WO2023125458A1 - 通信方法、装置及相关设备 - Google Patents

通信方法、装置及相关设备 Download PDF

Info

Publication number
WO2023125458A1
WO2023125458A1 PCT/CN2022/142110 CN2022142110W WO2023125458A1 WO 2023125458 A1 WO2023125458 A1 WO 2023125458A1 CN 2022142110 W CN2022142110 W CN 2022142110W WO 2023125458 A1 WO2023125458 A1 WO 2023125458A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
model
function
case
output
Prior art date
Application number
PCT/CN2022/142110
Other languages
English (en)
French (fr)
Inventor
杨昂
孙鹏
Original Assignee
维沃移动通信有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 维沃移动通信有限公司 filed Critical 维沃移动通信有限公司
Publication of WO2023125458A1 publication Critical patent/WO2023125458A1/zh

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/16Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using machine learning or artificial intelligence

Definitions

  • the present application belongs to the technical field of communication, and in particular relates to a communication method, device and related equipment.
  • AI Artificial Intelligence
  • Embodiments of the present application provide a communication method, device, and related equipment, which can solve the problem of poor performance of an AI model in an existing communication process.
  • a communication method includes:
  • the first terminal obtains first information, and the first information is used to indicate at least one of the following: the function of the artificial intelligence AI model, the input information of the AI model, and the output information of the AI model;
  • the first end uses an AI model to perform a communication operation based on the first information.
  • a communication device including:
  • An acquisition module configured to acquire first information, where the first information is used to indicate at least one of the following: the function of the artificial intelligence AI model, the input information of the AI model, and the output information of the AI model;
  • An execution module configured to use an AI model to execute a communication operation based on the first information.
  • a terminal in a third aspect, includes a processor and a memory, the memory stores programs or instructions that can run on the processor, and when the programs or instructions are executed by the processor, the following The steps of the communication method in one aspect.
  • a terminal including a processor and a communication interface, wherein the processor is configured to obtain first information, and based on the first information, use an AI model to perform a communication operation; the first information uses Indicates at least one of the following: the function of the artificial intelligence AI model, the input information of the AI model, and the output information of the AI model.
  • a network-side device in a fifth aspect, includes a processor and a memory, the memory stores programs or instructions that can run on the processor, and the programs or instructions are executed by the processor implement the steps of the communication method as described in the first aspect.
  • a network side device including a processor and a communication interface, wherein the processor is configured to obtain first information, and based on the first information, use an AI model to perform a communication operation; the first The information is used to indicate at least one of the following: the function of the artificial intelligence AI model, the input information of the AI model, and the output information of the AI model.
  • a readable storage medium where a program or an instruction is stored on the readable storage medium, and when the program or instruction is executed by a processor, the steps of the communication method according to the first aspect are implemented.
  • a chip in an eighth aspect, includes a processor and a communication interface, the communication interface is coupled to the processor, and the processor is used to run programs or instructions to realize the communication as described in the first aspect method.
  • a computer program/program product is provided, the computer program/program product is stored in a storage medium, and the computer program/program product is executed by at least one processor to implement the method described in the first aspect The steps of the communication method.
  • the function of the AI model, the input information of the AI model, and the output information of the AI model that the first terminal will use in the communication operation are clarified, so as to avoid the occurrence of unclear AI model functions or AI model input information and output information.
  • Information errors lead to poor performance of the AI model, so as to ensure that the AI model has better performance during the communication process, and also ensure that the first end can have better communication performance.
  • FIG. 1 is a block diagram of a wireless communication system to which an embodiment of the present application is applicable;
  • FIG. 2 is a flowchart of a communication method provided by an embodiment of the present application.
  • FIG. 3 is a structural diagram of a communication device provided in an embodiment of the present application.
  • FIG. 4 is a structural diagram of a communication device provided by an embodiment of the present application.
  • FIG. 5 is a structural diagram of a terminal provided in an embodiment of the present application.
  • Fig. 6 is a structural diagram of a network side device provided by an embodiment of the present application.
  • first, second and the like in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific sequence or sequence. It is to be understood that the terms so used are interchangeable under appropriate circumstances such that the embodiments of the application are capable of operation in sequences other than those illustrated or described herein and that "first" and “second” distinguish objects. It is usually one category, and the number of objects is not limited. For example, there may be one or more first objects.
  • “and/or” in the description and claims means at least one of the connected objects, and the character “/” generally means that the related objects are an "or” relationship.
  • LTE Long Term Evolution
  • LTE-Advanced LTE-Advanced
  • LTE-A Long Term Evolution-Advanced
  • CDMA Code Division Multiple Access
  • TDMA Time Division Multiple Access
  • FDMA Frequency Division Multiple Access
  • OFDMA Orthogonal Frequency Division Multiple Access
  • SC-FDMA Single-carrier Frequency Division Multiple Access
  • system and “network” in the embodiments of the present application are often used interchangeably, and the described technology can be used for the above-mentioned system and radio technology, and can also be used for other systems and radio technologies.
  • the following description describes the New Radio (New Radio, NR) system for example purposes, and uses NR terminology in most of the following descriptions, but these techniques can also be applied to applications other than NR system applications, such as the 6th generation (6th Generation , 6G) communication system.
  • 6G 6th generation
  • Fig. 1 shows a block diagram of a wireless communication system to which the embodiment of the present application is applicable.
  • the wireless communication system includes a terminal 11 and a network side device 12 .
  • the terminal 11 can be a mobile phone, a tablet computer (Tablet Personal Computer), a laptop computer (Laptop Computer) or a notebook computer, a personal digital assistant (Personal Digital Assistant, PDA), a palmtop computer, a netbook, a super mobile personal computer (Ultra-Mobile Personal Computer, UMPC), mobile Internet device (Mobile Internet Device, MID), augmented reality (Augmented Reality, AR) / virtual reality (Virtual Reality, VR) equipment, robot, wearable device (Wearable Device, WD), vehicle equipment (Vehicle User Equipment, VUE), pedestrian terminal (Personal User Equipment, PUE), smart home (home equipment with wireless communication functions, such as refrigerators, TVs, washing machines or furniture, etc.), game consoles, personal computers (Personal Computer, PC), teller machines or self-service machines
  • the network side device 12 may include an access network device or a core network device, wherein the access network device may also be called a radio access network device, a radio access network (Radio Access Network, RAN), a radio access network function, or a wireless access network unit.
  • RAN Radio Access Network
  • the access network device may include a base station, a wireless local area network (Wireless Local Area Network, WLAN) access point, or a wireless fidelity (Wireless Fidelity, WiFi) node, etc.
  • the base station may be called a node B, an evolved node B (eNB), Access point, base transceiver station (Base Transceiver Station, BTS), radio base station, radio transceiver, basic service set (Basic Service Set, BSS), extended service set (Extended Service Set, ESS), home B node, home Evolved Node B, Transmitting Receiving Point (TRP) or some other appropriate term in the field, as long as the same technical effect is achieved, the base station is not limited to specific technical terms.
  • eNB evolved node B
  • BTS base transceiver station
  • BSS basic service set
  • Extended Service Set Extended Service Set
  • ESS Extended Service Set
  • home B node home Evolved Node B
  • TRP Transmitting Receiving Point
  • Core network equipment may include but not limited to at least one of the following: core network nodes, core network functions, mobility management entities (Mobility Management Entity, MME), access mobility management functions (Access and Mobility Management Function, AMF), session management functions (Session Management Function, SMF), User Plane Function (UPF), Policy Control Function (Policy Control Function, PCF), Policy and Charging Rules Function (PCRF), edge application service Discovery function (Edge Application Server Discovery Function, EASDF), unified data management (Unified Data Management, UDM), unified data storage (Unified Data Repository, UDR), home subscriber server (Home Subscriber Server, HSS), centralized network configuration ( Centralized network configuration, CNC), network storage function (Network Repository Function, NRF), network exposure function (Network Exposure Function, NEF), local NEF (Local NEF, or L-NEF), binding
  • MME mobility management entities
  • AMF Access and Mobility Management Function
  • SMF Session Management Function
  • UPF User Plane Function
  • Policy Control Function Policy Control Function
  • FIG. 2 is a flowchart of a communication method provided by an embodiment of the present application. As shown in Figure 2, the communication method includes the following steps:
  • Step 201 the first terminal acquires first information, the first information is used to indicate at least one of the following: the function of the AI model, the input information of the AI model, and the output information of the AI model.
  • the first information is indication information sent by the second end, or, the first information may also be information predetermined by a protocol.
  • the first end receives first information sent by the second end, the first information is used to indicate the function of the AI model,
  • the first end is one of the terminal and the network side device
  • the second end is the other of the terminal and the network side device
  • the terminal sends the first information to the network side device
  • the network side device may send the first information to the terminal.
  • the first end and the second end are different nodes of the terminal, for example, the first node of the terminal can send the first information to the second node, or the second node can send the first information to the first node .
  • the first end and the second end are different nodes of the network side equipment, for example, the third node of the network side equipment can send the first information to the fourth node, or the fourth node can send the first information to the third node Send the first message.
  • the first information is used to indicate at least one of the following: functions of the AI model, input information of the AI model, and output information of the AI model.
  • functions of the AI model functions of the AI model
  • input information of the AI model input information of the AI model
  • output information of the AI model there may be an association relationship between the function of the AI model, the input information of the AI model, and the output information of the AI model.
  • the first information is only used to indicate the function of the AI model, and while determining the function of the AI model through the first information, the first end can also determine the input information corresponding to the AI model based on the association relationship and output information; or, the first information is only used to indicate the input information of the AI model, and the first end can determine the function of the AI model and the corresponding output information of the AI model based on the input information of the AI model; or, the The first information is only used to indicate the output information of the AI model, and the first end can determine the function of the AI model and the corresponding input information of the AI model based on the output information of the AI model. Understandably, the first information may also be two or three items used to indicate the function of the AI model, the input information of the AI model, and the output information of the AI model, which will not be listed here.
  • Step 202 The first end uses an AI model to perform a communication operation based on the first information.
  • the first terminal after obtaining the first information, can determine the AI model to be used based on the content indicated by the first information, and can also determine the input information and output of the AI model information, the first end uses the AI model to perform communication operations.
  • the communication operation may refer to inputting the input information of the AI model into the AI model, and/or processing the information output by the AI model to conform to the format of the output information of the AI model or related requirements.
  • the first end is a terminal
  • the second end is a network-side device.
  • the network-side device can perform communication operations based on the AI model, and the network-side device also determines the function of the AI model, the input information of the AI model, and the AI model.
  • the network side device may send the first information to the terminal to indicate the function of the AI model, the input information of the AI model, and the output information of the AI model; further, the terminal based on the first information, that is, Able to determine the AI model to be used, and perform information input to the AI model according to the input information of the AI model, and perform information output to the AI model according to the output information of the AI model, so that the terminal is using the AI model
  • the functions of the AI model and the input information and output information of the AI model can be aligned with the network-side equipment, so as to ensure the communication performance between the terminal and the network-side equipment, and avoid AI model function unknown or AI model
  • the problem of input information and output information error ensures the performance of the AI model in the communication process.
  • the function of the AI model, the input information of the AI model, and the output information of the AI model that the first terminal will use in the communication operation are clarified, so as to avoid the occurrence of unclear functions of the AI model or input information and output information of the AI model Errors lead to poor performance of the AI model, so as to ensure that the AI model has better performance during the communication process, and also ensure that the first end can have better communication performance.
  • the functions of the AI model include at least one of the following: used for channel state information (Channel State Information, CSI) encoding, used for CSI decoding, used for positioning, used for channel estimation, used for tracking reference signals (Tracking Reference Signal, TRS) estimation, for phase tracking reference information (Phase Tracking Reference Signal, PTRS) estimation, for beam management, for calibration signal, for digital pre-distortion (Digital Pre-Distortion, DPD).
  • CSI Channel State Information
  • TRS Track Reference Signal
  • PTRS Phase Tracking Reference Signal
  • the first information is used to indicate that the function of the AI model is for CSI coding, and the first end can use the AI model for CSI coding to perform communication operations based on the first information; or, the first information
  • the function of the AI model indicated by the first information may also include other possible situations, which are not listed here.
  • the first information may also be used to indicate at least one of the following:
  • the input information of the AI model is a CSI reference signal
  • the input information of the AI model is at least one of a precoding matrix indicator (Precoding Matrix Indicator, PMI) and CSI coding information;
  • PMI Precoding Matrix Indicator
  • the input information of the AI model is sounding reference signal (Sounding Reference Signal, SRS), positioning reference signal (Positioning Reference Signal, PRS) and CSI reference signal at least one;
  • the input information of the AI model is a reference signal
  • the input information of the AI model is TRS;
  • the input information of the AI model is PTRS
  • the input information of the AI model is the channel quality of the reference signal
  • the input information of the AI model is a signal to be calibrated
  • the input information of the AI model is an original signal.
  • the original signal has not been processed by digital pre-distortion, and after passing through the amplifier, it may be affected by the non-linear characteristics of the amplifier.
  • the function of the AI model is for CSI coding
  • the AI model that the first end needs to use is the AI model for CSI coding
  • the first information is used to indicate the
  • the input information of the AI model is the CSI reference signal. It should be noted that the function of the AI model being used for CSI coding may also be indicated by the first information.
  • the first information is used to indicate that the input information of the AI model is a reference signal, such as a CSI reference signal, a demodulation reference signal (Demodulation Reference Signal, DMRS), SRS and other reference signals.
  • a reference signal such as a CSI reference signal, a demodulation reference signal (Demodulation Reference Signal, DMRS), SRS and other reference signals.
  • the input information of the AI model is the channel quality of various reference signals, such as synchronization signals and physical broadcast channel signal blocks (Synchronization Signal and PBCH block, SSB), CSI-RS, SRS and other reference signal reference signal received power (Reference Signal Received Power, RSRP), reference signal received quality (Reference Signal Received Quality, RSRQ), signal to interference plus noise ratio (Signal-to -noise and Interference Ratio, SINR), etc.
  • the channel quality also includes the beam quality of layer 1 and/or the beam quality of layer 3.
  • the AI model can also be determined based on the function of the AI model.
  • the input information of the AI model indicated by the first information may also be other possible situations, which will not be repeated here.
  • the first information may also be used to indicate at least one of the following:
  • the output information of the AI model is at least one of PMI and CSI coding information
  • the output information of the AI model is at least one of CSI and channel related information obtained through CSI processing;
  • the output information of the AI model is at least one of position information and position-related information in channel information;
  • the output information of the AI model is estimated channel information
  • the output information of the AI model is time information
  • the output information of the AI model is at least one of phase information and phase tracking information
  • the output information of the AI model is at least one of the selected beam and the beam quality of the selected beam;
  • the output information of the AI model is a calibrated signal
  • the output information of the AI model is a pre-distorted signal.
  • the first information is used to indicate that the output information of the AI model is CSI and/or channel related information obtained through CSI processing.
  • the CSI may be a channel matrix, precoding information, channel quality, rank, etc.
  • the channel related information obtained through the CSI processing may be multi-user precoding information, etc.
  • the first information is used to indicate that the output information of the AI model is position information and/or position-related information in channel information.
  • the AI model output information can be timing time/timing (Timing), time of arrival (Timing of arrival, TOA), round-trip time (Round-Trip Time, RTT), observed time difference of arrival (Observed Time Difference of Arrival, OTDOA), Time Difference of Arrival (TDOA), Angle of Arrival (AOA), Angle of Departure (AOD), etc.
  • the output information of the AI model may be the current The beam quality of the beam and/or the beam quality of possibly selected future beams.
  • the first information is used to indicate that the output information of the AI model is a pre-distorted signal to combat the nonlinearity of other functional modules (such as power amplifier modules) distortion.
  • the format used by the first information to indicate the target information includes at least one of the following:
  • the contents of multiple fields in the target information are arranged in a preset order
  • the contents of multiple fields in the target information are converted into corresponding matrices, and the dimensions of the matrix match the number of fields.
  • the target information is the input information of the AI model or the output information of the AI model
  • the content of the domain includes at least one of the following: resources of the domain, signals of the domain, and information of the domain.
  • the target information is the input information of the AI model.
  • the input information of the AI model includes resources in multiple domains (such as time domain, frequency domain, and air domain, etc.), for example, it includes two resources in the time domain and two resources in the frequency domain.
  • the resources, the resources of the two domains included in the input information of the AI model may be arranged in a preset order, and the preset order may be the order of the cycle levels of different domains; for example, the input information of the AI model includes The first resource and the second resource in the time domain, and the first resource and the second resource in the frequency domain, then the arrangement order of each resource in the input information of the AI model is: the first resource in the time domain is the first resource in the frequency domain A resource, a second resource in the frequency domain on the first resource in the time domain, a first resource in the frequency domain on the second resource in the time domain, and a second resource in the frequency domain on the second resource in the time domain.
  • the target information is the output information of the AI model
  • the output information of the AI model includes the contents of multiple fields
  • the contents of the multiple fields in the output information of the AI model may also be in a preset order Arrangement, as mentioned above, is arranged in the order of the cycle levels of different domains, and will not be listed here.
  • the arrangement order of the contents of multiple fields in the input information of the same AI model may be the same as the arrangement order of the contents of the multiple fields in the output information of the AI model, so as to ensure that the input information of the same AI model
  • the format aligns or matches the format of the output information.
  • the first information is further used to indicate that the contents of the multiple fields in the target information are converted into corresponding matrices, where the dimensions of the matrix are the same as those of the fields , and then determine which dimension in the multiple dimensions the domain in the target information belongs to through the dimension of the matrix.
  • the target information is the input information of the AI model. If the input information of the AI model includes two domains, the input information of the AI model can be converted into a two-dimensional matrix format, and the two dimensions of the matrix correspond to the two domains respectively. Domain; as another example, the target information is the output information of the AI model, if the output information of the AI model includes three domains, the output information of the AI model can be converted into a three-dimensional matrix, and the three dimensions of the matrix correspond to the three domains respectively. area.
  • the input information of the AI model and/or the output information of the AI model include the content of multiple domains
  • the input information of the AI model and/or the output information of the AI model The input format and/or output format of the content of multiple domains is defined.
  • the first information is used to indicate input information corresponding to at least one input interface of the AI model; and/or, in the AI model When the model includes multiple output interfaces, the first information is used to indicate output information corresponding to at least one output interface of the AI model.
  • the first information may be used to indicate the input information corresponding to each interface of the AI model; or, when there is no information input to the input interface of the AI model, the The first information may not indicate the input information of these input interfaces; or, the first information indicates that at least one input interface of the AI model has no input information, or the first information indicates that at least one of the AI models is closed input interface.
  • one input interface may correspond to one type of input information, or one input interface may correspond to multiple types of input information, or multiple input interfaces may correspond to the same type of input information.
  • the first information may also be used to indicate the output information corresponding to each output interface of the AI model; or, there is no information output at the output interface of the AI model In some cases, the first information may not indicate the output information of these output interfaces; or, the first information indicates that at least one output interface of the AI model has no output information, or the first information indicates that the AI model is turned off. At least one output interface of the model.
  • one output interface may correspond to one type of output information, or one output interface may correspond to multiple types of output information, or multiple output interfaces may correspond to the same type of output information.
  • the first information when the first information is used to indicate the input information of the AI model, the first information is also used to indicate whether the input information of the AI model needs preprocessing; and/or ,
  • the first information is used to indicate the output information of the AI model
  • the first information is also used to indicate whether the output information of the AI model requires post-processing.
  • the pre-processing may refer to the processing of the input information before input into the AI model
  • the post-processing may refer to the processing of the output information of the AI model after output.
  • the pre-processing or the post-processing includes at least one of the following: transform domain processing, power processing, amplitude processing and phase processing.
  • the transform domain processing may include Fourier transform, fast Fourier transform (Fast Fourier Transform, FFT), discrete Fourier transform, fractional Fourier transform, short-term Fourier transform, Laplace transform (Laplace transform), Z-transform, wavelet transform, discrete wavelet transform, continuous wavelet transform; and can also include inverse Fourier transform, inverse fast Fourier transform, inverse discrete Fourier transform, inverse fractional Fourier transform Transform, Inverse Short-Time Fourier Transform, Inverse Laplace Transform (Inverse Laplace Transform), Inverse Z Transform, Inverse Wavelet Transform, Inverse Discrete Wavelet Transform, Inverse Continuous Wavelet Transform.
  • FFT fast Fourier transform
  • discrete Fourier transform fractional Fourier transform
  • Laplace transform Laplace transform
  • Z-transform wavelet transform, discrete wavelet transform, continuous wavelet transform
  • the power processing may be to divide the input information of the AI model and/or the output information of the AI model into resource groups, and process the total power of each resource group as a fixed value.
  • the input information of the AI model is processed with the Orthogonal Frequency Division Multiplex (OFDM) symbol in the time domain.
  • OFDM Orthogonal Frequency Division Multiplex
  • the power processing can also be performed by using one of the divided resource groups as the target resource group, and the total power of other resource groups Power normalization processing; for example, the total power of each resource group after power processing is equal to the total power of the resource group before processing divided by the total power of the target resource group.
  • the manner of the amplitude processing may refer to the power processing.
  • the phase processing may be phase normalization processing.
  • the input information of the AI model and/or the output information of the AI model are divided into resource groups, and one of the divided resource groups is used as the target resource group, and the phases of other resource groups are normalized based on the target resource group .
  • the input information of the AI model and/or the output information of the AI model further include preset information, and the preset information includes at least one of the following: channel environment information and device information.
  • the channel environment information includes timing information, signal-to-noise ratio, noise information, interference information, movement performance, movement speed, movement direction, beam quality, channel quality, position of the first end, and the like.
  • the device information may include terminal type, terminal identity (Identity, ID), cell ID, terminal state, etc.; wherein, the terminal state includes idle state, inactive state, and connected state.
  • the preset information may be indicated separately from the first information.
  • the method further includes the following steps:
  • the first terminal acquires second information, where the second information is used to indicate at least one of the following: the preset information and a format of the preset information.
  • the first end may acquire the second information before acquiring the first information, or acquire the second information after acquiring the first information, or acquire simultaneously.
  • the second information is used to indicate the preset information and/or the format of the preset information.
  • the format of the preset information may refer to the specific type of preset information, for example, the second information is used to indicate that the format of the preset information is beam quality, then the input information of the AI model and/or the output of the AI model Information may also include beam quality.
  • the method also includes at least one of the following:
  • the first terminal Before the first terminal performs information input to the AI model based on the first information, applying the preset information to the input information of the AI model;
  • the preset information is applied to the output information of the AI model.
  • the first terminal when it obtains the first information, it can also determine the AI model to be used, the function of the AI model, the input information of the AI model, and the AI model At least one of the output information of the AI model, the first end applies the channel environment information and/or device information to the input information of the AI model before executing the information input to the AI model, and then executes the information input to the AI model Input, for example, the input information input to the AI model also includes channel environment information and/or device information.
  • the preset information to the input information of the AI model in advance, it is possible to avoid affecting the format of the output information of the AI model.
  • the first end may also apply the preset information to the output information of the AI model, for example, the output information of the AI model includes the preset information; and then The output information of the AI model including the preset information is sent to the next functional module, so as to avoid affecting the format of the output information of the AI model.
  • the input information of the AI model and/or the output information of the AI model may also have partial information missing.
  • the method further includes:
  • the first end performs at least one of the following:
  • the target information is at least one of the input information of the AI model and the output information of the AI model; when the target information is the input information of the AI model, the adjacent information is the input information adjacent to the input information of the AI model, and when the target information is the output information of the AI model, the adjacent information is the output adjacent to the output information of the AI model information.
  • the missing part of the input information of the AI model may be supplemented based on a default value, for example, the default missing part be a certain constant; or, it is also possible to use the input information adjacent to the input information of the AI model to supplement the missing part, for example, to supplement the missing part based on the previous input information of the input information of the AI model Supplement; or, it is also possible to use multiple input information adjacent to the input information of the AI model to supplement the missing part, such as calculating the linear average of the first three input information of the input information of the AI model, The missing parts are supplemented based on this linear average.
  • the missing part may also be supplemented based on the above manner, and details are not described here.
  • the first information obtained by the first end further includes at least one of a calibration set and an error of the calibration set, and before performing the communication operation using the AI model, the method further includes:
  • the first end processes the target information based on the first information, and the processed target information satisfies the error of the calibration set;
  • the target information is at least one of input information of the AI model and output information of the AI model.
  • the calibration set is a set of input information and output information for information format calibration, where the input information for information format calibration corresponds to the format of the input information of the AI model, and/or the output of information format calibration There is a one-to-one correspondence between the information and the format of the output information of the AI model.
  • the AI model is used for CSI coding
  • the input information format for information format calibration is a 2-dimensional matrix
  • the first dimension is the air domain
  • 32 elements represent 32 base station antennas
  • the second dimension is the frequency domain
  • 13 elements represent 13 subbands
  • the input information of the AI model is the CSI reference signal
  • the format is a 2-dimensional matrix
  • the first dimension is 32 elements in the air domain
  • the second dimension is 13 elements in the frequency domain
  • the formats of the two correspond one-to-one.
  • the first end can determine at least one of the calibration set and the error of the calibration set based on the first information.
  • the first end can perform arbitrary processing on the input information of the AI model and/or the output information of the AI model, and the processed
  • the error of the input information of the AI model and/or the output information of the AI model is smaller than the error of the calibration set.
  • the first end processes the input information of the AI model based on the first information After inputting the AI model, and obtaining the output information of the AI model, comparing the output information of the AI model with the corresponding output information in the calibration set to obtain an error, if the error is less than or equal to the preset threshold value, then It is considered that the processing of the input information of the AI model by the first end satisfies the error of the calibration set, and if the error is greater than the preset threshold value, it is considered that the processing of the input information of the AI model by the first end is The error that does not satisfy the calibration set.
  • the performing a communication operation using an AI model includes:
  • a communication operation is performed on the processed target information by using an AI model, and the information output by the AI model satisfies the error of the calibration set.
  • the communication operation is that the first terminal performs any processing on the input information of the AI model and then inputs the AI model, and the information output by the AI model satisfies The error of the calibration set; if the target information is the output information of the AI model, the communication operation is that the first end performs arbitrary processing on the output information of the AI model, and outputs the processed output information of the AI model as the AI model information, and the information output by the AI model satisfies the error of the calibration set.
  • the first information can indicate the calibration set and/or the error of the calibration set, and then the first end can communicate with the input information of the AI model and/or the output information of the AI model during the communication process using the AI model. Perform arbitrary processing to ensure that the processed AI model input information and/or AI model output information meet the errors of the calibration set.
  • the communication method provided in the embodiment of the present application may be executed by a communication device.
  • the communication device provided in the embodiment of the present application is described by taking the communication device executing the communication method as an example.
  • FIG. 3 is a structural diagram of a communication device provided in an embodiment of the present application. As shown in FIG. 3, the communication device 300 includes:
  • An acquisition module 301 configured to acquire first information, where the first information is used to indicate at least one of the following: the function of the artificial intelligence AI model, the input information of the AI model, and the output information of the AI model;
  • the execution module 302 is configured to use an AI model to execute a communication operation based on the first information.
  • the functions of the AI model include at least one of the following: for channel state information CSI coding, for CSI decoding, for positioning, for channel estimation, for tracking reference signal TRS estimation, for phase Tracking reference information PTRS estimation, used for beam management, used for calibration signal, used for digital predistortion DPD.
  • the first information is used to indicate at least one of the following:
  • the input information of the AI model is a CSI reference signal
  • the input information of the AI model is at least one of precoding matrix indication PMI and CSI coding information
  • the input information of the AI model is at least one of a sounding reference signal SRS, a positioning reference signal PRS, and a CSI reference signal;
  • the input information of the AI model is a reference signal
  • the input information of the AI model is TRS;
  • the input information of the AI model is PTRS
  • the input information of the AI model is the channel quality of the reference signal
  • the input information of the AI model is a signal to be calibrated
  • the input information of the AI model is the original signal.
  • the first information is used to indicate at least one of the following:
  • the output information of the AI model is at least one of PMI and CSI coding information
  • the output information of the AI model is at least one of CSI and channel related information obtained through CSI processing;
  • the output information of the AI model is at least one of position information and position-related information in channel information;
  • the output information of the AI model is estimated channel information
  • the output information of the AI model is time information
  • the output information of the AI model is at least one of phase information and phase tracking information
  • the output information of the AI model is at least one of the selected beam and the beam quality of the selected beam;
  • the output information of the AI model is a calibrated signal
  • the output information of the AI model is a pre-distorted signal.
  • the format used by the first information to indicate the target information includes at least one of the following:
  • the contents of multiple fields in the target information are arranged in a preset order
  • the contents of multiple fields in the target information are converted into corresponding matrices, and the dimensions of the matrix match the number of fields.
  • the target information is the input information of the AI model or the output information of the AI model
  • the content of the domain includes at least one of the following: resources of the domain, signals of the domain, and information of the domain.
  • the first information is used to indicate input information corresponding to at least one input interface of the AI model.
  • the first information is used to indicate output information corresponding to at least one output interface of the AI model.
  • the first information when used to indicate the input information of the AI model, the first information is also used to indicate whether the input information of the AI model needs preprocessing; and/or,
  • the first information is used to indicate the output information of the AI model
  • the first information is also used to indicate whether the output information of the AI model requires post-processing.
  • the pre-processing or the post-processing includes at least one of the following: transform domain processing, power processing, magnitude processing and phase processing.
  • the input information of the AI model and/or the output information of the AI model further include preset information, and the preset information includes at least one of the following: channel environment information and device information.
  • the obtaining module 301 is also used for:
  • Acquire second information where the second information is used to indicate at least one of the following: the preset information and a format of the preset information.
  • the executing module 302 is also configured to execute at least one of the following:
  • the device Before the device performs information input to the AI model based on the first information, applying the preset information to the input information of the AI model;
  • the preset information is applied to the output information of the AI model.
  • the executing module 302 is further configured to execute at least one of the following:
  • the target information is at least one of the input information of the AI model and the output information of the AI model; when the target information is the input information of the AI model, the adjacent information is the input information adjacent to the input information of the AI model, and when the target information is the output information of the AI model, the adjacent information is the output adjacent to the output information of the AI model information.
  • the first information further includes at least one of a calibration set and an error of the calibration set
  • the executing module 302 is further configured to:
  • the target information is at least one of input information of the AI model and output information of the AI model.
  • the executing module 302 is further configured to:
  • a communication operation is performed on the processed target information by using an AI model, and the information output by the AI model satisfies the error of the calibration set.
  • the first information is indication information sent by the second end, or the first information is information stipulated in a protocol.
  • the apparatus is one of the terminal and the network-side device, and the second end is the other of the terminal and the network-side device; or,
  • the device and the second end are different nodes of a terminal; or,
  • the device and the second end are different nodes of the network side equipment.
  • the function of the AI model, the input information of the AI model, and the output information of the AI model that the communication device 300 will use in the communication operation are clarified, so as to avoid the occurrence of unclear functions of the AI model or input information and output information of the AI model. Errors lead to poor performance of the AI model, so as to ensure that the AI model has better performance during the communication process, and also ensure that the communication device 300 can have better communication performance.
  • the communication apparatus 300 in the embodiment of the present application may be an electronic device, such as an electronic device with an operating system, or a component in the electronic device, such as an integrated circuit or a chip.
  • the electronic device may be a terminal, or other devices other than the terminal.
  • the terminal may include, but not limited to, the types of terminal 11 listed above, and other devices may be servers, Network Attached Storage (NAS), etc., which are not specifically limited in this embodiment of the present application.
  • NAS Network Attached Storage
  • the communication device 300 provided in the embodiment of the present application can implement various processes implemented in the embodiment of the communication method shown in FIG. 2 and achieve the same technical effect. To avoid repetition, details are not repeated here.
  • this embodiment of the present application also provides a communication device 400, including a processor 401 and a memory 402, and the memory 402 stores programs or instructions that can run on the processor 401, such as
  • the communication device 400 is a terminal
  • the program or instruction is executed by the processor 401
  • each step of the communication method embodiment described in FIG. 2 can be implemented, and the same technical effect can be achieved.
  • the communication device 400 is a network-side device
  • the program or instruction is executed by the processor 401
  • the various steps of the above-mentioned communication method embodiment described in FIG. 2 can be implemented, and the same technical effect can be achieved. To avoid repetition, details are not repeated here. .
  • An embodiment of the present application further provides a terminal, including a processor and a communication interface, where the processor is configured to acquire first information, and based on the first information, use an AI model to perform a communication operation.
  • This terminal embodiment corresponds to the above-mentioned terminal-side method embodiment, and each implementation process and implementation mode of the above-mentioned method embodiment can be applied to this terminal embodiment, and can achieve the same technical effect.
  • FIG. 5 is a schematic diagram of a hardware structure of a terminal implementing an embodiment of the present application.
  • the terminal 500 includes, but is not limited to: a radio frequency unit 501, a network module 502, an audio output unit 503, an input unit 504, a sensor 505, a display unit 506, a user input unit 507, an interface unit 508, a memory 509, and a processor 510. At least some parts.
  • the terminal 500 can also include a power supply (such as a battery) for supplying power to various components, and the power supply can be logically connected to the processor 510 through the power management system, so as to manage charging, discharging, and power consumption through the power management system. Management and other functions.
  • a power supply such as a battery
  • the terminal structure shown in FIG. 5 does not constitute a limitation on the terminal, and the terminal may include more or fewer components than shown in the figure, or combine certain components, or arrange different components, which will not be repeated here.
  • the input unit 504 may include a graphics processing unit (Graphics Processing Unit, GPU) 5041 and a microphone 5042, and the graphics processor 5041 is used in a video capture mode or an image capture mode by an image capture device (such as the image data of the still picture or video obtained by the camera) for processing.
  • the display unit 506 may include a display panel 5061, and the display panel 5061 may be configured in the form of a liquid crystal display, an organic light emitting diode, or the like.
  • the user input unit 507 includes at least one of a touch panel 5071 and other input devices 5072 .
  • the touch panel 5071 is also called a touch screen.
  • the touch panel 5071 may include two parts, a touch detection device and a touch controller.
  • Other input devices 5072 may include, but are not limited to, physical keyboards, function keys (such as volume control keys, switch keys, etc.), trackballs, mice, and joysticks, which will not be repeated here.
  • the radio frequency unit 501 may transmit the downlink data from the network side device to the processor 510 for processing after receiving it; in addition, the radio frequency unit 501 may send uplink data to the network side device.
  • the radio frequency unit 501 includes, but is not limited to, an antenna, an amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, and the like.
  • the memory 509 can be used to store software programs or instructions as well as various data.
  • the memory 509 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data, wherein the first storage area may store an operating system, an application program or instructions required by at least one function (such as a sound playing function, image playback function, etc.), etc.
  • memory 509 may include volatile memory or nonvolatile memory, or, memory 509 may include both volatile and nonvolatile memory.
  • the non-volatile memory can be read-only memory (Read-Only Memory, ROM), programmable read-only memory (Programmable ROM, PROM), erasable programmable read-only memory (Erasable PROM, EPROM), electronically programmable Erase Programmable Read-Only Memory (Electrically EPROM, EEPROM) or Flash.
  • ROM Read-Only Memory
  • PROM programmable read-only memory
  • Erasable PROM Erasable PROM
  • EPROM erasable programmable read-only memory
  • Electrical EPROM Electrical EPROM
  • EEPROM electronically programmable Erase Programmable Read-Only Memory
  • Volatile memory can be random access memory (Random Access Memory, RAM), static random access memory (Static RAM, SRAM), dynamic random access memory (Dynamic RAM, DRAM), synchronous dynamic random access memory (Synchronous DRAM, SDRAM), double data rate synchronous dynamic random access memory (Double Data Rate SDRAM, DDRSDRAM), enhanced synchronous dynamic random access memory (Enhanced SDRAM, ESDRAM), synchronous connection dynamic random access memory (Synch link DRAM , SLDRAM) and Direct Memory Bus Random Access Memory (Direct Rambus RAM, DRRAM).
  • RAM Random Access Memory
  • SRAM static random access memory
  • DRAM dynamic random access memory
  • DRAM synchronous dynamic random access memory
  • SDRAM double data rate synchronous dynamic random access memory
  • Double Data Rate SDRAM Double Data Rate SDRAM
  • DDRSDRAM double data rate synchronous dynamic random access memory
  • Enhanced SDRAM, ESDRAM enhanced synchronous dynamic random access memory
  • Synch link DRAM , SLDRAM
  • Direct Memory Bus Random Access Memory Direct Rambus
  • the processor 510 may include one or more processing units; optionally, the processor 510 integrates an application processor and a modem processor, wherein the application processor mainly processes operations related to the operating system, user interface, and application programs, etc., Modem processors mainly process wireless communication signals, such as baseband processors. It can be understood that the foregoing modem processor may not be integrated into the processor 510 .
  • processor 510 is used for:
  • first information is used to indicate at least one of the following: the function of the artificial intelligence AI model, the input information of the AI model, and the output information of the AI model;
  • a communication operation is performed using an AI model.
  • the functions of the AI model include at least one of the following: for channel state information CSI coding, for CSI decoding, for positioning, for channel estimation, for tracking reference signal TRS estimation, for phase Tracking reference information PTRS estimation, used for beam management, used for calibration signal, used for digital predistortion DPD.
  • the first information is used to indicate at least one of the following:
  • the input information of the AI model is a CSI reference signal
  • the input information of the AI model is at least one of precoding matrix indication PMI and CSI coding information
  • the input information of the AI model is at least one of a sounding reference signal SRS, a positioning reference signal PRS, and a CSI reference signal;
  • the input information of the AI model is a reference signal
  • the input information of the AI model is TRS;
  • the input information of the AI model is PTRS
  • the input information of the AI model is the channel quality of the reference signal
  • the input information of the AI model is a signal to be calibrated
  • the input information of the AI model is an original signal.
  • the first information is used to indicate at least one of the following:
  • the output information of the AI model is at least one of PMI and CSI coding information
  • the output information of the AI model is at least one of CSI and channel related information obtained through CSI processing;
  • the output information of the AI model is at least one of position information and position-related information in channel information;
  • the output information of the AI model is estimated channel information
  • the output information of the AI model is time information
  • the output information of the AI model is at least one of phase information and phase tracking information
  • the output information of the AI model is at least one of the selected beam and the beam quality of the selected beam;
  • the output information of the AI model is a calibrated signal
  • the output information of the AI model is a pre-distorted signal.
  • the format used by the first information to indicate the target information includes at least one of the following:
  • the contents of multiple fields in the target information are arranged in a preset order
  • the contents of multiple fields in the target information are converted into corresponding matrices, and the dimensions of the matrix match the number of fields.
  • the target information is the input information of the AI model or the output information of the AI model
  • the content of the domain includes at least one of the following: resources of the domain, signals of the domain, and information of the domain.
  • the first information is used to indicate input information corresponding to at least one input interface of the AI model.
  • the first information is used to indicate output information corresponding to at least one output interface of the AI model.
  • the first information when used to indicate the input information of the AI model, the first information is also used to indicate whether the input information of the AI model needs preprocessing; and/or,
  • the first information is used to indicate the output information of the AI model
  • the first information is also used to indicate whether the output information of the AI model requires post-processing.
  • the pre-processing or the post-processing includes at least one of the following: transform domain processing, power processing, amplitude processing and phase processing.
  • the input information of the AI model and/or the output information of the AI model further include preset information, and the preset information includes at least one of the following: channel environment information and device information.
  • processor 510 is further configured to:
  • Acquire second information where the second information is used to indicate at least one of the following: the preset information and a format of the preset information.
  • processor 510 is further configured to perform at least one of the following:
  • the terminal 500 performs information input to the AI model based on the first information, applying the preset information to the input information of the AI model;
  • the preset information is applied to the output information of the AI model.
  • the processor 510 is further configured to perform at least one of the following:
  • the target information is at least one of the input information of the AI model and the output information of the AI model; when the target information is the input information of the AI model, the adjacent information is the input information adjacent to the input information of the AI model, and when the target information is the output information of the AI model, the adjacent information is the output adjacent to the output information of the AI model information.
  • the first information further includes at least one of a calibration set and an error of the calibration set
  • the processor 510 is further configured to:
  • the target information is at least one of input information of the AI model and output information of the AI model.
  • processor 510 is further configured to:
  • a communication operation is performed on the processed target information by using an AI model, and the information output by the AI model satisfies the error of the calibration set.
  • the first information is indication information sent by the second end, or the first information is information stipulated in a protocol.
  • the second end is a network side device; or,
  • the second end is a terminal node.
  • the function of the AI model, the input information of the AI model, and the output information of the AI model that the terminal will use in the communication operation are clarified, so as to avoid the occurrence of unclear functions of the AI model or errors in the input information and output information of the AI model.
  • the problem of poor performance of the AI model is caused to ensure that the AI model has better performance during the communication process, and also ensures that the terminal can have better communication performance.
  • the embodiment of the present application also provides a network side device, including a processor and a communication interface, the processor is used to obtain the first information, and based on the first information, use the AI model to perform a communication operation; the first information is used to indicate At least one of the following: the function of the artificial intelligence AI model, the input information of the AI model, and the output information of the AI model.
  • the network-side device embodiment corresponds to the above-mentioned method embodiment described in FIG. 2 , and each implementation process and implementation mode of the above-mentioned method embodiment can be applied to this network-side device embodiment, and can achieve the same technical effect.
  • the embodiment of the present application also provides a network side device.
  • the network side device 600 includes: an antenna 61 , a radio frequency device 62 , a baseband device 63 , a processor 64 and a memory 65 .
  • the antenna 61 is connected to the radio frequency device 62 .
  • the radio frequency device 62 receives information through the antenna 61, and sends the received information to the baseband device 63 for processing.
  • the baseband device 63 processes the information to be sent and sends it to the radio frequency device 62
  • the radio frequency device 62 processes the received information and sends it out through the antenna 61 .
  • the method performed by the network side device in the above embodiments may be implemented in the baseband device 63, where the baseband device 63 includes a baseband processor.
  • the baseband device 63 can include at least one baseband board, for example, a plurality of chips are arranged on the baseband board, as shown in FIG.
  • the program executes the network device operations shown in the above method embodiments.
  • the network side device may also include a network interface 66, such as a common public radio interface (Common Public Radio Interface, CPRI).
  • a network interface 66 such as a common public radio interface (Common Public Radio Interface, CPRI).
  • CPRI Common Public Radio Interface
  • the network-side device 600 in the embodiment of the present application further includes: instructions or programs stored in the memory 65 and operable on the processor 64, and the processor 64 calls the instructions or programs in the memory 65 to execute the various programs shown in FIG.
  • the method of module execution achieves the same technical effect, so in order to avoid repetition, it is not repeated here.
  • the embodiment of the present application also provides a readable storage medium, where a program or an instruction is stored on the readable storage medium, and when the program or instruction is executed by the processor, each process of the above-mentioned communication method embodiment described in FIG. 2 is implemented, and The same technical effect can be achieved, so in order to avoid repetition, details will not be repeated here.
  • the processor is the processor in the terminal described in the foregoing embodiments.
  • the readable storage medium includes computer readable storage medium, such as computer read-only memory, random access memory, magnetic disk or optical disk, and the like.
  • the embodiment of the present application further provides a chip, the chip includes a processor and a communication interface, the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the communication method described in Figure 2 above
  • the various processes of the embodiment can achieve the same technical effect, so in order to avoid repetition, details are not repeated here.
  • the chip mentioned in the embodiment of the present application may also be called a system-on-chip, a system-on-chip, a system-on-a-chip, or a system-on-a-chip.
  • the embodiment of the present application further provides a computer program/program product, the computer program/program product is stored in a storage medium, and the computer program/program product is executed by at least one processor to realize the communication described in FIG. 2 above.
  • Each process of the method embodiment can achieve the same technical effect, and will not be repeated here to avoid repetition.
  • the term “comprising”, “comprising” or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article or apparatus comprising a set of elements includes not only those elements, It also includes other elements not expressly listed, or elements inherent in the process, method, article, or device. Without further limitations, an element defined by the phrase “comprising a " does not preclude the presence of additional identical elements in the process, method, article, or apparatus comprising that element.
  • the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved. Functions are performed, for example, the described methods may be performed in an order different from that described, and various steps may also be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.
  • the methods of the above embodiments can be implemented by means of software plus a necessary general-purpose hardware platform, and of course also by hardware, but in many cases the former is better implementation.
  • the technical solution of the present application can be embodied in the form of computer software products, which are stored in a storage medium (such as ROM/RAM, magnetic disk, etc.) , CD-ROM), including several instructions to make a terminal (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) execute the methods described in the various embodiments of the present application.

Landscapes

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

Abstract

本申请公开了一种通信方法、装置及相关设备,属于通信技术领域,本申请实施例的通信方法包括:第一端获取第一信息,所述第一信息用于指示如下至少一项:人工智能AI模型的功能、AI模型的输入信息和AI模型的输出信息;所述第一端基于所述第一信息,使用AI模型执行通信操作。

Description

通信方法、装置及相关设备
相关申请的交叉引用
本申请主张在2021年12月31日在中国提交的中国专利申请No.202111672336.9的优先权,其全部内容通过引用包含于此。
技术领域
本申请属于通信技术领域,具体涉及一种通信方法、装置及相关设备。
背景技术
人工智能(Artificial Intelligence,AI)是研究和开发用于模拟、延伸、扩展人的智能的理论、方法、技术及应用***的一门新的技术科学,受到人们的广泛关注,针对AI的应用也越来越广泛。目前,在通信技术领域,对于AI模型的用途、输入格式和输出格式尚未明确,造成在通信过程中AI模型性能较差。
发明内容
本申请实施例提供一种通信方法、装置及相关设备,能够解决现有通信过程中AI模型性能差的问题。
第一方面,提供了一种通信方法,该方法包括:
第一端获取第一信息,所述第一信息用于指示如下至少一项:人工智能AI模型的功能、AI模型的输入信息和AI模型的输出信息;
所述第一端基于所述第一信息,使用AI模型执行通信操作。
第二方面,提供了一种通信装置,包括:
获取模块,用于获取第一信息,所述第一信息用于指示如下至少一项:人工智能AI模型的功能、AI模型的输入信息和AI模型的输出信息;
执行模块,用于基于所述第一信息,使用AI模型执行通信操作。
第三方面,提供了一种终端,该终端包括处理器和存储器,所述存储器存储可在所述处理器上运行的程序或指令,所述程序或指令被所述处理器执 行时实现如第一方面所述的通信方法的步骤。
第四方面,提供了一种终端,包括处理器及通信接口,其中,所述处理器用于获取第一信息,并基于所述第一信息,使用AI模型执行通信操作;所述第一信息用于指示如下至少一项:人工智能AI模型的功能、AI模型的输入信息和AI模型的输出信息。
第五方面,提供了一种网络侧设备,该网络侧设备包括处理器和存储器,所述存储器存储可在所述处理器上运行的程序或指令,所述程序或指令被所述处理器执行时实现如第一方面所述的通信方法的步骤。
第六方面,提供了一种网络侧设备,包括处理器及通信接口,其中,所述处理器用于获取第一信息,并基于所述第一信息,使用AI模型执行通信操作;所述第一信息用于指示如下至少一项:人工智能AI模型的功能、AI模型的输入信息和AI模型的输出信息。
第七方面,提供了一种可读存储介质,所述可读存储介质上存储程序或指令,所述程序或指令被处理器执行时实现如第一方面所述的通信方法的步骤。
第八方面,提供了一种芯片,所述芯片包括处理器和通信接口,所述通信接口和所述处理器耦合,所述处理器用于运行程序或指令,实现如第一方面所述的通信方法。
第九方面,提供了一种计算机程序/程序产品,所述计算机程序/程序产品被存储在存储介质中,所述计算机程序/程序产品被至少一个处理器执行以实现如第一方面所述的通信方法的步骤。
在本申请实施例中,明确了第一端在通信操作中会使用到的AI模型的功能、AI模型的输入信息和AI模型的输出信息,避免出现AI模型功能不明或者AI模型输入信息、输出信息错误而导致AI模型性能差的问题,以确保通信过程中AI模型具有较好的性能,也保障了第一端能够具有较好的通信性能。
附图说明
图1是本申请实施例可应用的一种无线通信***的框图;
图2是本申请实施例提供的一种通信方法的流程图;
图3是本申请实施例提供的一种通信装置的结构图;
图4是本申请实施例提供的一种通信设备的结构图;
图5是本申请实施例提供的一种终端的结构图;
图6是本申请实施例提供的一种网络侧设备的结构图。
具体实施方式
下面将结合本申请实施例中的附图,对本申请实施例中的技术方案进行清楚描述,显然,所描述的实施例是本申请一部分实施例,而不是全部的实施例。基于本申请中的实施例,本领域普通技术人员所获得的所有其他实施例,都属于本申请保护的范围。
本申请的说明书和权利要求书中的术语“第一”、“第二”等是用于区别类似的对象,而不用于描述特定的顺序或先后次序。应该理解这样使用的术语在适当情况下可以互换,以便本申请的实施例能够以除了在这里图示或描述的那些以外的顺序实施,且“第一”、“第二”所区别的对象通常为一类,并不限定对象的个数,例如第一对象可以是一个,也可以是多个。此外,说明书以及权利要求中“和/或”表示所连接对象的至少其中之一,字符“/”一般表示前后关联对象是一种“或”的关系。
值得指出的是,本申请实施例所描述的技术不限于长期演进型(Long Term Evolution,LTE)/LTE的演进(LTE-Advanced,LTE-A)***,还可用于其他无线通信***,诸如码分多址(Code Division Multiple Access,CDMA)、时分多址(Time Division Multiple Access,TDMA)、频分多址(Frequency Division Multiple Access,FDMA)、正交频分多址(Orthogonal Frequency Division Multiple Access,OFDMA)、单载波频分多址(Single-carrier Frequency Division Multiple Access,SC-FDMA)和其他***。本申请实施例中的术语“***”和“网络”常被可互换地使用,所描述的技术既可用于以上提及的***和无线电技术,也可用于其他***和无线电技术。以下描述出于示例目的描述了新空口(New Radio,NR)***,并且在以下大部分描述中使用NR术语,但是这些技术也可应用于NR***应用以外的应用,如第6代(6th Generation,6G)通信***。
图1示出本申请实施例可应用的一种无线通信***的框图。无线通信***包括终端11和网络侧设备12。其中,终端11可以是手机、平板电脑(Tablet Personal Computer)、膝上型电脑(Laptop Computer)或称为笔记本电脑、个人数字助理(Personal Digital Assistant,PDA)、掌上电脑、上网本、超级移动个人计算机(Ultra-Mobile Personal Computer,UMPC)、移动上网装置(Mobile Internet Device,MID)、增强现实(Augmented Reality,AR)/虚拟现实(Virtual Reality,VR)设备、机器人、可穿戴式设备(Wearable Device,WD)、车载设备(Vehicle User Equipment,VUE)、行人终端(Personal User Equipment,PUE)、智能家居(具有无线通信功能的家居设备,如冰箱、电视、洗衣机或者家具等)、游戏机、个人计算机(Personal Computer,PC)、柜员机或者自助机等终端侧设备,可穿戴式设备包括:智能手表、智能手环、智能耳机、智能眼镜、智能首饰(智能手镯、智能手链、智能戒指、智能项链、智能脚镯、智能脚链等)、智能腕带、智能服装等。需要说明的是,在本申请实施例并不限定终端11的具体类型。网络侧设备12可以包括接入网设备或核心网设备,其中,接入网设备也可以称为无线接入网设备、无线接入网(Radio Access Network,RAN)、无线接入网功能或无线接入网单元。接入网设备可以包括基站、无线局域网(Wireless Local Area Network,WLAN)接入点或无线保真技术(Wireless Fidelity,WiFi)节点等,基站可被称为节点B、演进节点B(eNB)、接入点、基收发机站(Base Transceiver Station,BTS)、无线电基站、无线电收发机、基本服务集(Basic Service Set,BSS)、扩展服务集(Extended Service Set,ESS)、家用B节点、家用演进型B节点、发送接收点(Transmitting Receiving Point,TRP)或所述领域中其他某个合适的术语,只要达到相同的技术效果,所述基站不限于特定技术词汇,需要说明的是,在本申请实施例中仅以NR***中的基站为例进行介绍,并不限定基站的具体类型。核心网设备可以包含但不限于如下至少一项:核心网节点、核心网功能、移动管理实体(Mobility Management Entity,MME)、接入移动管理功能(Access and Mobility Management Function,AMF)、会话管理功能(Session Management Function,SMF)、用户平面功能(User Plane Function,UPF)、策略控制功能(Policy Control Function,PCF)、策略与计费规则功能单元 (Policy and Charging Rules Function,PCRF)、边缘应用服务发现功能(Edge Application Server Discovery Function,EASDF)、统一数据管理(Unified Data Management,UDM),统一数据仓储(Unified Data Repository,UDR)、归属用户服务器(Home Subscriber Server,HSS)、集中式网络配置(Centralized network configuration,CNC)、网络存储功能(Network Repository Function,NRF),网络开放功能(Network Exposure Function,NEF)、本地NEF(Local NEF,或L-NEF)、绑定支持功能(Binding Support Function,BSF)、应用功能(Application Function,AF)等。需要说明的是,在本申请实施例中仅以NR***中的核心网设备为例进行介绍,并不限定核心网设备的具体类型。
下面结合附图,通过一些实施例及其应用场景对本申请实施例提供的通信方法进行详细地说明。
请参照图2,图2是本申请实施例提供的一种通信方法的流程图。如图2所示,所述通信方法包括以下步骤:
步骤201、第一端获取第一信息,所述第一信息用于指示如下至少一项:AI模型的功能、AI模型的输入信息和AI模型的输出信息。
可选地,所述第一信息为第二端发送的指示信息,或者,所述第一信息也可以为协议预定的信息。例如,所述第一端接收第二端发送的第一信息,所述第一信息用于指示AI模型的功能,
可选地,所述第一端为终端和网络侧设备中的一者,所述第二端为终端和网络侧设备中的另一者,例如第一端为终端,第二端为网络侧设备,或者,第一端为网络侧设备,第二端为终端。例如,终端向网络侧设备发送第一信息,或者也可以是网络侧设备向终端发送第一信息。
或者,所述第一端和所述第二端为终端的不同节点,例如终端的第一节点能够向第二节点发送第一信息,或者也可以是第二节点向第一节点发送第一信息。
或者,所述第一端和所述第二端为网络侧设备的不同节点,例如网络侧设备的第三节点能够向第四节点发送第一信息,或者也可以是第四节点向第三节点发送第一信息。
本申请实施例中,所述第一信息用于指示如下至少一项:AI模型的功能、 AI模型的输入信息和AI模型的输出信息。可选地,所述AI模型的功能与AI模型的输入信息和AI模型的输出信息之间可以是存在关联关系。例如,所述第一信息仅用于指示AI模型的功能,第一端在通过所述第一信息确定AI模型的功能的同时,还能够基于所述关联关系确定所述AI模型对应的输入信息和输出信息;或者,所述第一信息仅用于指示AI模型的输入信息,第一端基于所述AI模型的输入信息可以确定AI模型的功能以及对应的AI模型的输出信息;或者,所述第一信息仅用于指示AI模型的输出信息,第一端基于所述AI模型的输出信息可以确定AI模型的功能以及对应的AI模型的输入信息。可以理解地,所述第一信息还可以是用于指示AI模型的功能、AI模型的输入信息和AI模型的输出信息中的二项或三项,此处不再一一列举。
步骤202、所述第一端基于所述第一信息,使用AI模型执行通信操作。
本申请实施例中,第一端在获取到所述第一信息后,基于所述第一信息所指示的内容,能够确定需要使用的AI模型,还可以确定所述AI模型的输入信息和输出信息,则第一端使用所述AI模型进行通信操作。
需要说明地,所述通信操作可以是指将所述AI模型的输入信息输入所述AI模型,和/或对所述AI模型输出的信息进行处理,以符合所述AI模型的输出信息的格式或相关要求。例如,第一端为终端,第二端为网络侧设备,网络侧设备可以是基于AI模型来执行通信操作,则网络侧设备也就确定了AI模型的功能、AI模型的输入信息和AI模型的输出信息,网络侧设备可以是向终端发送第一信息,以指示所述AI模型的功能、AI模型的输入信息和AI模型的输出信息;进一步地,终端基于所述第一信息,也就能够确定所需要使用的AI模型,并能够按照所述AI模型的输入信息执行对AI模型的信息输入,以及按照所述AI模型的输出信息执行对AI模型的信息输出,使得终端在使用AI模型执行通信操作的过程中,能够与网络侧设备对齐AI模型的功能以及AI模型的输入信息和输出信息,从而以确保终端和网络侧设备之间的通信性能,避免出现AI模型功能不明或者AI模型输入信息、输出信息错误的问题,保障在通信过程中AI模型的性能。
本申请实施例中,明确了第一端在通信操作中会使用到的AI模型的功能、AI模型的输入信息和AI模型的输出信息,避免出现AI模型功能不明或者 AI模型输入信息、输出信息错误而导致AI模型性能差的问题,以确保通信过程中AI模型具有较好的性能,也保障了第一端能够具有较好的通信性能。
可选地,所述AI模型的功能包括如下至少一项:用于信道状态信息(Channel State Information,CSI)编码、用于CSI译码、用于定位、用于信道估计、用于跟踪参考信号(Tracking Reference Signal,TRS)估计、用于相位跟踪参考信息(Phase Tracking Reference Signal,PTRS)估计、用于波束管理、用于校准信号、用于数字预失真(Digital Pre-Distortion,DPD)。
例如,所述第一信息用于指示AI模型的功能为用于CSI编码,第一端基于所述第一信息也就能够使用用于CSI编码的AI模型来执行通信操作;或者,第一信息用于指示AI模型的功能为用于CSI编码和用于信道估计,则第一端基于所述第一信息,使用用于CSI编码的AI模型和用于信道估计的AI模型来执行通信操作。可选地,所述第一信息用于指示的AI模型的功能还可以包括其他的可能情况,此处不做一一列举。
可选地,所述第一信息还可以用于指示如下至少一项:
在所述AI模型的功能为用于CSI编码的情况下,所述AI模型的输入信息为CSI参考信号;
在所述AI模型的功能为用于CSI译码的情况下,所述AI模型的输入信息为预编码矩阵指示(Precoding Matrix Indicator,PMI)和CSI编码信息中的至少一项;
在所述AI模型的功能为用于定位的情况下,所述AI模型的输入信息为探测参考信号(Sounding Reference Signal,SRS)、定位参考信号(Positioning Reference Signal,PRS)和CSI参考信号中的至少一种;
在所述AI模型的功能为用于信道估计的情况下,所述AI模型的输入信息为参考信号;
在所述AI模型的功能为用于TRS估计的情况下,所述AI模型的输入信息为TRS;
在所述AI模型的功能为用于PTRS的情况下,所述AI模型的输入信息为PTRS;
在所述AI模型的功能为用于波束管理的情况下,所述AI模型的输入信 息为参考信号的信道质量;
在所述AI模型的功能为用于校准信号的情况下,所述AI模型的输入信息为待校准的信号;
在所述AI模型的功能为用于DPD的情况下,所述AI模型的输入信息为原始信号。其中,所述原始信号未经过数字预失真处理,经过放大器后,可能会受到放大器的非线性特性的影响。
示例性地,在所述AI模型的功能为用于CSI编码的情况下,也即第一端需要使用到的AI模型为用于CSI编码的AI模型,所述第一信息用于指示所述AI模型的输入信息为CSI参考信号。需要说明地,所述AI模型的功能为用于CSI编码也可以是通过第一信息指示。
又如,在所述AI模型的功能为用于信道估计的情况下,所述第一信息用于指示所述AI模型的输入信息为参考信号,例如CSI参考信号、解调参考信号(Demodulation Reference Signal,DMRS)、SRS等各类参考信号。
需要说明地,在所述AI模型的功能为用于波束管理的情况下,所述AI模型的输入信息为各类参考信号的信道质量,如同步信号和物理广播信道信号块(Synchronization Signal and PBCH block,SSB)、CSI-RS、SRS等参考信号的参考信号接收功率(Reference Signal Received Power,RSRP)、参考信号接收质量(Reference Signal Received Quality,RSRQ)、信号与干扰加噪声比(Signal-to-noise and Interference Ratio,SINR)等,所述信道质量还包括层1的波束质量和/或层3的波束质量。
可以理解地,AI模型的功能与所述AI模型的输入信息之间存在相应的关联关系,也即在确定了AI模型的功能的情况下,也能够基于所述AI模型的功能来确定该AI模型对应的输入信息。所述第一信息用于指示的AI模型的输入信息还可以是其他的可能情况,此处不做赘述。
可选地,所述第一信息还可以用于指示如下至少一项:
在所述AI模型的功能为用于CSI编码的情况下,所述AI模型的输出信息为PMI和CSI编码信息中的至少一项;
在所述AI模型的功能为用于CSI译码的情况下,所述AI模型的输出信息为CSI和通过CSI处理得到的信道相关信息中的至少一项;
在所述AI模型的功能为用于定位的情况下,所述AI模型的输出信息为位置信息和信道信息中与位置相关的信息中的至少一项;
在所述AI模型的功能为用于信道估计的情况下,所述AI模型的输出信息为估计的信道信息;
在所述AI模型的功能为用于TRS估计的情况下,所述AI模型的输出信息为时间信息;
在所述AI模型的功能为用于PTRS的情况下,所述AI模型的输出信息为相位信息和相位跟踪信息中的至少一项;
在所述AI模型的功能为用于波束管理的情况下,所述AI模型的输出信息为选择波束和所选波束的波束质量中的至少一项;
在所述AI模型的功能为用于校准信号的情况下,所述AI模型的输出信息为已校准的信号;
在所述AI模型的功能为用于DPD的情况下,所述AI模型的输出信息为经过预失真处理的信号。
例如,在所述AI模型的功能为用于CSI译码的情况下,所述第一信息用于指示AI模型的输出信息为CSI和/或通过CSI处理得到的信道相关信息。可选地,所述CSI可以是信道矩阵、预编码信息、信道质量、秩等,所述CSI处理得到的信道相关信息可以是多用户的预编码信息等。
又如,在所述AI模型的功能为用于定位的情况下,所述第一信息用于指示AI模型的输出信息为位置信息和/或信道信息中与位置相关的信息。例如,所述AI模型输出信息可以是计时时间/定时(Timing)、到达时间(Timing of arrival,TOA)、往返时间(Round-Trip Time,RTT)、观测的到达时差(Observed Time Difference of Arrival,OTDOA)、到达时差(Time Difference of Arrival,TDOA)、到达角度(Angle of arrival,AOA)、发射角度(Angle of departure,AOD)等。
需要说明地,在所述AI模型的功能为用于波束管理,第一信息用于指示的AI模型的输出信息包括所选波束的波束质量的情况下,所述AI模型的输出信息可以是当前波束的波束质量和/或可能选择的未来波束的波束质量。
其中,在所述AI模型的功能为用于DPD的情况下,第一信息用于指示 AI模型的输出信息为经过预失真处理的信号,以对抗其他功能模块(如功率放大器模块)的非线性失真。
本申请实施例中,在目标信息包括多个域的内容的情况下,所述第一信息用于指示所述目标信息的格式包括如下至少一项:
所述目标信息中的多个域的内容按照预设顺序排列;
所述目标信息中的多个域的内容转换为对应的矩阵,所述矩阵的维度与所述域的数量匹配。
其中,所述目标信息为所述AI模型的输入信息或所述AI模型的输出信息,所述域的内容包括如下至少一项:域的资源、域的信号和域的信息。
例如,所述目标信息为AI模型的输入信息,若AI模型的输入信息包括多个域(例如时域、频域、空域等)的资源,例如包括时域的两个资源以及频域的两个资源,则所述AI模型的输入信息包括的这两个域的资源可以是按照预设顺序排列,所述预设顺序可以是不同域的循环层级的顺序;例如,AI模型的输入信息包括时域的第一资源和第二资源,以及频域的第一资源和第二资源,则所述AI模型的输入信息中各个资源的排列顺序为:时域的第一资源上的频域第一资源、时域的第一资源上的频域第二资源、时域的第二资源上的频域第一资源、时域的第二资源上的频域第二资源。
需要说明地,在目标信息为AI模型的输出信息,AI模型的输出信息包括多个域的内容的情况下,所述AI模型的输出信息中的多个域的内容也可以是按照预设顺序排列,如上所述的按照不同域的循环层级的顺序排列,此处不再列举。可选地,同一AI模型的输入信息中的多个域的内容的排列顺序可以是与该AI模型的输出信息中的多个域的内容的排列顺序相同,以确保同一AI模型的输入信息的格式与输出信息的格式对齐或者说相匹配。
可选地,在目标信息包括多个域的内容的情况下,所述第一信息还用于指示所述目标信息中的多个域的内容转换为对应的矩阵,其中,矩阵的维度与域的数量匹配,进而通过矩阵的维度确定目标信息中的域属于多个维度中的哪一维度。
例如,目标信息为AI模型的输入信息,若AI模型的输入信息包括两个域,则AI模型的输入信息可以是转换为二维矩阵的格式,该矩阵的两个维度 分别对应所述两个域;又例如,目标信息为AI模型的输出信息,若AI模型的输出信息包括三个域,则AI模型的输出信息可以是转换为三维矩阵,该矩阵的三个维度分别对应所述三个域。
本申请实施例中,在AI模型的输入信息和/或AI模型的输出信息包括多个域的内容情况下,通过第一信息对所述AI模型的输入信息和/或AI模型的输出信息中多个域的内容的输入格式和/或输出格式进行了限定。
可选地,在所述AI模型包括多个输入接口的情况下,所述第一信息用于指示所述AI模型的至少一个所述输入接口对应的输入信息;和/或,在所述AI模型包括多个输出接口的情况下,所述第一信息用于指示所述AI模型的至少一个所述输出接口对应的输出信息。
例如,AI模型包括多个输入接口,则第一信息可以是用于指示所述AI模型的每一个接口对应的输入信息;或者,在所述AI模型的输入接口没有信息输入的情况下,所述第一信息可以不指示这些输入接口的输入信息;或者,所述第一信息指示所述AI模型的至少一个输入接口没有输入信息,或所述第一信息指示关闭所述AI模型的至少一个输入接口。可选地,一个所述输入接口可以是对应一种输入信息,或者,一个所述输入接口可以对应多种输入信息,或者,还可以是多个所述输入接口对应同一种输入信息。
示例性地,若AI模型包括多个输出接口,第一信息还可以是用于指示所述AI模型的每一个输出接口对应的输出信息;或者,在所述AI模型的输出接口没有信息输出的情况下,所述第一信息可以不指示这些输出接口的输出信息;或者,所述第一信息指示所述AI模型的至少一个输出接口没有输出信息,或所述第一信息指示关闭所述AI模型的至少一个输出接口。可选地,一个所述输出接口可以是对应一种输出信息,或者,一个所述输出接口对应多种输出信息,或者,还可以是多个输出接口对应同一种输出信息。
本申请实施例中,在所述第一信息用于指示所述AI模型的输入信息的情况下,所述第一信息还用于指示所述AI模型的输入信息是否需要预处理;和/或,
在所述第一信息用于指示所述AI模型的输出信息的情况下,所述第一信息还用于指示所述AI模型的输出信息是否需要后处理。
其中,所述预处理可以是指输入信息在输入AI模型之前进行的处理,所述后处理可以是指对AI模型的输出信息输出后进行的处理。
可选地,所述预处理或所述后处理包括如下至少一项:变换域处理、功率处理、幅度处理和相位处理。
其中,所述变换域处理可以包括傅里叶变换、快速傅里叶变换(Fast Fourier Transform,FFT)、离散傅里叶变换、分数傅里叶变换、短时距傅立叶变换、拉普拉斯变换(拉氏变换)、Z变换、小波变换、离散小波变换、连续小波变换;以及还可以包括傅里叶逆变换、快速傅里叶变换逆变换、离散傅里叶逆变换、分数傅里叶逆变换、短时距傅立叶逆变换、拉普拉斯逆变换(拉氏逆变换)、Z逆变换、小波逆变换、离散小波逆变换、连续小波逆变换。
可选地,所述功率处理可以是将AI模型的输入信息和/或AI模型的输出信息进行资源组划分,各资源组的总功率处理为固定数值。例如,以AI模型的输入信息为例,假设AI模型的输入信息包括时域和频域,以时域的正交频分复用(Orthogonal Frequency Division Multiplex,OFDM)符号对AI模型的输入信息进行划分,对划分后的每个OFDM符号上所有频域资源块(Resource Block,RB)或子带的总功率归一化处理为固定数值。
或者,在将AI模型的输入信息和/或AI模型的输出信息进行资源组划分后,功率处理也可以是以划分后的其中某个资源组作为目标资源组,其他各资源组的总功率进行功率归一化处理;例如,功率处理后的各资源组的总功率等于该资源组处理前的总功率除以目标资源组的总功率。
需要说明地,所述幅度处理的方式可以是参照所述功率处理。
可选地,所述相位处理可以是采用相位归一化处理。例如,将AI模型的输入信息和/或AI模型的输出信息进行资源组划分,以划分后的其中某个资源组作为目标资源组,其他各资源组的相位基于目标资源组进行归一化处理。
本申请实施例中,所述AI模型的输入信息和/或所述AI模型的输出信息还包括预设信息,所述预设信息包括如下至少一项:信道环境信息和设备信息。
可选地,所述信道环境信息包括定时信息、信噪比、噪声信息、干扰信息、移动性能、移动速度、移动方向、波束质量、信道质量、所述第一端的 位置等。
在所述第一端为终端的情况下,所述设备信息可以包括终端类型、终端身份(Identity,ID)、小区ID、终端状态等;其中,所述终端状态包括空闲态、非激活态和连接态。
可选地,所述预设信息可以是独立于第一信息单独指示。本申请实施例中,所述方法还包括如下步骤:
所述第一端获取第二信息,所述第二信息用于指示如下至少一项:所述预设信息和所述预设信息的格式。
示例性地,所述第一端可以是在获取第一信息之前获取所述第二信息,也可以是在获取第一信息之后获取所述第二信息,或者也可以是同时获取。其中,所述第二信息用于指示上述预设信息和/或预设信息的格式。所述预设信息的格式可以是指具体是哪一类预设信息,例如所述第二信息用于指示预设信息的格式为波束质量,则AI模型的输入信息和/或AI模型的输出信息还可以包括波束质量。
可选地,所述方法还包括如下至少一项:
在所述第一端基于所述第一信息对AI模型执行信息输入之前,将所述预设信息作用于所述AI模型的输入信息;
在所述第一端基于所述第一信息对AI模型执行信息输出之后,将所述预设信息作用于所述AI模型的输出信息。
本申请实施例中,第一端在获取到第一信息的情况下,也就能够确定所需要使用的AI模型,以及所述AI模型的功能、所述AI模型的输入信息和所述AI模型的输出信息中的至少一项,第一端在对所述AI模型执行信息输入之前,将信道环境信息和/或设备信息作用于所述AI模型的输入信息,然后再执行对AI模型的信息输入,例如输入AI模型的输入信息还包括信道环境信息和/或设备信息。通过将所述预设信息提前作用于AI模型的输入信息,能够避免影响AI模型的输出信息的格式。
示例性,第一端在对AI模型执行信息输出之后,还可以是将所述预设信息作用于所述AI模型的输出信息,例如所述AI模型的输出信息包括所述预设信息;而后将包括有所述预设信息的AI模型的输出信息发送给下一功能模 块,进而以避免影响AI模型的输出信息的格式。
本申请实施例中,AI模型的输入信息和/或AI模型的输出信息也可能存在缺失部分信息的情况。可选地,在目标信息存在缺失部分的情况下,所述第一端在执行第一操作之前,所述方法还包括:
所述第一端执行如下至少一项:
基于默认值对所述缺失部分进行补充;
基于所述目标信息的相邻信息对所缺失部分进行补充;
其中,所述目标信息为所述AI模型的输入信息和所述AI模型的输出信息中的至少一者;在所述目标信息为所述AI模型的输入信息的情况下,所述相邻信息为与所述AI模型的输入信息相邻的输入信息,在所述目标信息为所述AI模型的输出信息的情况下,所述相邻信息为与所述AI模型的输出信息相邻的输出信息。
例如,以目标信息为AI模型的输入信息为例,若所述AI模型的输入信息存在缺失部分,则可以是基于默认值对所述AI模型的输入信息的缺失部分进行补充,例如默认缺失部分为某个常数;或者,也可以是利用所述AI模型的输入信息相邻的输入信息对所述缺失部分进行补充,例如基于所述AI模型的输入信息的前一个输入信息对所述缺失部分进行补充;或者,还可以是利用所述AI模型的输入信息相邻的多个输入信息对所述缺失部分进行补充,例如计算所述AI模型的输入信息的前三个输入信息的线性平均,基于该线性平均对所述缺失部分进行补充。
需要说明地,在所述AI模型的输出信息包括缺失部分的情况下,同样可以基于上述方式来对所述缺失部分进行补充,此处不做具体赘述。
可选地,所述第一端获取到的第一信息还包括校准集合和所述校准集合的误差中的至少一项,所述使用AI模型执行通信操作之前,所述方法还包括:
所述第一端基于所述第一信息,对目标信息进行处理,处理后的目标信息满足所述校准集合的误差;
其中,所述目标信息为AI模型的输入信息和AI模型的输出信息中的至少一项。
可选地,所述校准集合为用于信息格式校准的输入信息和输出信息的集 合,其中信息格式校准的输入信息与AI模型的输入信息的格式一一对应,和/或信息格式校准的输出信息与AI模型的输出信息的格式一一对应。例如,AI模型用于CSI编码,信息格式校准的输入信息格式为2维矩阵,第一维是空域,32个元素代表32根基站天线,第二维是频域,13个元素代表13个子带,AI模型的输入信息为CSI参考信号,格式为2维矩阵,第一维是空域的32个元素,第二维是频域的13个元素,二者的格式一一对应。第一端能够基于第一信息确定校准集合和所述校准集合的误差中的至少一项,第一端可以是对AI模型的输入信息和/或AI模型的输出信息进行任意处理,处理后的AI模型的输入信息和/或AI模型的输出信息的误差小于校准集合的误差。
例如,以目标信息为AI模型的输入信息为例,若所述第一信息指示校准集合的误差为预设门限值,第一端在基于第一信息对所述AI模型的输入信息进行处理后输入AI模型,并得到AI模型的输出信息,将所述AI模型的输出信息与校准集合中对应的输出信息进行比较,得到误差,若所述误差小于等于所述预设门限值,则认为所述第一端对所述AI模型的输入信息的处理满足校准集合的误差,若所述误差大于所述预设门限值,则认为第一端对所述AI模型的输入信息的处理不满足校准集合的误差。
可选地,所述使用AI模型执行通信操作,包括:
对所述处理后的目标信息使用AI模型执行通信操作,所述AI模型输出的信息满足所述校准集合的误差。
例如,若所述目标信息为AI模型的输入信息,则所述通信操作为第一端对所述AI模型的输入信息进行任意处理后输入所述AI模型,且所述AI模型输出的信息满足校准集合的误差;若所述目标信息为AI模型的输出信息,则所述通信操作为第一端对AI模型的输出信息进行任意处理后,将处理后的AI模型的输出信息作为AI模型输出的信息,且AI模型输出的信息满足校准集合的误差。
本申请实施例中,第一信息能够指示校准集合和/或校准集合的误差,进而第一端能够在使用AI模型进行通信的过程中,对AI模型的输入信息和/或AI模型的输出信息进行任意处理,以确保处理后的AI模型的输入信息和/或AI模型的输出信息满足校准集合的误差。
本申请实施例提供的通信方法,执行主体可以为通信装置。本申请实施例中以通信装置执行通信方法为例,说明本申请实施例提供的通信装置。
请参照图3,图3是本申请实施例提供的一种通信装置的结构图。如图3所示,所述通信装置300包括:
获取模块301,用于获取第一信息,所述第一信息用于指示如下至少一项:人工智能AI模型的功能、AI模型的输入信息和AI模型的输出信息;
执行模块302,用于基于所述第一信息,使用AI模型执行通信操作。
可选地,所述AI模型的功能包括如下至少一项:用于信道状态信息CSI编码、用于CSI译码、用于定位、用于信道估计、用于跟踪参考信号TRS估计、用于相位跟踪参考信息PTRS估计、用于波束管理、用于校准信号、用于数字预失真DPD。
可选地,所述第一信息用于指示如下至少一项:
在所述AI模型的功能为用于CSI编码的情况下,所述AI模型的输入信息为CSI参考信号;
在所述AI模型的功能为用于CSI译码的情况下,所述AI模型的输入信息为预编码矩阵指示PMI和CSI编码信息中的至少一项;
在所述AI模型的功能为用于定位的情况下,所述AI模型的输入信息为探测参考信号SRS、定位参考信号PRS和CSI参考信号中的至少一种;
在所述AI模型的功能为用于信道估计的情况下,所述AI模型的输入信息为参考信号;
在所述AI模型的功能为用于TRS估计的情况下,所述AI模型的输入信息为TRS;
在所述AI模型的功能为用于PTRS的情况下,所述AI模型的输入信息为PTRS;
在所述AI模型的功能为用于波束管理的情况下,所述AI模型的输入信息为参考信号的信道质量;
在所述AI模型的功能为用于校准信号的情况下,所述AI模型的输入信息为待校准的信号;
在所述AI模型的功能为用于DPD的情况下,所述AI模型的输入信息为 原始信号。
可选地,所述第一信息用于指示如下至少一项:
在所述AI模型的功能为用于CSI编码的情况下,所述AI模型的输出信息为PMI和CSI编码信息中的至少一项;
在所述AI模型的功能为用于CSI译码的情况下,所述AI模型的输出信息为CSI和通过CSI处理得到的信道相关信息中的至少一项;
在所述AI模型的功能为用于定位的情况下,所述AI模型的输出信息为位置信息和信道信息中与位置相关的信息中的至少一项;
在所述AI模型的功能为用于信道估计的情况下,所述AI模型的输出信息为估计的信道信息;
在所述AI模型的功能为用于TRS估计的情况下,所述AI模型的输出信息为时间信息;
在所述AI模型的功能为用于PTRS的情况下,所述AI模型的输出信息为相位信息和相位跟踪信息中的至少一项;
在所述AI模型的功能为用于波束管理的情况下,所述AI模型的输出信息为选择波束和所选波束的波束质量中的至少一项;
在所述AI模型的功能为用于校准信号的情况下,所述AI模型的输出信息为已校准的信号;
在所述AI模型的功能为用于DPD的情况下,所述AI模型的输出信息为经过预失真处理的信号。
可选地,在目标信息包括多个域的内容的情况下,所述第一信息用于指示所述目标信息的格式包括如下至少一项:
所述目标信息中的多个域的内容按照预设顺序排列;
所述目标信息中的多个域的内容转换为对应的矩阵,所述矩阵的维度与所述域的数量匹配。
其中,所述目标信息为所述AI模型的输入信息或所述AI模型的输出信息,所述域的内容包括如下至少一项:域的资源、域的信号和域的信息。
可选地,在所述AI模型包括多个输入接口的情况下,所述第一信息用于指示所述AI模型的至少一个所述输入接口对应的输入信息;和/或,
在所述AI模型包括多个输出接口的情况下,所述第一信息用于指示所述AI模型的至少一个所述输出接口对应的输出信息。
可选地,在所述第一信息用于指示所述AI模型的输入信息的情况下,所述第一信息还用于指示所述AI模型的输入信息是否需要预处理;和/或,
在所述第一信息用于指示所述AI模型的输出信息的情况下,所述第一信息还用于指示所述AI模型的输出信息是否需要后处理。
可选地,所述预处理或所述后处理包括如下至少一项:变换域处理、功率处理、幅度处理和相位处理。
可选地,所述AI模型的输入信息和/或所述AI模型的输出信息还包括预设信息,所述预设信息包括如下至少一项:信道环境信息和设备信息。
可选地,所述获取模块301还用于:
获取第二信息,所述第二信息用于指示如下至少一项:所述预设信息和所述预设信息的格式。
可选地,所述执行模块302还用于执行如下至少一项:
在所述装置基于所述第一信息对AI模型执行信息输入之前,将所述预设信息作用于所述AI模型的输入信息;
在所述装置基于所述第一信息对AI模型执行信息输出之后,将所述预设信息作用于所述AI模型的输出信息。
可选地,在目标信息存在缺失部分的情况下,所述执行模块302还用于执行如下至少一项:
基于默认值对所述缺失部分进行补充;
基于所述目标信息的相邻信息对所缺失部分进行补充;
其中,所述目标信息为所述AI模型的输入信息和所述AI模型的输出信息中的至少一者;在所述目标信息为所述AI模型的输入信息的情况下,所述相邻信息为与所述AI模型的输入信息相邻的输入信息,在所述目标信息为所述AI模型的输出信息的情况下,所述相邻信息为与所述AI模型的输出信息相邻的输出信息。
可选地,所述第一信息还包括校准集合和所述校准集合的误差中的至少一项,所述执行模块302还用于:
基于所述第一信息,对目标信息进行处理,处理后的目标信息满足所述校准集合的误差;
其中,所述目标信息为AI模型的输入信息和AI模型的输出信息中的至少一项。
可选地,所述执行模块302还用于:
对所述处理后的目标信息使用AI模型执行通信操作,所述AI模型输出的信息满足所述校准集合的误差。
可选地,在所述装置为第一端的情况下,所述第一信息为第二端发送的指示信息,或者所述第一信息为协议约定的信息。
可选地,所述装置为终端和网络侧设备中的一者,所述第二端为终端和网络侧设备中的另一者;或者,
所述装置和所述第二端为终端的不同节点;或者,
所述装置和所述第二端为网络侧设备的不同节点。
本申请实施例中,明确了通信装置300在通信操作中会使用到的AI模型的功能、AI模型的输入信息和AI模型的输出信息,避免出现AI模型功能不明或者AI模型输入信息、输出信息错误而导致AI模型性能差的问题,以确保通信过程中AI模型具有较好的性能,也保障了通信装置300能够具有较好的通信性能。
本申请实施例中的通信装置300可以是电子设备,例如具有操作***的电子设备,也可以是电子设备中的部件,例如集成电路或芯片。该电子设备可以是终端,也可以为除终端之外的其他设备。示例性的,终端可以包括但不限于上述所列举的终端11的类型,其他设备可以为服务器、网络附属存储器(Network Attached Storage,NAS)等,本申请实施例不作具体限定。
本申请实施例提供的通信装置300能够实现图2所述通信方法实施例实现的各个过程,并达到相同的技术效果,为避免重复,这里不再赘述。
可选的,如图4所示,本申请实施例还提供一种通信设备400,包括处理器401和存储器402,存储器402上存储有可在所述处理器401上运行的程序或指令,例如,该通信设备400为终端时,该程序或指令被处理器401执行时实现上述图2所述通信方法实施例的各个步骤,且能达到相同的技术 效果。该通信设备400为网络侧设备时,该程序或指令被处理器401执行时实现上述图2所述通信方法实施例的各个步骤,且能达到相同的技术效果,为避免重复,这里不再赘述。
本申请实施例还提供一种终端,包括处理器和通信接口,处理器用于获取第一信息,并基于所述第一信息,使用AI模型执行通信操作。该终端实施例与上述终端侧方法实施例对应,上述方法实施例的各个实施过程和实现方式均可适用于该终端实施例中,且能达到相同的技术效果。具体地,图5为实现本申请实施例的一种终端的硬件结构示意图。
该终端500包括但不限于:射频单元501、网络模块502、音频输出单元503、输入单元504、传感器505、显示单元506、用户输入单元507、接口单元508、存储器509以及处理器510等中的至少部分部件。
本领域技术人员可以理解,终端500还可以包括给各个部件供电的电源(比如电池),电源可以通过电源管理***与处理器510逻辑相连,从而通过电源管理***实现管理充电、放电、以及功耗管理等功能。图5中示出的终端结构并不构成对终端的限定,终端可以包括比图示更多或更少的部件,或者组合某些部件,或者不同的部件布置,在此不再赘述。
应理解的是,本申请实施例中,输入单元504可以包括图形处理单元(Graphics Processing Unit,GPU)5041和麦克风5042,图形处理器5041对在视频捕获模式或图像捕获模式中由图像捕获装置(如摄像头)获得的静态图片或视频的图像数据进行处理。显示单元506可包括显示面板5061,可以采用液晶显示器、有机发光二极管等形式来配置显示面板5061。用户输入单元507包括触控面板5071以及其他输入设备5072中的至少一种。触控面板5071,也称为触摸屏。触控面板5071可包括触摸检测装置和触摸控制器两个部分。其他输入设备5072可以包括但不限于物理键盘、功能键(比如音量控制按键、开关按键等)、轨迹球、鼠标、操作杆,在此不再赘述。
本申请实施例中,射频单元501接收来自网络侧设备的下行数据后,可以传输给处理器510进行处理;另外,射频单元501可以向网络侧设备发送上行数据。通常,射频单元501包括但不限于天线、放大器、收发信机、耦合器、低噪声放大器、双工器等。
存储器509可用于存储软件程序或指令以及各种数据。存储器509可主要包括存储程序或指令的第一存储区和存储数据的第二存储区,其中,第一存储区可存储操作***、至少一个功能所需的应用程序或指令(比如声音播放功能、图像播放功能等)等。此外,存储器509可以包括易失性存储器或非易失性存储器,或者,存储器509可以包括易失性和非易失性存储器两者。其中,非易失性存储器可以是只读存储器(Read-Only Memory,ROM)、可编程只读存储器(Programmable ROM,PROM)、可擦除可编程只读存储器(Erasable PROM,EPROM)、电可擦除可编程只读存储器(Electrically EPROM,EEPROM)或闪存。易失性存储器可以是随机存取存储器(Random Access Memory,RAM),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,DDRSDRAM)、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(Synch link DRAM,SLDRAM)和直接内存总线随机存取存储器(Direct Rambus RAM,DRRAM)。本申请实施例中的存储器509包括但不限于这些和任意其它适合类型的存储器。
处理器510可包括一个或多个处理单元;可选的,处理器510集成应用处理器和调制解调处理器,其中,应用处理器主要处理涉及操作***、用户界面和应用程序等的操作,调制解调处理器主要处理无线通信信号,如基带处理器。可以理解的是,上述调制解调处理器也可以不集成到处理器510中。
其中,处理器510,用于:
获取第一信息,所述第一信息用于指示如下至少一项:人工智能AI模型的功能、AI模型的输入信息和AI模型的输出信息;
基于所述第一信息,使用AI模型执行通信操作。
可选地,所述AI模型的功能包括如下至少一项:用于信道状态信息CSI编码、用于CSI译码、用于定位、用于信道估计、用于跟踪参考信号TRS估计、用于相位跟踪参考信息PTRS估计、用于波束管理、用于校准信号、用于数字预失真DPD。
可选地,所述第一信息用于指示如下至少一项:
在所述AI模型的功能为用于CSI编码的情况下,所述AI模型的输入信息为CSI参考信号;
在所述AI模型的功能为用于CSI译码的情况下,所述AI模型的输入信息为预编码矩阵指示PMI和CSI编码信息中的至少一项;
在所述AI模型的功能为用于定位的情况下,所述AI模型的输入信息为探测参考信号SRS、定位参考信号PRS和CSI参考信号中的至少一种;
在所述AI模型的功能为用于信道估计的情况下,所述AI模型的输入信息为参考信号;
在所述AI模型的功能为用于TRS估计的情况下,所述AI模型的输入信息为TRS;
在所述AI模型的功能为用于PTRS的情况下,所述AI模型的输入信息为PTRS;
在所述AI模型的功能为用于波束管理的情况下,所述AI模型的输入信息为参考信号的信道质量;
在所述AI模型的功能为用于校准信号的情况下,所述AI模型的输入信息为待校准的信号;
在所述AI模型的功能为用于DPD的情况下,所述AI模型的输入信息为原始信号。
可选地,所述第一信息用于指示如下至少一项:
在所述AI模型的功能为用于CSI编码的情况下,所述AI模型的输出信息为PMI和CSI编码信息中的至少一项;
在所述AI模型的功能为用于CSI译码的情况下,所述AI模型的输出信息为CSI和通过CSI处理得到的信道相关信息中的至少一项;
在所述AI模型的功能为用于定位的情况下,所述AI模型的输出信息为位置信息和信道信息中与位置相关的信息中的至少一项;
在所述AI模型的功能为用于信道估计的情况下,所述AI模型的输出信息为估计的信道信息;
在所述AI模型的功能为用于TRS估计的情况下,所述AI模型的输出信 息为时间信息;
在所述AI模型的功能为用于PTRS的情况下,所述AI模型的输出信息为相位信息和相位跟踪信息中的至少一项;
在所述AI模型的功能为用于波束管理的情况下,所述AI模型的输出信息为选择波束和所选波束的波束质量中的至少一项;
在所述AI模型的功能为用于校准信号的情况下,所述AI模型的输出信息为已校准的信号;
在所述AI模型的功能为用于DPD的情况下,所述AI模型的输出信息为经过预失真处理的信号。
可选地,在目标信息包括多个域的内容的情况下,所述第一信息用于指示所述目标信息的格式包括如下至少一项:
所述目标信息中的多个域的内容按照预设顺序排列;
所述目标信息中的多个域的内容转换为对应的矩阵,所述矩阵的维度与所述域的数量匹配。
其中,所述目标信息为所述AI模型的输入信息或所述AI模型的输出信息,所述域的内容包括如下至少一项:域的资源、域的信号和域的信息。
可选地,在所述AI模型包括多个输入接口的情况下,所述第一信息用于指示所述AI模型的至少一个所述输入接口对应的输入信息;和/或,
在所述AI模型包括多个输出接口的情况下,所述第一信息用于指示所述AI模型的至少一个所述输出接口对应的输出信息。
可选地,在所述第一信息用于指示所述AI模型的输入信息的情况下,所述第一信息还用于指示所述AI模型的输入信息是否需要预处理;和/或,
在所述第一信息用于指示所述AI模型的输出信息的情况下,所述第一信息还用于指示所述AI模型的输出信息是否需要后处理。
可选地,所述预处理或所述后处理包括如下至少一项:变换域处理、功率处理、幅度处理和相位处理。
可选地,所述AI模型的输入信息和/或所述AI模型的输出信息还包括预设信息,所述预设信息包括如下至少一项:信道环境信息和设备信息。
可选地,所述处理器510还用于:
获取第二信息,所述第二信息用于指示如下至少一项:所述预设信息和所述预设信息的格式。
可选地,所述处理器510还用于执行如下至少一项:
在所述终端500基于所述第一信息对AI模型执行信息输入之前,将所述预设信息作用于所述AI模型的输入信息;
在所述终端500基于所述第一信息对AI模型执行信息输出之后,将所述预设信息作用于所述AI模型的输出信息。
可选地,在目标信息存在缺失部分的情况下,所述处理器510还用于执行如下至少一项:
基于默认值对所述缺失部分进行补充;
基于所述目标信息的相邻信息对所缺失部分进行补充;
其中,所述目标信息为所述AI模型的输入信息和所述AI模型的输出信息中的至少一者;在所述目标信息为所述AI模型的输入信息的情况下,所述相邻信息为与所述AI模型的输入信息相邻的输入信息,在所述目标信息为所述AI模型的输出信息的情况下,所述相邻信息为与所述AI模型的输出信息相邻的输出信息。
可选地,所述第一信息还包括校准集合和所述校准集合的误差中的至少一项,所述处理器510还用于:
基于所述第一信息,对目标信息进行处理,处理后的目标信息满足所述校准集合的误差;
其中,所述目标信息为AI模型的输入信息和AI模型的输出信息中的至少一项。
可选地,所述处理器510还用于:
对所述处理后的目标信息使用AI模型执行通信操作,所述AI模型输出的信息满足所述校准集合的误差。
可选地,所述第一信息为第二端发送的指示信息,或者所述第一信息为协议约定的信息。
可选地,所述第二端为网络侧设备;或者,
所述第二端为终端的节点。
本申请实施例中,明确了终端在通信操作中会使用到的AI模型的功能、AI模型的输入信息和AI模型的输出信息,避免出现AI模型功能不明或者AI模型输入信息、输出信息错误而导致AI模型性能差的问题,以确保通信过程中AI模型具有较好的性能,也保障了终端能够具有较好的通信性能。
本申请实施例还提供一种网络侧设备,包括处理器和通信接口,处理器用于获取第一信息,并基于所述第一信息,使用AI模型执行通信操作;所述第一信息用于指示如下至少一项:人工智能AI模型的功能、AI模型的输入信息和AI模型的输出信息。该网络侧设备实施例与上述图2所述方法实施例对应,上述方法实施例的各个实施过程和实现方式均可适用于该网络侧设备实施例中,且能达到相同的技术效果。
具体地,本申请实施例还提供了一种网络侧设备。如图6所示,该网络侧设备600包括:天线61、射频装置62、基带装置63、处理器64和存储器65。天线61与射频装置62连接。在上行方向上,射频装置62通过天线61接收信息,将接收的信息发送给基带装置63进行处理。在下行方向上,基带装置63对要发送的信息进行处理,并发送给射频装置62,射频装置62对收到的信息进行处理后经过天线61发送出去。
以上实施例中网络侧设备执行的方法可以在基带装置63中实现,该基带装置63包括基带处理器。
基带装置63例如可以包括至少一个基带板,该基带板上设置有多个芯片,如图6所示,其中一个芯片例如为基带处理器,通过总线接口与存储器65连接,以调用存储器65中的程序,执行以上方法实施例中所示的网络设备操作。
该网络侧设备还可以包括网络接口66,该接口例如为通用公共无线接口(Common Public Radio Interface,CPRI)。
具体地,本申请实施例的网络侧设备600还包括:存储在存储器65上并可在处理器64上运行的指令或程序,处理器64调用存储器65中的指令或程序执行图3所示各模块执行的方法,并达到相同的技术效果,为避免重复,故不在此赘述。
本申请实施例还提供一种可读存储介质,所述可读存储介质上存储有程序或指令,该程序或指令被处理器执行时实现上述图2所述通信方法实施例 的各个过程,且能达到相同的技术效果,为避免重复,这里不再赘述。
其中,所述处理器为上述实施例中所述的终端中的处理器。所述可读存储介质,包括计算机可读存储介质,如计算机只读存储器、随机存取存储器、磁碟或者光盘等。
本申请实施例另提供了一种芯片,所述芯片包括处理器和通信接口,所述通信接口和所述处理器耦合,所述处理器用于运行程序或指令,实现上述图2所述通信方法实施例的各个过程,且能达到相同的技术效果,为避免重复,这里不再赘述。
应理解,本申请实施例提到的芯片还可以称为***级芯片,***芯片,芯片***或片上***芯片等。
本申请实施例另提供了一种计算机程序/程序产品,所述计算机程序/程序产品被存储在存储介质中,所述计算机程序/程序产品被至少一个处理器执行以实现上述图2所述通信方法实施例的各个过程,且能达到相同的技术效果,为避免重复,这里不再赘述。
需要说明的是,在本文中,术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含,从而使得包括一系列要素的过程、方法、物品或者装置不仅包括那些要素,而且还包括没有明确列出的其他要素,或者是还包括为这种过程、方法、物品或者装置所固有的要素。在没有更多限制的情况下,由语句“包括一个……”限定的要素,并不排除在包括该要素的过程、方法、物品或者装置中还存在另外的相同要素。此外,需要指出的是,本申请实施方式中的方法和装置的范围不限按示出或讨论的顺序来执行功能,还可包括根据所涉及的功能按基本同时的方式或按相反的顺序来执行功能,例如,可以按不同于所描述的次序来执行所描述的方法,并且还可以添加、省去、或组合各种步骤。另外,参照某些示例所描述的特征可在其他示例中被组合。
通过以上的实施方式的描述,本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现,当然也可以通过硬件,但很多情况下前者是更佳的实施方式。基于这样的理解,本申请的技术方案本质上或者说对现有技术做出贡献的部分可以以计算机软件产品的 形式体现出来,该计算机软件产品存储在一个存储介质(如ROM/RAM、磁碟、光盘)中,包括若干指令用以使得一台终端(可以是手机,计算机,服务器,空调器,或者网络设备等)执行本申请各个实施例所述的方法。
上面结合附图对本申请的实施例进行了描述,但是本申请并不局限于上述的具体实施方式,上述的具体实施方式仅仅是示意性的,而不是限制性的,本领域的普通技术人员在本申请的启示下,在不脱离本申请宗旨和权利要求所保护的范围情况下,还可做出很多形式,均属于本申请的保护之内。

Claims (23)

  1. 一种通信方法,包括:
    第一端获取第一信息,所述第一信息用于指示如下至少一项:人工智能AI模型的功能、AI模型的输入信息和AI模型的输出信息;
    所述第一端基于所述第一信息,使用AI模型执行通信操作。
  2. 根据权利要求1所述的方法,其中,所述AI模型的功能包括如下至少一项:用于信道状态信息CSI编码、用于CSI译码、用于定位、用于信道估计、用于跟踪参考信号TRS估计、用于相位跟踪参考信息PTRS估计、用于波束管理、用于校准信号、用于数字预失真DPD。
  3. 根据权利要求1所述的方法,其中,所述第一信息用于指示如下至少一项:
    在所述AI模型的功能为用于CSI编码的情况下,所述AI模型的输入信息为CSI参考信号;
    在所述AI模型的功能为用于CSI译码的情况下,所述AI模型的输入信息为预编码矩阵指示PMI和CSI编码信息中的至少一项;
    在所述AI模型的功能为用于定位的情况下,所述AI模型的输入信息为探测参考信号SRS、定位参考信号PRS和CSI参考信号中的至少一种;
    在所述AI模型的功能为用于信道估计的情况下,所述AI模型的输入信息为参考信号;
    在所述AI模型的功能为用于TRS估计的情况下,所述AI模型的输入信息为TRS;
    在所述AI模型的功能为用于PTRS的情况下,所述AI模型的输入信息为PTRS;
    在所述AI模型的功能为用于波束管理的情况下,所述AI模型的输入信息为参考信号的信道质量;
    在所述AI模型的功能为用于校准信号的情况下,所述AI模型的输入信息为待校准的信号;
    在所述AI模型的功能为用于DPD的情况下,所述AI模型的输入信息为 原始信号。
  4. 根据权利要求1所述的方法,其中,所述第一信息用于指示如下至少一项:
    在所述AI模型的功能为用于CSI编码的情况下,所述AI模型的输出信息为PMI和CSI编码信息中的至少一项;
    在所述AI模型的功能为用于CSI译码的情况下,所述AI模型的输出信息为CSI和通过CSI处理得到的信道相关信息中的至少一项;
    在所述AI模型的功能为用于定位的情况下,所述AI模型的输出信息为位置信息和信道信息中与位置相关的信息中的至少一项;
    在所述AI模型的功能为用于信道估计的情况下,所述AI模型的输出信息为估计的信道信息;
    在所述AI模型的功能为用于TRS估计的情况下,所述AI模型的输出信息为时间信息;
    在所述AI模型的功能为用于PTRS的情况下,所述AI模型的输出信息为相位信息和相位跟踪信息中的至少一项;
    在所述AI模型的功能为用于波束管理的情况下,所述AI模型的输出信息为选择波束和所选波束的波束质量中的至少一项;
    在所述AI模型的功能为用于校准信号的情况下,所述AI模型的输出信息为已校准的信号;
    在所述AI模型的功能为用于DPD的情况下,所述AI模型的输出信息为经过预失真处理的信号。
  5. 根据权利要求1所述的方法,其中,在目标信息包括多个域的内容的情况下,所述第一信息用于指示所述目标信息的格式包括如下至少一项:
    所述目标信息中的多个域的内容按照预设顺序排列;
    所述目标信息中的多个域的内容转换为对应的矩阵,所述矩阵的维度与所述域的数量匹配;
    其中,所述目标信息为所述AI模型的输入信息或所述AI模型的输出信息,所述域的内容包括如下至少一项:域的资源、域的信号和域的信息。
  6. 根据权利要求1所述的方法,其中,在所述AI模型包括多个输入接 口的情况下,所述第一信息用于指示所述AI模型的至少一个所述输入接口对应的输入信息;和/或,
    在所述AI模型包括多个输出接口的情况下,所述第一信息用于指示所述AI模型的至少一个所述输出接口对应的输出信息。
  7. 根据权利要求1所述的方法,其中,在所述第一信息用于指示所述AI模型的输入信息的情况下,所述第一信息还用于指示所述AI模型的输入信息是否需要预处理;和/或,
    在所述第一信息用于指示所述AI模型的输出信息的情况下,所述第一信息还用于指示所述AI模型的输出信息是否需要后处理。
  8. 根据权利要求7所述的方法,其中,所述预处理或所述后处理包括如下至少一项:变换域处理、功率处理、幅度处理和相位处理。
  9. 根据权利要求1所述的方法,其中,所述AI模型的输入信息和/或所述AI模型的输出信息还包括预设信息,所述预设信息包括如下至少一项:信道环境信息和设备信息。
  10. 根据权利要求9所述的方法,其中,所述方法还包括:
    所述第一端获取第二信息,所述第二信息用于指示如下至少一项:所述预设信息和所述预设信息的格式。
  11. 根据权利要求9所述的方法,其中,所述方法还包括如下至少一项:
    在所述第一端基于所述第一信息对AI模型执行信息输入之前,将所述预设信息作用于所述AI模型的输入信息;
    在所述第一端基于所述第一信息对AI模型执行信息输出之后,将所述预设信息作用于所述AI模型的输出信息。
  12. 根据权利要求1所述的方法,其中,在目标信息存在缺失部分的情况下,所述第一端在执行第一操作之前,所述方法还包括:
    所述第一端执行如下至少一项:
    基于默认值对所述缺失部分进行补充;
    基于所述目标信息的相邻信息对所缺失部分进行补充;
    其中,所述目标信息为所述AI模型的输入信息和所述AI模型的输出信息中的至少一者;在所述目标信息为所述AI模型的输入信息的情况下,所述 相邻信息为与所述AI模型的输入信息相邻的输入信息,在所述目标信息为所述AI模型的输出信息的情况下,所述相邻信息为与所述AI模型的输出信息相邻的输出信息。
  13. 根据权利要求1所述的方法,其中,所述第一信息还包括校准集合和所述校准集合的误差中的至少一项,所述使用AI模型执行通信操作之前,所述方法还包括:
    所述第一端基于所述第一信息,对目标信息进行处理,处理后的目标信息满足所述校准集合的误差;
    其中,所述目标信息为AI模型的输入信息和AI模型的输出信息中的至少一项。
  14. 根据权利要求13所述的方法,其中,所述使用AI模型执行通信操作,包括:
    对所述处理后的目标信息使用AI模型执行通信操作,所述AI模型输出的信息满足所述校准集合的误差。
  15. 根据权利要求1所述的方法,其中,所述第一信息为第二端发送的指示信息,或者所述第一信息为协议约定的信息。
  16. 根据权利要求15所述的方法,其中,所述第一端为终端和网络侧设备中的一者,所述第二端为终端和网络侧设备中的另一者;或者,
    所述第一端和所述第二端为终端的不同节点;或者,
    所述第一端和所述第二端为网络侧设备的不同节点。
  17. 一种通信装置,包括:
    获取模块,用于获取第一信息,所述第一信息用于指示如下至少一项:人工智能AI模型的功能、AI模型的输入信息和AI模型的输出信息;
    执行模块,用于基于所述第一信息,使用AI模型执行通信操作。
  18. 根据权利要求17所述的装置,其中,所述AI模型的功能包括如下至少一项:用于信道状态信息CSI编码、用于CSI译码、用于定位、用于信道估计、用于跟踪参考信号TRS估计、用于相位跟踪参考信息PTRS估计、用于波束管理、用于校准信号、用于数字预失真DPD。
  19. 根据权利要求17所述的装置,其中,所述第一信息用于指示如下至 少一项:
    在所述AI模型的功能为用于CSI编码的情况下,所述AI模型的输入信息为CSI参考信号;
    在所述AI模型的功能为用于CSI译码的情况下,所述AI模型的输入信息为预编码矩阵指示PMI和CSI编码信息中的至少一项;
    在所述AI模型的功能为用于定位的情况下,所述AI模型的输入信息为探测参考信号SRS、定位参考信号PRS和CSI参考信号中的至少一种;
    在所述AI模型的功能为用于信道估计的情况下,所述AI模型的输入信息为参考信号;
    在所述AI模型的功能为用于TRS估计的情况下,所述AI模型的输入信息为TRS;
    在所述AI模型的功能为用于PTRS的情况下,所述AI模型的输入信息为PTRS;
    在所述AI模型的功能为用于波束管理的情况下,所述AI模型的输入信息为参考信号的信道质量;
    在所述AI模型的功能为用于校准信号的情况下,所述AI模型的输入信息为待校准的信号;
    在所述AI模型的功能为用于DPD的情况下,所述AI模型的输入信息为原始信号。
  20. 根据权利要求17所述的装置,其中,所述第一信息用于指示如下至少一项:
    在所述AI模型的功能为用于CSI编码的情况下,所述AI模型的输出信息为PMI和CSI编码信息中的至少一项;
    在所述AI模型的功能为用于CSI译码的情况下,所述AI模型的输出信息为CSI和通过CSI处理得到的信道相关信息中的至少一项;
    在所述AI模型的功能为用于定位的情况下,所述AI模型的输出信息为位置信息和信道信息中与位置相关的信息中的至少一项;
    在所述AI模型的功能为用于信道估计的情况下,所述AI模型的输出信息为估计的信道信息;
    在所述AI模型的功能为用于TRS估计的情况下,所述AI模型的输出信息为时间信息;
    在所述AI模型的功能为用于PTRS的情况下,所述AI模型的输出信息为相位信息和相位跟踪信息中的至少一项;
    在所述AI模型的功能为用于波束管理的情况下,所述AI模型的输出信息为选择波束和所选波束的波束质量中的至少一项;
    在所述AI模型的功能为用于校准信号的情况下,所述AI模型的输出信息为已校准的信号;
    在所述AI模型的功能为用于DPD的情况下,所述AI模型的输出信息为经过预失真处理的信号。
  21. 一种终端,包括处理器和存储器,所述存储器存储可在所述处理器上运行的程序或指令,所述程序或指令被所述处理器执行时实现如权利要求1至16中任一项所述的通信方法的步骤。
  22. 一种网络侧设备,包括处理器和存储器,所述存储器存储可在所述处理器上运行的程序或指令,所述程序或指令被所述处理器执行时实现如权利要求1至16中任一项所述的通信方法的步骤。
  23. 一种可读存储介质,所述可读存储介质上存储程序或指令,所述程序或指令被处理器执行时实现如权利要求1至16中任一项所述的通信方法的步骤。
PCT/CN2022/142110 2021-12-31 2022-12-26 通信方法、装置及相关设备 WO2023125458A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111672336.9 2021-12-31
CN202111672336.9A CN116418693A (zh) 2021-12-31 2021-12-31 通信方法、装置及相关设备

Publications (1)

Publication Number Publication Date
WO2023125458A1 true WO2023125458A1 (zh) 2023-07-06

Family

ID=86997817

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/142110 WO2023125458A1 (zh) 2021-12-31 2022-12-26 通信方法、装置及相关设备

Country Status (2)

Country Link
CN (1) CN116418693A (zh)
WO (1) WO2023125458A1 (zh)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105577314A (zh) * 2014-10-08 2016-05-11 展讯通信(上海)有限公司 一种捕获指示检测方法及移动终端
CN106559872A (zh) * 2015-09-30 2017-04-05 华为技术有限公司 一种资源分配方法、装置及无线接入***
US20210195462A1 (en) * 2019-12-19 2021-06-24 Qualcomm Incorporated Configuration of artificial intelligence (ai) modules and compression ratios for user-equipment (ue) feedback
WO2021163895A1 (zh) * 2020-02-18 2021-08-26 Oppo广东移动通信有限公司 网络模型的管理方法及建立或修改会话的方法、装置
EP3876567A1 (en) * 2020-03-05 2021-09-08 Fujitsu Limited A method in a wireless communication network and in a base station, and a wireless communication network and a base station

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107155199B (zh) * 2016-03-04 2023-09-26 华为技术有限公司 一种空口技术的配置方法、装置及无线通信***
CN113194531B (zh) * 2020-01-14 2023-01-20 维沃移动通信有限公司 定位方法及通信设备
KR20210117611A (ko) * 2020-03-19 2021-09-29 엘지전자 주식회사 Ai를 이용한 이동통신 방법

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105577314A (zh) * 2014-10-08 2016-05-11 展讯通信(上海)有限公司 一种捕获指示检测方法及移动终端
CN106559872A (zh) * 2015-09-30 2017-04-05 华为技术有限公司 一种资源分配方法、装置及无线接入***
US20210195462A1 (en) * 2019-12-19 2021-06-24 Qualcomm Incorporated Configuration of artificial intelligence (ai) modules and compression ratios for user-equipment (ue) feedback
WO2021163895A1 (zh) * 2020-02-18 2021-08-26 Oppo广东移动通信有限公司 网络模型的管理方法及建立或修改会话的方法、装置
EP3876567A1 (en) * 2020-03-05 2021-09-08 Fujitsu Limited A method in a wireless communication network and in a base station, and a wireless communication network and a base station

Also Published As

Publication number Publication date
CN116418693A (zh) 2023-07-11

Similar Documents

Publication Publication Date Title
WO2019218832A1 (zh) 上行数据传输指示方法、终端和网络侧设备
US20240073882A1 (en) Beam Control Method and Apparatus for Intelligent Surface Device and Electronic Device
WO2023125458A1 (zh) 通信方法、装置及相关设备
WO2023198058A1 (zh) 信息传输方法、装置、终端及网络侧设备
WO2023217030A1 (zh) 感知测量的处理方法及设备
WO2023125870A1 (zh) 通信方法、装置、通信设备及可读存储介质
WO2023179617A1 (zh) 定位方法、装置、终端及网络侧设备
WO2023236979A1 (zh) 定位模型的选择方法、终端及网络侧设备
WO2023131316A1 (zh) 探测参考信号的端口映射方法和终端
WO2024027580A1 (zh) 事件信息传输方法、lmf、接入网设备及终端
WO2024008111A1 (zh) 数据采集方法及装置
WO2023208042A1 (zh) 预失真处理方法、装置及设备
WO2023185724A1 (zh) 定位处理方法、装置、终端及网络侧设备
WO2023125656A1 (zh) 多端口定位参考信号配置方法、装置及通信设备
WO2024067439A1 (zh) 数据集生成方法、信息发送方法、装置及相关设备
WO2023098662A1 (zh) 定位方法及通信设备
WO2023143581A1 (zh) 信息传输方法、装置、终端及网络侧设备
WO2023193684A1 (zh) 验证终端位置的方法、终端及网络侧设备
WO2024027618A1 (zh) gap配置方法、装置、网络侧设备及存储介质
WO2023088423A1 (zh) 定位方法、装置、终端及网络侧设备
WO2023143361A1 (zh) 能力信息上报方法、装置及终端
WO2024022398A1 (zh) 托管网络的选网信息的获取方法、终端及网络侧设备
WO2023165395A1 (zh) 切换行为确定方法、参数信息配置方法、终端和设备
WO2022151218A1 (zh) 传播延迟补偿方法、装置、设备、基站、***以及介质
WO2023246756A1 (zh) 算力服务方法、装置、终端及核心网设备

Legal Events

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

Ref document number: 22914712

Country of ref document: EP

Kind code of ref document: A1