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

WO2024222577A1 - 信息处理方法、信息传输方法、装置、终端及网络侧设备 - Google Patents

信息处理方法、信息传输方法、装置、终端及网络侧设备 Download PDF

Info

Publication number
WO2024222577A1
WO2024222577A1 PCT/CN2024/088746 CN2024088746W WO2024222577A1 WO 2024222577 A1 WO2024222577 A1 WO 2024222577A1 CN 2024088746 W CN2024088746 W CN 2024088746W WO 2024222577 A1 WO2024222577 A1 WO 2024222577A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
layer
target
payload
channel characteristic
Prior art date
Application number
PCT/CN2024/088746
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 WO2024222577A1 publication Critical patent/WO2024222577A1/zh

Links

Definitions

  • the present application belongs to the field of communication technology, and specifically relates to an information processing method, an information transmission method, an apparatus, a terminal and a network side device.
  • the terminal can use an encoding artificial intelligence (AI) model to compress channel information and report the compressed channel characteristic information.
  • AI artificial intelligence
  • the network side can use a decoding AI model to restore the channel characteristic information reported by the terminal to obtain the terminal channel information. In this way, the overhead of the terminal reporting channel information can be reduced.
  • the terminal After estimating the Channel State Information-Reference Signal (CSI-RS), the terminal performs singular value decomposition (SVD) on the channel matrix to obtain relatively orthogonal precoding matrices of multiple layers.
  • the precoding matrix of each layer can be independently compressed through a coding AI model, and then the compression results of all layers are reported to the base station together.
  • the length of the compression results obtained after the precoding matrices of different layers are compressed using the same coding AI model is the same, which may cause the compression results of some important layers to be insufficiently accurate or cause the compression results of some unimportant layers to be too long.
  • the embodiments of the present application provide an information processing method, an information transmission method, an apparatus, a terminal and a network-side device.
  • the terminal can adjust the encoding AI model corresponding to each layer or the output length of the encoding AI model based on the first information, thereby being able to more flexibly adjust the length of the compression results of different layers.
  • an information processing method comprising:
  • the terminal obtains first information, wherein the first information indicates payload information of first channel characteristic information corresponding to at least one layer;
  • the terminal performs a first process on the channel information of the target layer using the target first AI unit based on the first information to obtain the first channel characteristic information corresponding to the target layer, wherein the payload information of the first channel characteristic information corresponding to the target layer matches the output length of the target first AI unit, and the at least one layer includes the target layer.
  • an information processing method comprising:
  • the network side device sends first information to the terminal, wherein the first information indicates payload information of first channel characteristic information corresponding to at least one layer;
  • the first information is used by the terminal to determine the payload of the first channel characteristic information corresponding to the target layer
  • the first channel characteristic information corresponding to the target layer is obtained by first processing the channel information of the target layer based on the target first AI unit corresponding to the target layer
  • the payload information of the first channel characteristic information corresponding to the target layer matches the output length of the target first AI unit
  • the at least one layer includes the target layer.
  • an information processing device comprising:
  • a first acquisition module configured to acquire first information, wherein the first information indicates payload information of first channel characteristic information corresponding to at least one layer;
  • a first processing module is used to perform a first processing on the channel information of a target layer using a target first AI unit based on the first information to obtain the first channel characteristic information corresponding to the target layer, wherein the payload information of the first channel characteristic information corresponding to the target layer matches the output length of the target first AI unit, and the at least one layer includes the target layer.
  • an information processing device comprising:
  • a first sending module configured to send first information to a terminal, wherein the first information indicates payload information of first channel characteristic information corresponding to at least one layer;
  • the first information is used by the terminal to determine the payload of the first channel characteristic information corresponding to the target layer
  • the first channel characteristic information corresponding to the target layer is obtained by first processing the channel information of the target layer based on the target first AI unit corresponding to the target layer
  • the payload information of the first channel characteristic information corresponding to the target layer matches the output length of the target first AI unit
  • the at least one layer includes the target layer.
  • a terminal comprising a processor and a memory, wherein the memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, the steps of the method described in the first aspect are implemented.
  • a terminal comprising a processor and a communication interface, wherein the communication interface is used to obtain first information, wherein the first information indicates payload information of first channel characteristic information corresponding to at least one layer; the processor is used to perform a first processing on the channel information of the target layer using a target first AI unit based on the first information to obtain the first channel characteristic information corresponding to the target layer, wherein the payload information of the first channel characteristic information corresponding to the target layer matches the output length of the target first AI unit, and the at least one layer includes the target layer.
  • a network side 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 method described in the second aspect are implemented.
  • a network side device including a processor and a communication interface, wherein the communication interface is used to send a The terminal sends first information, wherein the first information indicates the payload information of the first channel characteristic information corresponding to at least one layer; wherein the first information is used by the terminal to determine the payload of the first channel characteristic information corresponding to the target layer, the first channel characteristic information corresponding to the target layer is obtained by performing a first processing on the channel information of the target layer based on the target first AI unit corresponding to the target layer, the payload information of the first channel characteristic information corresponding to the target layer matches the output length of the target first AI unit, and the at least one layer includes the target layer.
  • 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 method described in the first aspect are implemented, or the steps of the method described in the second aspect are implemented.
  • a wireless communication system comprising: a terminal and a network side device, wherein the terminal can be used to execute the steps of the method described in the first aspect, and the network side device can be used to execute the steps of the method described in the second aspect.
  • 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 method described in the first aspect, or to implement the method described in the second aspect.
  • a computer program/program product is provided, wherein the computer program/program product is stored in a storage medium, and the program/program product is executed by at least one processor to implement the steps of the information processing method as described in the first aspect, or to implement the steps of the information processing method as described in the second aspect.
  • the terminal can determine the payload information of the first channel characteristic information corresponding to each layer based on the first information, so as to process the channel information of a layer using the first AI unit matching the payload information to obtain the channel characteristic information that conforms to the payload information.
  • the terminal can report channel characteristic information of different payloads to the network side device, and thus can more flexibly adjust the length of the channel characteristic information of different layers, while reducing the overhead of reporting the channel characteristic information, and can also improve the accuracy of the channel characteristic information of the layer with higher importance in a targeted manner, for example: the first information indicates that the payload of the channel characteristic information of the layer with higher importance, higher intensity or higher concentration is greater than the payload of the channel characteristic information of the layer with lower importance, lower intensity or lower concentration, so that the channel characteristic information of the layer with higher importance, higher intensity or higher concentration reported by the terminal is more accurate than the channel characteristic information of the layer with lower importance, lower intensity or lower concentration.
  • 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 schematic diagram of the architecture of a neural network model
  • Figure 3 is a schematic diagram of a neuron
  • FIG4 is a flow chart of an information processing method provided in an embodiment of the present application.
  • FIG5 is a flow chart of another information processing method provided in an embodiment of the present application.
  • FIG6 is a schematic diagram of the structure of an information processing device provided in an embodiment of the present application.
  • FIG7 is a schematic diagram of the structure of another information processing device provided in an embodiment of the present application.
  • FIG8 is a schematic diagram of the structure of a communication device provided in an embodiment of the present application.
  • FIG9 is a schematic diagram of the structure of a terminal provided in an embodiment of the present application.
  • FIG. 10 is a schematic diagram of the structure of a network-side device provided in an embodiment of the present application.
  • first, second, etc. 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 where appropriate, so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by “first” and “second” are generally of one type, and the number of objects is not limited, for example, the first object can be one or more.
  • “or” in the present application represents at least one of the connected objects.
  • “A or B” covers three schemes, namely, Scheme 1: including A but not including B; Scheme 2: including B but not including A; Scheme 3: including both A and B.
  • the character "/" generally indicates that the objects associated with each other are in an "or” relationship.
  • indication in this application can be a direct indication (or explicit indication) or an indirect indication (or implicit indication).
  • a direct indication can be understood as the sender explicitly informing the receiver of specific information, operations to be performed, or request results in the sent indication;
  • an indirect indication can be understood as the receiver determining the corresponding information according to the indication sent by the sender, or making a judgment and determining the operation to be performed or the request result according to the judgment result.
  • 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
  • 6G 6th Generation
  • FIG1 is a block diagram of a wireless communication system applicable to the 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), a personal digital assistant (Personal Digital Assistant, PDA), PDA, netbook, ultra-mobile personal computer (UMPC), mobile internet device (MID), augmented reality (AR), virtual reality (VR) equipment, robot, wearable device, flight vehicle, vehicle user equipment (VUE), shipborne equipment, pedestrian user equipment (PUE), smart home (home equipment with wireless communication function, such as refrigerator, TV, washing machine or furniture, etc.), game console, personal computer (PC), ATM or self-service machine and other terminal side equipment.
  • Tablet Personal Computer Tablet Personal Computer
  • laptop computer laptop computer
  • PDA Personal Digital Assistant
  • netbook ultra-mobile personal computer
  • UMPC mobile internet device
  • MID mobile internet device
  • AR augmented reality
  • VR virtual reality
  • robot wearable device
  • Wearable devices include: smart watches, smart bracelets, smart headphones, smart glasses, smart jewelry (smart bracelets, smart bracelets, smart rings, smart necklaces, smart anklets, smart anklets, etc.), smart wristbands, smart clothing, etc.
  • vehicle-mounted equipment can also be called vehicle-mounted terminal, vehicle-mounted controller, vehicle-mounted module, vehicle-mounted component, vehicle-mounted chip or vehicle-mounted unit, etc.
  • the network side device 12 may include an access network device or a core network device, wherein the access network device may also be referred to as a radio access network (RAN) device, a radio access network function or a radio access network unit.
  • RAN radio access network
  • the access network device may include a base station, a wireless local area network (WLAN) access point (AP) or a wireless fidelity (WiFi) node, etc.
  • the base station may be referred to as a Node B (NB), an evolved Node B (eNB), a next generation Node B (gNB), a New Radio Node B (NR Node B), an access point, a Relay Base Station (RBS), a Serving Base Station (SBS), a Base Transceiver Station (BTS), a radio base station, a radio transceiver, a Basic Service Set (BSS), an Extended Service Set (ESS), a Home Node B (HNB), a Home Evolved Node B, a Transmission Reception Point (TRP) or other appropriate terms in the field.
  • NB Node B
  • eNB evolved Node B
  • gNB next generation Node B
  • NR Node B New Radio Node B
  • RBS Relay Base Station
  • SBS Serving Base Station
  • the base station is not limited to specific technical terms. It should be noted that in the embodiments 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 network-side device sends CSI-Reference Signals (CSI-RS) on certain time-frequency resources in a certain time slot.
  • CSI-RS CSI-Reference Signals
  • 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 network-side device combines the channel information based on the codebook information fed back by the terminal, and uses this channel information for data precoding and multi-user scheduling before the terminal reports the CSI next time.
  • the terminal can change the PMI reported in each subband to the delay domain.
  • the PMI is reported in the frequency domain (delay domain). Since the channels in the delay domain are more concentrated, the PMIs with fewer delays can approximately represent the PMIs of all subbands. This can be regarded as compressing the delay domain information before reporting.
  • the network side device 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 device and report the coefficients corresponding to these ports.
  • the compression effect of channel characteristic information can be improved by compressing channel information using an AI unit.
  • the terminal can estimate the CSI reference signal (CSI Reference Signal, CSI-RS) or the tracking reference signal (Tracking Reference Signal, TRS), calculate according to the estimated channel information, obtain the calculated channel information, and then encode the calculated channel information or the original estimated channel information through an encoder to obtain the encoding result, and finally send the encoding result to the base station.
  • the base station can input the encoded result into the decoder after receiving it, and use the decoder to restore the channel information.
  • the CSI compression feedback scheme based on the neural network is that the terminal uses the encoding network to compress and encode the channel information, sends the compressed content to the base station, and decodes the compressed content using the decoding network at the base station to restore the channel information.
  • the decoding network of the base station and the encoding network of the terminal need to be jointly trained to achieve a reasonable matching degree.
  • the input of the encoding network is the channel information
  • the output is the encoding information, that is, the channel characteristic information.
  • the input of the decoding network is the encoding information, and the output is the restored channel information.
  • the terminal After the terminal estimates the CSI-RS, it performs singular value decomposition (SVD) on the channel matrix to obtain relatively orthogonal precoding matrices of multiple layers.
  • SVD singular value decomposition
  • the terminal feeds back the CSI, it needs to feed back the corresponding rank indicator (RI) and PMI.
  • RI represents the total number of selected layers
  • PMI is the precoding matrix of the corresponding layer.
  • the precoding matrix of each layer can independently obtain compressed channel feature information through a first AI unit, and then report the channel feature information of all layers together to the base station.
  • channel characteristic information with a larger payload can be used for a relatively important layer.
  • the longer the payload of the channel characteristic information the more accurate the channel information recovered by the network side device will be.
  • the accuracy of the channel information recovered by the network side device for the relatively important layer is improved; by reporting a smaller payload of channel characteristic information to a relatively unimportant layer, the overhead of reporting the channel characteristic information is reduced.
  • the AI unit in the embodiments of the present application may also be referred to as an AI model, an AI structure, etc., or the AI unit may also refer to a processing unit that can implement specific algorithms, formulas, processing procedures, capabilities, etc. related to AI, or the AI unit may be a processing method, algorithm, function, module or unit for a specific data set, or the AI unit may be a processing method, algorithm, function, module or unit running on AI-related hardware such as a graphics processing unit (GPU), a network processing unit (NPU), a tensor processing unit (TPU), an application specific integrated circuit (ASIC), etc., and the present application does not make specific limitations on this.
  • the specific data set includes the input or output of the AI unit.
  • the identifier of the AI unit may be an AI model identifier, an AI structure identifier, an AI algorithm identifier, or
  • the present application does not specifically limit the identification of the specific data set associated with the AI unit, or the identification of the specific scenario, environment, channel characteristics, equipment related to the AI, or the identification of the function, feature, capability or module related to the AI.
  • the AI unit is taken as a neural network in the embodiment of this application for illustration, but the specific type of the AI unit is not limited.
  • the neural network model includes an input layer, a hidden layer and an output layer, which can predict possible output results (Y) based on the input and output information ( X1 ⁇ Xn ) obtained by the input layer.
  • the neural network model is composed of a large number of neurons.
  • K the total number of input parameters.
  • 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 neural network 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 W and b to minimize the value of the above loss function. The smaller the loss value, the closer our model is to the actual 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 first AI unit i.e., the AI unit corresponding to the encoder, is deployed on the terminal side. Its input information is channel information, and its output information is channel feature information.
  • the second AI unit namely the AI unit corresponding to the decoder, is deployed on the network side. Its input information is channel characteristic information, and its output information is restored channel information.
  • FIG 4 An information processing method provided in an embodiment of the present application, the execution subject of which can be a terminal, wherein the terminal can be various types of terminals 11 listed in Figure 1, or other terminals except the terminal types listed in the embodiment shown in Figure 1, which are not specifically limited here.
  • the information processing method may include the following steps:
  • Step 401 The terminal obtains first information, wherein the first information indicates payload information of first channel characteristic information corresponding to at least one layer.
  • the first information may be a configuration or indication of a network-side device.
  • the first information may be agreed upon by a protocol.
  • a portion of the first information may be configuration or instruction of the network-side device, and another portion may be agreed upon by the protocol.
  • Step 402 The terminal performs a first process on the channel information of the target layer based on the first information using the target first AI unit to obtain the first channel characteristic information corresponding to the target layer, wherein the payload information of the first channel characteristic information corresponding to the target layer matches the output length of the target first AI unit, and the at least one layer includes the target layer.
  • the channel information of the target layer may be a precoding matrix of a layer.
  • the terminal measures or estimates the CSI-RS to obtain a channel matrix, and performs SVD decomposition on the channel matrix to obtain a relatively orthogonal precoding matrix of at least one layer.
  • the target layer may be each layer of the at least one relatively orthogonal layer, and based on the first information, the payload of the first channel characteristic information corresponding to each layer may be determined.
  • the payload of the first channel characteristic information matches the output length of the first AI unit.
  • the terminal can have at least two first AI units, and the output lengths of different first AI units can be different.
  • the payload of the first channel characteristic information of the target layer can be determined based on the first information, and then the target first AI unit that can output output information matching the payload can be obtained.
  • the target first AI unit can be associated with the target layer, and the target first AI unit can be used to perform the first processing on the channel information of the associated target layer.
  • the payload information of the first channel characteristic information corresponding to the target layer matches the output length of the target first AI unit, which may be the payload information of the first channel characteristic information corresponding to the target layer. is equal to or approximately equal to the output length of the target first AI unit.
  • the first processing may include at least one of compression, encoding, quantization, normalization and the like.
  • the output length of the first AI unit may be the number of bits.
  • the payload may also be the number of bits.
  • the output length of the first AI unit may be the number of floating-point numbers, and in this case, the payload may also be the number of floating-point numbers.
  • the network side device may indicate or pre-configure a quantization method, and the terminal quantizes the first channel characteristic information output by the first AI unit based on the quantization method indicated or pre-configured by the network side device, and sends the quantized first channel characteristic information to the network side device.
  • the first information includes at least one of the following:
  • the total amount of payload information corresponding to the candidate ranks one by one;
  • the total amount of payload information is the sum of the payloads of the first channel characteristic information corresponding to the at least one layer;
  • first relationship comprising a relationship between a payload of a first layer and a payload of a second layer, the at least one layer comprising the first layer and the second layer;
  • the preset maximum total payload amount information corresponding to the preset maximum rank is the preset maximum total payload amount information corresponding to the preset maximum rank.
  • the first information includes payload information corresponding one-to-one to the at least one layer, for example, the first information indicates the payload length corresponding to each layer, or the first information indicates the first AI unit corresponding to each layer, etc.
  • the terminal can use the first AI unit corresponding to the target layer or the first AI unit whose output information length matches the corresponding payload length as the target first AI unit.
  • the total amount of payload information corresponds to the candidate rank one-to-one
  • the candidate rank can be the range of ranks that the terminal can select configured by the network side device.
  • the payload information of the first channel characteristic information corresponding to each layer may be determined based on a preset rule, for example: determining that the payload of the first channel characteristic information corresponding to at least one layer is equal, that is, the first channel characteristic information corresponding to at least two layers evenly divides the total amount of payload.
  • a preset rule indicated by a network-side device or agreed upon by a protocol, such as a first relationship, the payload information of the first channel characteristic information corresponding to each layer may be determined.
  • the first relationship may include a payload relationship between layers, for example, the payload of the first channel characteristic information corresponding to the second layer is 60% of the payload of the first channel characteristic information corresponding to the first layer.
  • the total effective payload information is 500 bits
  • the first relationship is [0.3 0.3 0.2 0.2], that is, the payload of the first channel characteristic information corresponding to layer0 and layer1 accounts for 0.3 of the total effective payload, that is, 150 bits
  • the payload of the first channel characteristic information corresponding to layer2 and layer3 accounts for 0.2 of the total effective payload, that is, 100 bits.
  • the first information may directly indicate the sum of the payloads of the first channel characteristic information corresponding to the at least one layer.
  • the terminal may determine the payload information of the first channel characteristic information corresponding to each layer in a manner similar to that in the previous embodiment.
  • the first information may indicate a preset maximum total payload information corresponding to a preset maximum rank.
  • the preset maximum rank may be understood as the maximum value of the rank that the terminal can select. For example, assuming that the preset maximum rank is 4, the terminal can select a rank of 1, 2, 3 or 4.
  • the terminal may determine the total payload information of the first channel characteristic information corresponding to the at least one layer according to the selected target rank. For example, when the terminal determines that the target rank is less than the preset maximum rank, the terminal may determine that the total payload information of the first channel characteristic information corresponding to the at least one layer is all or part of the preset maximum payload information.
  • the terminal may determine the payload information of the first channel characteristic information corresponding to each layer in a manner similar to that in the previous embodiment.
  • the payload information of the first channel characteristic information corresponding to each layer can be determined based on a preset rule, for example: determining that the payload of the first channel characteristic information corresponding to at least one layer is equal, that is, the first channel characteristic information corresponding to at least two layers evenly divides the total amount of payload;
  • the payload information of the first channel characteristic information corresponding to each layer can be determined based on the rules agreed upon by the network side equipment or the protocol, for example: the payload information of the first channel characteristic information corresponding to each layer is determined based on the first relationship.
  • the method further includes:
  • the terminal determines the payload corresponding to the at least one layer in a one-to-one manner according to the first relationship and the total payload amount information.
  • the first relationship includes the relationship between the payload of the first layer and the payload of the second layer, and the at least one layer includes the first layer and the second layer.
  • the first relationship indicates that the payload of the first channel characteristic information corresponding to the first layer is 20% larger than the payload of the first channel characteristic information corresponding to the second layer, and the payload of the first channel characteristic information corresponding to the second layer is 10% larger than the payload of the first channel characteristic information corresponding to the third layer, and so on.
  • the method when the first information includes the first relationship and information about the total amount of payload corresponding one-to-one to the candidate ranks, the method further includes:
  • the terminal determines the target effective load corresponding to the target rank according to the total effective load information corresponding to the candidate ranks one by one.
  • Total load information wherein the target rank is a rank of a target channel corresponding to the at least one layer;
  • the terminal determines a payload corresponding to the at least one layer in a one-to-one manner according to the first relationship and the target payload total amount information.
  • the process of the terminal determining the payload corresponding one-to-one to the at least one layer according to the first relationship and the target payload total amount information is the same or similar to the process in the previous embodiment: the terminal determines the payload corresponding one-to-one to the at least one layer according to the first relationship and the target payload total amount information, and will not be repeated here.
  • the method further includes:
  • the terminal determines that the sum of the payloads of the at least one layer is equal to the preset maximum payload total amount information, or equal to the product of the preset maximum payload total amount information and a first value, wherein the first value is a ratio of a target rank to the preset maximum rank, and the target rank is a rank of a target channel corresponding to the at least one layer;
  • the terminal determines a payload corresponding to the at least one layer in a one-to-one manner according to the first relationship and the sum of the payloads of the at least one layer.
  • the first channel characteristic information corresponding to the at least one layer can be proportionally expanded, for example: expanded to X/Y times, where X represents the preset maximum rank and Y represents the target rank.
  • the terminal also sends the target rank or the identifier of the target rank to the network side to assist the network side device in determining the payload of the first channel characteristic information corresponding to each layer.
  • the payload information includes at least one of the following:
  • an identifier of a first data set the first data set being used to train at least one first AI unit, the output information of different first AI units having different payload lengths, the at least one first AI unit including the target first AI unit;
  • the identifier of the target first AI unit is the identifier of the target first AI unit.
  • the payload length may include the number of floating point numbers or the number of bits of the output information of the corresponding first AI unit.
  • the first data set is used to train at least one first AI unit.
  • the terminal can determine a first AI unit trained based on the first data set as a target AI unit, and the output length of the target AI unit is the payload length of the first channel feature information corresponding to the target layer, wherein the output length of the target AI unit refers to the length of the output information of the target AI unit; when the first data set is used to train at least two first AI units, the terminal can determine the target AI unit from the at least two first AI units based on a preset rule.
  • the payload information may include the payload length and the identifier of the first data set.
  • the terminal obtains at least two first AI units trained based on the first data set, and each first AI unit has its own output length.
  • the terminal can determine the payload length of the first channel characteristic information corresponding to the target layer based on the first information, and select a first AI unit whose output length is equal to or close to the length from at least two first AI units as the target AI unit.
  • the payload information may directly indicate the target first AI unit.
  • the payload length is the payload of the output information of the target first AI unit.
  • the first AI unit for obtaining the first channel characteristic information of each layer can be determined accordingly.
  • the terminal performs a first processing on the channel information of the target layer using the target first AI unit based on the first information to obtain the first channel feature information corresponding to the target layer, including:
  • the terminal determines, based on the first information, a target payload corresponding to a target layer
  • the terminal obtains a target first AI unit whose output information length matches the target payload
  • the terminal determines the first channel characteristic information of the target layer according to the channel information of the target first AI unit and the target layer.
  • the target payload corresponding to the target layer can be understood as: the payload of the first channel characteristic information corresponding to the target layer.
  • the target first AI unit may be an AI model.
  • the terminal determines the first channel characteristic information of the target layer based on the channel information of the target first AI unit and the target layer.
  • the channel information of the target layer may be input into the AI model, and the first channel characteristic information of the target layer output by the AI model is obtained.
  • the terminal determines first channel characteristic information of the target layer according to the target first AI unit and the channel information of the target layer, including:
  • the terminal obtains second channel characteristic information according to the channel information of the target first AI unit and the target layer;
  • the terminal determines that the first channel characteristic information includes the second channel characteristic information; or,
  • the terminal performs a first post-processing on the second channel characteristic information to obtain first channel characteristic information matching the effective load length corresponding to the target layer;
  • the terminal performs second post-processing on the second channel characteristic information to obtain first channel characteristic information that matches the effective payload length corresponding to the target layer.
  • the target first AI unit when the output length of the target first AI unit is the same as the payload corresponding to the target layer, the target first AI unit can be directly used to compress the channel information of the target layer to obtain the first channel feature information that matches the payload corresponding to the target layer.
  • the output length of the target first AI unit when the output length of the target first AI unit is greater than the payload corresponding to the target layer, the target first AI unit is used to compress the channel information of the target layer to obtain the second channel characteristic information, the length of the second channel characteristic information will be greater than the payload corresponding to the target layer.
  • the second channel characteristic information is post-processed for the first time to obtain the first channel characteristic information that matches the payload corresponding to the target layer.
  • the first post-processing may be a process capable of reducing the payload of the second channel characteristic information.
  • the first post-processing includes at least one of the following:
  • adjusting the quantization rule for the first channel characteristic information may be adjusting the quantization rule for the first channel characteristic information to a quantization rule with lower quantization accuracy, wherein the number of bits of the first channel characteristic information quantized based on the quantization rule with lower quantization accuracy is smaller.
  • the output length of the target first AI unit when the output length of the target first AI unit is smaller than the payload corresponding to the target layer, after the target first AI unit is used to compress the channel information of the target layer to obtain the second channel characteristic information, the length of the second channel characteristic information will be smaller than the payload corresponding to the target layer.
  • the second channel characteristic information is subjected to a second post-processing to obtain the first channel characteristic information that matches the payload corresponding to the target layer.
  • the second post-processing may be a process capable of increasing the payload of the second channel characteristic information.
  • the second post-processing includes at least one of the following:
  • the process repeats in a loop.
  • the zero-padding process may be to pad the second channel characteristic information with zeros so that its payload reaches the payload corresponding to the target layer.
  • the cyclic repetition process may be to repeat part of the information in the second channel characteristic information to obtain the first channel characteristic information that matches the payload corresponding to the target layer.
  • the first channel characteristic information may include: the second channel characteristic information + the first 50 bits of the second channel characteristic information.
  • the length of the second channel characteristic information can be adjusted based on the size relationship between the length of the second channel characteristic information obtained by the target first AI unit and the payload corresponding to the target layer, so that the length of the first channel characteristic information reported by the terminal is consistent with the payload corresponding to the target layer.
  • the method further includes:
  • the terminal sends second information to the network side device, wherein the second information includes the first channel characteristic information corresponding to the at least one layer.
  • the terminal may uniformly report the first channel characteristic information of all layers of a complete channel.
  • the second information further includes a target rank or identification information of the target rank, and the target rank is the rank of a target channel corresponding to the at least one layer.
  • the target rank selected by the terminal to the network device is the number of layers included in the target channel.
  • the network device can use this as a basis for determining the number of layers corresponding to the received first channel characteristic information.
  • the network side device can determine the first channel characteristic information of each layer according to the target rank.
  • the terminal can determine the payload information of the first channel characteristic information corresponding to each layer based on the first information, so as to process the channel information of a layer using the first AI unit matching the payload information to obtain the channel characteristic information that conforms to the payload information.
  • channel characteristic information of different payloads can be reported to the network side device, so that the length of the channel characteristic information of different layers can be configured more targetedly, while reducing the overhead of reporting the channel characteristic information, the accuracy of the channel characteristic information of the layer with higher importance can be improved in a targeted manner, for example: the first information indicates that the payload of the channel characteristic information of the layer with higher importance, higher intensity or higher concentration is greater than the payload of the channel characteristic information of the layer with lower importance, lower intensity or lower concentration, so that the channel characteristic information of the layer with higher importance, higher intensity or higher concentration reported by the terminal is more accurate than the channel characteristic information of the layer with lower importance, lower intensity or lower concentration.
  • FIG 5 is another information processing method provided in an embodiment of the present application.
  • the executor of the information processing method is a network side device, which may include the network side device listed in the embodiment shown in Figure 1, or other network side devices, which are not specifically limited here.
  • the information processing method may include the following steps:
  • Step 501 the network side device sends the first information to the terminal, wherein the first information indicates the payload information of the first channel characteristic information corresponding to at least one layer; wherein the first information is used by the terminal to determine the payload of the first channel characteristic information corresponding to the target layer, the first channel characteristic information corresponding to the target layer is obtained by performing a first processing on the channel information of the target layer based on the target first AI unit corresponding to the target layer, the payload information of the first channel characteristic information corresponding to the target layer matches the output length of the target first AI unit, and the at least one layer includes the target layer.
  • first information, first channel characteristic information, payload information and first AI unit have the same meanings as the first information, first channel characteristic information, payload information and first AI unit in the method embodiment shown in Figure 3, and are not repeated here.
  • the network side device configures or indicates the first information to the terminal, so that when the terminal selects a high rank scenario, the terminal reports the channel characteristic information of each layer based on the payload configured or indicated by the network side device.
  • the network side device can instruct the terminal to report channel characteristic information of different effective loads, and then can more specifically configure or indicate the length of the channel characteristic information of different layers, while reducing the overhead of reporting channel characteristic information, and can also specifically improve the accuracy of the channel characteristic information of layers with higher importance, higher intensity, or higher concentration.
  • the payload of the channel characteristic information of a layer with higher importance, higher intensity, or higher concentration is greater than the payload of the channel characteristic information of a layer with lower importance, lower intensity, or lower concentration, so that the channel characteristic information of the layer with higher importance, higher intensity, or higher concentration reported by the terminal is more accurate than the channel characteristic information of the layer with lower importance, lower intensity, or lower concentration, and the network side device has a higher importance, higher intensity, or higher concentration in the channel information recovered based on the second AI unit.
  • the channel information of a high-order layer is also more accurate than the channel information of a layer with less importance, less strength, or less concentration.
  • the first information includes at least one of the following:
  • the total amount of payload information corresponding to the candidate ranks one by one;
  • the total amount of payload information is the sum of the payloads of the first channel characteristic information corresponding to the at least one layer;
  • a first relationship includes a relationship between a payload of a first layer and a payload of a second layer, and the at least one layer includes the first layer and the second layer.
  • the payload information includes at least one of the following:
  • an identifier of a first data set the first data set being used to train at least one first AI unit, the output information of different first AI units having different payload lengths, the at least one first AI unit including the target first AI unit;
  • the identifier of the target first AI unit is the identifier of the target first AI unit.
  • the payload length includes at least one of the following:
  • the method further includes:
  • the network side device receives second information from the terminal, wherein the second information includes the first channel characteristic information corresponding to the at least one layer;
  • the method further comprises:
  • the network side device performs a second process on the first channel characteristic information corresponding to the at least one layer based on the second AI unit to obtain the channel information corresponding to the at least one layer.
  • the second AI unit is an AI unit corresponding to the decoder, and the second processing may include: at least one of decoding, dequantization, decompression, etc.
  • the second AI unit matches the first AI unit of the terminal, and the second processing may be the inverse processing of the first processing corresponding to the first AI unit.
  • the second AI unit can correspond one-to-one to the first AI unit.
  • the first channel characteristic information obtained based on the target first AI unit can be decoded by the target second AI unit corresponding to the target first AI unit to obtain the channel information corresponding to the target layer.
  • the input information of the second AI unit may be channel information of the entire channel, for example, first channel feature information of all layers corresponding to the target channel.
  • the second information also includes the target rank or identification information of the target rank, wherein the target rank is the rank of the target channel corresponding to the at least one layer.
  • the network side device may determine the first channel characteristics of each layer based on the target rank: For example: when the network side sets the preset maximum total payload information corresponding to the preset maximum rank, and the protocol stipulates the first relationship, if the terminal determines that the sum of the payloads of at least one layer is equal to the product of the preset maximum total payload information and the first value, the network side device can determine the first channel characteristic information of each layer according to the target rank, using the principle that the terminal determines the payload corresponding to the at least one layer one-to-one according to the first relationship and the sum of the payloads of the at least one layer, and then uses the corresponding second AI unit to perform a second processing on the first channel characteristic information of each layer to restore the channel information of each layer.
  • the network side device performs a second processing on the first channel feature information corresponding to the at least one layer based on the second AI unit to obtain the channel information corresponding to the at least one layer, including:
  • the network side device acquires first channel characteristic information corresponding to the target layer from the second information based on the first information
  • the network-side device determines a second AI unit according to the first information
  • the network side device determines the channel information corresponding to the target layer based on the second AI unit and the first channel characteristic information corresponding to the target layer.
  • the network side device determines the second AI unit based on the first information, which may be: the network side device determines that the payload of the input information of the second AI unit matches the payload of the first channel characteristic information corresponding to the at least one layer in the first information.
  • the input information length of the second AI unit matches the payload information of the first channel characteristic information corresponding to the target layer; or,
  • the identifier of the first data set in the first information indicates the data set used to train the second AI unit;
  • the first AI unit identifier in the first information is associated with the second AI unit.
  • the network side device determines the second AI unit according to the first information in a manner similar to the manner in which the terminal determines the first AI unit corresponding to each layer according to the first information, that is, the network side device determines that the target second AI unit corresponding to the target layer satisfies: the input length of the target second AI unit matches the payload of the first channel characteristic information corresponding to the target layer.
  • the network side device determines the second AI unit based on the first information, which may be: the network side device determines that the input length of the second AI unit matches the sum of the payloads of the first channel characteristic information of all layers of the target channel.
  • the second AI unit may be an AI model.
  • the network side device determines the channel information corresponding to the target layer based on the second AI unit and the first channel characteristic information corresponding to the target layer.
  • the method may be: the network side device inputs the first channel characteristic information corresponding to the target layer into the AI model, and obtains the channel information corresponding to the target layer output by the AI model.
  • the network side device can configure or indicate the first information to the terminal so that the terminal compresses the channel information of each layer according to the payload configured or indicated by the network side device, which has similar beneficial effects as the method embodiment shown in Figure 4. To avoid repetition, it will not be repeated here.
  • the information processing method provided in the embodiment of the present application is illustrated by example:
  • the maximum rank of the base station configuration is 4;
  • the terminal can perform rank adaptation in 1, 2, 3 and 4;
  • the maximum payload indicated by the base station is 500 bits.
  • the payload relationship between each layer can be indicated by the base station or agreed upon by the protocol;
  • the terminal calculates the payload of layer0 as 150 bits, the payload of layer1 as 150 bits, and the payloads of layer2 and layer3 as 100 bits.
  • the base station may indicate the relationship between the payload corresponding to each rank and the maximum payload, for example, rank 3 is 80% of rank 4, rank 2 is 50% of rank 4, and rank 1 is 40% of rank 4.
  • the actual payload determined by the terminal can be: 150 bits for layer 0 and layer 1, a total of 300 bits; or 250 bits for layer 0 and layer 1, a total of 500 bits;
  • the terminal uses the first AI unit with an output length of 150 bits or 250 bits to compress the channel information of layer0 and layer1 respectively, and obtains two 150 bits or 250 bits of first channel feature information.
  • 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.
  • the information processing device 600 provided in the embodiment of the present application may be a device in a terminal. As shown in FIG6 , the information processing device 600 may include the following modules:
  • a first acquisition module 601 is used to acquire first information, wherein the first information indicates payload information of first channel characteristic information corresponding to at least one layer;
  • the first processing module 602 is used to perform a first processing on the channel information of the target layer based on the first information using the target first AI unit to obtain the first channel characteristic information corresponding to the target layer, wherein the payload information of the first channel characteristic information corresponding to the target layer matches the output length of the target first AI unit, and the at least one layer includes the target layer.
  • the first information includes at least one of the following:
  • the total amount of payload information corresponding to the candidate ranks one by one;
  • the total amount of payload information is the sum of the payloads of the first channel characteristic information corresponding to the at least one layer;
  • first relationship comprising a relationship between a payload of a first layer and a payload of a second layer, the at least one layer comprising the first layer and the second layer;
  • the preset maximum total payload amount information corresponding to the preset maximum rank is the preset maximum total payload amount information corresponding to the preset maximum rank.
  • the information processing device 600 further includes:
  • the first determination module is used to determine the payload corresponding to the at least one layer one by one according to the first relationship and the total payload information.
  • the information processing device 600 further includes:
  • a second determination module is configured to determine target payload total amount information corresponding to a target rank according to payload total amount information corresponding one-to-one to candidate ranks, wherein the target rank is a rank of a target channel corresponding to the at least one layer;
  • the third determination module is used to determine the payload corresponding to the at least one layer one by one according to the first relationship and the target payload total amount information.
  • the information processing device 600 further includes:
  • a fourth determination module configured to determine that the sum of the payloads of the at least one layer is equal to the preset maximum payload total amount information, or equal to the product of the preset maximum payload total amount information and a first value, wherein the first value is a ratio of a target rank to the preset maximum rank, and the target rank is a rank of a target channel corresponding to the at least one layer;
  • a fifth determination module is used to determine the payload corresponding to the at least one layer one by one according to the first relationship and the sum of the payloads of the at least one layer.
  • the payload information includes at least one of the following:
  • an identifier of a first data set the first data set being used to train at least one first AI unit, the output information of different first AI units having different payload lengths, the at least one first AI unit including the target first AI unit;
  • the identifier of the target first AI unit is the identifier of the target first AI unit.
  • the payload length includes at least one of the following:
  • the first processing module 602 includes:
  • a first determining unit configured to determine a target payload corresponding to a target layer based on the first information
  • a first acquisition unit configured to acquire a target first AI unit whose output information length matches the target payload
  • the second determining unit is used to determine the first channel characteristic information of the target layer according to the channel information of the target first AI unit and the target layer.
  • the second determining unit includes:
  • a first determining subunit configured to obtain second channel characteristic information according to the channel information of the target first AI unit and the target layer;
  • a second determining subunit is configured to determine that the first channel characteristic information includes the second channel characteristic information when the second channel characteristic information is equal to the effective load length corresponding to the target layer;
  • a first processing subunit configured to perform a first post-processing on the second channel characteristic information to obtain first channel characteristic information matching the payload length corresponding to the target layer when the second channel characteristic information is greater than the payload length corresponding to the target layer;
  • the second processing subunit is used to perform second post-processing on the second channel characteristic information when the second channel characteristic information is smaller than the effective payload length corresponding to the target layer, so as to obtain first channel characteristic information matching the effective payload length corresponding to the target layer.
  • the first post-processing includes at least one of the following:
  • the second post-processing includes at least one of the following:
  • the process repeats in a loop.
  • the information processing device 600 further includes:
  • the second sending module is used to send second information to the network side device, wherein the second information includes the first channel characteristic information corresponding to the at least one layer.
  • the second information also includes a target rank or identification information of the target rank, and the target rank is the rank of a target channel corresponding to the at least one layer.
  • the information processing device 600 in the embodiment of the present application may be an electronic device, such as an electronic device with an operating system, or a component in an electronic device, such as an integrated circuit or a chip.
  • the electronic device may be a terminal.
  • the terminal may include but is not limited to the types of the terminal 11 listed above, and the embodiment of the present application does not specifically limit this.
  • the information processing device 600 provided in the embodiment of the present application can implement each process implemented by the method embodiment shown in Figure 4 and achieve the same technical effect. To avoid repetition, it will not be repeated here.
  • Another information processing device provided in an embodiment of the present application may be a device in a network-side device. As shown in FIG. 7 , the information processing device 700 may include the following modules:
  • a first sending module 701 is configured to send first information to a terminal, wherein the first information indicates payload information of first channel characteristic information corresponding to at least one layer;
  • the first information is used by the terminal to determine the payload of the first channel characteristic information corresponding to the target layer
  • the first channel characteristic information corresponding to the target layer is obtained by performing a first processing on the channel information of the target layer based on the target first AI unit corresponding to the target layer
  • the payload information of the first channel characteristic information corresponding to the target layer matches the output length of the target first AI unit
  • the at least one layer includes the target layer.
  • the first information includes at least one of the following:
  • the total amount of payload information corresponding to the candidate ranks one by one;
  • the total amount of payload information is the sum of the payloads of the first channel characteristic information corresponding to the at least one layer;
  • a first relationship includes a relationship between a payload of a first layer and a payload of a second layer, and the at least one layer includes the first layer and the second layer.
  • the payload information includes at least one of the following:
  • an identifier of a first data set the first data set being used to train at least one first AI unit, the output information of different first AI units having different payload lengths, the at least one first AI unit including the target first AI unit;
  • the identifier of the target first AI unit is the identifier of the target first AI unit.
  • the payload length includes at least one of the following:
  • the information processing device 700 further includes:
  • a receiving module configured to receive second information from the terminal, wherein the second information includes the first channel characteristic information corresponding to the at least one layer;
  • the information processing device 700 further includes:
  • the second processing module is used to perform a second processing on the first channel characteristic information corresponding to the at least one layer based on the second AI unit to obtain the channel information corresponding to the at least one layer.
  • the second information also includes the target rank or identification information of the target rank, wherein the target rank is the rank of the target channel corresponding to the at least one layer.
  • the second processing module includes:
  • an acquiring unit configured to acquire first channel characteristic information corresponding to a target layer from the second information based on the first information
  • a third determining unit configured to determine a second AI unit according to the first information
  • the fourth determination unit is used to determine the channel information corresponding to the target layer according to the second AI unit and the first channel characteristic information corresponding to the target layer.
  • the information processing device 700 provided in the embodiment of the present application can implement each process implemented by the method embodiment shown in Figure 5 and achieve the same technical effect. To avoid repetition, it will not be repeated here.
  • the embodiment of the present application further provides a communication device 800, including a processor 801 and a memory 802, wherein the memory 802 stores a program or instruction that can be run on the processor 801.
  • the communication device 800 is a terminal
  • the program or instruction is executed by the processor 801 to implement the various steps of the information processing method embodiment shown in FIG4 , and can achieve the same technical effect.
  • the communication device 800 is a first device
  • the program or instruction is executed by the processor 801 to implement the various steps of the information processing method embodiment shown in FIG5 , and can achieve the same technical effect. To avoid repetition, it will not be repeated here.
  • the present application also provides a terminal, including 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 steps in the method embodiment shown in FIG4.
  • the embodiment corresponds to the above-mentioned terminal side method embodiment, and each implementation process and implementation mode of the above-mentioned method embodiment can be applied to the terminal embodiment and can achieve the same technical effect.
  • Figure 9 is a schematic diagram of the hardware structure of a terminal implementing the embodiment of the present application.
  • the terminal 900 includes but is not limited to: a radio frequency unit 901, a network module 902, an audio output unit 903, an input unit 904, a sensor 905, a display unit 906, a user input unit 907, an interface unit 908, a memory 909 and at least some of the components of a processor 910.
  • the terminal 900 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 910 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 FIG9 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 904 may include a graphics processing unit (GPU) 9041 and a microphone 9042, and the graphics processing unit 9041 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 906 may include a display panel 9061, and the display panel 9061 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc.
  • the user input unit 907 includes a touch panel 9071 and at least one of other input devices 9072.
  • the touch panel 9071 is also called a touch screen.
  • the touch panel 9071 may include two parts: a touch detection device and a touch controller.
  • Other input devices 9072 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 901 can transmit the data to the processor 910 for processing; in addition, the RF unit 901 can send uplink data to the network side device.
  • the RF unit 901 includes but is not limited to an antenna, an amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, etc.
  • the memory 909 can be used to store software programs or instructions and various data.
  • the memory 909 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 909 may include a volatile memory or a non-volatile memory.
  • 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).
  • RAM random access memory
  • SRAM static random access memory
  • DRAM dynamic random access memory
  • SDRAM synchronous dynamic random access memory
  • DDRSDRAM double data rate synchronous dynamic random access memory
  • ESDRAM enhanced synchronous dynamic random access memory
  • SLDRAM synchronous link dynamic random access memory
  • DRRAM direct memory bus random access memory
  • the processor 910 may include one or more processing units; optionally, the processor 910 integrates an application processor and a modulation
  • the demodulation processor wherein the application processor mainly processes operations related to the operating system, user interface and application programs, and the modulation and demodulation processor mainly processes wireless communication signals, such as the baseband processor. It is understandable that the above-mentioned modulation and demodulation processor may not be integrated into the processor 910.
  • the radio frequency unit 901 is used to obtain first information, wherein the first information indicates payload information of first channel characteristic information corresponding to at least one layer;
  • Processor 910 is used to perform first processing on the channel information of the target layer using the target first AI unit based on the first information to obtain the first channel characteristic information corresponding to the target layer, wherein the payload information of the first channel characteristic information corresponding to the target layer matches the output length of the target first AI unit, and the at least one layer includes the target layer.
  • the first information includes at least one of the following:
  • the total amount of payload information corresponding to the candidate ranks one by one;
  • the total amount of payload information is the sum of the payloads of the first channel characteristic information corresponding to the at least one layer;
  • first relationship comprising a relationship between a payload of a first layer and a payload of a second layer, the at least one layer comprising the first layer and the second layer;
  • the preset maximum total payload amount information corresponding to the preset maximum rank is the preset maximum total payload amount information corresponding to the preset maximum rank.
  • the processor 910 is further used to determine the payload corresponding one-to-one to the at least one layer according to the first relationship and the total payload information.
  • the processor 910 is further configured to:
  • Target payload total amount information corresponding to a target rank according to the payload total amount information corresponding one-to-one to the candidate ranks, wherein the target rank is a rank of a target channel corresponding to the at least one layer;
  • a payload corresponding to the at least one layer is determined.
  • the processor 910 is further configured to:
  • the first value is a ratio of a target rank to the preset maximum rank, and the target rank is a rank of a target channel corresponding to the at least one layer;
  • a payload corresponding one-to-one to the at least one layer is determined.
  • the payload information includes at least one of the following:
  • an identifier of a first data set the first data set being used to train at least one first AI unit, wherein output information of different first AI units has different payload lengths, and the at least one first AI unit includes the target first AI unit;
  • the identifier of the target first AI unit is the identifier of the target first AI unit.
  • the payload length includes at least one of the following:
  • the processor 910 performs, based on the first information, a first target AI unit to perform a first processing on the channel information of the target layer to obtain the first channel feature information corresponding to the target layer, including:
  • the determining, according to the target first AI unit and the channel information of the target layer, the first channel characteristic information of the target layer executed by the processor 910 includes:
  • the second channel characteristic information is equal to the payload length corresponding to the target layer, determining that the first channel characteristic information includes the second channel characteristic information; or,
  • a second post-processing is performed on the second channel characteristic information to obtain first channel characteristic information that matches the effective payload length corresponding to the target layer.
  • the first post-processing includes at least one of the following:
  • the second post-processing includes at least one of the following:
  • the process repeats in a loop.
  • the radio frequency unit 901 is also used to send second information to the network side device, wherein the second information includes the first channel characteristic information corresponding to the at least one layer.
  • the second information also includes a target rank or identification information of the target rank, and the target rank is the rank of a target channel corresponding to the at least one layer.
  • the embodiment of the present application also provides a network side device, including a processor and a communication interface, the communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement the steps of the method embodiment shown in Figure 5.
  • the network side device embodiment corresponds to the above-mentioned network side device method embodiment, and each implementation process and implementation method of the above-mentioned method embodiment can be applied to the network side device embodiment, and can achieve the same technical effect.
  • the embodiment of the present application also provides a network side device.
  • the network side device 1000 includes: an antenna 1001, a radio frequency device 1002, a baseband device 1003, a processor 1004 and a memory 1005.
  • the antenna 1001 is connected to the radio frequency device 1002.
  • the radio frequency device 1002 receives information through the antenna 1001 and sends the received information to the baseband device 1003 for processing.
  • the baseband device 1003 processes the information to be sent and sends it to the radio frequency device 1002.
  • the radio frequency device 1002 processes the received information and sends it out through the antenna 1001.
  • the method executed by the network-side device in the above embodiment may be implemented in the baseband device 1003, which includes a baseband processor.
  • the baseband device 1003 may include, for example, at least one baseband board, on which a plurality of chips are arranged, as shown in FIG10 , wherein one of the chips is, for example, a baseband processor, which is connected to the memory 1005 through a bus interface to call a program in the memory 1005 and execute the network device operations shown in the above method embodiment.
  • the network side device may also include a network interface 1006, which is, for example, a Common Public Radio Interface (CPRI).
  • CPRI Common Public Radio Interface
  • the network side device 1000 of the embodiment of the present application also includes: instructions or programs stored in the memory 1005 and executable on the processor 1004.
  • the processor 1004 calls the instructions or programs in the memory 1005 to execute the method executed by each module shown in Figure 7 and achieves 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 4 or Figure 5 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 readable storage medium may be a non-transient readable storage medium.
  • An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the method embodiment shown in Figure 4 or Figure 5, and can achieve the same technical effect. To avoid repetition, it will not be repeated 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 embodiments shown in Figures 4 or 5, 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 processing method shown in Figure 4, and the network side device can be used to execute the steps of the information processing method shown in Figure 5.

Landscapes

  • Mobile Radio Communication Systems (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)
  • Communication Control (AREA)

Abstract

本申请公开了一种信息处理方法、信息传输方法、装置、终端及网络侧设备，属于通信技术领域，本申请实施例的信息处理方法包括：终端获取第一信息，其中，所述第一信息指示至少一个layer对应的第一信道特征信息的有效载荷信息；所述终端基于所述第一信息，采用目标第一AI单元对目标layer的信道信息进行第一处理，得到所述目标layer对应的所述第一信道特征信息，其中，所述目标layer对应的第一信道特征信息的有效载荷信息与所述目标第一AI单元的输出长度匹配，所述至少一个layer包括所述目标layer。

Description

信息处理方法、信息传输方法、装置、终端及网络侧设备
相关申请的交叉引用
本申请主张在2023年4月24日在中国提交的中国专利申请No.202310455140.7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，具体涉及一种信息处理方法、信息传输方法、装置、终端及网络侧设备。
背景技术
在相关技术中，终端可以采用编码人工智能(Artificial Intelligence，AI)模型对信道信息进行压缩，并上报压缩后的信道特征信息，网络侧则可以采用解码AI模型对终端上报的信道特征信息进行恢复处理，得到终端信道信息，这样，能够降低终端上报信道信息的开销。
在高秩(rank)场景下，终端估计信道状态信息-参考信号(Channel State Information-Reference Signal，CSI-RS)之后，对信道矩阵进行奇异值分解(Singular Value Decomposition，SVD)，得到相对正交的多个层(layer)的预编码矩阵。每个layer的预编码矩阵可以独立通过一个编码AI模型得到压缩后的结果，然后将所有layer的压缩结果一起上报给基站。
但是，不同layer的预编码矩阵采用同一个编码AI模型进行压缩后得到的压缩结果的长度是相同的，这样，会造成部分重要的layer的压缩结果的精确度不够或造成部分不重要的layer的压缩结果的长度过长。
发明内容
本申请实施例提供一种信息处理方法、信息传输方法、装置、终端及网络侧设备，终端可以基于第一信息调整各个layer对应的编码AI模型或编码AI模型的输出长度，从而能够更加有灵活地调整不同layer的压缩结果的长度。
第一方面，提供了一种信息处理方法，该方法包括：
终端获取第一信息，其中，所述第一信息指示至少一个layer对应的第一信道特征信息的有效载荷信息；
所述终端基于所述第一信息，采用目标第一AI单元对目标layer的信道信息进行第一处理，得到所述目标layer对应的所述第一信道特征信息，其中，所述目标layer对应的第一信道特征信息的有效载荷信息与所述目标第一AI单元的输出长度匹配，所述至少一个 layer包括所述目标layer。
第二方面，提供了一种信息处理方法，该方法包括：
网络侧设备向终端发送第一信息，其中，所述第一信息指示至少一个layer对应的第一信道特征信息的有效载荷信息；
其中，所述第一信息用于所述终端确定目标layer对应的第一信道特征信息的有效载荷，所述目标layer对应的第一信道特征信息基于所述目标layer对应的目标第一AI单元对所述目标layer的信道信息进行第一处理得到，所述目标layer对应的第一信道特征信息的有效载荷信息与所述目标第一AI单元的输出长度匹配，所述至少一个layer包括所述目标layer。
第三方面，提供了一种信息处理装置，包括：
第一获取模块，用于获取第一信息，其中，所述第一信息指示至少一个layer对应的第一信道特征信息的有效载荷信息；
第一处理模块，用于基于所述第一信息，采用目标第一AI单元对目标layer的信道信息进行第一处理，得到所述目标layer对应的所述第一信道特征信息，其中，所述目标layer对应的第一信道特征信息的有效载荷信息与所述目标第一AI单元的输出长度匹配，所述至少一个layer包括所述目标layer。
第四方面，提供了一种信息处理装置，包括：
第一发送模块，用于向终端发送第一信息，其中，所述第一信息指示至少一个layer对应的第一信道特征信息的有效载荷信息；
其中，所述第一信息用于所述终端确定目标layer对应的第一信道特征信息的有效载荷，所述目标layer对应的第一信道特征信息基于所述目标layer对应的目标第一AI单元对所述目标layer的信道信息进行第一处理得到，所述目标layer对应的第一信道特征信息的有效载荷信息与所述目标第一AI单元的输出长度匹配，所述至少一个layer包括所述目标layer。
第五方面，提供了一种终端，该终端包括处理器和存储器，所述存储器存储可在所述处理器上运行的程序或指令，所述程序或指令被所述处理器执行时实现如第一方面所述的方法的步骤。
第六方面，提供了一种终端，包括处理器及通信接口，其中，所述通信接口用于获取第一信息，其中，所述第一信息指示至少一个layer对应的第一信道特征信息的有效载荷信息；所述处理器用于基于所述第一信息，采用目标第一AI单元对目标layer的信道信息进行第一处理，得到所述目标layer对应的所述第一信道特征信息，其中，所述目标layer对应的第一信道特征信息的有效载荷信息与所述目标第一AI单元的输出长度匹配，所述至少一个layer包括所述目标layer。
第七方面，提供了一种网络侧设备，该网络侧设备包括处理器和存储器，所述存储器存储可在所述处理器上运行的程序或指令，所述程序或指令被所述处理器执行时实现如第二方面所述的方法的步骤。
第八方面，提供了一种网络侧设备，包括处理器及通信接口，所述通信接口用于向终 端发送第一信息，其中，所述第一信息指示至少一个layer对应的第一信道特征信息的有效载荷信息；其中，所述第一信息用于所述终端确定目标layer对应的第一信道特征信息的有效载荷，所述目标layer对应的第一信道特征信息基于所述目标layer对应的目标第一AI单元对所述目标layer的信道信息进行第一处理得到，所述目标layer对应的第一信道特征信息的有效载荷信息与所述目标第一AI单元的输出长度匹配，所述至少一个layer包括所述目标layer。
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方法的步骤，或者实现如第二方面所述的方法的步骤。
第十方面，提供了一种无线通信系统，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方法的步骤，所述网络侧设备可用于执行如第二方面所述的方法的步骤。
第十一方面，提供了一种芯片，所述芯片包括处理器和通信接口，所述通信接口和所述处理器耦合，所述处理器用于运行程序或指令，实现如第一方面所述的方法，或实现如第二方面所述的方法。
第十二方面，提供了一种计算机程序/程序产品，所述计算机程序/程序产品被存储在存储介质中，所述程序/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处理方法的步骤，或者实现如第二方面所述的信息处理方法的步骤。
在本申请实施例中，终端可以基于第一信息确定每一个layer对应的第一信道特征信息的有效载荷信息，从而采用与该有效载荷信息匹配的第一AI单元对一个layer的信道信息进行处理，得到符合该有效载荷信息的信道特征信息。这样，对于不同的layer，终端可以向网络侧设备上报不同有效载荷的信道特征信息，进而能够更加灵活地调整不同layer的信道特征信息的长度，在降低上报信道特征信息的开销的同时，还能够有针对性地提升重要程度较高的layer的信道特征信息的精确度，例如：通过第一信息指示重要程度较高或强度较高或集中度较高的layer的信道特征信息的有效载荷大于重要程度较低或强度较低或集中度较低的layer的信道特征信息的有效载荷，使得终端上报的重要程度较高或强度较高或集中度较高的layer的信道特征信息比重要程度较低或强度较低或集中度较低的layer的信道特征信息更精确。
附图说明
图1是本申请实施例能够应用的无线通信系统的结构示意图；
图2是神经网络模型的架构示意图；
图3是神经元的示意图；
图4是本申请实施例提供的一种信息处理方法的流程图；
图5是本申请实施例提供的另一种信息处理方法的流程图；
图6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7是本申请实施例提供的另一种信息处理装置的结构示意图；
图8是本申请实施例提供的一种通信设备的结构示意图；
图9是本申请实施例提供的一种终端的结构示意图；
图10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，本申请中的“或”表示所连接对象的至少其中之一。例如“A或B”涵盖三种方案，即，方案一：包括A且不包括B；方案二：包括B且不包括A；方案三：既包括A又包括B。字符“/”一般表示前后关联对象是一种“或”的关系。
本申请的术语“指示”既可以是一个直接的指示(或者说显式的指示)，也可以是一个间接的指示(或者说隐含的指示)。其中，直接的指示可以理解为，发送方在发送的指示中明确告知了接收方具体的信息、需要执行的操作或请求结果等内容；间接的指示可以理解为，接收方根据发送方发送的指示确定对应的信息，或者进行判断并根据判断结果确定需要执行的操作或请求结果等。
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)或其他系统。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系统以外的系统，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)、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)、飞行器(flight vehicle)、车载设备(Vehicle User Equipment，VUE)、船载设备、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。其中，车载设备也可以称为车载终端、车载控制器、车载模块、车载部件、车载芯片或车载单元等。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(Radio Access Network,RAN)设备、无线接入网功能或无线接入网单元。接入网设备可以包括基站、无线局域网(Wireless Local Area Network，WLAN)接入点(Access Point，AP)或无线保真(Wireless Fidelity，WiFi)节点等。其中，基站可被称为节点B(Node B，NB)、演进节点B(Evolved Node B，eNB)、下一代节点B(the next generation Node B，gNB)、新空口节点B(New Radio Node B，NR Node B)、接入点、中继站(Relay Base Station，RBS)、服务基站(Serving Base Station，SBS)、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(home Node B，HNB)、家用演进型B节点(home evolved Node B)、发送接收点(Transmission Reception 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。
在无线通信技术中，准确的信道状态信息(channel state information，CSI)反馈对信道容量至关重要。尤其是对于多天线系统来讲，发送端可以根据CSI优化信号的发送，使其更加匹配信道的状态。如：信道质量指示(Channel Quality Indicator，CQI)可以用来选择合适的调制编码方案(Modulation and Coding Scheme，MCS)，以实现链路自适应；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(如：多输入多输出(Multi-Input Multi-Output，MIMO))被提出以来，CSI的获取一直都是研究热点。
通常，网络侧设备在某个时隙(slot)的某些时频资源上发送CSI参考信号(CSI-Reference Signals，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，网络侧设备根据终端反馈的码本信息组合出信道信息，并在终端下一次上报CSI之前，网络侧设备以此信道信息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改成按照时延域(delay 域，即频域)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，其可以视作是将delay域信息压缩之后再上报。
同样，为了减少开销，网络侧设备可以事先对CSI-RS进行预编码，将编码后的CSI-RS发送给终端，终端看到的是经过编码之后的CSI-RS对应的信道，终端只需要在网络侧设备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。
在相关技术中，利用AI单元对信道信息进行压缩，能够提升信道特征信息的压缩效果。具体的，终端可以估计CSI参考信号(CSI Reference Signal，CSI-RS)或跟踪参考信号(Tracking Reference Signal，TRS)，根据该估计到的信道信息进行计算，得到计算的信道信息，然后，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器进行编码，得到编码结果，最后将编码结果发送给基站。在基站侧，基站可以在接收编码后的结果后，将其输入到解码器中，利用该解码器恢复信道信息。具体的，基于神经网络的CSI压缩反馈方案是，在终端利用编码网络对信道信息进行压缩编码，将压缩后的内容发送给基站，在基站利用解码网络对压缩后的内容进行解码，从而恢复信道信息，此时基站的解码网络和终端的编码网络需要联合训练，达到合理的匹配度。编码网络的输入是信道信息，输出是编码信息，即信道特征信息，解码网络的输入是编码信息，输出是恢复的信道信息。
终端估计CSI-RS之后，对信道矩阵进行奇异值分解(Singular Value Decomposition，SVD)，得到相对正交的多层(layer)的预编码矩阵，终端反馈CSI的时候需要反馈对应的秩指示(Rank Indicator，RI)和PMI，RI表示的是选择的layer的总数，PMI是对应layer的预编码矩阵。在基于AI的CSI反馈中，每个layer的预编码矩阵可以独立通过一个第一AI单元得到压缩后的信道特征信息，然后将所有layer的信道特征信息一起上报给基站。
本申请实施例中，在高秩(rank)场景下，基于不同layer的能量集中度不同，可以对相对重要的layer使用更大有效载荷(payload)的信道特征信息，这样，信道特征信息的payload越长，网络侧设备据此恢复的信道信息会越准确。这样，通过给相对重要的layer上报更大payload的信道特征信息，提升了网络侧设备恢复相对重要的layer的信道信息的准确度；通过给相对不重要的layer上报更小payload的信道特征信息，降低了上报信道特征信息的开销。
需要说明的是，本申请实施例中的AI单元也可称为AI模型、AI结构等，或者所述AI单元也可以是指能够实现与AI相关的特定的算法、公式、处理流程、能力等的处理单元，或者所述AI单元可以是针对特定数据集的处理方法、算法、功能、模块或单元，或者所述AI单元可以是运行在图形处理单元(Graphics Processing Unit，GPU)、网络处理单元(Neural-Network Processing Unit，NPU)、张量处理单元(Tensor Processing Unit，TPU)、专用集成电路(Application Specific Integrated Circuit，ASIC)等AI相关硬件上的处理方法、算法、功能、模块或单元，本申请对此不做具体限定。可选地，所述特定数据集包括AI单元的输入或输出。
可选地，所述AI单元的标识，可以是AI模型标识、AI结构标识、AI算法标识，或者 所述AI单元关联的特定数据集的标识，或者所述AI相关的特定场景、环境、信道特征、设备的标识，或者所述AI相关的功能、特性、能力或模块的标识，本申请对此不做具体限定。
另外，AI功能有多种实现方式，例如神经网络、决策树、支持向量机、贝叶斯分类器等，本申请对此不做具体限定。为了便于说明，本申请实施例中以AI单元为神经网络为例进行说明，但是并不限定AI单元的具体类型。例如：如图2所示，神经网络模型包括输入层、隐层和输出层，其可以根据输入层获取的出入信息(X1～Xn)预测可能的输出结果(Y)。神经网络模型由大量的神经元组成，如图3所示，神经元的参数包括：输入参数a1～aK、权值w、偏置b以及激活函数σ(z)，以及与这些参数获取输出值a，其中，常见的激活函数包括S型生长曲线(Sigmoid)函数、双曲正切(tanh)函数、线性整流函数(Rectified Linear Unit，ReLU，其也称之为修正线性单元)函数等等，且上述函数σ(z)中的z可以通过以下公式计算得到：
z＝a1wx+…+akwk+aKwK+b
其中，K表示输入参数的总数。
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(.)，有了模神经网络型后，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W和b，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，基本都是基于误差反向传播(error 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)、Nesterov(其表示带动量的随机梯度下降)、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。
本申请实施例中的AI单元包括：
第一AI单元，即编码器对应的AI单元，其部署在终端侧，其输入信息为信道信息，输出信息是信道特征信息；
第二AI单元，即解码器对应的AI单元，其部署在网络侧，其输入信息为信道特征信息，输出信息是恢复的信道信息。
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处理方法、信息处理装置以及相关设备进行详细地说明。
请参阅图4，本申请实施例提供的一种信息处理方法，其执行主体可以是终端，其中，终端可以是如图1中列举的各种类型的终端11，或者是除了如图1所示实施例中列举的终端类型之外的其他终端，在此不作具体限定。
如图4所示，该信息处理方法可以包括以下步骤：
步骤401、终端获取第一信息，其中，所述第一信息指示至少一个layer对应的第一信道特征信息的有效载荷信息。
一种实施方式中，第一信息可以是网络侧设备的配置或指示的。
另一种实施方式中，第一信息可以是协议约定的。
再一种实施方式中，第一信息可以是一部分是网络侧设备的配置或指示的，另一部分是协议约定的。
步骤402、所述终端基于所述第一信息，采用目标第一AI单元对目标layer的信道信息进行第一处理，得到所述目标layer对应的所述第一信道特征信息，其中，所述目标layer对应的第一信道特征信息的有效载荷信息与所述目标第一AI单元的输出长度匹配，所述至少一个layer包括所述目标layer。
本申请实施例中，目标layer的信道信息可以是一个layer的预编码矩阵，例如：终端对CSI-RS进行测量或估计，得到信道矩阵，通过对信道矩阵进行SVD分解，得到相对正交的至少一个layer的预编码矩阵。
可选地，目标layer可以是所述相对正交的至少一个layer中的每一个layer，基于第一信息，可以确定每一个layer各自对应的第一信道特征信息的有效载荷。
鉴于第一信道特征信息是第一AI单元的输出信息，此时，第一信道特征信息的有效载荷与第一AI单元的输出长度匹配。换而言之，终端可以具有至少两个第一AI单元，不同的第一AI单元的输出长度可以不同，此时，可以先基于第一信息确定目标layer的第一信道特征信息的有效载荷，再获取能够输出与该有效载荷匹配的输出信息的目标第一AI单元，这样，便可以将目标第一AI单元与目标layer关联，并使用目标第一AI单元对关联的目标layer的信道信息进行第一处理。
一种实施方式中，所述目标layer对应的第一信道特征信息的有效载荷信息与所述目标第一AI单元的输出长度匹配，可以是所述目标layer对应的第一信道特征信息的有效载荷 等于或约等于所述目标第一AI单元的输出长度。
可选地，所述第一处理可以包括压缩、编码、量化、归一化等处理中的至少一项。
一种实施方式中，在第一处理包括量化处理的情况下，所述第一AI单元的输出长度可以是比特(bit)数，此时，有效载荷也可以是bit数。
另一种实施方式中，在第一处理不包括量化处理的情况下，所述第一AI单元的输出长度可以是浮点数的个数，此时，有效载荷也可以是浮点数的个数。
可选地，在第一处理不包括量化处理的情况下，网络侧设备可以指示或预先配置量化方法，终端基于网络侧设备指示或预先配置的量化方法，对第一AI单元输出的第一信道特征信息进行量化，并将量化后的第一信道特征信息发送给网络侧设备。
作为一种可选的实施方式，所述第一信息包括以下至少一项：
与所述至少一个layer一一对应的有效载荷信息；
与候选秩一一对应的有效载荷总量信息；
有效载荷总量信息，其中，所述有效载荷总量信息为所述至少一个layer对应的第一信道特征信息的有效载荷的总和；
第一关系，所述第一关系包括第一layer的有效载荷与第二layer的有效载荷之间的关系，所述至少一个layer包括所述第一layer和所述第二layer；
与预设最大秩对应的预设最大有效载荷总量信息。
一种实施方式中，第一信息包括与所述至少一个layer一一对应的有效载荷信息，例如：第一信息指示每一layer各自对应的有效载荷长度，或第一信息指示每一layer各自对应的第一AI单元等，这样，对于目标layer，终端可以将该目标layer对应的第一AI单元或输出信息长度与对应的有效载荷长度匹配的第一AI单元作为目标第一AI单元。
另一种实施方式中，有效载荷总量信息与候选秩一一对应，候选秩可以是网络侧设备配置的终端可以选择的秩的范围，终端可以从候选秩中选择一个作为实际的目标秩，即选择实际的layer数。例如：对于rank＝1，其对应的有效载荷总量信息为100bit；对于rank＝2，其对应的有效载荷总量信息为200bit；对于rank＝3，其对应的有效载荷总量信息为300bit；对于rank＝4，其对应的有效载荷总量信息为400bit，终端若选择目标秩为2，则确定2个layer对应的第一信道特征信息的有效载荷的总量为200bit。
可选地，在确定至少一个layer对应的第一信道特征信息的有效载荷总量信息之后，可以基于预设规则确定每一个layer各自对应的第一信道特征信息的有效载荷信息，例如：确定至少一个layer对应的第一信道特征信息的有效载荷相等，即至少两个layer对应的第一信道特征信息均分有效载荷总量。或者基于网络侧设备指示或协议约定的预设规则，如第一关系，来确定每一个layer各自对应的第一信道特征信息的有效载荷信息。
其中，第一关系可以包括layer之间的payload关系，例如：第二个layer对应的第一信道特征信息的payload为第一个layer对应的第一信道特征信息的payload的60％。或者，第一关系可以包括有效载荷信息在各个layer之间的分配规则，例如：假设rank＝4，且确 定的有效载荷总量信息500bit，第一关系为[0.3 0.3 0.2 0.2]，即layer0和layer1对应的第一信道特征信息的payload分别占有效载荷总量的0.3，即150bit，layer2和layer3对应的第一信道特征信息的payload分别占有效载荷总量的0.2，即100bit。
再一种实施方式中，第一信息可以直接指示所述至少一个layer对应的第一信道特征信息的有效载荷的总和。可选地，在得到所述至少一个layer对应的第一信道特征信息的有效载荷的总和之后，终端可以基于与上一实施方式中相似的方式来确定每一个layer各自对应的第一信道特征信息的有效载荷信息。
又一种实施方式中，第一信息可以指示与预设最大秩对应的预设最大有效载荷总量信息。其中，预设最大秩可以理解为终端可选的秩的最大值，例如：假设预设最大秩为4，则终端可选的秩为1、2、3或4。此时，终端可以根据选择的目标秩来确定所述至少一个layer对应的第一信道特征信息的有效载荷总量信息，例如：在终端确定目标秩小于预设最大秩的情况下，终端可以确定所述至少一个layer对应的第一信道特征信息的有效载荷总量信息为所述预设最大有效载荷总量信息的全部或部分。可选地，在得到所述至少一个layer对应的第一信道特征信息的有效载荷的总和之后，终端可以基于与上一实施方式中相似的方式来确定每一个layer各自对应的第一信道特征信息的有效载荷信息。
值得提出的是，在确定至少一个layer对应的第一信道特征信息的有效载荷总量信息之后，可以基于预设规则确定每一个layer各自对应的第一信道特征信息的有效载荷信息，例如：确定至少一个layer对应的第一信道特征信息的有效载荷相等，即至少两个layer对应的第一信道特征信息均分有效载荷总量；
或者，
在确定至少一个layer对应的第一信道特征信息的有效载荷总量信息之后，可以基于网络侧设备或协议约定的规则，来确定每一个layer各自对应的第一信道特征信息的有效载荷信息，例如：基于第一关系确定每一个layer各自对应的第一信道特征信息的有效载荷信息。
可选地，在所述第一信息包括：所述第一关系和所述有效载荷总量信息的情况下，所述方法还包括：
所述终端根据所述第一关系和所述有效载荷总量信息，确定与所述至少一个layer一一对应的有效载荷。
本实施方式中，其中，第一关系包括第一layer的有效载荷与第二layer的有效载荷之间的关系，所述至少一个layer包括所述第一layer和所述第二layer。例如：将至少两个layer按照重要程度由高至低排列，第一关系指示：第一个layer对应的第一信道特征信息的有效载荷比第二个layer对应的第一信道特征信息的有效载荷大20％，第二个layer对应的第一信道特征信息的有效载荷比第三个layer对应的第一信道特征信息的有效载荷大10％等等。
另一种实施方式中，在所述第一信息包括所述第一关系以及与候选秩一一对应的有效载荷总量信息的情况下，所述方法还包括：
所述终端根据与候选秩一一对应的有效载荷总量信息，确定与目标秩对应的目标有效 载荷总量信息，其中，所述目标秩为与所述至少一个layer对应的目标信道的秩；
所述终端根据所述第一关系和所述目标有效载荷总量信息，确定与所述至少一个layer一一对应的有效载荷。
其中，终端根据所述第一关系和所述目标有效载荷总量信息，确定与所述至少一个layer一一对应的有效载荷的过程，与上一实施方式中的：终端根据所述第一关系和所述目标有效载荷总量信息，确定与所述至少一个layer一一对应的有效载荷的过程相同或相似，在此不再赘述。
再一种实施方式中，在所述第一信息包括所述第一关系以及与预设最大秩对应的预设最大有效载荷总量信息的情况下，所述方法还包括：
所述终端确定所述至少一个layer的有效载荷之和，等于所述预设最大有效载荷总量信息，或等于所述预设最大有效载荷总量信息与第一值的乘积，其中，所述第一值为目标秩与所述预设最大秩的比例值，所述目标秩为与所述至少一个layer对应的目标信道的秩；
所述终端根据所述第一关系和所述至少一个layer的有效载荷之和，确定与所述至少一个layer一一对应的有效载荷。
可选地，在所述终端确定所述至少一个layer的有效载荷之和等于所述预设最大有效载荷总量信息的情况下，可以对所述至少一个layer对应的第一信道特征信息进行等比例扩展，例如：扩展至X/Y倍，其中，X表示预设最大秩，Y表示目标秩。在实施中，终端还向网络侧发送目标秩或目标秩的标识，以辅助网络侧设备确定每一个layer各自对应的第一信道特征信息的payload。
作为一种可选的实施方式，所述有效载荷信息包括以下至少一项：
有效载荷长度；
第一数据集的标识，所述第一数据集用于训练至少一个第一AI单元，不同的所述第一AI单元的输出信息的有效载荷长度不同，所述至少一个第一AI单元包括所述目标第一AI单元；
所述目标第一AI单元的标识。
一种实施方式中，有效载荷长度可以包括对应的第一AI单元的输出信息的浮点数个数或bit数。
另一种实施方式中，第一数据集用于训练至少一个第一AI单元，在第一数据集用于训练一个第一AI单元的情况下，所述终端可以确定基于所述第一数据集训练的一个第一AI单元作为目标AI单元，该目标AI单元的输出长度即为目标layer对应的第一信道特征信息的有效载荷长度，其中，目标AI单元的输出长度是指目标AI单元的输出信息的长度；在第一数据集用于训练至少两个第一AI单元的情况下，所述终端可以基于预设规则从所述至少两个第一AI单元中确定目标AI单元。
例如：有效载荷信息可以包括有效载荷长度和第一数据集的标识，此时，终端获取基于第一数据集训练的至少两个第一AI单元，且每一个第一AI单元具有各自的输出长度，此 时终端可以基于第一信息确定目标layer对应的第一信道特征信息的有效载荷长度，并从至少两个第一AI单元中选择输出长度与该长度相等或相近的一个第一AI单元作为目标AI单元。
再一种实施方式中，所述有效载荷信息可以直接指示目标第一AI单元，此时，有效载荷长度为目标第一AI单元的输出信息的payload。
本申请实施例中，在基于第一信息确定每一个layer的第一信道特征信息的payload之后，可以据此确定用于得到每一个layer的第一信道特征信息的第一AI单元。
作为一种可选的实施方式，所述终端基于所述第一信息，采用目标第一AI单元对目标layer的信道信息进行第一处理，得到所述目标layer对应的所述第一信道特征信息，包括：
所述终端基于所述第一信息，确定与目标layer对应的目标有效载荷；
所述终端获取输出信息长度与所述目标有效载荷匹配的目标第一AI单元；
所述终端根据所述目标第一AI单元和所述目标layer的信道信息，确定所述目标layer的第一信道特征信息。
其中，目标layer对应的目标有效载荷，可以理解为：目标layer对应的第一信道特征信息的有效载荷。
一种实施方式中，目标第一AI单元可以是AI模型，此时，所述终端根据所述目标第一AI单元和所述目标layer的信道信息，确定所述目标layer的第一信道特征信息，可以是将所述目标layer的信道信息输入所述AI模型，并获取所述AI模型输出的所述目标layer的第一信道特征信息。
可选地，所述终端根据所述目标第一AI单元和所述目标layer的信道信息，确定所述目标layer的第一信道特征信息，包括：
所述终端根据所述目标第一AI单元和所述目标layer的信道信息，得到第二信道特征信息；
在所述第二信道特征信息等于所述目标layer对应的有效载荷长度的情况下，所述终端确定第一信道特征信息包括所述第二信道特征信息；或，
在所述第二信道特征信息大于所述目标layer对应的有效载荷长度的情况下，所述终端对所述第二信道特征信息进行第一后处理，得到与所述目标layer对应的有效载荷长度相匹配的第一信道特征信息；或，
在所述第二信道特征信息小于所述目标layer对应的有效载荷长度的情况下，所述终端对所述第二信道特征信息进行第二后处理，得到与所述目标layer对应的有效载荷长度相匹配的第一信道特征信息。
一种实施方式中，在目标第一AI单元的输出长度与目标layer对应的payload相同的情况下，可以直接使用目标第一AI单元对目标layer的信道信息进行压缩，得到与目标layer对应的payload相匹配的第一信道特征信息。
另一种实施方式中，在目标第一AI单元的输出长度大于目标layer对应的payload的情 况下，在使用目标第一AI单元对目标layer的信道信息进行压缩，得到第二信道特征信息后，第二信道特征信息的长度会大于目标layer对应的payload，此时，通过对第二信道特征信息进行第一后处理，以得到与目标layer对应的payload匹配的第一信道特征信息。
其中，第一后处理可以是能够降低第二信道特征信息的payload的处理，例如：所述第一后处理包括以下至少一项：
截断处理；
调整对所述第一信道特征信息的量化规则。
其中，调整对所述第一信道特征信息的量化规则，可以是将对所述第一信道特征信息的量化规则调整为量化精度更低的量化规则，其中，基于量化精度更低的量化规则量化后的第一信道特征信息的bit数更少。
再一种实施方式中，在目标第一AI单元的输出长度小于目标layer对应的payload的情况下，在使用目标第一AI单元对目标layer的信道信息进行压缩，得到第二信道特征信息后，第二信道特征信息的长度会小于目标layer对应的payload，此时，通过对第二信道特征信息进行第二后处理，以得到与目标layer对应的payload匹配的第一信道特征信息。
其中，第二后处理可以是能够提升第二信道特征信息的payload的处理，例如：所述第二后处理包括以下至少一项：
补零处理；
循环重复处理。
一种实施方式中，补零处理可以是对第二信道特征信息进行补零，使其payload达到目标layer对应的payload。
另一种实施方式中，循环重复处理可以是对第二信道特征信息中的部分信息进行重复，得到与目标layer对应的payload相匹配的第一信道特征信息。例如：假设第二信道特征信息为100bit，目标layer对应的payload为150bit，此时，可以使第一信道特征信息包括：第二信道特征信息+第二信道特征信息的前50bit。
本实施方式中，可以根据目标第一AI单元得到的第二信道特征信息的长度与目标layer对应的payload之间的大小关系，来调整第二信道特征信息的长度，以使终端上报的第一信道特征信息的长度与目标layer对应的payload一致。
作为一种可选的实施方式，所述方法还包括：
所述终端向网络侧设备发送第二信息，其中，所述第二信息包括所述至少一个layer对应的所述第一信道特征信息。
本实施方式中，终端可以统一上报一个完整信道的全部layer的第一信道特征信息。
作为一种可选的实施方式，所述第二信息还包括目标秩或所述目标秩的标识信息，所述目标秩为所述至少一个layer对应的目标信道的秩。
本实施方式中，终端向网络侧设备选择的目标秩，即目标信道包含的layer的数目。这样，网络侧设备可以据此作为确定接收的第一信道特征信息对应的layer数。可选地，在终 端统一上报一个完整信道的全部layer的第一信道特征信息的情况下，网络侧设备可以根据目标秩确定每一个layer各自的第一信道特征信息。
在本申请实施例中，终端可以基于第一信息确定每一个layer对应的第一信道特征信息的有效载荷信息，从而采用与该有效载荷信息匹配的第一AI单元对一个layer的信道信息进行处理，得到符合该有效载荷信息的信道特征信息。这样，对于不同的layer，可以向网络侧设备上报不同有效载荷的信道特征信息，进而能够更加有针对性的配置不同layer的信道特征信息的长度，在降低上报信道特征信息的开销的同时，还能够有针对性地提升重要程度较高的layer的信道特征信息的精确度，例如：通过第一信息指示重要程度较高或强度较高或集中度较高的layer的信道特征信息的有效载荷大于重要程度较低或强度较低或集中度较低的layer的信道特征信息的有效载荷，使得终端上报的重要程度较高或强度较高或集中度较高的layer的信道特征信息比重要程度较低或强度较低或集中度较低的layer的信道特征信息更精确。
请参阅图5，是本申请实施例提供的另一种信息处理方法，该信息处理方法的执行主体是网络侧设备，该网络侧设备可以包括如图1所示实施例中列举的网络侧设备，或者是其他网络侧设备，在此不作具体限定。
如图5所示，该信息处理方法可以包括以下步骤：
步骤501、网络侧设备向终端发送第一信息，其中，所述第一信息指示至少一个layer对应的第一信道特征信息的有效载荷信息；其中，所述第一信息用于所述终端确定目标layer对应的第一信道特征信息的有效载荷，所述目标layer对应的第一信道特征信息基于所述目标layer对应的目标第一AI单元对所述目标layer的信道信息进行第一处理得到，所述目标layer对应的第一信道特征信息的有效载荷信息与所述目标第一AI单元的输出长度匹配，所述至少一个layer包括所述目标layer。
在实施中，上述第一信息、第一信道特征信息、有效载荷信息和第一AI单元分别与如图3所示方法实施例中的第一信息、第一信道特征信息、有效载荷信息和第一AI单元具有相同的含义，在此不再赘述。
本申请实施例中，网络侧设备向终端配置或指示第一信息，以使终端在选择高rank场景下，终端基于网络侧设备配置或指示的payload来上报各个layer的信道特征信息。这样，对于不同的layer，网络侧设备可以指示终端上报不同有效载荷的信道特征信息，进而能够更加有针对性的配置或指示不同layer的信道特征信息的长度，在降低上报信道特征信息的开销的同时，还能够有针对性地提升重要程度较高或强度较高或集中度较高的layer的信道特征信息的精确度，例如：通过第一信息配置或指示重要程度较高或强度较高或集中度较高的layer的信道特征信息的有效载荷大于重要程度较低或强度较低或集中度较低的layer的信道特征信息的有效载荷，使得终端上报的重要程度较高或强度较高或集中度较高的layer的信道特征信息比重要程度较低或强度较低或集中度较低的layer的信道特征信息更精确，网络侧设备基于第二AI单元恢复的信道信息中，重要程度较高或强度较高或集中度较 高的layer的信道信息比重要程度较低或强度较低或集中度较低的layer的信道信息也更精确。
作为一种可选的实施方式，所述第一信息包括以下至少一项：
与所述至少一个layer一一对应的有效载荷信息；
与候选秩一一对应的有效载荷总量信息；
有效载荷总量信息，其中，所述有效载荷总量信息为所述至少一个layer对应的第一信道特征信息的有效载荷的总和；
第一关系，所述第一关系包括第一layer的有效载荷与第二layer的有效载荷之间的关系，所述至少一个layer包括所述第一layer和所述第二layer。
作为一种可选的实施方式，所述有效载荷信息包括以下至少一项：
有效载荷长度；
第一数据集的标识，所述第一数据集用于训练至少一个第一AI单元，不同的所述第一AI单元的输出信息的有效载荷长度不同，所述至少一个第一AI单元包括所述目标第一AI单元；
所述目标第一AI单元的标识。
作为一种可选的实施方式，所述有效载荷长度包括以下至少一项：
浮点数的个数；
bit数。
作为一种可选的实施方式，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信息，其中，所述第二信息包括所述至少一个layer对应的所述第一信道特征信息；
所述方法还包括：
所述网络侧设备基于第二AI单元，对所述至少一个layer对应的所述第一信道特征信息进行第二处理，得到所述至少一个layer对应的信道信息。
一种实施方式中，第二AI单元为解码器对应的AI单元，第二处理可以包括：解码、解量化、解压缩等处理中的至少一项，该第二AI单元与终端的第一AI单元匹配，且第二处理可以是第一AI单元对应的第一处理的逆处理。
可选地，第二AI单元与第一AI单元可以一一对应，此时，对于基于目标第一AI单元得到的第一信道特征信息，可以采用与该目标第一AI单元对应的目标第二AI单元进行解码，以得到目标layer对应的信道信息。
可选地，第二AI单元的输入信息可以是整个信道的信道信息，例如：目标信道对应的全部layer的第一信道特征信息。
作为一种可选的实施方式，所述第二信息还包括所述目标秩或所述目标秩的标识信息，其中，所述目标秩为与所述至少一个layer对应的目标信道的秩。
一种实施方式中，网络侧设备可以基于目标秩来确定每一个layer各自的第一信道特征 信息。例如：网络侧设置指示预设最大秩对应的预设最大有效载荷总量信息，且协议约定所述第一关系的情况下，若所述终端确定所述至少一个layer的有效载荷之和，等于所述预设最大有效载荷总量信息与第一值的乘积，则网络侧设备可以根据目标秩，采用终端根据所述第一关系和所述至少一个layer的有效载荷之和，确定与所述至少一个layer一一对应的有效载荷相对应的原理，来确定每一个layer各自的第一信道特征信息，进而采用对应的第二AI单元对各个layer的第一信道特征信息进行第二处理，以恢复各个layer的信道信息。
作为一种可选的实施方式，所述网络侧设备基于第二AI单元，对所述至少一个layer对应的所述第一信道特征信息进行第二处理，得到所述至少一个layer对应的信道信息，包括：
所述网络侧设备基于所述第一信息，从所述第二信息中获取目标layer对应的第一信道特征信息；
所述网络侧设备根据所述第一信息，确定第二AI单元；
所述网络侧设备根据所述第二AI单元和所述目标layer对应的所述第一信道特征信息，确定所述目标layer对应的信道信息。
一种实施方式中，所述网络侧设备根据所述第一信息，确定第二AI单元，可以是：网络侧设备确定第二AI单元的输入信息的payload与第一信息中的所述至少一个layer对应的第一信道特征信息的payload匹配。
可选地，所述第二AI单元的输入信息长度与所述目标layer对应的第一信道特征信息的有效载荷信息匹配；或，
所述第一信息中的第一数据集的标识，指示用于训练该第二AI单元的数据集；或，
所述第一信息中的第一AI单元标识与第二AI单元关联。
可选地，在第二AI单元与第一AI单元一一对应的情况下，所述网络侧设备根据所述第一信息，确定第二AI单元的方式，与终端根据所述第一信息，确定每一个layer各自对应的第一AI单元的方式相似，即网络侧设备确定目标layer对应的目标第二AI单元满足：目标第二AI单元的输入长度与目标layer对应的第一信道特征信息的payload匹配。
可选地，在第二AI单元用于输入目标信道的全部layer的第一信道特征信息的情况下，所述网络侧设备根据所述第一信息，确定第二AI单元，可以是：网络侧设备确定第二AI单元的输入长度与目标信道的全部layer的第一信道特征信息的payload之和匹配。
一种实施方式中，第二AI单元可以是AI模型，此时，所述网络侧设备根据所述第二AI单元和所述目标layer对应的所述第一信道特征信息，确定所述目标layer对应的信道信息，可以是：所述网络侧设备将目标layer对应的所述第一信道特征信息输入AI模型，并获取该AI模型输出的所述目标layer对应的信道信息。
本申请实施例中，网络侧设备可以向终端配置或指示第一信息，以使终端按照网络侧设备的配置或指示的payload来压缩各个layer的信道信息，其具有与如图4所示方法实施例相似的有益效果，为避免重复，在此不再赘述。
为了便于理解本申请实施例提供的信息处理方法，以基站向终端指示与预设最大秩对应的预设最大有效载荷总量信息为例，对本申请实施例提供的信息处理方法进行举例说明：
本申请实施例提供的信息处理方法可以包括以下步骤：
1.基站配置rank最大值为4；
2.终端可以在1、2、3和4中进行rank自适应；
3.基站指示最大payload为500bit，各个layer之间payload关系可以由基站指示或协议约定；
例如：假设第一关系为[0.3 0.3 0.2 0.2]，则在rank4下，终端计算layer0的paylaod为150bit，layer1的paylaod为150bit，layer2和layer3的paylaod是100bit。
可选地，对于第一关系，基站可以指示每个rank对应的payload与最大payload的关系，例如rank3是rank4的80％，rank2是rank4的50％，rank1是rank4的40％。
4.假设终端选择的目标rank为rank2，则终端确定实际paylaod可以是：layer0和layer1各150bit，一共300bit；或者layer0和layer1各250bit，一共500bit；
5.终端采用输出长度为150bit或250bit的第一AI单元分别对layer0和layer1的信道信息进行压缩，得到两个150bit或250bit的第一信道特征信。
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6，本申请实施例提供的信息处理装置600可以是终端内的装置。如图6所示，该信息处理装置600可以包括以下模块：
第一获取模块601，用于获取第一信息，其中，所述第一信息指示至少一个layer对应的第一信道特征信息的有效载荷信息；
第一处理模块602，用于基于所述第一信息，采用目标第一AI单元对目标layer的信道信息进行第一处理，得到所述目标layer对应的所述第一信道特征信息，其中，所述目标layer对应的第一信道特征信息的有效载荷信息与所述目标第一AI单元的输出长度匹配，所述至少一个layer包括所述目标layer。
可选地，所述第一信息包括以下至少一项：
与所述至少一个layer一一对应的有效载荷信息；
与候选秩一一对应的有效载荷总量信息；
有效载荷总量信息，其中，所述有效载荷总量信息为所述至少一个layer对应的第一信道特征信息的有效载荷的总和；
第一关系，所述第一关系包括第一layer的有效载荷与第二layer的有效载荷之间的关系，所述至少一个layer包括所述第一layer和所述第二layer；
与预设最大秩对应的预设最大有效载荷总量信息。
可选地，在所述第一信息包括：所述第一关系和所述有效载荷总量信息的情况下，信息处理装置600还包括：
第一确定模块，用于根据所述第一关系和所述有效载荷总量信息，确定与所述至少一个layer一一对应的有效载荷。
可选地，在所述第一信息包括所述第一关系以及与候选秩一一对应的有效载荷总量信息的情况下，信息处理装置600还包括：
第二确定模块，用于根据与候选秩一一对应的有效载荷总量信息，确定与目标秩对应的目标有效载荷总量信息，其中，所述目标秩为与所述至少一个layer对应的目标信道的秩；
第三确定模块，用于根据所述第一关系和所述目标有效载荷总量信息，确定与所述至少一个layer一一对应的有效载荷。
可选地，在所述第一信息包括所述第一关系以及与预设最大秩对应的预设最大有效载荷总量信息的情况下，信息处理装置600还包括：
第四确定模块，用于确定所述至少一个layer的有效载荷之和，等于所述预设最大有效载荷总量信息，或等于所述预设最大有效载荷总量信息与第一值的乘积，其中，所述第一值为目标秩与所述预设最大秩的比例值，所述目标秩为与所述至少一个layer对应的目标信道的秩；
第五确定模块，用于根据所述第一关系和所述至少一个layer的有效载荷之和，确定与所述至少一个layer一一对应的有效载荷。
可选地，所述有效载荷信息包括以下至少一项：
有效载荷长度；
第一数据集的标识，所述第一数据集用于训练至少一个第一AI单元，不同的所述第一AI单元的输出信息的有效载荷长度不同，所述至少一个第一AI单元包括所述目标第一AI单元；
所述目标第一AI单元的标识。
可选地，所述有效载荷长度包括以下至少一项：
浮点数的个数；
bit数。
可选地，第一处理模块602，包括：
第一确定单元，用于基于所述第一信息，确定与目标layer对应的目标有效载荷；
第一获取单元，用于获取输出信息长度与所述目标有效载荷匹配的目标第一AI单元；
第二确定单元，用于根据所述目标第一AI单元和所述目标layer的信道信息，确定所述目标layer的第一信道特征信息。
可选地，所述第二确定单元，包括：
第一确定子单元，用于根据所述目标第一AI单元和所述目标layer的信道信息，得到第二信道特征信息；
第二确定子单元，用于在所述第二信道特征信息等于所述目标layer对应的有效载荷长度的情况下，确定第一信道特征信息包括所述第二信道特征信息；或，
第一处理子单元，用于在所述第二信道特征信息大于所述目标layer对应的有效载荷长度的情况下，对所述第二信道特征信息进行第一后处理，得到与所述目标layer对应的有效载荷长度相匹配的第一信道特征信息；或，
第二处理子单元，用于在所述第二信道特征信息小于所述目标layer对应的有效载荷长度的情况下，对所述第二信道特征信息进行第二后处理，得到与所述目标layer对应的有效载荷长度相匹配的第一信道特征信息。
可选地，所述第一后处理包括以下至少一项：
截断处理；
调整对所述第一信道特征信息的量化规则。
可选地，所述第二后处理包括以下至少一项：
补零处理；
循环重复处理。
可选地，信息处理装置600还包括：
第二发送模块，用于向网络侧设备发送第二信息，其中，所述第二信息包括所述至少一个layer对应的所述第一信道特征信息。
可选地，所述第二信息还包括目标秩或所述目标秩的标识信息，所述目标秩为所述至少一个layer对应的目标信道的秩。
本申请实施例中的信息处理装置600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。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，本申请实施例不作具体限定。
本申请实施例提供的信息处理装置600能够实现图4所示方法实施例实现的各个过程，并达到相同的技术效果，为避免重复，这里不再赘述。
请参阅图7，本申请实施例提供的另一种信息处理装置，可以是网络侧设备内的装置，如图7所示，该信息处理装置700可以包括以下模块：
第一发送模块701，用于向终端发送第一信息，其中，所述第一信息指示至少一个layer对应的第一信道特征信息的有效载荷信息；
其中，所述第一信息用于所述终端确定目标layer对应的第一信道特征信息的有效载荷，所述目标layer对应的第一信道特征信息基于所述目标layer对应的目标第一AI单元对所述目标layer的信道信息进行第一处理得到，所述目标layer对应的第一信道特征信息的有效载荷信息与所述目标第一AI单元的输出长度匹配，所述至少一个layer包括所述目标layer。
可选地，所述第一信息包括以下至少一项：
与所述至少一个layer一一对应的有效载荷信息；
与候选秩一一对应的有效载荷总量信息；
有效载荷总量信息，其中，所述有效载荷总量信息为所述至少一个layer对应的第一信道特征信息的有效载荷的总和；
第一关系，所述第一关系包括第一layer的有效载荷与第二layer的有效载荷之间的关系，所述至少一个layer包括所述第一layer和所述第二layer。
可选地，所述有效载荷信息包括以下至少一项：
有效载荷长度；
第一数据集的标识，所述第一数据集用于训练至少一个第一AI单元，不同的所述第一AI单元的输出信息的有效载荷长度不同，所述至少一个第一AI单元包括所述目标第一AI单元；
所述目标第一AI单元的标识。
可选地，所述有效载荷长度包括以下至少一项：
浮点数的个数；
bit数。
可选地，信息处理装置700还包括：
接收模块，用于接收来自所述终端的第二信息，其中，所述第二信息包括所述至少一个layer对应的所述第一信道特征信息；
信息处理装置700还包括：
第二处理模块，用于基于第二AI单元，对所述至少一个layer对应的所述第一信道特征信息进行第二处理，得到所述至少一个layer对应的信道信息。
可选地，所述第二信息还包括所述目标秩或所述目标秩的标识信息，其中，所述目标秩为与所述至少一个layer对应的目标信道的秩。
可选地，第二处理模块，包括：
获取单元，用于基于所述第一信息，从所述第二信息中获取目标layer对应的第一信道特征信息；
第三确定单元，用于根据所述第一信息，确定第二AI单元；
第四确定单元，用于根据所述第二AI单元和所述目标layer对应的所述第一信道特征信息，确定所述目标layer对应的信道信息。
本申请实施例提供的信息处理装置700能够实现图5所示方法实施例实现的各个过程，并达到相同的技术效果，为避免重复，这里不再赘述。
如图8所示，本申请实施例还提供一种通信设备800，包括处理器801和存储器802，存储器802上存储有可在所述处理器801上运行的程序或指令，例如，该通信设备800为终端时，该程序或指令被处理器801执行时实现如图4所示信息处理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800为第一设备时，该程序或指令被处理器801执行时实现如图5所示信息处理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4所示方法实施例中的步骤。该终端实 施例与上述终端侧方法实施例对应，上述方法实施例的各个实施过程和实现方式均可适用于该终端实施例中，且能达到相同的技术效果。具体地，图9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900包括但不限于：射频单元901、网络模块902、音频输出单元903、输入单元904、传感器905、显示单元906、用户输入单元907、接口单元908、存储器909以及处理器910等中的至少部分部件。
本领域技术人员可以理解，终端900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910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9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904可以包括图形处理单元(Graphics Processing Unit，GPU)9041和麦克风9042，图形处理单元9041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906可包括显示面板9061，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9061。用户输入单元907包括触控面板9071以及其他输入设备9072中的至少一种。触控面板9071，也称为触摸屏。触控面板9071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9072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901接收来自网络侧设备的下行数据后，可以传输给处理器910进行处理；另外，射频单元901可以向网络侧设备发送上行数据。通常，射频单元901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909可用于存储软件程序或指令以及各种数据。存储器909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909可以包括易失性存储器或非易失性存储器。其中，非易失性存储器可以是只读存储器(Read-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909包括但不限于这些和任意其它适合类型的存储器。
处理器910可包括一个或多个处理单元；可选地，处理器910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910中。
其中，射频单元901，用于获取第一信息，其中，所述第一信息指示至少一个layer对应的第一信道特征信息的有效载荷信息；
处理器910，用于基于所述第一信息，采用目标第一AI单元对目标layer的信道信息进行第一处理，得到所述目标layer对应的所述第一信道特征信息，其中，所述目标layer对应的第一信道特征信息的有效载荷信息与所述目标第一AI单元的输出长度匹配，所述至少一个layer包括所述目标layer。
可选地，所述第一信息包括以下至少一项：
与所述至少一个layer一一对应的有效载荷信息；
与候选秩一一对应的有效载荷总量信息；
有效载荷总量信息，其中，所述有效载荷总量信息为所述至少一个layer对应的第一信道特征信息的有效载荷的总和；
第一关系，所述第一关系包括第一layer的有效载荷与第二layer的有效载荷之间的关系，所述至少一个layer包括所述第一layer和所述第二layer；
与预设最大秩对应的预设最大有效载荷总量信息。
可选地，在所述第一信息包括：所述第一关系和所述有效载荷总量信息的情况下，处理器910，还用于根据所述第一关系和所述有效载荷总量信息，确定与所述至少一个layer一一对应的有效载荷。
可选地，在所述第一信息包括所述第一关系以及与候选秩一一对应的有效载荷总量信息的情况下，处理器910，还用于：
根据与候选秩一一对应的有效载荷总量信息，确定与目标秩对应的目标有效载荷总量信息，其中，所述目标秩为与所述至少一个layer对应的目标信道的秩；
根据所述第一关系和所述目标有效载荷总量信息，确定与所述至少一个layer一一对应的有效载荷。
可选地，在所述第一信息包括所述第一关系以及与预设最大秩对应的预设最大有效载荷总量信息的情况下，处理器910，还用于：
确定所述至少一个layer的有效载荷之和，等于所述预设最大有效载荷总量信息，或等于所述预设最大有效载荷总量信息与第一值的乘积，其中，所述第一值为目标秩与所述预设最大秩的比例值，所述目标秩为与所述至少一个layer对应的目标信道的秩；
根据所述第一关系和所述至少一个layer的有效载荷之和，确定与所述至少一个layer一一对应的有效载荷。
可选地，所述有效载荷信息包括以下至少一项：
有效载荷长度；
第一数据集的标识，所述第一数据集用于训练至少一个第一AI单元，不同的所述第一AI单元的输出信息的有效载荷长度不同，所述至少一个第一AI单元包括所述目标第一AI单元；
所述目标第一AI单元的标识。
可选地，所述有效载荷长度包括以下至少一项：
浮点数的个数；
bit数。
可选地，处理器910执行的所述基于所述第一信息，采用目标第一AI单元对目标layer的信道信息进行第一处理，得到所述目标layer对应的所述第一信道特征信息，包括：
基于所述第一信息，确定与目标layer对应的目标有效载荷；
获取输出信息长度与所述目标有效载荷匹配的目标第一AI单元；
根据所述目标第一AI单元和所述目标layer的信道信息，确定所述目标layer的第一信道特征信息。
可选地，处理器910执行的所述根据所述目标第一AI单元和所述目标layer的信道信息，确定所述目标layer的第一信道特征信息，包括：
根据所述目标第一AI单元和所述目标layer的信道信息，得到第二信道特征信息；
在所述第二信道特征信息等于所述目标layer对应的有效载荷长度的情况下，确定第一信道特征信息包括所述第二信道特征信息；或，
在所述第二信道特征信息大于所述目标layer对应的有效载荷长度的情况下，对所述第二信道特征信息进行第一后处理，得到与所述目标layer对应的有效载荷长度相匹配的第一信道特征信息；或，
在所述第二信道特征信息小于所述目标layer对应的有效载荷长度的情况下，对所述第二信道特征信息进行第二后处理，得到与所述目标layer对应的有效载荷长度相匹配的第一信道特征信息。
可选地，所述第一后处理包括以下至少一项：
截断处理；
调整对所述第一信道特征信息的量化规则。
可选地，所述第二后处理包括以下至少一项：
补零处理；
循环重复处理。
可选地，射频单元901，还用于向网络侧设备发送第二信息，其中，所述第二信息包括所述至少一个layer对应的所述第一信道特征信息。
可选地，所述第二信息还包括目标秩或所述目标秩的标识信息，所述目标秩为所述至少一个layer对应的目标信道的秩。
可以理解，本实施例中提及的各实现方式的实现过程可以参照如图4所示信息处理方 法实施例的相关描述，并达到相同或相应的技术效果，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5所示的方法实施例的步骤。该网络侧设备实施例与上述网络侧设备方法实施例对应，上述方法实施例的各个实施过程和实现方式均可适用于该网络侧设备实施例中，且能达到相同的技术效果。
具体地，本申请实施例还提供了一种网络侧设备。如图10所示，该网络侧设备1000包括：天线1001、射频装置1002、基带装置1003、处理器1004和存储器1005。天线1001与射频装置1002连接。在上行方向上，射频装置1002通过天线1001接收信息，将接收的信息发送给基带装置1003进行处理。在下行方向上，基带装置1003对要发送的信息进行处理，并发送给射频装置1002，射频装置1002对收到的信息进行处理后经过天线1001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1003中实现，该基带装置1003包括基带处理器。
基带装置1003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10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1005连接，以调用存储器1005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1006，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1000还包括：存储在存储器1005上并可在处理器1004上运行的指令或程序，处理器1004调用存储器1005中的指令或程序执行图7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4或图5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。在一些示例中，可读存储介质可以是非瞬态的可读存储介质。
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4或图5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4或图5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4所示信息处理方法的步骤，所述网络侧设备可用于执行如图5所示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计算机软件产品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。该计算机软件产品存储在存储介质(如ROM、RAM、磁碟、光盘等)中，包括若干指令，用以使得终端或者网络侧设备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，还可做出很多形式的实施方式，这些实施方式均属于本申请的保护之内。

Claims (25)

  1. 一种信息处理方法，包括：
    终端获取第一信息，其中，所述第一信息指示至少一个layer对应的第一信道特征信息的有效载荷信息；
    所述终端基于所述第一信息，采用目标第一AI单元对目标layer的信道信息进行第一处理，得到所述目标layer对应的所述第一信道特征信息，其中，所述目标layer对应的第一信道特征信息的有效载荷信息与所述目标第一AI单元的输出长度匹配，所述至少一个layer包括所述目标layer。
  2. 根据权利要求1所述的方法，其中，所述第一信息包括以下至少一项：
    与所述至少一个layer一一对应的有效载荷信息；
    与候选秩一一对应的有效载荷总量信息；
    有效载荷总量信息，其中，所述有效载荷总量信息为所述至少一个layer对应的第一信道特征信息的有效载荷的总和；
    第一关系，所述第一关系包括第一layer的有效载荷与第二layer的有效载荷之间的关系，所述至少一个layer包括所述第一layer和所述第二layer；
    与预设最大秩对应的预设最大有效载荷总量信息。
  3. 根据权利要求2所述的方法，其中，在所述第一信息包括所述第一关系和所述有效载荷总量信息的情况下，所述方法还包括：
    所述终端根据所述第一关系和所述有效载荷总量信息，确定与所述至少一个layer一一对应的有效载荷。
  4. 根据权利要求2所述的方法，其中，在所述第一信息包括所述第一关系以及与候选秩一一对应的有效载荷总量信息的情况下，所述方法还包括：
    所述终端根据与候选秩一一对应的有效载荷总量信息，确定与目标秩对应的目标有效载荷总量信息，其中，所述目标秩为与所述至少一个layer对应的目标信道的秩；
    所述终端根据所述第一关系和所述目标有效载荷总量信息，确定与所述至少一个layer一一对应的有效载荷。
  5. 根据权利要求2所述的方法，其中，在所述第一信息包括所述第一关系以及与预设最大秩对应的预设最大有效载荷总量信息的情况下，所述方法还包括：
    所述终端确定所述至少一个layer的有效载荷之和，等于所述预设最大有效载荷总量信息，或等于所述预设最大有效载荷总量信息与第一值的乘积，其中，所述第一值为目标秩与所述预设最大秩的比例值，所述目标秩为与所述至少一个layer对应的目标信道的秩；
    所述终端根据所述第一关系和所述至少一个layer的有效载荷之和，确定与所述至少一个layer一一对应的有效载荷。
  6. 根据权利要求1至5中任一项所述的方法，其中，所述有效载荷信息包括以下至少一 项：
    有效载荷长度；
    第一数据集的标识，所述第一数据集用于训练至少一个第一AI单元，不同的所述第一AI单元的输出信息的有效载荷长度不同，所述至少一个第一AI单元包括所述目标第一AI单元；
    所述目标第一AI单元的标识。
  7. 根据权利要求6所述的方法，其中，所述有效载荷长度包括以下至少一项：
    浮点数的个数；
    bit数。
  8. 根据权利要求1至7中任一项所述的方法，其中，所述终端基于所述第一信息，采用目标第一AI单元对目标layer的信道信息进行第一处理，得到所述目标layer对应的所述第一信道特征信息，包括：
    所述终端基于所述第一信息，确定与目标layer对应的目标有效载荷；
    所述终端获取输出信息长度与所述目标有效载荷匹配的目标第一AI单元；
    所述终端根据所述目标第一AI单元和所述目标layer的信道信息，确定所述目标layer的第一信道特征信息。
  9. 根据权利要求8所述的方法，其中，所述终端根据所述目标第一AI单元和所述目标layer的信道信息，确定所述目标layer的第一信道特征信息，包括：
    所述终端根据所述目标第一AI单元和所述目标layer的信道信息，得到第二信道特征信息；
    在所述第二信道特征信息等于所述目标layer对应的有效载荷长度的情况下，所述终端确定第一信道特征信息包括所述第二信道特征信息；或，
    在所述第二信道特征信息大于所述目标layer对应的有效载荷长度的情况下，所述终端对所述第二信道特征信息进行第一后处理，得到与所述目标layer对应的有效载荷长度相匹配的第一信道特征信息；或，
    在所述第二信道特征信息小于所述目标layer对应的有效载荷长度的情况下，所述终端对所述第二信道特征信息进行第二后处理，得到与所述目标layer对应的有效载荷长度相匹配的第一信道特征信息。
  10. 根据权利要求9所述的方法，其中，所述第一后处理包括以下至少一项：
    截断处理；
    调整对所述第一信道特征信息的量化规则。
  11. 根据权利要求9所述的方法，其中，所述第二后处理包括以下至少一项：
    补零处理；
    循环重复处理。
  12. 根据权利要求1至11中任一项所述的方法，所述方法还包括：
    所述终端向网络侧设备发送第二信息，其中，所述第二信息包括所述至少一个layer对应的所述第一信道特征信息。
  13. 根据权利要求12所述的方法，其中，所述第二信息还包括目标秩或所述目标秩的标识信息，所述目标秩为所述至少一个layer对应的目标信道的秩。
  14. 一种信息传输方法，所述方法包括：
    网络侧设备向终端发送第一信息，其中，所述第一信息指示至少一个layer对应的第一信道特征信息的有效载荷信息；
    其中，所述第一信息用于所述终端确定目标layer对应的第一信道特征信息的有效载荷，所述目标layer对应的第一信道特征信息基于所述目标layer对应的目标第一AI单元对所述目标layer的信道信息进行第一处理得到，所述目标layer对应的第一信道特征信息的有效载荷信息与所述目标第一AI单元的输出长度匹配，所述至少一个layer包括所述目标layer。
  15. 根据权利要求14所述的方法，其中，所述第一信息包括以下至少一项：
    与所述至少一个layer一一对应的有效载荷信息；
    与候选秩一一对应的有效载荷总量信息；
    有效载荷总量信息，其中，所述有效载荷总量信息为所述至少一个layer对应的第一信道特征信息的有效载荷的总和；
    第一关系，所述第一关系包括第一layer的有效载荷与第二layer的有效载荷之间的关系，所述至少一个layer包括所述第一layer和所述第二layer。
  16. 根据权利要求14或15所述的方法，其中，所述有效载荷信息包括以下至少一项：
    有效载荷长度；
    第一数据集的标识，所述第一数据集用于训练至少一个第一AI单元，不同的所述第一AI单元的输出信息的有效载荷长度不同，所述至少一个第一AI单元包括所述目标第一AI单元；
    所述目标第一AI单元的标识。
  17. 根据权利要求16所述的方法，其中，所述有效载荷长度包括以下至少一项：
    浮点数的个数；
    bit数。
  18. 根据权利要求14至17中任一项所述的方法，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信息，其中，所述第二信息包括所述至少一个layer对应的所述第一信道特征信息；
    所述方法还包括：
    所述网络侧设备基于第二AI单元，对所述至少一个layer对应的所述第一信道特征信息进行第二处理，得到所述至少一个layer对应的信道信息。
  19. 根据权利要求18所述的方法，其中，所述第二信息还包括目标秩或所述目标秩的标识信息，其中，所述目标秩为与所述至少一个layer对应的目标信道的秩。
  20. 根据权利要求18或19所述的方法，其中，所述网络侧设备基于第二AI单元，对所述至少一个layer对应的所述第一信道特征信息进行第二处理，得到所述至少一个layer对应的信道信息，包括：
    所述网络侧设备基于所述第一信息，从所述第二信息中获取目标layer对应的第一信道特征信息；
    所述网络侧设备根据所述第一信息，确定第二AI单元；
    所述网络侧设备根据所述第二AI单元和所述目标layer对应的所述第一信道特征信息，确定所述目标layer对应的信道信息。
  21. 一种信息处理装置，包括：
    第一获取模块，用于获取第一信息，其中，所述第一信息指示至少一个layer对应的第一信道特征信息的有效载荷信息；
    第一处理模块，用于基于所述第一信息，采用目标第一AI单元对目标layer的信道信息进行第一处理，得到所述目标layer对应的所述第一信道特征信息，其中，所述目标layer对应的第一信道特征信息的有效载荷信息与所述目标第一AI单元的输出长度匹配，所述至少一个layer包括所述目标layer。
  22. 一种信息处理装置，包括：
    第一发送模块，用于向终端发送第一信息，其中，所述第一信息指示至少一个layer对应的第一信道特征信息的有效载荷信息；
    其中，所述第一信息用于所述终端确定目标layer对应的第一信道特征信息的有效载荷，所述目标layer对应的第一信道特征信息基于所述目标layer对应的目标第一AI单元对所述目标layer的信道信息进行第一处理得到，所述目标layer对应的第一信道特征信息的有效载荷信息与所述目标第一AI单元的输出长度匹配，所述至少一个layer包括所述目标layer。
  23. 一种终端，包括处理器和存储器，所述存储器存储可在所述处理器上运行的程序或指令，所述程序或指令被所述处理器执行时实现如权利要求1至13中任一项所述的信息处理方法的步骤。
  24. 一种网络侧设备，包括处理器和存储器，所述存储器存储可在所述处理器上运行的程序或指令，所述程序或指令被所述处理器执行时，实现如权利要求14至20中任一项所述的信息传输方法的步骤。
  25. 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13中任一项所述的信息处理方法的步骤，或者实现如权利要求14至20中任一项所述的信息传输方法的步骤。
PCT/CN2024/088746 2023-04-24 2024-04-19 信息处理方法、信息传输方法、装置、终端及网络侧设备 WO2024222577A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202310455140.7A CN118842550A (zh) 2023-04-24 2023-04-24 信息处理方法、信息传输方法、装置、终端及网络侧设备
CN202310455140.7 2023-04-24

Publications (1)

Publication Number Publication Date
WO2024222577A1 true WO2024222577A1 (zh) 2024-10-31

Family

ID=93137623

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2024/088746 WO2024222577A1 (zh) 2023-04-24 2024-04-19 信息处理方法、信息传输方法、装置、终端及网络侧设备

Country Status (2)

Country Link
CN (1) CN118842550A (zh)
WO (1) WO2024222577A1 (zh)

Also Published As

Publication number Publication date
CN118842550A (zh) 2024-10-25

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
WO2023185978A1 (zh) 信道特征信息上报及恢复方法、终端和网络侧设备
WO2023185995A1 (zh) 信道特征信息传输方法、装置、终端及网络侧设备
WO2024222577A1 (zh) 信息处理方法、信息传输方法、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
WO2024088162A1 (zh) 信息传输方法、信息处理方法、装置和通信设备
WO2024032606A1 (zh) 信息传输方法、装置、设备、系统及存储介质
WO2024088161A1 (zh) 信息传输方法、信息处理方法、装置和通信设备
WO2024037380A1 (zh) 信道信息处理方法、装置、通信设备及存储介质
WO2024217495A1 (zh) 信息处理方法、信息处理装置、终端及网络侧设备
WO2023179476A1 (zh) 信道特征信息上报及恢复方法、终端和网络侧设备
WO2023179473A1 (zh) 信道特征信息上报及恢复方法、终端和网络侧设备
WO2024093999A1 (zh) 信道信息的上报和接收方法、终端及网络侧设备
WO2024104126A1 (zh) 更新ai网络模型的方法、装置和通信设备
WO2023134628A1 (zh) 传输方法、装置和设备
Santipach et al. Optimal feedback interval for temporally-correlated multiantenna channel
CN117411527A (zh) 信道特征信息上报及恢复方法、终端和网络侧设备
WO2023185980A1 (zh) 信道特征信息传输方法、装置、终端及网络侧设备
WO2024055974A1 (zh) Cqi传输方法、装置、终端及网络侧设备
CN117978304A (zh) 信息传输方法、信息处理方法、装置和通信设备
CN116939647A (zh) 信道特征信息上报及恢复方法、终端和网络侧设备
CN117978218A (zh) 信息传输方法、信息处理方法、装置和通信设备
CN117335849A (zh) 信道特征信息上报及恢复方法、终端和网络侧设备
CN116828496A (zh) 信道特征信息辅助上报及恢复方法、终端和网络侧设备