep reinforcement learning, which can ensure that the generated constellation diagram best matches the current scene, and also design the negotiation cooperation between the two communication parties in the constellation diagram design process. process to ensure communication performance.
  • the embodiment of the present application further provides a communication device.
  • the communication device 700 includes a processing unit 701 and a transceiving unit 702, and the apparatus 700 can be used to implement the method described in the foregoing method embodiment applied to the first communication apparatus or the second communication apparatus.
  • the apparatus 700 is applied to the first communication apparatus, and the first communication apparatus may be a network device or a terminal device, for example, the first communication apparatus is a terminal device.
  • the processing unit 701 is configured to determine a constellation diagram design parameter
  • the transceiver unit 702 is configured to send the constellation diagram design parameters, where the constellation diagram design parameters include communication scenario design parameters and communication device design parameters; and receive information of a second constellation diagram, where the second constellation diagram corresponds to the The constellation diagram design parameters are described; the second constellation diagram is used for communication.
  • the transceiver unit 702 is further configured to use the first constellation diagram for communication before sending the constellation diagram design parameters.
  • the processing unit 701 is further configured to update the first constellation map to the second constellation map before the transceiver unit 702 uses the second constellation map for communication, the The first constellation diagram is different from the second constellation diagram.
  • the communication scenario design parameters include at least one of the following information: channel characteristics, environment visualization information; wherein, the channel characteristics include at least one of the following information: channel environment type indication, channel model indication, channel model ;
  • the environment visualization information includes at least one of the following information: images, depth pictures, point cloud data or three-dimensional pictures collected in the environment;
  • the communication device design parameters include at least one of the following information: user behavior portrait, constellation diagram designer reporting parameters; wherein, the user behavior portrait includes at least one of the following information: the location distribution of the first communication device, the Service type distribution of the first communication device, mobility distribution of the first communication device, code rate distribution of the first communication device, and hardware parameter distribution of the radio frequency link of the first communication device; the constellation diagram designer reports
  • the parameters include at least one of the following information: the performance fed back by the first communication device, the performance calculated by the constellation diagram designer, or a formula for evaluating the constellation diagram performance.
  • the processing unit 701 is further configured to transform the second constellation map into a third constellation map after the transceiver unit 702 receives the information of the second constellation map, and the third constellation map
  • the constellation diagram is the constellation diagram closest to the second constellation diagram in the preset constellation diagram.
  • the transceiver unit 702 is further configured to, after using the second constellation for communication, receive indication information, where the indication information is used to indicate that a fallback mechanism is used, and the fallback mechanism is used for Instruct to transform the second constellation map into the first constellation map; or send a first request message, where the first request message is used to request a fallback mechanism, and the fallback mechanism is used to instruct the The two constellation diagrams are transformed into the first constellation diagram.
  • the processing unit 701 is further configured to save the corresponding relationship between the constellation diagram design parameters and the second constellation diagram.
  • the processing unit 701 is further configured to search the second constellation diagram corresponding to the constellation diagram design parameter in the corresponding relationship according to the constellation diagram design parameter.
  • the apparatus 700 is applied to the second communication apparatus, and the second communication apparatus may be a network device or a terminal device, for example, the second communication apparatus is a network device (eg, a base station).
  • the second communication apparatus is a network device (eg, a base station).
  • the transceiver unit 702 is configured to receive constellation design parameters, where the constellation design parameters include communication scenario design parameters and communication device design parameters;
  • the processing unit 701 is configured to determine the constellation diagram design parameters, and determine a second constellation diagram, where the second constellation diagram corresponds to the constellation diagram design parameters;
  • the transceiver unit 702 is further configured to send the information of the second constellation; communicate by using the second constellation.
  • the transceiver unit 702 is further configured to use the first constellation diagram for communication before receiving the constellation diagram design parameters.
  • the processing unit 701 is further configured to, before the transceiver unit 702 sends the information of the second constellation diagram, update the first constellation diagram to the specified constellation diagram according to the constellation diagram design parameters the second constellation diagram, the first constellation diagram is different from the second constellation diagram.
  • the communication scenario design parameters include at least one of the following information: channel characteristics, environment visualization information; wherein, the channel characteristics include at least one of the following information: channel environment type indication, channel model indication, channel model ;
  • the environment visualization information includes at least one of the following information: images, depth pictures, point cloud data or three-dimensional pictures collected in the environment;
  • the communication device design parameters include at least one of the following information: user behavior portrait, constellation diagram designer reporting parameters; wherein, the user behavior portrait includes at least one of the following information: the location distribution of the first communication device, the Service type distribution of the first communication device, mobility distribution of the first communication device, code rate distribution of the first communication device, and hardware parameter distribution of the radio frequency link of the first communication device; the constellation diagram designer reports
  • the parameters include at least one of the following information: the performance fed back by the first communication device, the performance calculated by the constellation diagram designer, or a formula for evaluating the constellation diagram performance.
  • the processing unit 701 is specifically configured to input the constellation diagram design parameters into a constellation diagram designer; based on the constellation diagram designer, update the first constellation diagram to the first constellation diagram Two constellations.
  • the processing unit 701 is further configured to transform the second constellation into a third constellation, where the third constellation is a preset constellation that is closest to the second constellation Close up constellation diagram.
  • the transceiver unit 702 is further configured to send indication information after using the second constellation for communication, where the indication information is used to indicate that a fallback mechanism is used, and the fallback mechanism is used for Instruct to transform the second constellation map into the first constellation map; or receive a first request message, where the first request message is used to request a fallback mechanism, and the fallback mechanism is used to instruct the first constellation to be converted The two constellation diagrams are transformed into the first constellation diagram.
  • the processing unit 701 is further configured to save the corresponding relationship between the constellation diagram design parameters and the second constellation diagram.
  • the processing unit 701 is further configured to search the second constellation diagram corresponding to the constellation diagram design parameter in the corresponding relationship according to the constellation diagram design parameter.
  • each functional unit in each embodiment of the present application It can be integrated in one processing unit, or it can exist physically alone, or two or more units can be integrated in one unit.
  • the above-mentioned integrated units may be implemented in the form of hardware, or may be implemented in the form of software functional units.
  • the integrated unit if implemented in the form of a software functional unit and sold or used as an independent product, may be stored in a computer-readable storage medium.
  • the technical solutions of the present application can be embodied in the form of software products in essence, or the parts that contribute to the prior art, or all or part of the technical solutions, and the computer software products are stored in a storage medium , including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor (processor) to execute all or part of the steps of the methods described in the various embodiments of the present application.
  • the aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk and other media that can store program codes .
  • an embodiment of the present application further provides a schematic structural diagram of a communication apparatus 800 .
  • the apparatus 800 may be configured to implement the method described in the foregoing method embodiment applied to the first communication apparatus or the second communication apparatus, and reference may be made to the description in the foregoing method embodiment.
  • the apparatus 800 may be in or be a first communication apparatus or a second communication apparatus.
  • the apparatus 800 includes one or more processors 801 .
  • the processor 801 may be a general-purpose processor or a special-purpose processor or the like. For example, it may be a baseband processor, or a central processing unit.
  • the baseband processor may be used to process communication protocols and communication data
  • the central processing unit may be used to control communication devices (eg, base stations, terminals, or chips, etc.), execute software programs, and process data of software programs.
  • the communication device may include a transceiving unit for implementing signal input (reception) and output (transmission).
  • the transceiver unit may be a transceiver, a radio frequency chip, or the like.
  • the device 800 includes one or more processors 801, and the one or more processors 801 can implement the method of the first communication device or the second communication device in the above-described embodiments.
  • processor 801 may also implement other functions in addition to implementing the methods in the above-described embodiments.
  • the processor 801 may execute an instruction, so that the apparatus 800 executes the method described in the foregoing method embodiment.
  • the instructions may be stored in whole or in part within the processor, such as instruction 803, or may be stored in whole or in part in a memory 802 coupled to the processor, such as instruction 804, or may be jointly caused by instructions 803 and 804.
  • the apparatus 800 executes the methods described in the above method embodiments.
  • the communication apparatus 800 may also include a circuit, and the circuit may implement the function of the first communication apparatus or the second communication apparatus in the foregoing method embodiments.
  • the apparatus 800 may include one or more memories 802 having stored thereon instructions 804 that may be executed on the processor to cause the apparatus 800 to perform the above-described method methods described in the examples.
  • data may also be stored in the memory.
  • Instructions and/or data may also be stored in the optional processor.
  • the one or more memories 802 may store the correspondences described in the foregoing embodiments, or related parameters or tables involved in the foregoing embodiments, and the like.
  • the processor and the memory can be provided separately or integrated together.
  • the apparatus 800 may further include a transceiver 805 and an antenna 806 .
  • the processor 801 may be referred to as a processing unit, and controls the device (terminal or base station).
  • the transceiver 805 may be referred to as a transceiver, a transceiver circuit, or a transceiver unit, etc., and is used to implement the transceiver function of the device through the antenna 806 .
  • the processor in this embodiment of the present application may be an integrated circuit chip, which has a signal processing capability.
  • each step of the above method embodiments may be completed by a hardware integrated logic circuit in a processor or an instruction in the form of software.
  • the above-mentioned processor may be a general-purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), an off-the-shelf programmable gate array (field programmable gate array, FPGA), or other possible solutions.
  • DSP digital signal processor
  • ASIC application specific integrated circuit
  • FPGA field programmable gate array
  • Programming logic devices discrete gate or transistor logic devices, discrete hardware components.
  • a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
  • the steps of the method disclosed in conjunction with the embodiments of the present application may be directly embodied as executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor.
  • the software modules may be located in random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, registers and other storage media mature in the art.
  • the storage medium is located in the memory, and the processor reads the information in the memory, and completes the steps of the above method in combination with its hardware.
  • the memory in this embodiment of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memory.
  • the non-volatile memory can be read only memory (ROM), programmable read only memory (programmable ROM, PROM), erasable programmable read only memory (erasable PROM, EPROM), electrically erasable programmable read only memory Read memory (electrically EPROM, EEPROM) or flash memory.
  • Volatile memory may be random access memory (RAM), which acts as an external cache.
  • RAM random access memory
  • DRAM dynamic random access memory
  • SDRAM synchronous DRAM
  • SDRAM double data rate synchronous dynamic random access memory
  • ESDRAM enhanced synchronous dynamic random access memory
  • SLDRAM synchronous link dynamic random access memory
  • direct rambus RAM direct rambus RAM
  • Embodiments of the present application further provide a computer-readable medium on which a computer program is stored, and when the computer program is executed by a computer, implements any of the foregoing method embodiments applied to the first communication device or the second communication device. communication method.
  • the embodiments of the present application further provide a computer program product, which implements the communication method described in any of the above method embodiments applied to the first communication device or the second communication device when the computer program product is executed by a computer.
  • the above-mentioned embodiments it may be implemented in whole or in part by software, hardware, firmware or any combination thereof.
  • software it can be implemented in whole or in part in the form of a computer program product.
  • the computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present application are generated.
  • the computer may be a general purpose computer, special purpose computer, computer network, or other programmable device.
  • the computer instructions may be stored in or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be downloaded from a website site, computer, server, or data center Transmission to another website site, computer, server, or data center by wire (eg, coaxial cable, optical fiber, digital subscriber line, DSL) or wireless (eg, infrared, wireless, microwave, etc.).
  • the computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that includes an integration of one or more available media.
  • the available media may be magnetic media (eg, floppy disks, hard disks, magnetic tapes), optical media (eg, high-density digital video discs (DVDs)), or semiconductor media (eg, solid state disks, SSD)) etc.
  • An embodiment of the present application further provides a processing apparatus, including a processor and an interface; the processor is configured to execute the communication method described in any of the above method embodiments applied to the first communication apparatus or the second communication apparatus.
  • the above-mentioned processing device may be a chip, and the processor may be implemented by hardware or software.
  • the processor may be a logic circuit, an integrated circuit, etc.; when implemented by software
  • the processor may be a general-purpose processor, which is implemented by reading software codes stored in a memory, and the memory may be integrated in the processor or located outside the processor and exist independently.
  • An embodiment of the present application further provides a chip, including a logic circuit and an input-output interface, where the input-output interface is used for receiving/outputting code instructions or information, and the logic circuit is used for executing the code instructions or according to the information , to execute the communication method described in any of the above method embodiments applied to the first communication device or the second communication device.
  • the chip can implement the functions shown in the processing unit and/or the transceiver unit in the above embodiments.
  • the input-output interface is used for outputting constellation diagram design parameters, and the input-output interface is also used for inputting the information of the second constellation diagram.
  • the input and output interface may also be used to receive a code instruction, where the code instruction is used to instruct to update the first constellation diagram to the second constellation diagram, or instruct to convert the second constellation diagram to the third constellation diagram.
  • the input-output interface is used for inputting constellation diagram design parameters, and the input-output interface is further used for outputting the information of the second constellation diagram.
  • the input and output interface may also be used to receive a code instruction, where the code instruction is used to instruct to update the first constellation diagram to the second constellation diagram, or instruct to convert the second constellation diagram to the third constellation diagram.
  • An embodiment of the present application further provides a communication system, including a first communication device and a second communication device, where the first communication device is configured to execute the communication method described in any of the foregoing method embodiments applied to the first communication device , the second communication apparatus is configured to execute the communication method described in any one of the foregoing method embodiments applied to the second communication apparatus.
  • the disclosed system, apparatus and method may be implemented in other manners.
  • the apparatus embodiments described above are only illustrative.
  • the division of units is only a logical function division.
  • there may be other division methods for example, multiple units or components may be combined or integrated. to another system, or some features can be ignored, or not implemented.
  • the shown or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may also be electrical, mechanical or other forms of connection.
  • Units described as separate components may or may not be physically separated, and components shown as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solutions of the embodiments of the present application.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit.
  • the above-mentioned integrated units may be implemented in the form of hardware, or may be implemented in the form of software functional units.
  • Computer-readable media includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another.
  • a storage medium can be any available medium that a computer can access.
  • computer readable media may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage media or other magnetic storage devices, or be capable of carrying or storing instructions or data structures in the form of desired program code and any other medium that can be accessed by a computer. also.
  • any connection can be appropriately made into a computer-readable medium.
  • the software is transmitted from a website, server, or other remote source using coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwave
  • the coaxial cable , fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, wireless, and microwave are included in the fusing of the pertinent medium.
  • Disk and disc includes compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), floppy disk and blu-ray disc, where disks usually reproduce data magnetically, while discs Lasers are used to optically copy data. Combinations of the above should also be included within the scope of computer-readable media.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Physics & Mathematics (AREA)
  • Environmental & Geological Engineering (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • Electromagnetism (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

本申请实施例涉及一种通信方法及装置，用以设计出与通信场景匹配的星座图，能够适应不同的通信场景和通信性能要求，提高网络性能，该通信方法包括：第一通信装置发送星座图设计参数；所述星座图设计参数包括通信场景设计参数和通信装置设计参数；所述第一通信装置接收第二星座图的信息，所述第二星座图对应于所述星座图设计参数；所述第一通信装置采用所述第二星座图进行通信。

Description

一种通信方法及装置
相关申请的交叉引用
本申请要求在2020年08月25日提交中国专利局、申请号为202010864940.0、申请名称为“一种通信方法及装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及通信技术领域，尤其涉及一种通信方法及装置。
背景技术
数字通信系统是利用数字信号传输信息的系统，在数字通信系统中，待发送的信息在载波上完成传输。待发送的信息与载波上传输的信息通常采用数字调制的方式完成映射。数字调制可以在幅度和相位上区分信号，每种幅度和相位的组合可以表示为二维空间中的一点。所有幅度和相位组合的点在二维平面上可以看作一张星座图，即星座图中包括多个星座点，每个星座点由幅度和相位组合得到。一般的，将待发送的信息进行编码之后被映射到星座图(或星座图中的对应星座点)上，实现数字调制。
现有通信系统中采用固定的星座图设计，星座图中星座点的位置是固定的，通信双方根据固定的星座图完成通信的调制和解调。
但是随着通信技术及通信场景的发展，以及对通信系统性能要求的提高，固定的星座图无法适应变化的通信场景和通信性能要求，导致实际通信过程中的通信性能较差。
发明内容
本申请实施例提供一种通信方法及装置，用于设计出与通信场景匹配的星座图，能够适应不同的通信场景和通信性能要求，提高网络性能。
第一方面，本申请实施例提供一种通信方法，包括：第一通信装置发送星座图设计参数；所述星座图设计参数包括通信场景设计参数和通信装置设计参数；所述第一通信装置接收第二星座图的信息，所述第二星座图对应于所述星座图设计参数；所述第一通信装置采用所述第二星座图进行通信。
通信双方在通信过程中采用星座图进行调制和解调，随着通信场景的变化及通信性能要求的提高，采用固定的星座图已经无法满足通信需求，因此第一通信装置向第二通信装置发送星座图设计参数，所述第二通信装置基于星座图设计参数生成第二星座图，将所述第二星座图发送给所述第一通信装置，所述第一通信装置和所述第二通信装置可以采用新的所述第二星座图进行通信。可见在该方法中，通信双方在通信过程中采用的星座图可以根据通信场景的不同自适应改变，通过设计与当前通信场景更匹配的星座图，可以提高网络性能，保证网络性能的最大化。
在一种可能的实现中，所述第一通信装置发送星座图设计参数之前，所述第一通信装置还可以采用第一星座图进行通信。
可选的，所述第一通信装置可以采用所述第一星座图发送所述星座图设计参数，所述第二通信装置可以采用所述第一星座图接收所述星座图设计参数。
在一种可能的实现中，所述第一通信装置采用所述第二星座图进行通信之前，所述第一通信装置还可以将所述第一星座图更新为所述第二星座图，所述第一星座图与所述第二星座图不同。
所述第二星座图可以由所述第二通信装置根据所述星座图设计参数生成。
可选的，所述第一星座图和所述第二星座图中星座点的数量相同，并且对应的至少一个星座点的坐标不同，所述对应的至少一个星座点可以指位于相同象限内的至少一个星座点。
在一种可能的实现中，所述通信场景设计参数包括以下至少一种信息：信道特征、环境可视化信息；其中，所述信道特征包括以下至少一种信息：信道环境类型指示、信道模型指示、信道模型；所述环境可视化信息包括以下至少一种信息：环境中采集的图像、深度图片、点云数据、三维图片。
所述通信装置设计参数包括以下至少一种信息：用户行为画像、星座图设计器回报参数；其中，所述用户行为画像包括以下至少一种信息：通信装置的位置分布、通信装置服务类型分布、通信装置移动性分布、通信装置的码率分布、通信装置的射频链路硬件参数分布；所述星座图设计器回报参数包括以下至少一种信息：通信装置反馈的性能、星座图设计器计算得到的性能、用于评估星座图性能的公式。
通信装置包括第一通信装置和/或第二通信装置。例如所述通信装置的位置分布可以包括所述第一通信装置的位置分布和/或所述第二通信装置的位置分布，通信装置服务类型分布包括所述第一通信装置的服务类型分布和/或所述第二通信装置的位置分布，通信装置移动性分布包括所述第一通信装置的移动性分布和/或所述第二通信装置的移动性分布，所述通信装置的码率分布包括所述第一通信装置的码率分布和/或所述第二通信装置的码率分布，所述通信装置的射频链路硬件参数分布包括所述第一通信装置的射频链路硬件参数分布和/或所述第二通信装置的射频链路硬件参数分布，所述通信装置反馈的性能包括所述第一通信装置反馈的性能和/或所述第二通信装置反馈的性能。
在一种可能的实现中，所述第一通信装置接收第二星座图的信息之后，所述第一通信装置还可以将所述第二星座图变换为第三星座图，所述第三星座图为预设的星座图中与所述第二星座图最接近的星座图。
其中所述第三星座图的解调复杂度低于所述第二星座图的解调复杂度。
若第二星座图为深度强化学习得到，则所述第二星座图可能是非规则的，所述第二星座图的解调复杂度可能更高，因此可以预设有多个规则星座图来降低深度学习到的星座图的解调复杂度。所述第三星座图可以为规则星座图，即所述第三星座图中的星座点位置的分布具有规律性，如所述第三星座图中的星座图成对称分布。
在一种可能的实现中，所述第一通信装置采用所述第二星座图进行通信之后，还包括：
所述第一通信装置接收指示信息，所述指示信息用于指示采用回退机制，所述回退机制用于指示将所述第二星座图变换为所述第一星座图；或者
所述第一通信装置发送第一请求消息，所述第一请求消息用于请求采用回退机制，所述回退机制用于指示将所述第二星座图变换为所述第一星座图。
由于更新后的星座图可能无法工作，或者工作后的性能明显下降超过某个阈值，则表 示更新后的星座图无法适应当前场景，使用更新后的星座图无法很好进行通信，因此可以通过回退机制将第二星座图变换为第一星座图，所述回退机制可以由第一通信装置发起，或者可以由第二通信装置发起。
在一种可能的实现中，所述第一通信装置还可以保存所述星座图设计参数与所述第二星座图的对应关系。
在一种可能的实现中，所述第一通信装置还可以根据所述星座图设计参数，在所述对应关系中查找所述星座图设计参数对应的所述第二星座图。
星座图设计器基于相同或相近的通信场景，可以生成相同的星座图，因此第一通信装置中可以保存星座图设计参数与星座图的对应关系，方便后续快速获取相同通信场景所对应的星座图。
第二方面，本申请实施例提供一种通信方法，包括：第二通信装置接收星座图设计参数；所述星座图设计参数包括通信场景设计参数和通信装置设计参数；所述第二通信装置发送第二星座图的信息，所述第二星座图对应于所述星座图设计参数；所述第二通信装置采用所述第二星座图进行通信。
在一个可能的实现中，所述第二通信装置接收星座图设计参数之前，所述第二通信装置还可以采用第一星座图进行通信。
在一个可能的实现中，所述通信场景设计参数包括以下至少一种信息：信道特征、环境可视化信息；其中，所述信道特征包括以下至少一种信息：信道环境类型指示、信道模型指示、信道模型；所述环境可视化信息包括以下至少一种信息：环境中采集的图像、深度图片、点云数据或三维图片。
所述通信装置设计参数包括以下至少一种信息：用户行为画像、星座图设计器回报参数；其中，所述用户行为画像包括以下至少一种信息：通信装置的位置分布、通信装置服务类型分布、通信装置移动性分布、通信装置的码率分布、通信装置的射频链路硬件参数分布；所述星座图设计器回报参数包括以下至少一种信息：通信装置反馈的性能、星座图设计器计算得到的性能、或用于评估星座图性能的公式。
在一个可能的实现中，所述第二通信装置发送第二星座图的信息之前，所述第二通信装置还可以根据所述星座图设计参数，将所述第一星座图更新为所述第二星座图，所述第一星座图与所述第二星座图不同。
在一个可能的实现中，所述第二通信装置根据所述星座图设计参数，将所述第一星座图更新为所述第二星座图，包括：所述第二通信装置可以将所述星座图设计参数输入到星座图设计器中；所述第二通信装置基于所述星座图设计器，将所述第一星座图更新为所述第二星座图。
例如，所述星座图设计器可以根据所述星座图设计参数，生成第二星座图。所述星座图设计生成所述第二星座图的过程可以看作深度强化学习的过程。
在一个可能的实现中，所述第二通信装置基于所述星座图设计器，将所述第一星座图更新为所述第二星座图，包括：智能体确定待生成的第二星座图的调制等级，并确定所述调制等级对应的星座点数量N，N为正整数；所述智能体确定所述N个星座点的星座点坐标；评估器根据N个星座点坐标对应的场景状态及所述星座图设计参数，确定所述N个星座点的译码结果；所述智能体根据所述N个星座点的译码结果，对所述N个星座点坐标进行调整，直至所述星座图设计器收敛。
其中所述待生成的第二星座图的调制等级可以与所述第一星座图的调制等级相同，或者待生成的第二星座图的调制等级可以是所述第一通信装置和所述第二通信装置在通信时提前约定/协商好的。所述星座图设计器的收敛条件可以为深度强化学习的回合数，或当回报不再增大/改变时，确定星座图设计器收敛。回报用于评估生成的星座图的通信性能，可以包括以下指标中的一种或多种：吞吐、比特出错概率(bit error ratio，BER)、块错误率(block error rate，BLER)、频谱效率等参数。
在该实现中，深度强化学习中的状态包括所述智能体生成的星座图，深度强化学习中的行动包括智能体对星座点坐标进行的调整，深度强化学习中的回报包括评估器确定的译码结果。
所述星座图设计器位于通信链路中，即所述第一通信装置和所述第二通信装置的通信链路中包括所述星座图设计器。可选的，所述星座图设计器中包括所述智能体和所述评估器；或者可选的，所述星座图设计器中包括所述智能体，而所述评估器位于所述星座图设计器外部。
可选的，所述译码结果也可以为误码率，即将误码率作为回报反馈给所述智能体。
在一个可能的实现中，所述智能体根据所述N个星座点的译码结果，对所述N个星座点坐标进行调整，包括：所述智能体可以根据所述N个星座点的译码结果，对所述N个星座点中的部分星座点坐标进行调制。
在该实现中，智能体可以只设计星座图的一部分，例如星座图中共有8个星座点，可以强化学习只探索并设计其中的某两个星座点，其余星座点的坐标保持不变。这样星座度设计的时间步减少很多，相当于局部修正微调星座图，可以减少深度强化学习探索带来的资源消耗，另外可以保证探索得到的星座图与当前标准中的星座图相比，性能不会下降太多，可以保证系统的可靠传输。
在一个可能的实现中，所述星座图设计器确定所述N个星座点的星座点坐标包括：所述星座图设计器可以在设定坐标范围内确定所述N个星座点的星座点坐标。
在该实现中，考虑到设置星座点的探索界限，星座点的坐标值是从高斯分布中采样得到的，星座点的坐标值的取值范围理论上是无限大的，通过设置探索的星座点的坐标值范围，当探索输出的坐标值超过该坐标值范围时，可以将星座点的坐标设置到这个坐标值范围上，保证探索的星座图性能不会太差。
在一个可能的实现中，所述评估器还可以确定每次调整后的N个星座点坐标的译码结果；所述智能体选取译码结果最优的N个星座点坐标，生成第二星座图。
智能体的目标是让译码性能达到最大，即最优化译码性能并逐渐收敛。一段时间的训练后，译码性能几乎不再增加，这时可以选择性能最好的一个回合，记录每个时间步的行动/动作，并按顺序组成一个完整的星座图，从而得到针对当前场景设计的第二星座图。
在一个可能的实现中，如果解调时不需要输出软信息，所述网络设备还可以根据接收到的业务数据的信号与所述第二星座图中各星座点之间的距离，确定所述业务数据的信号解调得到的星座点。例如，可以将距离最小的星座点确定为对所述业务数据的信号进行解调得到的星座点。
如果解调时需要输出软信息，所述网络设备还可以根据接收到的业务数据的信号与所述第二星座图中各星座点之间的距离，对所述业务数据的信号进行译码，确定所述业务数据的评估结果。例如可以采用译码方法计算所述业务数据的评估结果，即软信息。
在一个可能的实现中，智能体还会输出通信链路中的其它参数，例如通信链路中的滤波器参数、导频信号配置参数、软信息处理配置参数、预编码配置参数等，通过联合调节并优化这些参数和星座图，获得最佳的译码性能。
在一个可能的实现中，所述第二通信装置采用所述第二星座图进行通信之前，所述第二通信装置还可以将所述第二星座图变换为第三星座图，所述第三星座图为预设的星座图中与所述第二星座图最接近的星座图。
其中所述第三星座图的解调复杂度低于所述第二星座图的解调复杂度，将所述第三星座图变换为所述第三星座图更易于通信过程中的调制和解调，有利于提高通信性能。
在一个可能的实现中，所述第二通信装置采用所述第二星座图进行通信之后，还包括：
所述第二通信装置发送指示信息，所述指示信息用于指示采用回退机制，所述回退机制用于指示将所述第二星座图变换为所述第一星座图；或者
所述第二通信装置接收第一请求消息，所述第一请求消息用于请求采用回退机制，所述回退机制用于指示将所述第二星座图变换为所述第一星座图。
由于更新后的星座图可能无法工作，或者工作后的性能明显下降超过某个阈值，则表示更新后的星座图无法适应当前场景，采用回退机制将所述第二星座图回退至所述第一星座图，避免通信装置之间的通信受到影响，可以保证通信装置之间的正常通信。
在一个可能的实现中，所述第二通信装置还可以保存所述星座图设计参数与所述第二星座图的对应关系。
在一个可能的实现中，所述第二通信装置还可以根据所述星座图设计参数，在所述对应关系中查找所述星座图设计参数对应的所述第二星座图。
星座图设计器基于相同或相近的通信场景，可以生成相同的星座图，因此第二通信装置中可以保存星座图设计参数与星座图的对应关系，方便后续快速获取相同通信场景所对应的星座图，提高网络性能。
第三方面，本申请实施例还提供了一种通信装置，所述通信装置具有实现上述方法实施例中的第一通信装置或第二通信装置的功能。这些功能可以通过硬件实现，也可以通过硬件执行相应的软件实现。所述硬件或软件包括一个或多个与上述功能相对应的功能模块。
第四方面，本申请实施例还提供了一种通信装置，该通信装置可以为上述方法实施例中的第一通信装置或第二通信装置，或者为设置在第一通信装置或第二通信装置中的芯片，该通信装置包括收发器以及处理器，可选的，还包括存储器，其中，该存储器用于存储计算机程序或指令，处理器分别与存储器、收发器耦合，当处理器执行所述计算机程序或指令时，使通信装置执行上述方法实施例中由第一通信装置或第二通信装置所执行的方法。
第五方面，本申请实施例还提供了一种计算机程序产品，所述计算机程序产品包括：计算机程序代码，当所述计算机程序代码在计算机上运行时，使得计算机执行上述任一方面所述的方法。
第六方面，本申请实施例还提供了一种芯片系统，该芯片系统包括处理器和存储器，所述处理器、所述存储器之间电耦合；所述存储器，用于存储计算机程序指令；所述处理器，用于执行所述存储器中的部分或者全部计算机程序指令，当所述部分或者全部计算机程序指令被执行时，用于实现上述任一方面所述的方法。
在一种可能的设计中，所述芯片系统还包括收发器，所述收发器，用于发送所述处理器处理后的信号，或者接收信号输入给所述处理器。该芯片系统，可以由芯片构成，也可 以包括芯片和其他分立器件。
第七方面，本申请实施例还提供了一种计算机可读存储介质，该计算机可读存储介质存储有计算机程序，当该计算机程序被运行时，实现上述任一方面所述的方法。
第八方面，本申请实施例还提供了一种通信系统，该系统可以包括执行上述第一方面和第一方面的任一可能的实现中所述的方法的第一通信装置、以及执行上述第二方面和第二方面的任一可能的实现中所述的方法的第二通信装置。
上述第二方面至第八方面中任一方面及其任一方面中任意一种可能的实现可以达到的技术效果，请参照上述第一方面及其第一方面中相应实现可以带来的技术效果描述，这里不再重复赘述。
附图说明
图1为本申请实施例中适用的一种网络系统的架构图；
图2、图3b、图6为本申请实施例中适用的一种通信流程示意图；
图3a、图3c、图4a、图4b为本申请实施例中适用的一种星座图设计示意图；
图5a、图5b为本申请实施例中适用的一种星座图示意图；
图7、图8为本申请实施例中适用的一种通信装置结构图。
具体实施方式
下面将结合附图对本发明作进一步地详细描述。
本申请将围绕可包括多个设备、组件、模块等的系统来呈现各个方面、实施例或特征。应当理解和明白的是，各个系统可以包括另外的设备、组件、模块等，并且/或者可以并不包括结合附图讨论的所有设备、组件、模块等。此外，还可以使用这些方案的组合。
另外，在本申请实施例中，“示例的”一词用于表示作例子、例证或说明。本申请中被描述为“示例”的任何实施例或设计方案不应被解释为比其他实施例或设计方案更优选或更具优势。确切而言，使用示例的一词旨在以具体方式呈现概念。
本申请实施例描述的网络架构以及业务场景是为了更加清楚的说明本申请实施例的技术方案，并不构成对于本申请实施例提供的技术方案的限定，本领域普通技术人员可知，随着网络架构的演变和新业务场景的出现，本申请实施例提供的技术方案对于类似的技术问题，同样适用。
以下对本申请实施例的部分用语进行解释说明，以便于本领域技术人员理解。
1)终端设备，包括向用户提供语音和/或数据连通性的设备，具体的，包括向用户提供语音的设备，或包括向用户提供数据连通性的设备，或包括向用户提供语音和数据连通性的设备。例如可以包括具有无线连接功能的手持式设备、或连接到无线调制解调器的处理设备。该终端设备可以经无线接入网(radio access network，RAN)与核心网进行通信，与RAN交换语音或数据，或与RAN交互语音和数据。该终端设备可以包括用户设备(user equipment，UE)、无线终端设备、移动终端设备、设备到设备通信(device-to-device，D2D)终端设备、车到一切(vehicle to everything，V2X)终端设备、机器到机器/机器类通信(machine-to-machine/machine-type communications，M2M/MTC)终端设备、物联网(internet of things，IoT)终端设备、轻型终端设备(light UE)、订户单元(subscriber unit)、订户站 (subscriber station)，移动站(mobile station)、远程站(remote station)、接入点(access point，AP)、远程终端(remote terminal)、接入终端(access terminal)、用户终端(user terminal)、用户代理(user agent)、或用户装备(user device)等。例如，可以包括移动电话(或称为“蜂窝”电话)，具有移动终端设备的计算机，便携式、袖珍式、手持式、计算机内置的移动装置等。例如，个人通信业务(personal communication service，PCS)电话、无绳电话、会话发起协议(session initiation protocol，SIP)话机、无线本地环路(wireless local loop，WLL)站、个人数字助理(personal digital assistant，PDA)、等设备。还包括受限设备，例如功耗较低的设备，或存储能力有限的设备，或计算能力有限的设备等。例如包括条码、射频识别(radio frequency identification，RFID)、传感器、全球定位系统(global positioning system，GPS)、激光扫描器等信息传感设备。
作为示例而非限定，在本申请实施例中，该终端设备还可以是可穿戴设备。可穿戴设备也可以称为穿戴式智能设备或智能穿戴式设备等，是应用穿戴式技术对日常穿戴进行智能化设计、开发出可以穿戴的设备的总称，如眼镜、手套、手表、服饰及鞋等。可穿戴设备即直接穿在身上，或是整合到用户的衣服或配件的一种便携式设备。可穿戴设备不仅仅是一种硬件设备，更是通过软件支持以及数据交互、云端交互来实现强大的功能。广义穿戴式智能设备包括功能全、尺寸大、可不依赖智能手机实现完整或者部分的功能，例如：智能手表或智能眼镜等，以及只专注于某一类应用功能，需要和其它设备如智能手机配合使用，如各类进行体征监测的智能手环、智能头盔、智能首饰等。
而如上介绍的各种终端设备，如果位于车辆上(例如放置在车辆内或安装在车辆内)，都可以认为是车载终端设备，车载终端设备例如也称为车载单元(on-board unit，OBU)。
本申请实施例中，终端设备还可以包括中继(relay)。或者理解为，能够与基站进行数据通信的都可以看作终端设备。
本申请实施例中，用于实现终端设备的功能的装置可以是终端设备，也可以是能够支持终端设备实现该功能的装置，例如芯片系统，该装置可以被安装在终端设备中。本申请实施例中，芯片系统可以由芯片构成，也可以包括芯片和其他分立器件。本申请实施例提供的技术方案中，以用于实现终端的功能的装置是终端设备为例，描述本申请实施例提供的技术方案。
2)网络设备，例如包括接入网(access network，AN)设备，例如基站(例如，接入点)，可以是指接入网中在空口通过一个或多个小区与无线终端设备通信的设备，或者例如，一种车到一切(vehicle-to-everything，V2X)技术中的网络设备为路侧单元(road side unit，RSU)。基站可用于将收到的空中帧与IP分组进行相互转换，作为终端设备与接入网的其余部分之间的路由器，其中接入网的其余部分可包括IP网络。RSU可以是支持V2X应用的固定基础设施实体，可以与支持V2X应用的其他实体交换消息。网络设备还可协调对空口的属性管理。例如，网络设备可以包括长期演进(long term evolution，LTE)系统或高级长期演进(long term evolution-advanced，LTE-A)中的演进型基站(NodeB或eNB或e-NodeB，evolutional Node B)，或者也可以包括第五代移动通信技术(the 5th generation，5G)NR系统(也简称为NR系统)中的下一代节点B(next generation node B，gNB)或者也可以包括云接入网(cloud radio access network，Cloud RAN)系统中的集中式单元
(centralized unit，CU)和分布式单元(distributed unit，DU)，或者可以是未来的通信系统中承载网络设备功能的装置，本申请实施例并不限定。
网络设备还可以包括核心网设备。核心网设备例如包括访问和移动管理功能(access and mobility management function，AMF)或用户面功能(user plane function，UPF)等。
网络设备还可以是设备到设备(Device to Device，D2D)通信、机器到机器(Machine to Machine，M2M)通信、车联网、或卫星通信系统中承载网络设备功能的装置。
3)星座图，用于通信装置在发送时对信号的调制，同时也用于通信装置在接收时对信号的解调，因此收发两端要采用同样的星座图进行通信。一般的，星座图可以用于定义信号元素的振幅和相位，数字调制可以在幅度和相位上区分信号。在星座图中，一个信号元素可以用一个星座点进行表示，每种幅度和相位的组合可以表示为一个星座点。例如星座图的水平X轴与同相载波相关，星座图的垂直Y轴与正交载波相关。
不同调制解调方式的星座图中星座点的数量和坐标可能不同，例如调制解调方式包括四相移相键控(quadrature phase shift keying，QPSK)、16正交振幅调制(quadrature amplitude modulation，QAM)或64QAM等。当一个星座图中有x个星座点时，意味着每个星座点可以代表log 2(x)位二进制信息，即该星座图对应log 2(x)调制等级。例如QPSK星座图中有4个星座点，每个星座点可以代表2位二进制信息，每个点也可看作一个具有2位二进制信息的码，四个星座点对应的码分别为00、01、10和11，这四个星座点的坐标可以分别设计为[1,1]、[-1,1]、[1,-1]和[-1,-1]。考虑到能量归一化，每个星座点的横纵坐标还可以除以√2。
在进行调制时，将待发送的二进制信息进行编码之后被映射到星座图中的星座点，即可实现数字调制(也称星座调制)。在进行解调时，根据接收到的信号与星座图中每个星座点的距离，确定发送端发送的是哪个信号，从而正确解调数据。例如，对接收到的QPSK信号进行解调时，根据QPSK信号与星座图中4个星座点之间的距离，如果距离00点最近，则可以确定接收到QPSK信号为00，或者又如QPSK星座图中的四个星座点对称分布在四个象限上，接收方通过判断接收信号在哪个象限上即可完成信号的解调。
其中在星座图的设计满足格雷码特点时，星座图中相邻星座点所代表的码尽量只相差1个比特。这样可以保证当一个星座点被误判为其相邻的码时，误判的比特数最少，也就是说BER可以尽量小。
通信性能受调制方式的影响，调值方式的设计包括：a基于比特随机等概率和加性高斯白噪声(additive white gaussian noise，AWGN)的信道假设，进行调制星座点的设计，使相邻星座点之间符合格雷码特点；b使用星座整形、概率整形等方法提高通信性能。方式a是在理想情况下设计的星座图，不能很好的适配实际通信场景。方式b是在设计好的星座图在使用时，再设计一种不等概率的星座映射，星座点的位置没有改变，仅改变映射的概率。现有通信系统中采用固定的星座图设计，即星座图中星座点的位置是固定的，通信双方均保存有该固定的星座图，并可以利用该固定的星座图完成通信的调制和解调。
随着通信技术及通信场景的发展，对通信系统的性能要求越来越高，并且出现了很多垂直应用场景(如工业互联网、车联网等)，也就是说对星座图提出了更高的设计需求，固定的星座图无法适应变化的通信场景和通信性能要求，导致实际通信过程中的通信性能较差。
在本申请中通信设备通信时采用的星座图可以根据通信场景的不同自适应改变，也就是说在不同场景下不同的星座图具有不同的性能，可以设计和当前场景更匹配的星座图，使网络的性能最大化。可选的，基于不同场景的星座图设计可以用到星座图设计器，星座 图设计器以当前场景相关信息为最基本的输入，输出适配这个场景的星座图。其中，星座图设计器设计星座图的过程可以基于深度强化学习实现。
4)深度强化学习(deep reinforcement learning，DRL)，是深度神经网络和强化学习相结合。
深度神经网络，具有输入层和输出层，并且在输入层和输出层之间具有至少一层隐藏层，隐藏层后可能具有非线性激活函数处理，如修正线性单元(rectified linear unit，ReLU)函数或tanh函数等。其中输入层、输出层和隐藏层可以统称为网络层，也可以简称为层。层与层之间通过每个层上的节点相互连接组成，一对连接的节点具有一个权重值和一个偏置值。深度神经网络可以看作是从输入到输出的非线性变换。输出还可以再通过一个损失函数(loss function)来计算损失，计算产生的梯度可以用回传(back-propagation)算法从输出层回传至输入层，以此来更新每层的权重值和偏置值，达到损失最小化。
强化学习，是智能体(agent)与环境交互，通过试错(或者探索)学习最优策略的过程。尤其是对于具有一系列决策的问题，在不能进行理论建模或求解困难时，强化学习可以提供解决方案。强化学习还可能包括如下概念：状态(或者观察)、策略、回报(也称奖励reward)、时间步、回合和值函数。其中智能体可以根据环境反馈的状态，对环境做出动作/行动，从而获取回报及下一个时刻的状态，目标是使智能体在一段时间内积累最大的回报(即最大化每个回合的总回报)。策略决定了在给定状态的情况下，智能体会采取何种行动，即策略可以认为是从状态到行动的映射。在深度强化学习过程中，观察可以是深度神经网络的输入，行动对应深度神经网络的输出。回报(值)是智能体在当前环境中采取某种行动后，环境反馈的值，即对智能体采取行动的好坏作出的评价。在每个时间步，智能体都会采取一种行动，然后环境会反馈一个回报值。通常遇到的问题都不是优化单一动作就可以解决的问题，而是优化一系列决策带来的最终结果或综合结果，因此，在强化学习优化某一问题的过程中，可以以回合为单位，每一回合包含多个时间步。环境可以在每个回合结束时的时间步反馈一个回报值，这种情况下回合结束之前的每个时间步的回报值可以用零替代。或者环境可以在每个回合未结束时就反馈一个非零的回报值，其中不同的环境对应不同的反馈方式。值函数也是一种映射，值函数的输入可以是状态，或者状态和行动的合集，值函数的输出是一个值，表示智能体对未来可以积累的总回报的估计值，该值越大，表示当前选择的行动更佳。在深度强化学习过程中，值函数也可以用深度神经网络表示，值函数的输入为深度神经网络的输入，值函数的输出为深度神经网络的输出。
5)本申请实施例中的术语“系统”和“网络”可被互换使用。“至少一个(种)”是指一个(种)或者多个(种)，“多个(种)”是指两个(种)或两个(种)以上。“和/或”，描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B的情况，其中A，B可以是单数或者复数。字符“/”一般表示前后关联对象是一种“或”的关系。“以下至少一项(个)”或其类似表达，是指的这些项中的任意组合，包括单项(个)或复数项(个)的任意组合。例如，a,b,或c中的至少一项(个)，可以表示：a,b,c,a-b,a-c,b-c,或a-b-c，其中a,b,c可以是单个，也可以是多个。
以及，除非有相反的说明，本申请实施例提及“第一”、“第二”等序数词是用于对多个对象进行区分，不用于限定多个对象的顺序、时序、优先级或者重要程度。例如，第一数据包和第二数据包，只是为了区分不同的数据包，而并不是表示这两个数据包的内容、优先级、发送顺序或者重要程度等的不同。
本申请实施例提供的通信方法可以应用于各类通信系统中，例如，卫星通信系统、物联网(internet of things，IoT)、窄带物联网(narrow band internet of things，NB-IoT)系统、全球移动通信系统(global system for mobile communications，GSM)、增强型数据速率GSM演进系统(enhanced data rate for GSM evolution，EDGE)、宽带码分多址系统(wideband code division multiple access，WCDMA)、码分多址2000系统(code division multiple access，CDMA2000)、时分同步码分多址系统(time division-synchronization code division multiple access，TD-SCDMA)，长期演进系统(long term evolution，LTE)、第五代(5G)通信系统，例如5G新无线(new radio，NR)，以及5G移动通信系统的三大应用场景增强型移动带宽(enhanced mobile broadband，eMBB)，超可靠、低时延通信(ultra reliable low latency communications，uRLLC)和海量机器类通信(massive machine type communications，mMTC)，或者还可以是其他的或者未来的通信系统。
为了便于理解本申请实施例，以图1所示的网络架构对本申请实施例所使用的应用场景进行说明，该网络架构可以应用于上述各类通信系统。图1所示的网络架构中包括网络设备和终端设备，所述网络设备和所述终端设备采用星座图进行通信。所述网络设备的数量可以为一个或多个，所述终端设备的数量可以为一个或多个(如图1所示为两个终端设备)，在本申请实施例中对网络设备和终端设备的类型和数量均不做限定。
目前通信标准中规定采用的星座图设计是固定的，例如在调制解调方式为QPSK时采用约定好的固定的第一星座图，在调制解调方式为16QAM时采用约定好的固定的第二星座图。而随着通信技术及通信场景的发展，对通信系统的性能要求越来越高，并且出现了很多垂直应用场景(如工业互联网、车联网等)，固定的星座图无法适应变化的通信场景和通信性能要求，导致实际通信过程中的通信性能较差。
基于此，本申请实施例提供一种通信方法，本申请实施例提供的通信方法适用于如图1所示的通信系统。该方法中，通信装置可以以当前场景相关信息为基础，对通信时采用的星座图进行自适应设计，可以保证设计出和当前场景更匹配的星座图，提高通信网络的性能。其中场景相关信息可以理解为星座图设计器的星座图设计参数。参阅图2所示，所述通信方法的具体流程可以包括：
S201：第一通信装置发送星座图设计参数，第二通信装置接收所述星座图设计参数，所述星座图设计参数包括通信场景设计参数和通信装置设计参数。
所述第一通信装置可以为终端设备或网络设备，例如所述第一通信装置为终端设备。所述第二通信装置可以为终端设备或网络设备，例如所述第二通信装置为网络设备(如基站)。
在一个示例中，所述第一通信装置可以主动发送所述星座图设计参数。例如所述第一通信装置可以周期性的获取星座图设计参数，然后将获取到的星座图设计参数发送给所述第二通信装置。又如在所述第一通信装置与所述第二通信装置之间的无线资源控制(radio resource control，RRC)连接建立时，所述第一通信装置获取星座图设计参数，然后将获取到的星座图设计参数发送给所述第二通信装置。
在另一个示例中，所述第二通信装置可以向所述第一通信装置发送第一消息，所述第一消息用于询问所述第一通信装置是否支持更新星座图，即询问所述第一通信装置是否具有更新星座图的能力，或者所述第一消息用于通知/指示/请求所述第一通信装置发送星座 图设计参数。
可选的，所述第二通信装置发送第一消息之前，所述第一通信装置还可以向所述第二通信装置主动请求更新星座图。
若所述第一消息用于询问所述第一通信装置是否支持更新星座图，所述第一通信装置可以向所述第二通信装置反馈能力信息，用于指示所述第一通信装置是否支持更新星座图。例如可以通过新增的updateConstellation字段来指示所述第一通信装置是否支持更新星座图，当updateConstellation字段的值为true时，表示所述第一通信装置支持更新星座图，当updateConstellation字段的值为false时，表示所述第一通信装置不支持更新星座图。如果所述第一通信装置支持更新星座图，所述第一通信装置可以后续在上行链路中发送星座图设计参数。一般的，所述第一通信装置支持更新星座图，如所述第一通信装置在硬件中支持对通信所采用的星座图进行更新，或者所述第一通信装置在硬件上支持获取星座图设计参数。可选的，核心网设备还可以对所述第一通信装置的能力信息进行鉴权。
若所述第一消息用于通知/指示/请求所述第一通信装置发送星座图设计参数，所述第一通信装置根据所述第一消息的通知/指示/请求，向所述第二通信装置发送星座图设计参数。
在该S201之前，所述第一通信装置和所述第二通信装置之间可以采用第一星座图进行通信。例如所述第一星座图可以为当前标准中规定的固定的星座图，又如所述第一星座图可以为根据星座图设计参数生成的星座图。
可选的，在该S201中，所述第一通信装置采用所述第一星座图，发送所述星座图设计参数；所述第二通信装置采用所述第一星座图，接收所述星座图设计参数。
一般的，用户在使用终端设备的过程中会产生移动位置，而网络设备在部署后一般不会移动位置，因此所述星座图设计参数可以主要与所述第一通信装置相关，如通信场景设计参数和通信装置设计参数中所涉及的通信装置主要是指所述第一通信装置。但这并不意味着不考虑与所述第二通信装置相关的设计参数对星座图设计产生的影响。
所述通信场景设计参数包括以下至少一种信息：信道特征、环境可视化信息、时间、天气等场景(context)相关信息。
所述信道特征是对通信装置所处信道环境的描述，可以是一段时间内统计的结果。所述信道特征可以包括信道环境类型指示，如城市、乡村、办公室A、街道B、家C这些可以反映不同信道特征的指示信息，如通信设备一天中一半时间在家，一半时间在办公室，则可以把家、0.5、办公室、0.5这些信息作为信道环境类型指示。所述信道特征可以包括信道模型指示，在通信系统中可以存储多个信道模型，每个信道模型可以对应不同的场景。通过提供信道模型指示，可以告知星座图设计器当前场景的信道特征，为了节省信令开销，也可以是发送已知信道模型中的部分替换参数。所述信道特征可以是统计得到的信道模型、或者可以是基于射线追踪等方法确定的信道模型、或者可以是通过神经网络实现的信道模型。可以理解，本申请实施例所涉及的通信装置包括所述第一通信装置和/或第二通信装置。
通过信道环境类型指示可以对信道特征有一个大概的了解，而环境可视化信息可以对场景提供进一步的描述，让星座图设计器设计出的星座图更加准确。提供环境可视化信息有助于通信系统通过射线追踪的方法对环境建模，以此建立信道模型或作为信道模型的输入。环境可视化信息用于描述物体在空间中大小和位置，可以包括环境中采集的图像、深度图片、点云数据、或三维图片中的一种或多种。
基于不同的星座图设计参数，设计的星座图也有区别，因此可以针对不同场景探索最优的星座图，以保证星座图在性能上可以进一步提升，因此可以通过不同星座图设计参数的选取，来设计出与当前场景最匹配的星座图。
所述通信装置设计参数包括以下至少一种信息：用户行为画像、星座图设计器回报参数、星座图设计器训练参数。
用户行为画像(user behavioral profile)代表了用户在一段时间内的行为偏好，所以可以用分布来表示，分布即是一段时间内的统计信息。所述用户行为画像可以包括通信装置的位置分布，所述位置分布可以为对通信装置的地理位置在一段时间内变化的统计。所述用户行为画像可以包括通信装置的服务类型，所述服务类型指一段时间内统计的通信装置使用的服务类型情况，如语音服务、数据服务等，数据服务可以分为对时延要求较高的游戏类、虚拟现实(virtual reality，VR)类，和/或对时延要求较低的网页类等。所述服务类型可能影响到接收到数据的分布，即信源分布。所述用户行为画像可以包括通信装置的移动性分布，所述移动性分布是对一段时间内通信装置移动性的统计。所述移动性是指通信装置移动的快慢，如静止、低移动性或高移动性等，或者所述移动性也可以是具体的移动速度。所述用户行为画像可以包括物理层配置信息。所述物理层配置信息可以是在一段时间内统计得到，所述物理层配置信息可以包括码率、编译码器类型、滤波器类型、波形信息、导频信息、天线配置、预编码信息等一种或多种。所述用户行为画像包括通信装置的射频链路硬件参数分布是指一段时间内统计的硬件参数变化。所述射频链路硬件参数包括通信设备使用的设备唯一识别码、国际移动用户识别码(international mobile subscriber identity，IMSI)、设备型号、天线型号、射频链路中的数模转换器(digital-to-analog converter，DAC)/模数转换器(analog-to-digital converter，ADC)精度、双工工作方式等一种或多种硬件相关信息。
星座图设计器回报参数包括以下至少一种信息：通信装置反馈的信息、星座图设计器计算得到的性能、或用于评估星座图性能的公式。性能指吞吐、误码率、数据速率、峰值平均功率比(peak to average power ratio，PAPR)等这些对通信系统性能有影响的指标、性能还可以是通信装置反馈的关键绩效指标(key performance indicator，KPI)，如容量、服务质量、延时、掉话统计等指标。评估星座图性能的公式可以是计算星座图是否满足格雷码的公式、或计算星座图码距的公式、或其他可以反映星座图使用在通信系统中的性能评估公式。
星座图设计器训练参数包括以下至少一种信息：训练的收敛条件、训练的回合数、每个回合包含的时间步、训练的迭代次数、星座点的坐标范围、或训练的星座点的数量。
所述星座图设计器达到训练的收敛条件时，可以认为所述星座图设计器收敛。所述训练的收敛条件可以是达到训练的迭代次数、或者可以是达到训练的回合数、或者可以是译码性能不再增加等。通过设置训练的星座点的数量，可以对星座图中的全部或部分星座点进行探索，在对部分星座点进行探索时，可以减少深度强化学习带来的资源消耗，也可以保证探索得到的星座图相比原第一星座图的性能不会下降太多。通过设置星座点的坐标范围，可以将星座点的坐标控制在一定的取值范围内，保证探索得到的星座图的性能不会太差。
通过星座图设计参数，星座图设计器可以对场景进行预测，例如根据历史场景，推断未来可能的场景，并根据未来可能的场景设计星座图。
S202：所述第二通信装置根据所述星座图设计参数，将所述第一星座图更新为第二星座图，所述第二星座图对应于所述星座图设计参数。
所述第二星座图用于所述第一通信装置和所述第二通信装置采用所述第二星座图进行通信，或者说所述第二星座图用于实现所述第一通信装置和所述第二通信装置之间的调制解调。所述第二星座图与所述第一星座图不同。可选的，所述第二星座图与所述第一星座图中星座点的数量相同，星座点的坐标不同。所述第二星座图中星座点可以无规则分布，也可以成对称分布。
通信链路中存在星座图设计器，例如所述第二通信装置中可以设置有星座图设计器。所述星座图设计器可以采用深度强化学习方法，所述星座图设计器的输入为场景相关信息，即星座图设计参数，所述星座图设计器的输出为第二星座图。这种根据场景决定星座图的方式可以看作是针对性的设计星座图。
如图3a所示，在S202中，所述第一通信装置将所述星座图设计参数发送给所述第一第二通信装置。所述第二通信装置将所述星座图设计参数输入到星座图设计器中，所述第二通信装置可以基于所述星座图设计器，生成所述第二星座图，然后所述第二通信装置可以将所述第一星座图更新为所述第二星座图，所述第二星座图即为适用于当前场景的星座图。所述第二通信装置可以将所述第二星座图发送给所述第一通信装置。
其中，基于所述星座图设计器生成所述第二星座图的过程可以参见下述详细说明。
S203：所述第二通信装置发送所述第二星座图的信息，所述第一通信装置接收所述第二星座图的信息。
所述第二星座图的信息可以为所述第二星座图的标识信息，或者可以为所述第二星座图中各星座点的坐标等。
所述第一通信装置接收所述第二星座图的信息后，可以向所述第二通信装置发送第二消息，所述第二消息用于请求切换为更新后的星座图(即所述第二星座图)进行通信。所述第二通信装置发起RRC连接重配置，在RRC连接重配置完成之后，所述第一通信装置和所述第二通信装置之间即可采用更新后的星座图进行通信。
S204：所述第一通信装置和所述第二通信装置采用所述第二星座图进行通信。
采用更新后的第二星座图进行通信的过程如图3b所示，发送方将待发送的信息比特进行信道编码，采用第二星座图对编码后的信号进行调制，将调制后的信号通过信道发送给接收方，所述第二星座图基于所述星座图设计器生成。所述接收方采用第二星座图对接收到的信号进行解调，对解调后的信号进行信道译码，得到译码比特，所述译码比特可以认为是发送方所发送的信息。
由于深度强化学习设计出的星座图不受规则限定，所以设计得到的星座图大概率是非规则的，非规则星座图的解调复杂度高于规则星座图的解调复杂度。其中非规则星座图中星座点的分布/位置/坐标不具有规律性，而规则星座图中星座点的分布/位置/坐标具有规律性(如星座点成对称分布)。因此所述第一通信装置还可以将所述第二星座图变换为第三星座图，所述第二通信装置也可以将所述第二星座图变换为所述第三星座图，所述第三星座图为预设的星座图中与所述第二星座图最接近的星座图。例如所述预设的星座图可以为规则星座图，具体的，所述第三星座图可以为规则的星座图中与所述第二星座图中星座点数量相同，且星座点坐标距离最近的星座图。所述第一通信装置和所述第二通信装置在变换为所述第三星座图之后，还可以采用所述第三星座图进行通信。
如果所述第一通信装置和所述第二通信装置采用所示第二星座图无法通信，或者采用所述第二星座图通信后性能明显下降超过第一阈值时，可以采取回退机制，将新的第二星座图退回到原来的第一星座图，所述第一阈值用于表示通信系统性能下降的程度，在本申请实施例中对所述第一阈值的取值不做限定。可选的，所述回退机制可以由第二通信装置发起，所述第二通信装置向所述第一通信装置发送指示信息，所述指示信息用于指示采用回退机制，所述回退机制用于指示将所述第二星座图变换为所述第一星座图。又或者可选的，所述回退机制可以由第一通信装置发起，所述第一通信装置向所述第二通信装置发送第一请求消息，所述第一请求消息用于请求采用回退机制，所述回退机制用于指示将所述第二星座图变换为所述第一星座图。所述第一通信装置和所述第二通信装置在RRC连接重配置完成之后，即可采用所述第一星座图进行通信。
可以理解的是，星座图的设计过程可以是在通信装置使用的过程中在线发生的，即根据通信装置所处的变化的环境、场景中工作时，通信装置在线设计并更新星座图。或者也可以根据某一特定场景离线设计一个具有针对性的星座图，例如，某个通信装置在生产时，就已经明确要应用在某个场景下，且这个场景基本不会发生变化，则可以预先为这种场景设计一种星座图。但是一般离线设计不如在线设计灵活，大部分通信装置都处于变化的环境、场景中工作，在线设计并更新星座图可以提供更高的灵活性，让通信装置一直处于高性能运行状态，因此可以根据实际需求选择在线设计星座图或者离线设计星座图。
由于星座图设计器以场景相关信息作为输入，因此对于相同或相近的“场景相关信息”，可以返回相同的星座图，因此在星座图设计的实现过程中，可以存储一个映射表，将针对通过深度强化学习得到的星座图，在映射表中进行保存。这样，根据获取到的星座图设计参数，通过查表可以直接确定对应的星座图，其中所述第一通信装置和所述第二通信装置均可以保存有所述映射表，所述第一通信装置和所述第二通信装置可以定时对所述映射表进行更新，或通过表格中的星座图序号选择更新对应的星座图。所述映射表可以如表1所示，表1中保存有部分星座图设计参数与星座图的对应关系，并为每个对应关系分配有序号/标识信息。编号为1的对应关系中，星座图设计参数包括信源分布为信源分布x、信道特征为高频室内信道、物理层配置为码率0.5、硬件参数为3bit ADC，星座图为星座图A；编号为2的对应关系中，星座图设计参数包括信源分布为信源分布y、信道特征为低频城市信道、物理层配置为码率0.75、硬件参数为全双工，星座图为星座图B。
表1
Figure PCTCN2021114246-appb-000001
具体的，所述第一通信装置和所述第二通信装置可以保存所述星座图设计参数与所述第二星座图的对应关系。可选的，所述第一通信装置和所述第二通信装置可以为该对应关系分配标识信息(如分配第一标识信息)。在后续使用过程中，所述第一通信装置和所述第二通信装置还可以根据所述星座图设计参数，在所述对应关系中查找所述星座图设计参数对应的所述第二星座图。
若所述第一通信装置和所述第二通信装置中保存了映射表，则在星座图设计过程中， 所述第一通信装置和所述第二通信装置可以优先在所述映射表中查找星座图设计参数对应的星座图，若映射表中不包括某一星座图设计参数对应的星座图，所述第二通信装置可以为该星座图设计参数，生成对应的星座图。
下面对基于星座图设计器生成第二星座图的过程进行详细说明。其中，基于星座图设计器生成第二星座图的过程可以看作是对星座图设计的学习训练过程，该过程中星座图设计参数可以包括星座图设计器回报参数和/或星座图设计训练参数。
在该对星座图设计的学习训练过程中，智能体可以基于从外部获取到的星座图设计参数尝试生成星座图，评估器可以对智能体尝试生成的星座图的性能进行评估，确定智能体尝试生成的星座图是否为与当前场景最匹配的星座图。具体的，星座图设计参数和智能体尝试生成的星座图作为评估器的输入，改变了评估器的评估条件，评估器根据改变后的评估条件重新计算回报，智能体可以以增大回报为目标，当回报不再增大时，认为智能体收敛，在收敛状态下输出的星座图即为最终的星座图，也就是第二星座图。其中状态为一种可能的星座图、动作为对这种星座图的改变、回报是采取动作之后新的星座图的价值即星座图的性能。
评估器可以是链路级仿真器，可以是系统级仿真器，可以是一种理论计算公式，或者可以是一种查表的方法，还可以是对实际通信情况的统计及组合，在本申请实施例中不做限定，只要评估器可以针对不同的星座图评估出相应的回报值即可。例如所述智能体生成的星座图输入到评估器中，所述评估器确定该星座图与已知且可靠的星座图的设计规律相违背，如背离了格雷码特点，则评估器可以直接为该星座图输出一个较小的回报值，可以不经过蒙特卡洛仿真方法，从而节省大量不合理的探索带来的时间消耗。又如多个网络设备可以在评估经验上共享，当所述智能体生成的星座图输入到评估器中时，所述评估器可以查询本设备或其他网络设备的历史评估结果，如果发现存在与该星座图相同或相似星座图的评估结果，则可以直接重用之前的评估结果，也可以节省蒙特卡洛仿真的时间，节省时间消耗。又如，通信双方采用所述智能体生成的星座图进行通信，评估器统计通信双方采用新星座图通信后的性能指标(如吞吐、BER、BLER、频谱效率等参数)，作为回报反馈给智能体，所述智能体根据回报对之前生成的星座图进行调整，直至所述智能体收敛。
当评估器是一个链路仿真器时，智能体和评估器的交互过程如图3c所示，智能体将设计的星座图作为行动输出，链路仿真器(即评估器)确定所述星座图的误码率，将所述误码率作为回报反馈给所述智能体。
具体的，在深度强化学习设计星座图的过程中，所述智能体首先确定待生成的星座图的调制等级。例如待生成的星座图的调制等级为3，星座图中包括2 3＝8个星座点，每个星座点由两个实数组成，因此一个设计完成的星座图需要有8*2＝16个实数，其中组成星座点的两个实数可以代表笛卡尔坐标系横轴和纵轴上的坐标值，也可以代表极坐标下幅度和相位的坐标值。
智能体中有关深度强化学习的元素中状态可以是1*16维(或总元素数大于或等于16的任意维度)的向量，也可以是4*4维度(或总元素数大于或等于16的任意维度)的矩阵，所述向量或所述矩阵中的元素取值可以为任意实数，表示星座图的各个星座点的位置坐标。
所述深度强化学习的元素中行动是每个时间步确定的星座点坐标的分布，例如假设设 置每个时间步确定一个星座点，涉及到两个坐标值的分布，坐标值的分布可以是高斯分布，高斯分布包含期望和方差两个实数，每个时间步需要深度神经网络输出2*2＝4个实数，该实数可以为任意实数，但是任意实数的空间太大，不利于智能体收敛，另外星座图最终要被归一化，过大的实数探索空间是没有必要的，因此可以在深度神经网络的输出之前加入tanh激活函数，让神经网络的实数输出取值在[-1，1]之间。此时，星座点坐标分布的期望在[-1，1]之间是可行的，但是分布的方差还需要进行处理，假设深度神经网络的方差输出为w，可以将2^(10*w)的值作为分布的方差，当w的取值在[-1，1]之间时，方差大于0，且方差可以是一个很小的值或可以是一个很大的值，这样设置既可以保证探索的多样性(开始方差比较大)，又可以让探索最终收敛(方差会越来越小)，这四个分布值组成两个高斯分布，可以从中采样得到两个实数值，给两个实数值即为该时间步最终得到的坐标值。
在训练的回合刚开始时，状态可能为全零或为任意初始值，智能体根据输入的状态输出一个星座点的坐标，该星座点的坐标导致状态发生改变，即在状态向量中该星座点的位置上设置的值从初始值变行动输出的星座点坐标，在本例中经过8个时间步后，当星座点全部设计之后，可以将最终的状态，也即完整的星座图，以及星座图设计参数输入到评估器。在本例中所述评估器是一个链路仿真器，链路仿真器输出所述星座图以及星座图设计参数的译码结果作为回报，译码结果可以是BLER(数值上有可能经过换算，如log10(BLER))或BER，其中星座图的设计是否符合格雷码特点与BER有关，所以可以采用BER作为回报。可见，上述过程体现了智能体通过行动和环境交互的过程，即行动输入环境，改变了状态，然后获得了环境的反馈。此时，一个回合结束，一个回合的回报为最后一个时间步获得的回报，这是因为星座图全部设计完成之后才能评估性能。当然，也可以在一个时间步内输出所有星座点的坐标，这样一个回合就是一个时间步。或者，也可以在一个时间步内只输出一个坐标值(一个星座点在横轴的坐标值或在纵轴的坐标值)，这样，本例中一个回合就需要经过16个时间步来设计出完整的星座图。可以理解，具体设计过程可以根据对深度强化学习的不同需求而进行更改。
深度强化学习在多个回合的训练中，智能体的目标是让译码性能之和最大化，即最优化译码性能并逐渐收敛。在经过一段时间的训练后，译码性能几乎不再增加，此时可以选择译码性能最好的一个回合，记录在该回合中每个时间步的行动，并按照顺序将每个时间步输出的坐标值组成一个完整的星座图，该星座图即可认为是深度强化学习针对当前场景设计的星座图。
在一个实现方式中，如图4a所述，所述星座图设计器中包括智能体和评估器，也就是说在第二通信装置中既包括智能体也包括评估器。
此时，评估器中可能包含一个信道模拟器，当星座图设计参数中包含信道特征时，所述评估器内部的信道模拟器可以模拟所述信道特征，并在所述信道特征下输出信道值，提供给评估器中的链路仿真器。信道特征可以包括信道强度、信道分布、多径分布及延迟等。
第二通信装置只需要从外部获取星座图设计参数，就可以尝试生成星座图，以及可以对尝试生成的星座图进行评估。
在另一个实现方式中，如图4b所示，所述星座图设计器中包括智能体，也就是说在所述第二通信装置中包括智能体，评估器位于所述第二通信装置外部。例如所述第二通信装置中包括所述智能体，所述第一通信装置中包括评估器。
第二通信装置从外部获取星座图设计参数，尝试生成星座图，将尝试生成的星座图发送给 所述第一通信装置，所述第一通信装置对所述星座图进行评估。所述第二通信装置根据评估结果/回报对星座图进行调整，直至所述智能体收敛。
可选的，若所述第二通信装置外部存在多个评估器，所述智能体可以同时向所述多个评估器发送星座图，并接收来自所述多个评估器评估结果。
如图3b所示，当智能体和评估器位于不同通信装置中，当智能体设置在调制侧/发送方，新的星座图的信息可以通过信道发送给解调侧/接收方，当智能体设置在解调侧/接收方，新的星座图的信息可以通过信道发送给调制侧/发送方。
由于深度强化学习得到的新星座图可能为非规则星座图，非规则星座图的解调方法与规则星座图的解调方法可能有所不同。如果新星座图解调时不需要输出软信息，可以通过计算接收信号和各个星座点的距离判断，将距离最小的星座点确定为解调得到的星座点。如果新星座图解调时需要输出软信息，可以计算接收信号和各个星座点的距离信息，再结合常用的译码算法，计算软信息，例如可以采用max-log译码方法计算软信息。
不同信息比特长度生成不同的星座图，根据本申请实施例中所示的深度强化学习生成的星座图的示意图如图5a和图5b所示。
如图5a为使用2bit ADC的链路下，通过强化学习得到如下8QAM星座图。星座图中各星座点的坐标值如表2所示。可以理解的是，对上述星座图的星座点顺序调换仍在本发明的保护范围内，对星座点的坐标值的缩放或一定范围的微调仍然在本发明的保护范围内。
表2
Figure PCTCN2021114246-appb-000002
如图5b为使用3bit ADC的链路下，通过强化学习得到如下8QAM星座图。星座图中各星座点的坐标值如表3所示。可以理解的是，对上述星座图的星座点顺序调换仍在本发明的保护范围内，对星座点的坐标值的缩放或一定范围的微调仍然在本发明的保护范围内。
表3
Figure PCTCN2021114246-appb-000003
下面以图6所示的具体实施例对本申请实施例的通信方法进行说明，包括以下步骤：
S601：基站询问终端设备是否具有更新星座图的能力。
S602：所述终端设备反馈所述终端设备具有更新星座图的能力信息。
根据具体的使用场景不同，本申请实施例还可能新增字段/信令消息。如下表4所示，本申请实施例中新增了字段(IE)/组名(Group Name)，包括更新星座图标识位 (updateConstellationFlag)字段，更新星座图(updateConstellation)字段和星座图相关参数(ConstellationRelatedParameters)字段。所述updateConstellationFlag字段的取值范围为布尔值0或1，用于指示终端设备是否支持更新星座图，即用于指示终端设备是否具有更新星座图的能力。所述updateConstellation字段的取值为[0，1024]范围内的整数，用于指示更新的星座图，即所述updateConstellation字段中可以包括更新的星座图中星座点的坐标。所述ConstellationRelatedParameters字段为set集合，为星座图相关的参数集合，即所述ConstellationRelatedParameters字段中可以包括星座图设计参数。
表4
Figure PCTCN2021114246-appb-000004
在该S602中，所述终端设备可以通过表4中新增的updateConstellationFlag字段，指示所述终端设备是否具有更新星座图的能力，updateConstellationFlag字段的取值范围可以为布尔值0或1。如果updateConstellationFlag字段值为1，则表示所述终端设备具有更新星座图的能力，如果updateConstellationFlag字段值为0，则表示所述终端设备不具有更新星座图的能力。一般的，在本申请实施例中，所述终端设备具有更新星座图的能力。
所述基站可以通过表4新增的updateConstellation字段，向所述终端设备发送更新后的星座图中星座点的坐标，其中updateConstellation字段的取值可以为任意实数，例如图5a或图5b所示，取值为在[-1.5,1.5]范围内的任意实数，或者如表4所示，取值为在[0,1024]范围内的整数。可以理解的是，若生成星座图的通信装置为所述终端设备，则所述终端设备也可以通过updateConstellation字段，向所述基站发送更新后的星座图中星座图点的坐标。可选的，所述updateConstellation字段可以通过RRC信令发送。
所述终端设备可以通过表4新增的ConstellationRelated Parameters字段，发送与星座图相关的参数集合，即星座图设计参数，所述ConstellationRelated Parameters为set集合。
S603：核心网设备对终端设备的更新星座图的能力信息进行鉴权。
S604：所述终端设备请求更新星座图。
S605：所述基站启动更新星座图的流程，并询问所述终端设备更新星座图所需的参数。
S606：所述终端设备根据本地的统计信息，发送更新星座图所需的参数(即星座图设计参数)。
在该S606中，所述终端设备可以通过新增的ConstellationRelated Parameters字段发送 星座图设计参数。
S607：所述基站根据所述参数，基于星座图设计器，生成新星座图。所述基站将新星座图的信息发送给所述终端设备。
S608：所述终端设备接收到所述新星座图后，请求所述基站切换新星座图。
S609：所述基站和所述终端设备之间进行RRC连接重配置，在RRC连接重配置完成之后，所述基站和所述终端设备之间切换为新星座图。
可选的S610a：所述基站确定新星座图不能工作，或工作后性能下降明显，所述基站发起回退标准星座图(即原星座图)指示。所述终端设备确认回退至所述标准星座图。
可选的S610b：所述终端设备确定新星座图不能工作，或工作后性能下降明显，所述终端设备请求回退至标准星座图。
其中在新星座图不能工作，或工作后性能下降明显时，可以回退至标准星座图。回退标准星座图的流程可以由所述基站发起(如S610a)，也可以由所述终端设备发起(如S610b)，S610a和S610b可以择一使用。
S611：所述基站和所述终端设备之间进行RRC连接重配置，在RRC连接重配置完成之后，所述基站和所述终端设备之间切换为标准星座图。
在本申请实施例中通信装置可以通过深度强化学习，基于当前场景相关参数生成星座图，可以保证生成的星座图与当前场景最匹配，并且还设计了通信双方在星座图设计过程中的协商配合过程，从而保证通信性能。
以上结合图1至图6详细说明了本申请实施例的通信方法，基于与上述通信方法的同一发明构思，本申请实施例还提供了一种通信装置，如图7所示，所述通信装置700中包含处理单元701和收发单元702，装置700可用于实现上述应用于第一通信装置或第二通信装置的方法实施例中描述的方法。
在一个实施例中，装置700应用于所述第一通信装置，所述第一通信装置可以为网络设备或终端设备，例如所述第一通信装置为终端设备。
具体的，所述处理单元701，用于确定星座图设计参数；
所述收发单元702，用于发送所述星座图设计参数，所述星座图设计参数包括通信场景设计参数和通信装置设计参数；接收第二星座图的信息，所述第二星座图对应于所述星座图设计参数；采用所述第二星座图进行通信。
在一个实现方式中，所述收发单元702，还用于在发送星座图设计参数之前，采用第一星座图进行通信。
在一个实现方式中，所述处理单元701，还用于在所述收发单元702采用所述第二星座图进行通信之前，将所述第一星座图更新为所述第二星座图，所述第一星座图与所述第二星座图不同。
在一个实现方式中，所述通信场景设计参数包括以下至少一种信息：信道特征、环境可视化信息；其中，所述信道特征包括以下至少一种信息：信道环境类型指示、信道模型指示、信道模型；所述环境可视化信息包括以下至少一种信息：环境中采集的图像、深度图片、点云数据或三维图片；
所述通信装置设计参数包括以下至少一种信息：用户行为画像、星座图设计器回报参数；其中，所述用户行为画像包括以下至少一种信息：所述第一通信装置的位置分布、所 述第一通信装置服务类型分布、所述第一通信装置移动性分布、所述第一通信装置的码率分布、所述第一通信装置的射频链路硬件参数分布；所述星座图设计器回报参数包括以下至少一种信息：所述第一通信装置反馈的性能、星座图设计器计算得到的性能、或用于评估星座图性能的公式。
在一个实现方式中，所述处理单元701，还用于在所述收发单元702接收所述第二星座图的信息之后，将所述第二星座图变换为第三星座图，所述第三星座图为预设的星座图中与所述第二星座图最接近的星座图。
在一个实现方式中，所述收发单元702，还用于在采用所述第二星座图进行通信之后，接收指示信息，所述指示信息用于指示采用回退机制，所述回退机制用于指示将所述第二星座图变换为所述第一星座图；或者发送第一请求消息，所述第一请求消息用于请求采用回退机制，所述回退机制用于指示将所述第二星座图变换为所述第一星座图。
在一个实现方式中，所述处理单元701，还用于保存所述星座图设计参数与所述第二星座图的对应关系。
在一个实现方式中，所述处理单元701，还用于根据所述星座图设计参数，在所述对应关系中查找所述星座图设计参数对应的所述第二星座图。
在另一个实施例中，装置700应用于所述第二通信装置，所述第二通信装置可以为网络设备或终端设备，例如所述第二通信装置为网络设备(如基站)。
具体的，所述收发单元702，用于接收星座图设计参数，所述星座图设计参数包括通信场景设计参数和通信装置设计参数；
所述处理单元701，用于确定所述星座图设计参数，并确定第二星座图，所述第二星座图对应于所述星座图设计参数；
所述收发单元702，还用于发送所述第二星座图的信息；采用所述第二星座图进行通信。
在一个实现方式中，所述收发单元702，还用于在接收星座图设计参数之前，采用第一星座图进行通信。
在一个实现方式中，所述处理单元701，还用于在所述收发单元702发送所述第二星座图的信息之前，根据所述星座图设计参数，将所述第一星座图更新为所述第二星座图，所述第一星座图与所述第二星座图不同。
在一个实现方式中，所述通信场景设计参数包括以下至少一种信息：信道特征、环境可视化信息；其中，所述信道特征包括以下至少一种信息：信道环境类型指示、信道模型指示、信道模型；所述环境可视化信息包括以下至少一种信息：环境中采集的图像、深度图片、点云数据或三维图片；
所述通信装置设计参数包括以下至少一种信息：用户行为画像、星座图设计器回报参数；其中，所述用户行为画像包括以下至少一种信息：所述第一通信装置的位置分布、所述第一通信装置服务类型分布、所述第一通信装置移动性分布、所述第一通信装置的码率分布、所述第一通信装置的射频链路硬件参数分布；所述星座图设计器回报参数包括以下至少一种信息：所述第一通信装置反馈的性能、星座图设计器计算得到的性能、或用于评估星座图性能的公式。
在一个实现方式中，所述处理单元701，具体用于将所述星座图设计参数输入到星座图设计器中；基于所述星座图设计器，将所述第一星座图更新为所述第二星座图。
在一个实现方式中，所述处理单元701，还用于将所述第二星座图变换为第三星座图，所述第三星座图为预设的星座图中与所述第二星座图最接近的星座图。
在一个实现方式中，所述收发单元702，还用于在采用所述第二星座图进行通信之后，发送指示信息，所述指示信息用于指示采用回退机制，所述回退机制用于指示将所述第二星座图变换为所述第一星座图；或者接收第一请求消息，所述第一请求消息用于请求采用回退机制，所述回退机制用于指示将所述第二星座图变换为所述第一星座图。
在一个实现方式中，所述处理单元701，还用于保存所述星座图设计参数与所述第二星座图的对应关系。
在一个实现方式中，所述处理单元701，还用于根据所述星座图设计参数，在所述对应关系中查找所述星座图设计参数对应的所述第二星座图。
需要说明的是，本申请实施例中对模块的划分是示意性的，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
所述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)或处理器(processor)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(read-only memory，ROM)、随机存取存储器(random access memory，RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
基于与上述通信方法相同的构思，如图8所示，本申请实施例还提供了一种通信装置800的结构示意图。装置800可用于实现上述应用于第一通信装置或第二通信装置的方法实施例中描述的方法，可以参见上述方法实施例中的说明。所述装置800可以处于第一通信装置或第二通信装置中或为第一通信装置或第二通信装置。
所述装置800包括一个或多个处理器801。所述处理器801可以是通用处理器或者专用处理器等。例如可以是基带处理器、或中央处理器。基带处理器可以用于对通信协议以及通信数据进行处理，中央处理器可以用于对通信装置(如，基站、终端、或芯片等)进行控制，执行软件程序，处理软件程序的数据。所述通信装置可以包括收发单元，用以实现信号的输入(接收)和输出(发送)。例如，所述收发单元可以为收发器，射频芯片等。
所述装置800包括一个或多个所述处理器801，所述一个或多个处理器801可实现上述所示的实施例中第一通信装置或第二通信装置的方法。
可选的，处理器801除了实现上述所示的实施例的方法，还可以实现其他功能。
可选的，一种设计中，处理器801可以执行指令，使得所述装置800执行上述方法实施例中描述的方法。所述指令可以全部或部分存储在所述处理器内，如指令803，也可以全部或部分存储在与所述处理器耦合的存储器802中，如指令804，也可以通过指令803和804共同使得装置800执行上述方法实施例中描述的方法。
在又一种可能的设计中，通信装置800也可以包括电路，所述电路可以实现前述方法实施例中第一通信装置或第二通信装置的功能。
在又一种可能的设计中所述装置800中可以包括一个或多个存储器802，其上存有指令804，所述指令可在所述处理器上被运行，使得所述装置800执行上述方法实施例中描述的方法。可选的，所述存储器中还可以存储有数据。可选的处理器中也可以存储指令和/或数据。例如，所述一个或多个存储器802可以存储上述实施例中所描述的对应关系，或者上述实施例中所涉及的相关的参数或表格等。所述处理器和存储器可以单独设置，也可以集成在一起。
在又一种可能的设计中，所述装置800还可以包括收发器805以及天线806。所述处理器801可以称为处理单元，对装置(终端或者基站)进行控制。所述收发器805可以称为收发机、收发电路、或者收发单元等，用于通过天线806实现装置的收发功能。
应注意，本申请实施例中的处理器可以是一种集成电路芯片，具有信号的处理能力。在实现过程中，上述方法实施例的各步骤可以通过处理器中的硬件的集成逻辑电路或者软件形式的指令完成。上述的处理器可以是通用处理器、数字信号处理器(digital signal processor，DSP)、专用集成电路(application specific integrated circuit，ASIC)、现成可编程门阵列(field programmable gate array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件。可以实现或者执行本申请实施例中的公开的各方法、步骤及逻辑框图。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。结合本申请实施例所公开的方法的步骤可以直接体现为硬件译码处理器执行完成，或者用译码处理器中的硬件及软件模块组合执行完成。软件模块可以位于随机存储器，闪存、只读存储器，可编程只读存储器或者电可擦写可编程存储器、寄存器等本领域成熟的存储介质中。该存储介质位于存储器，处理器读取存储器中的信息，结合其硬件完成上述方法的步骤。
可以理解，本申请实施例中的存储器可以是易失性存储器或非易失性存储器，或可包括易失性和非易失性存储器两者。其中，非易失性存储器可以是只读存储器(ROM)、可编程只读存储器(programmable ROM，PROM)、可擦除可编程只读存储器(erasable PROM，EPROM)、电可擦除可编程只读存储器(electrically EPROM，EEPROM)或闪存。易失性存储器可以是随机存取存储器(RAM)，其用作外部高速缓存。通过示例性但不是限制性说明，许多形式的RAM可用，例如静态随机存取存储器(static RAM，SRAM)、动态随机存取存储器(dynamic RAM，DRAM)、同步动态随机存取存储器(synchronous DRAM，SDRAM)、双倍数据速率同步动态随机存取存储器(double data rate SDRAM，DDR SDRAM)、增强型同步动态随机存取存储器(enhanced SDRAM，ESDRAM)、同步连接动态随机存取存储器(synchlink DRAM，SLDRAM)和直接内存总线随机存取存储器(direct rambus RAM，DR RAM)。应注意，本文描述的系统和方法的存储器旨在包括但不限于这些和任意其它适合类型的存储器。
本申请实施例还提供了一种计算机可读介质，其上存储有计算机程序，该计算机程序被计算机执行时实现上述应用于第一通信装置或第二通信装置的任一方法实施例所述的通信方法。
本申请实施例还提供了一种计算机程序产品，该计算机程序产品被计算机执行时实现上述应用于第一通信装置或第二通信装置的任一方法实施例所述的通信方法。
在上述实施例中，可以全部或部分地通过软件、硬件、固件或者其任意组合来实现。 当使用软件实现时，可以全部或部分地以计算机程序产品的形式实现。所述计算机程序产品包括一个或多个计算机指令。在计算机上加载和执行所述计算机指令时，全部或部分地产生按照本申请实施例所述的流程或功能。所述计算机可以是通用计算机、专用计算机、计算机网络、或者其他可编程装置。所述计算机指令可以存储在计算机可读存储介质中，或者从一个计算机可读存储介质向另一个计算机可读存储介质传输，例如，所述计算机指令可以从一个网站站点、计算机、服务器或数据中心通过有线(例如同轴电缆、光纤、数字用户线(digital subscriber line，DSL))或无线(例如红外、无线、微波等)方式向另一个网站站点、计算机、服务器或数据中心进行传输。所述计算机可读存储介质可以是计算机能够存取的任何可用介质或者是包含一个或多个可用介质集成的服务器、数据中心等数据存储设备。所述可用介质可以是磁性介质(例如，软盘、硬盘、磁带)、光介质(例如，高密度数字视频光盘(digital video disc，DVD))、或者半导体介质(例如，固态硬盘(solid state disk，SSD))等。
本申请实施例还提供了一种处理装置，包括处理器和接口；所述处理器，用于执行上述应用于第一通信装置或第二通信装置的任一方法实施例所述的通信方法。
应理解，上述处理装置可以是一个芯片，所述处理器可以通过硬件来实现也可以通过软件来实现，当通过硬件实现时，该处理器可以是逻辑电路、集成电路等；当通过软件来实现时，该处理器可以是一个通用处理器，通过读取存储器中存储的软件代码来实现，该存储器可以集成在处理器中，可以位于所述处理器之外，独立存在。
本申请实施例还提供了一种芯片，包括逻辑电路和输入输出接口，所述输入输出接口用于接收/输出代码指令或信息，所述逻辑电路用于执行所述代码指令或根据所述信息，以执行上述应用于第一通信装置或第二通信装置的任一方法实施例所述的通信方法。
所述芯片可以实现上述实施例中处理单元和/或收发单元所示的功能。
例如，所述输入输出接口用于输出星座图设计参数，所述输入输出接口还用于输入所述第二星座图的信息。可选的，所述输入输出接口还可以用于接收代码指令，该代码指令用于指示将第一星座图更新为第二星座图，或者指示将第二星座图变换为第三星座图。
又如，所述输入输出接口用于输入星座图设计参数，所述输入输出接口还用于输出所述第二星座图的信息。可选的，所述输入输出接口还可以用于接收代码指令，该代码指令用于指示将第一星座图更新为第二星座图，或者指示将第二星座图变换为第三星座图。
本申请实施例还提供了一种通信系统，包括第一通信装置和第二通信装置，所述第一通信装置用于执行上述应用于第一通信装置的任一方法实施例所述的通信方法，所述第二通信装置用于执行上述应用于第二通信装置的任一方法实施例所述的通信方法。
本领域普通技术人员可以意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、计算机软件或者二者的结合来实现，为了清楚地说明硬件和软件的可互换性，在上述说明中已经按照功能一般性地描述了各示例的组成及步骤。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。
所属领域的技术人员可以清楚地了解到，为了描述的方便和简洁，上述描述的系统、装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在本申请所提供的几个实施例中，应该理解到，所揭露的系统、装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另外，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口、装置或单元的间接耦合或通信连接，也可以是电的，机械的或其它的形式连接。
作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本申请实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以是两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
通过以上的实施方式的描述，所属领域的技术人员可以清楚地了解到本申请可以用硬件实现，或固件实现，或它们的组合方式来实现。当使用软件实现时，可以将上述功能存储在计算机可读介质中或作为计算机可读介质上的一个或多个指令或代码进行传输。计算机可读介质包括计算机存储介质和通信介质，其中通信介质包括便于从一个地方向另一个地方传送计算机程序的任何介质。存储介质可以是计算机能够存取的任何可用介质。以此为例但不限于：计算机可读介质可以包括RAM、ROM、EEPROM、CD-ROM或其他光盘存储、磁盘存储介质或者其他磁存储设备、或者能够用于携带或存储具有指令或数据结构形式的期望的程序代码并能够由计算机存取的任何其他介质。此外。任何连接可以适当的成为计算机可读介质。例如，如果软件是使用同轴电缆、光纤光缆、双绞线、数字用户线(DSL)或者诸如红外线、无线电和微波之类的无线技术从网站、服务器或者其他远程源传输的，那么同轴电缆、光纤光缆、双绞线、DSL或者诸如红外线、无线和微波之类的无线技术包括在所属介质的定影中。如本申请所使用的，盘(Disk)和碟(disc)包括压缩光碟(CD)、激光碟、光碟、数字通用光碟(DVD)、软盘和蓝光光碟，其中盘通常磁性的复制数据，而碟则用激光来光学的复制数据。上面的组合也应当包括在计算机可读介质的保护范围之内。
总之，以上所述仅为本申请技术方案的较佳实施例而已，并非用于限定本申请的保护范围。凡在本申请的精神和原则之内，所作的任何修改、等同替换、改进等，均应包含在本申请的保护范围之内。

Claims (39)

  1. 一种通信方法，其特征在于，包括：
    第一通信装置发送星座图设计参数；所述星座图设计参数包括通信场景设计参数和通信装置设计参数；
    所述第一通信装置接收第二星座图的信息，所述第二星座图对应于所述星座图设计参数；
    所述第一通信装置采用所述第二星座图进行通信。
  2. 如权利要求1所述的方法，其特征在于，所述第一通信装置发送星座图设计参数之前，还包括：
    所述第一通信装置采用第一星座图进行通信。
  3. 如权利要求2所述的方法，其特征在于，所述第一通信装置采用所述第二星座图进行通信之前，还包括：
    所述第一通信装置将所述第一星座图更新为所述第二星座图，所述第一星座图与所述第二星座图不同。
  4. 如权利要求1-3任一项所述的方法，其特征在于，
    所述通信场景设计参数包括以下至少一种信息：信道特征、环境可视化信息；其中，所述信道特征包括以下至少一种信息：信道环境类型指示、信道模型指示、信道模型；所述环境可视化信息包括以下至少一种信息：环境中采集的图像、深度图片、点云数据、三维图片；
    所述通信装置设计参数包括以下至少一种信息：用户行为画像、星座图设计器回报参数；其中，所述用户行为画像包括以下至少一种信息：所述第一通信装置的位置分布、所述第一通信装置服务类型分布、所述第一通信装置移动性分布、所述第一通信装置的码率分布、所述第一通信装置的射频链路硬件参数分布；所述星座图设计器回报参数包括以下至少一种信息：所述第一通信装置反馈的性能、星座图设计器计算得到的性能、用于评估星座图性能的公式。
  5. 如权利要求1-4任一项所述的方法，其特征在于，所述第一通信装置接收第二星座图的信息之后，还包括：
    所述第一通信装置将所述第二星座图变换为第三星座图，所述第三星座图为预设的星座图中与所述第二星座图最接近的星座图。
  6. 如权利要求2-5任一项所述的方法，其特征在于，所述第一通信装置采用所述第二星座图进行通信之后，还包括：
    所述第一通信装置接收指示信息，所述指示信息用于指示采用回退机制，所述回退机制用于指示将所述第二星座图变换为所述第一星座图；或者
    所述第一通信装置发送第一请求消息，所述第一请求消息用于请求采用回退机制，所述回退机制用于指示将所述第二星座图变换为所述第一星座图。
  7. 如权利要求1-6任一项所述的方法，其特征在于，还包括：
    所述第一通信装置保存所述星座图设计参数与所述第二星座图的对应关系。
  8. 如权利要求7所述的方法，其特征在于，还包括：
    所述第一通信装置根据所述星座图设计参数，在所述对应关系中查找所述星座图设计 参数对应的所述第二星座图。
  9. 一种通信方法，其特征在于，包括：
    第二通信装置接收星座图设计参数；所述星座图设计参数包括通信场景设计参数和通信装置设计参数；
    所述第二通信装置发送第二星座图的信息，所述第二星座图对应于所述星座图设计参数；
    所述第二通信装置采用所述第二星座图进行通信。
  10. 如权利要求9所述的方法，其特征在于，所述第二通信装置接收星座图设计参数之前，还包括：
    所述第二通信装置采用第一星座图进行通信。
  11. 如权利要求10所述的方法，其特征在于，所述第二通信装置发送第二星座图的信息之前，还包括：
    所述第二通信装置根据所述星座图设计参数，将所述第一星座图更新为所述第二星座图，所述第一星座图与所述第二星座图不同。
  12. 如权利要求9-11任一项所述的方法，其特征在于，
    所述通信场景设计参数包括以下至少一种信息：信道特征、环境可视化信息；其中，所述信道特征包括以下至少一种信息：信道环境类型指示、信道模型指示、信道模型；所述环境可视化信息包括以下至少一种信息：环境中采集的图像、深度图片、点云数据或三维图片；
    所述通信装置设计参数包括以下至少一种信息：用户行为画像、星座图设计器回报参数；其中，所述用户行为画像包括以下至少一种信息：所述第一通信装置的位置分布、所述第一通信装置服务类型分布、所述第一通信装置移动性分布、所述第一通信装置的码率分布、所述第一通信装置的射频链路硬件参数分布；所述星座图设计器回报参数包括以下至少一种信息：所述第一通信装置反馈的性能、星座图设计器计算得到的性能、或用于评估星座图性能的公式。
  13. 如权利要求11所述的方法，其特征在于，所述第二通信装置根据所述星座图设计参数，将所述第一星座图更新为所述第二星座图包括：
    所述第二通信装置将所述星座图设计参数输入到星座图设计器中；
    所述第二通信装置基于所述星座图设计器，将所述第一星座图更新为所述第二星座图。
  14. 如权利要求9-13任一项所述的方法，其特征在于，所述第二通信装置采用所述第二星座图进行通信之前，还包括：
    所述第二通信装置将所述第二星座图变换为第三星座图，所述第三星座图为预设的星座图中与所述第二星座图最接近的星座图。
  15. 如权利要求9-14任一项所述的方法，其特征在于，所述第二通信装置采用所述第二星座图进行通信之后，还包括：
    所述第二通信装置发送指示信息，所述指示信息用于指示采用回退机制，所述回退机制用于指示将所述第二星座图变换为所述第一星座图；或者
    所述第二通信装置接收第一请求消息，所述第一请求消息用于请求采用回退机制，所述回退机制用于指示将所述第二星座图变换为所述第一星座图。
  16. 如权利要求9-15任一项所述的方法，其特征在于，还包括：
    所述第二通信装置保存所述星座图设计参数与所述第二星座图的对应关系。
  17. 如权利要求16所述的方法，其特征在于，还包括：
    所述第二通信装置根据所述星座图设计参数，在所述对应关系中查找所述星座图设计参数对应的所述第二星座图。
  18. 一种通信装置，其特征在于，包括处理单元和收发单元；
    所述处理单元，用于确定星座图设计参数；
    所述收发单元，用于发送所述星座图设计参数，所述星座图设计参数包括通信场景设计参数和通信装置设计参数；接收第二星座图的信息，所述第二星座图对应于所述星座图设计参数；采用所述第二星座图进行通信。
  19. 如权利要求18所述的装置，其特征在于，所述收发单元，还用于在发送星座图设计参数之前，采用第一星座图进行通信。
  20. 如权利要求19所述的装置，其特征在于，所述处理单元，还用于在所述收发单元采用所述第二星座图进行通信之前，将所述第一星座图更新为所述第二星座图，所述第一星座图与所述第二星座图不同。
  21. 如权利要求18-20任一项所述的装置，其特征在于，
    所述通信场景设计参数包括以下至少一种信息：信道特征、环境可视化信息；其中，所述信道特征包括以下至少一种信息：信道环境类型指示、信道模型指示、信道模型；所述环境可视化信息包括以下至少一种信息：环境中采集的图像、深度图片、点云数据或三维图片；
    所述通信装置设计参数包括以下至少一种信息：用户行为画像、星座图设计器回报参数；其中，所述用户行为画像包括以下至少一种信息：所述第一通信装置的位置分布、所述第一通信装置服务类型分布、所述第一通信装置移动性分布、所述第一通信装置的码率分布、所述第一通信装置的射频链路硬件参数分布；所述星座图设计器回报参数包括以下至少一种信息：所述第一通信装置反馈的性能、星座图设计器计算得到的性能、或用于评估星座图性能的公式。
  22. 如权利要求18-21任一项所述的装置，其特征在于，所述处理单元，还用于在所述收发单元接收所述第二星座图的信息之后，将所述第二星座图变换为第三星座图，所述第三星座图为预设的星座图中与所述第二星座图最接近的星座图。
  23. 如权利要求19-22任一项所述的装置，其特征在于，所述收发单元，还用于在采用所述第二星座图进行通信之后，接收指示信息，所述指示信息用于指示采用回退机制，所述回退机制用于指示将所述第二星座图变换为所述第一星座图；或者发送第一请求消息，所述第一请求消息用于请求采用回退机制，所述回退机制用于指示将所述第二星座图变换为所述第一星座图。
  24. 如权利要求18-23任一项所述的装置，其特征在于，所述处理单元，还用于保存所述星座图设计参数与所述第二星座图的对应关系。
  25. 如权利要求24所述的装置，其特征在于，所述处理单元，还用于根据所述星座图设计参数，在所述对应关系中查找所述星座图设计参数对应的所述第二星座图。
  26. 一种通信装置，其特征在于，包括：处理单元和收发单元；
    所述收发单元，用于接收星座图设计参数，所述星座图设计参数包括通信场景设计参数和通信装置设计参数；
    所述处理单元，用于确定所述星座图设计参数，并确定所述第二星座图，所述第二星座图对应于所述星座图设计参数；
    所述收发单元，还用于发送所述第二星座图的信息；采用所述第二星座图进行通信。
  27. 如权利要求26所述的装置，其特征在于，所述收发单元，还用于在接收星座图设计参数之前，采用第一星座图进行通信。
  28. 如权利要求27所述的装置，其特征在于，所述处理单元，还用于在所述收发单元发送所述第二星座图的信息之前，根据所述星座图设计参数，将所述第一星座图更新为所述第二星座图，所述第一星座图与所述第二星座图不同。
  29. 如权利要求26-28任一项所述的装置，其特征在于，
    所述通信场景设计参数包括以下至少一种信息：信道特征、环境可视化信息；其中，所述信道特征包括以下至少一种信息：信道环境类型指示、信道模型指示、信道模型；所述环境可视化信息包括以下至少一种信息：环境中采集的图像、深度图片、点云数据或三维图片；
    所述通信装置设计参数包括以下至少一种信息：用户行为画像、星座图设计器回报参数；其中，所述用户行为画像包括以下至少一种信息：所述第一通信装置的位置分布、所述第一通信装置服务类型分布、所述第一通信装置移动性分布、所述第一通信装置的码率分布、所述第一通信装置的射频链路硬件参数分布；所述星座图设计器回报参数包括以下至少一种信息：所述第一通信装置反馈的性能、星座图设计器计算得到的性能、或用于评估星座图性能的公式。
  30. 如权利要求28所述的装置，其特征在于，所述处理单元，具体用于将所述星座图设计参数输入到星座图设计器中；基于所述星座图设计器，将所述第一星座图更新为所述第二星座图。
  31. 如权利要求26-30任一项所述的装置，其特征在于，所述处理单元，还用于将所述第二星座图变换为第三星座图，所述第三星座图为预设的星座图中与所述第二星座图最接近的星座图。
  32. 如权利要求26-31任一项所述的装置，其特征在于，所述收发单元，还用于在采用所述第二星座图进行通信之后，发送指示信息，所述指示信息用于指示采用回退机制，所述回退机制用于指示将所述第二星座图变换为所述第一星座图；或者接收第一请求消息，所述第一请求消息用于请求采用回退机制，所述回退机制用于指示将所述第二星座图变换为所述第一星座图。
  33. 如权利要求26-32任一项所述的装置，其特征在于，所述处理单元，还用于保存所述星座图设计参数与所述第二星座图的对应关系。
  34. 如权利要求33所述的装置，其特征在于，所述处理单元，还用于根据所述星座图设计参数，在所述对应关系中查找所述星座图设计参数对应的所述第二星座图。
  35. 一种通信装置，其特征在于，所述装置包括：处理器和存储器；所述处理器和所述存储器之间电耦合；
    所述存储器，用于存储计算机程序指令；
    所述处理器，用于执行所述存储器中的部分或者全部计算机程序指令，当所述部分或者全部计算机程序指令被执行时，以实现如权利要求1-8任一项所述的方法，或者实现如权利要求9-17任一项所述的方法。
  36. 一种计算机可读存储介质，其特征在于，所述计算机存储介质中存储有计算机可读指令，当计算机读取并执行所述计算机可读指令时，使得计算机执行如权利要求1-8任一项所述的方法，或者如权利要求9-17任一项所述的方法。
  37. 一种芯片，其特征在于，包括：逻辑电路和输入输出接口，所述输入输出接口用于接收代码指令或信息，所述逻辑电路用于执行所述代码指令或根据所述信息，以执行如权利要求1-8任一项所述的方法，或者如权利要求9-17任一项所述的方法。
  38. 一种通信系统，其特征在于，包括如权利要求18-25任一项所述的通信装置，和如权利要求26-34任一项所述的通信装置。
  39. 一种计算机程序产品，其特征在于，所述计算机程序产品包括：计算机程序，当所述计算机程序在计算机上运行时，使得计算机执行如权利要求1-8任一项所述的方法，或者如权利要求9-17任一项所述的方法。
PCT/CN2021/114246 2020-08-25 2021-08-24 一种通信方法及装置 WO2022042523A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
EP21860358.7A EP4192086A4 (en) 2020-08-25 2021-08-24 COMMUNICATION METHOD AND APPARATUS
BR112023003355A BR112023003355A2 (pt) 2020-08-25 2021-08-24 Método e aparelho de comunicação
US18/173,221 US20230198826A1 (en) 2020-08-25 2023-02-23 Communication method and apparatus

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010864940.0 2020-08-25
CN202010864940.0A CN114125917A (zh) 2020-08-25 2020-08-25 一种通信方法及装置

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US18/173,221 Continuation US20230198826A1 (en) 2020-08-25 2023-02-23 Communication method and apparatus

Publications (1)

Publication Number Publication Date
WO2022042523A1 true WO2022042523A1 (zh) 2022-03-03

Family

ID=80352694

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/114246 WO2022042523A1 (zh) 2020-08-25 2021-08-24 一种通信方法及装置

Country Status (5)

Country Link
US (1) US20230198826A1 (zh)
EP (1) EP4192086A4 (zh)
CN (1) CN114125917A (zh)
BR (1) BR112023003355A2 (zh)
WO (1) WO2022042523A1 (zh)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2017133635A1 (zh) * 2016-02-04 2017-08-10 中兴通讯股份有限公司 信号处理方法及装置
CN107222448A (zh) * 2017-05-18 2017-09-29 清华大学 一种星座图优化方法及系统
CN107332799A (zh) * 2017-07-03 2017-11-07 电子科技大学 用于索引调制ofdm系统的星座图设计方法
WO2018032268A1 (zh) * 2016-08-15 2018-02-22 华为技术有限公司 一种目标星座图的确定方法、数据发送方法及装置
CN108366036A (zh) * 2018-01-31 2018-08-03 东南大学 一种面向稀疏码多址接入系统的调制码本设计方法

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150163085A1 (en) * 2012-07-09 2015-06-11 Sony Corporation Coding and modulation apparatus using non-uniform constellation
WO2022271634A1 (en) * 2021-06-21 2022-12-29 Idac Holdings, Inc. Methods, procedures, appartuses and systems for data-driven wireless transmit/receive unit specific symbol modulation
WO2023004541A1 (en) * 2021-07-26 2023-02-02 Telefonaktiebolaget Lm Ericsson (Publ) Methods and apparatuses for adaptation of communication parameter

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2017133635A1 (zh) * 2016-02-04 2017-08-10 中兴通讯股份有限公司 信号处理方法及装置
WO2018032268A1 (zh) * 2016-08-15 2018-02-22 华为技术有限公司 一种目标星座图的确定方法、数据发送方法及装置
CN107222448A (zh) * 2017-05-18 2017-09-29 清华大学 一种星座图优化方法及系统
CN107332799A (zh) * 2017-07-03 2017-11-07 电子科技大学 用于索引调制ofdm系统的星座图设计方法
CN108366036A (zh) * 2018-01-31 2018-08-03 东南大学 一种面向稀疏码多址接入系统的调制码本设计方法

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
KRISHNAN RAJET; GRAELL I AMAT ALEXANDRE; ERIKSSON THOMAS; COLAVOLPE GIULIO: "Constellation Optimization in the Presence of Strong Phase Noise", IEEE TRANSACTIONS ON COMMUNICATIONS, IEEE SERVICE CENTER, PISCATAWAY, NJ. USA., vol. 61, no. 12, 1 December 2013 (2013-12-01), PISCATAWAY, NJ. USA. , pages 5056 - 5066, XP011534886, ISSN: 0090-6778, DOI: 10.1109/TCOMM.2013.102313.130131 *
See also references of EP4192086A4 *

Also Published As

Publication number Publication date
CN114125917A (zh) 2022-03-01
EP4192086A4 (en) 2024-02-28
EP4192086A1 (en) 2023-06-07
US20230198826A1 (en) 2023-06-22
BR112023003355A2 (pt) 2023-04-04

Similar Documents

Publication Publication Date Title
CN102656927B (zh) 多跳网络中的发射功率控制
WO2020125454A1 (zh) 一种信息处理方法、系统及装置
CN103609058A (zh) 用于千兆赫以下频带中的无线通信的范围扩展的系统和方法
CN104584325A (zh) 更新波束方向图表格
CN105637772A (zh) 用于信道状态信息反馈的方法和装置
CN105493606A (zh) 用于多用户上行链路的方法和装置
WO2016154968A1 (zh) 编码方法、装置、基站和用户设备
CN112054863A (zh) 一种通信方法及装置
CN104221411A (zh) 用于向网络以信号形式发送无线设备的能力的装置和方法
WO2022094778A1 (zh) 多输入多输出mimo系统的检测方法和装置
CN107404378B (zh) 一种数据传输方法及装置
CN108781454B (zh) 比特块大小确定方法及设备
Salama et al. Deep reinforcement learning based algorithm for symbiotic radio iot throughput optimization in 6g network
WO2022042523A1 (zh) 一种通信方法及装置
CN114189318A (zh) 数据传输方法和装置
US20230004839A1 (en) Model coordination method and apparatus
Park et al. Spatial capacity of LTE-based V2V communication
WO2022022516A1 (zh) 无线通信的方法和装置
CN106922023B (zh) 一种数据传输方法、设备和系统
WO2023207783A1 (zh) 一种通信方法、装置及系统
US20230421286A1 (en) Communication method and apparatus
WO2023179577A1 (zh) 一种通信方法及相关装置
WO2023226992A1 (zh) 通信的方法和装置
US20230042213A1 (en) Methods and systems for optimizing computation of log-likelihood ratio (llr) for decoding modulated symbols
CN113746775B (zh) 一种信号发送方法、信号接收方法与相关装置

Legal Events

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

Ref document number: 21860358

Country of ref document: EP

Kind code of ref document: A1

REG Reference to national code

Ref country code: BR

Ref legal event code: B01A

Ref document number: 112023003355

Country of ref document: BR

ENP Entry into the national phase

Ref document number: 2021860358

Country of ref document: EP

Effective date: 20230303

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 112023003355

Country of ref document: BR

Kind code of ref document: A2

Effective date: 20230223