Channel data transmission method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention relates to a channel data transmission method and device, electronic equipment and a storage medium, and the method comprises the steps: transmitting first indication information to a terminal, the first indication information being used for indicating the terminal to directly map compressed channel data outputted by a channel compression model to a time-frequency resource. According to the technical scheme provided by the embodiment of the invention, the transmission overhead can be reduced, and meanwhile, the processing flow on the terminal and the base station when the channel state information is fed back can be simplified.

Description

Technical Field

[0001] The present disclosure relates to the field of communication technologies, and in particular, to a method, an apparatus, an electronic device, and a storage medium for transmitting channel data. Background Art

[0002] In the field of mobile communication technologies, after a signal receiving end receives a signal from a signal sending end, it feeds back the channel state information of the communication channel to facilitate the signal sending end to accurately know the channel state and improve the signal transmission quality. For example, in a Multiple-Input Multiple-Output (MIMO) system, beamforming by obtaining channel state information (CSI) is a key condition for improving transmission performance. Especially for a Frequency Division Duplex (FDD) system, due to the lack of reciprocity of the complete uplink and downlink channels, the base station needs to rely on the feedback of the terminal to obtain the complete downlink CSI. In the NR system, the terminal mainly relies on the codebook method to feedback CSI. For example, CSI type I, type II, type II enhanced, and other types of codebooks can be used to feedback information such as rank indicator (IR), precoding matrix indicator (PMI), and channel quality indicator (CQI).

[0003] A prior art solution for feedback channel state information is to use a data-driven deep learning method to set a corresponding channel compression model and a channel decompression model. For example, a channel compression model is configured at the terminal. This channel compression model can extract low-dimensional features from channel data to generate compressed channel data, and then send the compressed channel data to the base station. The channel decompression model configured on the base station then decompresses the above compressed channel data to obtain the channel data. In the above solution for feedback signal state information, for the compressed signal data output by the channel compression model, it usually needs to be processed such as quantization, channel coding, and scrambling before transmission. The above prior art solution has the defects of large transmission overhead and complex processing procedures. Summary of the Invention

[0004] To solve the above technical problems, the present disclosure provides a method, an apparatus, an electronic device, and a storage medium for transmitting channel data.

[0005] An embodiment of the present disclosure provides a method for transmitting channel data, the method includes:

[0006] Send first indication information to the terminal, where the first indication information is used to instruct the terminal to directly map the compressed channel data output by the channel compression model to time-frequency resources.

[0007] In some embodiments, the first indication message is further used to instruct the terminal to directly map the neighboring reference signal to time-frequency resources.

[0008] In some embodiments, before sending the first indication information to the terminal, it further includes:

[0009] Obtain the channel evaluation quality;

[0010] The sending the first indication information to the terminal includes:

[0011] When the channel evaluation quality meets a first preset threshold, send the first indication information to the terminal.

[0012] In some embodiments, the channel evaluation quality includes any one of channel signal-to-noise ratio, bit error rate, and channel quality indicator;

[0013] If the channel evaluation quality includes the channel signal-to-noise ratio, the obtaining the channel evaluation quality includes:

[0014] Receive the sounding reference signal sent by the terminal, and calculate the channel signal-to-noise ratio according to the sounding reference signal.

[0015] In some embodiments, it further includes:

[0016] Obtain the pre-trained channel compression model, the pre-trained channel decompression model, and the number of compressed channel data input to the channel decompression model.

[0017] In some embodiments, it further includes:

[0018] Send the pre-trained channel compression model to the terminal.

[0019] In some embodiments, it further includes:

[0020] Obtain the normalization processing method for the terminal to perform normalization processing on the compressed channel data output by the channel compression model;

[0021] Send the normalization processing method to the terminal.

[0022] In some embodiments, it further includes:

[0023] Send first resource configuration information to the terminal, where the first resource configuration information is used to instruct the terminal to send the time-frequency resources required for sending the compressed channel data and sending the neighboring reference signal.

[0024] In some embodiments, the neighboring reference signal is set within the coherent bandwidth of the compressed channel data.

[0025] In some embodiments, before sending the first resource configuration information to the terminal, it further includes:

[0026] Obtain the number of compressed channel data input to the channel decompression model and the number of neighboring reference signals;

[0027] Based on the number of compressed channel data input to the channel decompression model and the number of neighboring reference signals, determine the time-frequency resources required for the terminal to send the compressed channel data and the neighboring reference signals.

[0028] In some embodiments, the terminal sends the compressed channel data in a combined manner or in a non-combined manner.

[0029] In some embodiments, it further includes:

[0030] Send second resource configuration information to the terminal, where the second resource configuration information is used to indicate the time-frequency resources for the terminal to send the normalization elements.

[0031] In some embodiments, it further includes:

[0032] Obtain the compressed channel data output by the channel compression model sent by the terminal;

[0033] Input the compressed channel data into the channel decompression model to decompress the channel data by the channel decompression model.

[0034] In some embodiments, the obtaining the compressed channel data output by the channel compression model sent by the terminal includes:

[0035] Obtain the neighboring reference signal directly mapped to the time-frequency resource, and resolve the channel according to the neighboring reference signal;

[0036] Obtain the compressed channel data output by the channel compression model sent by the terminal according to the resolved channel.

[0037] In some embodiments, it further includes:

[0038] Obtain the normalization elements used by the terminal during the normalization process of the compressed channel data;

[0039] The obtaining the compressed channel data output by the channel compression model sent by the terminal according to the resolved channel includes:

[0040] Obtain the compressed channel data output by the channel compression model sent by the terminal according to the resolved channel and the normalization elements.

[0041] In some embodiments, the normalization process is the maximization normalization method;

[0042] If the terminal sends compressed channel data in a combined manner, the normalization element is the maximum modulus value in the compressed channel data combination.

[0043] In some embodiments, it further includes:

[0044] Re-obtain the channel evaluation quality;

[0045] When the channel evaluation quality meets a second preset threshold, send second indication information to the terminal, where the second indication information is used to instruct the terminal to perform quantization processing on the compressed channel data output by the channel compression model and map the compressed channel data obtained by the quantization processing to time-frequency resources.

[0046] An embodiment of the present disclosure further provides a method for transmitting channel data, and the method includes:

[0047] Receive first indication information sent by the base station;

[0048] Directly map the compressed channel data output by the channel compression model to time-frequency resources according to the first indication information, so as to send to the base station.

[0049] In some embodiments, the directly mapping the compressed channel data output by the channel compression model to time-frequency resources according to the first indication information includes:

[0050] Directly map the compressed channel data output by the channel compression model and adjacent reference signals to time-frequency resources according to the first indication information.

[0051] In some embodiments, before receiving the first indication information sent by the base station, it further includes:

[0052] Establish a radio link control layer connection with the base station;

[0053] Send a sounding reference signal to the base station, so that the base station calculates the channel signal-to-noise ratio according to the sounding reference signal.

[0054] In some embodiments, before receiving the first indication information sent by the base station, it further includes:

[0055] Receive a pre-trained channel compression model sent by the base station;

[0056] Compress the channel data based on the pre-trained channel compression model and output compressed channel data.

[0057] In some embodiments, it further includes:

[0058] Receive the first resource configuration information sent by the base station, where the first resource configuration information is used to indicate the time-frequency resources for the terminal to send the compressed channel data and the neighboring reference signal;

[0059] The directly mapping the compressed channel data output by the channel compression model to the time-frequency resources includes:

[0060] Based on the first resource configuration information, directly map the compressed channel data and the neighboring reference signal to the time-frequency resources.

[0061] In some embodiments, the neighboring reference signal is set within the coherence bandwidth of the compressed channel data.

[0062] In some embodiments, the compressed channel data is sent in a combined manner or in a non-combined manner. If the compressed channel data is sent in a combined manner, the method further includes:

[0063] Perform data combination processing on the compressed channel data output by the channel compression model to obtain at least one compressed channel data combination;

[0064] The directly mapping the compressed channel data output by the channel compression model to the time-frequency resources includes:

[0065] Directly map the at least one compressed channel data combination to the time-frequency resources.

[0066] In some embodiments, it further includes:

[0067] Receive the normalization processing method sent by the base station;

[0068] Perform normalization processing on the compressed channel data according to the normalization processing method to obtain the normalized compressed channel data;

[0069] The directly mapping the compressed channel data output by the channel compression model to the time-frequency resources includes:

[0070] Directly map the normalized compressed channel data to the time-frequency resources.

[0071] In some embodiments, it further includes:

[0072] Receive the second resource configuration information sent by the terminal, where the second resource configuration information is used to indicate the time-frequency resources for the terminal to send the normalization elements;

[0073] According to the second resource configuration information, map the normalization elements used in the normalization process to the time-frequency resources for sending to the base station.

[0074] In some embodiments, the normalization method is the maximum normalization method;

[0075] If the terminal sends the compressed channel data in a combined manner, the normalization element is the maximum modulus value in the compressed channel data combination.

[0076] In some embodiments, it further includes:

[0077] Receiving the second indication information sent by the base station;

[0078] Quantizing the compressed channel data output by the channel compression model according to the second indication information, and mapping the quantized compressed channel data to time-frequency resources for sending to the base station.

[0079] The embodiments of the present disclosure further provide a transmission device for channel data, and the device includes:

[0080] A first indication sending module, configured to send first indication information to the terminal, where the first indication information is used to instruct the terminal to directly map the compressed channel data output by the channel compression model to time-frequency resources.

[0081] In some embodiments, the above first indication message is further used to instruct the terminal to directly map the neighboring reference signal to time-frequency resources.

[0082] In some embodiments, before sending the first indication information to the terminal, it further includes:

[0083] A first channel quality acquisition module, configured to acquire the channel evaluation quality before sending the first indication information to the terminal;

[0084] The first indication sending module is specifically configured to send the first indication information to the terminal when the channel evaluation quality meets a first preset threshold.

[0085] In some embodiments, the channel evaluation quality includes any one of channel signal-to-noise ratio, bit error rate, and channel quality indication; the first channel quality acquisition module is specifically configured to receive the sounding reference signal sent by the terminal and calculate the channel signal-to-noise ratio according to the sounding reference signal.

[0086] In some embodiments, it further includes:

[0087] A first acquisition module, configured to acquire a pre-trained channel compression model, a pre-trained channel decompression model, and the number of compressed channel data input to the channel decompression model;

[0088] A first sending module, configured to send the pre-trained channel compression model to the terminal.

[0089] In some embodiments, it further includes:

[0090] Normalization processing method acquisition module, which acquires the normalization processing method for the terminal to perform normalization processing on the compressed channel data output by the channel compression model;

[0091] In some embodiments, it further includes:

[0092] The first sending module is further configured to send the normalization processing method to the terminal.

[0093] In some embodiments, it further includes:

[0094] Configuration sending module, which is configured to send first resource configuration information to the terminal, and the first resource configuration information is used to indicate the time-frequency resources required for the terminal to send the compressed channel data and send the neighboring reference signal.

[0095] In some embodiments, the neighboring reference signal is set within the coherence bandwidth of the compressed channel data.

[0096] In some embodiments, it further includes:

[0097] Number acquisition module, which is configured to acquire the number of the compressed channel data input to the channel decompression model and the number of the neighboring reference signals before sending the first resource configuration information to the terminal;

[0098] Resource determination module, which is configured to determine the time-frequency resources required for the terminal to send the compressed channel data and send the neighboring reference signal based on the number of the compressed channel data input to the channel decompression model and the number of the neighboring reference signals.

[0099] In some embodiments, the terminal sends the compressed channel data in a combined manner or the compressed channel data in a non-combined manner.

[0100] In some embodiments, it further includes:

[0101] Send second resource configuration information to the terminal, and the second resource configuration information is used to indicate the time-frequency resources for the terminal to send the normalization elements.

[0102] In some embodiments, it further includes:

[0103] Channel data acquisition module, which is configured to acquire the compressed channel data output by the channel compression model sent by the terminal;

[0104] Decompression module, which is configured to input the compressed channel data into the channel decompression model to decompress the channel data by the channel decompression model.

[0105] In some embodiments, the channel data acquisition module includes:

[0106] A channel analysis unit, configured to obtain a neighboring reference signal directly mapped to the time-frequency resource, and analyze a channel according to the neighboring reference signal;

[0107] A data acquisition unit, configured to obtain compressed channel data output by a channel compression model sent by a terminal according to the analyzed channel.

[0108] In some embodiments, it further includes:

[0109] A normalization element acquisition unit, configured to obtain a normalization element used by the terminal during the normalization process of the compressed channel data;

[0110] A data acquisition unit, configured to obtain compressed channel data output by a channel compression model sent by a terminal according to the analyzed channel and the normalization element.

[0111] In some embodiments, the normalization method is the maximum normalization method;

[0112] If the terminal sends compressed channel data in a combined manner, the normalization element is the maximum modulus value in the compressed channel data combination.

[0113] In some embodiments, it further includes:

[0114] A second signal-to-noise ratio acquisition module, configured to re-acquire the channel evaluation quality;

[0115] A second indication information sending module, configured to send second indication information to the terminal when the channel evaluation quality meets a second preset threshold, where the second indication information is used to instruct the terminal to perform quantization processing on the compressed channel data output by the channel compression model, and map the compressed channel data obtained by the quantization processing to the time-frequency resource.

[0116] In an embodiment of the present disclosure, there is also provided a transmission device for channel data, which is applied to a terminal, and the device includes:

[0117] A first indication receiving module, configured to receive first indication information sent by a base station;

[0118] A first data sending module, configured to directly map the compressed channel data output by the channel compression model to the time-frequency resource according to the first indication information, so as to send to the base station.

[0119] In some embodiments, the first sending module is specifically configured to directly map the compressed channel data output by the channel compression model and the neighboring reference signal to the time-frequency resource according to the first indication information, so as to send to the base station.

[0120] In some embodiments, it further includes:

[0121] A connection establishment module, configured to establish a radio link control layer connection with the base station before receiving the first indication information sent by the receiving base station;

[0122] A detection module, configured to send a sounding reference signal to the base station, so that the base station calculates a channel signal-to-noise ratio according to the sounding reference signal.

[0123] In some embodiments, it further includes:

[0124] A model receiving module, configured to receive a pre-trained channel compression model sent by the receiving base station before receiving the first indication information sent by the receiving base station;

[0125] A compression module, configured to compress channel data based on the pre-trained channel compression model and output compressed channel data.

[0126] In some embodiments, it further includes:

[0127] A configuration information receiving module, configured to receive first resource configuration information sent by the base station, where the first resource configuration information is used to indicate time-frequency resources for the terminal to send the compressed channel data and send a neighboring reference signal;

[0128] The first data sending module is specifically configured to directly map the compressed channel data and the neighboring reference signal to time-frequency resources based on the first resource configuration information.

[0129] In some embodiments, the neighboring reference signal is set within the coherence bandwidth of the compressed channel data.

[0130] In some embodiments, the compressed channel data is sent in a combined manner or in a non-combined manner. If the compressed channel data is sent in a combined manner, the method further includes:

[0131] A combination module, configured to perform data combination processing on the compressed channel data output by the channel compression model to obtain at least one compressed channel data combination;

[0132] The first data sending module is specifically configured to directly map the at least one compressed channel data combination to time-frequency resources.

[0133] In some embodiments, it further includes:

[0134] A normalization processing method receiving module, configured to receive a normalization processing method sent by the base station;

[0135] A normalization processing module, configured to perform normalization processing on the compressed channel data according to the normalization processing method to obtain normalized compressed channel data;

[0136] The first data sending module is specifically configured to directly map the compressed channel data after the normalization processing to time-frequency resources.

[0137] In some embodiments, it further includes:

[0138] A second configuration information receiving module, configured to receive second resource configuration information sent by a terminal, where the second resource configuration information is used to indicate the time-frequency resources for the terminal to send normalization elements;

[0139] A normalization element sending module, configured to map the normalization elements used in the normalization processing to time-frequency resources according to the second resource configuration information, so as to send them to the base station.

[0140] In some embodiments, the normalization method is the maximum normalization method;

[0141] If the terminal sends compressed channel data in a combined manner, the normalization element is the maximum modulus value in the compressed channel data combination.

[0142] In some embodiments, it further includes:

[0143] A second indication information receiving module, configured to receive second indication information sent by the base station;

[0144] A second data sending module, configured to perform quantization processing on the compressed channel data output by the channel compression model according to the second indication information, and map the compressed channel data obtained by the quantization processing to time-frequency resources, so as to send it to the base station.

[0145] An embodiment of the present disclosure further provides an electronic device, where the electronic device includes:

[0146] A processor;

[0147] A memory for storing executable instructions of the processor;

[0148] The processor is configured to read the executable instructions from the memory and execute the instructions to implement any one of the above channel data transmission methods.

[0149] An embodiment of the present disclosure further provides a computer-readable storage medium, where the storage medium stores a computer program, and the computer program is used to execute any one of the above channel data transmission methods.

[0150] An embodiment of the present disclosure further provides a computer program product, and the computer program product is used to execute any one of the above channel data transmission methods.

[0151] Embodiments of the present disclosure provide a technical solution for feedback of channel state information. When a terminal sends channel data to a base station, the compressed channel data output by the channel compression model on the terminal is directly mapped to time-frequency resources and then sent to the base station, rather than first performing operations such as quantization processing and then mapping to time-frequency resources. In this way, after the base station receives the above-mentioned compressed channel data, there is no need to perform dequantization processing operations, which can not only reduce transmission overhead but also simplify the processing flow on the terminal and the base station during channel state information feedback. BRIEF DESCRIPTION OF THE DRAWINGS

[0152] In combination with the accompanying drawings and with reference to the following specific embodiments, the above and other features, advantages, and aspects of the embodiments of the present disclosure will become more apparent. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the original elements and elements are not necessarily drawn to scale.

[0153] Figure 1 Schematic flowchart of a method for transmitting channel data provided by an embodiment of the present disclosure;

[0154] Figure 2 Schematic flowchart of another method for transmitting channel data provided by an embodiment of the present disclosure;

[0155] Figure 3 Schematic flowchart of yet another method for transmitting channel data provided by an embodiment of the present disclosure;

[0156] Figure 4 Schematic flowchart of a process for determining time-frequency resources provided by an embodiment of the present disclosure;

[0157] Figure 5 Schematic flowchart of still another method for transmitting channel data provided by an embodiment of the present disclosure;

[0158] Figure 6 Schematic flowchart of yet another method for transmitting channel data provided by an embodiment of the present disclosure;

[0159] Figure 7 A flowchart showing a traditional process for a terminal to feedback channel state information to a base station is given;

[0160] Figure 8 Schematic flowchart of yet another data transmission method provided by an embodiment of the present disclosure;

[0161] Figure 9 Schematic flowchart of yet another method for transmitting channel data in an embodiment of the present disclosure;

[0162] Figure 10 Schematic flowchart of yet another method for transmitting channel data in an embodiment of the present disclosure;

[0163] Figure 11 This is a schematic diagram of resource mapping in an embodiment of the present disclosure;

[0164] Figure 12 This is a flowchart of resource mapping in an embodiment of the present disclosure;

[0165] Figure 13 This is a schematic flowchart of a specific implementation solution provided by an embodiment of the present disclosure;

[0166] Figure 14 This is a schematic structural diagram of a transmission device for channel data provided by an embodiment of the present disclosure;

[0167] Figure 15 This is a schematic structural diagram of another transmission device for channel data provided by an embodiment of the present disclosure;

[0168] Figure 16 This is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure. Detailed implementation manners

[0169] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although some embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Instead, these embodiments are provided to more thoroughly and completely understand the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not used to limit the protection scope of the present disclosure.

[0170] It should be understood that the steps recited in the method embodiments of the present disclosure can be executed in a different order and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this regard.

[0171] The term "including" and its variants used herein are open-ended, that is, "including but not limited to". The term "based on" is "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0172] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependent relationships.

[0173] It should be noted that the modifications of "one" and "multiple" mentioned in this disclosure are illustrative rather than restrictive. Those skilled in the art should understand that, unless otherwise clearly specified in the context, it should be understood as "one or more".

[0174] In the prior art, when performing channel state information feedback, the compressed signal data output by the channel compression model is usually quantized, channel-encoded, scrambled and other processed before transmission, resulting in the defects of large transmission overhead and complex processing flow. The embodiment of the present disclosure provides a technical solution for feedback of channel state information. When the terminal sends channel data to the base station, the compressed channel data output by the channel compression model on the terminal is directly mapped to time-frequency resources and then sent to the base station, rather than first performing quantization processing and other operations and then mapping to time-frequency resources. After the base station receives the above compressed channel data, there is no need to perform dequantization processing operations, which can not only reduce the transmission overhead, but also simplify the processing flow on the terminal and the base station during channel state information feedback. The technical solution provided by the embodiment of the present disclosure has improvements on both the terminal and the base station. The following embodiments will be described separately for the base station side and the terminal side.

[0175] For the transmission method of channel data provided in the embodiment of the present disclosure, the technical solution executed on the base station side can be specifically referred to Figure 1 as shown. Figure 1 It is a schematic flowchart of a transmission method of channel data provided in the embodiment of the present disclosure. As Figure 1 shown, the method includes the following steps:

[0176] Step 100, the base station sends first indication information to the terminal, and the first indication information is used to instruct the terminal to directly map the compressed channel data output by the channel compression model to time-frequency resources;

[0177] Specifically, in the embodiment of the present disclosure, the downlink channel data can be pre-collected through a radio access network AI model training system, and the channel compression model and the channel decompression model based on the AI autoencoder are trained offline. The above AI model training system can be deployed on the centralized unit (Centralized Unit, abbreviated as: CU) and / or the distributed unit (Distributed Unit, abbreviated as: DU) of the base station, or deployed on a logical entity across the CU. After the above channel compression model and channel decompression model are pre-trained, the channel compression model can be sent to the terminal, and the channel decompression model is set on the base station.

[0178] In this step, when the base station determines to send compressed channel data to the base station by directly mapping the compressed channel data to time-frequency resources, the corresponding first indication information is sent to the terminal, so that the terminal can directly map the compressed channel data output by the above-mentioned pre-trained channel compression model to time-frequency resources. The above-mentioned compressed channel data has not undergone operations such as quantization processing, channel coding, and scrambling, and is a kind of non-quantized data. By using this technical solution, the transmission overhead can be reduced, and at the same time, the processing flow on the terminal and the base station during channel state information feedback can also be simplified. The above-mentioned first indication information can be the value of an identification bit. For example, the value of the identification bit is set to 1.

[0179] Among them, the above determination of using the method of directly mapping compressed channel data to time-frequency resources to send compressed channel data to the base station can include various methods. For example, the base station is preset to use the above method for channel state information feedback. At this time, after the radio link control layer connection is established between the terminal and the base station, the first indication information can be sent to the accessed terminal to instruct the terminal to send compressed channel data in the above manner.

[0180] In some embodiments, the above-mentioned first indication message can also be used to instruct the terminal to directly map the neighboring reference signal to time-frequency resources. The above-mentioned neighboring reference signal is used as a pilot signal, and the channel can be resolved through this pilot signal, and further the compressed channel data can be resolved according to this channel.

[0181] In another case, the evaluation quality during communication with the terminal can be obtained by the base station, and then it is determined whether to send compressed channel data according to the above method based on the evaluation quality. The above evaluation quality can reflect the actual channel quality and interference situation. At this time, a preset threshold can be set. Only when the evaluation quality meets the first preset threshold, the method of directly mapping the compressed channel data to the time-frequency resource is selected to send the compressed channel data to the base station. The above channel evaluation quality includes any one of the channel signal-to-noise ratio, bit error rate, and channel quality indicator. For example, when the channel evaluation quality includes the channel signal-to-noise ratio, if the channel signal-to-noise ratio is large, it indicates that the channel quality is good. At this time, the channel signal-to-noise ratio can be set to be greater than or equal to a preset threshold, so that even if the technical solution of the embodiment of the present disclosure is adopted, the compressed channel data can still be sent to the base station better, and the situation that the compressed channel data cannot be effectively transmitted to the base station due to large noise and interference can be avoided; if the channel signal-to-noise ratio is less than the preset threshold, it indicates that the channel quality is poor. At this time, the compressed channel data output by the channel compression model can still be quantized, channel-encoded, scrambled, modulated, etc., and then resource mapping is performed to map the compressed channel data after the above series of processes to the time-frequency resource. If the channel evaluation quality includes the bit error rate, when the bit error rate is less than or equal to a preset threshold, the technical solution of the embodiment of the present disclosure is adopted to send the first indication information to the terminal. Or, if the channel evaluation quality includes the channel quality indicator, the channel quality indicator can be set to be greater than or equal to a preset threshold, and the technical solution of the embodiment of the present disclosure is adopted to send the first indication information to the terminal.

[0182] The specific method flowchart of the above situation can be as Figure 2 shown, Figure 2 which is a schematic flowchart of another method for transmitting channel data provided by the embodiment of the present disclosure. As Figure 2 shown, taking the channel signal-to-noise ratio as an example, the method includes the following steps:

[0183] Step 110: Obtain the channel signal-to-noise ratio;

[0184] Specifically, in this step, it can be specifically to first receive the sounding reference signal (SRS) sent by the terminal. After the base station obtains the sounding reference signal, the channel signal-to-noise ratio can be calculated based on the sounding reference signal;

[0185] Step 120: When the channel signal-to-noise ratio is greater than or equal to the preset threshold, send the first indication information to the terminal.

[0186] After the base station calculates the channel signal-to-noise ratio in this step, it determines the magnitude relationship between the channel signal-to-noise ratio and a preset threshold set in advance. When the channel signal-to-noise ratio is greater than or equal to the preset threshold, it sends a first indication message to the terminal, so that in the case of good channel quality, the compressed channel data can be mapped to time-frequency resources by the above direct mapping method to realize the feedback of channel state information and ensure the quality of information state feedback.

[0187] As described above, the channel compression model and the channel decompression model can be pre-trained on the base station to obtain the pre-trained channel compression model and the channel decompression model, and the pre-trained channel compression model needs to be sent to the terminal. In addition, for the channel compression model, generally, the range of its output value can be controlled by setting a suitable activation function at the end of the channel compression model. For example, the activation function can be set to the tan function. At this time, the output compressed channel data can be within the value range of [-1, 1]; if a suitable activation function is not set in the activation function, so that the output compressed channel data is not within the above value range at this time, the compressed channel data needs to be normalized before being directly mapped to time-frequency resources. Specifically, in the embodiments of the present disclosure, the base station can obtain the normalization processing method for the compressed channel data output by the terminal by the channel compression model, and then send the normalization processing method to the above terminal, so that the compressed channel data output by the channel compression model can be normalized on the terminal.

[0188] Through the above embodiments, the base station sends the channel compression model, the normalization processing method, etc. to the terminal, so that after receiving the first indication message, the terminal can use the direct mapping to time-frequency resources method for the compressed channel data output by the channel compression model to realize the feedback of channel state information to the base station, and if necessary, the compressed channel data can be normalized before being directly mapped to time-frequency resources, and operations such as quantization processing will not be performed.

[0189] In addition, in order for the terminal to obtain channel data, in the embodiments of the present disclosure, the base station can send a Channel State Information-Reference Signal (CSI-RS) to the terminal, so that the terminal can obtain channel data that can reflect the downlink channel quality according to the CSI-RS.

[0190] In order to successfully realize the direct mapping of the compressed channel data of the terminal to time-frequency resources, it is necessary to allocate time-frequency resources for each accessed terminal on the base station. Figure 3 It is a schematic flow chart of another method for transmitting channel data provided by the embodiments of the present disclosure. As Figure 3As shown, in addition to including the above-mentioned step 110 and step 120, the following steps are further included:

[0191] Step 130: Send first resource configuration information to the terminal, where the first resource configuration information is used to indicate the time-frequency resources for the terminal to send compressed channel data and send neighboring reference signals.

[0192] The neighboring reference signal among them needs to be sent in the time-frequency resources together while the terminal sends the compressed channel data. The base station can resolve the channel based on the neighboring reference signal, and then resolve the compressed channel data from the signals of this channel. In this step, the base station configures the time-frequency resources used by the terminal to send the compressed channel data and the neighboring reference signal, and then sends it to the terminal as the first resource configuration information.

[0193] In this step, when sending the first resource configuration information to the terminal, the execution order with the above-mentioned step 120 is not limited in the embodiments of the present disclosure. Any one of them can be executed first, and then the other one can be executed, or they can be executed simultaneously.

[0194] Before sending the above-mentioned first resource configuration information to the terminal, the base station needs to first determine the time-frequency resources used for the above-mentioned compressed channel data and neighboring reference signals for the terminal. Figure 4 It is a schematic flow diagram for determining the time-frequency resources provided by the embodiments of the present disclosure. As Figure 4 shown, the following steps are included:

[0195] Step 410: Obtain the number of compressed channel data and the number of neighboring reference signals input to the channel decompression model;

[0196] Specifically, in the above-mentioned embodiments, the above-mentioned channel compression model has been pre-trained. Therefore, the number of compressed channel data input to the above-mentioned channel decompression model can be determined, which is the same as the number of compressed channel data output by the channel compression model. For the number of neighboring reference signals, it can be set according to actual needs. Further, the neighboring reference signal can be set within the coherence bandwidth of the compressed channel data.

[0197] Step 420: Based on the number of compressed channel data and the number of neighboring reference signals output by the channel compression model, determine the time-frequency resources required for the terminal to send the compressed channel data and the neighboring reference signals.

[0198] Specifically, in the embodiments of the present disclosure, for example, when the number of compressed channel data output by the channel compression model and the number of compressed channel data input to the channel decompression model are N, in the non-combined mode, the time-frequency resources need to be configured according to N compressed channel data; however, in some combined modes, the compressed channel data output by the channel compression model can be combined, and several compressed channel data are combined into a compressed channel data combination. For example, when combined in pairs, if N is even, the number of compressed channel data combinations is N / 2, and if N is odd, the number of compressed channel data combinations is N / 2 + 1. Therefore, when combined in pairs, the number of compressed channel data combinations is the ceiling of the number of output compressed channel data divided by 2. At this time, the required time-frequency resources can be configured according to the result of dividing by 2 and taking the ceiling. The embodiments of the present disclosure adopt a method of combining several compressed channel data into a compressed channel data combination, which can save the required time-frequency resources. For example, in the above pairwise combination method, compared with the original method of transmitting one compressed channel data on each resource element (RE), in the embodiments of the present disclosure, it can be realized that one compressed channel data combination, that is, two compressed channel data, is transmitted on each RE. Similarly, after determining the number of neighboring reference signals to be transmitted, the required time-frequency resources can also be determined, and the time-frequency resources required by the neighboring reference signals and the compressed channel data are adjacent. The neighboring reference signals are set within the coherent bandwidth of the compressed channel data, so as to ensure that the same channel is used, and thus the channel in which the compressed channel data is located can be resolved according to the reference signal. In the embodiments of the present disclosure, the neighboring reference signal refers to the distance between the REs where it and the compressed channel data combination are mapped in the resource grid being less than a certain set threshold value.

[0199] After determining the time-frequency resources allocated to each terminal in this step, the first resource configuration information can be sent according to the Figure 3 embodiment shown. At the same time, in order to avoid conflicts, after allocating the above time-frequency resources to a certain terminal, the same time-frequency resources will not be allocated to other terminals.

[0200] Figure 5 It is a schematic flowchart of another method for transmitting channel data provided by the embodiments of the present disclosure, which is based on Figure 3 and, in some embodiments, further includes the following steps:

[0201] Step 140: Send second resource configuration information to the terminal. The second resource configuration information is used to indicate the time-frequency resources for the terminal to send the normalization elements. The above normalization elements are the normalization elements used by the terminal when normalizing the compressed channel data output by the channel compression model. After the terminal performs the normalization process, it needs to feedback the above normalization elements to the base station so that the base station can perform restoration according to the normalization elements later and obtain the compressed channel data before normalization on the base station.

[0202] In the above embodiment, after the base station has sent the pre-trained channel compression model, the normalization processing method, and also sent the first resource configuration information and the second resource configuration information to the terminal, the terminal can compress the channel data by inputting it into the channel compression model to obtain the compressed channel data, and can directly map the compressed channel data to the time-frequency resources indicated by the first resource configuration information, and then send it to the base station. Figure 6 It is a schematic flowchart of another method for transmitting channel data in the embodiments of the present disclosure. As Figure 6 shown, on the basis of the embodiment shown in Figure 3 it further includes:

[0203] Step 150: Obtain the compressed channel data directly mapped by the terminal to the time-frequency resources;

[0204] Specifically, the above time-frequency resources are configured by the base station for the terminal and indicated by the above first resource configuration information. In this step, the compressed channel data can be obtained through the above time-frequency resources.

[0205] Step 160: Input the compressed channel data into the channel decompression model to decompress the channel data by the channel decompression model.

[0206] The channel decompression model used in this step is a pre-trained channel decompression model, which is correspondingly set with the channel compression model deployed on the terminal. It can decompress the compressed channel data output by the channel decompression model to obtain the original channel data, so as to feedback the channel data obtained by the terminal device to the base station, thereby realizing the feedback of channel state information.

[0207] In the above step 150, obtaining the compressed channel data output by the channel compression model sent by the terminal can be specifically as follows: first, obtain the neighboring reference signal directly mapped to the time-frequency resources, and resolve the channel according to the neighboring reference signal. Since the neighboring reference signal is set within the coherence bandwidth of the compressed channel data, this can ensure that the same channel is used. After resolving the channel, it is convenient to obtain the compressed channel data output by the channel compression model according to the resolved channel.

[0208] As described in the above embodiments, at the terminal, the compressed channel data output by the channel decompression model can also be normalized. At this time, the compressed channel data obtained at the base station is actually the normalized compressed channel data. At this time, the terminal will also use the time-frequency resources indicated by the above second resource indication information to send the normalization elements used in the normalization process to the base station. Therefore, the base station can also obtain the normalization elements obtained by the terminal during the normalization process of the compressed channel data. The above-mentioned obtaining the compressed channel data output by the channel compression model sent by the terminal according to the parsed channel includes: obtaining the compressed channel data output by the channel compression model sent by the terminal according to the parsed channel and the normalization elements. The normalization elements are used to restore the normalized compressed channel data to the compressed channel data before normalization, so as to input the compressed channel data before normalization into the channel decompression model to obtain the original channel data.

[0209] In the above embodiments of the present disclosure, it is mainly a technical solution executed after obtaining the channel evaluation quality and when the channel evaluation quality meets the first preset threshold. In this technical solution, the compressed channel data output by the channel compression model is directly mapped to the time-frequency resources and then sent to the base station, avoiding operations such as quantization processing; during the communication process between the terminal and the base station, the base station can re-obtain the channel evaluation quality at a certain time interval. If the channel evaluation quality still meets the first preset threshold, the above technical solution is still executed. If the channel evaluation quality meets the second preset threshold, the base station will send the second indication information to the terminal. The second indication information is used to instruct the terminal to perform quantization processing on the compressed channel data output by the channel compression model and map the compressed channel data obtained by the quantization processing to the time-frequency resources. Specifically, the above channel evaluation quality may include channel signal-to-noise ratio, bit error rate, or channel quality indicator. The above channel evaluation quality meeting the second preset condition may include the channel signal-to-noise ratio being less than a preset threshold, the bit error rate being greater than a preset threshold, or the channel quality indicator being less than a preset threshold. At this time, it means that the channel quality is poor, and the method of performing quantization processing on the compressed channel data output by the channel compression model and mapping the compressed channel data obtained by the quantization processing to the time-frequency resources can be used for channel information feedback.

[0210] In this case, when the terminal sends the compressed channel data, the specific steps executed can refer to Figure 7 as shown in Figure 7 A flowchart of a traditional terminal feeding back channel state information to the base station is given, such as Figure 7As shown, in addition to quantizing the compressed channel data, steps such as cyclic redundancy check (CRC) verification, channel coding, rate matching, hybrid automatic repeat request (HARQ) coding, scrambling, modulation, layer mapping, discrete Fourier transform (DFT) uplink coding, multi-antenna precoding, resource mapping, and physical antenna mapping are also required. In the technical solution provided by the embodiments of the present disclosure, when the channel signal-to-noise ratio is greater than or equal to a preset threshold, the unquantized compressed channel data is directly resource-mapped and directly mapped to the specified time-domain resources. Obviously, more operation steps need to be added, which increases the difficulty and also causes a significant increase in transmission overhead. The technical solution proposed by the present disclosure when the channel signal-to-noise ratio is greater than or equal to the preset threshold can obviously overcome the above defects well.

[0211] Corresponding to the above method for transmitting channel data executed on the base station side, the following embodiments are methods for transmitting channel data executed on the terminal side. Figure 8 It is a schematic flowchart of yet another data transmission method provided by the embodiments of the present disclosure, as Figure 8 shown, and includes the following steps:

[0212] Step 810: Receive the first indication information sent by the base station;

[0213] As recorded in the above embodiments, the first indication information is the first indication information sent by the base station when it determines to send the compressed channel data to the base station by directly mapping the compressed channel data to the time-frequency resource. After receiving the first indication information, the terminal can confirm that the current method of feedback channel state information in the communication system is to directly map the compressed channel data to the time-frequency resource. The above first indication information can be the value of an identification bit. For example, the value of the identification bit is set to 1.

[0214] Step 820: Directly map the compressed channel data output by the channel compression model to the time-frequency resource according to the first indication information for sending to the base station.

[0215] Specifically, in this step, after the downlink channel measurement is performed at the terminal and channel data is obtained, compression is performed through a channel compression model to obtain compressed channel data. The base station may send a Channel State Information-Reference Signal (CSI-RS) in the downlink channel, and the terminal obtains channel data that can reflect the downlink channel quality based on the above CSI-RS. Since the compressed channel data output by the pre-trained channel compression model is directly mapped to time-frequency resources, the compressed channel data is not quantized, channel-coded, scrambled, etc., and is a non-quantized data. Using this technical solution can reduce the transmission overhead and simplify the processing flow at the terminal and the base station during the feedback of channel state information.

[0216] Furthermore, since the above channel compression model is a pre-trained model, the pre-training process is usually implemented on the CU or DU of the base station, or a logical entity across the CU. Therefore, in the embodiments of the present disclosure, it is also necessary to receive in advance the pre-trained channel compression model sent by the base station, and then the channel data can be compressed based on the pre-trained channel compression model, and compressed channel data can be output.

[0217] In some embodiments, the above first indication message may also be used to instruct the terminal to directly map the neighboring reference signal to time-frequency resources. The above neighboring reference signal is used as a pilot signal, and the channel can be resolved through the pilot signal, and further the compressed channel data can be resolved according to the channel. At this time, directly mapping the compressed channel data output by the channel compression model to time-frequency resources may specifically be to directly map the compressed channel data output by the channel compression model and the neighboring reference signal to time-frequency resources according to the first indication information. Figure 9 It is a schematic flowchart of another method for transmitting channel data in the embodiments of the present disclosure. As Figure 9 shown, in addition to including the above steps 810 and 820, before performing step 810, the following steps may also be included:

[0218] Step 910: Establish a Radio Resource Control (RRC) connection with the base station. After establishing the above connection, the terminal accesses the communication network;

[0219] Step 920: Send a Sounding Reference Signal (SRS) to the base station to enable the base station to calculate the channel signal-to-noise ratio according to the SRS. Specifically, as described in the embodiments shown above Figure 2 When the channel signal-to-noise ratio is greater than or equal to a preset threshold, the base station sends the first indication information to the terminal.

[0220] Regarding the time-frequency resources used by the terminal when transmitting the compressed channel data and the neighboring reference signal, they can be pre-configured by the base station. In this way, when multiple terminals access the base station, different terminals can still use different time-frequency resources. Specifically, reference can be made to, for example, Figure 10 as shown, it further includes:

[0221] Step 930: Receive the first resource configuration information sent by the base station, where the first resource configuration information is used to indicate the time-frequency resources for the terminal to transmit the compressed channel data and the neighboring reference signal;

[0222] At this time, directly mapping the compressed channel data output by the channel compression model to the time-frequency resources in the above step 820 can specifically be directly mapping the compressed channel data and the neighboring reference signal to the time-frequency resources based on the first resource configuration information.

[0223] As described in the above embodiments, the terminal transmits the compressed channel data in a combined manner or a non-combined manner. For example, if the number of compressed channel data output by the channel compression model is N, then in the non-combined manner, the time-frequency resources need to be configured according to N compressed channel data; however, in some cases, the compressed channel data output by the channel compression model can be combined, and several compressed channel data are combined into a compressed channel data combination. For example, when combining two by two, if N is even, the number of compressed channel data combinations is N / 2, and if N is odd, the number of compressed channel data combinations is N / 2 + 1. Therefore, when combining two by two, the number of compressed channel data groups is the number of output compressed channel data divided by 2 and rounded up. At this time, the required time-frequency resources can be configured according to the result of dividing by 2 and rounding up. The embodiments of the present disclosure adopt a method of combining several compressed channel data into a compressed channel data combination, which can save the required time-frequency resources. For example, in the above method of combining two by two, compared with the original need to transmit one compressed channel data on each resource element (RE), in the embodiments of the present disclosure, it can be realized that one compressed channel data combination, that is, two compressed channel data, is transmitted on each RE. Similarly, after determining the number of neighboring reference signals to be transmitted, the required time-frequency resources can also be determined, and the time-frequency resources required by the neighboring reference signal and the compressed channel data are adjacent. The neighboring reference signal is set within the coherent bandwidth of the compressed channel data, so that it can be ensured that the same channel is used, and thus the channel in which the compressed channel data is located can be resolved according to the reference signal. In the embodiments of the present disclosure, the neighboring reference signal refers to that when it is mapped on the resource grid together with the compressed channel data combination, the distance between the REs where they are located is less than a certain set threshold value.

[0224] In the embodiments of the present disclosure, if the compressed channel data is sent in a combined manner, when combining at least two pieces of compressed channel data into a compressed channel data group as described above, the following steps are further included on the terminal:

[0225] Perform data combination processing on the compressed channel data output by the channel compression model to obtain at least one compressed channel data combination;

[0226] Furthermore, the direct mapping of the compressed channel data output by the channel compression model to time-frequency resources in the above embodiments can be specifically: directly map at least one compressed channel data combination to time-frequency resources.

[0227] In the embodiments of the present disclosure, for the channel compression model, generally, the range of its output values can be controlled by setting an appropriate activation function at the end of the model. For example, the activation function can be set to the tan function, and at this time, the output compressed channel data can be within the value range of [-1, 1]; if an appropriate activation function is not set in the activation function, resulting in the output compressed channel data not being within the above value range, then the compressed channel data needs to be normalized before being directly mapped to time-frequency resources. The normalization processing method is generally determined by the base station, and after determining the normalization processing method, the base station will send it to the terminal; therefore, the terminal in this step will also perform the following steps:

[0228] Receive the normalization processing method sent by the base station, and then perform normalization processing on the compressed channel data according to the normalization processing method to obtain the normalized compressed channel data;

[0229] Then the direct mapping of the compressed channel data output by the channel compression model to time-frequency resources in the above embodiments can be specifically: directly map the normalized compressed channel data to time-frequency resources.

[0230] During the above normalization processing of the compressed channel data, normalization elements will be used. At this time, the base station side also needs to use the above normalization elements to restore the normalized compressed channel data to obtain the compressed channel data before normalization, that is, the compressed channel data output by the channel compression model. In this embodiment, the base station will also configure time-frequency resources for transmitting the normalization elements and send them to the terminal. Therefore, the following steps will also be performed on the terminal:

[0231] Receive the second resource configuration information sent by the terminal, where the second resource configuration information is used to indicate the time-frequency resources for the terminal to send the normalization elements;

[0232] According to the second resource configuration information, map the normalization elements used in the normalization processing to time-frequency resources for sending to the base station.

[0233] For the embodiments of the present disclosure, pairwise combination and normalization processing can be performed on the compressed channel data. Specifically, for example, after the channel data is compressed by the compression model, the output compressed channel data is [o1(t), o2(t), …, o N (t)], where o i (t) is a real number. The compressed channel data is pairwise combined to obtain compressed channel data combinations [(o1(t) + o2(t)j), (o3(t) + o4(t)j), …]. When N is even, the last compressed channel data combination is (o N-1 (t) + o N (t)j), and when N is odd, the last compressed channel data combination is (o N (t)). If normalization processing is required, the compressed channel data combinations (o1(t) + o2(t)j), (o3(t) + o4(t)j), … obtained by pairwise combination are normalized to obtain the normalized compressed channel data combinations Norm(o1(t) + o2(t)j), Norm(o3(t) + o4(t)j), …, and the normalized compressed channel data combinations and adjacent reference signals can be reported based on the time-frequency resources configured by the base station. Since the adjacent reference signal is set within the coherent bandwidth of the compressed channel data, this can ensure that the same channel is used. At this time, if the channel parsed from the adjacent reference signal is H(t), the compressed channel data combinations transmitted on the same channel are [H(Norm(o1(t) + o2(t)j)), H(Norm(o3(t) + o4(t)j)), …].

[0234] In the embodiments of the present disclosure, normalization processing can normalize the compressed channel data to a reasonable numerical range. The specific normalization processing method can be to select the maximum normalization method:

[0235] For the compressed channel data [o1(t), o2(t), …, o N (t)] of the channel compression model, calculate the maximum modulus value in (o i (t) + o i+1 (t)) (i = 1, 3, 5 …) represents rounding up. Divide the compressed channel data combinations after pairwise combination by O(t) to obtain the normalized compressed channel data combinations And the maximum modulus value O(t) on the market can be regarded as the normalization element. This normalization element can be sent to the base station by the time-frequency resources specified by the base station so that the base station can use this normalization element for restoration to obtain the compressed channel data group before normalization.

[0236] Figure 11A schematic diagram of resource mapping in an embodiment of the present disclosure is shown as follows Figure 11 As shown, a schematic diagram of resource mapping for compressed channel data combination and neighboring reference signals in an embodiment of the present disclosure is given. Assume that the neighboring reference signal transmitted by the terminal at time t is x(t), then the neighboring signal received by the base station is X(t), and the channel H(t) can be calculated through x(t) and X(t). Due to the coherence of the channel within a subband, it can be considered that Figure 10 the channel at the black position in Figure 10 is the same as the channel of the neighboring reference signal at its closest diagonal position. Therefore, as shown in the above-mentioned normalized compressed channel data combination

[0237] Figure 12 A flowchart of resource mapping in an embodiment of the present disclosure is shown as follows Figure 12 As shown, for the above-mentioned compressed channel data and neighboring reference signals, a resource mapping scheme of direct mapping can be adopted to map them to the time-frequency resources specified by the base station, and then physical antenna mapping can be performed and sent to the base station. This processing scheme is different from Figure 7 the scheme shown in

[0238] In the above embodiments of the present disclosure, it is mainly a technical solution executed after obtaining the channel signal-to-noise ratio and when the channel signal-to-noise ratio is greater than or equal to a preset threshold. In this technical solution, the compressed channel data output by the channel compression model is directly mapped to the time-frequency resources and then sent to the base station, avoiding operations such as quantization processing; during the communication process between the terminal and the base station, the base station can re-obtain the channel signal-to-noise ratio at a certain time interval. If the channel signal-to-noise ratio is still greater than or equal to the preset threshold, the above technical solution is still executed. If the channel signal-to-noise ratio is less than the preset threshold, the base station will send a second indication message to the terminal. Therefore, the following steps will also be executed on the terminal:

[0239] Receive the second indication information sent by the base station;

[0240] Quantize the compressed channel data output by the channel compression model according to the second indication information, and map the quantized compressed channel data to time-frequency resources for sending to the base station. In this case, when the terminal sends the compressed channel data, the specific steps can refer to the above Figure 7 as shown.

[0241] Figure 13 It is a schematic flowchart of a specific implementation solution provided by an embodiment of the present disclosure. As Figure 13 shown, it includes the following steps:

[0242] Step 1301: Deploy an AI model training system for the radio access network on the base station. Specifically, it can be deployed on the CU and / or DU of the base station, or on a logical entity across the CU. During pre-training, first collect the channel data of the downlink channel, and offline train a channel compression model (denoted as E) and a channel decompression model (denoted as D) based on an AI autoencoder. After the pre-training is completed, synchronize the pre-trained channel compression model and the normalization processing method to the terminal. The normalization processing method can be the maximum normalization method. In addition, synchronize the channel decompression model, the maximum normalization method, and the number 24 of the compressed channel data output by the channel compression model to the base station. The number of the compressed channel data output by the channel compression model is also the number of the compressed channel data input to the channel decompression model. For example, the base station pre-sets the channel signal-to-noise ratio threshold as δ = 20 dB according to the accuracy requirement of the user channel feedback;

[0243] Step 1302: The terminal accesses the network and enters the RRC-CONNECTED state, and sends SRS according to the pre-configuration;

[0244] Step 1303: The base station sends CSI-RS according to the pre-configuration, calculates the channel signal-to-noise ratio SINR of the uplink channel based on the received SRS, and compares it with the pre-set channel signal-to-noise ratio threshold. When the channel signal-to-noise ratio is greater than or equal to the preset threshold δ, for example, greater than or equal to 20, then send the identification bit 1 to the terminal. This identification bit 1 is used as the above-mentioned first indication information;

[0245] Further, the base station divides the number 24 of the compressed channel data input according to the channel decompression model by 2 and rounds up to get 12, and configures time-frequency resources according to the number 3 of the neighboring reference signals to be configured. The time-frequency resources are used for the terminal to feedback the compressed channel data and the neighboring reference signals output by the channel compression model; for the allocated time-frequency resources, the base station does not allocate them to other users / antennas. In addition, the base station also needs to configure the feedback resources for the terminal to feedback the normalization elements. When using the maximization normalization method, the above normalization elements are in the binary form of the maximum modulus value. For the feedback method of the binary form of the maximum modulus value, it can be adopted as Figure 13 shown in the feedback method. A series of operations such as modulation, layer mapping, discrete Fourier transform (Discrete Fourier Transform, abbreviated as: DFT) uplink coding, multi-antenna precoding, resource mapping, and physical antenna mapping need to be performed on it and then sent to the base station. The base station also sends the configured feedback resources to the terminal, and then executes step 1304;

[0246] If the above channel signal-to-noise ratio is less than the preset threshold δ, the base station sends the identification bit 0 to the terminal. The identification bit 0 is used as the second indication information to instruct the terminal to feedback the compressed channel data according to the Figure 6 embodiment shown. At this time, the feedback resources can also be configured according to the number of the compressed channel data input by the decompression model. The base station sends the information of the configured feedback resources to the terminal, and then executes step 107;

[0247] Step 1304: After the terminal receives the identification bit 1, at time t, it inputs the channel data into the channel compression model to complete the compression of the channel data, and outputs the compressed channel data [o1(t), o2(t), …, o 24 (t)], where o i (t) is a real number. The output compressed channel data is combined in pairs to obtain the compressed channel data combination Y(t) = [(o1(t) + o2(t)j), (o3(t) + o4(t)j), … (o 23 (t) + o 24 (t)j)]. By calculating the maximum modulus value in (o i (t) + o i+1 (t)j) (i = 1, 3, 5, … 23) Divide Y(t) by O(t) to obtain the normalized compressed channel data combination Then report the above normalized compressed channel data combination and the neighboring reference signals based on the time-frequency resources configured by the base station, and feedback the binary form of the maximum modulus value O(t) using the feedback resources configured by the base station.

[0248] Step 1305: The base station solves the channel H(t) based on the received neighboring reference signal. According to H(t), the binary form of the received maximum modulus O(t), and solves the compressed channel data [o1′(t), o2′(t), …, o 24 ′(t)], and then inputs the compressed channel data into the channel decompression model to decompress the required channel data;

[0249] Step 1306: The base station will subsequently recalculate the channel signal-to-noise ratio based on the SRS and compare the channel signal-to-noise ratio with a preset threshold. When the magnitude relationship between the channel signal-to-noise ratio and the preset threshold changes, the base station will adjust the identification bit sent to the terminal, as well as the feedback resources configured for the terminal, and will reconfigure and feedback the resources to the terminal. The compressed channel data generated on the terminal will be fed back to the base station according to the time-frequency resources adjusted by the base station. When the channel signal-to-noise ratio is greater than or equal to the preset threshold, the identification bit 1 will be sent to the terminal. The specific processing flow can still refer to the above steps 1303 - 1306; while when the channel signal-to-noise ratio is less than the preset threshold, the identification bit 0 will be sent to the terminal, and the subsequent processing flow refers to step 107;

[0250] Step 1307: When the terminal receives the identification bit 0, after completing the channel data compression through the channel compression model, it outputs the compressed channel data and reports the compressed channel data to the base station in Figure 7 the described traditional manner; after receiving the compressed channel data sent by the terminal, the base station inputs the compressed channel data into the channel decompression model to complete the decompression, obtains the channel data, and then executes step 1306.

[0251] Corresponding to the above method embodiments, the present disclosure embodiments also provide corresponding devices, which can implement the methods listed in the above embodiments and achieve the same technical effects.

[0252] The present disclosure embodiments also provide a transmission device for channel data. This transmission device can be applied to a base station. Figure 14 As shown in Figure 14 the structure diagram of a transmission device for channel data provided by the present disclosure embodiments, the device includes:

[0253] A first indication sending module 1400, configured to send a first indication message to the terminal, where the first indication message is used to instruct the terminal to directly map the compressed channel data output by the channel compression model to time-frequency resources.

[0254] In some embodiments, before sending the first indication message to the terminal, it further includes:

[0255] A first channel quality acquisition module, configured to acquire the channel evaluation quality before sending the first indication message to the terminal;

[0256] The first indication sending module is specifically configured to send first indication information to the terminal when the channel evaluation quality meets a first preset threshold.

[0257] In some embodiments, the channel evaluation quality includes any one of channel signal-to-noise ratio, bit error rate, and channel quality indicator. If the channel evaluation quality includes channel signal-to-noise ratio, the first channel quality acquisition module is specifically configured to receive a sounding reference signal sent by the terminal and calculate the channel signal-to-noise ratio according to the sounding reference signal.

[0258] In some embodiments, it further includes:

[0259] A first acquisition module, configured to acquire a pre-trained channel compression model, a pre-trained channel decompression model, and the number of compressed channel data input to the channel decompression model;

[0260] A first sending module, configured to send the pre-trained channel compression model to the terminal.

[0261] In some embodiments, it further includes:

[0262] A normalization processing method acquisition module, configured to acquire the normalization processing method for the terminal to perform normalization processing on the compressed channel data output by the channel compression model;

[0263] The first sending module is further configured to send the normalization processing method to the terminal.

[0264] In some embodiments, it further includes:

[0265] A configuration sending module, configured to send first resource configuration information to the terminal, where the first resource configuration information is used to indicate the time-frequency resources required for the terminal to send the compressed channel data and send the neighboring reference signal.

[0266] In some embodiments, the neighboring reference signal is set within the coherence bandwidth of the compressed channel data.

[0267] In some embodiments, it further includes:

[0268] A number acquisition module, configured to acquire the number of compressed channel data input to the channel decompression model and the number of neighboring reference signals before sending the first resource configuration information to the terminal;

[0269] A resource determination module, configured to determine the time-frequency resources required for the terminal to send the compressed channel data and send the neighboring reference signal based on the number of compressed channel data input to the channel decompression model and the number of neighboring reference signals.

[0270] In some embodiments, the terminal sends compressed channel data in a combined manner or compressed channel data in a non-combined manner.

[0271] In some embodiments, it further includes:

[0272] Sending second resource configuration information to the terminal, where the second resource configuration information is used to indicate the time-frequency resources for the terminal to send normalization elements.

[0273] In some embodiments, it further includes:

[0274] A channel data acquisition module, configured to acquire the compressed channel data output by the channel compression model sent by the terminal;

[0275] A decompression module, configured to input the compressed channel data into the channel decompression model to decompress the channel data by the channel decompression model.

[0276] In some embodiments, the channel data acquisition module includes:

[0277] A channel parsing unit, configured to acquire adjacent reference signals directly mapped to the time-frequency resources, and parse the channel according to the adjacent reference signals;

[0278] A data acquisition unit, configured to acquire the compressed channel data output by the channel compression model sent by the terminal according to the parsed channel.

[0279] In some embodiments, it further includes:

[0280] A normalization element acquisition unit, configured to acquire the normalization elements used by the terminal during the normalization process of the compressed channel data;

[0281] A data acquisition unit, configured to acquire the compressed channel data output by the channel compression model sent by the terminal according to the parsed channel and the normalization elements.

[0282] In some embodiments, the normalization processing method is the maximum normalization method;

[0283] If the terminal sends compressed channel data in a combined manner, the normalization element is the maximum modulus value in the compressed channel data combination.

[0284] In some embodiments, it further includes:

[0285] A second signal-to-noise ratio acquisition module, configured to re-acquire the channel evaluation quality;

[0286] A second indication information sending module, configured to send second indication information to a terminal when the channel evaluation quality meets a second preset threshold, where the second indication information is used to instruct the terminal to perform quantization processing on the compressed channel data output by a channel compression model, and map the compressed channel data obtained by the quantization processing to time-frequency resources.

[0287] In an embodiment of the present disclosure, a transmission device for channel data is further provided. This transmission device can be applied to a terminal. Figure 15 As shown in the structural schematic diagram of another transmission device for channel data provided by an embodiment of the present disclosure, Figure 15 as shown, the device includes:

[0288] A first indication receiving module 1501, configured to receive first indication information sent by a base station;

[0289] A first data sending module 1502, configured to directly map the compressed channel data output by a channel compression model to time-frequency resources according to the first indication information, so as to send to the base station.

[0290] In some embodiments, it further includes:

[0291] A connection establishment module, configured to establish a radio link control layer connection with the base station before receiving the first indication information sent by the base station;

[0292] A detection module, configured to send a sounding reference signal to the base station, so that the base station calculates a channel signal-to-noise ratio according to the sounding reference signal.

[0293] In some embodiments, it further includes:

[0294] A model receiving module, configured to receive a pre-trained channel compression model sent by the base station before receiving the first indication information sent by the base station;

[0295] A compression module, configured to compress channel data based on the pre-trained channel compression model, and output compressed channel data.

[0296] In some embodiments, it further includes:

[0297] A configuration information receiving module, configured to receive first resource configuration information sent by the base station, where the first resource configuration information is used to indicate time-frequency resources for the terminal to send the compressed channel data and send a neighboring reference signal;

[0298] The first data sending module is specifically configured to directly map the compressed channel data and the neighboring reference signal to time-frequency resources based on the first resource configuration information.

[0299] In some embodiments, the neighboring reference signal is set within the coherent bandwidth of the compressed channel data.

[0300] In some embodiments, the compressed channel data is sent in a combined manner or in a non - combined manner. If the compressed channel data is sent in a combined manner, the method further includes:

[0301] A combining module, configured to perform data combination processing on the compressed channel data output by the channel compression model to obtain at least one compressed channel data combination;

[0302] The first data sending module is specifically configured to directly map the at least one compressed channel data combination to time - frequency resources.

[0303] In some embodiments, it further includes:

[0304] A normalization processing method receiving module, configured to receive the normalization processing method sent by the base station;

[0305] A normalization processing module, configured to perform normalization processing on the compressed channel data according to the normalization processing method to obtain the normalized compressed channel data;

[0306] The first data sending module is specifically configured to directly map the normalized compressed channel data to time - frequency resources.

[0307] In some embodiments, it further includes:

[0308] A second configuration information receiving module, configured to receive the second resource configuration information sent by the terminal, where the second resource configuration information is used to indicate the time - frequency resources for the terminal to send normalization elements;

[0309] A normalization element sending module, configured to map the normalization elements used in the normalization processing process to time - frequency resources according to the second resource configuration information, so as to send them to the base station.

[0310] In some embodiments, the normalization method is the maximum normalization method;

[0311] If the terminal sends the compressed channel data in a combined manner, the normalization element is the maximum modulus value in the compressed channel data combination.

[0312] In some embodiments, it further includes:

[0313] A second indication information receiving module, configured to receive the second indication information sent by the base station;

[0314] A second data sending module, configured to perform quantization processing on the compressed channel data output by the channel compression model according to the second indication information, and map the compressed channel data obtained through the quantization processing to time-frequency resources, so as to send the data to the base station.

[0315] The method for transmitting channel data provided by the embodiments of the present disclosure corresponds to the method embodiment shown above Figure 1-13 and can execute the method and achieve corresponding technical effects. The embodiments of the present disclosure will not be described in detail. The specific implementation manners and achieved technical effects can refer to the above embodiments.

[0316] Specifically, referring to Figure 16 , which shows a schematic structural diagram of an electronic device suitable for implementing the embodiments of the present disclosure. The electronic device 600 in the embodiments of the present disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Tablet Computers), PMPs (Portable Multimedia Players), vehicle terminals (such as vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. The shown electronic device is only an example and should not impose any limitation on the functions and usage scope of the embodiments of the present disclosure.

[0317] As shown in the figure, the electronic device 600 may include a processing device (such as a central processing unit, a graphics processing unit, etc.) 601, which may perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the electronic device 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0318] Generally, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device 600 to communicate with other devices wirelessly or wiredly to exchange data. Although the electronic device 600 with various devices is shown, it should be understood that it is not required to implement or include all the shown devices. More or fewer devices may be alternatively implemented or included.

[0319] In particular, according to embodiments of the present disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product that includes a computer program carried on a non-transitory computer-readable medium, and the computer program includes program code for performing the methods shown in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device 609, or installed from a storage device 608, or installed from a ROM 602. When the computer program is executed by a processing device 601, the above-described functions defined in the method for transmitting channel data according to embodiments of the present disclosure are performed.

[0320] It should be noted that the above-mentioned computer-readable medium in the present disclosure can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium can include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present disclosure, a computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, and the computer-readable signal medium can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0321] In some embodiments, the client and the server can communicate using any currently known or future-developed network protocol such as HTTP (HyperText Transfer Protocol), and can be interconnected with digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include local area networks ("LAN"), wide area networks ("WAN"), the Internet (e.g., the Internet), and end-to-end networks (e.g., ad hoc end-to-end networks), as well as any currently known or future-developed networks.

[0322] The above computer-readable medium can be included in the above electronic device; or it can exist separately without being assembled into the electronic device.

[0323] The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by the electronic device, the electronic device is caused to:

[0324] Send first indication information to the terminal, where the first indication information is used to instruct the terminal to directly map the compressed channel data output by the channel compression model to time-frequency resources. Alternatively, the electronic device is caused to: receive the first indication information sent by the base station;

[0325] According to the first indication information, directly map the compressed channel data output by the channel compression model to time-frequency resources for sending to the base station.

[0326] Computer program code for performing the operations of the present disclosure can be written in one or more programming languages or combinations thereof. The above programming languages include, but are not limited to, object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., by using an Internet service provider to connect through the Internet).

[0327] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a part of code that contains one or more executable instructions for implementing the specified logical function. It should also be noted that, in some alternative implementations, the functions noted in the blocks may occur in a different order than that noted in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions.

[0328] The units involved in the embodiments described in the present disclosure can be implemented in software or in hardware. In some cases, the name of the unit does not constitute a limitation on the unit itself.

[0329] The functions described above herein can be performed, at least in part, by one or more hardware logic components. By way of example, and not limitation, the types of hardware logic components that may be used include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0330] In the context of the present disclosure, a machine-readable medium may be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0331] According to one or more embodiments of the present disclosure, the present disclosure provides a computer-readable storage medium storing a computer program for executing the method for transmitting channel data as provided in any one of the present disclosure.

[0332] The above description is only a preferred embodiment of the present disclosure and an explanation of the applied technical principles. Those skilled in the art should understand that the scope of the disclosure involved in the present disclosure is not limited to the technical solutions formed by the specific combination of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosure concept. For example, the technical solutions formed by mutually replacing the above features with the technical features (but not limited to) having similar functions disclosed in the present disclosure.

[0333] In addition, although the operations are depicted in a particular order, this should not be construed as requiring that the operations be performed in the particular order shown or in sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, although several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the present disclosure. Certain features described in the context of separate embodiments may also be implemented combinatorially in a single embodiment. Conversely, the various features described in the context of a single embodiment may also be implemented separately or in any suitable sub-combination in multiple embodiments.

[0334] Although the subject matter has been described in language specific to structural features and / or methodological acts, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. On the contrary, the specific features and acts described above are merely example forms for implementing the claims.

Claims

1. A method for transmitting channel data, characterized in that, The method includes: Receiving first indication information sent by a base station; Directly mapping the compressed channel data output by a channel compression model to time-frequency resources according to the first indication information, so as to send to the base station.

2. The method according to claim 1, wherein Before receiving the first indication information sent by the base station, it further includes: Receiving a pre-trained channel compression model sent by the base station; Compressing channel data based on the pre-trained channel compression model and outputting compressed channel data.

3. The method according to claim 1, characterized in that The directly mapping the compressed channel data output by the channel compression model to time-frequency resources according to the first indication information includes: Directly mapping the compressed channel data output by the channel compression model and adjacent reference signals to time-frequency resources according to the first indication information.

4. The method according to claim 3, characterized in that, It further includes: Receiving first resource configuration information sent by the base station, where the first resource configuration information is used to indicate the time-frequency resources for the terminal to send the compressed channel data and send adjacent reference signals, and the adjacent reference signals are set within the coherence bandwidth of the compressed channel data; The directly mapping the compressed channel data output by the channel compression model and adjacent reference signals to time-frequency resources includes: Directly mapping the compressed channel data and the adjacent reference signals to time-frequency resources based on the first resource configuration information.

5. The method according to claim 1, wherein Sending the compressed channel data in a combined manner or sending the compressed channel data in a non-combined manner. If the compressed channel data is sent in a combined manner, the method further includes: Performing data combination processing on the compressed channel data output by the channel compression model to obtain at least one compressed channel data combination; The directly mapping the compressed channel data output by the channel compression model to time-frequency resources includes: Directly mapping the at least one compressed channel data combination to time-frequency resources.

6. The method according to claim 1, wherein It further includes: Receiving a normalization processing method sent by the base station; Performing normalization processing on the compressed channel data according to the normalization processing method to obtain normalized compressed channel data; The directly mapping the compressed channel data output by the channel compression model to time-frequency resources includes: Directly mapping the normalized compressed channel data to time-frequency resources.

7. The method according to claim 6, wherein It further includes: Receiving second resource configuration information sent by the terminal, where the second resource configuration information is used to indicate the time-frequency resources for the terminal to send normalization elements; Mapping the normalization elements used in the normalization processing to time-frequency resources according to the second resource configuration information, so as to send to the base station.

8. The method according to claim 1, characterized in that It further includes: Receiving second indication information sent by the base station; Performing quantization processing on the compressed channel data output by the channel compression model according to the second indication information, and mapping the compressed channel data obtained by the quantization processing to time-frequency resources, so as to send to the base station.

9. A method for transmitting channel data, characterized in that, The method includes: Sending first indication information to the terminal, where the first indication information is used to indicate the terminal to directly map the compressed channel data output by the channel compression model to time-frequency resources.

10. The method according to claim 9, wherein The first indication message is further used to indicate the terminal to directly map adjacent reference signals to time-frequency resources.

11. The method according to claim 9, wherein Before sending the first indication information to the terminal, it further includes: Obtaining channel evaluation quality; The sending the first indication information to the terminal includes: When the channel evaluation quality meets a first preset threshold, send first indication information to the terminal.

12. The method according to claim 9, characterized in that It further includes: Obtain a pre-trained channel compression model, a pre-trained channel decompression model, and the number of compressed channel data input to the channel decompression model; Send the pre-trained channel compression model to the terminal.

13. The method according to claim 9, wherein It further includes: Obtain the normalization processing method for the terminal to normalize the compressed channel data output by the channel compression model; Send the normalization processing method to the terminal.

14. The method according to any one of claims 10 - 13, characterized in that It further includes: Send first resource configuration information to the terminal, where the first resource configuration information is used to indicate the time-frequency resources required for the terminal to send the compressed channel data and send adjacent reference signals, and the adjacent reference signals are set within the coherent bandwidth of the compressed channel data.

15. The method according to claim 14, wherein Before sending the first resource configuration information to the terminal, it further includes: Obtain the number of compressed channel data input to the channel decompression model and the number of adjacent reference signals; Based on the number of compressed channel data input to the channel decompression model and the number of adjacent reference signals, determine the time-frequency resources required for the terminal to send the compressed channel data and send adjacent reference signals.

16. The method according to claim 14, wherein The terminal sends compressed channel data in a combined manner or non-combined manner.

17. The method according to claim 14, characterized in that, It further includes: Send second resource configuration information to the terminal, where the second resource configuration information is used to indicate the time-frequency resources for the terminal to send normalization elements.

18. The method according to claim 17, wherein It further includes: Obtain the compressed channel data output by the channel compression model sent by the terminal; Input the compressed channel data into the channel decompression model to decompress the channel data by the channel decompression model; Among them, obtaining the compressed channel data output by the channel compression model sent by the terminal includes: Obtain adjacent reference signals directly mapped to the time-frequency resources, and resolve the channel according to the adjacent reference signals; Obtain the compressed channel data output by the channel compression model sent by the terminal according to the resolved channel.

19. The method according to claim 18, wherein It further includes: Obtain the normalization elements used by the terminal during the normalization process of the compressed channel data; The obtaining the compressed channel data output by the channel compression model sent by the terminal according to the resolved channel includes: Obtain the compressed channel data output by the channel compression model sent by the terminal according to the resolved channel and the normalization elements.

20. The method according to claim 9, characterized in that, It further includes: Re-obtain the channel evaluation quality; When the channel evaluation quality meets a second preset threshold, send second indication information to the terminal, where the second indication information is used to indicate the terminal to perform quantization processing on the compressed channel data output by the channel compression model and map the quantized compressed channel data to time-frequency resources.

21. A transmission device for channel data, applied to a terminal, characterized in that, The device includes: A first indication receiving module, configured to receive first indication information sent by the base station; A first data sending module, configured to directly map the compressed channel data output by the channel compression model to time-frequency resources according to the first indication information, so as to send to the base station.

22. A transmission device for channel data, characterized in that, The device includes: The first indication sending module is configured to send first indication information to a terminal, where the first indication information is used to instruct the terminal to directly map the compressed channel data output by the channel compression model to time-frequency resources.

23. An electronic device, characterized in that, The electronic device includes: a processor; a memory for storing executable instructions of the processor; The processor is configured to read the executable instructions from the memory and execute the instructions to implement the channel data transmission method according to any one of claims 1-8 or the channel data transmission method according to any one of claims 9-20.

24. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, and the computer program is used to execute the channel data transmission method according to any one of claims 1-8 or the channel data transmission method according to any one of claims 9-20.

Images