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

Abstract

Embodiments of the present disclosure relate to a channel data transmission method and apparatus, an electronic device and a storage medium. The method comprises: sending first instruction information to a receiving end, wherein the first instruction information is used for instructing the receiving end to directly map compressed channel data output by a channel compression model to a time-frequency resource.

Description

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

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to Chinese patent application No. 202311785851.7 filed in China on December 22, 2023, the entire contents of which are incorporated herein by reference. Technical Field

[0003] The present disclosure relates to the field of communication technology, and in particular to a method, device, electronic device, and storage medium for transmitting channel data. Background Art

[0004] In the field of mobile communications, after receiving a signal from a transmitter, a signal receiver feeds back channel state information (CSI) of the communication channel to enable the transmitter to accurately understand the channel state and improve signal transmission quality. For example, in a multiple-input multiple-output (MIMO) system, beamforming based on CSI is a key requirement for improving transmission performance. This is especially true for frequency division duplex (FDD) systems, where complete uplink and downlink channel reciprocity is absent. The transmitter relies on receiver feedback to obtain complete downlink CSI. In New Radio (NR) systems, CSI feedback from the receiver primarily relies on codebooks. For example, CSI Type I, Type II, and enhanced Type II codebooks can be used to feed back information such as rank indicator (IR), precoding matrix indicator (PMI), and channel quality indicator (CQI).

[0005] A related art solution for feeding back channel state information utilizes a data-driven deep learning approach to set up corresponding channel compression and decompression models. For example, a channel compression model is configured at the receiving end, which can extract low-dimensional features from the channel data to generate compressed channel data. The compressed channel data is then sent to the transmitting end, where the channel decompression model configured on the transmitting end decompresses the compressed channel data to obtain the channel data. In this solution for feeding back signal state information, the compressed signal data output by the channel compression model typically requires quantization, channel coding, and scrambling before transmission. This related art solution suffers from high transmission overhead and a complex processing flow. Summary of the Invention

[0006] In order to solve the above technical problems, the present disclosure provides a method, device, electronic device and storage medium for transmitting channel data.

[0007] An embodiment of the present disclosure provides a method for transmitting channel data, the method comprising:

[0008] First indication information is sent to a receiving end, where the first indication information is used to instruct the receiving end to directly map compressed channel data output by the channel compression model to time-frequency resources.

[0009] In some embodiments, the first indication message is further used to instruct the receiving end to directly map the adjacent reference signal to the time-frequency resource.

[0010] In some embodiments, before sending the first indication information to the receiving end, the method further includes:

[0011] Obtain channel assessment quality;

[0012] The sending the first indication information to the receiving end includes:

[0013] When the channel evaluation quality meets a first preset threshold, first indication information is sent to the receiving end.

[0014] In some embodiments, the channel assessment quality includes any one of a channel signal-to-noise ratio, a bit error rate, and a channel quality indicator;

[0015] If the channel estimation quality includes a channel signal-to-noise ratio, obtaining the channel estimation quality includes:

[0016] A sounding reference signal is received from a receiving end, and a channel signal-to-noise ratio is calculated according to the sounding reference signal.

[0017] In some embodiments, further comprising:

[0018] A pre-trained channel compression model, a pre-trained channel decompression model, and the number of compressed channel data input by the channel decompression model are obtained.

[0019] In some embodiments, further comprising:

[0020] The pre-trained channel compression model is sent to the receiving end.

[0021] In some embodiments, further comprising:

[0022] Obtaining a normalization processing method for performing normalization processing on compressed channel data output by the channel compression model at the receiving end;

[0023] The normalized processing mode is sent to the receiving end.

[0024] In some embodiments, further comprising:

[0025] First resource configuration information is sent to a receiving end, where the first resource configuration information is used to instruct the receiving end to use time-frequency resources required to send the compressed channel data and the adjacent reference signal.

[0026] In some embodiments, the adjacent reference signal is disposed within a coherence bandwidth of the compressed channel data.

[0027] In some embodiments, before sending the first resource configuration information to the receiving end, the method further includes:

[0028] Acquire the number of compressed channel data input by the channel decompression model and the number of the adjacent reference signals;

[0029] Based on the number of compressed channel data input into the channel decompression model and the number of the adjacent reference signals, the time-frequency resources required by the receiving end to send the compressed channel data and the adjacent reference signals are determined.

[0030] In some embodiments, the receiving end sends compressed channel data in a combined manner or compressed channel data in a non-combined manner.

[0031] In some embodiments, further comprising:

[0032] Second resource configuration information is sent to the receiving end, where the second resource configuration information is used to instruct the receiving end to send the time-frequency resource of the normalized element.

[0033] In some embodiments, further comprising:

[0034] Acquire compressed channel data output by the channel compression model and sent by a receiving end;

[0035] The compressed channel data is input to the channel decompression model so as to be decompressed by the channel decompression model to obtain the channel data.

[0036] In some embodiments, obtaining compressed channel data sent by the receiving end and output by the channel compression model includes:

[0037] Acquire an adjacent reference signal directly mapped to the time-frequency resource, and parse out a channel according to the adjacent reference signal;

[0038] The compressed channel data output by the channel compression model and sent by the receiving end is obtained according to the parsed channel.

[0039] In some embodiments, further comprising:

[0040] Obtaining a normalization element used by a receiving end in a process of normalizing the compressed channel data;

[0041] The step of obtaining compressed channel data output by the channel compression model and sent by a receiving end according to the parsed channel includes:

[0042] The compressed channel data output by the channel compression model and sent by the receiving end is obtained according to the parsed channel and the normalization element.

[0043] In some embodiments, the normalization processing method is a maximization normalization method;

[0044] If the receiving end sends compressed channel data in a combination, the normalization element is the maximum modulus value in the compressed channel data combination.

[0045] In some embodiments, further comprising:

[0046] Re-acquire channel assessment quality;

[0047] When the channel evaluation quality meets a second preset threshold, second indication information is sent to the receiving end, wherein the second indication information is used to instruct the receiving end to quantize 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.

[0048] The present disclosure also provides a method for transmitting channel data, the method comprising:

[0049] receiving first indication information sent by a sending end;

[0050] The compressed channel data output by the channel compression model is directly mapped to time-frequency resources according to the first indication information, so as to be sent to the transmitting end.

[0051] In some embodiments, directly mapping the compressed channel data output by the channel compression model to the time-frequency resources according to the first indication information includes:

[0052] The compressed channel data and adjacent reference signals output by the channel compression model are directly mapped to time-frequency resources according to the first indication information.

[0053] In some embodiments, before receiving the first indication information sent by the transmitting end, the method further includes:

[0054] Establishing a radio link control layer connection with the transmitting end;

[0055] A sounding reference signal is sent to the transmitting end, so that the transmitting end calculates a channel signal-to-noise ratio according to the sounding reference signal.

[0056] In some embodiments, before receiving the first indication information sent by the transmitting end, the method further includes:

[0057] Receive the pre-trained channel compression model sent by the transmitter;

[0058] The channel data is compressed based on the pre-trained channel compression model, and the compressed channel data is output.

[0059] In some embodiments, it further includes:

[0060] receiving first resource configuration information sent by a transmitting end, where the first resource configuration information is used to instruct the receiving end to send the compressed channel data and a time-frequency resource for sending an adjacent reference signal;

[0061] Directly mapping the compressed channel data output by the channel compression model onto the time-frequency resources includes:

[0062] The compressed channel data and the adjacent reference signal are directly mapped onto time-frequency resources based on the first resource configuration information.

[0063] In some embodiments, the adjacent reference signal is disposed within a coherence bandwidth of the compressed channel data.

[0064] 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 comprises:

[0065] performing data combination processing on the compressed channel data output by the channel compression model to obtain at least one compressed channel data combination;

[0066] Directly mapping the compressed channel data output by the channel compression model onto the time-frequency resources includes:

[0067] The at least one compressed channel data combination is directly mapped onto time-frequency resources.

[0068] In some embodiments, further comprising:

[0069] Normalization processing method sent by the receiving and sending end;

[0070] performing normalization processing on the compressed channel data according to the normalization processing method to obtain normalized compressed channel data;

[0071] Directly mapping the compressed channel data output by the channel compression model onto the time-frequency resources includes:

[0072] The normalized compressed channel data is directly mapped onto time-frequency resources.

[0073] In some embodiments, further comprising:

[0074] receiving second resource configuration information sent by a receiving end, where the second resource configuration information is used to instruct the receiving end to send a time-frequency resource for a normalized element;

[0075] According to the second resource configuration information, the normalization elements used in the normalization process are mapped to time-frequency resources to send to the transmitting end.

[0076] In some embodiments, the normalization method is a maximization normalization method;

[0077] If the receiving end sends the compressed channel data in a combined manner, the normalization element is the maximum modulus value in the compressed channel data combination.

[0078] In some embodiments, further comprising:

[0079] receiving second sending instruction information sent by the sending end;

[0080] The compressed channel data output by the channel compression model is quantized according to the second indication information, and the compressed channel data obtained by the quantization is mapped to time-frequency resources to be sent to the transmitting end.

[0081] The present disclosure also provides a device for transmitting channel data, the device comprising:

[0082] The first indication sending module is used to send first indication information to the receiving end, where the first indication information is used to instruct the receiving end to directly map the compressed channel data output by the channel compression model to the time-frequency resources.

[0083] In some embodiments, the first indication message is further used to instruct the receiving end to directly map the adjacent reference signal to the time-frequency resource.

[0084] In some embodiments, before sending the first indication information to the receiving end, the method further includes:

[0085] A first channel quality acquisition module, configured to acquire channel evaluation quality before sending first indication information to a receiving end;

[0086] The first indication sending module is specifically configured to send first indication information to the receiving end when the channel evaluation quality meets a first preset threshold.

[0087] In some embodiments, the channel assessment quality includes any one of a channel signal-to-noise ratio, a bit error rate, and a channel quality indicator; the first channel quality acquisition module is specifically used to receive a sounding reference signal sent by a receiving end, and calculate the channel signal-to-noise ratio based on the sounding reference signal.

[0088] In some embodiments, it further includes:

[0089] A first acquisition module is used to acquire a pre-trained channel compression model, a pre-trained channel decompression model and the number of compressed channel data input by the channel decompression model;

[0090] The first sending module is used to send the pre-trained channel compression model to the receiving end.

[0091] In some embodiments, it further includes:

[0092] A normalization processing method acquisition module is used to obtain a normalization processing method used by the receiving end to normalize the compressed channel data output by the channel compression model;

[0093] In some embodiments, it further includes:

[0094] The first sending module is further configured to send the normalized processing mode to the receiving end.

[0095] In some embodiments, it further includes:

[0096] The configuration sending module is used to send first resource configuration information to the receiving end, where the first resource configuration information is used to instruct the receiving end to send the compressed channel data and the time-frequency resources required to send the adjacent reference signal.

[0097] In some embodiments, the adjacent reference signal is disposed within a coherence bandwidth of the compressed channel data.

[0098] In some embodiments, it further includes:

[0099] a number acquisition module, configured to acquire the number of compressed channel data input by the channel decompression model and the number of adjacent reference signals before sending the first resource configuration information to the receiving end;

[0100] The resource determination module is used to determine the time-frequency resources required by the receiving end to send the compressed channel data and the adjacent reference signals based on the number of compressed channel data input on the channel decompression model and the number of the adjacent reference signals.

[0101] In some embodiments, the receiving end sends compressed channel data in a combined manner or compressed channel data in a non-combined manner.

[0102] In some embodiments, further comprising:

[0103] Second resource configuration information is sent to the receiving end, where the second resource configuration information is used to instruct the receiving end to send the time-frequency resource of the normalized element.

[0104] In some embodiments, further comprising:

[0105] A channel data acquisition module, configured to acquire compressed channel data output by the channel compression model and sent by a receiving end;

[0106] The decompression module is configured to input the compressed channel data into the channel decompression model so as to decompress the channel data using the channel decompression model.

[0107] In some embodiments, the channel data acquisition module includes:

[0108] a channel parsing unit, configured to obtain an adjacent reference signal directly mapped onto the time-frequency resource, and parse out a channel based on the adjacent reference signal;

[0109] A data acquisition unit is used to acquire compressed channel data output by the channel compression model and sent by a receiving end according to the parsed channel.

[0110] In some embodiments, further comprising:

[0111] a normalization element acquisition unit, configured to acquire a normalization element used by a receiving end in a process of normalizing the compressed channel data;

[0112] A data acquisition unit is used to acquire compressed channel data output by the channel compression model and sent by a receiving end according to the parsed channel and the normalization element.

[0113] In some embodiments, the normalization processing method is a maximization normalization method;

[0114] If the receiving end sends compressed channel data in a combination, the normalization element is the maximum modulus value in the compressed channel data combination.

[0115] In some embodiments, further comprising:

[0116] A second signal-to-noise ratio acquisition module, configured to reacquire channel assessment quality;

[0117] A second indication information sending module is used to send second indication information to the receiving end when the channel evaluation quality meets the second preset threshold value. The second indication information is used to instruct the receiving end to quantize 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.

[0118] The present disclosure also provides a channel data transmission device, which is applied to a receiving end and includes:

[0119] A first indication receiving module, configured to receive first indication information sent by a sending end;

[0120] The first data sending module is configured to directly map the compressed channel data output by the channel compression model onto time-frequency resources according to the first indication information, so as to send the data to the sending end.

[0121] In some embodiments, the first sending module is specifically configured to directly map the compressed channel data and adjacent reference signals output by the channel compression model onto time-frequency resources according to the first indication information, so as to send the compressed channel data and adjacent reference signals to the transmitting end.

[0122] In some embodiments, further comprising:

[0123] a connection establishing module, configured to establish a radio link control layer connection with the sending end before receiving the first indication information sent by the sending end;

[0124] The sounding module is configured to send a sounding reference signal to the transmitting end, so that the transmitting end calculates a channel signal-to-noise ratio according to the sounding reference signal.

[0125] In some embodiments, further comprising:

[0126] A model receiving module, configured to receive a pre-trained channel compression model sent by the sending end before receiving the first indication information sent by the sending end;

[0127] The compression module is used to compress the channel data based on the pre-trained channel compression model and output the compressed channel data.

[0128] In some embodiments, it further includes:

[0129] a configuration information receiving module, configured to receive first resource configuration information sent by a transmitting end, where the first resource configuration information is used to instruct the receiving end to send the compressed channel data and the time-frequency resources for sending the adjacent reference signal;

[0130] The first data sending module is specifically configured to directly map the compressed channel data and the adjacent reference signal to time-frequency resources based on the first resource configuration information.

[0131] In some embodiments, the adjacent reference signal is disposed within a coherence bandwidth of the compressed channel data.

[0132] 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 comprises:

[0133] a combining module, configured to perform data combining processing on the compressed channel data output by the channel compression model to obtain at least one compressed channel data combination;

[0134] The first data sending module is specifically configured to directly map the at least one compressed channel data combination onto the time-frequency resources.

[0135] In some embodiments, further comprising:

[0136] A normalization processing mode receiving module is used to receive the normalization processing mode sent by the sending end;

[0137] 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;

[0138] The first data sending module is specifically configured to directly map the normalized compressed channel data onto time-frequency resources.

[0139] In some embodiments, further comprising:

[0140] A second configuration information receiving module is configured to receive second resource configuration information sent by a receiving end, where the second resource configuration information is used to instruct the receiving end to send a time-frequency resource for a normalized element;

[0141] The normalization element sending module is used to map the normalization element used in the normalization processing process to the time-frequency resource according to the second resource configuration information, so as to send it to the sending end.

[0142] In some embodiments, the normalization method is a maximization normalization method;

[0143] If the receiving end sends the compressed channel data in a combined manner, the normalization element is the maximum modulus value in the compressed channel data combination.

[0144] In some embodiments, further comprising:

[0145] A second indication information receiving module, configured to receive the second sending indication information sent by the sending end;

[0146] The second data sending module is used to quantize 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 to send it to the sending end.

[0147] An embodiment of the present disclosure further provides an electronic device, the electronic device comprising:

[0148] processor;

[0149] a memory for storing instructions executable by the processor;

[0150] The processor is configured to read the executable instructions from the memory and execute the instructions to implement any one of the above-mentioned channel data transmission methods.

[0151] An embodiment of the present disclosure further provides a computer-readable storage medium, wherein the storage medium stores a computer program, and the computer program is used to execute any of the above-mentioned channel data transmission methods.

[0152] The embodiments of the present disclosure further provide a computer program product, which is used to execute any of the above-mentioned channel data transmission methods.

[0153] An embodiment of the present disclosure further provides a computer program product, comprising computer instructions, which, when executed by a processor, implement any of the above channel data transmission methods.

[0154] The embodiments of the present disclosure provide a technical solution for feeding back channel state information, wherein when a receiving end sends channel data to a transmitting end, the compressed channel data output by the channel compression model on the receiving end is directly mapped to time-frequency resources and then sent to the transmitting end, rather than first performing quantization processing and other operations and then mapping to time-frequency resources. In this way, after the transmitting end receives the above-mentioned compressed channel data, there is no need to perform dequantization processing operations, which not only reduces transmission overhead, but also simplifies the processing flow at the receiving end and the transmitting end when feedback of channel state information is provided. BRIEF DESCRIPTION OF THE DRAWINGS

[0155] The above and other features, advantages, and aspects of the various embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that the originals and elements are not necessarily drawn to scale.

[0156] FIG1 is a schematic flow chart of a method for transmitting channel data according to an embodiment of the present disclosure;

[0157] FIG2 is a schematic flow chart of another method for transmitting channel data according to an embodiment of the present disclosure;

[0158] FIG3 is a schematic flow chart of another method for transmitting channel data according to an embodiment of the present disclosure;

[0159] FIG4 is a schematic diagram of a process for determining time-frequency resources according to an embodiment of the present disclosure;

[0160] FIG5 is a schematic flow chart of another method for transmitting channel data according to an embodiment of the present disclosure;

[0161] FIG6 is a schematic flow chart of another method for transmitting channel data according to an embodiment of the present disclosure;

[0162] FIG7 shows a flow chart of a conventional receiving end feeding back channel state information to a transmitting end;

[0163] FIG8 is a flow chart of yet another data transmission method provided by an embodiment of the present disclosure;

[0164] FIG9 is a schematic flow chart of yet another method for transmitting channel data according to an embodiment of the present disclosure;

[0165] FIG10 is a schematic flow chart of yet another method for transmitting channel data according to an embodiment of the present disclosure;

[0166] FIG11 is a schematic diagram of resource mapping according to an embodiment of the present disclosure;

[0167] FIG12 is a flow chart of a resource mapping according to an embodiment of the present disclosure;

[0168] FIG13 is a flow chart of a specific implementation scheme provided by an embodiment of the present disclosure;

[0169] FIG14 is a schematic structural diagram of a channel data transmission device provided by an embodiment of the present disclosure;

[0170] FIG15 is a schematic structural diagram of another channel data transmission device provided by an embodiment of the present disclosure;

[0171] FIG16 is a schematic structural diagram of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0172] The following describes embodiments of the present disclosure in more detail with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying 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 described herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

[0173] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders 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 respect.

[0174] As used herein, the term "including" and its variations are open-ended, i.e., "including but not limited to." The term "based on" means "based, at least in part, on." The term "one embodiment" means "at least one embodiment," the term "another embodiment" means "at least one additional embodiment," and the term "some embodiments" means "at least some embodiments." Other terms are defined in the following description.

[0175] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0176] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, they should be understood as "one or more".

[0177] In the related art, when feedback of channel state information is performed, the compressed signal data output by the channel compression model is usually quantized, channel-coded, and scrambled before being transmitted, resulting in defects such as large transmission overhead and complex processing flow. The embodiment of the present disclosure provides a technical solution for feedback of channel state information, wherein when the receiving end sends channel data to the transmitting end, the compressed channel data output by the channel compression model on the receiving end is directly mapped to the time-frequency resources and then sent to the transmitting end, rather than first performing quantization processing and other operations and then mapping to the time-frequency resources. In this way, after the transmitting end receives the above-mentioned compressed channel data, there is no need to perform dequantization processing operations, thereby not only reducing transmission overhead, but also simplifying the processing flow on the receiving end and the transmitting end when feedback of channel state information. The technical solution provided by the embodiment of the present disclosure has improvements on both the receiving end and the transmitting end, and the following embodiments will be explained from the transmitting end side and the receiving end side respectively.

[0178] The channel data transmission method provided in the embodiment of the present disclosure is a technical solution implemented on the transmitting end side, which can be specifically shown in Figure 1. Figure 1 is a flow chart of a channel data transmission method provided in the embodiment of the present disclosure. As shown in Figure 1, the method includes the following steps:

[0179] Step 100: The transmitting end sends first indication information to the receiving end, where the first indication information is used to instruct the receiving end to directly map the compressed channel data output by the channel compression model to the time-frequency resources;

[0180] In the embodiment of the present disclosure, the transmitting end may be a network side device (such as a base station), and the receiving end may be a terminal.

[0181] Specifically, in the embodiment of the present disclosure, a wireless access network artificial intelligence (AI) model training system may be used to pre-collect downlink channel data and offline train a channel compression model and a channel decompression model based on an AI autoencoder. The above-mentioned AI model training system may be deployed on a centralized unit (CU) and / or distributed unit (DU) at the transmitting end, or deployed on a logical entity across CUs. After pre-training the above-mentioned channel compression model and channel decompression model, the channel compression model may be sent to the receiving end, and the channel decompression model may be set on the transmitting end.

[0182] In this step, when the transmitting end determines to send compressed channel data to the transmitting end by directly mapping the compressed channel data to the time-frequency resources, the corresponding first indication information is sent to the receiving end so that the receiving end can directly map the compressed channel data output by the above-mentioned pre-trained channel compression model to the time-frequency resources. The above-mentioned compressed channel data is not subjected to quantization processing, channel coding, scrambling and other operations, and is a kind of non-quantized data. By using this technical solution, the transmission overhead can be reduced, and the processing flow at the receiving end and the transmitting end when the channel state information is fed back 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.

[0183] Among them, the above-mentioned determination of sending compressed channel data to the transmitting end by directly mapping the compressed channel data to time-frequency resources can include multiple methods. For example, the transmitting end is preset to use the above-mentioned method to feedback channel state information. At this time, after the receiving end and the transmitting end establish a wireless link control layer connection, the first indication information can be sent to the connected receiving end to instruct the receiving end to send compressed channel data in the above-mentioned method.

[0184] In some embodiments, the first indication message may also be used to instruct the receiving end to directly map the adjacent reference signal to the time-frequency resource. The adjacent reference signal is used as a pilot signal, and the channel can be parsed from the pilot signal, and the compressed channel data can be further parsed from the channel.

[0185] In another case, the transmitting end may obtain the evaluation quality when communicating with the receiving end, and then determine whether to send the 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 compressed channel data is directly mapped to the time-frequency resource to send the compressed channel data to the transmitting end. The above-mentioned channel evaluation quality includes any one of the channel signal-to-noise ratio, the bit error rate and the 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 means 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 transmitting end well, avoiding the inability to effectively transmit the compressed channel data to the transmitting end due to large noise and interference; if the channel signal-to-noise ratio is less than the preset threshold, it means that the channel quality is poor. At this time, the compressed channel data output by the channel compression model can still be quantized, channel coded, scrambled and modulated, and then resource mapping can be performed to map the compressed channel data after the above series of processing to the time-frequency resources. If the channel assessment quality includes a bit error rate, and the bit error rate can be set to be less than or equal to a preset threshold, the technical solution of the embodiment of the present disclosure is adopted to send first indication information to the receiving end, or if the channel assessment quality includes a channel quality indication, the channel quality indication 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 first indication information to the receiving end.

[0186] The specific method flow chart of the above situation can be shown in Figure 2, which is a flow chart of another channel data transmission method provided by an embodiment of the present disclosure. As shown in Figure 2, taking the channel signal-to-noise ratio as an example, the method includes the following steps:

[0187] Step 110: Obtain channel signal-to-noise ratio;

[0188] Specifically, in this step, a sounding reference signal (SRS) sent by the receiving end may be first received. After the transmitting end obtains the sounding reference signal, the channel signal-to-noise ratio may be calculated based on the sounding reference signal.

[0189] Step 120: When the channel signal-to-noise ratio is greater than or equal to a preset threshold, send first indication information to the receiving end.

[0190] In this step, after the transmitting end calculates the channel signal-to-noise ratio, it determines the relationship between the channel signal-to-noise ratio and a preset threshold value, and sends first indication information to the receiving end when the channel signal-to-noise ratio is greater than or equal to the preset threshold value. This allows the compressed channel data to be mapped to the time-frequency resources using the above-mentioned direct mapping method when the channel quality is good, thereby realizing feedback of the channel state information and ensuring the quality of the information state feedback.

[0191] As described above, the channel compression model and the channel decompression model can be pre-trained on the transmitting end to obtain a pre-trained channel compression model and a channel decompression model, wherein the pre-trained channel compression model needs to be sent to the receiving end. In addition, for the channel compression model, the range of its output value can generally 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 a tan function. At this time, the compressed channel data output can be in the value range of [-1, 1]. If a suitable activation function is not set in the activation function, so that the compressed channel data output at this time is not in the above value range, it is necessary to normalize the compressed channel data and then directly map it to the time-frequency resource. Specifically, in the embodiment of the present disclosure, the transmitting end can obtain the normalization processing method for the receiving end to normalize the compressed channel data output by the channel compression model, and then send the normalization processing method to the above-mentioned receiving end, so that the compressed channel data output by the channel compression model can be normalized on the receiving end.

[0192] Through the above embodiments, the transmitting end sends the channel compression model, normalization processing method, etc. to the receiving end, so that after receiving the first indication information, the receiving end can directly map the compressed channel data output by the channel compression model to the time-frequency resources according to the first indication information to realize the feedback of channel state information to the transmitting end, and when necessary, the compressed channel data can be normalized and then directly mapped to the time-frequency resources without performing quantization processing and other operations.

[0193] In addition, in order for the receiving end to obtain channel data, the transmitting end in the embodiment of the present disclosure can send a channel state information reference signal (CSI-RS) to the receiving end, so that the receiving end can obtain channel data that can reflect the downlink channel quality based on the CSI-RS.

[0194] In order to successfully enable the receiving end to directly map the compressed channel data to the time-frequency resources, it is necessary to allocate time-frequency resources to each receiving end at the transmitting end. Figure 3 is a flow chart of another channel data transmission method provided by an embodiment of the present disclosure. As shown in Figure 3, in addition to the above steps 110 and 120, the following steps are also included:

[0195] Step 130: Send first resource configuration information to the receiving end, where the first resource configuration information is used to instruct the receiving end to use time-frequency resources for sending compressed channel data and sending adjacent reference signals.

[0196] The adjacent reference signal is required to be transmitted simultaneously with the compressed channel data in the time-frequency resources at the receiving end. The transmitting end can parse the channel identified by the adjacent reference signal and then parse the compressed channel data from the signal on that channel. In this step, the transmitting end configures the time-frequency resources used by the receiving end to transmit the compressed channel data and the adjacent reference signal, and then sends this information to the receiving end as the first resource configuration information.

[0197] In this step, the first resource configuration information is sent to the receiving end. The execution order of this step and the above step 120 is not limited in the embodiment of the present disclosure. Any one of them can be executed first, and then the other, or they can be executed simultaneously.

[0198] Before sending the first resource configuration information to the receiving end, the transmitting end needs to first determine the time-frequency resources used by the receiving end when compressing the channel data and the adjacent reference signal. FIG4 is a schematic diagram of a process for determining time-frequency resources according to an embodiment of the present disclosure. As shown in FIG4 , the process includes the following steps:

[0199] Step 410: Obtain the number of compressed channel data and the number of adjacent reference signals inputted by the channel decompression model;

[0200] Specifically, in the above embodiment, the above-mentioned channel compression model has been pre-trained, so the number of compressed channel data input by 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. As for the number of adjacent reference signals, it can be set according to actual needs. Furthermore, the adjacent reference signals can be set within the coherent bandwidth of the compressed channel data.

[0201] Step 420: Based on the number of compressed channel data and the number of adjacent reference signals output by the channel compression model, determine the time-frequency resources required for the receiving end to send the compressed channel data and the adjacent reference signals.

[0202] Specifically, in an embodiment 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 by the channel decompression model is N, then z needs to configure time-frequency resources according to N compressed channel data in a non-combination manner; however, in some combination manners, the compressed channel data output by the channel compression model can be combined, and several compressed channel data can be combined into one compressed channel data combination. For example, when combining two by two, if N is an even number, the number of compressed channel data combinations is N / 2, and if N is an odd number, the number of compressed channel data combinations is N / 2+1. Therefore, when combining two by two, the number of compressed channel data combinations is the number of compressed channel data output 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 embodiment of the present disclosure uses a combination method to combine several compressed channel data into one compressed channel data combination, which can save the required time-frequency resources. For example, the above-mentioned two-by-two combination method can save the required time-frequency resources compared to the original method that requires each resource element (Resource In the embodiment of the present disclosure, a compressed channel data is transmitted on a frame element (RE). In the embodiment of the present disclosure, it is possible to transmit a compressed channel data combination on each RE, that is, two compressed channel data. Similarly, after determining the number of adjacent reference signals that need to be transmitted, the time-frequency resources required therefor can also be determined, and the adjacent reference signals and the time-frequency resources required for the compressed channel data are adjacent. The adjacent reference signals are set within the coherent bandwidth of the compressed channel data, so that the channels they use are the same, so that the channel where the compressed channel data is located can be parsed according to the reference signals. In the embodiment of the present disclosure, the adjacent reference signal means that when it is mapped on the resource grid with the compressed channel number combination, the distance between the REs where the two are located is less than a set threshold value.

[0203] After determining the time-frequency resources allocated to each receiving terminal in this step, the first resource configuration information can be sent according to the embodiment shown in Figure 3. At the same time, to avoid conflicts, after allocating the above time-frequency resources to a receiving terminal, the same time-frequency resources will not be allocated to other receiving terminals.

[0204] FIG5 is a flow chart of another method for transmitting channel data provided by an embodiment of the present disclosure, which is based on FIG3 and, in some embodiments, further includes the following steps:

[0205] Step 140: Send second resource configuration information to the receiving end. The second resource configuration information is used to indicate the time-frequency resources for the receiving end to send a normalization element. The normalization element is used by the receiving end to normalize the compressed channel data output by the channel compression model. After performing the normalization process, the receiving end needs to feed the normalization element back to the transmitting end so that the transmitting end can subsequently restore the compressed channel data based on the normalization element and obtain the compressed channel data before normalization.

[0206] In the above embodiment, after the transmitting end has sent the pre-trained channel compression model and normalization processing method to the receiving end, and also sent the first resource configuration information and the second resource configuration information to the receiving end, the receiving end can then compress the channel data according to the input of the channel compression model to obtain 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 transmitting end. Figure 6 is a flow diagram of another channel data transmission method in an embodiment of the present disclosure. As shown in Figure 6, based on the embodiment shown in Figure 3, it also includes:

[0207] Step 150: Obtain compressed channel data directly mapped to time-frequency resources by the receiving end;

[0208] Specifically, the above-mentioned time-frequency resources are configured by the transmitting end for the receiving end, and are time-frequency resources indicated by the above-mentioned first resource configuration information. In this step, the compressed channel data can be obtained through the above-mentioned time-frequency resources.

[0209] Step 160: Input the compressed channel data into the channel decompression model so that the channel decompression model decompresses the channel data.

[0210] The channel decompression model used in this step is a pre-trained channel decompression model, which is set corresponding to the channel compression model deployed on the receiving end. It can decompress the compressed channel data output by the channel decompression model to obtain the original channel data, thereby feeding back the channel data obtained by the receiving device to the sending end, thereby realizing the feedback of channel state information.

[0211] In the above-mentioned step 150, the compressed channel data output by the channel compression model and sent by the receiving end is obtained. Specifically, the adjacent reference signal directly mapped to the time-frequency resource is first obtained, and the channel is parsed according to the adjacent reference signal. Since the adjacent reference signal is set within the coherent bandwidth of the compressed channel data, it can be ensured that the channel used is the same. After the channel is parsed, the compressed channel data output by the channel compression model can be easily obtained from the parsed channel.

[0212] As described in the above embodiment, the compressed channel data output by the channel decompression model can also be normalized at the receiving end. At this time, the compressed channel data obtained at the sending end is actually the compressed channel data after normalization. At this time, the receiving end 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 sending end. Therefore, the sending end can also obtain the normalization elements obtained by the receiving end in the process of normalizing the compressed channel data. The above-mentioned acquisition of the compressed channel data output by the channel compression model sent by the receiving end according to the parsed channel includes: acquiring the compressed channel data output by the channel compression model sent by the receiving end according to the parsed channel and the normalization element. The normalization element is used to restore the compressed channel data after normalization to the compressed channel data before normalization, so that the compressed channel data before normalization is input into the channel decompression model to obtain the original channel data.

[0213] In the above-mentioned embodiment of the present disclosure, it is mainly a technical solution that is 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 transmitting end, avoiding operations such as quantization processing; and during the communication process between the receiving end and the transmitting end, the transmitting end can re-obtain the channel evaluation quality according to a certain time interval. If the channel evaluation quality still meets the first preset threshold, the above-mentioned technical solution is still executed. If the channel evaluation quality meets the second preset threshold, a second indication information is sent to the receiving end. The second indication information is used to instruct the receiving end to quantize 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-mentioned channel assessment quality may include a channel signal-to-noise ratio, a bit error rate or a channel quality indication. The above-mentioned channel assessment quality meeting the second preset condition may include a channel signal-to-noise ratio less than a preset threshold, a bit error rate greater than a preset threshold or a channel quality indication less than a preset threshold. In this case, it indicates that the channel quality is poor. Channel information feedback can be performed by quantizing the compressed channel data output by the channel compression model and mapping the compressed channel data obtained by the quantization processing to time-frequency resources.

[0214] In this case, when the receiving end sends compressed channel data, the specific steps performed can be referred to as shown in FIG7 . FIG7 shows a flowchart of a traditional receiving end feeding back channel state information to the transmitting end. As shown in FIG7 , in addition to quantizing the compressed channel data, steps such as cyclic redundancy check (CRC), 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. Compared with the technical solution provided in the embodiment of the present disclosure, when the channel signal-to-noise ratio is greater than or equal to a preset threshold, resource mapping is directly performed on the unquantized compressed channel data to the specified time domain resources. This obviously requires more operational steps, increases the difficulty, and significantly increases the transmission overhead. The technical solution proposed in the present disclosure when the channel signal-to-noise ratio is greater than or equal to the preset threshold can obviously overcome the above-mentioned shortcomings.

[0215] Corresponding to the above-mentioned method for transmitting channel data executed on the transmitting end side, the following embodiment is a method for transmitting channel data executed on the receiving end side. FIG8 is a flow chart of another data transmission method provided by an embodiment of the present disclosure, as shown in FIG8 , including the following steps:

[0216] Step 810: Receive first indication information sent by the sending end;

[0217] As described in the above embodiment, the first indication information is the first indication information sent by the transmitting end to the receiving end when the transmitting end determines to transmit compressed channel data to the transmitting end by directly mapping the compressed channel data to time-frequency resources. After receiving the first indication information, the receiving end can confirm that the current communication system's method for feeding back channel state information is to directly map the compressed channel data to time-frequency resources. The above-mentioned first indication information can be the value of a flag bit, for example, the value of the flag bit is set to 1.

[0218] Step 820: Map the compressed channel data output by the channel compression model directly to the time-frequency resources according to the first indication information, so as to send the data to the transmitting end.

[0219] Specifically, in this step, after the receiving end performs downlink channel measurement and obtains channel data, it is compressed through the channel compression model to obtain compressed channel data, wherein the transmitting end may send a channel state information reference signal (Channel State Information-Reference Signal, CSI-RS) in the downlink channel, and the receiving end obtains channel data that can reflect the downlink channel quality based on the above CSI-RS. Since the compressed channel data output by the above-mentioned pre-trained channel compression model is directly mapped to the time-frequency resources, the compressed channel data is not subjected to quantization processing, channel coding, scrambling and other operations, and is a non-quantized data. By using this technical solution, the transmission overhead can be reduced, and the processing flow at the receiving end and the transmitting end when the channel state information is fed back can also be simplified.

[0220] Furthermore, since the above-mentioned channel compression model is a pre-trained model, the pre-training process is usually implemented on the CU or DU at the transmitting end, or on a logical entity across CUs. Therefore, in the embodiment of the present disclosure, it is also necessary to receive the pre-trained channel compression model sent by the transmitting end in advance, and then the channel data can be compressed based on the pre-trained channel compression model and the compressed channel data can be output.

[0221] In some embodiments, the above-mentioned first indication message can also be used to instruct the receiving end to map the neighboring reference signal directly to the time-frequency resource. The above-mentioned neighboring reference signal is used as a pilot signal, and the channel can be parsed out through the pilot signal, and the compressed channel data can be further parsed out based on the channel. At this time, directly mapping the compressed channel data output by the channel compression model to the time-frequency resource can be specifically mapping the compressed channel data and the neighboring reference signal output by the channel compression model directly to the time-frequency resource according to the first indication information. Figure 9 is a flow chart of yet another channel data transmission method in an embodiment of the present disclosure. As shown in Figure 9, in addition to the above-mentioned steps 810 and 820, before executing step 810, the following steps can also be included:

[0222] Step 910: Establish a radio link control layer connection (RRC-CONNECTED) with the transmitting end. After the above connection is established, the receiving end accesses the communication network;

[0223] Step 920: Send a sounding reference signal (SRS) to the transmitter so that the transmitter calculates the channel signal-to-noise ratio (SNR) based on the SRS. Specifically, as described in the embodiment shown in FIG2 , the transmitter sends a first indication to the receiver when the channel SNR is greater than or equal to a preset threshold.

[0224] The time-frequency resources used by the receiving end when sending the compressed channel data and the adjacent reference signal can be pre-configured by the transmitting end, so that when multiple receiving ends are connected to the transmitting end, different time-frequency resources can still be used by different receiving ends. Specifically, as shown in Figure 10, it also includes:

[0225] Step 930: Receive first resource configuration information sent by the transmitting end, where the first resource configuration information is used to instruct the receiving end to send compressed channel data and time-frequency resources for sending adjacent reference signals;

[0226] At this time, in the above step 820, the compressed channel data output by the channel compression model is directly mapped to the time-frequency resources, which can be specifically mapped directly to the time-frequency resources based on the first resource configuration information.

[0227] As described in the above embodiments, the receiving end sends compressed channel data in a combined manner or compressed channel data in a non-combined manner. For example, when the number of compressed channel data output by the channel compression model is N, in a non-combination manner, 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 can be combined into a compressed channel data combination. For example, when combined in pairs, if N is an even number, the number of compressed channel data combinations is N / 2, and if N is an odd number, the number of compressed channel data combinations is N / 2+1. Therefore, when combined in pairs, the number of compressed channel data groups is the number of compressed channel data output 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 embodiment of the present disclosure adopts a combination manner to combine several compressed channel data into a compressed channel data combination, which can save the required time-frequency resources. For example, compared with the above-mentioned pairwise combination method, which originally required one compressed channel data to be transmitted on each resource element RE (Resource Element, RE), the embodiment of the present disclosure can realize the transmission of one compressed channel data combination on each RE, that is, two compressed channel data. Similarly, after determining the number of adjacent reference signals to be transmitted, the required time-frequency resources can also be determined. The adjacent reference signals are adjacent to the time-frequency resources required for the compressed channel data, and are set within the coherent bandwidth of the compressed channel data. This ensures that they utilize the same channel, allowing the compressed channel data to be parsed based on the reference signals. In the disclosed embodiment, an adjacent reference signal refers to one in which, when mapped on the resource grid with the number of compressed channels, the distance between the REs containing the adjacent reference signals is less than a predetermined threshold.

[0228] In the embodiment of the present disclosure, if the compressed channel data is sent in a combined manner, when the at least two compressed channel data are combined into one compressed channel data group, the receiving end further includes the following steps:

[0229] performing data combination processing on the compressed channel data output by the channel compression model to obtain at least one compressed channel data combination;

[0230] Furthermore, in the above embodiment, directly mapping the compressed channel data output by the channel compression model to the time-frequency resources may specifically be: directly mapping at least one compressed channel data combination to the time-frequency resources.

[0231] In the embodiment of the present disclosure, for the channel compression model, the range of its output value can generally be controlled by setting a suitable activation function at the end of the model. For example, the activation function can be set to a tan function, and the compressed channel data output at this time can be within the value range of [-1, 1]. If a suitable activation function is not set in the activation function, so that the compressed channel data output at this time is not within the above value range, it is necessary to normalize the compressed channel data before directly mapping it to the time-frequency resource. The normalization processing method is generally determined by the sending end. After determining the normalization processing method, the sending end will send it to the receiving end. Therefore, the receiving end in this step will also perform the following steps:

[0232] receiving a normalization processing method sent by a transmitting end, and then performing normalization processing on the compressed channel data according to the normalization processing method to obtain normalized compressed channel data;

[0233] Then, in the above embodiment, directly mapping the compressed channel data output by the channel compression model to the time-frequency resources may specifically be: directly mapping the normalized compressed channel data to the time-frequency resources.

[0234] During the normalization process of the compressed channel data, a normalization element is used. The transmitter also needs to use the normalization element to restore the compressed channel data after normalization to obtain the compressed channel data before normalization, i.e., the compressed channel data output from the channel compression model. In this embodiment, the transmitter also configures time-frequency resources for transmitting the normalization element and sends it to the receiver. Therefore, the following steps are also performed on the receiver:

[0235] receiving second resource configuration information sent by a receiving end, where the second resource configuration information is used to instruct the receiving end to send a time-frequency resource for a normalized element;

[0236] According to the second resource configuration information, the normalization elements used in the normalization process are mapped to the time-frequency resources to be sent to the transmitting end.

[0237] In the embodiment of the present disclosure, the compressed channel data can be combined and normalized in pairs, which can be specifically, for example, the channel data is compressed by the compression model, and the output compressed channel data is [o1(t), o2(t), L, o N (t)], where o i (t) is a real number. Combining the compressed channel data in pairs, the compressed channel data combination is [(o1(t)+o2(t)j), (o3(t)+o4(t)j), L]. When N is an even number, the last compressed channel data combination is (o N-1 (t)+o N (t)j), when N is an odd number, the last compressed channel data combination is (o N (t)). If normalization is required, the compressed channel data combinations (o1(t)+o2(t)j), (o3(t)+o4(t)j), L obtained by pairwise combination are normalized to obtain the normalized compressed channel data combination Norm(o1(t)+o2(t)j), Norm(o3(t)+o4(t)j), L. The normalized compressed channel data combination and the adjacent reference signal can be reported based on the time-frequency resources configured by the transmitter. Since the adjacent reference signal is set within the coherent bandwidth of the compressed channel data, this ensures that the channel used is the same. At this time, if the adjacent reference signal is parsed and its channel is H(t), the compressed channel data combination transmitted on the same channel is [H(Norm(o1(t)+o2(t)j)), H(Norm(o3(t)+o4(t)j)), L].

[0238] In the embodiment of the present disclosure, normalization processing is performed to normalize the compressed channel data to a reasonable value range. Specifically, the normalization processing method may be a maximum normalization method:

[0239] The compressed channel data [o1(t),o2(t),L,o N (t)], calculate (o i (t)+o i+1 (t)) (i=1,3,5L) the maximum modulus value in Indicates rounding up, dividing the compressed channel data combination after pairwise combination by O(t) to obtain the normalized compressed channel data combination And the maximum modulus value O(t) listed can be regarded as a normalization element, which can be sent to the sender by the time-frequency resources specified by the sender, so that the sender can use the normalization element to restore and obtain the compressed channel data group before normalization.

[0240] FIG11 is a schematic diagram of resource mapping in an embodiment of the present disclosure. As shown in FIG11 , a schematic diagram of resource mapping of a compressed channel data combination and a neighboring reference signal in an embodiment of the present disclosure is given. Assuming that the neighboring reference signal sent by the receiving end at time t is x(t), the neighboring signal received by the transmitting end is X(t), and the channel H(t) can be calculated by x(t) and X(t). Due to the coherence of the channel within a sub-band, it can be considered that the channel at the black position in FIG10 is the same as the channel of the neighboring reference signal at its nearest oblique position, so the above normalized compressed channel data combination can be used as shown in FIG10. Insert the black resource blocks and the adjacent reference signals into the shaded resource blocks. If multiple adjacent reference signals exist, use the average channel of the adjacent reference signals or any one of their corresponding channels. Assuming the channel is H(t), and the signal S(t) is received on a time-frequency resource configured for adjacent feedback, the transmitted signal can be estimated as S(t) / H(t).

[0241] Figure 12 is a flowchart of a resource mapping in an embodiment of the present disclosure. As shown in Figure 12, for the above-mentioned compressed channel data and adjacent reference signals, a direct resource mapping scheme can be adopted to map them to the time-frequency resources specified by the transmitter, and then perform physical antenna mapping before sending them to the transmitter. This processing scheme is different from the scheme shown in Figure 7. It is necessary to first quantize the compressed channel data, and then perform a series of operations such as cyclic redundancy check (CRC), channel coding, rate matching, hybrid automatic repeat request (HARQ) coding, scrambling, modulation, layer mapping, discrete Fourier transform (DFT) uplink coding, multi-antenna precoding, etc. before performing resource mapping.

[0242] In the above-mentioned embodiment of the present disclosure, a technical solution is mainly implemented after the channel signal-to-noise ratio is obtained 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 transmitting end, thereby avoiding operations such as quantization processing. During the communication process between the receiving end and the transmitting end, the transmitting end can re-acquire 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-mentioned technical solution is still implemented. If the channel signal-to-noise ratio is less than the preset threshold, second indication information is sent to the receiving end. Therefore, the following steps are also implemented on the receiving end:

[0243] receiving second sending instruction information sent by the sending end;

[0244] The compressed channel data output by the channel compression model is quantized according to the second indication information, and the compressed channel data obtained by the quantization is mapped to time-frequency resources for transmission to the transmitting end. In this case, when the receiving end transmits the compressed channel data, the specific steps performed can refer to those shown in FIG. 7 above.

[0245] FIG13 is a flowchart of a specific implementation scheme provided by an embodiment of the present disclosure, as shown in FIG13 , including the following steps:

[0246] Step 1301, deploy the AI ​​model training system of the wireless access network on the transmitting end, which can be specifically deployed on the CU and / or DU of the transmitting end, or deployed on a logical entity across CUs. During pre-training, first collect the channel data of the downlink channel in advance, and train the channel compression model (denoted as E) and the channel decompression model (denoted as D) based on the AI ​​autoencoder (autoencoder) offline. After the pre-training is completed, the pre-trained channel compression model and the normalization processing method are synchronized to the receiving end, where the normalization processing method can be a maximization normalization method. In addition, the channel decompression model, the maximization normalization method and the number 24 of compressed channel data output by the channel compression model are synchronized to the transmitting end, where the number of compressed channel data output by the channel compression model is the number of compressed channel data input by the channel decompression model. For example, the transmitting end pre-sets the channel signal-to-noise ratio threshold to δ=20dB according to the accuracy requirement of the user channel feedback;

[0247] Step 1302: The receiving end accesses the network, enters the RRC-CONNECTED state, and sends SRS according to pre-configuration;

[0248] Step 1303: The transmitting end sends the CSI-RS according to the pre-configured configuration, calculates the uplink channel signal-to-noise ratio (SINR) based on the received SRS, and compares it with a preset 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, a flag bit 1 is sent to the receiving end. The flag bit 1 serves as the first indication information.

[0249] Furthermore, the transmitting end configures time-frequency resources based on the number of compressed channel data 24 input by the channel decompression model, divided by 2 and rounded up to 12, and the number of adjacent reference signals 3 to be configured. The time-frequency resources are used by the receiving end to feedback the compressed channel data and adjacent reference signals output by the channel compression model; the transmitting end no longer allocates the above-allocated time-frequency resources to other users / antennas. In addition, the transmitting end also needs to configure feedback resources for the receiving end to feedback the normalization element. When the maximum normalization method is adopted, the above-mentioned normalization element is in the binary form of the maximum modulus. For the feedback method of the binary form of the maximum modulus, the feedback method shown in Figure 13 can be adopted. It needs to be subjected to a series of operations such as modulation, layer mapping, discrete Fourier transform (DFT) uplink coding, multi-antenna precoding, resource mapping and physical antenna mapping before being sent to the transmitting end. The transmitting end also sends the configured feedback resources to the receiving end, and then executes step 1304.

[0250] If the channel signal-to-noise ratio is less than the preset threshold δ, the transmitting end sends a flag bit 0 to the receiving end. The flag bit 0 serves as second indication information, instructing the receiving end to feed back compressed channel data according to the embodiment shown in FIG6 . In this case, feedback resources may also be configured based on the amount of compressed channel data input by the decompression model. The transmitting end sends information about the feedback resource configuration to the receiving end, and then executes step 107.

[0251] Step 1304: After receiving the flag 1, the receiving end inputs the channel data into the channel compression model at time t to complete the compression of the channel data and outputs the compressed channel data [o1(t), o2(t), L, o 24 (t)], where o i (t) is a real number. The compressed channel data output is combined in pairs to obtain the compressed channel data combination Y(t) = [(o1(t) + o2(t)j), (o3(t) + o4(t)j), L(o 23 (t)+o 24 (t)j)]. By calculating (o i (t)+o i+1 (t) The maximum modulus value in j)(i=1,3,5,L 23) Divide Y(t) by O(t) to get the normalized compressed channel data combination Then, based on the time-frequency resources configured by the transmitter, the normalized compressed channel data combination and the adjacent reference signal are reported, and the binary form of the maximum modulus value O(t) is fed back using the feedback resources configured by the transmitter.

[0252] Step 1305: The transmitter decodes the channel H(t) based on the received adjacent reference signal, and calculates the channel H(t) based on H(t), the binary form of the received maximum modulus O(t) and Decompressed channel data [o1′(t), o2′(t), L, o 24 ′(t)], and then input the compressed channel data into the channel decompression model to decompress the required channel data;

[0253] Step 1306: The transmitting end 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 relationship between the channel signal-to-noise ratio and the preset threshold changes, the transmitting end will adjust the flag sent to the receiving end, as well as the feedback resources configured for the receiving end, and will re-feed back the configured resources to the receiving end. The compressed channel data generated on the receiving end will be fed back to the transmitting end based on the time-frequency resources adjusted by the transmitting end. When the channel signal-to-noise ratio is greater than or equal to the preset threshold, a flag of 1 will be sent to the receiving end. The specific processing flow can still refer to the above steps 1303-1306; when the channel signal-to-noise ratio is less than the preset threshold, a flag of 0 will be sent to the receiving end. The subsequent processing flow can refer to step 107.

[0254] Step 1307: The receiving end receives the identification bit 0, completes the channel data compression through the channel compression model, outputs the compressed channel data, and reports the compressed channel data to the sending end in the traditional manner described in Figure 7; after receiving the compressed channel data sent by the receiving end, the sending end inputs the compressed channel data into the channel decompression model to complete decompression, obtains the channel data, and then executes step 1306.

[0255] Corresponding to the above method embodiments, the embodiments of the present disclosure also provide corresponding devices, which can implement the methods listed in the above embodiments and achieve the same technical effects.

[0256] The present disclosure also provides a channel data transmission device, which can be used in a transmitting end. FIG14 is a schematic structural diagram of a channel data transmission device provided by an embodiment of the present disclosure. As shown in FIG14 , the device includes:

[0257] The first indication sending module 1400 is used to send first indication information to the receiving end, where the first indication information is used to instruct the receiving end to directly map the compressed channel data output by the channel compression model to the time-frequency resources.

[0258] In some embodiments, before sending the first indication information to the receiving end, the method further includes:

[0259] A first channel quality acquisition module, configured to acquire channel evaluation quality before sending first indication information to a receiving end;

[0260] The first indication sending module is specifically configured to send first indication information to the receiving end when the channel evaluation quality meets a first preset threshold.

[0261] In some embodiments, the channel assessment quality includes any one of a channel signal-to-noise ratio, a bit error rate, and a channel quality indication. If the channel assessment quality includes a channel signal-to-noise ratio, the first channel quality acquisition module is specifically used to receive a sounding reference signal sent by a receiving end, and calculate the channel signal-to-noise ratio based on the sounding reference signal.

[0262] In some embodiments, further comprising:

[0263] A first acquisition module is used to acquire a pre-trained channel compression model, a pre-trained channel decompression model and the number of compressed channel data input by the channel decompression model;

[0264] The first sending module is used to send the pre-trained channel compression model to the receiving end.

[0265] In some embodiments, further comprising:

[0266] A normalization processing method acquisition module is used to obtain a normalization processing method used by the receiving end to normalize the compressed channel data output by the channel compression model;

[0267] The first sending module is further configured to send the normalized processing mode to the receiving end.

[0268] In some embodiments, further comprising:

[0269] The configuration sending module is used to send first resource configuration information to the receiving end, where the first resource configuration information is used to instruct the receiving end to send the compressed channel data and the time-frequency resources required to send the adjacent reference signal.

[0270] In some embodiments, the adjacent reference signal is disposed within a coherence bandwidth of the compressed channel data.

[0271] In some embodiments, further comprising:

[0272] a number acquisition module, configured to acquire the number of compressed channel data input by the channel decompression model and the number of adjacent reference signals before sending the first resource configuration information to the receiving end;

[0273] The resource determination module is used to determine the time-frequency resources required by the receiving end to send the compressed channel data and the adjacent reference signals based on the number of compressed channel data input on the channel decompression model and the number of the adjacent reference signals.

[0274] In some embodiments, the receiving end sends compressed channel data in a combined manner or compressed channel data in a non-combined manner.

[0275] In some embodiments, it further includes:

[0276] Second resource configuration information is sent to the receiving end, where the second resource configuration information is used to instruct the receiving end to send the time-frequency resource of the normalized element.

[0277] In some embodiments, it further includes:

[0278] A channel data acquisition module, configured to acquire compressed channel data output by the channel compression model and sent by a receiving end;

[0279] The decompression module is configured to input the compressed channel data into the channel decompression model so as to decompress the channel data using the channel decompression model.

[0280] In some embodiments, the channel data acquisition module includes:

[0281] a channel parsing unit, configured to obtain an adjacent reference signal directly mapped onto the time-frequency resource, and parse out a channel based on the adjacent reference signal;

[0282] A data acquisition unit is used to acquire compressed channel data output by the channel compression model and sent by a receiving end according to the parsed channel.

[0283] In some embodiments, it further includes:

[0284] a normalization element acquisition unit, configured to acquire a normalization element used by a receiving end in a process of normalizing the compressed channel data;

[0285] A data acquisition unit is used to acquire compressed channel data output by the channel compression model and sent by a receiving end according to the parsed channel and the normalization element.

[0286] In some embodiments, the normalization processing method is a maximization normalization method;

[0287] If the receiving end sends compressed channel data in a combination, the normalization element is the maximum modulus value in the compressed channel data combination.

[0288] In some embodiments, it further includes:

[0289] A second signal-to-noise ratio acquisition module, configured to reacquire channel assessment quality;

[0290] A second indication information sending module is used to send second indication information to the receiving end when the channel evaluation quality meets the second preset threshold value. The second indication information is used to instruct the receiving end to quantize 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.

[0291] The present disclosure also provides a channel data transmission device, which can be applied to a receiving end. FIG15 is a schematic structural diagram of another channel data transmission device provided by the present disclosure. As shown in FIG15 , the device includes:

[0292] A first indication receiving module 1501 is configured to receive first indication information sent by a sending end;

[0293] The first data sending module 1502 is configured to directly map the compressed channel data output by the channel compression model onto time-frequency resources according to the first indication information, so as to send the data to the sending end.

[0294] In some embodiments, it further includes:

[0295] a connection establishing module, configured to establish a radio link control layer connection with the sending end before receiving the first indication information sent by the sending end;

[0296] The sounding module is configured to send a sounding reference signal to the transmitting end, so that the transmitting end calculates a channel signal-to-noise ratio according to the sounding reference signal.

[0297] In some embodiments, it further includes:

[0298] A model receiving module, configured to receive a pre-trained channel compression model sent by the sending end before receiving the first indication information sent by the sending end;

[0299] The compression module is used to compress the channel data based on the pre-trained channel compression model and output the compressed channel data.

[0300] In some embodiments, it further includes:

[0301] a configuration information receiving module, configured to receive first resource configuration information sent by a transmitting end, where the first resource configuration information is used to instruct the receiving end to send the compressed channel data and the time-frequency resources for sending the adjacent reference signal;

[0302] The first data sending module is specifically configured to directly map the compressed channel data and the adjacent reference signal to time-frequency resources based on the first resource configuration information.

[0303] In some embodiments, the adjacent reference signal is disposed within a coherence bandwidth of the compressed channel data.

[0304] 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 comprises:

[0305] a combining module, configured to perform data combining processing on the compressed channel data output by the channel compression model to obtain at least one compressed channel data combination;

[0306] The first data sending module is specifically configured to directly map the at least one compressed channel data combination onto the time-frequency resources.

[0307] In some embodiments, it further includes:

[0308] A normalization processing mode receiving module is used to receive the normalization processing mode sent by the sending end;

[0309] 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;

[0310] The first data sending module is specifically configured to directly map the normalized compressed channel data onto time-frequency resources.

[0311] In some embodiments, it further includes:

[0312] A second configuration information receiving module is configured to receive second resource configuration information sent by a receiving end, where the second resource configuration information is used to instruct the receiving end to send a time-frequency resource for a normalized element;

[0313] The normalization element sending module is used to map the normalization element used in the normalization processing process to the time-frequency resource according to the second resource configuration information, so as to send it to the sending end.

[0314] In some embodiments, the normalization method is a maximization normalization method;

[0315] If the receiving end sends the compressed channel data in a combined manner, the normalization element is the maximum modulus value in the compressed channel data combination.

[0316] In some embodiments, it further includes:

[0317] A second indication information receiving module, configured to receive the second sending indication information sent by the sending end;

[0318] The second data sending module is used to quantize 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 to send it to the sending end.

[0319] The channel data transmission method provided by the embodiment of the present disclosure corresponds to the method embodiment shown in Figures 1-13 above, and can execute the method and achieve corresponding technical effects. The embodiment of the present disclosure will not be described in detail. The specific method and the technical effects achieved can refer to the above embodiment.

[0320] 16, which shows a schematic diagram of the structure 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 receiving terminals such as mobile phones, laptop computers, digital broadcast receivers, personal digital assistants (PDAs), tablet computers (PADs), portable multimedia players (PMPs), vehicle-mounted receiving terminals (e.g., vehicle-mounted navigation receiving terminals), and fixed receiving terminals such as digital TVs and desktop computers. The electronic device shown is merely an example and should not limit the functionality and scope of the embodiments of the present disclosure.

[0321] As shown in the figure, the electronic device 600 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can 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. Various programs and data required for the operation of the electronic device 600 are also stored in the RAM 603. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0322] Typically, 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 by wire to exchange data. Although the electronic device 600 is shown as having various devices, it should be understood that it is not required to implement or have all of the devices shown. More or fewer devices may be implemented or have alternatively.

[0323] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program includes program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 609, or installed from the storage device 608, or installed from the ROM 602. When the computer program is executed by the processing device 601, the above-mentioned functions defined in the channel data transmission method of the embodiment of the present disclosure are performed.

[0324] It should be noted that the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. The computer-readable storage medium may be, for example, (but not limited to) an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with 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 disc 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 may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, device, or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that 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 may be transmitted using any suitable medium, including but not limited to wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0325] In some embodiments, the client and the server can communicate using any currently known or future developed network protocol, such as the HyperText Transfer Protocol (HTTP), and can be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0326] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0327] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device:

[0328] Sending first indication information to the receiving end, wherein the first indication information is used to instruct the receiving end to directly map the compressed channel data output by the channel compression model to the time-frequency resources. Alternatively, the electronic device: receives the first indication information sent by the transmitting end;

[0329] The compressed channel data output by the channel compression model is directly mapped to time-frequency resources according to the first indication information, so as to be sent to the transmitting end.

[0330] An embodiment of the present disclosure also provides a computer program product, including computer instructions, which, when executed by a processor, implement the steps in the channel data transmission method as described in any one of the above items and can achieve the same technical effect. To avoid repetition, they will not be repeated here.

[0331] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, or a combination thereof, including, but not limited to, object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server. In cases involving a remote computer, the remote computer may 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 may be connected to an external computer (e.g., through the Internet using an Internet Service Provider).

[0332] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0333] The units involved in the embodiments described in this disclosure may be implemented in software or hardware, wherein the name of a unit does not necessarily limit the unit itself.

[0334] The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, and without limitation, exemplary types of hardware logic components that may be used include: Field Programmable Gate Array (FPGA), Application Specific Integrated Circuit (ASIC), Application Specific Standard Parts (ASSP), System on Chip (SOC), Complex Programmable Logic Device (CPLD), and the like.

[0335] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, 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 foregoing.

[0336] According to one or more embodiments of the present disclosure, the present disclosure provides a computer-readable storage medium, wherein the storage medium stores a computer program, and the computer program is used to execute any channel data transmission method provided by the present disclosure.

[0337] The above description is merely a preferred embodiment of the present disclosure and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by the specific combination of the above-mentioned technical features, but also includes other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the above-mentioned disclosed concepts. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features with similar functions disclosed in this disclosure.

[0338] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details have been included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0339] Although the subject matter has been described in language specific to structural features and / or methodological logical 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. Rather, the specific features and acts described above are merely example forms of implementing the claims.

Claims

1. A method for transmitting channel data, the method comprising: Receiving first indication information sent by a sending end; The compressed channel data output by the channel compression model is directly mapped to the time-frequency resources according to the first indication information, so as to be sent to the transmitting end.

2. The method according to claim 1, wherein: Before receiving the first indication information sent by the transmitting end, the method further includes: receiving a pre-trained channel compression model sent by a transmitter; The channel data is compressed based on the pre-trained channel compression model, and the compressed channel data is output.

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

4. The method according to claim 3, further comprising: Receive first resource configuration information sent by a transmitting end, where the first resource configuration information is used to indicate a time-frequency resource for the receiving end to send the compressed channel data and send an adjacent reference signal, where the adjacent reference signal is set within a coherent bandwidth of the compressed channel data; The step of directly mapping the compressed channel data and the adjacent reference signal output by the channel compression model to the time-frequency resources comprises: The compressed channel data and the adjacent reference signal are directly mapped onto time-frequency resources based on the first resource configuration information.

5. The method according to claim 1, wherein: 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 comprises: 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 step of directly mapping the compressed channel data output by the channel compression model to the time-frequency resources comprises: The at least one compressed channel data combination is directly mapped onto time-frequency resources.

6. The method according to claim 1, further comprising: The normalization processing method sent by the receiving and sending end; Performing normalization processing on the compressed channel data according to the normalization processing method to obtain normalized compressed channel data; The step of directly mapping the compressed channel data output by the channel compression model to the time-frequency resources comprises: The normalized compressed channel data is directly mapped onto the time-frequency resources.

7. The method according to claim 6, further comprising: Receiving second resource configuration information sent by a receiving end, where the second resource configuration information is used to indicate a time-frequency resource for the receiving end to send a normalized element; According to the second resource configuration information, the normalization elements used in the normalization process are mapped to time-frequency resources to send to the transmitting end.

8. The method according to claim 1, further comprising: Receiving second sending indication information sent by the sending end; The compressed channel data output by the channel compression model is quantized according to the second indication information, and the compressed channel data obtained by the quantization is mapped to time-frequency resources to be sent to the transmitting end.

9. A method for transmitting channel data, the method comprising: First indication information is sent to a receiving end, where the first indication information is used to instruct the receiving end to directly map compressed channel data output by a channel compression model to time-frequency resources.

10. The method according to claim 9, wherein: The first indication message is also used to instruct the receiving end to directly map the adjacent reference signal to the time-frequency resource.

11. The method according to claim 9, wherein: Before sending the first indication information to the receiving end, the method further includes: Obtain channel assessment quality; The sending the first indication information to the receiving end includes: When the channel evaluation quality meets a first preset threshold, first indication information is sent to the receiving end.

12. The method according to claim 9, further comprising: Acquire a pre-trained channel compression model, a pre-trained channel decompression model, and the number of compressed channel data input by the channel decompression model; The pre-trained channel compression model is sent to the receiving end.

13. The method according to claim 9, further comprising: Obtaining a normalization processing method for the receiving end to normalize the compressed channel data output by the channel compression model; The normalized processing mode is sent to the receiving end.

14. The method according to any one of claims 10 to 13, further comprising: First resource configuration information is sent to a receiving end, where the first resource configuration information is used to indicate the time-frequency resources required for the receiving end to send the compressed channel data and send an adjacent reference signal, where the adjacent reference signal is set within a coherent bandwidth of the compressed channel data.

15. The method according to claim 14, wherein: Before sending the first resource configuration information to the receiving end, the method further includes: Acquire the number of compressed channel data input by the channel decompression model and the number of adjacent reference signals; Based on the number of compressed channel data input into the channel decompression model and the number of the adjacent reference signals, the time-frequency resources required by the receiving end to send the compressed channel data and the adjacent reference signals are determined.

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

17. The method according to claim 14, further comprising: Second resource configuration information is sent to a receiving end, where the second resource configuration information is used to instruct the receiving end to send a time-frequency resource for a normalized element.

18. The method according to claim 17, further comprising: Acquire compressed channel data output by the channel compression model and sent by a receiving end; Inputting the compressed channel data into the channel decompression model so as to decompress the channel data by the channel decompression model; The step of obtaining compressed channel data output by the channel compression model and sent by the receiving end includes: Acquire an adjacent reference signal directly mapped onto the time-frequency resource, and parse out a channel according to the adjacent reference signal; The compressed channel data output by the channel compression model and sent by the receiving end is obtained according to the parsed channel.

19. The method according to claim 18, further comprising: Acquire a normalization element used by the receiving end in a process of normalizing the compressed channel data; The step of obtaining compressed channel data output by the channel compression model and sent by a receiving end according to the parsed channel includes: The compressed channel data output by the channel compression model and sent by the receiving end is obtained according to the parsed channel and the normalized element.

20. The method according to claim 9, further comprising: Re-acquire channel assessment quality; When the channel evaluation quality meets a second preset threshold, second indication information is sent to the receiving end, wherein the second indication information is used to instruct the receiving end to quantize 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.

21. A channel data transmission device, applied to a receiving end, the device comprising: A first indication receiving module, used to receive first indication information sent by a sending end; The first data sending module is used to directly map the compressed channel data output by the channel compression model to the time-frequency resources according to the first indication information, so as to send the compressed channel data to the sending end.

22. A device for transmitting channel data, the device comprising: The first indication sending module is used to send first indication information to the receiving end, where the first indication information is used to instruct the receiving end to directly map the compressed channel data output by the channel compression model to the time-frequency resources.

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

24. A computer-readable storage medium storing a computer program, wherein the computer program is used to execute the channel data transmission method according to any one of claims 1 to 8 or the channel data transmission method according to any one of claims 9 to 20.

25. A computer program product, comprising computer instructions, which, when executed by a processor, implement the channel data transmission method according to any one of claims 1 to 8 or the channel data transmission method according to any one of claims 9 to 20.

Images