[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

WO2024088161A1 - 信息传输方法、信息处理方法、装置和通信设备 - Google Patents

信息传输方法、信息处理方法、装置和通信设备 Download PDF

Info

Publication number
WO2024088161A1
WO2024088161A1 PCT/CN2023/125560 CN2023125560W WO2024088161A1 WO 2024088161 A1 WO2024088161 A1 WO 2024088161A1 CN 2023125560 W CN2023125560 W CN 2023125560W WO 2024088161 A1 WO2024088161 A1 WO 2024088161A1
Authority
WO
WIPO (PCT)
Prior art keywords
frequency domain
information
domain resources
groups
channel
Prior art date
Application number
PCT/CN2023/125560
Other languages
English (en)
French (fr)
Inventor
任千尧
吴昊
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 WO2024088161A1 publication Critical patent/WO2024088161A1/zh

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L5/00Arrangements affording multiple use of the transmission path
    • H04L5/003Arrangements for allocating sub-channels of the transmission path
    • H04L5/0053Allocation of signaling, i.e. of overhead other than pilot signals
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04BTRANSMISSION
    • H04B7/00Radio transmission systems, i.e. using radiation field
    • H04B7/02Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas
    • H04B7/04Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
    • H04B7/06Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04BTRANSMISSION
    • H04B7/00Radio transmission systems, i.e. using radiation field
    • H04B7/02Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas
    • H04B7/04Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
    • H04B7/06Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station
    • H04B7/0613Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission
    • H04B7/0615Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission of weighted versions of same signal
    • H04B7/0619Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission of weighted versions of same signal using feedback from receiving side
    • H04B7/0621Feedback content
    • H04B7/0626Channel coefficients, e.g. channel state information [CSI]
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04BTRANSMISSION
    • H04B7/00Radio transmission systems, i.e. using radiation field
    • H04B7/02Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas
    • H04B7/04Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
    • H04B7/06Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station
    • H04B7/0613Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission
    • H04B7/0615Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission of weighted versions of same signal
    • H04B7/0619Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission of weighted versions of same signal using feedback from receiving side
    • H04B7/0621Feedback content
    • H04B7/0632Channel quality parameters, e.g. channel quality indicator [CQI]
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04BTRANSMISSION
    • H04B7/00Radio transmission systems, i.e. using radiation field
    • H04B7/02Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas
    • H04B7/04Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
    • H04B7/06Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station
    • H04B7/0613Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission
    • H04B7/0615Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission of weighted versions of same signal
    • H04B7/0619Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission of weighted versions of same signal using feedback from receiving side
    • H04B7/0636Feedback format
    • H04B7/0639Using selective indices, e.g. of a codebook, e.g. pre-distortion matrix index [PMI] or for beam selection
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/08Configuration management of networks or network elements
    • H04L41/0803Configuration setting
    • H04L41/0823Configuration setting characterised by the purposes of a change of settings, e.g. optimising configuration for enhancing reliability
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L5/00Arrangements affording multiple use of the transmission path
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W72/00Local resource management
    • H04W72/04Wireless resource allocation
    • H04W72/044Wireless resource allocation based on the type of the allocated resource
    • H04W72/0453Resources in frequency domain, e.g. a carrier in FDMA

Definitions

  • the present application belongs to the field of communication technology, and specifically relates to an information transmission method, an information processing method, an apparatus and a communication device.
  • the AI network model may include an encoding part (i.e., an encoding AI network model) and a decoding part (i.e., a decoding AI network model).
  • the encoding AI network model is used to encode channel information into channel characteristic information
  • the decoding AI network model is used to restore the channel characteristic information output by the encoding AI network model into channel information.
  • the input dimension of the same AI network model is fixed.
  • Different AI network models need to be used for channel information with different numbers of subbands.
  • the AI network model trained based on the precoding matrix of 13 subbands cannot be used under the channel of 13 subbands, it is necessary to train and transmit AI network models that match the number of subbands. This will increase the computational complexity of training AI network models that match the number of subbands, and increase the overhead of transmitting AI network models that match the number of subbands.
  • the embodiments of the present application provide an information transmission method, an information processing method, an apparatus, and a communication device, so that an AI network model trained based on channel information with a low number of subbands can process channel information with a high number of subbands, thereby improving the multiplexing efficiency and flexibility of the AI network model.
  • a method for transmitting information comprising:
  • the terminal determines, based on the first information, K groups of second channel information from the first channel information, wherein the first information includes grouping information of K groups of frequency domain resources, the K groups of second channel information correspond one-to-one to the K groups of frequency domain resources, each group of frequency domain resources in the K groups of frequency domain resources includes at least one frequency domain resource, and K is an integer greater than or equal to 1;
  • the terminal performs a first processing on the M groups of second channel information based on the first AI network model corresponding to each of the M groups of second channel information to obtain M channel characteristic information, the K groups of second channel information include the M groups of second channel information, and M is a positive integer less than or equal to K;
  • the terminal sends second information to the network side device, where the second information includes the M channel characteristic information.
  • an information transmission device which is applied to a terminal, and the device includes:
  • the first determination module is used to determine K groups of second channel information from the first channel information based on the first information, wherein:
  • the first information includes grouping information of K groups of frequency domain resources, the K groups of second channel information correspond one-to-one to the K groups of frequency domain resources, each group of frequency domain resources in the K groups of frequency domain resources includes at least one frequency domain resource, and K is an integer greater than or equal to 1;
  • a first processing module configured to perform a first processing on the M groups of second channel information based on the first AI network model corresponding to each of the M groups of second channel information to obtain M channel feature information, wherein the K groups of second channel information include the M groups of second channel information, and M is a positive integer less than or equal to K;
  • the first sending module is used to send second information to the network side device, where the second information includes the M channel characteristic information.
  • an information processing method comprising:
  • the network side device receives second information from the terminal, wherein the second information includes M channel characteristic information, and the M channel characteristic information is channel characteristic information obtained by performing a first processing on the M groups of second channel information based on the first AI network model corresponding to each of the M groups of second channel information, and M is an integer greater than or equal to 1;
  • the network side device determines, according to the first information, a second AI network side model corresponding to each of the M channel characteristic information, wherein the first information includes grouping information of K groups of frequency domain resources, the K groups of second channel information correspond one-to-one to the K groups of frequency domain resources, each group of frequency domain resources in the K groups of frequency domain resources includes at least one frequency domain resource, and K is an integer greater than or equal to M;
  • the network side device performs a second processing on the M channel characteristic information based on the second AI network side models corresponding to each of the M channel characteristic information to obtain the M groups of second channel information.
  • an information processing device which is applied to a network side device, and the device includes:
  • a first receiving module configured to receive second information from a terminal, wherein the second information includes M channel characteristic information, and the M channel characteristic information is channel characteristic information obtained by performing a first processing on the M groups of second channel information based on the first AI network model corresponding to each of the M groups of second channel information, and M is an integer greater than or equal to 1;
  • a second determination module used to determine, according to the first information, a second AI network-side model corresponding to each of the M channel characteristic information, wherein the first information includes grouping information of K groups of frequency domain resources, the K groups of second channel information correspond one-to-one to the K groups of frequency domain resources, each group of frequency domain resources in the K groups of frequency domain resources includes at least one frequency domain resource, and K is an integer greater than or equal to M;
  • the second processing module is used to perform a second processing on the M channel characteristic information based on the second AI network side model corresponding to each of the M channel characteristic information to obtain the M groups of second channel information.
  • a communication device which includes a processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the program or instructions are executed by the processor, the steps of the information transmission method described in the first aspect or the information processing method described in the third aspect are implemented.
  • a terminal comprising a processor and a communication interface, wherein the processor is used to determine K groups of second channel information from the first channel information based on the first information, wherein the first information includes grouping information of K groups of frequency domain resources, and the K groups of second channel information correspond to the K groups of frequency domain resources one by one, and the K groups of frequency domain resources correspond to the K groups of frequency domain resources one by one.
  • Each group of frequency domain resources in the resources includes at least one frequency domain resource, K is an integer greater than or equal to 1; the processor is also used to perform a first processing on the M groups of second channel information based on the first AI network model corresponding to each of the M groups of second channel information to obtain M channel characteristic information, the K groups of second channel information include the M groups of second channel information, M is a positive integer less than or equal to K; the communication interface is used to send second information to the network side device, and the second information includes the M channel characteristic information.
  • a network side device comprising a processor and a communication interface, wherein the communication interface is used to receive second information from a terminal, wherein the second information includes M channel characteristic information, and the M channel characteristic information is channel characteristic information obtained by first processing the M groups of second channel information based on the first AI network model corresponding to each of the M groups of second channel information, and M is an integer greater than or equal to 1; the processor is used to determine the second AI network side model corresponding to each of the M channel characteristic information according to the first information, wherein the first information includes grouping information of K groups of frequency domain resources, the K groups of second channel information correspond one-to-one to the K groups of frequency domain resources, each group of frequency domain resources in the K groups of frequency domain resources includes at least one frequency domain resource, and K is an integer greater than or equal to M; the processor is also used to perform a second processing on the M channel characteristic information based on the second AI network side model corresponding to each of the M channel characteristic information to obtain the M groups of second channel information.
  • a communication system comprising: a terminal and a network side device, wherein the terminal can be used to execute the steps of the information transmission method as described in the first aspect, and the network side device can be used to execute the steps of the information processing method as described in the third aspect.
  • a readable storage medium on which a program or instruction is stored.
  • the program or instruction is executed by a processor, the steps of the information transmission method described in the first aspect are implemented, or the steps of the information processing method described in the third aspect are implemented.
  • a chip comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement the information transmission method as described in the first aspect, or to implement the information processing method as described in the third aspect.
  • a computer program/program product is provided, wherein the computer program/program product is stored in a storage medium, and the computer program/program product is executed by at least one processor to implement the steps of the information transmission method as described in the first aspect, or the computer program/program product is executed by at least one processor to implement the steps of the information processing method as described in the third aspect.
  • frequency domain resources are grouped, and the channel information of each group of frequency domain resources is processed using a corresponding AI network model, wherein the first channel information of a channel can be divided into K groups, and each AI network model only inputs the channel information of a corresponding group of frequency domain resources without inputting the channel information of the entire channel, so that the AI network model with a low number of frequency domain resources can be used to process the channel information of a high number of frequency domain resources, thereby improving the multiplexing efficiency and flexibility of the AI network model.
  • FIG1 is a schematic diagram of the structure of a wireless communication system to which an embodiment of the present application can be applied;
  • FIG2 is a flow chart of an information transmission method provided in an embodiment of the present application.
  • FIG3 is a flow chart of an information processing method provided in an embodiment of the present application.
  • FIG4 is a schematic diagram of the structure of an information transmission device provided in an embodiment of the present application.
  • FIG5 is a schematic diagram of the structure of an information processing device provided in an embodiment of the present application.
  • FIG6 is a schematic diagram of the structure of a communication device provided in an embodiment of the present application.
  • FIG. 7 is a schematic diagram of the hardware structure of a terminal provided in an embodiment of the present application.
  • FIG8 is a schematic diagram of the structure of a network side device provided in an embodiment of the present application.
  • first, second, etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way are interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by “first” and “second” are generally of the same type, and the number of objects is not limited.
  • the first object can be one or more.
  • “and/or” in the specification and claims represents at least one of the connected objects, and the character “/" generally represents that the objects associated with each other are in an "or” relationship.
  • LTE 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
  • FIG1 shows a block diagram of a wireless communication system applicable to an embodiment of the present application.
  • the wireless communication system includes a terminal 11 and a network side device 12.
  • the terminal 11 may be a mobile phone, a tablet computer (Tablet Personal Computer), a laptop computer (Laptop Computer) or a notebook computer, a personal digital assistant (Personal Digital Assistant, PDA), a handheld computer, a netbook, an ultra-mobile personal computer (ultra-mobile personal computer, UMPC), a mobile Internet device (Mobile Internet Device, MID), an augmented reality (augmented reality, AR)/virtual reality (virtual reality, VR) device, a robot, a wearable device (Wearable Device), a vehicle user equipment (VUE), a pedestrian terminal (Pedestrian User Equipment, PUE), a smart home (with wireless
  • the terminal side devices 12 include household appliances with wireless communication functions, such as refrigerators, televisions, washing machines or furniture, etc.), game consoles, personal computers (PCs), ATMs or self-service machines, and
  • the network side device 12 may include access network equipment or core network equipment, wherein the access network equipment may also be referred to as wireless access network equipment, wireless access network (Radio Access Network, RAN), wireless access network function or wireless access network unit.
  • the access network equipment may include a base station, a WLAN access point or a WiFi node, etc.
  • the base station may be referred to as a node B, an evolved node B (eNB), an access point, a base transceiver station (Base Transceiver Station, BTS), a radio base station, a radio transceiver, a basic service set (Basic Service Set, BSS), an extended service set (Extended Service Set, ESS), a home B node, a home evolved B node, a transmitting and receiving point (Transmitting Receiving Point, TRP) or some other suitable term in the field.
  • the base station is not limited to specific technical vocabulary. It should be noted that in the embodiment of the present application, only the base station in the NR system is used as an example for introduction, and the specific type of the base station is not limited.
  • the transmitter can optimize the signal transmission based on CSI to make it more compatible with the channel state.
  • the channel quality indicator CQI
  • MCS modulation and coding scheme
  • PMI precoding matrix indicator
  • MIMO multi-input multi-output
  • the base station sends a CSI Reference Signal (CSI-RS) on certain time-frequency resources in a certain time slot.
  • CSI-RS CSI Reference Signal
  • the terminal performs channel estimation based on the CSI-RS, calculates the channel information on this slot, and feeds back the PMI to the base station through the codebook.
  • the base station combines the channel information based on the codebook information fed back by the terminal, and uses this to perform data precoding and multi-user scheduling before the next CSI report.
  • the terminal can change the PMI reported in each subband to reporting PMI according to delay. Since the channels in the delay domain are more concentrated, the PMI of all subbands can be approximately represented by PMIs with fewer delays, that is, the delay domain information is compressed before reporting.
  • the base station can pre-code the CSI-RS in advance and send the encoded CSI-RS to the terminal.
  • the terminal sees the channel corresponding to the encoded CSI-RS.
  • the terminal only needs to select several ports with higher strength from the ports indicated by the network side and report the coefficients corresponding to these ports.
  • neural network or machine learning methods can be used.
  • AI modules such as neural networks, decision trees, support vector machines, Bayesian classifiers, etc. This application uses neural networks as an example for illustration, but does not limit the specific type of AI modules.
  • the parameters of the neural network are optimized through optimization algorithms.
  • An optimization algorithm is a type of algorithm that can help us minimize or maximize an objective function (sometimes called a loss function).
  • the objective function is often a mathematical combination of model parameters and data. For example, given data X and its corresponding label Y, we build a neural network model f(.). With the model, we can get the predicted output f(x) based on the input x, and we can calculate the difference between the predicted value and the true value (f(x)-Y), which is the loss function. Our goal is to find the right weights and biases to minimize the value of the above loss function. The smaller the loss value, the closer our model is to the real situation.
  • the common optimization algorithms are basically based on the error back propagation (BP) algorithm.
  • BP error back propagation
  • the basic idea of the BP algorithm is that the learning process consists of two processes: the forward propagation of the signal and the back propagation of the error.
  • the input sample is transmitted from the input layer, processed by each hidden layer layer by layer, and then transmitted to the output layer. If the actual output of the output layer does not match the expected output, it will enter the error back propagation stage.
  • Error back propagation is to propagate the output error layer by layer through the hidden layer to the input layer in some form, and distribute the error to all units in each layer, so as to obtain the error signal of each layer unit, and this error signal is used as the basis for correcting the weights of each unit.
  • This process of adjusting the weights of each layer of the signal forward propagation and error back propagation is repeated.
  • the process of continuous adjustment of weights is the learning and training process of the network. This process continues until the error of the network output is reduced to an acceptable level, or until the pre-set number of learning times is reached.
  • the CSI compression recovery process is as follows: the terminal estimates the CSI-RS, calculates the channel information, obtains the encoding result of the calculated channel information or the original estimated channel information through the encoding AI network model, and sends the encoding result to the base station.
  • the base station receives the encoded result and inputs it into the decoding AI network model to recover the channel information.
  • the neural network-based CSI compression feedback solution is to compress and encode the channel information at the terminal, send the compressed content to the base station, and decode the compressed content at the base station to restore the channel information.
  • the decoding AI network model of the base station and the encoding AI network model of the terminal need to be jointly trained to achieve a reasonable match.
  • the input of the encoding AI network model is channel information
  • the output is encoding information, that is, channel feature information.
  • the input of the decoding AI network model is encoding information, and the output is restored channel information.
  • the channel information input to the coding AI network model is usually the channel matrix or precoding matrix of all subbands.
  • the precoding matrix is the rank number, that is, the total number of layers, and the number of rows of the precoding matrix is the number of CSI-RS ports.
  • the input dimension of the coding AI network model is determined by the number of ranks, the number of CSI-RS ports, and the number of subbands.
  • the channel information of each channel uses a coding AI network model. For processing, in this way, for CSI-RS with different numbers of subbands, it is necessary to use the AI network model with the corresponding input dimension to process.
  • the input dimension of a certain AI network model is the channel information of CSI-RS with 26 subbands
  • the input dimension of another AI network model is the channel information of CSI-RS with 13 subbands. Since the input dimension of the channel information of CSI-RS with 26 subbands is twice that of the channel information of CSI-RS with 13 subbands, it is impossible to directly use the AI network model with 26 subbands to process the channel information of CSI-RS with 13 subbands, nor can it directly use the AI network model with 13 subbands to process the channel information of CSI-RS with 26 subbands.
  • frequency domain resources are grouped, and channel information corresponding to at least one frequency domain resource in a group is processed using an AI network model, so that the AI network model corresponding to the number of low-frequency domain resources can process the channel information corresponding to the number of high-frequency domain resources, thereby reducing the number of AI network models and the size of the AI network models.
  • a CSI-RS has 26 subbands, which can be divided into 13 groups, each with 2 subbands. Then, an AI network model can be reused to process the channel information of the 13 groups of subbands respectively, and the input dimension of the AI network model is reduced to the channel information of 2 subbands.
  • an information transmission method provided in an embodiment of the present application the execution subject of which is a terminal.
  • the information transmission method executed by the terminal may include the following steps:
  • Step 201 The terminal determines K groups of second channel information from the first channel information based on the first information, wherein the first information includes grouping information of K groups of frequency domain resources, the K groups of second channel information correspond one-to-one to the K groups of frequency domain resources, each group of frequency domain resources in the K groups of frequency domain resources includes at least one frequency domain resource, and K is an integer greater than or equal to 1.
  • the division of frequency domain resources can be based on frequency domain resource units such as sub-bands and physical resource blocks (PRBs).
  • frequency domain resource units such as sub-bands and physical resource blocks (PRBs).
  • PRBs physical resource blocks
  • the frequency domain resources are sub-bands as an example in the embodiments of the present application, which does not constitute a specific limitation here.
  • the above-mentioned first channel information may be complete channel information of a certain channel, which may specifically be at least one of the original channel matrix or vector, the precoding matrix or vector, the preprocessed channel matrix or vector, and the preprocessed precoding matrix or vector.
  • the embodiments of the present application are generally illustrated by taking the channel information as a precoding matrix, which is not specifically limited here.
  • the first information is used to divide the frequency domain resources of CSI-RS into K groups.
  • the K groups of second information represent channel information obtained by the terminal measuring the CSI-RS transmitted on a corresponding group of frequency domain resources.
  • the second channel information may include at least one of the following:
  • the precoding matrix or vector after preprocessing is the precoding matrix or vector after preprocessing.
  • the preprocessing may include preprocessing for compressing the channel information of the frequency domain resources in the same group, for example, performing preprocessing related to subband compression on the channel information of the subbands in the same group. For example, based on the similarity of the channel quality of two subbands in a group of frequency domain resources, the channel information of the two subbands may be compressed to reduce the length of the preprocessed channel information, thereby reducing the complexity of the first processing of the preprocessed channel information, and reducing the resource loss of transmitting the first processed channel characteristic information.
  • the second channel information when the second channel information is channel information of a layer, the channel matrix corresponding to the channel information of the layer has only one column, and in this case, the second channel information can be referred to as a vector.
  • the second channel information when the second channel information includes channel information of at least two layers, the channel information of the at least two layers can also be processed into a vector by preprocessing, which is not specifically described here.
  • the grouping information of the K groups of frequency domain resources includes at least one of the following:
  • the frequency domain span of the frequency domain resources within each group of frequency domain resources
  • the frequency domain resources of CSI-RS can be evenly divided into K groups, for example: a group of 3 subbands; or the frequency domain resources of CSI-RS can be divided into K uneven groups, for example: a group of 3 subbands and a group of 4 subbands.
  • the frequency domain resources of CSI-RS can be divided into K groups according to the number of frequency domain resources in each group of frequency domain resources.
  • the grouping information of K groups of frequency domain resources includes the number of frequency domain resources in each group of frequency domain resources, the number of frequency domain resources in each group of frequency domain resources is determined, but which frequency domain resources in a group of frequency domain resources are specifically adjustable.
  • the terminal can divide the frequency domain resources of CSI-RS into each group in sequence according to the arrangement order of the frequency domain resources of CSI-RS, such as: if the frequency domain resources of CSI-RS include 13 subbands, the first information indicates that the first group of frequency domain resources includes 3 subbands, the second group of frequency domain resources includes 4 subbands, and the third group of frequency domain resources includes 6 subbands, then the terminal can divide the 1st to 3rd subbands of CSI-RS into one group, the 4th to 7th subbands into one group, and the 8th to 13th subbands into one group.
  • the terminal can randomly divide the frequency domain resources of CSI-RS into each group, etc., and the specific division rules can be agreed by the protocol, or indicated by the network side device, or determined by the terminal itself.
  • the frequency domain resources of the CSI-RS can be divided according to the identifiers of the frequency domain resources.
  • the first information directly indicates that subband 1, subband 4, subband 5, and subband 6 are divided into one group, subband 2 and subband 3 are divided into one group, and subbands 7 to 13 are divided into one group.
  • the K groups of frequency domain resources may correspond to the same or different frequency domain intervals.
  • the adjacent frequency domain resources in each group of frequency domain resources may be discontinuous in the frequency domain. For example: assuming that there are 8 sub-bands in total, and the sub-bands in the middle part have deep attenuation, sub-bands 1, 2, 7, and 8 can be divided into one group of frequency domain resources, and sub-bands 3 to 6 can be divided into one group of frequency domain resources. At this time, the sub-bands in the two groups of frequency domain resources have different frequency domain intervals, so that sub-bands with similar channel quality can be located in the same group of frequency domain resources.
  • the grouping information of K groups of frequency domain resources includes the frequency domain span of the frequency domain resources in each group of frequency domain resources
  • the span from the starting frequency domain resource position to the ending frequency domain resource position of the frequency domain resources in each group is certain.
  • all or part of the frequency domain resources within a frequency domain span can be divided into a group.
  • the frequency domain span of the frequency domain resources in each group of frequency domain resources is 3 subbands
  • the first group of frequency domain resources can include the 1st to 3rd subbands
  • the second group of frequency domain resources can include the 4th to 6th subbands.
  • the frequency domain spans of frequency domain resources in different groups may be different.
  • the starting frequency domain resource position of the frequency domain resources within each group of frequency domain resources is certain, and the frequency domain positions of the frequency domain resources within each group of frequency domain resources include the starting frequency domain resource position and the frequency domain resources located after the starting frequency domain resource position. For example: assuming that the starting frequency domain resource position of a group of frequency domain resources is the 4th subband, and the frequency domain span of the group of frequency domain resources is 3 subbands, it can be determined that the group of frequency domain resources includes the 4th to 6th subbands.
  • the ending frequency domain resource position of the frequency domain resources within each group of frequency domain resources is certain, and the frequency domain position of the frequency domain resources within each group of frequency domain resources includes the ending frequency domain resource position and the frequency domain resources located before the ending frequency domain resource position. For example: assuming that the ending frequency domain resource position of a group of frequency domain resources is the 4th subband, and the frequency domain span of the group of frequency domain resources is 3 subbands, it can be determined that the group of frequency domain resources includes the 2nd to 4th subbands.
  • the frequency domain resources in each group of frequency domain resources can be made to satisfy the comb distribution. For example, assuming that the density of frequency domain resources in each group of frequency domain resources is 2, the subbands arranged in odd positions of all CSI-RS subbands can be divided into one group, and the subbands arranged in even positions can be divided into one group.
  • the density of the frequency domain resources in the above set of frequency domain resources can be understood in the following two ways:
  • each frequency domain resource Indicates the proportion of each frequency domain resource to a group of frequency domain resources. For example, if the subband density is 0.5, it means that each subband occupies 0.5 of a group of subbands. At this time, every two subbands correspond to a group of subbands, that is, one of the two consecutive subbands belongs to the first group of subbands, and the other belongs to the second group of subbands;
  • the frequency domain resources in each group of frequency domain resources can be determined based on the offset of the frequency domain position of the frequency domain resources relative to the reference frequency domain position. For example: assuming that the starting frequency domain position of the frequency domain resources in a group of frequency domain resources is taken as the reference frequency domain position, the other frequency domain resources in the group of frequency domain resources can be determined by indicating the offset value of the other frequency domain resources in the group of frequency domain resources compared with the reference frequency domain position through the first information, or the above-mentioned reference frequency domain position can also be 0 or any other frequency domain position by default, which is not specifically limited here.
  • the grouping information of the K groups of frequency domain resources may include at least two items of the above options one to nine, for example: the grouping information of the K groups of frequency domain resources includes the starting frequency domain position and the ending frequency domain resource position in each group of frequency domain resources in the K groups of frequency domain resources. At this time, a part of the frequency domain resources located between the starting frequency domain position and the ending frequency domain resource position may be selected as a corresponding group of frequency domain resources, or the frequency domain resources located between the starting frequency domain position and the ending frequency domain resource position of the same group of frequency domain resources may be used as the group of frequency domain resources.
  • the starting frequency domain position of a group of frequency domain resources is indicated to be the 3rd subband and the ending frequency domain resource position is the 8th subband, it can be determined that the group of frequency domain resources includes the 3rd to 8th subbands.
  • Step 202 The terminal performs a first processing on the M groups of second channel information based on the first AI network model corresponding to each of the M groups of second channel information to obtain M channel characteristic information, and the K groups of second channel information include the M groups of second channel information, where M is a positive integer less than or equal to K.
  • the above-mentioned first AI network model may be an encoding AI network model and/or a compression AI network model, that is, an AI network model that processes channel information on the terminal side to obtain CSI-related information, and the name of the first AI network model is not specifically limited herein.
  • the first AI network model is an encoding AI network model
  • the encoding AI network model matches the decoding AI network model and/or decompression AI network model (that is, the second AI network model in the embodiments of the present application) of the network side device, and/or the first AI network model is jointly trained with the second AI network model of the network side device.
  • the second AI network model may be an AI network model for processing channel feature information on the base station side, and the name of the second AI network model is not specifically limited herein.
  • the second AI network model is a decoding AI network model.
  • the first processing may include at least one of compression processing, encoding processing, and quantization processing.
  • the first processing is an encoding processing as an example.
  • the above-mentioned M groups of second channel information may correspond to the same first AI network model.
  • a common first AI network model is used to perform first processing on the M groups of second channel information respectively to obtain channel characteristic information output by the first AI network model M times.
  • the M groups of second channel information may correspond to different first AI network models.
  • the M first AI network models respectively perform a first processing on a group of second channel information corresponding to each of them to obtain channel characteristic information respectively output by the M first AI network models.
  • a portion of the above-mentioned M groups of second channel information may correspond to the same first AI network model, and another portion may correspond to a different first AI network model.
  • the M group of second channel information is divided into two parts, and the V group of second channel information in the first part uses the same first AI network model, and the (M-V) group of second channel information in the second part uses the same first AI network model, and the first AI network model used by the V group of second channel information and the first AI network model used by the (M-X) group of second channel information are not the same first AI network model.
  • Step 203 The terminal sends second information to the network side device, where the second information includes the M channel characteristic information.
  • the terminal may send the second information to the network side device by CSI reporting, or the terminal may send the second information to the network side device by signaling, which is not specifically limited herein.
  • the first information includes a processing rule for the channel information of X frequency domain resources, wherein H is the number of frequency domain resources of the channel corresponding to the first channel information, X is equal to the remainder of H divided by L, and L, X and H are respectively integers greater than or equal to 1.
  • the remainder that is, the channel information of the X frequency domain resources, may be processed according to at least one of the following processing rules:
  • Y is equal to L.
  • X frequency domain resources can be merged into any group of frequency domain resources. For example: assuming that H is equal to 13 and L is equal to 6, the 13 subbands can be divided into 2 groups, and the remainder of the subband can be merged into the first group of frequency domain resources or the second group of frequency domain resources. For example: the first 6 subbands are in one group, and the last 7 subbands are in one group; or, the subbands arranged in odd positions or with odd subband numbers are in one group, and the subbands arranged in even positions or with even subband numbers are in another group.
  • the two groups of subbands can use the same or different AI network models, where if the number of subbands in the two groups of subbands is different, in this case, the channel information of the group with fewer subbands can be padded to the input dimension of the AI network model by padding with zeros.
  • Y is equal to (L-X).
  • X frequency domain resources and repeated (L-X) frequency domain resources can constitute a group of frequency domain resources, and the group of frequency domain resources has L frequency domain resources.
  • the repeated (L-X) frequency domain resources can be a frequency domain resource repeated (L-X) times within the group or other groups, or (L-X) frequency domain resources within the group or other groups are repeated in the first group of frequency domain resources.
  • the 13 subbands can be divided into 3 groups, the first group is subband 1 to subband 6, the second group is subband 7 to subband 12, and the third group is subband 13 and repeated 5 subbands.
  • the subbands in the third group can be [1, 2, 3, 4, 5, 13], or subband [12, 12, 12, 12, 13], or subband [13, 13, 13, 13, 13], or subband [8, 9, 10, 11, 12, 13], which are not exhaustive here.
  • Y is equal to 0.
  • X frequency domain resources are directly used as a group of frequency domain resources.
  • the method of supplementing the dimension of the channel information of the X frequency domain resources to the target dimension may be to fill in zeros or to supplement the interpolation values determined according to preset rules, wherein, in the case of supplementing the interpolation values determined according to preset rules, the preset rules may be trained together with the first AI network model and the second AI network model.
  • the network-side device restores the M groups of second channel information based on the second AI network models corresponding to the M channel feature information, and discards the supplemented interpolation values based on the above preset rules.
  • the first information satisfies at least one of the following:
  • the network side device may indicate the grouping information of the frequency domain resources through signaling, for example: including the number of groups K, or the number of frequency domain resources in each group of frequency domain resources, or which frequency domain resources are specifically included in each group of frequency domain resources.
  • the network side device may configure the grouping information of frequency domain resources in the CSI report configuration (report config).
  • the terminal may determine a method for grouping frequency domain resources according to an input dimension of the first AI network model it has, so that each group of second channel information after grouping matches the input dimension of the first AI network model of the terminal.
  • the terminal may report the first information to the network side device.
  • the frequency domain resources in the same group meet at least one of the following conditions:
  • the frequency domain spans are the same or the frequency domain spans are different;
  • the frequency domain intervals are the same or the frequency domain intervals are different;
  • the frequency domain positions partially overlap or the frequency domain positions do not overlap
  • the corresponding channel quality difference is less than a preset threshold.
  • the frequency domain span of frequency domain resources within the same group may be the frequency domain range of a single frequency domain resource within a group of frequency domain resources.
  • a group of frequency domain resources includes frequency domain resource A and frequency domain resource B, wherein the frequency range of frequency domain resource A is 2800 to 3000 Hz, i.e., the frequency domain span of frequency domain resource A is 200 Hz, and the frequency range of frequency domain resource B is 3100 to 3200 Hz, i.e., the frequency domain span of frequency domain resource B is 100 Hz.
  • the frequency domain interval of frequency domain resources within the same group may be the interval frequency between two adjacent frequency domain resources within a group of frequency domain resources.
  • a group of frequency domain resources includes subband 1, subband 2, and subband 4, wherein the frequency domain interval between subband 1 and subband 2 is 1 subband, and the frequency domain interval between subband 2 and subband 4 is 2 subbands.
  • the partial overlap of the frequency domain positions of the frequency domain resources in the same group may be that the frequency domain positions of at least two frequency domain resources in a group of frequency domain resources partially overlap, for example: a group of frequency domain resources includes frequency domain resource A and frequency domain resource B.
  • Source B wherein the frequency range of frequency domain resource A is 2800-3150 Hz, and the frequency range of frequency domain resource B is 3100-3200 Hz, at this time, the frequency ranges of frequency domain resource A and frequency domain resource B partially overlap.
  • the frequency domain positions of frequency domain resources in the same group do not overlap, and the frequency domain positions of at least two frequency domain resources in a group of frequency domain resources may not overlap at all, which will not be described in detail here.
  • the difference in channel quality corresponding to frequency domain resources in the same group is less than a preset threshold, and frequency domain resources with similar channel quality may be divided into one group. For example, assuming that there are 8 sub-bands in total, among which the sub-bands in the middle part have deep attenuation, sub-bands 1, 2, 7, and 8 may be divided into one group of frequency domain resources, and sub-bands 3 to 6 may be divided into one group of frequency domain resources. In this case, sub-bands with similar channel quality may be located in the same group of frequency domain resources.
  • the method before the terminal determines K groups of second channel information from the first channel information based on the first information, the method further includes:
  • the terminal receives first indication information from the network side device, wherein the first indication information indicates the first information or an identifier of the first information or an identifier of the first AI network model, and the first AI network model is associated with the first information;
  • the terminal determines the first information according to the first indication information.
  • the terminal obtains a first association relationship between the first information and the identifier of the first information.
  • the association relationship between various first information and its identifier may be agreed upon in the protocol or the network side device may configure the association relationship in advance. In this way, when the network side device indicates the identifier of the first information, the terminal may determine the first information based on the association relationship between the identifier and the first information.
  • the first AI network model is associated with the first information, and the first information and the first AI network model are trained and/or transmitted together. For example, in the process of training the first AI network model, the frequency domain interval of the channel information that can be input by the first AI network model and the number of frequency domain resources are determined. In this way, when the terminal obtains the first AI network model, it also obtains the first information associated with the first AI network model. In this way, the network side device can instruct the terminal which first AI network model to use, and the terminal determines the first information associated with the first AI network model to be used accordingly.
  • the network side device may configure in advance the first information associated with at least two first AI network models. In this way, when the network side device indicates an identifier of a first AI network model, the terminal may determine the first information based on the association between the identifier and the first information.
  • the first indication information may be included in a CSI report configuration (CSI report config).
  • the first information may be indicated or configured by the network side device.
  • the information transmission method further includes:
  • the terminal sends second indication information to the network side device, wherein the second indication information indicates the first information or an identifier of the first information or an identifier of the first AI network model, and the first AI network model is associated with the first information.
  • the network side device may indicate part of the first information and/or the protocol may agree on part of the first information, and the terminal determines the complete first information according to the indication of the network side device and/or the agreement of the protocol, for example: Assume that the network side device indicates that K is equal to 4, and the protocol stipulates that X frequency domain resources remaining after H and L are divided by (L-X) frequency domain resources constitute the first group of frequency domain resources, and the terminal obtains the rank of the target downlink channel equal to 13, then the terminal decides to divide the 13 subbands into 4 groups.
  • the terminal can determine the number of subbands included in each group of frequency domain resources according to the indication of the network side and the agreement of the protocol, and/or determine which one or which subbands are specifically included in each group of frequency domain resources.
  • the first group of frequency domain resources is subbands 1 to 4, the second group is subbands 5 to 8, the third group is subbands 9 to 12, and the fourth group is subbands 10 to 13; or, the first group is subbands 1 to 4, the second group of frequency domain resources is subbands 4 to 7, the third group of frequency domain resources is subbands 7 to 10, and the fourth group of frequency domain resources is subbands 10 to 13; or, the first group of frequency domain resources is subbands 1 to 4, the second group of frequency domain resources is subbands 5 to 8, the third group of frequency domain resources is subbands 9 to 12, and the fourth group of frequency domain resources is subbands [12,12,12,13].
  • the terminal may determine the number of frequency domain resources contained in each group of frequency domain resources according to the input dimension of the first AI network model it has, for example: matching the dimension of each group of second channel information divided according to the first information with the input dimension of the first AI network side model.
  • the information transmission method further includes:
  • the terminal determines, according to the third information, frequency domain resources in each group of frequency domain resources in the K groups of frequency domain resources, where the grouping information of the K groups of frequency domain resources includes a correspondence between the K groups of frequency domain resources and the frequency domain resources respectively included;
  • the third information includes the frequency domain interval of the frequency domain resources in each group of frequency domain resources agreed by the protocol, and the number of frequency domain resources in each group of frequency domain resources or the value of K indicated by the network side device.
  • the terminal can determine to divide the 16 subbands into 4 groups, such as: the first group is subbands [1,3,5,7], the second group is subbands [2,4,6,8], the third group is subbands [9,11,13,15], and the fourth group is subbands [10,12,14,16].
  • the information transmission method further includes:
  • the terminal determines, according to the fourth information, frequency domain resources in each group of frequency domain resources in the K groups of frequency domain resources, where the grouping information of the K groups of frequency domain resources includes a correspondence between the K groups of frequency domain resources and the frequency domain resources respectively included;
  • the fourth information includes the processing rules agreed upon by the protocol, and the target frequency domain interval and/or target number of frequency domain resources associated with the first AI network model, the target frequency domain interval is the frequency domain interval of frequency domain resources within a group of frequency domain resources, and the target number of frequency domain resources is the number of frequency domain resources within a group of frequency domain resources.
  • the protocol stipulates that the processing rule for the X frequency domain resources remaining after the division of H and L is not to report, and stipulates that the target frequency domain interval associated with at least one first AI network model is 1, and the target number of frequency domain resources L is 4, if the actual number of subbands H of the target downlink channel is 13, then X is equal to 1, and the terminal can determine that the 13 subbands are divided into 3 groups, the first group is subbands [1,2,3,4], the second group is subbands [5,6,7,8], and the third group is subbands [9,10,11,12], and the terminal does not perform the first processing on subband 13, and does not report the channel characteristic information after the first processing of subband 13.
  • the protocol stipulates that the processing rule for the X frequency domain resources remaining after the division of H and L is to fill the channel information of the X frequency domain resources with zeros to the length of the channel information of the L frequency domain resources as a group of frequency domain resources, and stipulate that the target frequency domain interval associated with at least one first AI network model is 1, and the number of target frequency domain resources L is 4.
  • the terminal can determine to divide the 13 subbands into 4 groups, the first group is subbands [1,2,3,4], the second group is subbands [5,6,7,8], the third group is subbands [9,10,11,12], and the fourth group is subbands [13,0,0,0].
  • the terminal can report the selected first information to the network side device, so that after obtaining the second information, the network side device can determine the channel information of which frequency domain resources each channel characteristic information is based on according to the first information reported by the terminal, thereby restoring the channel information of these frequency domain resources and obtaining the first channel information.
  • the information processing method further includes:
  • the terminal sends target capability information to the network side device, where the target capability information indicates whether the terminal supports frequency domain resource grouping capability.
  • the target capability information indicates at least one of the following:
  • the frequency domain interval between frequency domain resources in the same group supported by the terminal is the same group supported by the terminal.
  • the terminal reports the target capability information to the network side device, so that the network side device can configure or indicate the first information that the terminal can support when configuring or indicating the first information; and/or, the network side device can configure or indicate the first AI network model that matches its capability for the terminal when configuring or indicating the first AI network model.
  • the information processing method further includes:
  • the terminal receives fifth information from the network side device, where the fifth information indicates and/or configures the first AI network model corresponding to each of the M groups of second channel information, or the fifth information indicates the first AI network model corresponding to the second channel information of at least some groups in the M groups of second channel information;
  • the terminal determines the first information according to the fifth information.
  • the M groups of second channel information may correspond to different first AI network models.
  • the network side device indicates the first AI network model used by each group of second channel information through the fifth information.
  • the terminal can determine the first AI network model corresponding to each group of second channel information according to the instruction of the network side device, and determine the first information that can process a group of second channel information into an input format that conforms to the corresponding first AI network model.
  • At least part of the second channel information of the group may correspond to the same first AI network model.
  • the network side device indicates the first AI network model used by at least part of the second channel information of the group through the fifth information.
  • the terminal can determine the first AI network model corresponding to the at least part of the second channel information of the group according to the instruction of the network side device, and determine the first information capable of processing at least part of the second channel information of the group into an input format that conforms to the corresponding first AI network model.
  • the network side device may indicate each group of second channel information or at least part of the group of second channel information.
  • the corresponding first AI network model may indicate each group of second channel information or at least part of the group of second channel information.
  • the information processing method further includes:
  • the terminal sends third indication information to the network side device, where the third indication information indicates a first AI network model corresponding to each of the M groups of second channel information.
  • the terminal can select and report to the network side device the first AI network model corresponding to each group of second channel information or at least part of the group of second channel information.
  • the first AI network model corresponding to each of the M groups of second channel information satisfies at least one of the following:
  • the frequency domain resource groups including the same number of frequency domain resources correspond to the same first AI network model
  • the M groups of second channel information correspond to the same first AI network model
  • a dimension of a set of second channel information matches a dimension of input information of a corresponding first AI network model
  • the network side device indicates the first AI network side model corresponding to each of the M groups of second channel information.
  • the first AI network model corresponds to the value of L, for example, a set of frequency domain resources having 2 subbands and a set of frequency domain resources having 3 subbands have different first AI network models.
  • the input dimension of the first AI network model may match the dimension of the channel information of the corresponding L frequency domain resources.
  • the M groups of second channel information may correspond to the same first AI network model.
  • the M groups of second channel information are respectively input into the same first AI network model to obtain M channel feature information obtained by the first AI network model through M times of first processing.
  • the terminal may determine the first AI network-side model corresponding to each group of second channel information according to an instruction of the network-side device.
  • frequency domain resources are grouped, and the channel information of each group of frequency domain resources is processed using a corresponding AI network model, wherein the first channel information of a channel can be divided into K groups, and each AI network model only inputs the channel information of a corresponding group of frequency domain resources without inputting the channel information of the entire channel, so that the AI network model with a low number of frequency domain resources can be used to process the channel information of a high number of frequency domain resources, thereby improving the multiplexing efficiency and flexibility of the AI network model.
  • the information processing method provided in the embodiment of the present application may be executed by a network-side device. As shown in FIG3 , the information processing method may include the following steps:
  • Step 301 the network side device receives the second information from the terminal, wherein the second information includes M channel characteristic information, and the M channel characteristic information is channel characteristic information obtained by performing a first processing on the M groups of second channel information based on the first AI network model corresponding to each of the M groups of second channel information, and M is an integer greater than or equal to 1.
  • the second information has the same meaning as the second information in the method embodiment shown in FIG. 2 , and will not be described in detail here.
  • Step 302 The network side device determines, according to the first information, a second AI network side model corresponding to each of the M channel characteristic information, wherein the first information includes grouping information of K groups of frequency domain resources, and the K groups of second information
  • the channel information corresponds to the K groups of frequency domain resources one by one, each group of frequency domain resources in the K groups of frequency domain resources includes at least one frequency domain resource, and K is an integer greater than or equal to M.
  • the above-mentioned first information has the same meaning as the first information in the method embodiment shown in Figure 2, and the network side device is used to determine the second AI network side model corresponding to each of the M channel characteristic information according to the first information, wherein the first AI network model for obtaining the channel characteristic information and the second AI network side model corresponding to the channel characteristic information are mutually matched AI network models or AI network models obtained by joint training, such as: the first AI network model is an encoding AI network model or the encoding part of an AI network model, and the second AI network model is a decoding AI network model or the decoding part of an AI network model.
  • Step 303 The network side device performs a second processing on the M channel characteristic information based on the second AI network side model corresponding to each of the M channel characteristic information to obtain the M groups of second channel information.
  • the second processing may include at least one of decoding, decompression, and dequantization.
  • the frequency domain resources include a subband or a physical resource block PRB.
  • the grouping information of the K groups of frequency domain resources includes at least one of the following:
  • the frequency domain span of the frequency domain resources within each group of frequency domain resources
  • the first information includes a processing rule for the channel information of X frequency domain resources, wherein H is the number of frequency domain resources of the channel corresponding to the first channel information, X is equal to the remainder of H divided by L, and L, X and H are respectively integers greater than or equal to 1.
  • the processing rule includes at least one of the following:
  • first group of frequency domain resources based on (L-X) frequency domain resources and the X frequency domain resources, wherein the K groups of frequency domain resources include the first group of frequency domain resources, and the frequency domain resources of the channel corresponding to the first channel information include the (L-X) frequency domain resources;
  • the dimension of the channel information of the X frequency domain resources is supplemented to the target dimension, where the target dimension is the dimension of the channel information of the L frequency domain resources.
  • the network side device can restore the channel information of X frequency domain resources according to the processing rule of the channel information of X frequency domain resources, or, when the processing rule of the channel information of X frequency domain resources is to abandon the reporting of the In the case of channel information of X frequency domain resources, the network side device does not obtain the channel characteristic information corresponding to the channel information of X frequency domain resources. At this time, the network side device can obtain and restore the channel information of other parts.
  • the first information satisfies at least one of the following:
  • the frequency domain resources in the same group meet at least one of the following conditions:
  • the frequency domain spans are the same or the frequency domain spans are different;
  • the frequency domain intervals are the same or the frequency domain intervals are different;
  • the frequency domain positions partially overlap or the frequency domain positions do not overlap
  • the corresponding channel quality difference is less than a preset threshold.
  • the information processing method before the network side device receives the second information from the terminal, the information processing method further includes:
  • the network side device sends first indication information to the terminal, wherein the first indication information indicates the first information or an identifier of the first information or an identifier of the first AI network model, and the first AI network model is associated with the first information.
  • the information processing method before the network side device determines, according to the first information, the second AI network side model corresponding to each of the M channel characteristic information, the information processing method further includes:
  • the network-side device receives second indication information from the terminal, wherein the second indication information indicates the first information or an identifier of the first information or an identifier of the first AI network model, and the first AI network model is associated with the first information;
  • the network side device determines the first information according to the second indication information.
  • the second channel information includes at least one of the following:
  • the precoding matrix or vector after preprocessing is the precoding matrix or vector after preprocessing.
  • the information processing method further includes:
  • the network side device receives target capability information from the terminal, where the target capability information indicates whether the terminal supports frequency domain resource grouping capability.
  • the target capability information indicates at least one of the following:
  • the frequency domain interval between frequency domain resources in the same group supported by the terminal is the same group supported by the terminal.
  • the information processing method further includes:
  • the network side device sends fifth information to the terminal, where the fifth information indicates and/or configures the first AI network model corresponding to each of the M groups of second channel information, or the fifth information indicates the first AI network model corresponding to the second channel information of at least some groups in the M groups of second channel information.
  • the information processing method further includes:
  • the network side device receives third indication information from the terminal, where the third indication information indicates a first AI network model corresponding to each of the M groups of second channel information.
  • the terminal can select and report the first AI network model corresponding to each of the M groups of second channel information.
  • the network side device can determine the second AI network model corresponding to each of the M groups of second channel information based on the first AI network model corresponding to each of the M groups of second channel information, wherein the first AI network model and the second AI network model corresponding to the same group of second channel information are encoding and decoding AI network models that are matched with each other or obtained by joint training.
  • the first AI network model corresponding to each of the M groups of second channel information satisfies at least one of the following:
  • the frequency domain resource groups including the same number of frequency domain resources correspond to the same first AI network model
  • the M groups of second channel information correspond to the same first AI network model
  • a dimension of a set of second channel information matches a dimension of input information of a corresponding first AI network model
  • the network side device indicates the first AI network side model corresponding to each of the M groups of second channel information.
  • a network side device receives M channel characteristic information from a terminal, and determines, based on the first information, a second AI network model corresponding to each of the M channel characteristic information, thereby using the second AI network model to restore the corresponding channel characteristic information into second channel information, thereby realizing the channel characteristic information reception and recovery process, wherein the input of the second AI network model is the channel characteristic information of part of the frequency domain resources, so that the model size of the second AI network model is smaller, and in addition, by dividing the same number of frequency domain resources into a group, the same second AI network model can be reused for channels with different numbers of frequency domain resources, so that the AI network model with a low number of frequency domain resources can be used to process the channel information with a high number of frequency domain resources, thereby improving the reuse efficiency and flexibility of the AI network model.
  • the information transmission method provided in the embodiment of the present application can be executed by an information transmission device.
  • the information transmission device provided in the embodiment of the present application is described by taking the information transmission method executed by the information transmission device as an example.
  • An information transmission device provided in an embodiment of the present application may be a device in a terminal. As shown in FIG. 4 , the information transmission device 400 may include the following modules:
  • a first determination module 401 is configured to determine K groups of second channel information from the first channel information based on the first information, wherein the first information includes grouping information of K groups of frequency domain resources, the K groups of second channel information correspond to the K groups of frequency domain resources one by one, each group of frequency domain resources in the K groups of frequency domain resources includes at least one frequency domain resource, and K is an integer greater than or equal to 1;
  • a first processing module 402 is used to perform a first processing on the M groups of second channel information based on the first AI network model corresponding to each of the M groups of second channel information to obtain M channel feature information, the K groups of second channel information include the M groups of second channel information, and M is a positive integer less than or equal to K;
  • the first sending module 403 is used to send second information to the network side device, where the second information includes the M channel characteristic information.
  • the frequency domain resources include subbands or physical resource blocks (PRBs).
  • PRBs physical resource blocks
  • the grouping information of the K groups of frequency domain resources includes at least one of the following:
  • the frequency domain span of the frequency domain resources within each group of frequency domain resources
  • the first information includes a processing rule for channel information of X frequency domain resources, wherein H is the number of frequency domain resources of the channel corresponding to the first channel information, X is equal to the remainder of H divided by L, and L, X and H are respectively integers greater than or equal to 1.
  • the processing rule includes at least one of the following:
  • the K groups of frequency domain resources include the first group of frequency domain resources, and the frequency domain resources of the channel corresponding to the first channel information include the Y frequency domain resources;
  • the dimension of the channel information of the X frequency domain resources is supplemented to the target dimension, where the target dimension is the dimension of the channel information of the L frequency domain resources.
  • the first information satisfies at least one of the following:
  • the frequency domain resources in the same group satisfy at least one of the following:
  • the frequency domain spans are the same or the frequency domain spans are different;
  • the frequency domain intervals are the same or the frequency domain intervals are different;
  • the frequency domain positions partially overlap or the frequency domain positions do not overlap
  • the corresponding channel quality difference is less than a preset threshold.
  • the information transmission device 400 further includes:
  • a second receiving module configured to receive first indication information from the network side device, wherein the first indication information indicates the first information or an identifier of the first information or an identifier of the first AI network model, and the first AI network model is associated with the first information;
  • a third determining module is used to determine the first information according to the first indication information.
  • the information transmission device 400 further includes:
  • a second sending module is used to send second indication information to the network side device, wherein the second indication information indicates the first information or the identifier of the first information or the identifier of the first AI network model, and the first AI network model is associated with the first information.
  • the information transmission device 400 further includes:
  • a fourth determination module configured to determine frequency domain resources in each group of frequency domain resources in the K groups of frequency domain resources according to the third information, wherein the grouping information of the K groups of frequency domain resources includes a correspondence between the K groups of frequency domain resources and the frequency domain resources respectively included;
  • the third information includes the frequency domain interval of the frequency domain resources in each group of frequency domain resources agreed by the protocol, and the number of frequency domain resources in each group of frequency domain resources or the value of K indicated by the network side device.
  • the information transmission device 400 further includes:
  • a fifth determination module configured to determine frequency domain resources in each group of frequency domain resources in the K groups of frequency domain resources according to the fourth information, wherein the grouping information of the K groups of frequency domain resources includes a correspondence between the K groups of frequency domain resources and the frequency domain resources respectively included;
  • the fourth information includes the processing rules agreed upon by the protocol, and the target frequency domain interval and/or target number of frequency domain resources associated with the first AI network model, the target frequency domain interval is the frequency domain interval of frequency domain resources within a group of frequency domain resources, and the target number of frequency domain resources is the number of frequency domain resources within a group of frequency domain resources.
  • the second channel information includes at least one of the following:
  • the precoding matrix or vector after preprocessing is the precoding matrix or vector after preprocessing.
  • the preprocessing includes preprocessing of compressing channel information of frequency domain resources in the same group.
  • the information transmission device 400 further includes:
  • the third sending module is used to send target capability information to the network side device, where the target capability information indicates whether the terminal supports the capability of frequency domain resource grouping.
  • the target capability information indicates at least one of the following:
  • the frequency domain interval between frequency domain resources in the same group supported by the terminal is the same group supported by the terminal.
  • the information transmission device 400 further includes:
  • a third receiving module is configured to receive fifth information from the network side device, where the fifth information indicates and/or configures the first AI network model corresponding to each of the M groups of second channel information, or the fifth information indicates the first AI network model corresponding to the second channel information of at least some groups in the M groups of second channel information;
  • a sixth determination module is used to determine the first information according to the fifth information.
  • the information transmission device 400 further includes:
  • the fourth sending module is used to send third indication information to the network side device, where the third indication information indicates the first AI network model corresponding to each of the M groups of second channel information.
  • the first AI network model corresponding to each of the M groups of second channel information satisfies at least one of the following:
  • the frequency domain resource groups including the same number of frequency domain resources correspond to the same first AI network model
  • the M groups of second channel information correspond to the same first AI network model
  • a dimension of a set of second channel information matches a dimension of input information of a corresponding first AI network model
  • the network side device indicates the first AI network side model corresponding to each of the M groups of second channel information.
  • the information transmission device in the embodiment of the present application can be an electronic device, such as an electronic device with an operating system, or a component in an electronic device, such as an integrated circuit or a chip.
  • the electronic device can be a terminal, or it can be other devices other than a terminal.
  • the terminal can include but is not limited to the types of terminal 11 listed above, and other devices can be servers, network attached storage (NAS), etc., which are not specifically limited in the embodiment of the present application.
  • the information transmission device 400 provided in the embodiment of the present application can implement each process implemented by the terminal in the method embodiment shown in Figure 2, and can achieve the same beneficial effects. To avoid repetition, it will not be described here.
  • the information processing method provided in the embodiment of the present application can be executed by an information processing device.
  • the information processing device provided in the embodiment of the present application is described by taking the information processing device executing the information processing method as an example.
  • An information processing device provided in an embodiment of the present application may be a device in a network-side device. As shown in FIG5 , the information processing device 500 may include the following modules:
  • a first receiving module 501 is used to receive second information from a terminal, wherein the second information includes M channel characteristic information, and the M channel characteristic information is channel characteristic information obtained by performing a first processing on the M groups of second channel information based on the first AI network model corresponding to each of the M groups of second channel information, and M is an integer greater than or equal to 1;
  • the second determination module 502 is used to determine the second AI network side model corresponding to each of the M channel characteristic information according to the first information, wherein the first information includes grouping information of K groups of frequency domain resources, the K groups of second channel information correspond to the K groups of frequency domain resources one by one, and each group of frequency domain resources in the K groups of frequency domain resources includes at least one frequency domain resources, K is an integer greater than or equal to M;
  • the second processing module 503 is used to perform a second processing on the M channel characteristic information based on the second AI network side model corresponding to each of the M channel characteristic information to obtain the M groups of second channel information.
  • the frequency domain resources include subbands or physical resource blocks (PRBs).
  • PRBs physical resource blocks
  • the grouping information of the K groups of frequency domain resources includes at least one of the following:
  • the frequency domain span of the frequency domain resources within each group of frequency domain resources
  • the first information includes a processing rule for channel information of X frequency domain resources, wherein H is the number of frequency domain resources of the channel corresponding to the first channel information, X is equal to the remainder of H divided by L, and L, X and H are respectively integers greater than or equal to 1.
  • the processing rule includes at least one of the following:
  • first group of frequency domain resources based on (L-X) frequency domain resources and the X frequency domain resources, wherein the K groups of frequency domain resources include the first group of frequency domain resources, and the frequency domain resources of the channel corresponding to the first channel information include the (L-X) frequency domain resources;
  • the dimension of the channel information of the X frequency domain resources is supplemented to a target dimension, where the target dimension is the dimension of the channel information of the L frequency domain resources.
  • the first information satisfies at least one of the following:
  • the frequency domain resources in the same group satisfy at least one of the following:
  • the frequency domain spans are the same or the frequency domain spans are different;
  • the frequency domain intervals are the same or the frequency domain intervals are different;
  • the frequency domain positions partially overlap or the frequency domain positions do not overlap
  • the corresponding channel quality difference is less than a preset threshold.
  • the information processing device 500 further includes:
  • a fifth sending module configured to send first indication information to the terminal, wherein the first indication information indicates the first information or an identifier of the first information or an identifier of the first AI network model, and the first AI network model is associated with the first information.
  • the information processing device 500 further includes:
  • a fourth receiving module configured to receive second indication information from the terminal, wherein the second indication information indicates the first information or an identifier of the first information or an identifier of the first AI network model, and the first AI network model is associated with the first information;
  • a seventh determination module is used to determine the first information according to the second indication information.
  • the second channel information includes at least one of the following:
  • the precoding matrix or vector after preprocessing is the precoding matrix or vector after preprocessing.
  • the information processing device 500 further includes:
  • the fifth receiving module is used to receive target capability information from the terminal, where the target capability information indicates whether the terminal supports frequency domain resource grouping capability.
  • the target capability information indicates at least one of the following:
  • the frequency domain interval between frequency domain resources in the same group supported by the terminal is the same group supported by the terminal.
  • the information processing device 500 further includes:
  • a sixth sending module is used to send fifth information to the terminal, where the fifth information indicates and/or configures the first AI network model corresponding to each of the M groups of second channel information, or the fifth information indicates the first AI network model corresponding to the second channel information of at least some groups in the M groups of second channel information.
  • the information processing device 500 further includes:
  • a sixth receiving module is used to receive third indication information from the terminal, where the third indication information indicates the first AI network model corresponding to each of the M groups of second channel information.
  • the first AI network model corresponding to each of the M groups of second channel information satisfies at least one of the following:
  • the frequency domain resource groups including the same number of frequency domain resources correspond to the same first AI network model
  • the M groups of second channel information correspond to the same first AI network model
  • a dimension of a set of second channel information matches a dimension of input information of a corresponding first AI network model
  • the network side device indicates the first AI network side model corresponding to each of the M groups of second channel information.
  • the information processing device 500 provided in the embodiment of the present application can implement each process implemented by the network side device in the method embodiment shown in Figure 3, and can achieve the same beneficial effects. To avoid repetition, it will not be described here.
  • the embodiment of the present application further provides a communication device 600, including a processor 601 and a memory 602, wherein the memory 602 stores a program or instruction that can be run on the processor 601.
  • the communication device 600 is a terminal
  • the program or instruction is executed by the processor 601 to implement the various steps of the method embodiment shown in FIG2, and the same technical effect can be achieved.
  • the communication device 600 is a network side device
  • the program or instruction is executed by the processor 601 to implement the various steps of the method embodiment shown in FIG3, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.
  • the embodiment of the present application also provides a terminal, including a processor and a communication interface, the processor is used to determine K groups of second channel information from the first channel information based on the first information, wherein the first information includes the grouping information of the K groups of frequency domain resources, the K groups of second channel information correspond to the K groups of frequency domain resources one by one, each group of frequency domain resources in the K groups of frequency domain resources includes at least one frequency domain resource, K is an integer greater than or equal to 1; the processor is also used to perform a first processing on the M groups of second channel information based on the first AI network model corresponding to each of the M groups of second channel information to obtain M channel feature information, the K groups of second channel information include the M groups of second channel information, M is a positive integer less than or equal to K; the communication interface is used to send the second information to the network side device, and the second information includes the M channel feature information.
  • This terminal embodiment can implement the various processes performed by the information transmission device 400 shown in Figure 4, and can achieve the same technical effect, which will not be repeated
  • 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 and at least some of the components of a processor 710.
  • the terminal 700 may also include a power source (such as a battery) for supplying power to each component, and the power source may be logically connected to the processor 710 through a power management system, so as to implement functions such as managing charging, discharging, and power consumption management through the power management system.
  • a power source such as a battery
  • the terminal structure shown in FIG7 does not constitute a limitation on the terminal, and the terminal may include more or fewer components than shown in the figure, or combine certain components, or arrange components differently, which will not be described in detail here.
  • the input unit 704 may include a graphics processing unit (GPU) 7041 and a microphone 7042, and the graphics processor 7041 processes the image data of a static picture or video obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode.
  • the display unit 706 may include a display panel 7061, and the display panel 7061 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc.
  • the user input unit 707 includes a touch panel 7071 and at least one of other input devices 7072.
  • the touch panel 7071 is also called a 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, a physical keyboard, function keys (such as a volume control key, a switch key, etc.), a trackball, a mouse, and a joystick, which will not be repeated here.
  • the RF unit 701 can transmit the data to the processor 710 for processing; in addition, the RF unit 701 can send uplink data to the network side device.
  • 701 includes but is not limited to antennas, amplifiers, transceivers, couplers, low noise amplifiers, duplexers, etc.
  • the memory 709 can be used to store software programs or instructions and 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 instruction required for at least one function (such as a sound playback function, an image playback function, etc.), etc.
  • the memory 709 may include a volatile memory or a non-volatile memory, or the memory 709 may include both volatile and non-volatile memories.
  • the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory.
  • the volatile memory may be a random access memory (RAM), a static random access memory (SRAM), a dynamic random access memory (DRAM), a synchronous dynamic random access memory (SDRAM), a double data rate synchronous dynamic random access memory (DDRSDRAM), an enhanced synchronous dynamic random access memory (ESDRAM), a synchronous link dynamic random access memory (SLDRAM) and a direct memory bus random access memory (DRRAM).
  • the memory 709 in the embodiment of the present application includes but is not limited to these and any other suitable types of memories.
  • the processor 710 may include one or more processing units; optionally, the processor 710 integrates an application processor and a modem processor, wherein the application processor mainly processes operations related to an operating system, a user interface, and application programs, and the modem processor mainly processes wireless communication signals, such as a baseband processor. It is understandable that the modem processor may not be integrated into the processor 710.
  • the processor 710 is configured to determine K groups of second channel information from the first channel information based on the first information, wherein the first information includes grouping information of K groups of frequency domain resources, the K groups of second channel information correspond to the K groups of frequency domain resources one by one, each group of frequency domain resources in the K groups of frequency domain resources includes at least one frequency domain resource, and K is an integer greater than or equal to 1;
  • the processor 710 is further configured to perform a first process on the M groups of second channel information based on the first AI network model corresponding to each of the M groups of second channel information to obtain M channel feature information, the K groups of second channel information including the M groups of second channel information, where M is a positive integer less than or equal to K;
  • the radio frequency unit 701 is used to send second information to the network side device, where the second information includes the M channel characteristic information.
  • the frequency domain resources include subbands or physical resource blocks (PRBs).
  • PRBs physical resource blocks
  • the grouping information of the K groups of frequency domain resources includes at least one of the following:
  • the frequency domain span of the frequency domain resources within each group of frequency domain resources
  • the first information includes a processing rule for channel information of X frequency domain resources, wherein H is the number of frequency domain resources of the channel corresponding to the first channel information, X is equal to the remainder of H divided by L, and L, X and H are respectively integers greater than or equal to 1.
  • the processing rule includes at least one of the following:
  • the K groups of frequency domain resources include the first group of frequency domain resources, and the frequency domain resources of the channel corresponding to the first channel information include the Y frequency domain resources;
  • the dimension of the channel information of the X frequency domain resources is supplemented to the target dimension, where the target dimension is the dimension of the channel information of the L frequency domain resources.
  • the first information satisfies at least one of the following:
  • the frequency domain resources in the same group satisfy at least one of the following:
  • the frequency domain spans are the same or the frequency domain spans are different;
  • the frequency domain intervals are the same or the frequency domain intervals are different;
  • the frequency domain positions partially overlap or the frequency domain positions do not overlap
  • the corresponding channel quality difference is less than a preset threshold.
  • the processor 710 performs the step of determining K groups of second channel information from the first channel information based on the first information:
  • the radio frequency unit 701 is further configured to receive first indication information from the network side device, wherein the first indication information indicates the first information or an identifier of the first information or an identifier of the first AI network model, and the first AI network model is associated with the first information;
  • the processor 710 is further configured to determine the first information according to the first indication information.
  • the radio frequency unit 701 is further used to send second indication information to the network side device, wherein the second indication information indicates the first information or the identifier of the first information or the identifier of the first AI network model, and the first AI network model is associated with the first information.
  • the processor 710 is further configured to determine, according to the third information, each group of frequency domain resources in the K groups of frequency domain resources.
  • the grouping information of the K groups of frequency domain resources includes a correspondence between the K groups of frequency domain resources and the frequency domain resources respectively included;
  • the third information includes the frequency domain interval of the frequency domain resources in each group of frequency domain resources agreed by the protocol, and the number of frequency domain resources in each group of frequency domain resources or the value of K indicated by the network side device.
  • the processor 710 is further configured to determine, according to the fourth information, frequency domain resources in each group of frequency domain resources in the K groups of frequency domain resources, where the grouping information of the K groups of frequency domain resources includes a correspondence between the K groups of frequency domain resources and the frequency domain resources respectively included;
  • the fourth information includes the processing rules agreed upon by the protocol, and the target frequency domain interval and/or target number of frequency domain resources associated with the first AI network model, the target frequency domain interval is the frequency domain interval of frequency domain resources within a group of frequency domain resources, and the target number of frequency domain resources is the number of frequency domain resources within a group of frequency domain resources.
  • the second channel information includes at least one of the following:
  • the precoding matrix or vector after preprocessing is the precoding matrix or vector after preprocessing.
  • the preprocessing includes preprocessing of compressing channel information of frequency domain resources in the same group.
  • the radio frequency unit 701 is further configured to send target capability information to the network side device, where the target capability information indicates whether the terminal supports frequency domain resource grouping capability.
  • the target capability information indicates at least one of the following:
  • the frequency domain interval between frequency domain resources in the same group supported by the terminal is the same group supported by the terminal.
  • the radio frequency unit 701 is further used to receive fifth information from the network side device, where the fifth information indicates and/or configures the first AI network model corresponding to each of the M groups of second channel information, or the fifth information indicates the first AI network model corresponding to the second channel information of at least some groups in the M groups of second channel information;
  • the processor 710 is further configured to determine the first information according to the fifth information.
  • the radio frequency unit 701 is also used to send third indication information to the network side device, where the third indication information indicates the first AI network model corresponding to each of the M groups of second channel information.
  • the first AI network model corresponding to each of the M groups of second channel information satisfies at least one of the following:
  • the frequency domain resource groups including the same number of frequency domain resources correspond to the same first AI network model
  • the M groups of second channel information correspond to the same first AI network model
  • a dimension of a set of second channel information matches a dimension of input information of a corresponding first AI network model
  • the network side device indicates the first AI network side model corresponding to each of the M groups of second channel information.
  • the terminal 700 provided in the embodiment of the present application can implement each process performed by the information transmission device 400 shown in Figure 4, and can achieve the same beneficial effects. To avoid repetition, it will not be described here.
  • An embodiment of the present application also provides a network side device, including a processor and a communication interface, the communication interface being used to receive second information from a terminal, wherein the second information includes M channel characteristic information, and the M channel characteristic information is channel characteristic information obtained by performing a first processing on the M groups of second channel information based on the first AI network model corresponding to each of the M groups of second channel information, and M is an integer greater than or equal to 1;
  • the processor is used to determine, according to the first information, a second AI network side model corresponding to each of the M channel characteristic information, wherein the first information includes grouping information of K groups of frequency domain resources, the K groups of second channel information correspond one-to-one to the K groups of frequency domain resources, each group of frequency domain resources in the K groups of frequency domain resources includes at least one frequency domain resource, and K is an integer greater than or equal to M;
  • the processor is also used to perform a second processing on the M channel characteristic information based on the second AI network side model corresponding to each of the M channel characteristic information to obtain the
  • the network side device 800 includes: an antenna 801, a radio frequency device 802, a baseband device 803, a processor 804 and a memory 805.
  • the antenna 801 is connected to the radio frequency device 802.
  • the radio frequency device 802 receives information through the antenna 801 and sends the received information to the baseband device 803 for processing.
  • the baseband device 803 processes the information to be sent and sends it to the radio frequency device 802.
  • the radio frequency device 802 processes the received information and sends it out through the antenna 801.
  • the method executed by the network-side device in the above embodiment may be implemented in the baseband device 803, which includes a baseband processor.
  • the baseband device 803 may include, for example, at least one baseband board, on which multiple chips are arranged, as shown in Figure 8, one of which is, for example, a baseband processor, which is connected to the memory 805 through a bus interface to call the program in the memory 805 and execute the network device operations shown in the above method embodiment.
  • the network side device may also include a network interface 806, which is, for example, a Common Public Radio Interface (CPRI).
  • CPRI Common Public Radio Interface
  • the network side device 800 of the embodiment of the present application also includes: instructions or programs stored in the memory 805 and executable on the processor 804.
  • the processor 804 calls the instructions or programs in the memory 805 to execute the methods executed by the modules shown in Figure 5 and achieve the same technical effect. To avoid repetition, it will not be repeated here.
  • An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored.
  • a program or instruction is stored.
  • the program or instruction is executed by a processor, each process of the method embodiment shown in Figure 2 or Figure 3 is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.
  • the processor is the processor in the terminal described in the above embodiment.
  • the readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.
  • the present application embodiment further provides a chip, the chip comprising a processor and a communication interface, the communication interface and The processors are coupled, and the processors are used to run programs or instructions to implement the various processes of the method embodiments shown in Figures 2 or 3, and can achieve the same technical effects. To avoid repetition, they are not described here.
  • the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.
  • the embodiments of the present application further provide a computer program/program product, which is stored in a storage medium, and is executed by at least one processor to implement the various processes of the method embodiment shown in Figure 2 or Figure 3, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.
  • An embodiment of the present application also provides a communication system, including: a terminal and a network side device, wherein the terminal can be used to execute the steps of the information transmission method shown in Figure 2, and the network side device can be used to execute the steps of the information processing method shown in Figure 3.
  • the technical solution of the present application can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM/RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present application.
  • a storage medium such as ROM/RAM, a magnetic disk, or an optical disk
  • a terminal which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.

Landscapes

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

Abstract

本申请公开了一种信息传输方法、信息处理方法、装置和通信设备,属于通信技术领域,本申请实施例的信息传输方法包括:终端基于第一信息,从第一信道信息中确定K组第二信道信息,其中,所述第一信息包括K组频域资源的分组信息,所述K组第二信道信息与所述K组频域资源一一对应,所述K组频域资源中的每一组频域资源包括至少一个频域资源,K为大于或等于1的整数;所述终端基于M组第二信道信息各自对应的第一AI网络模型对所述M组第二信道信息进行第一处理,得到M个信道特征信息,所述K组第二信道信息包括所述M组第二信道信息,M为小于或等于K的正整数;所述终端向网络侧设备发送第二信息,所述第二信息包括所述M个信道特征信息。

Description

信息传输方法、信息处理方法、装置和通信设备
相关申请的交叉引用
本申请主张在2022年10月27日在中国提交的中国专利申请No.202211328601.6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,具体涉及一种信息传输方法、信息处理方法、装置和通信设备。
背景技术
在相关技术中,对借助AI网络模型来传输信道特征信息的方法进行了研究。
该AI网络模型可以包括编码部分(即编码AI网络模型)和解码部分(即解码AI网络模型),编码AI网络模型用于将信道信息编码成信道特征信息,解码AI网络模型用于将编码AI网络模型输出的信道特征信息恢复成信道信息。
相关技术中,同一个AI网络模型的输入维度是固定的,对于不同子带数的信道信息,需要使用不同的AI网络模型,例如:因为基于13个子带的预编码矩阵训练的AI网络模型无法在13个子带的信道下使用,从而需要训练以及传递与各个子带数匹配的AI网络模型,这样会增加训练与各个子带数匹配的AI网络模型的计算量,且增加传输与各个子带数匹配的AI网络模型的开销。
发明内容
本申请实施例提供一种信息传输方法、信息处理方法、装置和通信设备,使得基于低子带数的信道信息训练的AI网络模型可以处理高子带数的信道信息,从而提高了AI网络模型的复用效率和灵活度。
第一方面,提供了一种信息传输方法,该方法包括:
终端基于第一信息,从第一信道信息中确定K组第二信道信息,其中,所述第一信息包括K组频域资源的分组信息,所述K组第二信道信息与所述K组频域资源一一对应,所述K组频域资源中的每一组频域资源包括至少一个频域资源,K为大于或等于1的整数;
所述终端基于M组第二信道信息各自对应的第一AI网络模型对所述M组第二信道信息进行第一处理,得到M个信道特征信息,所述K组第二信道信息包括所述M组第二信道信息,M为小于或等于K的正整数;
所述终端向网络侧设备发送第二信息,所述第二信息包括所述M个信道特征信息。
第二方面,提供了一种信息传输装置,应用于终端,该装置包括:
第一确定模块,用于基于第一信息,从第一信道信息中确定K组第二信道信息,其中, 所述第一信息包括K组频域资源的分组信息,所述K组第二信道信息与所述K组频域资源一一对应,所述K组频域资源中的每一组频域资源包括至少一个频域资源,K为大于或等于1的整数;
第一处理模块,用于基于M组第二信道信息各自对应的第一AI网络模型对所述M组第二信道信息进行第一处理,得到M个信道特征信息,所述K组第二信道信息包括所述M组第二信道信息,M为小于或等于K的正整数;
第一发送模块,用于向网络侧设备发送第二信息,所述第二信息包括所述M个信道特征信息。
第三方面,提供了一种信息处理方法,包括:
网络侧设备接收来自终端的第二信息,其中,所述第二信息包括M个信道特征信息,所述M个信道特征信息是基于M组第二信道信息各自对应的第一AI网络模型对所述M组第二信道信息进行第一处理得到的信道特征信息,M为大于或等于1的整数;
所述网络侧设备根据第一信息,确定所述M个信道特征信息各自对应的第二AI网络侧模型,其中,所述第一信息包括K组频域资源的分组信息,所述K组第二信道信息与所述K组频域资源一一对应,所述K组频域资源中的每一组频域资源包括至少一个频域资源,K为大于或等于M的整数;
所述网络侧设备基于所述M个信道特征信息各自对应的第二AI网络侧模型对所述M个信道特征信息进行第二处理,得到所述M组第二信道信息。
第四方面,提供了一种信息处理装置,应用于网络侧设备,该装置包括:
第一接收模块,用于接收来自终端的第二信息,其中,所述第二信息包括M个信道特征信息,所述M个信道特征信息是基于M组第二信道信息各自对应的第一AI网络模型对所述M组第二信道信息进行第一处理得到的信道特征信息,M为大于或等于1的整数;
第二确定模块,用于根据第一信息,确定所述M个信道特征信息各自对应的第二AI网络侧模型,其中,所述第一信息包括K组频域资源的分组信息,所述K组第二信道信息与所述K组频域资源一一对应,所述K组频域资源中的每一组频域资源包括至少一个频域资源,K为大于或等于M的整数;
第二处理模块,用于基于所述M个信道特征信息各自对应的第二AI网络侧模型对所述M个信道特征信息进行第二处理,得到所述M组第二信道信息。
第五方面,提供了一种通信设备,该通信设备包括处理器和存储器,所述存储器存储可在所述处理器上运行的程序或指令,所述程序或指令被所述处理器执行时实现如第一方面所述的信息传输方法或第三方面所述的信息处理方法的步骤。
第六方面,提供了一种终端,包括处理器及通信接口,其中,所述处理器用于基于第一信息,从第一信道信息中确定K组第二信道信息,其中,所述第一信息包括K组频域资源的分组信息,所述K组第二信道信息与所述K组频域资源一一对应,所述K组频域 资源中的每一组频域资源包括至少一个频域资源,K为大于或等于1的整数;所述处理器还用于基于M组第二信道信息各自对应的第一AI网络模型对所述M组第二信道信息进行第一处理,得到M个信道特征信息,所述K组第二信道信息包括所述M组第二信道信息,M为小于或等于K的正整数;所述通信接口用于向网络侧设备发送第二信息,所述第二信息包括所述M个信道特征信息。
第七方面,提供了一种网络侧设备,包括处理器及通信接口,其中,所述通信接口用于接收来自终端的第二信息,其中,所述第二信息包括M个信道特征信息,所述M个信道特征信息是基于M组第二信道信息各自对应的第一AI网络模型对所述M组第二信道信息进行第一处理得到的信道特征信息,M为大于或等于1的整数;所述处理器用于根据第一信息,确定所述M个信道特征信息各自对应的第二AI网络侧模型,其中,所述第一信息包括K组频域资源的分组信息,所述K组第二信道信息与所述K组频域资源一一对应,所述K组频域资源中的每一组频域资源包括至少一个频域资源,K为大于或等于M的整数;所述处理器还用于基于所述M个信道特征信息各自对应的第二AI网络侧模型对所述M个信道特征信息进行第二处理,得到所述M组第二信道信息。
第八方面,提供了一种通信系统,包括:终端和网络侧设备,所述终端可用于执行如第一方面所述的信息传输方法的步骤,所述网络侧设备可用于执行如第三方面所述的信息处理方法的步骤。
第九方面,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息传输方法的步骤,或者实现如第三方面所述的信息处理方法的步骤。
第十方面,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息传输方法,或实现如第三方面所述的信息处理方法。
第十一方面,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息传输方法的步骤,或者所述计算机程序/程序产品被至少一个处理器执行以实现如第三方面所述的信息处理方法的步骤。
在本申请实施例中,对频域资源进行分组,每一组频域资源的信道信息采用对应的一个AI网络模型进行处理,其中,一个信道的第一信道信息能够划分为K组,且每一个AI网络模型仅输入对应的一组频域资源的信道信息,而无需输入整个信道的信道信息,这样,低频域资源数的AI网络模型能够用于处理高频域资源数的信道信息,从而提高了AI网络模型的复用效率和灵活度。
附图说明
图1是本申请实施例能够应用的一种无线通信系统的结构示意图;
图2是本申请实施例提供的一种信息传输方法的流程图;
图3是本申请实施例提供的一种信息处理方法的流程图;
图4是本申请实施例提供的一种信息传输装置的结构示意图;
图5是本申请实施例提供的一种信息处理装置的结构示意图;
图6是本申请实施例提供的一种通信设备的结构示意图;
图7是本申请实施例提供的一种终端的硬件结构示意图
图8是本申请实施例提供的一种网络侧设备的结构示意图。
具体实施方式
下面将结合本申请实施例中的附图,对本申请实施例中的技术方案进行清楚描述,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、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。
由信息论可知,准确的信道状态信息(channel state information,CSI)对信道容量的至关重要。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,基站在在某个时隙(slot)的某些时频资源上发送CSI参考信号(CSI 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改成按照时延(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发送个终端,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,为了更好的压缩信道信息,可以使用神经网络或机器学习的方法。
人工智能目前在各个领域获得了广泛的应用。AI模块有多种实现方式,例如神经网络、决策树、支持向量机、贝叶斯分类器等。本申请以神经网络为例进行说明,但是并不限定AI模块的具体类型。
神经网络的参数通过优化算法进行优化。优化算法就是一种能够帮我们最小化或者最大化目标函数(有时候也叫损失函数)的一类算法。而目标函数往往是模型参数和数据的数学组合。例如给定数据X和其对应的标签Y,我们构建一个神经网络模型f(.),有了模型后,根据输入x就可以得到预测输出f(x),并且可以计算出预测值和真实值之间的差距(f(x)-Y),这个就是损失函数。我们的目的是找到合适的权值和偏置,使上述的损失函数的值达到最小,损失值越小,则说明我们的模型越接近于真实情况。
目前常见的优化算法,基本都是基于误差(error)反向传播(Back Propagation,BP)算法。BP算法的基本思想是,学习过程由信号的正向传播与误差的反向传播两个过程组成。正向传播时,输入样本从输入层传入,经各隐层逐层处理后,传向输出层。若输出层的实际输出与期望的输出不符,则转入误差的反向传播阶段。误差反传是将输出误差以某种形式通过隐层向输入层逐层反传,并将误差分摊给各层的所有单元,从而获得各层单元的误差信号,此误差信号即作为修正各单元权值的依据。这种信号正向传播与误差反向传播的各层权值调整过程,是周而复始地进行的。权值不断调整的过程,也就是网络的学习训练过程。此过程一直进行到网络输出的误差减少到可接受的程度,或进行到预先设定的学习次数为止。
常见的优化算法有梯度下降(Gradient Descent)、随机梯度下降(Stochastic Gradient Descent,SGD)、小批量梯度下降(mini-batch gradient descent)、动量法(Momentum)、带动量的随机梯度下降(Nesterov)、自适应梯度下降(Adaptive gradient descent,Adagrad)、自适应学习率调整(Adadelta)、均方根误差降速(root mean square prop,RMSprop)、自适应动量估计(Adaptive Moment Estimation,Adam)等。
这些优化算法在误差反向传播时,都是根据损失函数得到的误差/损失,对当前神经元求导数/偏导,加上学习速率、之前的梯度/导数/偏导等影响,得到梯度,将梯度传给上一层。
CSI压缩恢复流程为: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编码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,输入到解码AI网络模型中,恢复信道信息。
具体的,基于神经网络的CSI压缩反馈方案是,在终端对信道信息进行压缩编码,将压缩后的内容发送给基站,在基站对压缩后的内容进行解码,从而恢复信道信息,此时基站的解码AI网络模型和终端的编码AI网络模型需要联合训练,达到合理的匹配度。编码AI网络模型的输入是信道信息,输出是编码信息,即信道特征信息,解码AI网络模型的输入是编码信息,输出是恢复的信道信息。
输入编码AI网络模型的信道信息通常是全部子带的信道矩阵或预编码矩阵,以预编码矩阵为例,预编码矩阵的列数为秩(rank)数,即层(layer)总数,预编码矩阵的行数为CSI-RS端口数,这样,编码AI网络模型的输入维度是由rank数,CSI-RS端口数,以及子带数共同决定的。在相关技术中,每一个信道的信道信息采用一个编码AI网络模型 进行处理,这样,对于不同子带数的CSI-RS,需要使用与之相对应的输入维度的AI网络模型来处理。例如:某一AI网络模型输入维度是26个子带的CSI-RS的信道信息,另一AI网络模型输入维度是13个子带的CSI-RS的信道信息,由于26个子带的CSI-RS的信道信息的输入维度是13个子带的CSI-RS的信道信息的两倍,因此,无法直接使用26个子带的AI网络模型来处理13个子带的CSI-RS的信道信息,也不能直接使用13个子带的AI网络模型来处理26个子带的CSI-RS的信道信息。
在相关技术中,需要训练和配置与全部子带数一一对应的AI网络模型,这样,会增大训练AI网络模型的复杂度,以及增大传递AI网络模型的开销。
而本申请实施例中,对频域资源进行分组,位于一个组内的至少一个频域资源对应的信道信息采用一个AI网络模型进行处理,使得与低频域资源数对应的AI网络模型能够处理与高频域资源数对应的信道信息,且降低了AI网络模型的数量,以及降低了AI网络模型的大小。
例如:一个CSI-RS有26个子带,将其划分为13组,每一组2个子带,则可以复用一个AI网络模型,分别处理13组子带的信道信息,且该AI网络模型的输入维度降低为2个子带的信道信息。
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息传输方法、信息处理方法、信息传输装置、信息处理装置及通信设备等进行详细地说明。
请参阅图2,本申请实施例提供的一种信息传输方法,其执行主体是终端,如图2所示,该终端执行的信息传输方法可以包括以下步骤:
步骤201、终端基于第一信息,从第一信道信息中确定K组第二信道信息,其中,所述第一信息包括K组频域资源的分组信息,所述K组第二信道信息与所述K组频域资源一一对应,所述K组频域资源中的每一组频域资源包括至少一个频域资源,K为大于或等于1的整数。
其中,频域资源的划分可以是基于子带、物理资源块(Physical Resource Block,PRB)等频域资源单位来划分频域资源,为了便于说明,本申请实施例中以频域资源是子带为例进行举例说明,在此不构成具体限定。
上述第一信道信息可以是某一信道的完整的信道信息,其具体可以是原始的信道矩阵或向量、预编码矩阵或向量、预处理后的信道矩阵或向量、预处理后的预编码矩阵或向量中的至少一项,为了便于说明,本申请实施例中通常以信道信息为预编码矩阵为例进行举例说明,在此不构成具体限定。
上述第一信息用于将CSI-RS的频域资源划分为K组,这样,K组第二信息表示终端分别对各自对应的一组频域资源上传输的CSI-RS进行测量所得到的信道信息。
作为一种可选的实施方式,上述第二信道信息可以包括以下至少一项:
原始的信道矩阵或向量;
预编码矩阵或向量;
预处理后的信道矩阵或向量;
预处理后的预编码矩阵或向量。
一种实施方式中,上述预处理可以包括对同一组内的频域资源的信道信息进行压缩的预处理,例如:对同一组内的子带的信道信息进行与子带压缩有关的预处理。例如:基于一组频域资源内的两个子带的信道质量接近,可以对这两个子带的信道信息进行压缩处理,以减少预处理后的信道信息的长度,从而降低对该预处理后的信道信息进行第一处理的复杂度,以及降低传输第一处理后的信道特征信息的资源损耗。
一种实施方式中,在第二信道信息是一个layer的信道信息的情况下,该layer的信道信息对应的信道矩阵只有一列,此时,该第二信道信息可以称之为向量。当然,在第二信道信息包括至少两个layer的信道信息的情况下,也可以通过预处理将该至少两个layer的信道信息处理成向量,在此不作具体阐述。
作为一种可选的实施方式,所述K组频域资源的分组信息包括以下至少一项:
K的取值;
每一组频域资源内的频域资源的数目;
每一组频域资源内的频域资源的标识;
每一组频域资源内的频域资源的频域间隔;
每一组频域资源内的频域资源的频域跨度;
每一组频域资源内的起始频域资源位置;
每一组频域资源内的终止频域资源位置;
每一组频域资源的密度;
每一组频域资源的偏移值。
选项一,在K组频域资源的分组信息包括K的取值的情况下,可以将CSI-RS的频域资源均匀的划分为K组,例如:一组3个子带;或者将CSI-RS的频域资源划分为K个不均匀的分组,例如:一组3个子带,一组4个子带。
选项二,在K组频域资源的分组信息包括每一组频域资源内的频域资源的数目的情况下,可以按照每一组频域资源内的频域资源的数目,将CSI-RS的频域资源划分为K组。
需要说明的是,在K组频域资源的分组信息包括每一组频域资源内的频域资源的数目的情况下,每一组频域资源内的频域资源的数目是确定的,但是,一组频域资源内的频域资源具体是哪一些是可以调整的。例如:终端可以按照CSI-RS的频域资源的排列顺序,依次将CSI-RS的频域资源划分至各个分组内,如:若CSI-RS的频域资源包括13个子带,第一信息指示第一组频域资源包括3个子带、第二组频域资源包括4个子带、第三组频域资源包括6个子带,则终端可以将CSI-RS的第1至第3个子带划分为一组,将第4个至第7个子带划分为一组,以及将第8至第13个子带划分为一组。或者,终端可以随机的将CSI-RS的频域资源划分至各个分组内等,其具体的划分规则可以由协议约定,或者由网络侧设备指示,或者由终端自主决定。
选项三,在K组频域资源的分组信息包括每一组频域资源内的频域资源的标识的情况下,可以按照频域资源的标识来划分CSI-RS的频域资源。例如:第一信息直接指示子带1、子带4、子带5、子带6划分为一组,将子带2、子带3划分为一组,将子带7至13划分为一组。
选项四,在K组频域资源的分组信息包括每一组频域资源内的频域资源的频域间隔的情况下,所述K组频域资源可以对应相同或者不同的频域间隔,此时,每一组频域资源内的相邻频域资源之间可以是频域不连续的。例如:假设共有8个子带,其中,中间部分的子带有深衰,则可以将子带1、子带2、子带7和子带8划分为一组频域资源,将子带3至6划分为一组频域资源,此时两组频域资源内的子带的频域间隔不同,可以使信道质量接近的子带位于同一组频域资源内。
选项五,在K组频域资源的分组信息包括每一组频域资源内的频域资源的频域跨度的情况下,每一组内的频域资源的起始频域资源位置至终止频域资源位置的跨度是一定的。此时,可以将一个频域跨度内的全部或部分频域资源划分为一组。例如:假设每一组频域资源内的频域资源的频域跨度为3个子带,则第一组频域资源可以包括第1至第3个子带,第二组频域资源可以包括第4至第6个子带。当然,在实施中,不同组的频域资源的频域跨度可以不同。
选项六,在K组频域资源的分组信息包括每一组频域资源内的起始频域资源位置的情况下,每一组频域资源内的频域资源的起始频域资源位置是一定的,且每一组频域资源内的频域资源的频域位置包括该起始频域资源位置和位于该起始频域资源位置之后的频域资源,例如:假设某一组频域资源的起始频域资源位置为第4个子带,且该组频域资源的频域跨度为3个子带,则可以确定该组频域资源包括第4至第6个子带。
选项七,在K组频域资源的分组信息包括每一组频域资源内的终止频域资源位置的情况下,每一组频域资源内的频域资源的终止频域资源位置是一定的,且每一组频域资源内的频域资源的频域位置包括该终止频域资源位置和位于该终止频域资源位置之前的频域资源,例如:假设某一组频域资源的终止频域资源位置为第4个子带,且该组频域资源的频域跨度为3个子带,则可以确定该组频域资源包括第2至第4个子带。
选项八,在K组频域资源的分组信息包括每一组频域资源的密度的情况下,可以使每一组频域资源内的频域资源满足梳状分布。例如:假设每一组频域资源内的频域资源的密度为2,可以将CSI-RS的全部子带中排列于奇数位的子带划分为一组,将排列于偶数位的子带划分为一组。
需要说明的是,上述一组频域资源内的频域资源的密度可以有以下两种理解方式:
1)指示每个频域资源占一组频域资源的比例数,例如:若子带密度为0.5表示每个子带占一组子带的0.5,此时,每两个子带对应一组子带,即连续的两个子带中一个属于第一组子带,另一个属于第二组子带;
2)指示一组频域资源内每几个频域资源不重复,例如:上述例子中用密度2表示每 两个连续的子带不会出现在同一组子带内,即每两个子带中一个子带是第一组子带,另一个子带是第二组子带。
选项九,在K组频域资源的分组信息包括每一组频域资源的偏移值的情况下,可以基于频域资源的频域位置相对基准频域位置的偏移量来确定每一组频域资源内的频域资源。例如:假设将一组频域资源内的频域资源的起始频域位置作为基准频域位置,通过第一信息指示该组频域资源内的其他频域资源相较该基准频域位置的偏移值可以确定该组频域资源内的其他频域资源,或者,上述基准频域位置还可以默认是0等任意频域位置,在此不作具体限定。
值得提出的是,所述K组频域资源的分组信息可以包括上述选项一至选项九中的至少两项,例如:所述K组频域资源的分组信息包括所述K组频域资源中每一组频域资源内的起始频域位置和终止频域资源位置,此时,可以从位于起始频域位置和和终止频域资源位置之间的频域资源内选择部分作为对应的一组频域资源,或者可以将位于同一组频域资源的起始频域位置和终止频域资源位置之间的频域资源作为该组频域资源。例如:若指示一组频域资源的起始频域位置为第3个子带,终止频域资源位置为第8个子带,则可以确定该组频域资源包括第3至第8个子带。
步骤202、所述终端基于M组第二信道信息各自对应的第一AI网络模型对所述M组第二信道信息进行第一处理,得到M个信道特征信息,所述K组第二信道信息包括所述M组第二信道信息,M为小于或等于K的正整数。
一种实施方式中,上述第一AI网络模型可以是编码AI网络模型和/或压缩AI网络模型,即在终端侧对信道信息进行处理得到CSI相关信息的AI网络模型,在此对第一AI网络模型的名称不作具体限定。为了便于说明,本申请实施例中,以第一AI网络模型是编码AI网络模型为例进行举例说明,该编码AI网络模型与网络侧设备的解码AI网络模型和/或解压缩AI网络模型(即本申请实施例中的第二AI网络模型)匹配,和/或,该第一AI网络模型与网络侧设备的第二AI网络模型联合训练。与之相对应的,第二AI网络模型可以是基站侧用于处理信道特征信息的AI网络模型,在此对第二AI网络模型的名称不作具体限定。为了便于说明,本申请实施例中,以第二AI网络模型是解码AI网络模型为例进行举例说明。
一种实施方式中,上述第一处理可以包括压缩处理、编码处理、量化处理中的至少一项,为了便于说明,本申请实施例中,以第一处理是编码处理为例进行举例说明。
一种实施方式中,上述M组第二信道信息可以对应同一个第一AI网络模型,此时,采用公共的第一AI网络模型分别对M组第二信道信息进行第一处理,得到第一AI网络模型分M次输出的信道特征信息。
一种实施方式中,上述M组第二信道信息可以对应不同的第一AI网络模型,此时,M个第一AI网络模型分别对各自对应的一组第二信道信息进行第一处理,得到M个第一AI网络模型分别输出的信道特征信息。
一种实施方式中,上述M组第二信道信息中的一部分可以对应相同的第一AI网络模型,另一部分可以对应不同的第一AI网络模型,例如:将M组第二信道信息划分为两个部分,第一部分内的V组第二信道信息使用相同的第一AI网络模型,第二部分内的(M-V)组第二信道信息使用相同的第一AI网络模型,且V组第二信道信息使用的第一AI网络模型与(M-X)组第二信道信息使用的第一AI网络模型不是同一个第一AI网络模型。
步骤203、所述终端向网络侧设备发送第二信息,所述第二信息包括所述M个信道特征信息。
一种实施方式中,终端可以采用CSI上报的方式向网络侧设备发送第二信息,或者,终端采用信令的方式向网络侧设备发送第二信息,在此不作具体限定。
作为一种可选的实施方式,在所述K组频域资源中的每一组频域资源分别包括L个频域资源,且H不能整除L的情况下,所述第一信息包括对X个频域资源的信道信息的处理规则,其中,H为所述第一信道信息对应的信道的频域资源数目,X等于H除以L的余数,L、X和H分别为大于或等于1的整数。
一种实施方式中,在H不能整除L的情况下,可以把除余的部分,即X个频域资源的信道信息按照以下处理规则中的至少一项进行处理:
1)基于Y个频域资源和所述X个频域资源组成第一组频域资源,其中,所述K组频域资源包括所述第一组频域资源,所述第一信道信息对应的信道的频域资源包括所述Y个频域资源。
一种实施方式中,Y等于L,此时,可以把X个频域资源合并至任一组频域资源中。例如:假设H等于13,L等于6,则可以把13个子带分为2组,将除余的一个子带合并子第一组频域资源或第二组频域资源。例如:前6个子带一组,后7个子带一组;或者,排列于奇数位或子带编号为奇数的子带为一组,排列于偶数位或子带编号为偶数的子带为另一组。可选地,两组子带可以使用相同或者不同的AI网络模型,其中,若两组子带的子带个数不同,此时,可以通过补零的方式,将子带数少的一组的信道信息补齐至该AI网络模型的输入维度。
一种实施方式中,Y等于(L-X),此时,可以使X个频域资源与重复的(L-X)个频域资源构成一组频域资源,且该组频域资源具有L个频域资源。其中,重复的(L-X)个频域资源可以是组内或其他组的一个频域资源重复(L-X)次,或者是组内或其他组的(L-X)个频域资源在第一组频域资源中重复出现。例如:假设H等于13,L等于6,可以把13个子带分为3组,第一组为子带1至子带6,第二组为子带7至子带12,第三组为子带13和重复的5个子带。其中,第三组中的子带可以是[1,2,3,4,5,13],或者是子带[12,12,12,12,12,13],或者是子带[13,13,13,13,13,13],或者是子带[8,9,10,11,12,13],在此并不穷举。
一种实施方式中,Y等于0,此时,直接将X个频域资源作为一组频域资源。
2)舍弃上报所述X个频域资源的信道信息。例如:即不对该X个频域资源的信道信 息进行第一处理,也不上报该X个频域资源的信道信息对应的信道特征信息;
3)将所述X个频域资源的信道信息的维度补充至目标维度,所述目标维度为L个频域资源的信道信息的维度。其中,将X个频域资源的信道信息的维度补充至目标维度的方式,可以是补零或者是补充按照预设规则确定的外插值,其中,在补充按照预设规则确定的外插值的情况下,该预设规则可以与第一AI网络模型和第二AI网路模型一起训练。网络侧设备在获取到M个信道特征信息后,基于该M个信道特征信息各自对应的第二AI网络模型恢复M组第二信道信息,并基于上述预设规则将补充的外插值丢弃。
作为一种可选的实施方式,所述第一信息满足以下至少一项:
由所述网络侧设备指示;
由所述终端选择并上报;
由协议约定;
与所述第一AI网络模型关联。
一种实施方式中,网络侧设备可以通过信令指示频域资源的分组信息,例如:包括分组数量K,或每组频域资源内的频域资源数目,或每组频域资源内具体包括哪个或哪些频域资源。
一种实施方式中,网络侧设备可以在CSI报告配置(report config)中配置频域资源的分组信息。
一种实施方式中,终端可以根据自身具有的第一AI网络模型的输入维度来确定频域资源的分组方式,以使分组后的每一组第二信道信息,与终端具有的第一AI网络模型的输入维度匹配。
在实施中,若终端选择或确定第一信息,则终端可以向网络侧设备上报所述第一信息。
作为一种可选的实施方式,位于同一组内的频域资源满足以下至少一项:
频域跨度相同或频域跨度不相同;
频域间隔相同或频域间隔不相同;
频域位置部分重叠或频域位置不重叠;
对应的信道质量之差小于预设阈值。
一种实施方式中,同一组内的频域资源的频域跨度,可以是一组频域资源内的单个频域资源的频域范围,例如:一组频域资源包括频域资源A和频域资源B,其中,频域资源A的频率范围是2800~3000Hz,即频域资源A的频域跨度是200Hz,频域资源B的频率范围是3100~3200Hz,即频域资源B的频域跨度是100Hz。
一种实施方式中,同一组内的频域资源的频域间隔,可以是一组频域资源内的两个相邻的频域资源之间的间隔频率,例如:一组频域资源包括子带1、子带2和子带4,其中,子带1和子带2之间的频域间隔是1个子带,子带2和子带4之间的频域间隔是2个子带。
一种实施方式中,同一组内的频域资源的频域位置部分重叠可以是,一组频域资源内的至少两个频域资源的频域位置部分重叠,例如:一组频域资源包括频域资源A和频域资 源B,其中,频域资源A的频率范围是2800~3150Hz,频域资源B的频率范围是3100~3200Hz,此时,频域资源A和频域资源B的频率范围部分重叠。与之相对应的,同一组内的频域资源的频域位置不重叠,可以是一组频域资源内的至少两个频域资源的频域位置完全不重叠,在此不再赘述。
一种实施方式中,同一组内的频域资源对应的信道质量之差小于预设阈值,可以是将信道质量接近的频域资源划分为一组。例如:假设共有8个子带,其中,中间部分的子带有深衰,则可以将子带1、子带2、子带7和子带8划分为一组频域资源,将子带3至6划分为一组频域资源,此时,可以使信道质量接近的子带位于同一组频域资源内。
作为一种可选的实施方式,在所述终端基于第一信息,从第一信道信息中确定K组第二信道信息之前,所述方法还包括:
所述终端接收来自所述网络侧设备的第一指示信息,其中,所述第一指示信息指示所述第一信息或所述第一信息的标识或所述第一AI网络模型的标识,所述第一AI网络模型与所述第一信息关联;
所述终端根据所述第一指示信息确定所述第一信息。
一种实施方式中,所述终端获知了所述第一信息和所述第一信息的标识之间的第一关联关系,具体可以是在协议中约定或网络侧设备提前配置了各种第一信息与其标识之间的关联关系,这样,在网络侧设备指示第一信息的标识的情况下,终端可以根据该标识和第一信息的关联关系来确定第一信息。
一种实施方式中,所述第一AI网络模型与所述第一信息关联,可以是第一信息与第一AI网络模型是一起训练和/或一起传递的,例如:在训练第一AI网络模型的过程中,确定该第一AI网络模型能够输入的信道信息的频域间隔,以及频域资源数目。这样,终端在获取第一AI网络模型时,也获取了该第一AI网络模型关联的第一信息,这样,网络侧设备可以指示终端使用哪一个第一AI网络模型,终端据此确定使用的第一AI网络模型所关联的第一信息。
一种实施方式中,还可以在协议中约定或网络侧设备提前配置了至少两个第一AI网络模型各自关联的第一信息,这样,在网络侧设备指示一个第一AI网络模型的标识的情况下,终端可以根据该标识和第一信息的关联关系来确定第一信息。
一种实施方式中,上述第一指示信息可以包含在CSI报告配置(CSI report config)中。
本实施方式中,第一信息可以由网络侧设备指示或配置。
作为一种可选的实施方式,所述信息传输方法还包括:
所述终端向所述网络侧设备发送第二指示信息,其中,所述第二指示信息指示所述第一信息或所述第一信息的标识或所述第一AI网络模型的标识,所述第一AI网络模型与所述第一信息关联。
一种实施方式中,网络侧设备可以指示第一信息的部分和/或协议可以约定第一信息的部分,所述终端根据网络侧设备的指示和/或协议的约定来确定完整的第一信息,例如: 假设网络侧设备指示K等于4,协议约定H与L除余的X个频域资源与(L-X)个频域资源构成第一组频域资源,终端获取目标下行信道的秩(rank)等于13,则终端决定将13个子带划分为4组,此时,终端可以根据网络侧的指示和协议的约定来确定每一组频域资源内包含的子带数,和/或确定每一组频域资源内具体包含哪一个或哪一些子带。如,第一组频域资源为子带1至4,第二组为子带5至8,第三组为子带9至12,第四组为子带10至13;或者,第一组为子带1至4,第二组频域资源为子带4至7,第三组频域资源为子带7至10,第四组频域资源为子带10至13;或者,第一组频域资源为子带1至4,第二组频域资源为子带5至8,第三组频域资源为子带9至12,第四组频域资源为子带[12,12,12,13]。
一种实施方式中,终端可以根据自身具有的第一AI网络模型的输入维度来确定每一组频域资源内包含的频域资源数目,例如:使按照第一信息划分的每一组第二信道信息的维度与该第一AI网络侧模型的输入维度匹配。
一种实施方式中,所述信息传输方法还包括:
所述终端根据第三信息确定所述K组频域资源中每一组频域资源内的频域资源,所述K组频域资源的分组信息包括所述K组频域资源与各自包含的频域资源之间的对应关系;
其中,所述第三信息包括协议约定的所述每一组频域资源内的频域资源的频域间隔,以及所述网络侧设备指示的所述每一组频域资源内的频域资源的数目或所述K的取值。
例如:假设协议约定每一组频域资源内的频域资源的频域间隔为2,网络侧设备指示的每一组频域资源内的频域资源的数目均为4,或者指示K等于4,若目标下行信道的实际子带数为16,则终端可以确定将16个子带划分为4组,如:第一组为子带[1,3,5,7],第二组为子带[2,4,6,8],第三组为子带[9,11,13,15],第四组为子带[10,12,14,16]。
一种实施方式中,所述信息传输方法还包括:
所述终端根据第四信息确定所述K组频域资源中每一组频域资源内的频域资源,所述K组频域资源的分组信息包括所述K组频域资源与各自包含的频域资源之间的对应关系;
其中,所述第四信息包括协议约定的所述处理规则,以及与所述第一AI网络模型关联的目标频域间隔和/或目标频域资源数目,所述目标频域间隔为一组频域资源内的频域资源的频域间隔,所述目标频域资源数目为一组频域资源内的频域资源的数目。
例如:假设协议约定对于H和L除余的X个频域资源的处理规则是不上报,且约定至少一个第一AI网络模型所关联的目标频域间隔为1,目标频域资源数目L为4,若目标下行信道的实际子带数H为13,则X等于1,则终端可以确定将13个子带划分为3组,第一组为子带[1,2,3,4],第二组为子带[5,6,7,8],第三组为子带[9,10,11,12],且终端不对子带13进行第一处理,且不上报子带13进行第一处理后的信道特征信息。
再例如:假设协议约定对于H和L除余的X个频域资源的处理规则是将X个频域资源的信道信息补零至L个频域资源的信道信息的长度后,作为一组频域资源,且约定至少一个第一AI网络模型所关联的目标频域间隔为1,目标频域资源数目L为4,若目标下行 信道的实际子带数H为13,则X等于1,则终端可以确定将13个子带划分为4组,第一组为子带[1,2,3,4],第二组为子带[5,6,7,8],第三组为子带[9,10,11,12],第四组为子带[13,0,0,0]。
本实施方式中,终端可以将选择的第一信息上报给网络侧设备,以使网络侧设备在获取到第二信息后,能够根据终端上报的第一信息来确定每一信道特征信息是基于哪些频域资源的信道信息确定的,从而恢复这些频域资源的信道信息,进而得到第一信道信息。
作为一种可选的实施方式,所述信息处理方法还包括:
所述终端向所述网络侧设备发送目标能力信息,所述目标能力信息指示所述终端是否支持频域资源分组的能力。
可选地,所述目标能力信息指示以下至少一项:
所述终端是否支持频域资源分组;
所述终端支持的频域资源分组的最大数目;
所述终端支持的频域资源分组的标识;
所述终端支持的并行处理的频域资源分组的数目;
所述终端支持的同一组内的频域资源之间的频域间隔。
本实施方式中,终端向网络侧设备上报目标能力信息,可以使网络侧设备在配置或指示第一信息的情况下,为终端配置或指示其能够支持的第一信息;和/或,使网络侧设备在配置或指示第一AI网络模型的情况下,为终端配置或指示与其能力相匹配的第一AI网络模型。
作为一种可选的实施方式,所述信息处理方法还包括:
所述终端接收来自所述网络侧设备的第五信息,所述第五信息指示和/或配置所述M组第二信道信息各自对应的第一AI网络模型,或者,所述第五信息指示所述M组第二信道信息中的至少部分组的第二信道信息对应的第一AI网络模型;
所述终端根据所述第五信息确定所述第一信息。
一种实施方式中,所述M组第二信道信息可以对应不同的第一AI网络模型,此时,网络侧设备通过上述第五信息,指示每一组第二信道信息使用的第一AI网络模型,这样,终端可以按照网络侧设备的指示,来确定每一组第二信道信息对应的第一AI网络模型,并据此确定能够将一组第二信道信息处理成符合对应的第一AI网络模型的输入格式的第一信息。
一种实施方式中,至少部分组第二信道信息可以对应相同的第一AI网络模型,此时,网络侧设备通过上述第五信息,指示至少部分组第二信道信息使用的第一AI网络模型,这样,终端可以按照网络侧设备的指示,来确定上述至少部分组第二信道信息所对应的第一AI网络模型,并据此确定能够将至少部分组第二信道信息处理成符合对应的第一AI网络模型的输入格式的第一信息。
本实施方式中,网络侧设备可以指示每一组第二信道信息或至少部分组第二信道信息 所对应的第一AI网络模型。
作为一种可选的实施方式,所述信息处理方法还包括:
所述终端向所述网络侧设备发送第三指示信息,所述第三指示信息指示所述M组第二信道信息各自对应的第一AI网络模型。
本实施方式中,终端可以选择并向网络侧设备上报每一组第二信道信息或至少部分组第二信道信息所对应的第一AI网络模型。
作为一种可选的实施方式,所述M组第二信道信息各自对应的第一AI网络模型满足以下至少一项:
包括相同数目的频域资源的频域资源分组对应同一个第一AI网络模型;
所述M组第二信道信息对应同一个第一AI网络模型;
一组第二信道信息的维度与对应的第一AI网络模型的输入信息维度匹配;
所述网络侧设备指示所述M组第二信道信息各自对应的第一AI网络侧模型。
一种实施方式中,第一AI网络模型与L的取值对应,例如:具有2个子带的一组频域资源和具有3个子带的一组频域资源,两者对应的第一AI网络模型不同。其中,第一AI网络模型的输入维度可以与对应的L个频域资源的信道信息的维度相匹配。
一种实施方式中,所述M组第二信道信息可以对应同一个第一AI网络模型,例如:分别将M组第二信道信息输入至同一个第一AI网络模型,以获取该第一AI网络模型分M次第一处理得到的M个信道特征信息。
一种实施方式中,终端可以按照网络侧设备的指示来确定每一组第二信道信息所对应的第一AI网络侧模型。
在本申请实施例中,对频域资源进行分组,每一组频域资源的信道信息采用对应的一个AI网络模型进行处理,其中,一个信道的第一信道信息能够划分为K组,且每一个AI网络模型仅输入对应的一组频域资源的信道信息,而无需输入整个信道的信道信息,这样,低频域资源数的AI网络模型能够用于处理高频域资源数的信道信息,从而提高了AI网络模型的复用效率和灵活度。
请参阅图3,本申请实施例提供的信息处理方法,其执行主体可以是网络侧设备,如图3所示,该信息处理方法可以包括以下步骤:
步骤301、网络侧设备接收来自终端的第二信息,其中,所述第二信息包括M个信道特征信息,所述M个信道特征信息是基于M组第二信道信息各自对应的第一AI网络模型对所述M组第二信道信息进行第一处理得到的信道特征信息,M为大于或等于1的整数。
其中,上述第二信息与如图2所示方法实施例中的第二信息的含义相同,在此不再赘述。
步骤302、所述网络侧设备根据第一信息,确定所述M个信道特征信息各自对应的第二AI网络侧模型,其中,所述第一信息包括K组频域资源的分组信息,所述K组第二信 道信息与所述K组频域资源一一对应,所述K组频域资源中的每一组频域资源包括至少一个频域资源,K为大于或等于M的整数。
其中,上述第一信息与如图2所示方法实施例中的第一信息的含义相同,所述网络侧设备用于根据第一信息确定所述M个信道特征信息各自对应的第二AI网络侧模型,其中,得到所述信道特征信息的第一AI网络模型,与该信道特征信息对应的第二AI网络侧模型,为相互匹配的AI网络模型或联合训练得到的AI网络模型,如:第一AI网络模型为编码AI网络模型或AI网络模型的编码部分,第二AI网络模型为解码AI网络模型或AI网络模型的解码部分。
步骤303、所述网络侧设备基于所述M个信道特征信息各自对应的第二AI网络侧模型对所述M个信道特征信息进行第二处理,得到所述M组第二信道信息。
其中,第二处理可以包括解码、解压缩、解量化处理中的至少一项。
作为一种可选的实施方式,所述频域资源包括子带或物理资源块PRB。
作为一种可选的实施方式,所述K组频域资源的分组信息包括以下至少一项:
K的取值;
每一组频域资源内的频域资源的数目;
每一组频域资源内的频域资源的标识;
每一组频域资源内的频域资源的频域间隔;
每一组频域资源内的频域资源的频域跨度;
每一组频域资源内的起始频域资源位置;
每一组频域资源内的终止频域资源位置;
每一组频域资源的密度;
每一组频域资源的偏移值。
作为一种可选的实施方式,在所述K组频域资源中的每一组频域资源分别包括L个频域资源,且H不能整除L的情况下,所述第一信息包括对X个频域资源的信道信息的处理规则,其中,H为所述第一信道信息对应的信道的频域资源数目,X等于H除以L的余数,L、X和H分别为大于或等于1的整数。
可选地,所述处理规则包括以下至少一项:
基于(L-X)个频域资源和所述X个频域资源组成第一组频域资源,其中,所述K组频域资源包括所述第一组频域资源,所述第一信道信息对应的信道的频域资源包括所述(L-X)个频域资源;
舍弃上报所述X个频域资源的信道信息;
将所述X个频域资源的信道信息的维度补充至目标维度,所述目标维度为L个频域资源的信道信息的维度。
本实施方式中,网络侧设备能够根据对X个频域资源的信道信息的处理规则来恢复X个频域资源的信道信息,或者,在对X个频域资源的信道信息的处理规则为舍弃上报所述 X个频域资源的信道信息的情况下,网络侧设备未获取X个频域资源的信道信息对应的信道特征信息,此时,网络侧设备可以获取并恢复其他部分的信道信息。
作为一种可选的实施方式,所述第一信息满足以下至少一项:
由所述网络侧设备指示;
由所述终端选择并上报;
由协议约定;
与所述第一AI网络模型关联。
作为一种可选的实施方式,位于同一组内的频域资源满足以下至少一项:
频域跨度相同或频域跨度不相同;
频域间隔相同或频域间隔不相同;
频域位置部分重叠或频域位置不重叠;
对应的信道质量之差小于预设阈值。
作为一种可选的实施方式,在所述网络侧设备接收来自终端的第二信息之前,所述信息处理方法还包括:
所述网络侧设备向所述终端发送第一指示信息,其中,所述第一指示信息指示所述第一信息或所述第一信息的标识或所述第一AI网络模型的标识,所述第一AI网络模型与所述第一信息关联。
作为一种可选的实施方式,在所述网络侧设备根据第一信息,确定所述M个信道特征信息各自对应的第二AI网络侧模型之前,所述信息处理方法还包括:
所述网络侧设备接收来自所述终端的第二指示信息,其中,所述第二指示信息指示所述第一信息或所述第一信息的标识或所述第一AI网络模型的标识,所述第一AI网络模型与所述第一信息关联;
所述网络侧设备根据所述第二指示信息确定所述第一信息。
作为一种可选的实施方式,所述第二信道信息包括以下至少一项:
原始的信道矩阵或向量;
预编码矩阵或向量;
预处理后的信道矩阵或向量;
预处理后的预编码矩阵或向量。
作为一种可选的实施方式,所述信息处理方法还包括:
所述网络侧设备接收来自所述终端的目标能力信息,所述目标能力信息指示所述终端是否支持频域资源分组的能力。
作为一种可选的实施方式,所述目标能力信息指示以下至少一项:
所述终端是否支持频域资源分组;
所述终端支持的频域资源分组的最大数目;
所述终端支持的频域资源分组的标识;
所述终端支持的并行处理的频域资源分组的数目;
所述终端支持的同一组内的频域资源之间的频域间隔。
作为一种可选的实施方式,所述信息处理方法还包括:
所述网络侧设备向所述终端发送第五信息,所述第五信息指示和/或配置所述M组第二信道信息各自对应的第一AI网络模型,或者,所述第五信息指示所述M组第二信道信息中的至少部分组的第二信道信息对应的第一AI网络模型。
作为一种可选的实施方式,所述信息处理方法还包括:
所述网络侧设备接收来自所述终端的第三指示信息,所述第三指示信息指示所述M组第二信道信息各自对应的第一AI网络模型。
本实施方式中,终端可以选择并上报所述M组第二信道信息各自对应的第一AI网络模型,这样,网络侧设备可以根据所述M组第二信道信息各自对应的第一AI网络模型,确定所述M组第二信道信息各自对应的第二AI网络模型,其中,同一组第二信道信息对应的第一AI网络模型和第二AI网络模型为相互匹配或联合训练得到的编码和解码AI网络模型。
作为一种可选的实施方式,所述M组第二信道信息各自对应的第一AI网络模型满足以下至少一项:
包括相同数目的频域资源的频域资源分组对应同一个第一AI网络模型;
所述M组第二信道信息对应同一个第一AI网络模型;
一组第二信道信息的维度与对应的第一AI网络模型的输入信息维度匹配;
所述网络侧设备指示所述M组第二信道信息各自对应的第一AI网络侧模型。
本申请实施例中,网络侧设备接收来自终端的M个信道特征信息,并根据第一信息,确定该M个信道特征信息各自对应的第二AI网络模型,从而使用第二AI网络模型将对应的信道特征信息恢复成第二信道信息,从而实现信道特征信息的接收和恢复过程,其中,第二AI网络模型的输入为部分频域资源的信道特征信息,使得第二AI网络模型的模型尺寸较小,此外,通过将相同数目的频域资源划分为一组的方式,可以实现相同的第二AI网络模型可重复用于不同频域资源数的信道,这样,低频域资源数数的AI网络模型能够用于处理高频域资源数数的信道信息,从而提高了AI网络模型的复用效率和灵活度。
本申请实施例提供的信息传输方法,执行主体可以为信息传输装置。本申请实施例中以信息传输装置执行信息传输方法为例,说明本申请实施例提供的信息传输装置。
请参阅图4,本申请实施例提供的一种信息传输装置,可以是终端内的装置,如图4所示,该信息传输装置400可以包括以下模块:
第一确定模块401,用于基于第一信息,从第一信道信息中确定K组第二信道信息,其中,所述第一信息包括K组频域资源的分组信息,所述K组第二信道信息与所述K组频域资源一一对应,所述K组频域资源中的每一组频域资源包括至少一个频域资源,K为大于或等于1的整数;
第一处理模块402,用于基于M组第二信道信息各自对应的第一AI网络模型对所述M组第二信道信息进行第一处理,得到M个信道特征信息,所述K组第二信道信息包括所述M组第二信道信息,M为小于或等于K的正整数;
第一发送模块403,用于向网络侧设备发送第二信息,所述第二信息包括所述M个信道特征信息。
可选地,所述频域资源包括子带或物理资源块PRB。
可选地,所述K组频域资源的分组信息包括以下至少一项:
K的取值;
每一组频域资源内的频域资源的数目;
每一组频域资源内的频域资源的标识;
每一组频域资源内的频域资源的频域间隔;
每一组频域资源内的频域资源的频域跨度;
每一组频域资源内的起始频域资源位置;
每一组频域资源内的终止频域资源位置;
每一组频域资源的密度;
每一组频域资源的偏移值。
可选地,在所述K组频域资源中的每一组频域资源分别包括L个频域资源,且H不能整除L的情况下,所述第一信息包括对X个频域资源的信道信息的处理规则,其中,H为所述第一信道信息对应的信道的频域资源数目,X等于H除以L的余数,L、X和H分别为大于或等于1的整数。
可选地,所述处理规则包括以下至少一项:
基于Y个频域资源和所述X个频域资源组成第一组频域资源,其中,所述K组频域资源包括所述第一组频域资源,所述第一信道信息对应的信道的频域资源包括所述Y个频域资源;
舍弃上报所述X个频域资源的信道信息;
将所述X个频域资源的信道信息的维度补充至目标维度,所述目标维度为L个频域资源的信道信息的维度。
可选地,所述第一信息满足以下至少一项:
由所述网络侧设备指示;
由所述终端选择并上报;
由协议约定;
与所述第一AI网络模型关联。
可选地,位于同一组内的频域资源满足以下至少一项:
频域跨度相同或频域跨度不相同;
频域间隔相同或频域间隔不相同;
频域位置部分重叠或频域位置不重叠;
对应的信道质量之差小于预设阈值。
可选地,信息传输装置400还包括:
第二接收模块,用于接收来自所述网络侧设备的第一指示信息,其中,所述第一指示信息指示所述第一信息或所述第一信息的标识或所述第一AI网络模型的标识,所述第一AI网络模型与所述第一信息关联;
第三确定模块,用于根据所述第一指示信息确定所述第一信息。
可选地,信息传输装置400还包括:
第二发送模块,用于向所述网络侧设备发送第二指示信息,其中,所述第二指示信息指示所述第一信息或所述第一信息的标识或所述第一AI网络模型的标识,所述第一AI网络模型与所述第一信息关联。
可选地,信息传输装置400还包括:
第四确定模块,用于根据第三信息确定所述K组频域资源中每一组频域资源内的频域资源,所述K组频域资源的分组信息包括所述K组频域资源与各自包含的频域资源之间的对应关系;
其中,所述第三信息包括协议约定的所述每一组频域资源内的频域资源的频域间隔,以及所述网络侧设备指示的所述每一组频域资源内的频域资源的数目或所述K的取值。
可选地,信息传输装置400还包括:
第五确定模块,用于根据第四信息确定所述K组频域资源中每一组频域资源内的频域资源,所述K组频域资源的分组信息包括所述K组频域资源与各自包含的频域资源之间的对应关系;
其中,所述第四信息包括协议约定的所述处理规则,以及与所述第一AI网络模型关联的目标频域间隔和/或目标频域资源数目,所述目标频域间隔为一组频域资源内的频域资源的频域间隔,所述目标频域资源数目为一组频域资源内的频域资源的数目。
可选地,所述第二信道信息包括以下至少一项:
原始的信道矩阵或向量;
预编码矩阵或向量;
预处理后的信道矩阵或向量;
预处理后的预编码矩阵或向量。
可选地,所述预处理包括对同一组内的频域资源的信道信息进行压缩的预处理。
可选地,信息传输装置400还包括:
第三发送模块,用于向所述网络侧设备发送目标能力信息,所述目标能力信息指示所述终端是否支持频域资源分组的能力。
可选地,所述目标能力信息指示以下至少一项:
所述终端是否支持频域资源分组;
所述终端支持的频域资源分组的最大数目;
所述终端支持的频域资源分组的标识;
所述终端支持的并行处理的频域资源分组的数目;
所述终端支持的同一组内的频域资源之间的频域间隔。
可选地,信息传输装置400还包括:
第三接收模块,用于接收来自所述网络侧设备的第五信息,所述第五信息指示和/或配置所述M组第二信道信息各自对应的第一AI网络模型,或者,所述第五信息指示所述M组第二信道信息中的至少部分组的第二信道信息对应的第一AI网络模型;
第六确定模块,用于根据所述第五信息确定所述第一信息。
可选地,信息传输装置400还包括:
第四发送模块,用于向所述网络侧设备发送第三指示信息,所述第三指示信息指示所述M组第二信道信息各自对应的第一AI网络模型。
可选地,所述M组第二信道信息各自对应的第一AI网络模型满足以下至少一项:
包括相同数目的频域资源的频域资源分组对应同一个第一AI网络模型;
所述M组第二信道信息对应同一个第一AI网络模型;
一组第二信道信息的维度与对应的第一AI网络模型的输入信息维度匹配;
所述网络侧设备指示所述M组第二信道信息各自对应的第一AI网络侧模型。
本申请实施例中的信息传输装置可以是电子设备,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息传输装置400,能够实现如图2所示方法实施例中终端实现的各个过程,且能够取得相同的有益效果,为避免重复,在此不再赘述。
本申请实施例提供的信息处理方法,执行主体可以为信息处理装置。本申请实施例中以信息处理装置执行信息处理方法为例,说明本申请实施例提供的信息处理装置。
请参阅图5,本申请实施例提供的一种信息处理装置,可以是网络侧设备内的装置,如图5所示,该信息处理装置500可以包括以下模块:
第一接收模块501,用于接收来自终端的第二信息,其中,所述第二信息包括M个信道特征信息,所述M个信道特征信息是基于M组第二信道信息各自对应的第一AI网络模型对所述M组第二信道信息进行第一处理得到的信道特征信息,M为大于或等于1的整数;
第二确定模块502,用于根据第一信息,确定所述M个信道特征信息各自对应的第二AI网络侧模型,其中,所述第一信息包括K组频域资源的分组信息,所述K组第二信道信息与所述K组频域资源一一对应,所述K组频域资源中的每一组频域资源包括至少一 个频域资源,K为大于或等于M的整数;
第二处理模块503,用于基于所述M个信道特征信息各自对应的第二AI网络侧模型对所述M个信道特征信息进行第二处理,得到所述M组第二信道信息。
可选地,所述频域资源包括子带或物理资源块PRB。
可选地,所述K组频域资源的分组信息包括以下至少一项:
K的取值;
每一组频域资源内的频域资源的数目;
每一组频域资源内的频域资源的标识;
每一组频域资源内的频域资源的频域间隔;
每一组频域资源内的频域资源的频域跨度;
每一组频域资源内的起始频域资源位置;
每一组频域资源内的终止频域资源位置;
每一组频域资源的密度;
每一组频域资源的偏移值。
可选地,在所述K组频域资源中的每一组频域资源分别包括L个频域资源,且H不能整除L的情况下,所述第一信息包括对X个频域资源的信道信息的处理规则,其中,H为所述第一信道信息对应的信道的频域资源数目,X等于H除以L的余数,L、X和H分别为大于或等于1的整数。
可选地,所述处理规则包括以下至少一项:
基于(L-X)个频域资源和所述X个频域资源组成第一组频域资源,其中,所述K组频域资源包括所述第一组频域资源,所述第一信道信息对应的信道的频域资源包括所述(L-X)个频域资源;
舍弃上报所述X个频域资源的信道信息;
将所述X个频域资源的信道信息的维度补充至目标维度,所述目标维度为L个频域资源的信道信息的维度。
可选地,所述第一信息满足以下至少一项:
由所述网络侧设备指示;
由所述终端选择并上报;
由协议约定;
与所述第一AI网络模型关联。
可选地,位于同一组内的频域资源满足以下至少一项:
频域跨度相同或频域跨度不相同;
频域间隔相同或频域间隔不相同;
频域位置部分重叠或频域位置不重叠;
对应的信道质量之差小于预设阈值。
可选地,信息处理装置500还包括:
第五发送模块,用于向所述终端发送第一指示信息,其中,所述第一指示信息指示所述第一信息或所述第一信息的标识或所述第一AI网络模型的标识,所述第一AI网络模型与所述第一信息关联。
可选地,信息处理装置500还包括:
第四接收模块,用于接收来自所述终端的第二指示信息,其中,所述第二指示信息指示所述第一信息或所述第一信息的标识或所述第一AI网络模型的标识,所述第一AI网络模型与所述第一信息关联;
第七确定模块,用于根据所述第二指示信息确定所述第一信息。
可选地,所述第二信道信息包括以下至少一项:
原始的信道矩阵或向量;
预编码矩阵或向量;
预处理后的信道矩阵或向量;
预处理后的预编码矩阵或向量。
可选地,信息处理装置500还包括:
第五接收模块,用于接收来自所述终端的目标能力信息,所述目标能力信息指示所述终端是否支持频域资源分组的能力。
可选地,所述目标能力信息指示以下至少一项:
所述终端是否支持频域资源分组;
所述终端支持的频域资源分组的最大数目;
所述终端支持的频域资源分组的标识;
所述终端支持的并行处理的频域资源分组的数目;
所述终端支持的同一组内的频域资源之间的频域间隔。
可选地,信息处理装置500还包括:
第六发送模块,用于向所述终端发送第五信息,所述第五信息指示和/或配置所述M组第二信道信息各自对应的第一AI网络模型,或者,所述第五信息指示所述M组第二信道信息中的至少部分组的第二信道信息对应的第一AI网络模型。
可选地,信息处理装置500还包括:
第六接收模块,用于接收来自所述终端的第三指示信息,所述第三指示信息指示所述M组第二信道信息各自对应的第一AI网络模型。
可选地,所述M组第二信道信息各自对应的第一AI网络模型满足以下至少一项:
包括相同数目的频域资源的频域资源分组对应同一个第一AI网络模型;
所述M组第二信道信息对应同一个第一AI网络模型;
一组第二信道信息的维度与对应的第一AI网络模型的输入信息维度匹配;
所述网络侧设备指示所述M组第二信道信息各自对应的第一AI网络侧模型。
本申请实施例提供的信息处理装置500,能够实现如图3所示方法实施例中网络侧设备实现的各个过程,且能够取得相同的有益效果,为避免重复,在此不再赘述。
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执行时实现如图2所示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执行时实现如图3所示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,所述处理器用于基于第一信息,从第一信道信息中确定K组第二信道信息,其中,所述第一信息包括K组频域资源的分组信息,所述K组第二信道信息与所述K组频域资源一一对应,所述K组频域资源中的每一组频域资源包括至少一个频域资源,K为大于或等于1的整数;所述处理器还用于基于M组第二信道信息各自对应的第一AI网络模型对所述M组第二信道信息进行第一处理,得到M个信道特征信息,所述K组第二信道信息包括所述M组第二信道信息,M为小于或等于K的正整数;所述通信接口用于向网络侧设备发送第二信息,所述第二信息包括所述M个信道特征信息。该终端实施例能够实现如图4所示信息传输装置400执行的各个过程,且能达到相同的技术效果,在此不再赘述。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;可选地,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,用于基于第一信息,从第一信道信息中确定K组第二信道信息,其中,所述第一信息包括K组频域资源的分组信息,所述K组第二信道信息与所述K组频域资源一一对应,所述K组频域资源中的每一组频域资源包括至少一个频域资源,K为大于或等于1的整数;
处理器710,还用于基于M组第二信道信息各自对应的第一AI网络模型对所述M组第二信道信息进行第一处理,得到M个信道特征信息,所述K组第二信道信息包括所述M组第二信道信息,M为小于或等于K的正整数;
射频单元701,用于向网络侧设备发送第二信息,所述第二信息包括所述M个信道特征信息。
可选地,所述频域资源包括子带或物理资源块PRB。
可选地,所述K组频域资源的分组信息包括以下至少一项:
K的取值;
每一组频域资源内的频域资源的数目;
每一组频域资源内的频域资源的标识;
每一组频域资源内的频域资源的频域间隔;
每一组频域资源内的频域资源的频域跨度;
每一组频域资源内的起始频域资源位置;
每一组频域资源内的终止频域资源位置;
每一组频域资源的密度;
每一组频域资源的偏移值。
可选地,在所述K组频域资源中的每一组频域资源分别包括L个频域资源,且H不能整除L的情况下,所述第一信息包括对X个频域资源的信道信息的处理规则,其中,H为所述第一信道信息对应的信道的频域资源数目,X等于H除以L的余数,L、X和H分别为大于或等于1的整数。
可选地,所述处理规则包括以下至少一项:
基于Y个频域资源和所述X个频域资源组成第一组频域资源,其中,所述K组频域资源包括所述第一组频域资源,所述第一信道信息对应的信道的频域资源包括所述Y个频域资源;
舍弃上报所述X个频域资源的信道信息;
将所述X个频域资源的信道信息的维度补充至目标维度,所述目标维度为L个频域资源的信道信息的维度。
可选地,所述第一信息满足以下至少一项:
由所述网络侧设备指示;
由所述终端选择并上报;
由协议约定;
与所述第一AI网络模型关联。
可选地,位于同一组内的频域资源满足以下至少一项:
频域跨度相同或频域跨度不相同;
频域间隔相同或频域间隔不相同;
频域位置部分重叠或频域位置不重叠;
对应的信道质量之差小于预设阈值。
可选地,在处理器710执行所述基于第一信息,从第一信道信息中确定K组第二信道信息之前:
射频单元701,还用于接收来自所述网络侧设备的第一指示信息,其中,所述第一指示信息指示所述第一信息或所述第一信息的标识或所述第一AI网络模型的标识,所述第一AI网络模型与所述第一信息关联;
处理器710,还用于根据所述第一指示信息确定所述第一信息。
可选地,射频单元701,还用于向所述网络侧设备发送第二指示信息,其中,所述第二指示信息指示所述第一信息或所述第一信息的标识或所述第一AI网络模型的标识,所述第一AI网络模型与所述第一信息关联。
可选地,处理器710,还用于根据第三信息确定所述K组频域资源中每一组频域资源 内的频域资源,所述K组频域资源的分组信息包括所述K组频域资源与各自包含的频域资源之间的对应关系;
其中,所述第三信息包括协议约定的所述每一组频域资源内的频域资源的频域间隔,以及所述网络侧设备指示的所述每一组频域资源内的频域资源的数目或所述K的取值。
可选地,处理器710,还用于根据第四信息确定所述K组频域资源中每一组频域资源内的频域资源,所述K组频域资源的分组信息包括所述K组频域资源与各自包含的频域资源之间的对应关系;
其中,所述第四信息包括协议约定的所述处理规则,以及与所述第一AI网络模型关联的目标频域间隔和/或目标频域资源数目,所述目标频域间隔为一组频域资源内的频域资源的频域间隔,所述目标频域资源数目为一组频域资源内的频域资源的数目。
可选地,所述第二信道信息包括以下至少一项:
原始的信道矩阵或向量;
预编码矩阵或向量;
预处理后的信道矩阵或向量;
预处理后的预编码矩阵或向量。
可选地,所述预处理包括对同一组内的频域资源的信道信息进行压缩的预处理。
可选地,射频单元701,还用于向所述网络侧设备发送目标能力信息,所述目标能力信息指示所述终端是否支持频域资源分组的能力。
可选地,所述目标能力信息指示以下至少一项:
所述终端是否支持频域资源分组;
所述终端支持的频域资源分组的最大数目;
所述终端支持的频域资源分组的标识;
所述终端支持的并行处理的频域资源分组的数目;
所述终端支持的同一组内的频域资源之间的频域间隔。
可选地,射频单元701,还用于接收来自所述网络侧设备的第五信息,所述第五信息指示和/或配置所述M组第二信道信息各自对应的第一AI网络模型,或者,所述第五信息指示所述M组第二信道信息中的至少部分组的第二信道信息对应的第一AI网络模型;
处理器710,还用于根据所述第五信息确定所述第一信息。
可选地,射频单元701,还用于向所述网络侧设备发送第三指示信息,所述第三指示信息指示所述M组第二信道信息各自对应的第一AI网络模型。
可选地,所述M组第二信道信息各自对应的第一AI网络模型满足以下至少一项:
包括相同数目的频域资源的频域资源分组对应同一个第一AI网络模型;
所述M组第二信道信息对应同一个第一AI网络模型;
一组第二信道信息的维度与对应的第一AI网络模型的输入信息维度匹配;
所述网络侧设备指示所述M组第二信道信息各自对应的第一AI网络侧模型。
本申请实施例提供的终端700能够实现如图4所示信息传输装置400执行的各个过程,且能够取得相同的有益效果,为避免重复,在此不再赘述。
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来自终端的第二信息,其中,所述第二信息包括M个信道特征信息,所述M个信道特征信息是基于M组第二信道信息各自对应的第一AI网络模型对所述M组第二信道信息进行第一处理得到的信道特征信息,M为大于或等于1的整数;所述处理器用于根据第一信息,确定所述M个信道特征信息各自对应的第二AI网络侧模型,其中,所述第一信息包括K组频域资源的分组信息,所述K组第二信道信息与所述K组频域资源一一对应,所述K组频域资源中的每一组频域资源包括至少一个频域资源,K为大于或等于M的整数;所述处理器还用于基于所述M个信道特征信息各自对应的第二AI网络侧模型对所述M个信道特征信息进行第二处理,得到所述M组第二信道信息。
该网络侧设备实施例能够实现如图5所示信息处理装置500执行的各个过程,且能达到相同的技术效果,在此不再赘述。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801、射频装置802、基带装置803、处理器804和存储器805。天线801与射频装置802连接。在上行方向上,射频装置802通过天线801接收信息,将接收的信息发送给基带装置803进行处理。在下行方向上,基带装置803对要发送的信息进行处理,并发送给射频装置802,射频装置802对收到的信息进行处理后经过天线801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803中实现,该基带装置803包括基带处理器。
基带装置803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805连接,以调用存储器805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806,该接口例如为通用公共无线接口(Common Public Radio Interface,CPRI)。
具体地,本申请实施例的网络侧设备800还包括:存储在存储器805上并可在处理器804上运行的指令或程序,处理器804调用存储器805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如图2或图3所示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,实现如图2或图3所示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如图2或图3所示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:终端和网络侧设备,所述终端可用于执行如图2所示的信息传输方法的步骤,所述网络侧设备可用于执行如图3所示的信息处理方法的步骤。
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 (37)

  1. 一种信息传输方法,包括:
    终端基于第一信息,从第一信道信息中确定K组第二信道信息,其中,所述第一信息包括K组频域资源的分组信息,所述K组第二信道信息与所述K组频域资源一一对应,所述K组频域资源中的每一组频域资源包括至少一个频域资源,K为大于或等于1的整数;
    所述终端基于M组第二信道信息各自对应的第一AI网络模型对所述M组第二信道信息进行第一处理,得到M个信道特征信息,所述K组第二信道信息包括所述M组第二信道信息,M为小于或等于K的正整数;
    所述终端向网络侧设备发送第二信息,所述第二信息包括所述M个信道特征信息。
  2. 根据权利要求1所述的方法,其中,所述频域资源包括子带或物理资源块PRB。
  3. 根据权利要求1所述的方法,其中,所述K组频域资源的分组信息包括以下至少一项:
    K的取值;
    每一组频域资源内的频域资源的数目;
    每一组频域资源内的频域资源的标识;
    每一组频域资源内的频域资源的频域间隔;
    每一组频域资源内的频域资源的频域跨度;
    每一组频域资源内的起始频域资源位置;
    每一组频域资源内的终止频域资源位置;
    每一组频域资源的密度;
    每一组频域资源的偏移值。
  4. 根据权利要求1所述的方法,其中,在所述K组频域资源中的每一组频域资源分别包括L个频域资源,且H不能整除L的情况下,所述第一信息包括对X个频域资源的信道信息的处理规则,其中,H为所述第一信道信息对应的信道的频域资源数目,X等于H除以L的余数,L、X和H分别为大于或等于1的整数。
  5. 根据权利要求4所述的方法,其中,所述处理规则包括以下至少一项:
    基于Y个频域资源和所述X个频域资源组成第一组频域资源,其中,所述K组频域资源包括所述第一组频域资源,所述第一信道信息对应的信道的频域资源包括所述Y个频域资源;
    舍弃上报所述X个频域资源的信道信息;
    将所述X个频域资源的信道信息的维度补充至目标维度,所述目标维度为L个频域资源的信道信息的维度。
  6. 根据权利要求1至5中任一项所述的方法,其中,所述第一信息满足以下至少一项:
    由所述网络侧设备指示;
    由所述终端选择并上报;
    由协议约定;
    与所述第一AI网络模型关联。
  7. 根据权利要求1至5中任一项所述的方法,其中,位于同一组内的频域资源满足以下至少一项:
    频域跨度相同或频域跨度不相同;
    频域间隔相同或频域间隔不相同;
    频域位置部分重叠或频域位置不重叠;
    对应的信道质量之差小于预设阈值。
  8. 根据权利要求1至5中任一项所述的方法,其中,在所述终端基于第一信息,从第一信道信息中确定K组第二信道信息之前,所述方法还包括:
    所述终端接收来自所述网络侧设备的第一指示信息,其中,所述第一指示信息指示所述第一信息或所述第一信息的标识或所述第一AI网络模型的标识,所述第一AI网络模型与所述第一信息关联;
    所述终端根据所述第一指示信息确定所述第一信息。
  9. 根据权利要求1至5中任一项所述的方法,其中,所述方法还包括:
    所述终端向所述网络侧设备发送第二指示信息,其中,所述第二指示信息指示所述第一信息或所述第一信息的标识或所述第一AI网络模型的标识,所述第一AI网络模型与所述第一信息关联。
  10. 根据权利要求3所述的方法,其中,所述方法还包括:
    所述终端根据第三信息确定所述K组频域资源中每一组频域资源内的频域资源,所述K组频域资源的分组信息包括所述K组频域资源与各自包含的频域资源之间的对应关系;
    其中,所述第三信息包括协议约定的所述每一组频域资源内的频域资源的频域间隔,以及所述网络侧设备指示的所述每一组频域资源内的频域资源的数目或所述K的取值。
  11. 根据权利要求4所述的方法,其中,所述方法还包括:
    所述终端根据第四信息确定所述K组频域资源中每一组频域资源内的频域资源,所述K组频域资源的分组信息包括所述K组频域资源与各自包含的频域资源之间的对应关系;
    其中,所述第四信息包括协议约定的所述处理规则,以及与所述第一AI网络模型关联的目标频域间隔和/或目标频域资源数目,所述目标频域间隔为一组频域资源内的频域资源的频域间隔,所述目标频域资源数目为一组频域资源内的频域资源的数目。
  12. 根据权利要求1至5中任一项所述的方法,其中,所述第二信道信息包括以下至少一项:
    原始的信道矩阵或向量;
    预编码矩阵或向量;
    预处理后的信道矩阵或向量;
    预处理后的预编码矩阵或向量。
  13. 根据权利要求12所述的方法,其中,所述预处理包括对同一组内的频域资源的信道信息进行压缩的预处理。
  14. 根据权利要求1至5中任一项所述的方法,其中,所述方法还包括:
    所述终端向所述网络侧设备发送目标能力信息,所述目标能力信息指示所述终端是否支持频域资源分组的能力。
  15. 根据权利要求14所述的方法,其中,所述目标能力信息指示以下至少一项:
    所述终端是否支持频域资源分组;
    所述终端支持的频域资源分组的最大数目;
    所述终端支持的频域资源分组的标识;
    所述终端支持的并行处理的频域资源分组的数目;
    所述终端支持的同一组内的频域资源之间的频域间隔。
  16. 根据权利要求1至5中任一项所述的方法,其中,所述方法还包括:
    所述终端接收来自所述网络侧设备的第五信息,所述第五信息指示和/或配置所述M组第二信道信息各自对应的第一AI网络模型,或者,所述第五信息指示所述M组第二信道信息中的至少部分组的第二信道信息对应的第一AI网络模型;
    所述终端根据所述第五信息确定所述第一信息。
  17. 根据权利要求1至5中任一项所述的方法,其中,所述方法还包括:
    所述终端向所述网络侧设备发送第三指示信息,所述第三指示信息指示所述M组第二信道信息各自对应的第一AI网络模型。
  18. 根据权利要求1至5中任一项所述的方法,其中,所述M组第二信道信息各自对应的第一AI网络模型满足以下至少一项:
    包括相同数目的频域资源的频域资源分组对应同一个第一AI网络模型;
    所述M组第二信道信息对应同一个第一AI网络模型;
    一组第二信道信息的维度与对应的第一AI网络模型的输入信息维度匹配;
    所述网络侧设备指示所述M组第二信道信息各自对应的第一AI网络侧模型。
  19. 一种信息处理方法,包括:
    网络侧设备接收来自终端的第二信息,其中,所述第二信息包括M个信道特征信息,所述M个信道特征信息是基于M组第二信道信息各自对应的第一AI网络模型对所述M组第二信道信息进行第一处理得到的信道特征信息,M为大于或等于1的整数;
    所述网络侧设备根据第一信息,确定所述M个信道特征信息各自对应的第二AI网络侧模型,其中,所述第一信息包括K组频域资源的分组信息,所述K组第二信道信息与所述K组频域资源一一对应,所述K组频域资源中的每一组频域资源包括至少一个频域资源,K为大于或等于M的整数;
    所述网络侧设备基于所述M个信道特征信息各自对应的第二AI网络侧模型对所述M个信道特征信息进行第二处理,得到所述M组第二信道信息。
  20. 根据权利要求19所述的方法,其中,所述频域资源包括子带或物理资源块PRB。
  21. 根据权利要求19所述的方法,其中,所述K组频域资源的分组信息包括以下至少一项:
    K的取值;
    每一组频域资源内的频域资源的数目;
    每一组频域资源内的频域资源的标识;
    每一组频域资源内的频域资源的频域间隔;
    每一组频域资源内的频域资源的频域跨度;
    每一组频域资源内的起始频域资源位置;
    每一组频域资源内的终止频域资源位置;
    每一组频域资源的密度;
    每一组频域资源的偏移值。
  22. 根据权利要求19所述的方法,其中,在所述K组频域资源中的每一组频域资源分别包括L个频域资源,且H不能整除L的情况下,所述第一信息包括对X个频域资源的信道信息的处理规则,其中,H为目标下行信道的频域资源数目,X等于H除以L的余数,L、X和H分别为大于或等于1的整数,所述目标下行信道为所述第二信道信息对应的信道。
  23. 根据权利要求22所述的方法,其中,所述处理规则包括以下至少一项:
    基于(L-X)个频域资源和所述X个频域资源组成第一组频域资源,其中,所述K组频域资源包括所述第一组频域资源,所述目标下行信道的频域资源包括所述(L-X)个频域资源;
    舍弃上报所述X个频域资源的信道信息;
    将所述X个频域资源的信道信息的维度补充至目标维度,所述目标维度为L个频域资源的信道信息的维度。
  24. 根据权利要求19至23中任一项所述的方法,其中,所述第一信息满足以下至少一项:
    由所述网络侧设备指示;
    由所述终端选择并上报;
    由协议约定;
    与所述第一AI网络模型关联。
  25. 根据权利要求19至23中任一项所述的方法,其中,位于同一组内的频域资源满足以下至少一项:
    频域跨度相同或频域跨度不相同;
    频域间隔相同或频域间隔不相同;
    频域位置部分重叠或频域位置不重叠;
    对应的信道质量之差小于预设阈值。
  26. 根据权利要求19至23中任一项所述的方法,其中,在所述网络侧设备接收来自终端的第二信息之前,所述方法还包括:
    所述网络侧设备向所述终端发送第一指示信息,其中,所述第一指示信息指示所述第一信息或所述第一信息的标识或所述第一AI网络模型的标识,所述第一AI网络模型与所述第一信息关联。
  27. 根据权利要求19至23中任一项所述的方法,其中,在所述网络侧设备根据第一信息,确定所述M个信道特征信息各自对应的第二AI网络侧模型之前,所述方法还包括:
    所述网络侧设备接收来自所述终端的第二指示信息,其中,所述第二指示信息指示所述第一信息或所述第一信息的标识或所述第一AI网络模型的标识,所述第一AI网络模型与所述第一信息关联;
    所述网络侧设备根据所述第二指示信息确定所述第一信息。
  28. 根据权利要求19至23中任一项所述的方法,其中,所述第二信道信息包括以下至少一项:
    原始的信道矩阵或向量;
    预编码矩阵或向量;
    预处理后的信道矩阵或向量;
    预处理后的预编码矩阵或向量。
  29. 根据权利要求19至23中任一项所述的方法,其中,所述方法还包括:
    所述网络侧设备接收来自所述终端的目标能力信息,所述目标能力信息指示所述终端是否支持频域资源分组的能力。
  30. 根据权利要求29所述的方法,其中,所述目标能力信息指示以下至少一项:
    所述终端是否支持频域资源分组;
    所述终端支持的频域资源分组的最大数目;
    所述终端支持的频域资源分组的标识;
    所述终端支持的并行处理的频域资源分组的数目;
    所述终端支持的同一组内的频域资源之间的频域间隔。
  31. 根据权利要求19至23中任一项所述的方法,其中,所述方法还包括:
    所述网络侧设备向所述终端发送第五信息,所述第五信息指示和/或配置所述M组第二信道信息各自对应的第一AI网络模型,或者,所述第五信息指示所述M组第二信道信息中的至少部分组的第二信道信息对应的第一AI网络模型。
  32. 根据权利要求19至23中任一项所述的方法,其中,所述方法还包括:
    所述网络侧设备接收来自所述终端的第三指示信息,所述第三指示信息指示所述M 组第二信道信息各自对应的第一AI网络模型。
  33. 根据权利要求19至23中任一项所述的方法,其中,所述M组第二信道信息各自对应的第一AI网络模型满足以下至少一项:
    包括相同数目的频域资源的频域资源分组对应同一个第一AI网络模型;
    所述M组第二信道信息对应同一个第一AI网络模型;
    一组第二信道信息的维度与对应的第一AI网络模型的输入信息维度匹配;
    所述网络侧设备指示所述M组第二信道信息各自对应的第一AI网络侧模型。
  34. 一种信息传输装置,应用于终端,所述装置包括:
    第一确定模块,用于基于第一信息,从第一信道信息中确定K组第二信道信息,其中,所述第一信息包括K组频域资源的分组信息,所述K组第二信道信息与所述K组频域资源一一对应,所述K组频域资源中的每一组频域资源包括至少一个频域资源,K为大于或等于1的整数;
    第一处理模块,用于基于M组第二信道信息各自对应的第一AI网络模型对所述M组第二信道信息进行第一处理,得到M个信道特征信息,所述K组第二信道信息包括所述M组第二信道信息,M为小于或等于K的正整数;
    第一发送模块,用于向网络侧设备发送第二信息,所述第二信息包括所述M个信道特征信息。
  35. 一种信息处理装置,应用于网络侧设备,所述装置包括:
    第一接收模块,用于接收来自终端的第二信息,其中,所述第二信息包括M个信道特征信息,所述M个信道特征信息是基于M组第二信道信息各自对应的第一AI网络模型对所述M组第二信道信息进行第一处理得到的信道特征信息,M为大于或等于1的整数;
    第二确定模块,用于根据第一信息,确定所述M个信道特征信息各自对应的第二AI网络侧模型,其中,所述第一信息包括K组频域资源的分组信息,所述K组第二信道信息与所述K组频域资源一一对应,所述K组频域资源中的每一组频域资源包括至少一个频域资源,K为大于或等于M的整数;
    第二处理模块,用于基于所述M个信道特征信息各自对应的第二AI网络侧模型对所述M个信道特征信息进行第二处理,得到所述M组第二信道信息。
  36. 一种通信设备,包括处理器和存储器,所述存储器存储可在所述处理器上运行的程序或指令,所述程序或指令被所述处理器执行时实现如权利要求1至18中任一项所述的信息传输方法的步骤,或者实现如权利要求19至33中任一项所述的信息处理方法的步骤。
  37. 一种可读存储介质,所述可读存储介质上存储程序或指令,所述程序或指令被处理器执行时实现如权利要求1至18中任一项所述的信息传输方法的步骤,或者实现如权利要求19至33中任一项所述的信息处理方法的步骤。
PCT/CN2023/125560 2022-10-27 2023-10-20 信息传输方法、信息处理方法、装置和通信设备 WO2024088161A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202211328601.6 2022-10-27
CN202211328601.6A CN117997484A (zh) 2022-10-27 2022-10-27 信息传输方法、信息处理方法、装置和通信设备

Publications (1)

Publication Number Publication Date
WO2024088161A1 true WO2024088161A1 (zh) 2024-05-02

Family

ID=90830100

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/125560 WO2024088161A1 (zh) 2022-10-27 2023-10-20 信息传输方法、信息处理方法、装置和通信设备

Country Status (2)

Country Link
CN (1) CN117997484A (zh)
WO (1) WO2024088161A1 (zh)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2022033456A1 (zh) * 2020-08-13 2022-02-17 华为技术有限公司 一种信道状态信息测量反馈方法及相关装置
CN114531355A (zh) * 2020-11-23 2022-05-24 维沃移动通信有限公司 通信方法、装置及通信设备
CN114697984A (zh) * 2020-12-28 2022-07-01 中国移动通信有限公司研究院 信息传输方法、终端及网络设备
CN115134052A (zh) * 2021-03-29 2022-09-30 华为技术有限公司 一种参考信号配置方法及装置
CN115244970A (zh) * 2022-06-16 2022-10-25 北京小米移动软件有限公司 Csi上报方法、信息发送方法、装置、设备及介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2022033456A1 (zh) * 2020-08-13 2022-02-17 华为技术有限公司 一种信道状态信息测量反馈方法及相关装置
CN114531355A (zh) * 2020-11-23 2022-05-24 维沃移动通信有限公司 通信方法、装置及通信设备
CN114697984A (zh) * 2020-12-28 2022-07-01 中国移动通信有限公司研究院 信息传输方法、终端及网络设备
CN115134052A (zh) * 2021-03-29 2022-09-30 华为技术有限公司 一种参考信号配置方法及装置
CN115244970A (zh) * 2022-06-16 2022-10-25 北京小米移动软件有限公司 Csi上报方法、信息发送方法、装置、设备及介质

Also Published As

Publication number Publication date
CN117997484A (zh) 2024-05-07

Similar Documents

Publication Publication Date Title
US20230412430A1 (en) Inforamtion reporting method and apparatus, first device, and second device
WO2023246618A1 (zh) 信道矩阵处理方法、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
WO2023185978A1 (zh) 信道特征信息上报及恢复方法、终端和网络侧设备
WO2024088161A1 (zh) 信息传输方法、信息处理方法、装置和通信设备
WO2024088162A1 (zh) 信息传输方法、信息处理方法、装置和通信设备
WO2024222577A1 (zh) 信息处理方法、信息传输方法、装置、终端及网络侧设备
WO2024222601A1 (zh) Cpu数量上报方法、接收方法、装置、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
WO2024222573A1 (zh) 信息处理方法、信息处理装置、终端及网络侧设备
WO2023185980A1 (zh) 信道特征信息传输方法、装置、终端及网络侧设备
WO2024140578A1 (zh) 基于ai模型的csi反馈方法、终端及网络侧设备
WO2024104126A1 (zh) 更新ai网络模型的方法、装置和通信设备
WO2024217495A1 (zh) 信息处理方法、信息处理装置、终端及网络侧设备
WO2024037380A1 (zh) 信道信息处理方法、装置、通信设备及存储介质
WO2023179476A1 (zh) 信道特征信息上报及恢复方法、终端和网络侧设备
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
WO2023179460A1 (zh) 信道特征信息传输方法、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
WO2023179570A1 (zh) 信道特征信息传输方法、装置、终端及网络侧设备
WO2024032606A1 (zh) 信息传输方法、装置、设备、系统及存储介质
WO2023179473A1 (zh) 信道特征信息上报及恢复方法、终端和网络侧设备
WO2024140422A1 (zh) Ai单元的性能监测方法、终端及网络侧设备
WO2023134628A1 (zh) 传输方法、装置和设备

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: 23881739

Country of ref document: EP

Kind code of ref document: A1