WO2023185980A1 - 信道特征信息传输方法、装置、终端及网络侧设备 - Google Patents

信道特征信息传输方法、装置、终端及网络侧设备 Download PDF

Info

Publication number
WO2023185980A1
WO2023185980A1 PCT/CN2023/084964 CN2023084964W WO2023185980A1 WO 2023185980 A1 WO2023185980 A1 WO 2023185980A1 CN 2023084964 W CN2023084964 W CN 2023084964W WO 2023185980 A1 WO2023185980 A1 WO 2023185980A1
Authority
WO
WIPO (PCT)
Prior art keywords
domain
coefficients
orthogonal
terminal
orthogonal basis
Prior art date
Application number
PCT/CN2023/084964
Other languages
English (en)
French (fr)
Inventor
任千尧
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 WO2023185980A1 publication Critical patent/WO2023185980A1/zh

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/02—Arrangements for optimising operational condition
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B17/00—Monitoring; Testing
    • H04B17/30—Monitoring; Testing of propagation channels
    • H04B17/382—Monitoring; Testing of propagation channels for resource allocation, admission control or handover
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L25/00—Baseband systems
    • H04L25/02—Details ; arrangements for supplying electrical power along data transmission lines
    • H04L25/0202—Channel estimation
    • H04L25/0224—Channel estimation using sounding signals
    • H04L25/0228—Channel estimation using sounding signals with direct estimation from sounding signals
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L25/00—Baseband systems
    • H04L25/02—Details ; arrangements for supplying electrical power along data transmission lines
    • H04L25/0202—Channel estimation
    • H04L25/024—Channel estimation channel estimation algorithms
    • H04L25/0242—Channel estimation channel estimation algorithms using matrix methods
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/10—Scheduling measurement reports ; Arrangements for measurement reports

Definitions

  • This application belongs to the field of communication technology, and specifically relates to a channel characteristic information transmission method, device, terminal and network side equipment.
  • AI artificial intelligence
  • communication data can be transmitted between network-side devices and terminals based on the AI network model.
  • the channel information compression feedback scheme based on the AI network model compresses and codes the channel information at the terminal, and decodes the compressed content on the network side to restore the channel information.
  • the decoding network on the network side and the terminal side The encoding network needs to be jointly trained to achieve reasonable matching.
  • channel information of different lengths usually corresponds to different AI network models, resulting in a corresponding increase in power consumption on the terminal side and network side.
  • Embodiments of the present application provide a channel characteristic information transmission method, device, terminal and network side equipment, which can solve the problem in related technologies that different AI network models need to be configured for channel information of different lengths.
  • a channel characteristic information transmission method including:
  • the terminal obtains channel information
  • the terminal calculates the coefficients of the channel information on the orthogonal basis of at least one of the first domain and the second domain, and inputs the coefficients into the first artificial intelligence AI network model for quantization processing to obtain the The channel characteristic information output by the first AI network model;
  • the terminal reports the channel characteristic information to the network side device.
  • a channel characteristic information transmission method including:
  • the network side device receives the channel characteristic information reported by the terminal
  • the channel characteristic information is that the terminal calculates the coefficients of the channel information on an orthogonal basis of at least one of the first domain and the second domain, and inputs the coefficients into the first AI network model for quantization processing. Output the obtained information.
  • a channel characteristic information transmission device including:
  • Acquisition module used to obtain channel information
  • a processing module configured to calculate coefficients of the channel information on an orthogonal basis of at least one of the first domain and the second domain, and input the coefficients to the first artificial intelligence AI network model for quantization processing, to obtain The channel characteristic information output by the first AI network model;
  • a reporting module is used to report the channel characteristic information to the network side device.
  • a channel characteristic information transmission device including:
  • the second receiving module is used to receive the channel characteristic information reported by the terminal;
  • the channel characteristic information is that the terminal calculates the coefficients of the channel information on an orthogonal basis of at least one of the first domain and the second domain, and inputs the coefficients into the first AI network model for quantization processing. Output the obtained information.
  • a terminal in a fifth aspect, includes a processor and a memory.
  • the memory stores programs or instructions that can be run on the processor.
  • the program or instructions are executed by the processor, the following implementations are implemented: The steps of the channel characteristic information transmission method described in one aspect.
  • a terminal including a processor and a communication interface, wherein the processor is configured to obtain channel information and calculate an orthogonal basis of the channel information in at least one of the first domain and the second domain. coefficients on, and input the coefficients to the first artificial intelligence AI network model for quantification processing, to obtain the channel characteristic information output by the first AI network model, and the communication interface is used to report the channel to the network side device. Feature information.
  • a network side device in a seventh aspect, includes a processor and a memory.
  • the memory stores programs or instructions that can be run on the processor.
  • the program or instructions are executed by the processor.
  • a network-side device including a processor and a communication interface.
  • the communication interface is used to receive channel characteristic information reported by a terminal, wherein the channel characteristic information is used by the terminal to calculate channel information in the first domain. and the coefficients on the orthogonal basis of at least one of the second domain, and input the coefficients into the first AI network model for quantization processing and then output the obtained information.
  • a ninth aspect provides a communication system, including: a terminal and a network side device.
  • the terminal can be used to perform the steps of the channel characteristic information transmission method as described in the first aspect.
  • the network side device can be used to perform the steps of the channel characteristic information transmission method as described in the first aspect. The steps of the channel characteristic information transmission method described in the second aspect.
  • a readable storage medium In a tenth aspect, a readable storage medium is provided. Programs or instructions are stored on the readable storage medium. When the programs or instructions are executed by a processor, the steps of the channel characteristic information transmission method as described in the first aspect are implemented. , or implement the steps of the channel characteristic information transmission method described in the second aspect.
  • a chip in an eleventh aspect, includes a processor and a communication interface.
  • the communication interface is coupled to the processor.
  • the processor is used to run programs or instructions to implement the method described in the first aspect. Channel characteristic information transmission method, or implement the channel characteristic information transmission method as described in the second aspect.
  • 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 as described in the first aspect
  • the steps of the channel characteristic information transmission method, or the steps of implementing the channel characteristic information transmission method as described in the second aspect are provided.
  • the terminal calculates the coefficients of the channel information on the orthogonal basis of at least one of the first domain and the second domain, inputs the coefficients into the first AI network model for quantization processing, and obtains the first AI network
  • the channel characteristic information output by the model is reported to the network side device.
  • the terminal can process the channel information based on a first AI network model by calculating the coefficients of the channel information on at least one of the orthogonal bases in the first domain and the second domain, and there is no need to process the channel information for different lengths.
  • the channel information is configured with different AI network models respectively, which can save the power consumption of the network-side device for training the AI network model, save the transmission overhead for the AI network model between the network-side device and the terminal, and also reduce the power consumption of the terminal.
  • Figure 1 is a block diagram of a wireless communication system applicable to the embodiment of the present application.
  • Figure 2 is a flow chart of a channel characteristic information transmission method provided by an embodiment of the present application.
  • Figure 3 is a flow chart of another channel characteristic information transmission method provided by an embodiment of the present application.
  • Figure 4 is a structural diagram of a channel characteristic information transmission device provided by an embodiment of the present application.
  • Figure 5 is a structural diagram of another channel characteristic information transmission device provided by an embodiment of the present application.
  • Figure 6 is a structural diagram of a communication device provided by an embodiment of the present application.
  • Figure 7 is a structural diagram of a terminal provided by an embodiment of the present application.
  • Figure 8 is a structural diagram of a network side device provided by an embodiment of the present application.
  • first, second, etc. in the description and claims of this application are used to distinguish similar objects and are not used to describe a specific order or sequence. It is to be understood that the terms so used are interchangeable under appropriate circumstances so that the embodiments of the present application can be practiced in sequences other than those illustrated or described herein, and that "first" and “second” are distinguished objects It is usually one type, and the number of objects is not limited.
  • the first object can be one or multiple.
  • “and/or” in the description and claims indicates at least one of the connected objects, and the character “/" generally indicates that the related objects are in an "or” relationship.
  • LTE Long Term Evolution
  • LTE-Advanced, LTE-A Long Term Evolution
  • LTE-A Long Term Evolution
  • 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
  • NR New Radio
  • FIG. 1 shows a block diagram of a wireless communication system to which embodiments of the present application are 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 handheld computer, a netbook, or a super mobile personal computer.
  • Tablet Personal Computer Tablet Personal Computer
  • laptop computer laptop computer
  • PDA Personal Digital Assistant
  • PDA Personal Digital Assistant
  • UMPC ultra-mobile personal computer
  • UMPC mobile Internet device
  • MID mobile Internet device
  • augmented reality augmented reality, AR
  • VR virtual reality
  • robots wearable devices
  • Vehicle user equipment VUE
  • pedestrian terminal pedestrian terminal
  • PUE pedestrian terminal
  • 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 machine or self-service machine and other terminal-side devices.
  • Wearable devices include: smart watches, smart bracelets, smart headphones, smart glasses, smart jewelry (smart bracelets, smart bracelets, smart rings, smart necklaces, smart anklets) bracelets, smart anklets, etc.), smart wristbands, smart clothing, etc.
  • the network side equipment 12 may include access network equipment or core network equipment, where the access network equipment may also be called wireless access network equipment, radio access network (Radio Access Network, RAN), radio access network function or wireless access network unit.
  • Access network equipment can include base stations, Wireless Local Area Network (WLAN) access points or WiFi nodes, etc.
  • WLAN Wireless Local Area Network
  • the base station can be called Node B, Evolved Node B (eNB), access point, base transceiver station ( Base Transceiver Station (BTS), radio base station, radio transceiver, Basic Service Set (BSS), Extended Service Set (ESS), home B-node, home evolved B-node, sending and receiving point ( Transmitting Receiving Point (TRP) or some other suitable term in the field, as long as the same technical effect is achieved, the base station is not limited to specific technical terms. It should be noted that in the embodiment of this application, only the NR system is used The base station is introduced as an example, and the specific type of base station is not limited.
  • channel state information is crucial to channel capacity.
  • the transmitter can optimize signal transmission based on CSI to better match the channel status.
  • channel quality indicator CQI
  • MCS modulation and coding scheme
  • precoding matrix indicator precoding matrix indicator
  • PMI precoding matrix indicator
  • Eigen beamforming Eigen beamforming
  • network-side equipment such as a base station
  • CSI-RS Channel state information reference signal
  • the terminal performs channel estimation based on CSI-RS, calculates the channel information in this slot, and feeds PMI back to the base station through the codebook.
  • the base station combines the codebook information fed back by the terminal to Channel information is used by the base station to perform data precoding and multi-user scheduling before the next CSI report.
  • the terminal can change the PMI reported on each subband to report PMI based on delay. Since the channels in the delay domain are more concentrated, PMI with fewer delays can approximately represent the PMI of all subbands. That is, the delay field information will be compressed before reporting.
  • the base station can precode the CSI-RS in advance and send the coded CSI-RS to the terminal. What the terminal sees is the channel corresponding to the coded CSI-RS. The terminal only needs to Just select several ports with greater strength among the indicated ports and report the coefficients corresponding to these ports.
  • the terminal uses the AI network model to compress and encode the channel information, and the base station decodes the compressed content through the AI network model to restore the channel information.
  • the base station's AI network model for decoding and the terminal's use The AI network model for coding needs to be jointly trained to achieve a reasonable matching degree.
  • the terminal's AI network model for encoding and the base station's AI network model for decoding form a joint neural network model, which is jointly trained by the network side.
  • the base station sends the AI network model for encoding to the terminal. .
  • the terminal estimates CSI-RS, calculates channel information, uses the calculated channel information or original estimated channel information through the AI network model to obtain the coding result, and sends the coding result to the base station.
  • the base station receives the coding result and inputs it into the AI network model. decode and recover the channel information.
  • the encoding and decoding of channel information is for the entire channel information, and the required number of inputs is fixed. For different numbers of inputs, for example, under different broadbands, the number of subbands is different, the number of channel matrices obtained by channel estimation is different, or the number of ports is different. Configuration, different dimensions of the channel matrix will lead to different numbers of inputs to the AI network model. For each length, the corresponding AI network model needs to be trained separately to achieve different amounts of channel information encoding.
  • Figure 2 is a flow chart of a channel characteristic information transmission method provided by an embodiment of the present application. This method is applied to terminals. As shown in Figure 2, the method includes the following steps:
  • Step 201 The terminal obtains channel information.
  • the terminal may detect the CSI Reference Signal (CSI-RS) or Tracking Reference Signal (TRS) at a location specified by the network side device, and perform channel estimation to obtain channel information. For example, the terminal obtains the channel matrix of each subband through CSI-RS channel estimation.
  • the channel information may be the channel matrix of each subband, or the corresponding precoding matrix obtained by precoding the channel matrix, or a specific The precoding matrix of the layer, etc.
  • the channel matrix is a matrix of Nr ⁇ Nt, where Nr is the number of receiving antennas and Nt is the number of CSI-RS ports.
  • Step 202 The terminal calculates the coefficients of the channel information on the orthogonal basis of at least one of the first domain and the second domain, and inputs the coefficients into the first AI network model for quantization processing to obtain the The first AI network model output channel characteristic information.
  • the first domain is the spatial domain, or also called the angle domain
  • the second domain is the frequency domain, or also called the delay domain.
  • the terminal may calculate the coefficient of the channel information on the orthogonal basis of the first domain; or it may also calculate the coefficient of the channel information on the orthogonal basis of the second domain. coefficients; or calculate the coefficients of the channel information on the orthogonal basis in the first domain and the coefficients on the orthogonal basis in the second domain, for example, select 4 orthogonal bases in the air domain and 4 orthogonal bases in the frequency domain. Orthogonal basis, the terminal calculates a total of 16 coefficients of the channel information on these orthogonal basis; or it can also calculate the coefficients of the channel information on the joint orthogonal basis of the first domain and the second domain, for example, select 8 orthogonal coefficients in the spatial domain.
  • the terminal can calculate the coefficients of the channel information on these 32 orthogonal bases, or the terminal can also calculate the coefficients of the channel information from these 32 space-frequency joint orthogonal bases.
  • the terminal inputs the calculated coefficients into the first AI network model for quantization processing, and obtains the channel characteristic information output by the first AI network model.
  • the first AI network model compresses and codes the input coefficients into a bit sequence, and the channel characteristic information output by the first AI network model is also the bit sequence.
  • the terminal may input all the calculated coefficients into the first AI network model, or may select a certain number of coefficients corresponding to orthogonal bases from the calculated coefficients and input them into the first AI network model. For example, after calculating the coefficients of channel information on these 32 orthogonal bases based on 32 space-frequency joint orthogonal bases, the terminal may select coefficients of 24 orthogonal bases and input them to the first AI network model.
  • Step 203 The terminal reports the channel characteristic information to the network side device.
  • the terminal reports the channel characteristic information to the network side device.
  • the network side device includes a second AI network model that matches the first AI network model.
  • the first AI network model and the second AI network model are jointly trained through the network side device, and the network side device transfers the trained first AI network
  • the model is sent to the terminal.
  • the terminal encodes the input coefficients through the first AI network model and outputs channel characteristic information.
  • the terminal reports the channel characteristic information to the network side device, and the network side device inputs the channel characteristic information into the matching second AI network model.
  • the second AI network model decodes the channel characteristic information to obtain the channel information output by the second AI network model, and then the network side device recovers the channel information through the second AI network model.
  • terminals and network-side devices can encode and decode channel information through matching AI network models.
  • channel information coding mentioned in the embodiments of this application is different from channel coding.
  • the terminal calculates the coefficients of the channel information on the orthogonal basis of at least one of the first domain and the second domain, inputs the coefficients into the first AI network model for quantization processing, and obtains the first AI network model.
  • the output channel characteristic information is reported to the network side device.
  • the terminal can process the channel information based on a first AI network model by calculating the coefficients of the channel information on at least one of the orthogonal bases in the first domain and the second domain, and there is no need to process the channel information for different lengths.
  • the channel information is configured with different AI network models respectively, which can save the power consumption of the network-side device for training the AI network model, save the transmission overhead for the AI network model between the network-side device and the terminal, and also reduce the power consumption of the terminal.
  • the first domain is the spatial domain
  • the second domain is the frequency domain.
  • the orthogonal basis of the first domain may be at least one of a discrete Fourier Transform (DFT) orthogonal basis, a CSI-RS port, and a beam.
  • DFT orthonormal basis may be an orthogonal basis that has been over-sampled, or it may be an orthonormal basis that has not been over-sampled.
  • the orthogonal basis of the second domain may be at least one of a DFT orthogonal basis, a delay, and a delay tap.
  • the precoding matrix of a layer can be a 32*1 matrix, and the projection is generated 32 orthogonal DFT vectors, each DFT vector length is 32, project this precoding matrix into 32 orthogonal DFT vectors, select several with larger coefficient amplitudes, and then use the coefficients and/or corresponding DFT vectors as Preprocessing results.
  • Oversampling occurs during projection. For example, taking 4 times oversampling as an example, four groups of 32 orthogonal DFT vectors are generated. Each group of 32 DFT vectors is orthogonal. There is no orthogonality between groups. Then select 4 groups. The group closest to the precoding matrix is projected as above.
  • the maximum number of orthogonal bases in the first domain is the number of CSI-RS ports; the maximum number of orthogonal bases in the second domain is the number of frequency domain sampling points.
  • the determination of the orthogonal basis may be indicated by a network side device.
  • the method may also include:
  • the terminal receives first indication information sent by the network side device, where the first indication information is used to indicate the orthogonal base used by the terminal, or used to indicate the number of orthogonal bases used by the terminal.
  • the terminal selects N1 in the first domain based on the first indication information.
  • orthogonal bases select N2 orthogonal bases in the second domain, and calculate the coefficients of the channel information on the N1 orthogonal bases selected in the first domain, and calculate the channel information on the N2 orthogonal bases selected in the second domain coefficients on, and then input the calculated coefficients into the first AI network model for quantification processing.
  • the first indication information may also directly instruct the terminal to use an orthogonal base, that is, the terminal does not need to select an orthogonal base.
  • the terminal can directly determine the orthogonal base to be used based on the first indication information, and then Calculate the coefficients of the channel information on these indicated orthogonal bases.
  • the terminal calculates coefficients of the channel information on an orthogonal basis of at least one of the first domain and the second domain, and inputs the coefficients into the first AI network model for quantization processing, including :
  • the terminal determines an orthogonal basis adopted by at least one of the first domain and the second domain based on the first indication information
  • the terminal calculates the coefficients of the channel information on the adopted orthogonal basis, and inputs the coefficients into the first AI network model for quantization processing.
  • the length of the coefficients and the first indication information indicate that the terminal The number of orthogonal bases used matches.
  • the first indication information is used to indicate that the orthogonal bases used in the first domain are a1, a2, a3, a4, and the orthogonal bases used in the second domain are b1, b2, b3, b4, then the terminal calculates The coefficients of channel information a1 in b1, b2, b3, b4, the coefficients of a2 in b1, b2, b3, b4... A total of 16 coefficients are calculated, and the calculated 16 coefficients are input into the first AI network model for quantification processing . It is understandable that the first indication information may also only indicate the orthogonal basis used by the terminal in the first domain, or only indicate the orthogonal basis used in the second domain, which will not be described in detail in this embodiment.
  • the length of the coefficients input by the first AI network model matches the number of orthogonal bases that the first instruction information indicates the terminal to use, and the terminal can then determine the coefficients input by the first AI network model through the number of orthogonal bases. length.
  • the orthogonal bases used in the first domain are all orthogonal bases in the spatial domain.
  • the first indication information may only indicate that all orthogonal bases are used in the air domain, and no indication is given for the orthogonal bases in the frequency domain; then the terminal calculates the coefficients of the channel information on all orthogonal bases in the air domain, and calculates the coefficients of the channel information in the frequency domain. Coefficients on all orthogonal bases in the frequency domain, or coefficients on certain orthogonal bases in the frequency domain for calculating channel information.
  • the terminal can determine the orthogonal base used in the frequency domain by itself.
  • the first indication information may also indicate only the orthogonal basis used in the frequency domain.
  • the terminal adopts a method for at least one of the first domain and the second domain based on the first indication information.
  • Orthogonal basis selection including:
  • the terminal determines the orthogonal basis adopted by the second domain based on the first indication information, where the first indication information is used to indicate the orthogonal basis adopted by the second domain;
  • the terminal calculates the coefficients of the channel information on the selected orthogonal basis, and inputs the coefficients into the first AI network model for quantization processing, including:
  • the terminal calculates the first coefficients of the channel information on all orthogonal bases in the first domain, and calculates the second coefficients of the channel information on the orthogonal bases used in the second domain, and calculates The first coefficient and the second coefficient are input to the first AI network model for quantization processing.
  • the first indication information only indicates the orthogonal basis used in the frequency domain, and does not indicate the orthogonal basis used in the air domain; in this case, all orthogonal bases are selected in the air domain, and the terminal calculates all orthogonal bases in the air domain for channel information.
  • the first coefficient on the basis, and the second coefficient on the orthogonal basis of the indicated frequency domain for calculating the channel information, and the first coefficient and the second coefficient are input into the first AI network model for quantization processing.
  • the terminal can decide on its own to calculate the coefficients of the channel information on all orthogonal bases in the airspace to ensure that the terminal is accurate for the channel information in the airspace. deal with.
  • the orthogonal base may also be determined through a protocol agreement, that is, the terminal determines the orthogonal base to be used based on the protocol agreement.
  • the protocol stipulates that all orthogonal bases in the airspace are selected, and the terminal calculates the coefficients of the channel information on all orthogonal bases in the airspace based on the protocol stipulation.
  • the terminal calculates the coefficient of the channel information on the orthogonal basis of at least one of the first domain and the second domain, include:
  • the terminal determines an oversampling factor, and calculates a coefficient of the channel information on an orthogonal basis of a target domain based on the oversampling factor, where the target domain includes at least one of a first domain and a second domain.
  • the target domain is the first domain
  • the terminal determines the oversampling factor of the orthogonal basis in the first domain, and calculates the channel information based on the oversampling factor. Coefficients on an orthogonal basis of a domain.
  • the terminal can also report the over-exploitation factor to the network side device.
  • the terminal calculates the orthogonality of the channel information in at least one of the first domain and the second domain. based on the coefficients, and inputting the coefficients into the first AI network model for quantization processing, which may also include:
  • the terminal calculates corresponding coefficients of the channel information on M orthogonal bases in at least one of the first domain and the second domain, and the M orthogonal bases include at least one target orthogonal base;
  • the terminal inputs the target coefficient to the first AI network model for quantification processing, and the target coefficient includes any one of the following:
  • a preset number of coefficients corresponding to the target orthogonal basis and the preset coefficients is a preset number of coefficients corresponding to the target orthogonal basis and the preset coefficients.
  • the M is 4, and the M may be indicated by the network side device, or may be selected by the terminal.
  • the terminal may calculate coefficients of the channel signal on four orthogonal bases in the first domain and coefficients on four orthogonal bases in the second domain, assuming that the target orthogonal base is 4 on the first domain.
  • orthogonal bases the terminal may input the coefficients corresponding to the four orthogonal bases in the first domain as target coefficients into the first AI network model for quantization processing, or it may select the four orthogonal bases in the first domain.
  • the coefficients corresponding to 2 of the bases are used as the target coefficients, or the coefficients corresponding to the 4 orthogonal bases in the first domain and the preset coefficients are used as the target coefficients, or the 4 coefficients in the first domain are selected. Two corresponding coefficients in the orthogonal basis and the preset coefficient are used as target coefficients. In this way, the terminal becomes more flexible in selecting the target coefficients for inputting the first AI network model.
  • the above M, target orthogonal basis and target coefficient are only examples and do not constitute a limitation on the present application.
  • the preset number may be a network-side device configuration.
  • the preset number is a preset ratio, and the preset ratio ranges from 0 to 1.
  • the number of target orthogonal bases is 4, and the preset ratio is 50%, that is, the coefficients corresponding to two orthogonal bases in the target orthogonal base are selected as the target coefficients.
  • the preset number may be the first L coefficients corresponding to the target orthogonal basis with larger values, and the value of L is less than or equal to the number of the target orthogonal basis.
  • the input length of the first AI network model matches the number of the input target coefficients.
  • the input length is 2 times the number of target coefficients.
  • the coefficients are complex numbers
  • the input of the first AI network model is real numbers
  • the coefficients can be sorted in a specified order.
  • the M orthogonal bases may include the target orthogonal base and other orthogonal bases other than the target orthogonal base, and the coefficients corresponding to the other orthogonal bases are the predetermined Set the coefficient.
  • the preset coefficient may be a protocol stipulation or a network side device configuration.
  • the protocol stipulates that the preset coefficient is 0 or a fixed value.
  • the preset coefficient satisfies any one of the following:
  • the preset coefficient is associated with the first AI network model
  • the preset coefficients corresponding to the other orthogonal bases are the same;
  • the preset coefficients corresponding to the other orthogonal bases are different, and one of the other orthogonal bases corresponds to one preset coefficient;
  • the preset coefficient is 0.
  • the preset coefficient is associated with the first AI network model and is configured together with the network side device, such as The network side device can configure different first AI network models corresponding to different preset coefficients.
  • the preset coefficients corresponding to other orthogonal bases other than the target orthogonal base are the same.
  • the preset coefficient is a preset value.
  • Orthogonal bases other than orthonormal bases use this default value.
  • each orthogonal base among the M orthogonal bases except the target orthogonal base corresponds to a preset coefficient, that is, the preset coefficient can be a series of values, and these preset coefficients can also be agreed upon by agreement or Network side device configuration.
  • the network side device configures the preset coefficient to be 0.
  • the processing complexity of the input coefficients of the first AI network model can be reduced, which can also reduce the network structure size of the first AI network model, and also enable the network side device to process the input coefficients.
  • the training of an AI network model is simpler.
  • the M orthogonal bases are all orthogonal bases of the target domain, and the target domain includes at least one of the first domain and the second domain.
  • the target domain is the first domain
  • the first domain is the air domain.
  • the terminal may calculate the coefficients of the channel information on all orthogonal bases in the air domain.
  • the terminal before inputting the calculated coefficients into the first AI network model, the terminal may also sort the coefficients.
  • the terminal calculates coefficients of the channel information on an orthogonal basis of at least one of the first domain and the second domain, and inputs the coefficients into the first AI network model for quantization processing, including :
  • the terminal calculates coefficients of the channel information on an orthogonal basis of at least one of the first domain and the second domain, sorts the coefficients, and inputs the sorted coefficients into the first AI network
  • the model is quantified.
  • the terminal calculates the coefficients of the channel information on the orthogonal basis of the first domain and the coefficients on the orthogonal basis of the second domain, and sorts all the calculated coefficients, for example, the coefficients can be sorted from large to large in amplitude.
  • the coefficients can be sorted according to the amplitude from small to large, etc.
  • the sorting method of the coefficients can be a protocol agreement, or it can also be a network side device configuration.
  • the terminal inputs the sorted coefficients into the first AI network model for quantization processing. In this way, the coefficients input to the first AI network model are more regular, which is more conducive to the processing of coefficients by the first AI network model.
  • the method may also include:
  • the terminal reports to the network side device the order of the orthogonal bases corresponding to the sorted coefficients, or reports the order identification of the orthogonal bases corresponding to the sorted coefficients.
  • the terminal may send data to the network side.
  • the device reports the order of the orthogonal bases corresponding to the sorted coefficients, or reports the order identification of the orthogonal bases corresponding to the sorted coefficients.
  • the network side device can learn the order of the coefficients input to the first AI network model based on the reported order of the orthogonal bases or the order identification of the orthogonal bases, so as to better restore the channel information.
  • the terminal may transmit the channel information to the terminal
  • the sum of squares of the coefficients calculated on the orthogonal basis of the airspace is sorted from large to small.
  • the terminal reports the order of the beams corresponding to the sorted coefficients.
  • the order of polarization can be agreed upon by the agreement or related to First AI network model matching.
  • the coefficients on the orthogonal basis of the first domain and the coefficients on the orthogonal basis of the second domain are sorted separately; or, when the target domain includes the first domain and the second domain, Next, the coefficients on the orthogonal basis of the first domain and the coefficients on the orthogonal basis of the second domain are jointly sorted.
  • the method may further include:
  • the terminal reports the adopted orthogonal basis to the network side device.
  • the terminal reports these orthogonal bases to the network side device.
  • the network side device can recover the channel information based on the reported orthogonal basis used by the terminal and the coefficients on these orthogonal basis restored through the second AI network model.
  • the network side device may have multiple second AI network models that match the first AI network model of the terminal, and the network side device includes multiple second AI network models that match the first AI network model.
  • the method also includes:
  • the terminal reports the position of the orthogonal basis corresponding to the maximum coefficient to the network side device.
  • the channel characteristic information when the network side device receives the channel characteristic information reported by the terminal, the channel characteristic information may be input into one of the second AI network models for decoding processing to obtain the recovered coefficients, and the network side device compares the maximum coefficient obtained by decoding. Is the position of the orthogonal base corresponding to the maximum coefficient reported by the terminal consistent? If not, the network side device can replace a second AI network model to decode the channel characteristic information to select the appropriate third AI network model. The second AI network model restores channel information.
  • the terminal calculates the channel information on the orthogonal basis of at least one of the first domain and the second domain. coefficients, including:
  • the terminal determines an orthogonal basis based on the CSI-RS port, and calculates a coefficient of the channel information on the orthogonal basis determined based on the CSI-RS port.
  • the network side device may encode the orthogonal base used by the terminal into the CSI-RS port through a precoder, and then the terminal may determine the orthogonal basis used based on the CSI-RS port. basis, and calculate the coefficients of the channel information on the determined orthogonal basis, and input the coefficients into the first AI network model.
  • the terminal can directly determine the orthogonal base based on the CSI-RS port, without the terminal having to select an orthogonal base, which further helps to simplify the terminal's processing flow.
  • Figure 3 is a flow chart of another channel characteristic information transmission method provided by an embodiment of the present application. This method is applied to network side equipment. As shown in Figure 3, the method includes the following steps:
  • Step 301 The network side device receives the channel characteristic information reported by the terminal;
  • the channel characteristic information is that the terminal calculates the coefficients of the channel information on an orthogonal basis of at least one of the first domain and the second domain, and inputs the coefficients into the first AI network model for quantization processing. Output the obtained information.
  • the network side device includes a second AI network model that matches the first AI network model.
  • the first AI network model and the second AI network model are jointly trained through the network side device.
  • the network side device will train the The first AI network model is sent to the terminal.
  • the terminal encodes the input coefficients through the first AI network model and outputs channel characteristic information.
  • the terminal reports the channel characteristic information to the network side device, and the network side device inputs the channel characteristic information into the matching second AI network model.
  • the second AI network model decodes the channel characteristic information to obtain the channel information output by the second AI network model, and then the network side device recovers the channel information through the second AI network model.
  • terminals and network-side devices can encode and decode channel information through matching AI network models.
  • the terminal can process the channel information based on a first AI network model by calculating the coefficients of the channel information on at least one of the orthogonal basis in the first domain and the second domain, and then the network side
  • the device does not need to train different AI network models for channel information of different lengths, thereby saving the power consumption of the network-side device for training the AI network model, and also saving the transmission overhead of the AI network model between the network-side device and the terminal.
  • the first domain is the spatial domain
  • the second domain is the frequency domain
  • the maximum number of orthogonal bases in the first domain is the number of CSI-RS ports; the maximum number of orthogonal bases in the second domain is the number of frequency domain sampling points.
  • the method before the network side device receives the channel characteristic information reported by the terminal, the method further includes:
  • the network side device sends first indication information to the terminal, where the first indication information is used to indicate the orthogonal base used by the terminal, or to indicate the number of orthogonal bases used by the terminal.
  • the terminal selects N1 in the first domain based on the first indication information.
  • orthogonal bases select N2 orthogonal bases in the second domain, and calculate the coefficients of the channel information on the N1 orthogonal bases selected in the first domain, and calculate the channel information on the N2 orthogonal bases selected in the second domain coefficients on, and then input the calculated coefficients into the first AI network model for quantification processing.
  • the first indication information may also directly instruct the terminal to use an orthogonal base, that is, the terminal does not need to select an orthogonal base.
  • the terminal can directly determine the orthogonal base to be used based on the first indication information, and then Calculate the coefficients of the channel information on these indicated orthogonal bases.
  • the method further includes:
  • the network side device receives the adopted orthogonal basis reported by the terminal.
  • the network side device can recover the channel information based on the reported orthogonal basis used by the terminal and the coefficients on these orthogonal basis restored through the second AI network model.
  • the method also includes:
  • the network side device receives the position of the orthogonal basis corresponding to the maximum coefficient reported by the terminal.
  • the channel characteristic information when the network side device receives the channel characteristic information reported by the terminal, the channel characteristic information may be input into one of the second AI network models for decoding processing to obtain the recovered coefficients, and the network side device compares the decoded coefficients. Whether the position of the obtained orthogonal base of the maximum coefficient is consistent with the position of the orthogonal base corresponding to the maximum coefficient reported by the terminal. If they are inconsistent, the network side device can replace a second AI network model to decode the channel characteristic information. Select an appropriate second AI network model to restore channel information.
  • the method may also include:
  • the network side device encodes the orthogonal basis into the CSI-RS port.
  • the network side device may encode the orthogonal base used by the terminal into the CSI-RS port through a precoder, and then the terminal may determine the orthogonal basis used based on the CSI-RS port. basis, and calculate the coefficients of the channel information on the determined orthogonal basis, and input the coefficients into the first AI network model.
  • the terminal can directly determine the orthogonal base based on the CSI-RS port, without the terminal having to select an orthogonal base, which further helps to simplify the terminal's processing flow.
  • channel characteristic information transmission method applied to network side equipment corresponds to the above-mentioned method applied to the terminal.
  • the relevant concepts and specific implementation processes involved in the embodiment of the present application can be as shown in Figure 2 above. To avoid repetition, the description in the above embodiment will not be repeated in this embodiment.
  • the execution subject may be a channel characteristic information transmission device.
  • the channel characteristic information transmission method performed by the channel characteristic information transmission device is used as an example to illustrate the channel characteristic information transmission device provided by the embodiment of the present application.
  • the channel characteristic information transmission device 400 includes:
  • Obtain module 401 used to obtain channel information
  • the processing module 402 is used to calculate the coefficients of the channel information on the orthogonal basis of at least one of the first domain and the second domain, and input the coefficients to the first artificial intelligence AI network model for quantization processing, Obtain the channel characteristic information output by the first AI network model;
  • the reporting module 403 is used to report the channel characteristic information to the network side device.
  • the first domain is the air domain
  • the second domain is the frequency domain
  • the maximum number of orthogonal bases in the first domain is the number of ports of the channel state information reference signal CSI-RS;
  • the maximum number of orthogonal bases in the second domain is the number of frequency domain sampling points.
  • the device also includes:
  • the first receiving module is configured to receive first indication information sent by the network side device, where the first indication information is used to indicate the orthogonal base used by the terminal, or to indicate the number of orthogonal bases used by the terminal.
  • processing module 402 is also used to:
  • the length of the coefficients is consistent with the orthogonal basis used by the first indication information.
  • the number of cross bases matches.
  • the first domain when the first domain is the spatial domain and the second domain is the frequency domain, the first domain adopts an orthogonal
  • the bases are all orthogonal bases of the space.
  • the processing module 402 is also used to:
  • the first indication information Based on the first indication information, determine the orthogonal basis adopted by the second domain, and the first indication information is used to indicate the orthogonal basis adopted by the second domain;
  • the orthogonal basis is determined through a protocol.
  • the processing module 402 is also used to:
  • An oversampling factor is determined, and a coefficient of the channel information on an orthogonal basis of a target domain is calculated based on the oversampling factor, where the target domain includes at least one of a first domain and a second domain.
  • processing module 402 is also used to:
  • Input the target coefficient to the first AI network model for quantification processing, and the target coefficient includes any of the following:
  • a preset number of coefficients corresponding to the target orthogonal basis and the preset coefficients is a preset number of coefficients corresponding to the target orthogonal basis and the preset coefficients.
  • the input length of the first AI network model matches the number of the input target coefficients.
  • the M orthogonal bases include the target orthogonal base and other orthogonal bases other than the target orthogonal base, and coefficients corresponding to the other orthogonal bases are the preset coefficients.
  • the preset coefficient satisfies any one of the following:
  • the preset coefficient is associated with the first AI network model
  • the preset coefficients corresponding to the other orthogonal bases are the same;
  • the preset coefficients corresponding to the other orthogonal bases are different, and one of the other orthogonal bases corresponds to one preset coefficient;
  • the preset coefficient is 0.
  • the M orthogonal bases are all orthogonal bases of the target domain, and the target domain includes at least one of the first domain and the second domain.
  • processing module 402 is also used to:
  • reporting module 403 is also used to:
  • the beams corresponding to the spatial domain orthogonal basis selected on each polarization are the same, and the coefficients on the spatial domain orthogonal basis selected on each polarization are jointly sorted.
  • the coefficients on the orthogonal basis of the first domain and the coefficients on the orthogonal basis of the second domain are sorted separately; or,
  • the coefficients on the orthogonal basis of the first domain and the coefficients on the orthogonal basis of the second domain are jointly sorted.
  • reporting module 403 is also used to:
  • the reporting module 403 is also used to:
  • the processing module 402 is also used to:
  • An orthogonal basis is determined based on the CSI-RS port, and a coefficient of the channel information on the orthogonal basis determined based on the CSI-RS port is calculated.
  • the device can process the channel information based on a first AI network model by calculating the coefficient of the channel information on an orthogonal basis of at least one of the first domain and the second domain, and also There is no need to configure different AI network models for channel information of different lengths, thereby saving the power consumption of network-side equipment for training the AI network model, saving the transmission overhead for the AI network model between the network-side equipment and the device, and also Reduce the power consumption of the device.
  • the channel characteristic information transmission device 400 in the embodiment of the present application may be an electronic device, such as an electronic device with an operating system, or may be a component in the electronic device, such as an integrated circuit or chip.
  • the electronic device may be a terminal or other devices other than the terminal.
  • terminals may include but are not limited to the types of terminals 11 listed above, and other devices may be servers, network attached storage (Network Attached Storage, NAS), etc., which are not specifically limited in the embodiment of this application.
  • the channel characteristic information transmission device 400 provided by the embodiment of the present application can implement each process implemented by the terminal in the method embodiment of Figure 2 and achieve the same technical effect. To avoid duplication, the details will not be described here.
  • Figure 5 is a structural diagram of another channel characteristic information transmission device provided by an embodiment of the present application. As shown in Figure 5, the channel characteristic information transmission device 500 includes:
  • the second receiving module 501 is used to receive channel characteristic information reported by the terminal;
  • the channel characteristic information is that the terminal calculates the coefficients of the channel information on an orthogonal basis of at least one of the first domain and the second domain, and inputs the coefficients into the first AI network model for quantization processing. Output the obtained information.
  • the first domain is the air domain
  • the second domain is the frequency domain
  • the maximum number of orthogonal bases in the first domain is the number of CSI-RS ports
  • the orthogonal bases in the second domain are The maximum number of bases is the number of frequency domain sampling points.
  • the device also includes:
  • the sending module is configured to send first indication information to the terminal, where the first indication information is used to indicate the orthogonal base used by the terminal, or to indicate the number of orthogonal bases used by the terminal.
  • the second receiving module 501 is also used to:
  • the second receiving module 501 is also used to:
  • the device also includes:
  • Coding module Used to encode the orthogonal base used by the terminal into the CSI-RS port.
  • the terminal can process the channel information based on a first AI network model by calculating the coefficient of the channel information on the orthogonal basis of at least one of the first domain and the second domain, and then the The device does not need to train different AI network models for channel information of different lengths, thereby saving the power consumption of the device in training the AI network model, and also saving the transmission overhead of the AI network model between the device and the terminal.
  • the channel characteristic information transmission device 500 provided by the embodiment of the present application can implement each process implemented by the network side device in the method embodiment of Figure 3, and achieve the same technical effect. To avoid duplication, the details will not be described here.
  • this embodiment of the present application also provides a communication device 600, which includes a processor 601 and a memory 602.
  • the memory 602 stores programs or instructions that can be run on the processor 601, for example.
  • the communication device 600 is a terminal, when the program or instruction is executed by the processor 601, each step of the method embodiment described in Figure 2 is implemented, and the same technical effect can be achieved.
  • the communication device 600 is a network-side device, when the program or instruction is executed by the processor 601, each step of the method embodiment described in FIG. 3 is implemented, and the same technical effect can be achieved. To avoid duplication, the details will not be described here.
  • Embodiments of the present application also provide a terminal, including a processor and a communication interface.
  • the processor is configured to obtain channel information and calculate the channel information on an orthogonal basis of at least one of the first domain and the second domain. coefficients, and input the coefficients into the first artificial intelligence AI network model for quantification processing to obtain the channel characteristic information output by the first AI network model.
  • the communication interface is used to report the channel characteristic information to the network side device. .
  • This terminal embodiment corresponds to the above-mentioned terminal-side method embodiment. Each implementation process and implementation manner of the above-mentioned method embodiment can be applied to this terminal embodiment, and can achieve the same technical effect.
  • FIG. 7 is a schematic diagram of the hardware structure of a terminal that implements an embodiment of the present application.
  • the terminal 700 includes but is not limited to: a radio frequency unit 701, a network module 702, an audio output unit 703, an input unit 704, a sensor 705, a display unit 706, a user input unit 707, an interface unit 708, a memory 709, a processor 710, etc. At least some parts.
  • the terminal 700 may also include a power supply (such as a battery) that supplies power to various components.
  • the power supply may be logically connected to the processor 710 through a power management system, thereby managing charging, discharging, and power consumption through the power management system. Management and other functions.
  • the terminal structure shown in Figure 7 does not constitute a limitation on the terminal.
  • the terminal can include It may include more or fewer components than those shown in the figures, or combine certain components, or arrange different components, which will not be described again here.
  • the input unit 704 may include a graphics processing unit (Graphics Processing Unit, GPU) 7041 and a microphone 7042.
  • the graphics processor 7041 is responsible for the image capture device (GPU) in the video capture mode or the image capture mode. Process the image data of still pictures or videos obtained by cameras (such as cameras).
  • the display unit 706 may include a display panel 7061, which may be configured in the form of a liquid crystal display, an organic light emitting diode, or the like.
  • the user input unit 707 includes a touch panel 7071 and at least one of other input devices 7072 .
  • Touch panel 7071 also called touch screen.
  • the touch panel 7071 may include two parts: a touch detection device and a touch controller.
  • Other input devices 7072 may include but are not limited to physical keyboards, function keys (such as volume control keys, switch keys, etc.), trackballs, mice, and joysticks, which will not be described again here.
  • the radio frequency unit 701 after receiving downlink data from the network side device, can transmit it to the processor 710 for processing; in addition, the radio frequency unit 701 can send uplink data to the network side device.
  • the radio frequency unit 701 includes, but is not limited to, an antenna, amplifier, transceiver, coupler, low noise amplifier, duplexer, etc.
  • Memory 709 may be used to store software programs or instructions as well as various data.
  • the memory 709 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 for at least one function (such as a sound playback function, Image playback function, etc.) etc.
  • memory 709 may include volatile memory or non-volatile memory, or memory 709 may include both volatile and non-volatile memory.
  • 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), electrically removable memory. Erase programmable read-only memory (Electrically EPROM, EEPROM) or flash 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 link 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 synchronous link dynamic random access memory
  • SLDRAM direct memory bus
  • the processor 710 may include one or more processing units; optionally, the processor 710 integrates an application processor and a modem processor, where the application processor mainly handles operations related to the operating system, user interface, application programs, etc., Modem processors mainly process wireless communication signals, such as baseband processors. It can be understood that the above-mentioned modem processor may not be integrated into the processor 710.
  • the processor 710 is used to obtain channel information; and, calculate coefficients of the channel information on an orthogonal basis of at least one of the first domain and the second domain, and input the coefficients to the first artificial
  • the intelligent AI network model performs quantification processing to obtain the channel characteristic information output by the first AI network model
  • the radio frequency unit 701 is used to report the channel characteristic information to the network side device.
  • the first domain is the spatial domain
  • the second domain is the frequency domain
  • the maximum number of orthogonal bases of the first domain is The number of ports of the channel state information reference signal CSI-RS
  • the maximum number of orthogonal bases in the second domain is the number of frequency domain sampling points.
  • the radio frequency unit 701 is also used for:
  • processor 710 is also used to:
  • the length of the coefficients is consistent with the orthogonal basis used by the first indication information.
  • the number of cross bases matches.
  • the orthogonal bases used in the first domain are all orthogonal bases in the spatial domain.
  • the processor 710 is also configured to:
  • the first indication information Based on the first indication information, determine the orthogonal basis adopted by the second domain, and the first indication information is used to indicate the orthogonal basis adopted by the second domain;
  • the orthogonal basis is determined through a protocol.
  • the processor 710 is also configured to:
  • An oversampling factor is determined, and a coefficient of the channel information on an orthogonal basis of a target domain is calculated based on the oversampling factor, where the target domain includes at least one of a first domain and a second domain.
  • processor 710 is also used to:
  • Input the target coefficient to the first AI network model for quantification processing, and the target coefficient includes any of the following:
  • a preset number of coefficients corresponding to the target orthogonal basis and the preset coefficients is a preset number of coefficients corresponding to the target orthogonal basis and the preset coefficients.
  • the input length of the first AI network model matches the number of the input target coefficients.
  • the M orthogonal bases include the target orthogonal base and other orthogonal bases other than the target orthogonal base, and coefficients corresponding to the other orthogonal bases are the preset coefficients.
  • the preset coefficient satisfies any one of the following:
  • the preset coefficient is associated with the first AI network model
  • the preset coefficients corresponding to the other orthogonal bases are the same;
  • the preset coefficients corresponding to the other orthogonal bases are different, and one of the other orthogonal bases corresponds to one preset coefficient;
  • the preset coefficient is 0.
  • the M orthogonal bases are all orthogonal bases of the target domain, and the target domain includes at least one of the first domain and the second domain.
  • processor 710 is also used to:
  • the terminal calculates coefficients of the channel information on an orthogonal basis of at least one of the first domain and the second domain, sorts the coefficients, and inputs the sorted coefficients into the first AI network
  • the model is quantified.
  • the radio frequency unit 701 is also used for:
  • the beams corresponding to the spatial domain orthogonal basis selected on each polarization are the same, and the coefficients on the spatial domain orthogonal basis selected on each polarization are jointly sorted.
  • the coefficients on the orthogonal basis of the first domain and the coefficients on the orthogonal basis of the second domain are sorted separately; or,
  • the coefficients on the orthogonal basis of the first domain and the coefficients on the orthogonal basis of the second domain are jointly sorted.
  • the radio frequency unit 701 is also used for:
  • the radio frequency unit 701 is also used to:
  • the processor 710 is also used to:
  • An orthogonal basis is determined based on the CSI-RS port, and a coefficient of the channel information on the orthogonal basis determined based on the CSI-RS port is calculated.
  • the terminal can process the channel information based on a first AI network model by calculating the coefficients of the channel information on at least one of the orthogonal bases in the first domain and the second domain, and there is no need to Configuring different AI network models for channel information of different lengths can save the power consumption of network-side devices training AI network models, save the transmission overhead of AI network models between network-side devices and terminals, and also reduce the power of terminals. Consumption.
  • Embodiments of the present application also provide a network-side device, including a processor and a communication interface.
  • the communication interface is used to receive channel characteristic information reported by a terminal.
  • the channel characteristic information calculates channel information for the terminal in the first domain. and the coefficients on the orthogonal basis of at least one of the second domain, and input the coefficients into the first AI network model for quantization processing and then output the obtained information.
  • This network-side device embodiment corresponds to the above-mentioned network-side device method embodiment.
  • Each implementation process and implementation manner of the above-mentioned method embodiment can be applied to this network-side device embodiment, and the same technology can be achieved. Technological effect.
  • the embodiment of the present application also provides a network side device.
  • the network side device 800 includes: an antenna 81 , a radio frequency device 82 , a baseband device 83 , a processor 84 and a memory 85 .
  • the antenna 81 is connected to the radio frequency device 82 .
  • the radio frequency device 82 receives information through the antenna 81 and sends the received information to the baseband device 83 for processing.
  • the baseband device 83 processes the information to be sent and sends it to the radio frequency device 82.
  • the radio frequency device 82 processes the received information and then sends it out through the antenna 81.
  • the method performed by the network side device in the above embodiment can be implemented in the baseband device 83, which includes a baseband processor.
  • the baseband device 83 may include, for example, at least one baseband board on which multiple chips are disposed, as shown in FIG. Program to perform the network device operations shown in the above method embodiments.
  • the network side device may also include a network interface 86, which is, for example, a common public radio interface (CPRI).
  • a network interface 86 which is, for example, a common public radio interface (CPRI).
  • CPRI common public radio interface
  • the network side device 800 in this embodiment of the present invention also includes: instructions or programs stored in the memory 85 and executable on the processor 84.
  • the processor 84 calls the instructions or programs in the memory 85 to execute the various operations shown in Figure 5. The method of module execution and achieving the same technical effect will not be described in detail here to avoid duplication.
  • Embodiments of the present application also provide a readable storage medium.
  • Programs or instructions are stored on the readable storage medium.
  • the program or instructions are executed by a processor, each process of the method embodiment described in Figure 2 is implemented, or Each process of the method embodiment described in Figure 3 above can achieve the same technical effect. To avoid repetition, it will not be described again here.
  • the processor is the processor in the terminal described in the above embodiment.
  • the readable storage medium includes computer readable storage media, such as computer read-only memory ROM, random access memory RAM, magnetic disk or optical disk, etc.
  • An 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.
  • the processor is used to run programs or instructions to implement the method described in Figure 2.
  • chips mentioned in the embodiments of this application may also be called system-on-chip, system-on-a-chip, system-on-chip or system-on-chip, etc.
  • Embodiments of the present application further provide a computer program/program product.
  • the computer program/program product is stored in a storage medium.
  • the computer program/program product is executed by at least one processor to implement the method described in Figure 2 above.
  • Each process of the embodiment, or each process of implementing the above method embodiment described in Figure 3, can achieve the same technical effect. To avoid repetition, it will not be described again here.
  • Embodiments of the present application also provide a communication system, including: a terminal and a network side device.
  • the terminal can be used to perform the steps of the channel characteristic information transmission method as shown in Figure 2.
  • the network side device can be used to perform the steps of the channel characteristic information transmission method as shown in the above figure. The steps of the channel characteristic information transmission method described in 3.
  • the methods of the above embodiments can be implemented by means of software plus the necessary general hardware platform. Of course, it can also be implemented 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 a computer software product that is essentially or contributes to the existing technology.
  • the computer software product is stored in a storage medium (such as ROM/RAM, disk , CD), including several instructions to cause a terminal (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in various embodiments of this application.

Landscapes

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

Abstract

本申请公开了一种信道特征信息传输方法、装置、终端及网络侧设备，属于通信技术领域，本申请实施例的信道特征信息传输方法包括：终端获取信道信息；所述终端计算所述信道信息在第一域和第二域中的至少一者的正交基上的系数，并将所述系数输入至第一人工智能AI网络模型进行量化处理，获取所述第一AI网络模型输出的信道特征信息；所述终端向网络侧设备上报所述信道特征信息。

Description

信道特征信息传输方法、装置、终端及网络侧设备
相关申请的交叉引用
本申请主张在2022年4月1日在中国提交的中国专利申请No.202210349446.X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，具体涉及一种信道特征信息传输方法、装置、终端及网络侧设备。
背景技术
随着科学技术的发展，人们已经开始研究将人工智能(Artificial Intelligence，AI)网络模型应用在通信系统中，例如网络侧设备和终端之间可以基于AI网络模型来传输通信数据。目前，基于AI网络模型的信道信息压缩反馈方案，通过在终端对信道信息进行压缩编码，在网络侧对压缩后的内容进行解码，从而恢复信道信息，此时网络侧的解码网络和终端侧的编码网络需要联合训练，以达到合理的匹配度。但是，对于不同长度的信道信息，通常对应不同的AI网络模型，导致终端侧和网络侧的功耗相应增加。
发明内容
本申请实施例提供一种信道特征信息传输方法、装置、终端及网络侧设备，能够解决相关技术中对于不同长度的信道信息需要配置不同的AI网络模型的问题。
第一方面，提供了一种信道特征信息传输方法，包括：
终端获取信道信息；
所述终端计算所述信道信息在第一域和第二域中的至少一者的正交基上的系数，并将所述系数输入至第一人工智能AI网络模型进行量化处理，获取所述第一AI网络模型输出的信道特征信息；
所述终端向网络侧设备上报所述信道特征信息。
第二方面，提供了一种信道特征信息传输方法，包括：
网络侧设备接收终端上报的信道特征信息；
其中，所述信道特征信息为所述终端计算信道信息在第一域和第二域中的至少一者的正交基上的系数，并将所述系数输入第一AI网络模型进行量化处理后输出得到的信息。
第三方面，提供了一种信道特征信息传输装置，包括：
获取模块，用于获取信道信息；
处理模块，用于计算所述信道信息在第一域和第二域中的至少一者的正交基上的系数，并将所述系数输入至第一人工智能AI网络模型进行量化处理，获取所述第一AI网络模型输出的信道特征信息；
上报模块，用于向网络侧设备上报所述信道特征信息。
第四方面，提供了一种信道特征信息传输装置，包括：
第二接收模块，用于接收终端上报的信道特征信息；
其中，所述信道特征信息为所述终端计算信道信息在第一域和第二域中的至少一者的正交基上的系数，并将所述系数输入第一AI网络模型进行量化处理后输出得到的信息。
第五方面，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信道特征信息传输方法的步骤。
第六方面，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信道信息，计算所述信道信息在第一域和第二域中的至少一者的正交基上的系数，并将所述系数输入至第一人工智能AI网络模型进行量化处理，获取所述第一AI网络模型输出的信道特征信息，所述通信接口用于向网络侧设备上报所述信道特征信息。
第七方面，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二方面所述的信道特征信息传输方法的步骤。
第八方面，提供了一种网络侧设备，包括处理器及通信接口，所述通信接口用于接收终端上报的信道特征信息其中，所述信道特征信息为所述终端计算信道信息在第一域和第二域中的至少一者的正交基上的系数，并将所述系数输入第一AI网络模型进行量化处理后输出得到的信息。
第九方面，提供了一种通信系统，包括：终端及网络侧设备，所述终端可用于执行如第一方面所述的信道特征信息传输方法的步骤，所述网络侧设备可用于执行如第二方面所述的信道特征信息传输方法的步骤。
第十方面，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信道特征信息传输方法的步骤，或者实现如第二方面所述的信道特征信息传输方法的步骤。
第十一方面，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信道特征信息传输方法，或实现如第二方面所述的信道特征信息传输方法。
第十二方面，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信道特征信息传输方法的步骤，或实现如第二方面所述的信道特征信息传输方法的步骤。
在本申请实施例中，终端计算信道信息在第一域和第二域中至少一者的正交基上的系数，将所述系数输入第一AI网络模型进行量化处理，获取第一AI网络模型输出的信道特征信息，将所述信道特征信息上报给网络侧设备。这样，终端通过计算信道信息在第一域和第二域中至少一者的正交基上的系数，基于一个第一AI网络模型就能够实现对信道信息的处理，也就无需针对不同长度的信道信息分别配置不同的AI网络模型，进而能够节省网络侧设备训练AI网络模型的功耗，节省网络侧设备和终端之间针对AI网络模型的传输开销，也能够降低终端的功耗。
附图说明
图1是本申请实施例可应用的一种无线通信系统的框图；
图2是本申请实施例提供的一种信道特征信息传输方法的流程图；
图3是本申请实施例提供的另一种信道特征信息传输方法的流程图；
图4是本申请实施例提供的一种信道特征信息传输装置的结构图；
图5是本申请实施例提供的另一种信道特征信息传输装置的结构图；
图6是本申请实施例提供的一种通信设备的结构图；
图7是本申请实施例提供的一种终端的结构图；
图8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)系统，还可用于其他无线通信系统，诸如码分多址(Code Division Multiple Access，CDMA)、时分多址(Time Division Multiple Access，TDMA)、频分多址(Frequency Division Multiple Access，FDMA)、正交频分多址(Orthogonal Frequency Division Multiple Access，OFDMA)、单载波频分多址(Single-carrier Frequency Division Multiple Access，SC-FDMA)和其他系统。本申请实施例中的术语“系统”和“网 络”常被可互换地使用，所描述的技术既可用于以上提及的系统和无线电技术，也可用于其他系统和无线电技术。以下描述出于示例目的描述了新空口(New Radio，NR)系统，并且在以下大部分描述中使用NR术语，但是这些技术也可应用于NR系统应用以外的应用，如第6代(6th Generation，6G)通信系统。
图1示出本申请实施例可应用的一种无线通信系统的框图。无线通信系统包括终端11和网络侧设备12。其中，终端11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)、车载设备(Vehicle User Equipment，VUE)、行人终端(Pedestrian 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系统中的基站为例进行介绍，并不限定基站的具体类型。
为更好地理解本申请的技术方案，以下对本申请实施例中可能涉及的相关概念进行解释说明。
由信息论可知，准确的信道状态信息(channel state information，CSI)对信道容量至关重要。尤其是对于多天线系统来讲，发送端可以根据CSI优化信号的发送，使其更加匹配信道的状态。如：信道质量指示(channel quality indicator，CQI)可以用来选择合适的调制编码方案(modulation and coding scheme，MCS)实现链路自适应；预编码矩阵指示(precoding matrix indicator，PMI)可以用来实现特征波束成形(eigen beamforming)从而最大化接收信号的强度，或者用来抑制干扰(如小区间干扰、多用户之间干扰等)。因此，自从多天线技术(multi-input multi-output，MIMO)被提出以来，CSI获取一直都是研究热点。
通常，网络侧设备(例如基站)在在某个时隙(slot)的某些时频资源上发送CSI参 考信号(channel state information reference signal，CSI-RS)，终端根据CSI-RS进行信道估计，计算这个slot上的信道信息，通过码本将PMI反馈给基站，基站根据终端反馈的码本信息组合出信道信息，在下一次CSI上报之前，基站以此进行数据预编码及多用户调度。
为了进一步减少CSI反馈开销，终端可以将每个子带上报PMI改成按照延迟(delay)上报PMI，由于delay域的信道更集中，用更少的delay的PMI就可以近似表示全部子带的PMI，即将delay域信息压缩之后再上报。
同样，为了减少开销，基站可以事先对CSI-RS进行预编码，将编码后的CSI-RS发送给终端，终端看到的是经过编码之后的CSI-RS对应的信道，终端只需要在网络侧指示的端口中选择若干个强度较大的端口，并上报这些端口对应的系数即可。
进一步地，为了更好地压缩信道信息，可以使用神经网络或机器学习的方法。具体地，在终端通过AI网络模型对信道信息进行压缩编码，在基站通过AI网络模型对压缩后的内容进行解码，从而恢复信道信息，此时基站的用于解码的AI网络模型和终端的用于编码的AI网络模型需要联合训练，达到合理的匹配度。通过终端的用于编码的AI网络模型和基站的用于解码的AI网络模型组成联合的神经网络模型，由网络侧进行联合训练，训练完成后，基站将用于编码的AI网络模型发送给终端。
终端估计CSI-RS，计算信道信息，将计算的信道信息或者原始的估计到的信道信息通过AI网络模型得到编码结果，将编码结果发送给基站，基站接收编码后的结果，输入到AI网络模型中进行解码，恢复信道信息。
信道信息的编解码是针对整个信道信息的，要求输入的数量是固定的，针对不同数量的输入，例如不同宽带下，子带数量不同，信道估计得到的信道矩阵数量不同，或者，不同端口数配置，信道矩阵的维度不同，都会导致AI网络模型的输入的数量不同，针对每一种长度，都需要单独训练对应的AI网络模型，以实现不同数量的信道信息编码。
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信道特征信息传输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信道特征信息传输方法的流程图，该方法应用于终端。如图2所示，所述方法包括以下步骤：
步骤201、终端获取信道信息。
可选地，终端可以是在网络侧设备指定的位置检测CSI参考信号(CSI Reference Signal，CSI-RS)或跟踪参考信号(Tracking Reference Signal，TRS)，并进行信道估计，得到信道信息。例如，终端通过CSI-RS信道估计，获得每个子带的信道矩阵，所述信道信息可以是每个子带的信道矩阵，或者是信道矩阵经过预编码计算得到的对应的预编码矩阵，或者是特定层的预编码矩阵等。其中，所述信道矩阵为Nr×Nt的矩阵，其中Nr是接收天线数，Nt是CSI-RS端口数。
步骤202、所述终端计算所述信道信息在第一域和第二域中的至少一者的正交基上的系数，并将所述系数输入至第一AI网络模型进行量化处理，获取所述第一AI网络模型输 出的信道特征信息。
可选地，所述第一域为空域，或者也称角度域；所述第二域为频域，或者也称时延域。
本申请实施例中，终端在获得信道信息后，可以是计算所述信道信息在第一域的正交基上的系数；或者也可以是计算所述信道信息在第二域的正交基上的系数；或者是计算所述信道信息分别在第一域的正交基上的系数以及在第二域的正交基上的系数，例如空域选择4个正交基，频域选择4个正交基，终端计算信道信息在这些正交基上的共16个系数；或者还可以是计算信道信息在第一域和第二域的联合正交基上的系数，例如空域选择8个正交基，频域选择4个正交基，一共是32个空频联合正交基，则终端可以是计算信道信息在这32个正交基上的系数，或者终端还可以是从这32个空频联合正交基中选择24个正交基，计算信道信息在选择的24个正交基上的系数。
进一步地，终端将计算得到的系数输入至第一AI网络模型进行量化处理，获取所述第一AI网络模型输出的信道特征信息。例如，第一AI网络模型对输入的系数压缩编码成比特(bit)序列，所述第一AI网络模型输出的信道特征信息也即所述bit序列。
需要说明地，终端可以是将计算得到的全部系数输入第一AI网络模型，或者可以是从计算得到的系数中，选择一定数量的正交基对应的系数输入至第一AI网络模型。例如，终端在基于32个空频联合正交基，计算信道信息在这32个正交基上的系数后，可以是从中选择24个正交基的系数输入至第一AI网络模型。
步骤203、所述终端向网络侧设备上报所述信道特征信息。
可以理解地，终端在获取到第一AI网络模型输出的信道特征信息后，将所述信道特征信息上报给网络侧设备。网络侧设备包括与所述第一AI网络模型匹配的第二AI网络模型，第一AI网络模型和第二AI网络模型通过网络侧设备进行联合训练，网络侧设备将训练好的第一AI网络模型发送给终端。终端通过第一AI网络模型对输入的系数进行编码处理，输出信道特征信息，终端将信道特征信息上报给网络侧设备，网络侧设备将所述信道特征信息输入匹配的第二AI网络模型，第二AI网络模型对信道特征信息进行解码处理，得到第二AI网络模型输出的信道信息，进而网络侧设备通过第二AI网络模型实现对信道信息的恢复。这样，终端和网络侧设备也就能够通过匹配的AI网络模型实现对信道信息的编码和解码处理。
需要说明地，本申请实施例中提及的信道信息编码，不同于信道编码。
本申请实施例中，终端计算信道信息在第一域和第二域中至少一者的正交基上的系数，将所述系数输入第一AI网络模型进行量化处理，获取第一AI网络模型输出的信道特征信息，将所述信道特征信息上报给网络侧设备。这样，终端通过计算信道信息在第一域和第二域中至少一者的正交基上的系数，基于一个第一AI网络模型就能够实现对信道信息的处理，也就无需针对不同长度的信道信息分别配置不同的AI网络模型，进而能够节省网络侧设备训练AI网络模型的功耗，节省网络侧设备和终端之间针对AI网络模型的传输开销，也能够降低终端的功耗。
可选地，所述第一域为空域，所述第二域为频域。所述第一域的正交基可以是离散傅里叶变换(Discrete Fourier Transform，DFT)正交基、CSI-RS端口、波束(beam)中的至少一个。其中，DFT正交基可以是经过过采的正交基，或者也可以是没有经过过采的正交基。所述第二域的正交基可以是DFT正交基、延迟(delay)、时延抽头中的至少一个。
需要说明地，所述为正交基投影的一个进阶，以预编码矩阵为例，CSI-RS端口数是32，则一个layer的预编码矩阵可以是一个32*1的矩阵，投影是生成32个正交DFT向量，每个DFT向量长度为32，将这个预编码矩阵投影在32个正交DFT向量中，选择系数幅度较大的若干个，然后使用系数和/或对应的DFT向量作为预处理结果。过采则是在投影的时候，例如以4倍过采为例，生成4组32个正交DFT向量，每组32个DFT向量正交，组与组之间不正交，然后选择4组中最接近预编码矩阵的一组，再按照上面的方式投影。
可选地，所述第一域的正交基的最大个数为CSI-RS的端口数；所述第二域的正交基的最大个数为频域采样点的个数。
本申请实施例中，所述正交基的确定可以是通过网络侧设备指示。
可选地，所述方法还可以包括：
所述终端接收网络侧设备发送的第一指示信息，所述第一指示信息用于指示终端采用的正交基，或者用于指示终端采用的正交基的数量。
例如，网络侧设备通过第一指示信息指示终端在第一域采用N1个正交基，在第二域采用N2个正交基，则终端基于所述第一指示信息，在第一域选择N1个正交基，在第二域选择N2个正交基，并计算信道信息在第一域选择的N1个正交基上的系数，以及计算信道信息在第二域选择的N2个正交基上的系数，然后将计算得到的系数输入第一AI网络模型进行量化处理。
或者，所述第一指示信息还可以是直接指示终端采用的正交基，也即终端无需进行正交基的选择，终端基于所述第一指示信息能直接确定需要采用的正交基，进而计算信道信息在这些指示的正交基上的系数。
可选地，所述终端计算所述信道信息在第一域和第二域中的至少一者的正交基上的系数，并将所述系数输入至第一AI网络模型进行量化处理，包括：
所述终端基于所述第一指示信息，确定第一域和第二域中至少一者采用的正交基；
所述终端计算所述信道信息在所述采用的正交基上的系数，并将所述系数输入至第一AI网络模型进行量化处理，所述系数的长度与所述第一指示信息指示终端采用的正交基的数量匹配。
例如，所述第一指示信息用于指示第一域上采用的正交基为a1、a2、a3、a4，第二域上采用的正交基为b1、b2、b3、b4，则终端计算信道信息a1在b1、b2、b3、b4的系数，a2在b1、b2、b3、b4的系数……共计算得到16个系数，将计算得到的16个系数输入第一AI网络模型进行量化处理。可以理解地，所述第一指示信息也可以是仅指示终端在第一域上采用的正交基，或者仅指示在第二域上采用的正交基，本实施例不做具体赘述。
需要说明地，第一AI网络模型输入的系数长度与第一指示信息指示终端采用的正交基的数量匹配，进而终端也就能够通过正交基的数量来确定第一AI网络模型输入的系数的长度。
可选地，在所述第一域为空域，所述第二域为频域的情况下，所述第一域采用的正交基为所述空域的全部正交基。例如，第一指示信息可以是仅指示空域采用全部的正交基，对于频域的正交基不做指示；进而终端计算信道信息在空域的全部正交基上的系数，计算信道信息在频域的全部正交基上的系数，或者也可以是计算信道信息在频域的某些正交基上的系数，终端可以是自行确定频域采用的正交基。
或者，第一指示信息也可以是仅指示频域采用的正交基。
可选地，在所述第一域为空域，所述第二域为频域的情况下，所述终端基于所述第一指示信息，对第一域和第二域中至少一者采用的正交基进行选择，包括：
所述终端基于所述第一指示信息，确定所述第二域采用的正交基，所述第一指示信息用于指示所述第二域采用的正交基；
所述终端计算所述信道信息在选择的正交基上的系数，并将所述系数输入至第一AI网络模型进行量化处理，包括：
所述终端计算所述信道信息在所述第一域的所有正交基上的第一系数，以及计算所述信道信息在所述第二域采用的正交基上的第二系数，并将所述第一系数和所述第二系数输入至第一AI网络模型进行量化处理。
例如，第一指示信息仅指示频域采用的正交基，对于空域采用的正交基不做指示；这种情况下，空域选择全部的正交基，终端计算信道信息在空域的全部正交基上的第一系数，以及计算信道信息在指示的频域的正交基上的第二系数，将第一系数和第二系数输入第一AI网络模型进行量化处理。进而，在第一指示信息并未对空域采用的正交基进行指示的情况下，终端可以自行决定计算信道信息在空域的全部正交基上的系数，以确保终端对于信道信息在空域上的处理。
可选地，所述正交基的确定还可以是通过协议约定，也即终端基于协议约定确定采用的正交基。例如，协议约定空域选择全部的正交基，终端基于协议约定计算信道信息在空域的全部正交基上的系数。
可选地，在目标域的正交基为过采正交基的情况下，所述终端计算所述信道信息在第一域和第二域中的至少一者的正交基上的系数，包括：
所述终端确定过采因子，基于所述过采因子计算所述信道信息在目标域的正交基上的系数，所述目标域包括第一域和第二域中的至少一者。
例如，目标域为第一域，若第一域的正交基为过采正交基，终端确定第一域上正交基的过采因子，并基于所述过采因子计算信道信息在第一域的正交基上的系数。可选地，终端还可以向网络侧设备上报所述过采因子。
本申请实施例中，所述终端计算所述信道信息在第一域和第二域中的至少一者的正交 基上的系数，并将所述系数输入至第一AI网络模型进行量化处理，还可以包括：
所述终端计算所述信道信息在第一域和第二域中的至少一者的M个正交基上各自对应的系数，所述M个正交基包括至少一个目标正交基；
所述终端将目标系数输入至第一AI网络模型进行量化处理，所述目标系数包括如下任意一项：
全部所述目标正交基对应的系数；
预设数量的所述目标正交基对应的系数；
全部所述目标正交基对应的系数及预设系数；
预设数量的所述目标正交基对应的系数及预设系数。
例如，所述M为4，所述M可以是网络侧设备指示，或者也可以是终端自行选择。可选地，终端可以是计算信道信在第一域的4个正交基上的系数以及在第二域的4个正交基上的系数，假设目标正交基为第一域上的4个正交基，则终端可以是将第一域上的4个正交基对应的系数作为目标系数输入第一AI网络模型进行量化处理，或者也可以是选择第一域上的4个正交基中的其中2个对应的系数作为目标系数，或者还可以是将第一域上的4个正交基对应的系数与预设系数作为目标系数，还可以是选择第一域上的4个正交基中的其中2个对应的系数以及预设系数作为目标系数。这样，也就使得终端对于输入第一AI网络模型的目标系数的选择更为灵活。以上M、目标正交基及目标系数仅是举例说明，并不构成对本申请的限定。
其中，所述预设数量可以是网络侧设备配置，例如预设数量为预设比例，该预设比例的取值范围为0～1，例如目标正交基的数量为4，预设比例为50％，也即选择目标正交基中的2个正交基对应的系数作为目标系数。可选地，所述预设数量可以是目标正交基对应的系数中数值较大的前L个，L的数值小于等于目标正交基的数量。
可选地，所述第一AI网络模型的输入长度与输入的所述目标系数的数量匹配。例如，输入长度为目标系数的数量的2倍。
需要说明地，系数为复数，第一AI网络模型的输入为实数，系数可以是按照指定的顺序进行排序。
本申请实施例中，所述M个正交基可以是包括所述目标正交基及除所述目标正交基以外的其他正交基，所述其他正交基对应的系数为所述预设系数。可选地，所述预设系数可以是协议约定或者是网络侧设备配置，例如协议约定预设系数为0或者某个固定的数值。
可选地，所述预设系数满足如下任意一项：
所述预设系数与第一AI网络模型关联；
所述其他正交基对应的所述预设系数相同；
所述其他正交基对应的所述预设系数不同，一个所述其他正交基对应一个预设系数；
所述预设系数为0。
例如，所述预设系数是与第一AI网络模型关联的，由网络侧设备一起配置，例如网 络侧设备可以配置不同的第一AI网络模型对应不同的预设系数。
或者，M个正交基中除所述目标正交基以外的其他正交基对应的预设系数相同，例如所述预设系数为一个预设值，M个正交基中除所述目标正交基以外的其他正交基都使用该预设值。
或者，M个正交基中除所述目标正交基以外的每一个正交基各自对应一个预设系数，也即预设系数可以是一系列值，这些预设系数也可以是协议约定或者网络侧设备配置。
或者，还可以是协议约定或者网络侧设备配置所述预设系数为0。
本申请实施例中，通过预设系数的设置，能够降低第一AI网络模型对于输入的系数的处理复杂度，也就能够减少第一AI网络模型的网络结构大小，也使得网络侧设备对于第一AI网络模型的训练更加简单。
可选地，所述M个正交基为所述目标域的所有正交基，所述目标域包括所述第一域和所述第二域中的至少一者。例如目标域为第一域，第一域为空域，终端可以是计算信道信息在空域的全部正交基上的系数。
本申请实施例中，终端在将计算得到的系数输入第一AI网络模型之前，还可以对所述系数进行排序。
可选地，所述终端计算所述信道信息在第一域和第二域中的至少一者的正交基上的系数，并将所述系数输入至第一AI网络模型进行量化处理，包括：
所述终端计算所述信道信息在第一域和第二域中的至少一者的正交基上的系数，并对所述系数进行排序，将排序后的所述系数输入至第一AI网络模型进行量化处理。
例如，终端计算信道信息在第一域的正交基上的系数以及在第二域的正交基上的系数，并将计算得到的所有系数进行排序，例如可以是将系数按照幅度从大到小进行排序，或者可以是按照幅度从小到大进行排序等，系数的排序方式可以是协议约定，或者也可以是网络侧设备配置。进一步地，终端将排序后的系数输入至第一AI网络模型进行量化处理。这样，也就使得输入第一AI网络模型的系数更具规律性，更有利于第一AI网络模型对系数的处理。
可选地，所述方法还可以包括：
所述终端向网络侧设备上报排序后的所述系数对应的正交基的顺序，或者上报排序后的所述系数对应的正交基的顺序标识。
本申请实施例中，终端在对输入第一AI网络模型的系数进行排序，并将排序后的系数输入至第一AI网络模型进行处理，得到输出的信道特征信息后，终端可以是向网络侧设备上报排序后的所述系数对应的正交基的顺序，或者是上报排序后的所述系数对应的正交基的顺序标识。这样，也就使得网络侧设备能够基于上报的正交基的顺序或正交基的顺序标识，获知输入第一AI网络模型的系数的顺序，以更好地恢复信道信息。
可选地，在所述第一域为空域的情况下，每个极化上选择的空域正交基对应的波束相同，每个极化上选择的空域正交基上的系数联合排序。例如，终端可以是将信道信息在极 化后空域的正交基上计算得到的系数的平方和按照从大到小的顺序进行排序，终端上报的是排序后的系数对应的波束的顺序，极化的顺序可以是协议约定或者是与第一AI网络模型匹配。
可选地，所述第一域的正交基上的系数和所述第二域的正交基上的系数进行分开排序；或者，在所述目标域包括第一域和第二域的情况下，所述第一域的正交基上的系数和所述第二域的正交基上的系数进行联合排序。
本申请实施例中，所述方法还可以包括：
所述终端向网络侧设备上报采用的所述正交基。
例如，终端在第一域采用的正交基为a1、a2、a3、a4，第二域上采用的正交基为b1、b2、b3、b4，则终端向网络侧设备上报这些正交基，如第一域正交基a1、a2、a3、a4，第二域正交基b1、b2、b3、b4。进而，网络侧设备基于上报的终端所采用的正交基，以及通过第二AI网络模型恢复的这些正交基上的系数，也就能够恢复得到信道信息。
可选地，网络侧设备可以是有多个第二AI网络模型与终端的第一AI网络模型匹配，在网络侧设备包括与所述第一AI网络模型匹配的多个第二AI网络模型的情况下，所述方法还包括：
所述终端向网络侧设备上报最大系数对应的正交基的位置。
本申请实施例中，网络侧设备在接收到终端上报的信道特征信息，可以是将信道特征信息输入其中一个第二AI网络模型进行解码处理得到恢复的系数，网络侧设备比较解码得到的最大系数的正交基与终端上报的最大系数对应的正交基的位置是否一致，如果不一致，则网络侧设备可以更换一个第二AI网络模型对信道特征信息进行解码处理，以此来选择合适的第二AI网络模型恢复信道信息。
可选地，在网络侧设备将正交基编码至CSI-RS端口中的情况下，所述终端计算所述信道信息在第一域和第二域中的至少一者的正交基上的系数，包括：
所述终端基于所述CSI-RS端口确定正交基，并计算所述信道信息在基于所述CSI-RS端口确定的正交基上的系数。
本申请实施例中，网络侧设备可以是将终端采用的正交基通过预编码器(precoder)编码至CSI-RS端口中，则终端可以是基于所述CSI-RS端口来确定采用的正交基，并计算信道信息在确定采用的正交基上的系数，将所述系数输入至第一AI网络模型中。这样，终端也就能够直接基于CSI-RS端口来确定正交基，无需终端再进行正交基的选择，更有助于简化终端的处理流程。
请参照图3，图3是本申请实施例提供的另一种信道特征信息传输方法的流程图，该方法应用于网络侧设备。如图3所示，所述方法包括以下步骤：
步骤301、网络侧设备接收终端上报的信道特征信息；
其中，所述信道特征信息为所述终端计算信道信息在第一域和第二域中的至少一者的正交基上的系数，并将所述系数输入第一AI网络模型进行量化处理后输出得到的信息。
需要说明地，网络侧设备包括与所述第一AI网络模型匹配的第二AI网络模型，第一AI网络模型和第二AI网络模型通过网络侧设备进行联合训练，网络侧设备将训练好的第一AI网络模型发送给终端。终端通过第一AI网络模型对输入的系数进行编码处理，输出信道特征信息，终端将信道特征信息上报给网络侧设备，网络侧设备将所述信道特征信息输入匹配的第二AI网络模型，第二AI网络模型对信道特征信息进行解码处理，得到第二AI网络模型输出的信道信息，进而网络侧设备通过第二AI网络模型实现对信道信息的恢复。这样，终端和网络侧设备也就能够通过匹配的AI网络模型实现对信道信息的编码和解码处理。
本申请实施例中，终端通过计算信道信息在第一域和第二域中至少一者的正交基上的系数，基于一个第一AI网络模型就能够实现对信道信息的处理，进而网络侧设备也就无需针对不同长度的信道信息分别训练不同的AI网络模型，进而能够节省网络侧设备训练AI网络模型的功耗，也能够节省网络侧设备和终端之间针对AI网络模型的传输开销。
可选地，所述第一域为空域，所述第二域为频域。
可选地，所述第一域的正交基的最大个数为CSI-RS的端口数；所述第二域的正交基的最大个数为频域采样点的个数。
可选地，所述网络侧设备接收终端上报的信道特征信息之前，所述方法还包括：
所述网络侧设备向终端发送第一指示信息，所述第一指示信息用于指示终端采用的正交基，或者用于指示终端采用的正交基的数量。
例如，网络侧设备通过第一指示信息指示终端在第一域采用N1个正交基，在第二域采用N2个正交基，则终端基于所述第一指示信息，在第一域选择N1个正交基，在第二域选择N2个正交基，并计算信道信息在第一域选择的N1个正交基上的系数，以及计算信道信息在第二域选择的N2个正交基上的系数，然后将计算得到的系数输入第一AI网络模型进行量化处理。
或者，所述第一指示信息还可以是直接指示终端采用的正交基，也即终端无需进行正交基的选择，终端基于所述第一指示信息能直接确定需要采用的正交基，进而计算信道信息在这些指示的正交基上的系数。
本申请实施例中，所述方法还包括：
所述网络侧设备接收所述终端上报的所采用的正交基。
这样，网络侧设备基于上报的终端所采用的正交基，以及通过第二AI网络模型恢复的这些正交基上的系数，也就能够恢复得到信道信息。
可选地，所述方法还包括：
在网络侧设备包括与所述第一AI网络模型匹配的多个第二AI网络模型的情况下，所述网络侧设备接收所述终端上报的最大系数对应的正交基的位置。
本申请实施例中，网络侧设备在接收到终端上报的信道特征信息，可以是将信道特征信息输入其中一个第二AI网络模型进行解码处理得到恢复的系数，网络侧设备比较解码 得到的最大系数的正交基与终端上报的最大系数对应的正交基的位置是否一致，如果不一致，则网络侧设备可以更换一个第二AI网络模型对信道特征信息进行解码处理，以此来选择合适的第二AI网络模型恢复信道信息。
可选地，所述方法还可以包括：
所述网络侧设备将正交基编码至CSI-RS端口中。
本申请实施例中，网络侧设备可以是将终端采用的正交基通过预编码器(precoder)编码至CSI-RS端口中，则终端可以是基于所述CSI-RS端口来确定采用的正交基，并计算信道信息在确定采用的正交基上的系数，将所述系数输入至第一AI网络模型中。这样，终端也就能够直接基于CSI-RS端口来确定正交基，无需终端再进行正交基的选择，更有助于简化终端的处理流程。
需要说明地，本申请实施例提供的应用于网络侧设备的信道特征信息传输方法与上述应用于终端的方法对应，本申请实施例中涉及的相关概念及具体实现流程可以是参照上述图2所述实施例中的描述，为避免重复，本实施例不再赘述。
本申请实施例提供的信道特征信息传输方法，执行主体可以为信道特征信息传输装置。本申请实施例中以信道特征信息传输装置执行信道特征信息传输方法为例，说明本申请实施例提供的信道特征信息传输装置。
请参照图4，图4是本申请实施例提供的一种信道特征信息传输装置的结构图，如图4所示，所述信道特征信息传输装置400包括：
获取模块401，用于获取信道信息；
处理模块402，用于计算所述信道信息在第一域和第二域中的至少一者的正交基上的系数，并将所述系数输入至第一人工智能AI网络模型进行量化处理，获取所述第一AI网络模型输出的信道特征信息；
上报模块403，用于向网络侧设备上报所述信道特征信息。
可选地，所述第一域为空域，所述第二域为频域，所述第一域的正交基的最大个数为信道状态信息参考信号CSI-RS的端口数；
所述第二域的正交基的最大个数为频域采样点的个数。
可选地，所述装置还包括：
第一接收模块，用于接收网络侧设备发送的第一指示信息，所述第一指示信息用于指示终端采用的正交基，或者用于指示终端采用的正交基的数量。
可选地，所述处理模块402还用于：
基于所述第一指示信息，确定第一域和第二域中至少一者采用的正交基；
计算所述信道信息在所述采用的正交基上的系数，并将所述系数输入至第一AI网络模型进行量化处理，所述系数的长度与所述第一指示信息指示终端采用的正交基的数量匹配。
可选地，在所述第一域为空域，所述第二域为频域的情况下，所述第一域采用的正交 基为所述空域的全部正交基。
可选地，在所述第一域为空域，所述第二域为频域的情况下，所述处理模块402还用于：
基于所述第一指示信息，确定所述第二域采用的正交基，所述第一指示信息用于指示所述第二域采用的正交基；
计算所述信道信息在所述第一域的所有正交基上的第一系数，以及计算所述信道信息在所述第二域采用的正交基上的第二系数，并将所述第一系数和所述第二系数输入至第一AI网络模型进行量化处理。
可选地，所述正交基的确定通过协议约定。
可选地，在目标域的正交基为过采正交基的情况下，所述处理模块402还用于：
确定过采因子，基于所述过采因子计算所述信道信息在目标域的正交基上的系数，所述目标域包括第一域和第二域中的至少一者。
可选地，所述处理模块402还用于：
计算所述信道信息在第一域和第二域中的至少一者的M个正交基上各自对应的系数，所述M个正交基包括至少一个目标正交基；
将目标系数输入至第一AI网络模型进行量化处理，所述目标系数包括如下任意一项：
全部所述目标正交基对应的系数；
预设数量的所述目标正交基对应的系数；
全部所述目标正交基对应的系数及预设系数；
预设数量的所述目标正交基对应的系数及预设系数。
可选地，所述第一AI网络模型的输入长度与输入的所述目标系数的数量匹配。
可选地，所述M个正交基包括所述目标正交基及除所述目标正交基以外的其他正交基，所述其他正交基对应的系数为所述预设系数。
可选地，所述预设系数满足如下任意一项：
所述预设系数与第一AI网络模型关联；
所述其他正交基对应的所述预设系数相同；
所述其他正交基对应的所述预设系数不同，一个所述其他正交基对应一个预设系数；
所述预设系数为0。
可选地，所述M个正交基为所述目标域的所有正交基，所述目标域包括所述第一域和所述第二域中的至少一者。
可选地，所述处理模块402还用于：
计算所述信道信息在第一域和第二域中的至少一者的正交基上的系数，并对所述系数进行排序，将排序后的所述系数输入至第一AI网络模型进行量化处理。
可选地，所述上报模块403还用于：
向网络侧设备上报排序后的所述系数对应的正交基的顺序，或者上报排序后的所述系 数对应的正交基的顺序标识。
可选地，在所述第一域为空域的情况下，每个极化上选择的空域正交基对应的波束相同，每个极化上选择的空域正交基上的系数联合排序。
可选地，所述第一域的正交基上的系数和所述第二域的正交基上的系数进行分开排序；或者，
在所述目标域包括第一域和第二域的情况下，所述第一域的正交基上的系数和所述第二域的正交基上的系数进行联合排序。
可选地，所述上报模块403还用于：
向网络侧设备上报采用的所述正交基。
可选地，在网络侧设备包括与所述第一AI网络模型匹配的多个第二AI网络模型的情况下，所述上报模块403还用于：
向网络侧设备上报最大系数对应的正交基的位置。
可选地，在网络侧设备将正交基编码至CSI-RS端口中的情况下，所述处理模块402还用于：
基于所述CSI-RS端口确定正交基，并计算所述信道信息在基于所述CSI-RS端口确定的正交基上的系数。
本申请实施例中，所述装置通过计算信道信息在第一域和第二域中至少一者的正交基上的系数，基于一个第一AI网络模型就能够实现对信道信息的处理，也就无需针对不同长度的信道信息分别配置不同的AI网络模型，进而能够节省网络侧设备训练AI网络模型的功耗，节省网络侧设备和所述装置之间针对AI网络模型的传输开销，也能够降低所述装置的功耗。
本申请实施例中的信道特征信息传输装置400可以是电子设备，例如具有操作系统的电子设备，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信道特征信息传输装置400能够实现图2方法实施例中终端实现的各个过程，并达到相同的技术效果，为避免重复，这里不再赘述。
请参照图5，图5是本申请实施例提供的另一种信道特征信息传输装置的结构图，如图5所示，所述信道特征信息传输装置500包括：
第二接收模块501，用于接收终端上报的信道特征信息；
其中，所述信道特征信息为所述终端计算信道信息在第一域和第二域中的至少一者的正交基上的系数，并将所述系数输入第一AI网络模型进行量化处理后输出得到的信息。
可选地，所述第一域为空域，所述第二域为频域，所述第一域的正交基的最大个数为CSI-RS的端口数；所述第二域的正交基的最大个数为频域采样点的个数。
可选地，所述装置还包括：
发送模块，用于向终端发送第一指示信息，所述第一指示信息用于指示终端采用的正交基，或者用于指示终端采用的正交基的数量。
可选地，所述第二接收模块501还用于：
接收所述终端上报的所采用的正交基。
可选地，在所述装置包括与所述第一AI网络模型匹配的多个第二AI网络模型的情况下，所述第二接收模块501还用于：
接收所述终端上报的最大系数对应的正交基的位置。
可选地，所述装置还包括：
编码模块。用于将终端采用的正交基编码至CSI-RS端口中。
本申请实施例中，终端通过计算信道信息在第一域和第二域中至少一者的正交基上的系数，基于一个第一AI网络模型就能够实现对信道信息的处理，进而所述装置也就无需针对不同长度的信道信息分别训练不同的AI网络模型，进而能够节省所述装置训练AI网络模型的功耗，也能够节省所述装置和终端之间针对AI网络模型的传输开销。
本申请实施例提供的信道特征信息传输装置500能够实现图3方法实施例中网络侧设备实现的各个过程，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6所示，本申请实施例还提供一种通信设备600，包括处理器601和存储器602，存储器602上存储有可在所述处理器601上运行的程序或指令，例如，该通信设备600为终端时，该程序或指令被处理器601执行时实现上述图2所述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600为网络侧设备时，该程序或指令被处理器601执行时实现上述图3所述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，处理器用于用于获取信道信息，计算所述信道信息在第一域和第二域中的至少一者的正交基上的系数，并将所述系数输入至第一人工智能AI网络模型进行量化处理，获取所述第一AI网络模型输出的信道特征信息，所述通信接口用于向网络侧设备上报所述信道特征信息。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7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700包括但不限于：射频单元701、网络模块702、音频输出单元703、输入单元704、传感器705、显示单元706、用户输入单元707、接口单元708、存储器709以及处理器710等中的至少部分部件。
本领域技术人员可以理解，终端700还可以包括给各个部件供电的电源(比如电池)，电源可以通过电源管理系统与处理器710逻辑相连，从而通过电源管理系统实现管理充电、放电、以及功耗管理等功能。图7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704可以包括图形处理单元(Graphics Processing Unit，GPU)7041和麦克风7042，图形处理器7041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706可包括显示面板7061，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7061。用户输入单元707包括触控面板7071以及其他输入设备7072中的至少一种。触控面板7071，也称为触摸屏。触控面板7071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7072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701接收来自网络侧设备的下行数据后，可以传输给处理器710进行处理；另外，射频单元701可以向网络侧设备发送上行数据。通常，射频单元701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709可用于存储软件程序或指令以及各种数据。存储器709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系统、至少一个功能所需的应用程序或指令(比如声音播放功能、图像播放功能等)等。此外，存储器709可以包括易失性存储器或非易失性存储器，或者，存储器709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709包括但不限于这些和任意其它适合类型的存储器。
处理器710可包括一个或多个处理单元；可选的，处理器710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系统、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710中。
其中，处理器710，用于获取信道信息；以及，计算所述信道信息在第一域和第二域中的至少一者的正交基上的系数，并将所述系数输入至第一人工智能AI网络模型进行量化处理，获取所述第一AI网络模型输出的信道特征信息；
射频单元701，用于向网络侧设备上报所述信道特征信息。
可选地，所述第一域为空域，所述第二域为频域，所述第一域的正交基的最大个数为 信道状态信息参考信号CSI-RS的端口数；所述第二域的正交基的最大个数为频域采样点的个数。
可选地，射频单元701，还用于：
接收网络侧设备发送的第一指示信息，所述第一指示信息用于指示终端采用的正交基，或者用于指示终端采用的正交基的数量。
可选地，处理器710，还用于：
基于所述第一指示信息，确定第一域和第二域中至少一者采用的正交基；
计算所述信道信息在所述采用的正交基上的系数，并将所述系数输入至第一AI网络模型进行量化处理，所述系数的长度与所述第一指示信息指示终端采用的正交基的数量匹配。
可选地，在所述第一域为空域，所述第二域为频域的情况下，所述第一域采用的正交基为所述空域的全部正交基。
可选地，在所述第一域为空域，所述第二域为频域的情况下，处理器710，还用于：
基于所述第一指示信息，确定所述第二域采用的正交基，所述第一指示信息用于指示所述第二域采用的正交基；
计算所述信道信息在所述第一域的所有正交基上的第一系数，以及计算所述信道信息在所述第二域采用的正交基上的第二系数，并将所述第一系数和所述第二系数输入至第一AI网络模型进行量化处理。
可选地，所述正交基的确定通过协议约定。
可选地，在目标域的正交基为过采正交基的情况下，处理器710，还用于：
确定过采因子，基于所述过采因子计算所述信道信息在目标域的正交基上的系数，所述目标域包括第一域和第二域中的至少一者。
可选地，处理器710，还用于：
计算所述信道信息在第一域和第二域中的至少一者的M个正交基上各自对应的系数，所述M个正交基包括至少一个目标正交基；
将目标系数输入至第一AI网络模型进行量化处理，所述目标系数包括如下任意一项：
全部所述目标正交基对应的系数；
预设数量的所述目标正交基对应的系数；
全部所述目标正交基对应的系数及预设系数；
预设数量的所述目标正交基对应的系数及预设系数。
可选地，所述第一AI网络模型的输入长度与输入的所述目标系数的数量匹配。
可选地，所述M个正交基包括所述目标正交基及除所述目标正交基以外的其他正交基，所述其他正交基对应的系数为所述预设系数。
可选地，所述预设系数满足如下任意一项：
所述预设系数与第一AI网络模型关联；
所述其他正交基对应的所述预设系数相同；
所述其他正交基对应的所述预设系数不同，一个所述其他正交基对应一个预设系数；
所述预设系数为0。
可选地，所述M个正交基为所述目标域的所有正交基，所述目标域包括所述第一域和所述第二域中的至少一者。
可选地，处理器710，还用于：
所述终端计算所述信道信息在第一域和第二域中的至少一者的正交基上的系数，并对所述系数进行排序，将排序后的所述系数输入至第一AI网络模型进行量化处理。
可选地，射频单元701，还用于：
向网络侧设备上报排序后的所述系数对应的正交基的顺序，或者上报排序后的所述系数对应的正交基的顺序标识。
可选地，在所述第一域为空域的情况下，每个极化上选择的空域正交基对应的波束相同，每个极化上选择的空域正交基上的系数联合排序。
可选地，所述第一域的正交基上的系数和所述第二域的正交基上的系数进行分开排序；或者，
在所述目标域包括第一域和第二域的情况下，所述第一域的正交基上的系数和所述第二域的正交基上的系数进行联合排序。
可选地，射频单元701，还用于：
向网络侧设备上报采用的所述正交基。
可选地，在网络侧设备包括与所述第一AI网络模型匹配的多个第二AI网络模型的情况下，射频单元701，还用于：
向网络侧设备上报最大系数对应的正交基的位置。
可选地，在网络侧设备将正交基编码至CSI-RS端口中的情况下，处理器710，还用于：
基于所述CSI-RS端口确定正交基，并计算所述信道信息在基于所述CSI-RS端口确定的正交基上的系数。
本申请实施例中，终端通过计算信道信息在第一域和第二域中至少一者的正交基上的系数，基于一个第一AI网络模型就能够实现对信道信息的处理，也就无需针对不同长度的信道信息分别配置不同的AI网络模型，进而能够节省网络侧设备训练AI网络模型的功耗，节省网络侧设备和终端之间针对AI网络模型的传输开销，也能够降低终端的功耗。
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，所述通信接口用于接收终端上报的信道特征信息其中，所述信道特征信息为所述终端计算信道信息在第一域和第二域中的至少一者的正交基上的系数，并将所述系数输入第一AI网络模型进行量化处理后输出得到的信息。该网络侧设备实施例与上述网络侧设备方法实施例对应，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8所示，该网络侧设备800包括：天线81、射频装置82、基带装置83、处理器84和存储器85。天线81与射频装置82连接。在上行方向上，射频装置82通过天线81接收信息，将接收的信息发送给基带装置83进行处理。在下行方向上，基带装置83对要发送的信息进行处理，并发送给射频装置82，射频装置82对收到的信息进行处理后经过天线81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83中实现，该基带装置83包括基带处理器。
基带装置83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8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85连接，以调用存储器85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86，该接口例如为通用公共无线接口(common public radio interface，CPRI)。
具体地，本发明实施例的网络侧设备800还包括：存储在存储器85上并可在处理器84上运行的指令或程序，处理器84调用存储器85中的指令或程序执行图5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所述方法实施例的各个过程，或者实现上述图3所述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ROM、随机存取存储器RAM、磁碟或者光盘等。
本申请实施例另提供了一种芯片，所述芯片包括处理器和通信接口，所述通信接口和所述处理器耦合，所述处理器用于运行程序或指令，实现上述图2所述方法实施例的各个过程，或者实现上述图3所述方法实施例的各个过程，且能达到相同的技术效果，为避免重复，这里不再赘述。
应理解，本申请实施例提到的芯片还可以称为系统级芯片，系统芯片，芯片系统或片上系统芯片等。
本申请实施例另提供了一种计算机程序/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所述方法实施例的各个过程，或者实现上述图3所述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。
本申请实施例还提供了一种通信系统，包括：终端及网络侧设备，所述终端可用于执行如图2所述的信道特征信息传输方法的步骤，所述网络侧设备可用于执行如上图3所述的信道特征信息传输方法的步骤。
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 (32)

  1. 一种信道特征信息传输方法，包括：
    终端获取信道信息；
    所述终端计算所述信道信息在第一域和第二域中的至少一者的正交基上的系数，并将所述系数输入至第一人工智能AI网络模型进行量化处理，获取所述第一AI网络模型输出的信道特征信息；
    所述终端向网络侧设备上报所述信道特征信息。
  2. 根据权利要求1所述的方法，其中，所述第一域为空域，所述第二域为频域，所述第一域的正交基的最大个数为信道状态信息参考信号CSI-RS的端口数；
    所述第二域的正交基的最大个数为频域采样点的个数。
  3. 根据权利要求1所述的方法，其中，所述方法还包括：
    所述终端接收网络侧设备发送的第一指示信息，所述第一指示信息用于指示终端采用的正交基，或者用于指示终端采用的正交基的数量。
  4. 根据权利要求3所述的方法，其中，所述终端计算所述信道信息在第一域和第二域中的至少一者的正交基上的系数，并将所述系数输入至第一AI网络模型进行量化处理，包括：
    所述终端基于所述第一指示信息，确定第一域和第二域中至少一者采用的正交基；
    所述终端计算所述信道信息在所述采用的正交基上的系数，并将所述系数输入至第一AI网络模型进行量化处理，所述系数的长度与所述第一指示信息指示终端采用的正交基的数量匹配。
  5. 根据权利要求4所述的方法，其中，在所述第一域为空域，所述第二域为频域的情况下，所述第一域采用的正交基为所述空域的全部正交基。
  6. 根据权利要求4所述的方法，其中，在所述第一域为空域，所述第二域为频域的情况下，所述终端基于所述第一指示信息，确定第一域和第二域中至少一者采用的正交基，包括：
    所述终端基于所述第一指示信息，确定所述第二域采用的正交基，所述第一指示信息用于指示所述第二域采用的正交基；
    所述终端计算所述信道信息在选择的正交基上的系数，并将所述系数输入至第一AI网络模型进行量化处理，包括：
    所述终端计算所述信道信息在所述第一域的所有正交基上的第一系数，以及计算所述信道信息在所述第二域采用的正交基上的第二系数，并将所述第一系数和所述第二系数输入至第一AI网络模型进行量化处理。
  7. 根据权利要求1所述的方法，其中，在目标域的正交基为过采正交基的情况下，所述终端计算所述信道信息在第一域和第二域中的至少一者的正交基上的系数，包括：
    所述终端确定过采因子，基于所述过采因子计算所述信道信息在目标域的正交基上的系数，所述目标域包括第一域和第二域中的至少一者。
  8. 根据权利要求1所述的方法，其中，所述终端计算所述信道信息在第一域和第二域中的至少一者的正交基上的系数，并将所述系数输入至第一AI网络模型进行量化处理，包括：
    所述终端计算所述信道信息在第一域和第二域中的至少一者的M个正交基上各自对应的系数，所述M个正交基包括至少一个目标正交基；
    所述终端将目标系数输入至第一AI网络模型进行量化处理，所述目标系数包括如下任意一项：
    全部所述目标正交基对应的系数；
    预设数量的所述目标正交基对应的系数；
    全部所述目标正交基对应的系数及预设系数；
    预设数量的所述目标正交基对应的系数及预设系数。
  9. 根据权利要求8所述的方法，其中，所述第一AI网络模型的输入长度与输入的所述目标系数的数量匹配。
  10. 根据权利要求8所述的方法，其中，所述M个正交基包括所述目标正交基及除所述目标正交基以外的其他正交基，所述其他正交基对应的系数为所述预设系数。
  11. 根据权利要求10所述的方法，其中，所述预设系数满足如下任意一项：
    所述预设系数与第一AI网络模型关联；
    所述其他正交基对应的所述预设系数相同；
    所述其他正交基对应的所述预设系数不同，一个所述其他正交基对应一个预设系数；
    所述预设系数为0。
  12. 根据权利要求1所述的方法，其中，所述终端计算所述信道信息在第一域和第二域中的至少一者的正交基上的系数，并将所述系数输入至第一AI网络模型进行量化处理，包括：
    所述终端计算所述信道信息在第一域和第二域中的至少一者的正交基上的系数，并对所述系数进行排序，将排序后的所述系数输入至第一AI网络模型进行量化处理。
  13. 根据权利要求12所述的方法，其中，所述方法还包括：
    所述终端向网络侧设备上报排序后的所述系数对应的正交基的顺序，或者上报排序后的所述系数对应的正交基的顺序标识。
  14. 根据权利要求12所述的方法，其中，在所述第一域为空域的情况下，每个极化上选择的空域正交基对应的波束相同，每个极化上选择的空域正交基上的系数联合排序。
  15. 根据权利要求12所述的方法，其中，所述第一域的正交基上的系数和所述第二域的正交基上的系数进行分开排序；或者，
    在目标域包括第一域和第二域的情况下，所述第一域的正交基上的系数和所述第二域 的正交基上的系数进行联合排序。
  16. 根据权利要求1-15中任一项所述的方法，其中，所述方法还包括：
    所述终端向网络侧设备上报采用的所述正交基；或者，
    在网络侧设备包括与所述第一AI网络模型匹配的多个第二AI网络模型的情况下，所述终端向网络侧设备上报最大系数对应的正交基的位置。
  17. 根据权利要求1所述的方法，其中，在网络侧设备将正交基编码至CSI-RS端口中的情况下，所述终端计算所述信道信息在第一域和第二域中的至少一者的正交基上的系数，包括：
    所述终端基于所述CSI-RS端口确定正交基，并计算所述信道信息在基于所述CSI-RS端口确定的正交基上的系数。
  18. 一种信道特征信息传输方法，包括：
    网络侧设备接收终端上报的信道特征信息；
    其中，所述信道特征信息为所述终端计算信道信息在第一域和第二域中的至少一者的正交基上的系数，并将所述系数输入第一AI网络模型进行量化处理后输出得到的信息。
  19. 根据权利要求18所述的方法，其中，所述第一域为空域，所述第二域为频域，所述第一域的正交基的最大个数为CSI-RS的端口数；
    所述第二域的正交基的最大个数为频域采样点的个数。
  20. 根据权利要求18所述的方法，其中，所述网络侧设备接收终端上报的信道特征信息之前，所述方法还包括：
    所述网络侧设备向终端发送第一指示信息，所述第一指示信息用于指示终端采用的正交基，或者用于指示终端采用的正交基的数量。
  21. 根据权利要求18所述的方法，其中，所述方法还包括：
    所述网络侧设备接收所述终端上报的所采用的正交基；或者，
    在网络侧设备包括与所述第一AI网络模型匹配的多个第二AI网络模型的情况下，所述网络侧设备接收所述终端上报的最大系数对应的正交基的位置。
  22. 根据权利要求18-21中任一项所述的方法，其中，所述方法还包括：
    所述网络侧设备将终端采用的正交基编码至CSI-RS端口中。
  23. 一种信道特征信息传输装置，包括：
    获取模块，用于获取信道信息；
    处理模块，用于计算所述信道信息在第一域和第二域中的至少一者的正交基上的系数，并将所述系数输入至第一AI网络模型进行量化处理，获取所述第一AI网络模型输出的信道特征信息；
    上报模块，用于向网络侧设备上报所述信道特征信息。
  24. 根据权利要求23所述的装置，其中，所述装置还包括：
    第一接收模块，用于接收网络侧设备发送的第一指示信息，所述第一指示信息用于指 示终端采用的正交基，或者用于指示终端采用的正交基的数量。
  25. 根据权利要求24所述的装置，其中，所述处理模块还用于：
    基于所述第一指示信息，确定第一域和第二域中至少一者采用的正交基；
    计算所述信道信息在所述采用的正交基上的系数，并将所述系数输入至第一AI网络模型进行量化处理，所述系数的长度与所述第一指示信息指示终端采用的正交基的数量匹配。
  26. 根据权利要求23所述的装置，其中，所述处理模块还用于：
    计算所述信道信息在第一域和第二域中的至少一者的M个正交基上各自对应的系数，所述M个正交基包括至少一个目标正交基；
    将目标系数输入至第一AI网络模型进行量化处理，所述目标系数包括如下任意一项：
    全部所述目标正交基对应的系数；
    预设数量的所述目标正交基对应的系数；
    全部所述目标正交基对应的系数及预设系数；
    预设数量的所述目标正交基对应的系数及预设系数。
  27. 根据权利要求23所述的装置，其中，所述处理模块还用于：
    计算所述信道信息在第一域和第二域中的至少一者的正交基上的系数，并对所述系数进行排序，将排序后的所述系数输入至第一AI网络模型进行量化处理。
  28. 一种信道特征信息传输装置，包括：
    第二接收模块，用于接收终端上报的信道特征信息；
    其中，所述信道特征信息为所述终端计算信道信息在第一域和第二域中的至少一者的正交基上的系数，并将所述系数输入第一AI网络模型进行量化处理后输出得到的信息。
  29. 根据权利要求28所述的装置，其中，所述装置还包括：
    编码模块，用于将终端采用的正交基编码至CSI-RS端口中。
  30. 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，其中，所述程序或指令被所述处理器执行时实现如权利要求1-17中任一项所述的信道特征信息传输方法的步骤。
  31. 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，其中，所述程序或指令被所述处理器执行时实现如权利要求18-22中任一项所述的信道特征信息传输方法的步骤。
  32. 一种可读存储介质，所述可读存储介质上存储程序或指令，其中，所述程序或指令被处理器执行时实现如权利要求1-17中任一项所述的信道特征信息传输方法的步骤，或者实现如权利要求18-22中任一项所述的信道特征信息传输方法的步骤。
PCT/CN2023/084964 2022-04-01 2023-03-30 信道特征信息传输方法、装置、终端及网络侧设备 WO2023185980A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210349446.XA CN116939650A (zh) 2022-04-01 2022-04-01 信道特征信息传输方法、装置、终端及网络侧设备
CN202210349446.X 2022-04-01

Publications (1)

Publication Number Publication Date
WO2023185980A1 true WO2023185980A1 (zh) 2023-10-05

Family

ID=88199374

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/084964 WO2023185980A1 (zh) 2022-04-01 2023-03-30 信道特征信息传输方法、装置、终端及网络侧设备

Country Status (2)

Country Link
CN (1) CN116939650A (zh)
WO (1) WO2023185980A1 (zh)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105208572A (zh) * 2015-06-26 2015-12-30 华为技术有限公司 一种波束成形方法及基站
US20180278316A1 (en) * 2017-03-24 2018-09-27 Mediatek Inc. CSI Acquisition With Channel Reciprocity In Mobile Communications
CN111434049A (zh) * 2017-06-19 2020-07-17 弗吉尼亚科技知识产权有限公司 使用多天线收发器无线传输的信息的编码和解码
CN113938232A (zh) * 2020-07-13 2022-01-14 华为技术有限公司 通信的方法及通信装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105208572A (zh) * 2015-06-26 2015-12-30 华为技术有限公司 一种波束成形方法及基站
US20180278316A1 (en) * 2017-03-24 2018-09-27 Mediatek Inc. CSI Acquisition With Channel Reciprocity In Mobile Communications
CN111434049A (zh) * 2017-06-19 2020-07-17 弗吉尼亚科技知识产权有限公司 使用多天线收发器无线传输的信息的编码和解码
CN113938232A (zh) * 2020-07-13 2022-01-14 华为技术有限公司 通信的方法及通信装置

Also Published As

Publication number Publication date
CN116939650A (zh) 2023-10-24

Similar Documents

Publication Publication Date Title
WO2023246618A1 (zh) 信道矩阵处理方法、装置、终端及网络侧设备
JP2024512358A (ja) 情報報告方法、装置、第１機器及び第２機器
WO2023185978A1 (zh) 信道特征信息上报及恢复方法、终端和网络侧设备
WO2023185980A1 (zh) 信道特征信息传输方法、装置、终端及网络侧设备
WO2023185995A1 (zh) 信道特征信息传输方法、装置、终端及网络侧设备
WO2023179460A1 (zh) 信道特征信息传输方法、装置、终端及网络侧设备
WO2024055974A1 (zh) Cqi传输方法、装置、终端及网络侧设备
WO2024007949A1 (zh) Ai模型处理方法、装置、终端及网络侧设备
WO2023179570A1 (zh) 信道特征信息传输方法、装置、终端及网络侧设备
WO2024055993A1 (zh) Cqi传输方法、装置、终端及网络侧设备
WO2023179476A1 (zh) 信道特征信息上报及恢复方法、终端和网络侧设备
WO2024149156A1 (zh) 信息传输方法、装置、终端及网络侧设备
WO2024093999A1 (zh) 信道信息的上报和接收方法、终端及网络侧设备
WO2024164961A1 (zh) 信息处理方法、装置、终端及网络侧设备
WO2024088161A1 (zh) 信息传输方法、信息处理方法、装置和通信设备
WO2024037380A1 (zh) 信道信息处理方法、装置、通信设备及存储介质
WO2024051564A1 (zh) 信息传输方法、ai网络模型训练方法、装置和通信设备
WO2024149157A1 (zh) Csi传输方法、装置、终端及网络侧设备
WO2024088162A1 (zh) 信息传输方法、信息处理方法、装置和通信设备
WO2024140422A1 (zh) Ai单元的性能监测方法、终端及网络侧设备
WO2024217495A1 (zh) 信息处理方法、信息处理装置、终端及网络侧设备
WO2024140578A1 (zh) 基于ai模型的csi反馈方法、终端及网络侧设备
WO2023207920A1 (zh) 信道信息反馈方法、终端及网络侧设备
WO2024051594A1 (zh) 信息传输方法、ai网络模型训练方法、装置和通信设备
WO2023179473A1 (zh) 信道特征信息上报及恢复方法、终端和网络侧设备

Legal Events

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

Ref document number: 23778345

Country of ref document: EP

Kind code of ref document: A1