Channel feature information reporting and recovery method, terminal and network side device

Abstract

The application discloses a channel feature information reporting and recovery method, a terminal and a network side device, and belongs to the technical field of communication. The channel feature information reporting method of the application comprises the following steps: a terminal adopts a target AI network model to process target channel information into first channel feature information with a first length; and the terminal sends second channel feature information to a network side device, wherein the second channel feature information is part of the first channel feature information.

Description

Technical Field

[0001] This application belongs to the field of communication technology, specifically relating to a method for reporting and recovering channel characteristic information, a terminal, and network-side equipment. Background Technology

[0002] With the application of artificial intelligence (AI) in the field of communications, AI network models can be used to encode and decode channel state information (CSI).

[0003] However, the compressibility of channel information varies under different channel environments, resulting in different encoded information lengths. For example, simple channel information requires only a short coding length, while complex channel information requires a longer coding length. Furthermore, the weight parameters and even the network structure of the AI ​​network model differ for coded information of different lengths. In related technologies, it is necessary to train and use a separate AI network model for encoding and decoding each type of channel information. This results in the need to transmit multiple AI network models between the terminal and network-side devices, increasing the overhead of AI network model transmission. Summary of the Invention

[0004] This application provides a method for reporting and recovering channel feature information, a terminal, and a network-side device, enabling the terminal to adaptively use the same AI network model for encoding based on the length of the channel information, thereby reducing the overhead of transmitting the AI ​​network model between the terminal and the network-side device.

[0005] Firstly, a method for reporting channel feature information is provided, applied to a terminal. This method includes:

[0006] The terminal uses a target AI network model to process the target channel information into first channel feature information of the first length.

[0007] The terminal sends second channel feature information to the network-side device. The second channel feature information is a part of the first channel feature information.

[0008] Secondly, a channel feature information reporting device is provided for use in a terminal, the device comprising:

[0009] The first processing module is used to process the target channel information into first channel feature information of a first length using the target AI network model;

[0010] The first transmitting module is used to send second channel characteristic information to the network-side device. The second channel characteristic information is a part of the first channel characteristic information.

[0011] Thirdly, a channel feature information recovery method is provided, applied to network-side devices, the method comprising:

[0012] The network-side device receives second channel feature information from the terminal, wherein the second channel feature information includes a portion of the first channel feature information, and the first channel feature information is channel feature information of a first length obtained by the terminal processing the target channel information using the target AI network model;

[0013] The network-side device uses a first AI network model to process the second channel feature information to obtain the target channel information.

[0014] Fourthly, a channel feature information recovery device is provided, applied to network-side equipment, the device comprising:

[0015] The second receiving module is used to receive second channel feature information from the terminal, wherein the second channel feature information includes a portion of the first channel feature information, and the first channel feature information is channel feature information of a first length obtained by the terminal processing the target channel information using the target AI network model;

[0016] The second processing module is used to process the second channel feature information using the first AI network model to obtain the target channel information.

[0017] Fifthly, a terminal is provided, the terminal including a processor and a memory, the memory storing a program or instructions executable on the processor, the program or instructions, when executed by the processor, implementing the steps of the method as described in the first aspect.

[0018] In a sixth aspect, a terminal is provided, including a processor and a communication interface, wherein the processor is used to process target channel information into first channel feature information of a first length using a target AI network model, and the communication interface is used to send second channel feature information to a network-side device, the second channel feature information being a portion of the first channel feature information.

[0019] In a seventh aspect, a network-side device is provided, the network-side device including a processor and a memory, the memory storing a program or instructions executable on the processor, the program or instructions, when executed by the processor, implementing the steps of the method as described in the first aspect.

[0020] Eighthly, a network-side device is provided, including a processor and a communication interface, wherein the communication interface is used to receive second channel feature information from a terminal, the second channel feature information including a portion of first channel feature information, the first channel feature information being channel feature information of a first length obtained by the terminal processing target channel information using a target AI network model; the processor is used to process the second channel feature information using a first AI network model to obtain the target channel information.

[0021] A ninth aspect provides a communication system comprising: a terminal and a network-side device, wherein the terminal is configured to perform the steps of the channel feature information reporting method as described in the first aspect, and the network-side device is configured to perform the steps of the channel feature information recovery method as described in the third aspect.

[0022] In a tenth aspect, a readable storage medium is provided, on which a program or instructions are stored, which, when executed by a processor, implement the steps of the method described in the first aspect, or implement the steps of the method described in the third aspect.

[0023] Eleventhly, a chip is provided, the chip including a processor and a communication interface, the communication interface being coupled to the processor, the processor being used to run programs or instructions to implement the method as described in the first aspect, or to implement the method as described in the third aspect.

[0024] In a twelfth aspect, a computer program / program product is provided, which is stored in a storage medium and is executed by at least one processor to perform the steps of the method as described in the first or third aspect.

[0025] In this embodiment, the terminal uses a target AI network model to process the target channel information into first channel feature information of a first length; the terminal then sends second channel feature information to the network-side device, the second channel feature information being a portion of the first channel feature information. In this way, under different channel environments, the terminal can adaptively use the same AI network model for encoding based on the length of the channel information, and only report a portion of the channel feature information of the corresponding length to the network-side device. This allows the network side to use a pre-configured AI network model corresponding to that length to decode that portion of the channel feature information, and reduces the overhead of transmitting the AI ​​network model between the terminal and the network-side device. Attached Figure Description

[0026] Figure 1 This is a schematic diagram of the structure of a wireless communication system that can be applied to the embodiments of this application;

[0027] Figure 2This is a flowchart of a channel feature information reporting method provided in an embodiment of this application;

[0028] Figure 3 This is a schematic diagram of the neural network model architecture;

[0029] Figure 4 This is a schematic diagram of a neuron;

[0030] Figure 5 This is a schematic diagram of the power spectrum of the time delay path in the embodiments of this application;

[0031] Figure 6 This is a flowchart of a channel feature information recovery method provided in an embodiment of this application;

[0032] Figure 7a This is one of the schematic diagrams illustrating the correspondence between the decoder and channel feature information in the embodiments of this application;

[0033] Figure 7b This is the second schematic diagram illustrating the correspondence between the decoder and channel feature information in the embodiments of this application;

[0034] Figure 8 This is a schematic diagram of the structure of a channel feature information reporting device provided in an embodiment of this application;

[0035] Figure 9 This is a schematic diagram of the structure of a channel feature information recovery device provided in an embodiment of this application;

[0036] Figure 10 This is a schematic diagram of the structure of a communication device provided in an embodiment of this application;

[0037] Figure 11 This is a schematic diagram of the structure of a terminal provided in an embodiment of this application;

[0038] Figure 12 This is a schematic diagram of the structure of a network-side device provided in an embodiment of this application. Detailed Implementation

[0039] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0040] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such terms can be used interchangeably where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first" and "second" are generally of the same class, not limited in number; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0041] It is worth noting that the technologies described in this application are not limited to Long Term Evolution (LTE) / LTE-Advanced (LTE-A) systems, but can also be used in other wireless communication systems, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access (OFDMA), Single-carrier Frequency Division Multiple Access (SC-FDMA), and other systems. The terms "system" and "network" in this application are often used interchangeably, and the described technologies can be used with the systems and radio technologies mentioned above, as well as with other systems and radio technologies. The following description describes New Radio (NR) systems for illustrative purposes, and NR terminology is used in most of the following description; however, these technologies can also be applied to applications beyond NR systems, such as 6th generation (6G) radio systems. th Generation 6G communication system.

[0042] Figure 1This diagram illustrates a block diagram of a wireless communication system applicable to embodiments of this application. The wireless communication system includes a terminal 11 and a network-side device 12. Terminal 11 can be a mobile phone, tablet computer, laptop computer, personal digital assistant (PDA), handheld computer, netbook, ultra-mobile personal computer (UMPC), mobile internet device (MID), augmented reality (AR) / virtual reality (VR) device, robot, wearable device, vehicle-mounted device (VUE), pedestrian terminal (PUE), smart home (home devices with wireless communication capabilities, such as refrigerators, televisions, washing machines, or furniture), game console, personal computer (PC), ATM, or self-service machine, etc. Wearable devices include: smartwatches, smart bracelets, smart headphones, smart glasses, smart jewelry (smart bracelets, smart chains, smart rings, smart necklaces, smart anklets, smart anklets, etc.), smart wristbands, smart clothing, etc. It should be noted that the specific type of terminal 11 is not limited in this embodiment. Network-side equipment 12 may include access network equipment or core network equipment. Access network equipment 12 may also be referred to as radio access network equipment, radio access network (RAN), radio access network function, or radio access network unit. Access network equipment 12 may include base stations, WLAN access points, or WiFi nodes, etc. Base stations may be referred to as Node B, evolved Node B (eNB), access point, base transceiver station (BTS), radio base station, radio transceiver, Basic Service Set (BSS), Extended Service Set (ESS), home B node, home evolved B node, Transmitting Receiving Point (TRP), or any other suitable term in the field, as long as the same technical effect is achieved. The base station is not limited to specific technical terms. It should be noted that in this application embodiment, only a base station in an NR system is used as an example for description, and the specific type of base station is not limited.

[0043] In wireless communication technology, accurate Channel Quality Indicator (CSI) feedback is crucial for channel capacity. This is especially true for multi-antenna systems, where the transmitter can optimize signal transmission based on CSI to better match the channel conditions. For example, the CQI can be used to select an appropriate modulation and coding scheme (MCS) for link adaptation; the Precoding Matrix Indicator (PMI) can be used to implement eigenbeamforming, maximizing the strength of the received signal, or to suppress interference (such as inter-cell interference or multi-user interference). Therefore, since the introduction of multi-antenna technologies (such as Multi-Input Multi-Output (MIMO)), CSI acquisition has been a hot research topic.

[0044] Typically, network-side equipment transmits CSI-Reference Signals (CSI-RS) on certain time-frequency resources within a specific slot. The terminal performs channel estimation based on the CSI-RS, calculates the channel information for that slot, and feeds back the PMI (Program Information Management) to the base station via a codebook. The network-side equipment then combines the channel information based on the codebook information fed back by the terminal. Before the terminal reports CSI again, the network-side equipment uses this channel information for data precoding and multi-user scheduling.

[0045] To further reduce CSI feedback overhead, the terminal can change the PMI reporting for each sub-band to reporting PMI according to the delay domain (i.e., frequency domain). Since the channels in the delay domain are more concentrated, the PMI of all sub-bands can be approximately represented by PMI with less delay. This can be regarded as compressing the delay domain information before reporting.

[0046] Similarly, to reduce overhead, network-side devices can pre-encode CSI-RS 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.

[0047] In related technologies, using AI network models to compress channel information can improve the compression effect of channel feature information. AI network models can be implemented in various ways, such as neural networks, decision trees, support vector machines, and Bayesian classifiers. For ease of explanation, this application uses a neural network model as an example, but it does not limit the specific type of AI network model.

[0048] In this embodiment, the terminal uses a target AI network model with encoding function (i.e., the AI ​​network model in the encoder, which can also be called the encoder network model or the encoding AI network model) to compress and encode the channel information, and reports the encoded channel feature information to the network-side device (e.g., the base station). At the base station, a first AI network model with decoding function (i.e., the AI ​​network model in the decoder, which can also be called the decoder network model or the decoding AI network model) is used to decode the compressed channel feature information to recover the channel information. At this time, the base station's first AI network model and the terminal's target AI network model need to be jointly trained to achieve a reasonable matching degree. The neural network is formed by the terminal's encoder network model and the base station's decoder network model, and is jointly trained by the network-side device. After training is complete, the base station sends the encoder network model to the terminal.

[0049] The terminal estimates the CSI Reference Signal (CSI-RS), calculates the channel information based on this estimate, and then encodes the calculated channel information or the original estimated channel information through a coding network model to obtain the encoded result. Finally, the encoded result is sent to the base station. On the base station side, after receiving the encoded result, the base station inputs it into a decoding network model to recover the channel information.

[0050] However, the compressibility of channel information varies under different channel environments, resulting in different encoded channel information lengths. For example, simple channel information requires only a short encoding length, while complex channel information requires a longer encoding length. Consequently, the weight parameters and even the network structure of the AI ​​network model differ for encoded information of different lengths, necessitating the retraining of an AI network model matching that encoding length. Therefore, in related technologies, it is necessary to train and use a separate AI network model for encoding and decoding each type of channel information. This results in the need to transmit multiple AI network models between the terminal and network-side devices, increasing the transmission overhead of the AI ​​network models and the computational burden on the network-side devices when training and using separate AI network models for encoding and decoding each type of channel information.

[0051] In this embodiment, the terminal can use the target AI network model to process the channel information into fixed-length encoded information (i.e., first channel feature information) and report a portion of the first channel feature information to the network-side device. In this way, the terminal can select the second length of the second channel feature information to be reported according to the instructions of the network-side device and / or the terminal can choose independently. The terminal can also extract a portion of the second length from the first channel feature information and report it to the network-side device. In this way, the terminal only needs to use one encoding network to encode the channel information, and the network-side device only needs to use the decoding network corresponding to the second length to decode the portion of the second-length channel feature information.

[0052] It should be noted that, in implementation, the aforementioned terminal reports the second channel characteristic information to the network-side device, which can be done by including the second channel characteristic information in the CSI report and reporting it to the network-side device using the CSI reporting method. Specifically, the channel characteristic information can be PMI information. Of course, the aforementioned second channel characteristic information can also be reported to the network-side device in any other way. For ease of explanation, this embodiment uses the CSI reporting method as an example, and does not constitute a specific limitation.

[0053] Furthermore, in the embodiments of this application, the first length and the second length can be the number of bits of the corresponding channel feature information after quantization, or the number of coefficients included in the corresponding channel feature information before quantization. For ease of explanation, the embodiments of this application use the number of bits for both the first length and the second length as examples, which does not constitute a specific limitation.

[0054] The channel feature information reporting method, channel feature information recovery method, channel feature information reporting device, channel feature information recovery device, and communication equipment provided in this application will be described in detail below with reference to the accompanying drawings and through some embodiments and application scenarios.

[0055] Please see Figure 2 The channel feature information reporting method provided in this application embodiment can be executed by a terminal, which can be, for example, a terminal with the following characteristics: Figure 1 The various types of terminals listed in the document 11, or other than those listed below. Figure 1 Terminals other than those listed in the illustrated embodiments are not specifically limited herein. Figure 2 As shown, the channel feature information reporting method may include the following steps:

[0056] Step 201: The terminal uses the target AI network model to process the target channel information into first channel feature information of the first length.

[0057] In implementation, the aforementioned target AI network model may include various types of AI algorithm modules, such as neural networks, decision trees, support vector machines, Bayesian classifiers, etc., without specific limitations. For ease of explanation, the following embodiments use a neural network model as an example of the AI ​​algorithm model, which does not constitute a specific limitation.

[0058] like Figure 3 As shown, the neural network model includes an input layer, a hidden layer, and an output layer, which can generate output information based on the input and output information (X1~X2) obtained from the input layer. n Predict the possible output (Y). A neural network model consists of a large number of neurons, such as... Figure 4 As shown, the parameters of the neuron include: input parameters a1 to a2. K The parameters include weights w, bias b, and activation function σ(z), and the output value a obtained from these parameters. Common activation functions include the sigmoid function, the hyperbolic tangent function, and the rectified linear unit (ReLU) function, etc. The z in the above function σ(z) can be calculated by the following formula:

[0059] z = a1w1 + ... + a k w k +a K w K +b

[0060] Where K represents the total number of input parameters.

[0061] The parameters of a neural network are optimized using optimization algorithms. Optimization algorithms are a class of algorithms that 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 construct a neural network model f(.). With the neural network model, we can obtain the predicted output f(x) based on the input x, and calculate the difference between the predicted value and the true value (f(x) - Y), which is the loss function. Our goal is to find suitable W and b that minimize the value of the loss function. The smaller the loss value, the closer our model is to the reality.

[0062] Most common optimization algorithms are based on backpropagation. The basic idea of ​​backpropagation is that the learning process consists of two parts: forward propagation of the signal and backward propagation of the error. During forward propagation, input samples are introduced from the input layer, processed layer by layer by the hidden layers, and then transmitted to the output layer. If the actual output of the output layer does not match the expected output, the process transitions to backpropagation. Backpropagation transmits the output error in some form back through the hidden layers to the input layer, distributing the error to all units in each layer, thus obtaining the error signal for each unit. This error signal serves as the basis for adjusting the weights of each unit. This process of adjusting the weights through forward and backward propagation is cyclical. This continuous adjustment of weights is the learning and training process of the network. This process continues until the error in the network output is reduced to an acceptable level, or until a predetermined number of learning iterations are completed.

[0063] Common optimization algorithms include gradient descent, stochastic gradient descent (SGD), mini-batch gradient descent, momentum method, Nesterov (which represents stochastic gradient descent with momentum), adaptive gradient descent (Adagrad), adaptive learning rate adjustment (Adadelta), root mean square prop (RMSprop), and adaptive momentum estimation (Adam).

[0064] During error backpropagation, these optimization algorithms calculate the gradient based on the error / loss obtained from the loss function with respect to the current neuron, add the learning rate, previous gradients / derivatives / partial derivatives, etc., and then pass the gradient to the previous layer.

[0065] In implementation, the target AI network model can be used to encode channel information, enabling it to encode channel information under various channel environments into a first channel feature information of a fixed length (i.e., a first length). In implementation, this first length can be a relatively long length. If the encoded result of the channel information under a certain channel environment is shorter than the first length, zero-padding, redundant coding, or any other method can be used to supplement the encoded result of the channel information under that channel environment to the first length.

[0066] Optionally, before the terminal processes the target channel information into first channel feature information of a first length using the target AI network model, the method further includes:

[0067] The terminal performs channel estimation on the Channel State Information-Reference Signal (CSI-RS) or Tracking Reference Signal (TRS) to obtain the target channel information; or...

[0068] The terminal preprocesses the channel information obtained from channel estimation to obtain the target channel information.

[0069] In this embodiment, the target channel information encoded using the target AI network model can be the channel information obtained by the terminal estimating the CSI-RS channel or TRS channel, or the channel information obtained by the terminal performing certain preprocessing on the estimated channel information. No specific limitation is made here.

[0070] Step 202: The terminal sends second channel feature information to the network-side device. The second channel feature information is a part of the first channel feature information.

[0071] In practice, the aforementioned second channel feature information being a part of the first channel feature information can be achieved by the terminal extracting a portion of the first channel feature information as the second channel feature information.

[0072] In implementation, the terminal can send the second bit of the second channel feature information to the network-side device; or, the terminal can send M second channel feature information of different lengths or contents to the network-side device in M ​​channel feature information reporting processes. That is, one second channel feature information is reported in each channel feature information reporting process, but the length or content of the second channel feature information reported in different channel feature information reporting processes is different.

[0073] <As an optional implementation method>

[0074] The terminal sends second channel characteristic information to the network-side device, including:

[0075] The terminal sends a second channel feature information of a second length extracted from the first channel feature information to the network-side device, wherein the second length is less than or equal to the first length.

[0076] In this embodiment, the terminal only reports the second channel feature information to the network-side device, and the length of the second channel feature information can be a second length.

[0077] In implementation, the second length can be determined based on instructions from the network-side device, and / or by the terminal. Correspondingly, when the network-side device receives the second channel feature information of the second length, it can use the first AI network model corresponding to the second length to decode the second channel feature information, thereby recovering the channel information.

[0078] It should be noted that during wireless communication, the terminal can report channel feature information at different time domain locations, and the second length corresponding to each channel feature information report can be the same or different, without specific limitations. For example, if the first channel feature information of the first length can be divided into K channel feature information segments, then the second channel feature information of the second length can include 1 to K channel feature information segments.

[0079] In one possible implementation, when the network-side device receives the second channel feature information currently reported by the terminal, it can input the second channel feature information into the first AI network model so that the first AI network model can process the second channel feature information to recover the channel information.

[0080] In another possible implementation, the network-side device can store historical channel feature information reported by the terminal within a historical time period. When receiving the second channel feature information currently reported by the terminal, it can update the historical channel feature information based on the second channel feature information, and then process the updated historical channel feature information using a first AI network model to obtain the target channel information. For example, assuming the terminal reports channel feature information cyclically in the order of second lengths N0, N1, ..., when the network-side device receives the second channel feature information of length N0 for the first time, it performs channel recovery based on the second channel feature information of length N0. Then, when the network-side device receives the second channel feature information of length N1, it performs channel recovery based on both the second channel feature information of length N0 and the second channel feature information of length N1. Furthermore, in the next cycle, when the network-side device receives the second channel feature information of length N0, it replaces the second channel feature information of length N0 in the historical channel feature information with the second channel feature information of length N0, and uses the updated historical channel feature information for channel recovery.

[0081] For example: the terminal first reports second channel feature information of length N0, then reports second channel feature information of length N1-N0, then reports second channel feature information of length N2-N1, and so on in a loop. After receiving the second channel feature information, the base station decodes it using all of the second channel feature information. That is, if only second channel feature information of length N0 is available, it uses that length N0; if both N0 and N1-N0 are available, it combines the N0 and N1-N0 lengths to form second channel feature information of length N1, and decodes it, iterating until a first channel feature information of length L is formed. In the next loop, it still decodes using length L, and replaces the corresponding N0 channel feature information in the historical channel feature information with the new N0, updating and iterating accordingly.

[0082] In practical applications, the target AI network model and the first AI network model can be jointly trained by network-side devices, and one target AI network model can correspond to at least one first AI network model. Each first AI network model has its own corresponding length. Thus, after determining the second length, the first AI network model corresponding to the second length can be used to decode the second channel feature information to achieve channel recovery.

[0083] Optionally, the second channel feature information of the second length includes at least one of the following:

[0084] The first N bits or coefficients in the first channel feature information, where N is equal to the number of bits corresponding to the second length or the number of coefficients corresponding to the second length;

[0085] The first channel feature information contains N bits or coefficients whose importance level is greater than a preset level;

[0086] The first channel feature information includes N bits or coefficients in addition to the reported channel feature information.

[0087] Option 1: If the second channel feature information of the second length includes the first N bits or coefficients of the first channel feature information, the terminal directly reports the second channel feature information of N bits or coefficients according to the order of each bit in the first channel feature information. For example, if N equals 100 bits, then the first 100 bits of the first channel feature information are reported.

[0088] Option 2: If the second channel feature information of the second length includes N bits or coefficients in the first channel feature information whose importance level is greater than a preset level, then each bit or bit interval or coefficient contained in the first channel feature information can be divided into importance levels. In this way, the terminal can prioritize reporting the N bits or coefficients with higher importance levels in the first channel feature information to the network-side device.

[0089] Option 3, where the second channel feature information of the second length includes N bits or coefficients from the first channel feature information excluding the already reported second channel feature information, differs from Option 1 in that, during multiple channel feature information reports by the terminal, Option 3 avoids duplicate reporting of channel feature information. For example, if the terminal reports channel feature information twice, with the first report corresponding to a second length of 100 bits and the second report corresponding to a second length of 200 bits, then with Option 1, the terminal can report bits 0-99 of the first channel feature information the first time and bits 0-199 the second time; while with Option 3, the terminal can report bits 0-99 of the first channel feature information the first time and the remaining 200 bits after bit 100 the second time.

[0090] It should be noted that, in implementation, at least two of options one to three above can be combined. For example, when the second channel feature information of the second length includes option one and option three, the second channel feature information reported by the terminal for the first time can be bits 0 to (N0-1) of the first channel feature information, and the second channel feature information reported for the second time can be the 0 to (N0-1) part of the first channel feature information and the length N1-N0 in N0-(L-1), where L represents the first length, N0 represents the second length used in the first report, and N1 represents the second length used in the second report. In implementation, the second channel feature information reported for the second time can include the bit content of the first report, and can also include additional content of length N1-N0, and the 0 to (N0-1) part and the length N1-N0 in N0-(L-1) can be two consecutive or discontinuous segments of channel feature information bits.

[0091] In practice, the second length can be indicated by the network-side device or determined by the terminal according to the conditions agreed upon in the protocol.

[0092] As an optional implementation, before the terminal sends the second channel feature information of a second length extracted from the first channel feature information to the network-side device, the method further includes:

[0093] The terminal receives first indication information from the network-side device, wherein the first indication information indicates the second length and / or a first encoding identifier, and the first encoding identifier is associated with the second length.

[0094] In implementation, the aforementioned first encoding identifier can be understood as the identifier information of the encoding length corresponding to the first AI network model. Thus, based on this first encoding identifier, the required encoding length of the second channel feature information to be reported by the terminal can be determined. For example, one target AI network model corresponds to K first AI network models, where the inputs of the K first AI network models are part or all of the channel feature information output by the target AI network model, and the input lengths of the K first AI network models are N1, N2, and so on, respectively. K Then the first encoding identifier mentioned above can be N i In the context of i or i-1, the input lengths of the K first AI network models can be agreed upon by the protocol. Both the network-side device and the terminal know the input lengths of the K first AI network models. Thus, when the network-side device indicates an encoding identifier to the terminal, the terminal can determine the second length to be reported based on this identifier, thereby extracting a length of N from the encoded first channel feature information of the first length. i The part where i is the first encoded identifier indicated by the network-side device.

[0095] The first indication information is configured by higher-layer signaling, for example, by configuring the second length in advance through Radio Resource Control (RRC) signaling or Medium Access Control (MAC) control element (CE), so that the terminal can report the same length of second channel feature information in each channel feature information report.

[0096] Of course, when the second channel feature information is carried in the Channel State Information (CSI) report, the first indication information mentioned above can also be the indication information in the CSI report configuration, or the network-side device can configure the length corresponding to each CSI resource. In this case, the second length indicated by the first indication information can be understood as the length corresponding to the CSI resource used by the terminal. Here, the first indication information is not specifically limited.

[0097] In this embodiment, the network-side device can instruct the terminal to have a second length, so that the terminal can extract the second channel feature information of the corresponding length from the first channel feature information according to the instruction of the network-side device and report it to the network-side device.

[0098] As another optional implementation, before the terminal sends the second channel feature information of a second length extracted from the first channel feature information to the network-side device, the method further includes:

[0099] The terminal determines the second length based on at least one of the channel characteristics and channel conditions corresponding to the target channel information.

[0100] In implementation, the terminal determines the second length based on at least one of the channel characteristics and channel conditions corresponding to the target channel information. This can be achieved by the terminal determining the channel characteristics of the target channel based on the target channel information, thereby determining the second length corresponding to the channel characteristics; and / or, the terminal can determine whether the channel quality of the target channel meets preset channel conditions based on the target channel information, thereby determining the corresponding second length based on the determination result.

[0101] In this embodiment, the difference from the embodiment in which the network-side device indicates the second length to the terminal is that the terminal can determine the second length based on the target channel information, and then report the second channel feature information of the second length to the network-side device.

[0102] In one optional implementation, the terminal determines the second length based on the channel characteristics corresponding to the target channel information, including:

[0103] The terminal determines, based on a first association relationship, that the length associated with the target channel parameter values ​​of the target channel corresponding to the target channel information is the second length, wherein the first association relationship includes the association relationship between each value or range of the target channel parameter and the length; or...

[0104] The terminal determines, based on the second association relationship, the length of the encoding identifier associated with the value of the target channel parameter of the target channel corresponding to the target channel information is the second length, wherein the second association relationship includes the association relationship between each value or range of the target channel parameter and the encoding identifier.

[0105] In practice, in addition to the first indication information mentioned above indicating the second length or the first coding identifier corresponding to the second length, the terminal can also determine the second length associated with the target channel parameters based on the correlation between the channel parameter values ​​and the length or coding identifier.

[0106] The target channel parameters of the target channel may include at least one of the following:

[0107] The target channel is either Line of Sight (LOS) propagation or Non-Line of Sight (NLOS) propagation;

[0108] The number of effective delay paths of the target channel;

[0109] The delay spacing between two target paths of the target channel;

[0110] The number of effective beams of the target channel, where the effective beams include the beams corresponding to the orthogonal basis of the Discrete Fourier Transform (DFT) with power greater than the first threshold.

[0111] Option 1: When the above target channel is LOS propagation, its channel quality is better than that in NLOS propagation. When the target channel is LOS propagation, shorter second channel characteristic information can be reported, while when the target channel is NLOS propagation, longer second channel characteristic information can be reported. For example, assuming K = 2, N0 is used for LOS and N1 is used for NLOS, N0 < N1. Specifically, N1 = L, where K represents the number of value selections of the second length, and L represents the first length;

[0112] Option 2: The more the number of effective delay paths of the target channel, the longer the reported second channel characteristic information can be. The effective delay paths include at least one of the following: the delay paths with corresponding power or amplitude greater than the first threshold, and the delay paths with corresponding power or amplitude being the maximum value. For example: As shown in the power spectrum diagram, assuming the effective delay paths include the delay paths with power or amplitude greater than the first threshold, the effective delay paths are four paths located at the time delay domain positions: -2, 0, 1, 4 respectively; assuming the effective delay paths include the delay paths with power or amplitude being the maximum value, the effective delay paths are three paths located at the time delay domain positions: -2, 0, 4 respectively. Figure 5 As shown in the power spectrum diagram, assuming the effective delay paths include the delay paths with power or amplitude greater than the first threshold, the effective delay paths are four paths located at the time delay domain positions: -2, 0, 1, 4 respectively; assuming the effective delay paths include the delay paths with power or amplitude being the maximum value, the effective delay paths are three paths located at the time delay domain positions: -2, 0, 4 respectively.

[0113] Option 3: The greater the delay spacing between two target paths of the target channel, the longer the reported second channel characteristic information can be. The two target paths can be any two paths of the target channel. For example: the paths corresponding to two maximum values. The delay spacing between the two target paths can reflect the concentration intensity of the paths included in the target channel in the frequency domain.

[0114] Option 4: The more the number of effective beams of the target channel, the longer the reported second channel characteristic information can be.

[0115] In this embodiment, the terminal can determine the second length according to the value of the target channel parameter of the detected target channel, so that the second channel characteristic information of the reported second length matches the channel state of the target channel.

[0116] In another alternative implementation, the method further includes:

[0117] The terminal receives relevant information from K first AI network models from the network-side device, wherein the K first AI network models correspond to the target AI network model, and the K first AI network models are used to decode channel feature information of their respective lengths.

[0118] The terminal determines the second length based on channel conditions, including:

[0119] The terminal extracts K second channel feature information from the first channel feature information, and processes the second channel feature information of corresponding length into first channel information through K first AI network models respectively;

[0120] The terminal acquires the matching degree between K pieces of the first channel information and the target channel information;

[0121] When the terminal determines that the matching degree between the target first channel information and the target channel information meets a preset condition, it determines that the second length is equal to the length of the first AI network model used to process and obtain the target first channel information, wherein the K first channel information obtained by the K first AI network models include the target first channel information.

[0122] In implementation, the relevant information of the aforementioned first AI network model can include model parameters, model configuration, model identification information, etc. The terminal can determine which first AI network model the network-side device will use to decode the second channel feature information based on this relevant information. Then, the terminal can use the first AI network model or a simplified network model of the first AI network model to simulate the decoding process of the network-side device for the corresponding length of second channel feature information, thereby comparing the simulated decoding result (i.e., the first channel information) with the target channel information to determine the degree of matching between the two.

[0123] The higher the degree of matching between the first channel information and the target channel information, the more accurately the first AI network model can recover the target channel information. In practical applications, the degree of matching between the target first channel information and the target channel information meets the preset conditions, which can be understood as: the decoding result of the first AI network model that derives the target first channel information on the corresponding length of the second channel feature information can meet service requirements or communication quality requirements, etc.

[0124] Optionally, the terminal device can traverse each first AI network model to determine whether the degree of matching between the decoding result of the second channel feature information of each first AI network model and the target channel information meets the preset conditions. In implementation, there may be cases where the degree of matching between the first channel information obtained by at least two first AI network models and the target channel information meets the preset conditions. In this case, the smallest one can be selected from the lengths corresponding to the at least two first AI network models as the second length, thereby extracting the second channel feature information of the second length from the first channel feature information and reporting it to the network-side device.

[0125] Of course, the terminal device can also sequentially determine the degree of matching between the decoding result of the second channel feature information of the corresponding length of the first AI network model and the target channel information, and determine the second length as the length of the first AI network model if the degree of matching between the decoding result of the second channel feature information of the corresponding length of a certain first AI network model and the target channel information meets the preset conditions. In this way, the amount of calculation for determining the second length can be reduced.

[0126] Optionally, the degree of matching between the target first channel information and the target channel information satisfies a preset condition including at least one of the following:

[0127] The correlation between the target first channel information and the target channel information is greater than or equal to a preset correlation.

[0128] The channel capacity of the target first channel information is greater than or equal to a first preset value multiple of the channel capacity of the target channel information, wherein the first preset value is greater than 0 and less than or equal to 1.

[0129] The target first channel information is the channel quality indicator (CQI) among the K first channel information that is the same as or closest to the CQI of the target channel information;

[0130] The target first channel information is one of the K first channel information that has the same or closest modulation and coding scheme (MCS) as the target channel information.

[0131] In practice, the correlation between the aforementioned target first channel information and the target channel information can be the similarity of the information content of the target first channel information and the target channel information, such as the mutual information between the target first channel information and the target channel information.

[0132] Furthermore, the second channel feature information may contain only a portion of the first channel feature information, and the first channel information may contain only a portion of the target channel information. Therefore, the channel capacity, CQI, MCS, etc., contained in the channel information decoded based on second channel feature information of different lengths and / or positions can be different. In this case, it is preferable to select the length of the first AI network model whose channel capacity of the derived first channel information is greater than a first preset value multiple of the channel capacity of the target channel information as the second length. The first preset value can be a value indicated by the network-side device or agreed upon by the protocol. When the channel capacity meets the first preset value, the second channel feature information of this second length can decode channel information that meets service requirements and / or channel quality requirements. Additionally, the first channel information closest to the CQI and / or MCS in the target channel information can also be used as the target first channel information.

[0133] Optionally, the channel feature information reporting method further includes:

[0134] The terminal sends a second indication message to the network-side device, the second indication message indicating the second length.

[0135] In this embodiment, when the terminal determines the second length, it also reports the second length to the network-side device so that the network-side device can directly use the first AI network model corresponding to the second length to decode the second channel feature information.

[0136] It should be noted that, in practice, after the terminal determines the second length, the terminal may not report the second length to the network-side device. In this case, the network-side device can detect the length of the second channel feature information reported by the terminal, and then use the first AI network model corresponding to the length to decode the second channel feature information. No specific limitations are made here.

[0137] In practice, a CSI report may include a fixed-length CSI section (e.g., CSI Part 1) and a variable-length CSI section (e.g., CSI Part 2). In this case, the aforementioned second indication information may be carried in either the fixed-length or variable-length CSI section of the CSI report.

[0138] In addition, the second channel feature information of the second length can also be located in the variable-length CSI part, or part of it can be located in the fixed-length CSI part and the other part can be located in the variable-length CSI part.

[0139] Specifically, given that the range of values ​​for the second length can include multiple values ​​between the minimum length and the first length, and the fixed-length CSI section in the CSI report often only accommodates a small portion of the second channel feature information, the minimum length portion of the second channel feature information can be placed in the fixed-length CSI section of the CSI report, while the other portions of the second channel feature information are placed in the variable-length CSI section of the CSI report. In implementation, the aforementioned minimum length can be less than or equal to the second length, that is, the minimum length can be equal to the smallest possible value of the second length. For example, suppose the input lengths of the K first AI network models are arranged in ascending order as N1 to N2. K Then the minimum length can be equal to N1. In implementation, N2 to N K Both contain channel feature information corresponding to N1, so that the fixed-length CSI part in the CSI report can carry the content of the 0th to (N1-1)th bits of the first channel feature information. When the second length is greater than N1, the content of the second channel feature information after the (N1-1)th bit can be placed in the variable-length CSI part of the CSI report.

[0140] Of course, the above examples are merely illustrations. In practical applications, the position of the minimum length portion of the second channel feature information within the second channel feature information can be determined by the protocol. For example, the minimum length portion of the second channel feature information may include at least one of the following:

[0141] The first X bits of the second channel feature information, where X is equal to the minimum length;

[0142] The second channel feature information contains X bits whose importance level is greater than the preset level.

[0143] For example, the second indication information is carried in a fixed-length CSI portion of the CSI report, and the second channel characteristic information of the second length is carried in a variable-length CSI portion of the CSI report.

[0144] Example 2: The minimum length portion of the second channel feature information of the second length and the second indication information are carried in the fixed-length CSI portion of the CSI report, and the variable-length portion of the second channel feature information of the second length other than the minimum length portion is carried in the variable-length CSI portion of the CSI report.

[0145] Example 3: The second indication information and the second channel characteristic information of the second length are both carried in the variable-length CSI section of the CSI report.

[0146] <As an optional implementation method two>

[0147] The terminal sends second channel characteristic information to the network-side device, including:

[0148] In each of the M channel feature information reports, the terminal sends a second channel feature information extracted from the first channel feature information to the network-side device, where M is an integer greater than 1. The lengths of the second channel feature information reported in the M channel feature information reports are all different, or the contents of the second channel feature information reported in the M channel feature information reports are all different.

[0149] In implementation, the aforementioned M second channel feature information items can be reported in M ​​installments, meaning the terminal reports one second channel feature information item each time. Of course, in practical applications, the terminal can also report at least two second channel feature information items at once; this is not specifically limited here.

[0150] For example, in M ​​channel feature information reports, the terminal can send second channel feature information extracted from the first channel feature information to the network-side device in ascending order of length. In this way, the network-side device can gradually improve the accuracy of channel recovery during the channel recovery process based on the received second channel feature information.

[0151] For example, in M ​​channel feature information reports, the terminal can determine the corresponding second length for each of the M reports based on the current channel environment. In this case, the second lengths of the M second channel feature information reports can be the same or different. After a period of time, the network-side device may acquire M second channel feature information reports of different lengths (i.e., historical channel feature information includes the M second channel feature information reports of different lengths submitted by the terminal within a historical time period). In the subsequent channel recovery process, the network-side device can update the historical channel feature information based on the terminal's currently submitted second channel feature information and perform channel recovery based on the updated historical channel feature information. In other words, the length of all historical channel feature information can be the same as the length of the first channel feature information; however, part of the historical channel feature information contains the current channel feature information, and another part contains channel feature information previously submitted by the terminal.

[0152] Optionally, when the second channel feature is carried in the CSI report, the time-frequency resource location reported by the M channel feature information is configured by a CSI report configuration information;

[0153] or,

[0154] The time-frequency resource locations reported by the M channel feature information are configured by the M CSI report configuration information.

[0155] In one optional implementation, the time-frequency resource locations for the aforementioned M channel feature information reports can be configured in the same CSI report config, that is, one CSI report config configures the time-frequency resource locations for M channel feature information reports, and the terminal reports the second channel feature information at each time-frequency resource location.

[0156] This simplifies the configuration process for the time-frequency resource locations of the Mth channel feature information reporting.

[0157] In another optional implementation, the time-frequency resource locations reported by the aforementioned M channel feature information can be configured in M ​​CSI report configuration files, that is, configure M CSI report configuration files, each of which can be used to configure the time-frequency resource location for one channel feature information report.

[0158] This allows for more flexible configuration of the time and frequency resource locations for each channel feature information report.

[0159] As an optional implementation, the lengths of the second channel feature information reported by the M channel feature information are sequentially increased from the minimum length to the first length;

[0160] or,

[0161] The second channel feature information reported by the Mth channel feature information includes non-overlapping portions of the first channel feature information, and the sum of the lengths of the second channel feature information reported by the Mth channel feature information is equal to the first length.

[0162] In an optional implementation, the lengths of the second channel feature information reported in the M channel feature information reports increase sequentially from the minimum length to the first length. In this case, during the M channel feature information reports, the terminal sends the second channel feature information extracted from the first channel feature information to the network-side device, including:

[0163] In the M channel feature information reporting, the terminal sends the second channel feature information to the network-side device in ascending order of length.

[0164] On the network side, network devices can use the second channel feature information reported sequentially from shortest to longest to gradually improve the accuracy of the recovered channel information.

[0165] In another optional implementation, the second channel feature information reported by the M-times of channel feature information respectively includes non-overlapping portions of the first channel feature information, and the sum of the lengths of the second channel feature information reported by the M-times of channel feature information is equal to the first length. In this case, the terminal, in the M-times of channel feature information reporting, sends the second channel feature information extracted from the first channel feature information to the network-side device, including:

[0166] In the M channel feature information reporting, the terminal sends the second channel feature information to the network-side device according to the order in which the second channel feature information is arranged in the first channel feature information.

[0167] In this way, the terminal can report non-overlapping channel feature information content during multiple channel feature information reporting processes. On the network side, the network-side device can store the historical channel feature information already reported by the terminal, and when the terminal reports the second channel feature information, it can use the second channel feature information to update the previously reported historical channel feature information, and use the updated historical channel feature information as a whole to recover the channel information. This can reduce the amount of information in the second channel feature information reported by the terminal, and can also increase the amount of information in the historical channel feature information used by the network-side device when performing channel recovery.

[0168] In this embodiment, the terminal uses a target AI network model to process the target channel information into first channel feature information of a first length; the terminal then sends second channel feature information to the network-side device, the second channel feature information being a portion of the first channel feature information. In this way, under different channel environments, the terminal can adaptively use the same AI network model for encoding based on the length of the channel information, and only report a portion of the channel feature information of the corresponding length to the network-side device. This allows the network side to use a pre-configured AI network model corresponding to that length to decode that portion of the channel feature information, and reduces the overhead of transmitting the AI ​​network model between the terminal and the network-side device.

[0169] Please see Figure 6 The channel feature information recovery method provided in this application embodiment can be executed by a network-side device, and the terminal can be such as... Figure 1 The various types of network-side devices listed in the document 12, or other than those listed below, are also included. Figure 1 Other network-side devices besides those listed in the illustrated embodiments are not specifically limited herein. For example... Figure 6 As shown, the channel feature information recovery method may include the following steps:

[0170] Step 601: The network-side device receives second channel feature information from the terminal, wherein the second channel feature information includes a portion of the first channel feature information, and the first channel feature information is channel feature information of a first length obtained by the terminal processing the target channel information using the target AI network model.

[0171] In implementation, the aforementioned first channel characteristic information, second channel characteristic information, and target channel information are respectively compared with, for example, as shown in the figure. Figure 2 The first channel feature information, the second channel feature information, and the target channel information in the method embodiment shown have the same meaning, and will not be repeated here.

[0172] Step 602: The network-side device uses a first AI network model to process the second channel feature information to obtain the target channel information.

[0173] In implementation, the network-side device uses a first AI network model to process the second channel feature information to obtain the target channel information. This can be achieved by the network-side device using a first AI network model corresponding to the length of the second channel feature information to process the second channel feature information to obtain the target channel information; or by the network-side device using at least two first AI network models corresponding to the second channel feature information to process the second channel feature information to obtain the target channel information.

[0174] As an optional implementation, the network-side device receives second channel characteristic information from the terminal, including:

[0175] The network-side device receives second channel feature information of a second length extracted from the first channel feature information from the terminal, wherein the second length is less than or equal to the first length.

[0176] The second channel feature information of the second length mentioned above and such Figure 2 The second channel feature information of the second length in the method embodiment shown has the same meaning, and also indicates that the terminal can determine the second length according to the instructions of the network-side device or according to the conditions agreed upon in the protocol, and report the second channel feature information of the second length to the network-side device. No specific limitation is made here.

[0177] In one possible implementation, the network-side device uses a first AI network model to process the second channel feature information to obtain the target channel information, including:

[0178] The network-side device uses a first AI network model corresponding to the second channel feature information of the second length to process the second channel feature information of the second length, thereby obtaining the target channel information.

[0179] For example: Figure 7a As shown, assuming one encoder corresponds to five decoders (decoder 1 to decoder 5 respectively), and each decoder has its own first AI network model, and each first AI network model has its own corresponding second length: N0 to N4. In this way, each decoder can obtain the target channel information by decoding the second channel feature information of its own corresponding second length.

[0180] In this embodiment, the network-side device uses a first AI network model corresponding to the second length for channel recovery each time.

[0181] In another possible implementation, the network-side device uses a first AI network model to process the second channel feature information to obtain the target channel information, including:

[0182] When the network-side device stores the historical channel feature information of the terminal, the network-side device updates the historical channel feature information according to the second channel feature information of the second length;

[0183] The network-side device uses a first AI network model to process the updated historical channel feature information to obtain the target channel information.

[0184] In implementation, the aforementioned network-side device processes the updated historical channel feature information using a first AI network model to obtain the target channel information. This can be achieved by using a first AI network model corresponding to the length of the updated historical channel feature information to process the updated historical channel feature information and obtain the target channel information. For example: Figure 7a As shown, assuming that the bit length of the updated historical channel feature information corresponds to that of decoder 5, the first AI network model in decoder 5 is used to decode the updated historical channel feature information.

[0185] Of course, the network-side device described above can also process the updated historical channel feature information using a first AI network model to obtain the target channel information, or it can process the updated historical channel feature information using at least one first AI network model corresponding to the length of the updated historical channel feature information and / or its position in the first channel feature information to obtain the target channel information, for example: Figure 7bAs shown, assuming one encoder corresponds to four decoders (decoders 1 to 4), and each decoder has its own first AI network model, and the second length corresponding to each first AI network model is the same (assuming the second length is N bits) but they do not overlap, if the updated historical channel feature information includes the second channel feature information corresponding to decoders 1 and 2 respectively, the network-side device can use the first AI network model in decoder 1 to decode the corresponding second channel feature information, and use the first AI network model in decoder 2 to decode the corresponding second channel feature information. Finally, the decoding results of decoders 1 and 2 are combined to obtain the target channel information. That is, the incremental part of the channel feature information corresponding to each decoder is combined with the results of multiple decoders to recover the channel information.

[0186] Optionally, the second channel feature information of the second length includes at least one of the following:

[0187] The first N bits or coefficients in the first channel feature information, where N is equal to the number of bits corresponding to the second length or the number of coefficients corresponding to the second length;

[0188] The first channel feature information contains N bits or coefficients whose importance level is greater than a preset level;

[0189] The first channel feature information includes N bits or coefficients in addition to the reported channel feature information.

[0190] Optionally, before the network-side device receives second channel feature information of a second length extracted from the first channel feature information from the terminal, the method further includes:

[0191] The network-side device sends a first indication message to the terminal, wherein the first indication message indicates the second length and / or a first encoding identifier, and the first encoding identifier is associated with the second length.

[0192] Optionally, the first indication information is configured by higher-level signaling; or,

[0193] The second channel feature information is carried in the Channel State Information (CSI) report, and the first indication information is the indication information in the CSI report configuration, or the first indication information corresponds to the CSI resources used by the terminal.

[0194] Optionally, the channel feature information recovery method further includes:

[0195] The network-side device receives a second indication information from the terminal, the second indication information indicating the second length.

[0196] Optionally, the second indication information is carried in a fixed-length CSI section of the CSI report, and the second-length second channel characteristic information is carried in a variable-length CSI section of the CSI report; or,

[0197] The minimum length portion of the second channel feature information of the second length and the second indication information are carried in the fixed-length CSI portion of the CSI report; the variable-length portion of the second channel feature information of the second length, excluding the minimum length portion, is carried in the variable-length CSI portion of the CSI report; or,

[0198] Both the second indication information and the second channel characteristic information of the second length are carried in the variable-length CSI section of the CSI report.

[0199] Optionally, the minimum length is less than or equal to the second length.

[0200] Optionally, the network-side device receives second channel feature information from the terminal, including:

[0201] The network-side device receives second channel feature information in the M channel feature information reports of the terminal, where M is an integer greater than 1. The lengths of the second channel feature information reported in the M channel feature information reports are different from each other, or the contents of the second channel feature information reported in the M channel feature information reports are different from each other.

[0202] Optionally, the network-side device uses a first AI network model to process the second channel feature information to obtain the target channel information, including:

[0203] The network-side devices respectively use M first AI network models to process the second channel feature information of their respective lengths to obtain the target channel information. The length of each of the M first AI network models includes the length of the second channel feature information reported by the M channel feature information reports; or...

[0204] The network-side device uses a first AI network model to process the second channel feature information reported by the M channel feature information to obtain the target channel information.

[0205] In one optional implementation, the network-side devices respectively use M first AI network models to process the second channel feature information of their respective lengths to obtain the target channel information, and then... Figure 7b The embodiments shown are similar and have the same beneficial effects, and will not be described again here.

[0206] In another optional implementation, the network-side device uses a first AI network model to process the second channel feature information reported by the M channel feature information to obtain the target channel information, and then compares it with... Figure 7a The embodiments shown are similar and have the same beneficial effects, and will not be described again here.

[0207] Optionally, when the second channel feature is carried in the CSI report, the time-frequency resource location reported by the M channel feature information is configured by a CSI report configuration information;

[0208] or,

[0209] The time-frequency resource locations reported by the M channel feature information are configured by the M CSI report configuration information.

[0210] Optionally, the lengths of the second channel feature information reported by the M channel feature information are sequentially increased from the minimum length to the first length;

[0211] or,

[0212] The second channel feature information reported by the Mth channel feature information includes non-overlapping parts of the channel feature information, and the sum of the lengths of the second channel feature information reported by the Mth channel feature information is equal to the first length.

[0213] Optionally, the network-side device receives second channel feature information reported by the terminal's Mth channel feature information, including:

[0214] In the M channel feature information reporting by the terminal, the network-side device receives the second channel feature information from the terminal in a preset order, the preset order including:

[0215] The second channel feature information is arranged in ascending order of length;

[0216] The order in which the second channel feature information is arranged within the first channel feature information.

[0217] In this embodiment, the network-side device can use the first AI network model corresponding to the length of a portion of the first channel feature information (i.e., the second channel feature information) reported by the terminal to perform channel recovery on the second channel feature information, which can reduce the overhead of transmitting the AI ​​network model between the terminal and the network-side device.

[0218] To facilitate the explanation of the channel feature information reporting method and channel feature information recovery method provided in this application, the following channel feature information interaction flow is used as an example to illustrate the channel feature information reporting method and channel feature information recovery method provided in this application. In this embodiment, the channel feature information interaction flow includes the following steps:

[0219] Step 1: The terminal detects CSI-RS or TRS at the time-frequency domain location specified by the network and performs channel estimation to obtain target channel information;

[0220] Step 2: The terminal encodes the target channel information into first channel feature information through the target AI network model (i.e., the AI ​​coding network model);

[0221] Step 3: The terminal selects a portion of the first channel feature information as the second channel feature information to be reported;

[0222] Step 4: The terminal combines the second channel feature information to be reported with other control information into uplink control information (UCI), or uses the second channel feature information to be reported as UCI;

[0223] Step 5: The terminal segments the UCI according to its length and adds Cyclic Redundancy Check (CRC) bits.

[0224] Step 6: The terminal performs channel coding on the UCI with added CRC bits;

[0225] Step 7: The terminal performs rate matching for the UCI;

[0226] Step 8: The terminal performs code block association on the UCI;

[0227] Step 9: The terminal maps the UCI to the Physical Uplink Control Channel (PUCCH) or the Physical Uplink Shared Channel (PUSCH) for reporting.

[0228] It should be noted that the order of some steps in the above-mentioned channel feature information interaction process can be adjusted or omitted, which does not constitute a specific limitation.

[0229] The channel feature information reporting method provided in this application can be executed by a channel feature information reporting device. This application uses the example of a channel feature information reporting device executing the channel feature information reporting method to illustrate the channel feature information reporting device provided in this application.

[0230] Please see Figure 8 The channel feature information reporting device provided in this application embodiment can be a device within a terminal, such as... Figure 8 As shown, the channel feature information reporting device 800 may include the following modules:

[0231] The first processing module 801 is used to process the target channel information into first channel feature information of a first length using the target AI network model;

[0232] The first transmitting module 802 is used to transmit second channel feature information to the network-side device. The second channel feature information is a part of the first channel feature information.

[0233] Optionally, the first transmitting module 802 is specifically used for:

[0234] Send a second channel feature information of a second length extracted from the first channel feature information to the network-side device, wherein the second length is less than or equal to the first length.

[0235] Optionally, the first length is the number of bits of the first channel feature information, or the first length is the number of coefficients included in the first channel feature information; and / or,

[0236] The second length is the number of bits of the second channel feature information, or the second length is the number of coefficients included in the second channel feature information.

[0237] Optionally, the second channel feature information of the second length includes at least one of the following:

[0238] The first N bits or coefficients in the first channel feature information, where N is equal to the number of bits corresponding to the second length or the number of coefficients corresponding to the second length;

[0239] The first channel feature information contains N bits or coefficients whose importance level is greater than a preset level;

[0240] The first channel feature information includes N bits or coefficients in addition to the reported channel feature information.

[0241] Optionally, the channel feature information reporting device 800 further includes:

[0242] A first receiving module is configured to receive first indication information from the network-side device, wherein the first indication information indicates the second length and / or a first encoding identifier, and the first encoding identifier is associated with the second length.

[0243] Optionally, the first indication information is configured by higher-level signaling; or,

[0244] The second channel feature information is carried in the Channel State Information (CSI) report, and the first indication information is the indication information in the CSI report configuration, or the first indication information corresponds to the CSI resources used by the terminal.

[0245] Optionally, the channel feature information reporting device 800 further includes:

[0246] The determining module is used to determine the second length based on at least one of the channel characteristics and channel conditions corresponding to the target channel information.

[0247] Optionally, the channel feature information reporting device 800 further includes:

[0248] The third sending module is used to send a second indication information to the network-side device, the second indication information indicating the second length.

[0249] Optionally, the second indication information is carried in a fixed-length CSI portion of the CSI report, and the second-length second channel characteristic information is carried in a variable-length CSI portion of the CSI report; or,

[0250] The minimum length portion of the second channel feature information of the second length and the second indication information are carried in the fixed-length CSI portion of the CSI report; the variable-length portion of the second channel feature information of the second length, excluding the minimum length portion, is carried in the variable-length CSI portion of the CSI report; or,

[0251] Both the second indication information and the second channel characteristic information of the second length are carried in the variable-length CSI section of the CSI report.

[0252] Optionally, the minimum length is less than or equal to the second length.

[0253] Optionally, the determining module is specifically configured to perform any of the following:

[0254] Based on the first association relationship, the length associated with the value of the target channel parameter of the target channel corresponding to the target channel information is determined to be the second length, wherein the first association relationship includes the association relationship between each value or range of the target channel parameter and the length;

[0255] Based on the second association relationship, the length of the encoding identifier associated with the value of the target channel parameter of the target channel corresponding to the target channel information is determined to be the second length, wherein the second association relationship includes the association relationship between each value or range of the target channel parameter and the encoding identifier.

[0256] Optionally, the target channel parameters of the target channel include at least one of the following:

[0257] The target channel is either line-of-sight propagation or non-line-of-sight propagation;

[0258] The number of effective delay paths of the target channel;

[0259] The time delay interval between the two target paths of the target channel;

[0260] The number of effective beams of the target channel, wherein the effective beams include beams corresponding to the Discrete Fourier Transform (DFT) orthogonal basis with power greater than a first threshold.

[0261] Optionally, the effective delay path includes at least one of the following:

[0262] The corresponding time delay path with power or amplitude greater than the first threshold;

[0263] The corresponding time delay path with maximum power or amplitude.

[0264] Optionally, the channel feature information reporting device 800 further includes:

[0265] The fourth receiving module is used to receive relevant information of K first AI network models from the network-side device, wherein the K first AI network models correspond to the target AI network model, and the K first AI network models are used to decode channel feature information of their respective lengths.

[0266] The determining module includes:

[0267] The second processing unit is used to extract K second channel feature information from the first channel feature information, and process the second channel feature information of corresponding length into first channel information through K first AI network models respectively.

[0268] The acquisition unit is used to acquire the matching degree between K pieces of the first channel information and the target channel information, respectively;

[0269] The determining unit is configured to determine, when the matching degree between the target first channel information and the target channel information meets a preset condition, that the second length is equal to the length of the first AI network model used to process and obtain the target first channel information, wherein the K first channel information obtained by the K first AI network models include the target first channel information.

[0270] Optionally, the degree of matching between the target first channel information and the target channel information satisfies a preset condition including at least one of the following:

[0271] The correlation between the target first channel information and the target channel information is greater than or equal to a preset correlation.

[0272] The channel capacity of the target first channel information is greater than or equal to a first preset value multiple of the channel capacity of the target channel information, wherein the first preset value is greater than 0 and less than or equal to 1.

[0273] The target first channel information is the channel quality indicator (CQI) among the K first channel information pieces that is the same as or closest to the CQI of the target channel information;

[0274] The target first channel information is one of the K first channel information that has the same or closest modulation and coding scheme (MCS) as the target channel information.

[0275] Optionally, the first transmitting module 802 is specifically used for:

[0276] In the Mth channel feature information reporting, the second channel feature information extracted from the first channel feature information is sent to the network-side device, where M is an integer greater than 1. The lengths of the second channel feature information reported in the Mth channel feature information reporting are different from each other, or the contents of the second channel feature information reported in the Mth channel feature information reporting are different from each other.

[0277] Optionally, when the second channel feature is carried in the CSI report, the time-frequency resource location reported by the M channel feature information is configured by a CSI report configuration information;

[0278] or,

[0279] The time-frequency resource locations reported by the M channel feature information are configured by the M CSI report configuration information.

[0280] Optionally, the lengths of the second channel feature information reported by the M channel feature information are sequentially increased from the minimum length to the first length;

[0281] or,

[0282] The second channel feature information reported by the Mth channel feature information includes non-overlapping portions of the first channel feature information, and the sum of the lengths of the second channel feature information reported by the Mth channel feature information is equal to the first length.

[0283] Optionally, the first transmitting module 802 is specifically used for:

[0284] In the Mth channel feature information reporting, the second channel feature information is sent to the network-side device in a preset order, the preset order including:

[0285] The second channel feature information is arranged in ascending order of length;

[0286] The order in which the second channel feature information is arranged within the first channel feature information.

[0287] Optionally, the channel feature information reporting device 800 further includes:

[0288] The channel estimation module is used to perform channel estimation on the Channel State Information-Reference Signal (CSI-RS) or Tracking Reference Signal (TRS) to obtain the target channel information; or...

[0289] The preprocessing module is used to preprocess the channel information obtained from channel estimation to obtain the target channel information.

[0290] The channel feature information reporting device 800 in this application embodiment can be an electronic device, such as an electronic device with an operating system, or a component in an electronic device, such as an integrated circuit or a chip. The electronic device can be a terminal, or other devices besides a terminal. For example, the terminal can include, but is not limited to, the type of terminal 11 listed above; other devices can be servers, network attached storage (NAS), etc., and this application embodiment does not specifically limit the type.

[0291] The channel feature information reporting device 800 provided in this application embodiment can achieve... Figure 2 The various processes implemented in the method embodiment shown achieve the same technical effect, and will not be described again here to avoid repetition.

[0292] The channel feature information recovery method provided in this application can be executed by a channel feature information recovery device. This application uses the example of a channel feature information recovery device executing the channel feature information recovery method to illustrate the channel feature information recovery device provided in this application.

[0293] Please see Figure 9 The channel feature information recovery device provided in this application embodiment can be a device within a network-side device, such as... Figure 9 As shown, the channel feature information recovery device 900 may include the following modules:

[0294] The second receiving module 901 is used to receive second channel feature information from the terminal, wherein the second channel feature information includes a portion of the first channel feature information, and the first channel feature information is channel feature information of a first length obtained by the terminal processing the target channel information using the target AI network model;

[0295] The second processing module 902 is used to process the second channel feature information using a first AI network model to obtain the target channel information.

[0296] Optionally, the second receiving module 901 is specifically used for:

[0297] Receive second channel feature information of a second length extracted from the first channel feature information from the terminal, wherein the second length is less than or equal to the first length.

[0298] Optionally, the first length is the number of bits of the first channel feature information, or the first length is the number of coefficients included in the first channel feature information; and / or,

[0299] The second length is the number of bits of the second channel feature information, or the second length is the number of coefficients included in the second channel feature information.

[0300] Optionally, the second processing module 902 is specifically used for:

[0301] The target channel information is obtained by processing the second channel feature information of the second length using a first AI network model corresponding to the second channel feature information of the second length.

[0302] Optionally, the second processing module 902 includes:

[0303] The update unit is configured to update the historical channel feature information according to the second channel feature information of the second length when the network-side device stores the historical channel feature information of the terminal.

[0304] The first processing unit is used to process the updated historical channel feature information using a first AI network model to obtain the target channel information.

[0305] Optionally, the second channel feature information of the second length includes at least one of the following:

[0306] The first N bits or coefficients in the first channel feature information, where N is equal to the number of bits corresponding to the second length or the number of coefficients corresponding to the second length;

[0307] The first channel feature information contains N bits or coefficients whose importance level is greater than a preset level;

[0308] The first channel feature information includes N bits or coefficients in addition to the reported channel feature information.

[0309] Optionally, the channel feature information recovery device 900 further includes:

[0310] The fourth sending module is used to send first indication information to the terminal, wherein the first indication information indicates the second length and / or the first encoding identifier, and the first encoding identifier is associated with the second length.

[0311] Optionally, the first indication information is configured by higher-level signaling; or,

[0312] The second channel feature information is carried in the Channel State Information (CSI) report, and the first indication information is the indication information in the CSI report configuration, or the first indication information corresponds to the CSI resources used by the terminal.

[0313] Optionally, the channel feature information recovery device 900 further includes:

[0314] The third receiving module is used to receive second indication information from the terminal, wherein the second indication information indicates the second length.

[0315] Optionally, the second indication information is carried in a fixed-length CSI section of the CSI report, and the second-length second channel characteristic information is carried in a variable-length CSI section of the CSI report; or,

[0316] The minimum length portion of the second channel feature information of the second length and the second indication information are carried in the fixed-length CSI portion of the CSI report; the variable-length portion of the second channel feature information of the second length, excluding the minimum length portion, is carried in the variable-length CSI portion of the CSI report; or,

[0317] Both the second indication information and the second channel characteristic information of the second length are carried in the variable-length CSI section of the CSI report.

[0318] Optionally, the minimum length is less than or equal to the second length.

[0319] Optionally, the second receiving module 901 is specifically used for:

[0320] In the M channel feature information reports of the terminal, second channel feature information is received respectively, where M is an integer greater than 1. The lengths of the second channel feature information reported in the M channel feature information reports are different from each other, or the contents of the second channel feature information reported in the M channel feature information reports are different from each other.

[0321] Optionally, the second processing module 902 is specifically used to perform any of the following:

[0322] M first AI network models are used to process the second channel feature information of their respective lengths to obtain the target channel information. The length of each of the M first AI network models includes the length of the second channel feature information reported by the M channel feature information.

[0323] A first AI network model is used to process the second channel feature information reported by the M channel feature information to obtain the target channel information.

[0324] Optionally, when the second channel feature is carried in the CSI report, the time-frequency resource location reported by the M channel feature information is configured by a CSI report configuration information;

[0325] or,

[0326] The time-frequency resource locations reported by the M channel feature information are configured by the M CSI report configuration information.

[0327] Optionally, the lengths of the second channel feature information reported by the M channel feature information are sequentially increased from the minimum length to the first length;

[0328] or,

[0329] The second channel feature information reported by the Mth channel feature information includes non-overlapping parts of the channel feature information, and the sum of the lengths of the second channel feature information reported by the Mth channel feature information is equal to the first length.

[0330] Optionally, the second receiving module 901 is specifically used for:

[0331] In the M channel feature information reporting of the terminal, the second channel feature information from the terminal is received in a preset order, the preset order including:

[0332] The second channel feature information is arranged in ascending order of length;

[0333] The order in which the second channel feature information is arranged within the first channel feature information.

[0334] The channel feature information recovery device 900 in this application embodiment can be an electronic device, such as an electronic device with an operating system, or a component in an electronic device, such as an integrated circuit or a chip. This electronic device can be a network-side device or other devices besides network-side devices. For example, the terminal can be, but is not limited to, the type of network-side device 12 listed above. Other devices can be servers, network attached storage (NAS), etc., and this application embodiment does not specifically limit the scope of the device.

[0335] The channel feature information recovery device 900 provided in this application embodiment can achieve... Figure 6 The various processes implemented in the method embodiment shown achieve the same technical effect, and will not be described again here to avoid repetition.

[0336] Optional, such as Figure 10 As shown, this application embodiment also provides a communication device 1000, including a processor 1001 and a memory 1002. The memory 1002 stores programs or instructions that can run on the processor 1001. For example, when the communication device 1000 is a terminal, the program or instructions executed by the processor 1001 implement the various steps of the above-described channel feature information reporting method embodiment and achieve the same technical effect. When the communication device 1000 is a network-side device, the program or instructions executed by the processor 1001 implement the various steps of the above-described channel feature information recovery method embodiment and achieve the same technical effect. To avoid repetition, further details are omitted here.

[0337] This application embodiment also provides a terminal, including a processor and a communication interface. The processor is used to process target channel information into first channel feature information of a first length using a target AI network model. The communication interface is used to send second channel feature information to a network-side device. The second channel feature information is a part of the first channel feature information.

[0338] This terminal embodiment corresponds to the above-described terminal-side method embodiment. All implementation processes and methods of the above-described method embodiment can be applied to this terminal embodiment and can achieve the same technical effect.

[0339] Specifically, Figure 11 A schematic diagram of the hardware structure of a terminal to implement an embodiment of this application.

[0340] The terminal 1100 includes, but is not limited to, at least some of the following components: radio frequency unit 1101, network module 1102, audio output unit 1103, input unit 1104, sensor 1105, display unit 1106, user input unit 1107, interface unit 1108, memory 1109, and processor 1110.

[0341] Those skilled in the art will understand that the terminal 1100 may also include a power supply (such as a battery) for supplying power to various components. The power supply may be logically connected to the processor 1110 through a power management system, thereby enabling functions such as managing charging, discharging, and power consumption through the power management system. Figure 11The terminal structure shown does not constitute a limitation on the terminal. The terminal may include more or fewer components than shown, or combine certain components, or have different component arrangements, which will not be elaborated here.

[0342] It should be understood that, in this embodiment, the input unit 1104 may include a graphics processing unit (GPU) 11041 and a microphone 11042. The GPU 11041 processes image data of still images or videos obtained by an image capture device (such as a camera) in video capture mode or image capture mode. The display unit 1106 may include a display panel 11061, which may be configured in the form of a liquid crystal display, an organic light-emitting diode, etc. The user input unit 1107 includes at least one of a touch panel 11071 and other input devices 11072. The touch panel 11071 is also called a touch screen. The touch panel 11071 may include a touch detection device and a touch controller. Other input devices 11072 may include, but are not limited to, physical keyboards, function keys (such as volume control buttons, power buttons, etc.), trackballs, mice, joysticks, etc., which will not be described in detail here.

[0343] In this embodiment, after receiving downlink data from the network-side device, the radio frequency unit 1101 can transmit it to the processor 1110 for processing; in addition, the radio frequency unit 1101 can send uplink data to the network-side device. Typically, the radio frequency unit 1101 includes, but is not limited to, antennas, amplifiers, transceivers, couplers, low-noise amplifiers, duplexers, etc.

[0344] The memory 1109 can be used to store software programs or instructions and various data. The memory 1109 may primarily include a first storage area for storing programs or instructions and a second storage area for storing data. The first storage area may store the operating system, application programs or instructions required for at least one function (such as sound playback function, image playback function, etc.). Furthermore, the memory 1109 may include volatile memory or non-volatile memory, or both. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus RAM (DRRAM). The memory 1109 in this embodiment includes, but is not limited to, these and any other suitable types of memory.

[0345] Processor 1110 may include one or more processing units; optionally, processor 1110 integrates an application processor and a modem processor, wherein the application processor mainly handles operations involving the operating system, user interface, and applications, and the modem processor mainly handles wireless communication signals, such as a baseband processor. It is understood that the aforementioned modem processor may also not be integrated into processor 1110.

[0346] The processor 1110 is used to process the target channel information into first channel feature information of a first length using the target AI network model;

[0347] The radio frequency unit 1101 is used to send second channel characteristic information to the network-side device. The second channel characteristic information is a part of the first channel characteristic information.

[0348] Optionally, the sending of the second channel characteristic information to the network-side device by the radio frequency unit 1101 includes:

[0349] Send a second channel feature information of a second length extracted from the first channel feature information to the network-side device, wherein the second length is less than or equal to the first length.

[0350] Optionally, the first length is the number of bits of the first channel feature information, or the first length is the number of coefficients included in the first channel feature information; and / or,

[0351] The second length is the number of bits of the second channel feature information, or the second length is the number of coefficients included in the second channel feature information.

[0352] Optionally, the second channel feature information of the second length includes at least one of the following:

[0353] The first N bits or coefficients in the first channel feature information, where N is equal to the number of bits corresponding to the second length or the number of coefficients corresponding to the second length;

[0354] The first channel feature information contains N bits or coefficients whose importance level is greater than a preset level;

[0355] The first channel feature information includes N bits or coefficients in addition to the reported channel feature information.

[0356] Optionally, before sending the second channel feature information of a second length extracted from the first channel feature information to the network-side device, the radio frequency unit 1101 is further configured to receive first indication information from the network-side device, wherein the first indication information indicates the second length and / or a first encoding identifier, the first encoding identifier being associated with the second length.

[0357] Optionally, the first indication information is configured by higher-level signaling; or,

[0358] The second channel feature information is carried in the Channel State Information (CSI) report, and the first indication information is the indication information in the CSI report configuration, or the first indication information corresponds to the CSI resources used by the terminal.

[0359] Optionally, before the radio frequency unit 1101 executes the step of sending the second channel feature information of a second length extracted from the first channel feature information to the network-side device, the processor 1110 is further configured to determine the second length based on at least one of the channel characteristics and channel conditions corresponding to the target channel information.

[0360] Optionally, the radio frequency unit 1101 is further configured to send a second indication information to the network-side device, the second indication information indicating the second length.

[0361] Optionally, the second indication information is carried in a fixed-length CSI portion of the CSI report, and the second-length second channel characteristic information is carried in a variable-length CSI portion of the CSI report; or,

[0362] The minimum length portion of the second channel feature information of the second length and the second indication information are carried in the fixed-length CSI portion of the CSI report; the variable-length portion of the second channel feature information of the second length, excluding the minimum length portion, is carried in the variable-length CSI portion of the CSI report; or,

[0363] Both the second indication information and the second channel characteristic information of the second length are carried in the variable-length CSI section of the CSI report.

[0364] Optionally, the minimum length is less than or equal to the second length.

[0365] Optionally, the step of determining the second length based on the channel characteristics corresponding to the target channel information, executed by the processor 1110, includes:

[0366] Based on the first association relationship, the length associated with the target channel parameter values ​​of the target channel corresponding to the target channel information is determined to be the second length, wherein the first association relationship includes the association relationship between each value or range of the target channel parameter and the length; or...

[0367] Based on the second association relationship, the length of the encoding identifier associated with the value of the target channel parameter of the target channel corresponding to the target channel information is determined to be the second length, wherein the second association relationship includes the association relationship between each value or range of the target channel parameter and the encoding identifier.

[0368] Optionally, the target channel parameters of the target channel include at least one of the following:

[0369] The target channel is either line-of-sight propagation or non-line-of-sight propagation;

[0370] The number of effective delay paths of the target channel;

[0371] The time delay interval between the two target paths of the target channel;

[0372] The number of effective beams of the target channel, wherein the effective beams include beams corresponding to the Discrete Fourier Transform (DFT) orthogonal basis with power greater than a first threshold.

[0373] Optionally, the effective delay path includes at least one of the following:

[0374] The corresponding time delay path with power or amplitude greater than the first threshold;

[0375] The corresponding time delay path with maximum power or amplitude.

[0376] Optionally, the radio frequency unit 1101 is further configured to receive relevant information from K first AI network models from the network-side device, wherein the K first AI network models correspond to the target AI network model, and the K first AI network models are respectively used to decode channel feature information of their respective lengths;

[0377] The process of determining the second length based on channel conditions, executed by processor 1110, includes:

[0378] The processor 1110 extracts K second channel feature information from the first channel feature information, and processes the second channel feature information of corresponding length into first channel information through K first AI network models respectively;

[0379] Processor 1110 acquires the matching degree between K pieces of the first channel information and the target channel information;

[0380] When the processor 1110 determines that the matching degree between the target first channel information and the target channel information meets a preset condition, it determines that the second length is equal to the length of the first AI network model used to process and obtain the target first channel information, wherein the K first channel information obtained by the K first AI network models include the target first channel information.

[0381] Optionally, the degree of matching between the target first channel information and the target channel information satisfies a preset condition including at least one of the following:

[0382] The correlation between the target first channel information and the target channel information is greater than or equal to a preset correlation.

[0383] The channel capacity of the target first channel information is greater than or equal to a first preset value multiple of the channel capacity of the target channel information, wherein the first preset value is greater than 0 and less than or equal to 1.

[0384] The target first channel information is the channel quality indicator (CQI) among the K first channel information pieces that is the same as or closest to the CQI of the target channel information;

[0385] The target first channel information is one of the K first channel information that has the same or closest modulation and coding scheme (MCS) as the target channel information.

[0386] Optionally, the sending of the second channel characteristic information to the network-side device by the radio frequency unit 1101 includes:

[0387] In the M channel feature information reporting of the terminal, the second channel feature information extracted from the first channel feature information is sent to the network-side device respectively, where M is an integer greater than 1. The lengths of the second channel feature information reported in the M channel feature information reports are different from each other, or the contents of the second channel feature information reported in the M channel feature information reports are different from each other.

[0388] Optionally, when the second channel feature is carried in the CSI report, the time-frequency resource location reported by the M channel feature information is configured by a CSI report configuration information;

[0389] or,

[0390] The time-frequency resource locations reported by the M channel feature information are configured by the M CSI report configuration information.

[0391] Optionally, the lengths of the second channel feature information reported by the M channel feature information are sequentially increased from the minimum length to the first length;

[0392] or,

[0393] The second channel feature information reported by the Mth channel feature information includes non-overlapping portions of the first channel feature information, and the sum of the lengths of the second channel feature information reported by the Mth channel feature information is equal to the first length.

[0394] Optionally, the step of the radio frequency unit 1101 in sending second channel feature information extracted from the first channel feature information to the network-side device during the M channel feature information reporting includes:

[0395] In the Mth channel feature information reporting, the second channel feature information is sent to the network-side device in a preset order, the preset order including:

[0396] The second channel feature information is arranged in ascending order of length;

[0397] The order in which the second channel feature information is arranged within the first channel feature information.

[0398] Optionally, before the processor 1110 executes the process of using the target AI network model to process the target channel information into first channel feature information of a first length:

[0399] Radio frequency unit 1101 is also used to perform channel estimation on channel state information-reference signal CSI-RS or tracking reference signal TRS to obtain the target channel information; or,

[0400] The processor 1110 is also used to preprocess the channel information obtained from channel estimation to obtain the target channel information.

[0401] The terminal 1100 provided in this embodiment of the application is capable of performing tasks such as... Figure 8 The various processes executed by each module in the channel feature information reporting device shown are all effective and can achieve the same beneficial results. To avoid repetition, they will not be described in detail here.

[0402] This application embodiment also provides a network-side device, including a processor and a communication interface. The communication interface is used to receive second channel feature information from a terminal. The second channel feature information includes a portion of first channel feature information. The first channel feature information is channel feature information of a first length obtained by the terminal processing target channel information using a target AI network model. The processor is used to process the second channel feature information using a first AI network model to obtain the target channel information.

[0403] This network-side device embodiment corresponds to the above-described network-side device method embodiment. All implementation processes and methods of the above-described method embodiment can be applied to this network-side device embodiment and can achieve the same technical effect.

[0404] Specifically, embodiments of this application also provide a network-side device. For example... Figure 12 As shown, the network-side device 1200 includes: an antenna 1201, a radio frequency (RF) device 1202, a baseband device 1203, a processor 1204, and a memory 1205. The antenna 1201 is connected to the RF device 1202. In the uplink direction, the RF device 1202 receives information through the antenna 1201 and transmits the received information to the baseband device 1203 for processing. In the downlink direction, the baseband device 1203 processes the information to be transmitted and sends it to the RF device 1202. The RF device 1202 processes the received information and transmits it through the antenna 1201.

[0405] The method executed by the network-side device in the above embodiments can be implemented in the baseband device 1203, which includes a baseband processor.

[0406] The baseband device 1203 may include, for example, at least one baseband board on which multiple chips are disposed, such as... Figure 12 As shown, one of the chips is, for example, a baseband processor, which is connected to the memory 1205 via a bus interface to call the program in the memory 1205 and execute the network device operation shown in the above method embodiment.

[0407] The network-side device may also include a network interface 1206, such as a common public radio interface (CPRI).

[0408] Specifically, the network-side device 1200 of this embodiment further includes: instructions or programs stored in memory 1205 and executable on processor 1204, wherein processor 1204 calls the instructions or programs in memory 1205 to execute. Figure 9 The methods executed by each module shown achieve the same technical effect, and to avoid repetition, they will not be described in detail here.

[0409] This application embodiment also provides a readable storage medium storing a program or instructions that, when executed by a processor, implement... Figure 2 or Figure 6 The various processes of the method embodiments shown can achieve the same technical effect, and will not be described again here to avoid repetition.

[0410] The processor is the processor in the terminal described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0411] This application embodiment also provides a chip, the chip including a processor and a communication interface, the communication interface being coupled to the processor, the processor being used to run programs or instructions to implement, as described above. Figure 2 or Figure 6 The various processes of the method embodiments shown can achieve the same technical effect, and will not be described again here to avoid repetition.

[0412] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0413] This application embodiment also provides a computer program / program product, which is stored in a storage medium and executed by at least one processor to implement the following: Figure 2 or Figure 6The various processes of the method embodiments shown can achieve the same technical effect, and will not be described again here to avoid repetition.

[0414] This application also provides a communication system, including: a terminal and a network-side device, wherein the terminal can be used to perform the steps of the channel feature information reporting method as described above, and the network-side device can be used to perform the steps of the channel feature information recovery method as described above.

[0415] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0416] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0417] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. A method for reporting channel feature information, characterized in that, include: The terminal uses a target AI network model to process the target channel information into first channel feature information of a first length, where the first length is a fixed length. The terminal sends a second channel feature information to the network-side device, and the second channel feature information is a part of the first channel feature information. The terminal sends second channel characteristic information to the network-side device, including: The terminal sends second channel feature information of a second length extracted from the first channel feature information to the network-side device, wherein the second length is less than or equal to the first length. Before the terminal sends the second channel feature information of a second length extracted from the first channel feature information to the network-side device, the method further includes: The terminal receives first indication information from the network-side device, wherein the first indication information indicates the second length and / or a first encoding identifier, and the first encoding identifier is associated with the second length.

2. The method according to claim 1, characterized in that, The first length is the number of bits of the first channel feature information, or the first length is the number of coefficients included in the first channel feature information; and / or, The second length is the number of bits of the second channel feature information, or the second length is the number of coefficients included in the second channel feature information.

3. The method according to claim 1, characterized in that, The second channel feature information of the second length includes at least one of the following: The first N bits or coefficients in the first channel feature information, where N is equal to the number of bits corresponding to the second length or the number of coefficients corresponding to the second length; The first channel feature information contains N bits or coefficients whose importance level is greater than a preset level; The first channel feature information includes N bits or coefficients in addition to the reported channel feature information.

4. The method according to claim 1, characterized in that, The first indication information is configured by higher-level signaling; or, The second channel feature information is carried in the Channel State Information (CSI) report, and the first indication information is the indication information in the CSI report configuration, or the first indication information corresponds to the CSI resources used by the terminal.

5. The method according to claim 1 or 3, characterized in that, Before the terminal sends the second channel feature information of a second length extracted from the first channel feature information to the network-side device, the method further includes: The terminal determines the second length based on at least one of the channel characteristics and channel conditions corresponding to the target channel information.

6. The method according to claim 5, characterized in that, The method further includes: The terminal sends a second indication message to the network-side device, the second indication message indicating the second length.

7. The method according to claim 6, characterized in that, The second indication information is carried in a fixed-length CSI portion of the CSI report, and the second channel characteristic information of the second length is carried in a variable-length CSI portion of the CSI report; or, The minimum length portion of the second channel feature information of the second length and the second indication information are carried in the fixed-length CSI portion of the CSI report, and the variable-length portion of the second channel feature information of the second length other than the minimum length portion is carried in the variable-length CSI portion of the CSI report; or, Both the second indication information and the second channel characteristic information of the second length are carried in the variable-length CSI section of the CSI report.

8. The method according to claim 7, characterized in that, The minimum length is less than or equal to the second length.

9. The method according to claim 5, characterized in that, The terminal determines the second length based on the channel characteristics corresponding to the target channel information, including: The terminal determines, based on a first association relationship, that the length associated with the target channel parameter values ​​of the target channel corresponding to the target channel information is the second length, wherein the first association relationship includes the association relationship between each value or range of the target channel parameter and the length; or... The terminal determines, based on the second association relationship, the length of the encoding identifier associated with the value of the target channel parameter of the target channel corresponding to the target channel information is the second length, wherein the second association relationship includes the association relationship between each value or range of the target channel parameter and the encoding identifier.

10. The method according to claim 9, characterized in that, The target channel parameters of the target channel include at least one of the following: The target channel is either line-of-sight propagation or non-line-of-sight propagation; The number of effective delay paths of the target channel; The time delay interval between the two target paths of the target channel; The number of effective beams of the target channel, wherein the effective beams include beams corresponding to the Discrete Fourier Transform (DFT) orthogonal basis with power greater than a first threshold.

11. The method according to claim 10, characterized in that, The effective delay path includes at least one of the following: The corresponding time delay path with power or amplitude greater than the first threshold; The corresponding time delay path with maximum power or amplitude.

12. The method according to claim 5, characterized in that, The method further includes: The terminal receives relevant information from K first AI network models from the network-side device, wherein the K first AI network models correspond to the target AI network model, and the K first AI network models are used to decode channel feature information of their respective lengths. The terminal determines the second length based on channel conditions, including: The terminal extracts K second channel feature information from the first channel feature information, and processes the second channel feature information of corresponding length into first channel information through K first AI network models respectively; The terminal acquires the matching degree between K pieces of the first channel information and the target channel information; When the terminal determines that the matching degree between the target first channel information and the target channel information meets a preset condition, it determines that the second length is equal to the length of the first AI network model used to process and obtain the target first channel information, wherein the K first channel information obtained by the K first AI network models include the target first channel information.

13. The method according to claim 12, characterized in that, The matching degree between the target first channel information and the target channel information satisfies at least one of the following preset conditions: The correlation between the target first channel information and the target channel information is greater than or equal to a preset correlation. The channel capacity of the target first channel information is greater than or equal to a first preset value multiple of the channel capacity of the target channel information, wherein the first preset value is greater than 0 and less than or equal to 1. The target first channel information is the channel quality indicator (CQI) among the K first channel information pieces that is the same as or closest to the CQI of the target channel information; The target first channel information is one of the K first channel information that has the same or closest modulation and coding scheme (MCS) as the target channel information.

14. The method according to claim 1, characterized in that, The terminal sends second channel characteristic information to the network-side device, including: In each of the M channel feature information reports, the terminal sends a second channel feature information extracted from the first channel feature information to the network-side device, where M is an integer greater than 1. The lengths of the second channel feature information reported in the M channel feature information reports are all different, or the contents of the second channel feature information reported in the M channel feature information reports are all different.

15. The method according to claim 14, characterized in that, When the second channel feature is carried in the CSI report, the time-frequency resource location reported by the M channel feature information is configured by a CSI report configuration information; or, The time-frequency resource locations reported by the M channel feature information are configured by the M CSI report configuration information.

16. The method according to claim 14, characterized in that, The lengths of the second channel feature information reported by the Mth channel feature information are sequentially increased from the minimum length to the first length; or, The second channel feature information reported by the Mth channel feature information includes non-overlapping portions of the first channel feature information, and the sum of the lengths of the second channel feature information reported by the Mth channel feature information is equal to the first length.

17. The method according to any one of claims 14 to 16, characterized in that, In each of the M channel feature information reports, the terminal sends a second channel feature information extracted from the first channel feature information to the network-side device, including: In the Mth channel feature information reporting, the terminal sends the second channel feature information to the network-side device in a preset order, the preset order including: The second channel feature information is arranged in ascending order of length; The order in which the second channel feature information is arranged within the first channel feature information.

18. The method according to claim 1, characterized in that, Before the terminal processes the target channel information into first channel feature information of a first length using the target AI network model, the method further includes: The terminal performs channel estimation on the Channel State Information-Reference Signal (CSI-RS) or Tracking Reference Signal (TRS) to obtain the target channel information; or... The terminal preprocesses the channel information obtained from channel estimation to obtain the target channel information.

19. A channel feature information reporting device, characterized in that, Applied to a terminal, the device includes: The first processing module is used to process the target channel information into first channel feature information of a first length using the target AI network model, wherein the first length is a fixed length. The first sending module is used to send second channel feature information to the network-side device, wherein the second channel feature information is a part of the first channel feature information. The first sending module is specifically used for: Send to the network-side device second channel feature information of a second length extracted from the first channel feature information, wherein the second length is less than or equal to the first length; The device further includes: A first receiving module is configured to receive first indication information from the network-side device, wherein the first indication information indicates the second length and / or a first encoding identifier, and the first encoding identifier is associated with the second length.

20. A method for recovering channel feature information, characterized in that, include: The network-side device receives second channel feature information from the terminal, wherein the second channel feature information includes a portion of the first channel feature information, and the first channel feature information is channel feature information of a first length obtained by the terminal processing the target channel information using the target AI network model, and the first length is a fixed length; The network-side device uses a first AI network model to process the second channel feature information to obtain the target channel information; The network-side device receives second channel feature information from the terminal, including: The network-side device receives second channel feature information of a second length extracted from the first channel feature information from the terminal, wherein the second length is less than or equal to the first length; Before the network-side device receives second channel feature information of a second length extracted from the first channel feature information from the terminal, the method further includes: The network-side device sends a first indication message to the terminal, wherein the first indication message indicates the second length and / or a first encoding identifier, and the first encoding identifier is associated with the second length.

21. The method according to claim 20, characterized in that, The network-side device uses a first AI network model to process the second channel feature information to obtain the target channel information, including: The network-side device uses a first AI network model corresponding to the second channel feature information of the second length to process the second channel feature information of the second length, thereby obtaining the target channel information.

22. The method according to claim 20, characterized in that, The network-side device uses a first AI network model to process the second channel feature information to obtain the target channel information, including: When the network-side device stores the historical channel feature information of the terminal, the network-side device updates the historical channel feature information according to the second channel feature information of the second length; The network-side device uses a first AI network model to process the updated historical channel feature information to obtain the target channel information.

23. The method according to any one of claims 20 to 22, characterized in that, The method further includes: The network-side device receives a second indication information from the terminal, the second indication information indicating the second length.

24. The method according to claim 20, characterized in that, The network-side device receives second channel feature information from the terminal, including: The network-side device receives second channel feature information in the M channel feature information reports of the terminal, where M is an integer greater than 1, and the lengths of the second channel feature information reported in the M channel feature information reports are different from each other, or the contents of the second channel feature information reported in the M channel feature information reports are different from each other.

25. The method according to claim 24, characterized in that, When the second channel feature is carried in the CSI report, the time-frequency resource location reported by the M channel feature information is configured by a CSI report configuration information; or, The time-frequency resource locations reported by the M channel feature information are configured by the M CSI report configuration information.

26. A channel feature information recovery device, characterized in that, Applied to network-side devices, the device includes: The second receiving module is used to receive second channel feature information from the terminal, wherein the second channel feature information includes a portion of the first channel feature information, and the first channel feature information is channel feature information of a first length obtained by the terminal processing the target channel information using the target AI network model, and the first length is a fixed length; The second processing module is used to process the second channel feature information using the first AI network model to obtain the target channel information; The second receiving module is specifically used for: Receive second channel feature information of a second length extracted from the first channel feature information from the terminal, wherein the second length is less than or equal to the first length; The device further includes: The fourth sending module is used to send first indication information to the terminal, wherein the first indication information indicates the second length and / or the first encoding identifier, and the first encoding identifier is associated with the second length.

27. A terminal, characterized in that, It includes a processor and a memory, the memory storing programs or instructions that can run on the processor, the programs or instructions being executed by the processor to implement the steps of the channel feature information reporting method as described in any one of claims 1 to 18.

28. A network-side device, characterized in that, It includes a processor and a memory, the memory storing programs or instructions that can run on the processor, the programs or instructions being executed by the processor to implement the steps of the channel feature information recovery method as described in any one of claims 20 to 25.

29. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor, implement the steps of the channel feature information reporting method as described in any one of claims 1 to 18, or the steps of the channel feature information recovery method as described in any one of claims 20 to 25.

Images