First communication device, second communication device and data transmission method

Abstract

The embodiment of the invention discloses first communication equipment, second communication equipment and a data transmission method, and the first communication equipment comprises a first transceiver; and a first processor coupled to the first transceiver; the first processor is configured to perform semantic coding on first data to obtain a first coding sequence; the first coding sequence comprises at least one piece of coding data; determining at least one piece of target coded data from the first coded sequence; transmitting, via the first transceiver, the at least one target encoded data to a second communication device; transmitting location information to the second communication device via the first transceiver; the position information is used for indicating the position of the at least one target coded data in the first coded sequence.

Description

Technical Field

[0001] The present application relates to but is not limited to the field of communication technology, and in particular to a first communication device, a second communication device and a data transmission method. Background Art

[0002] As a strong competitor to the 6G standard, semantic communication is gaining increasing attention. This communication method based on understanding the content of information aims to improve the efficiency and reliability of information transmission. Unlike the communication method that focuses on the transmission of bit streams, semantic communication focuses on the semantic level of information and its transmission and recovery. In related technologies, when transmitting data, the transmitted data is not distinguished, and all the transmitted data is transmitted to the receiving end, resulting in a waste of channel resources. Summary of the invention

[0003] The embodiments of the present application at least provide a first communication device, a second communication device and a data transmission method.

[0004] The technical solution of the embodiment of the present application is implemented as follows:

[0005] An embodiment of the present application provides a first communication device, including: a first transceiver; and

[0006] A first processor is coupled to the first transceiver; the first processor is configured to:

[0007] Performing semantic encoding on the first data to obtain a first encoding sequence; the first encoding sequence includes at least one encoding data;

[0008] Determining at least one target coded data from a first coded sequence;

[0009] transmitting at least one target encoded data to a second communication device via the first transceiver;

[0010] The position information is sent to the second communication device via the first transceiver; the position information is used to indicate the position of at least one target coded data in the first coding sequence.

[0011] In some embodiments, the first processor is configured to:

[0012] The first mutual information is sent to the second communication device via the first transceiver; the first mutual information is the mutual information that the second communication device is expected to receive based on the first coding sequence.

[0013] In some embodiments, the first processor is configured to:

[0014] At least one target coded data is determined from the first coded sequence based on the first mutual information and second mutual information of each coded data in the first coded sequence, wherein the second mutual information is the predicted mutual information of the coded data received by the second communication device.

[0015] In some embodiments, the first processor is configured to:

[0016] Determine fourth mutual information based on the first mutual information and the third mutual information, where the third mutual information is the mutual information that the second communication device has received based on the first coding sequence, and the fourth mutual information is the mutual information expected to be sent;

[0017] At least one target coded data is determined from the first coded sequence based on the fourth mutual information and the second mutual information of each coded data in the first coded sequence.

[0018] In some embodiments, the first processor is configured to:

[0019] Determining a first information entropy of the coded data, the first information entropy being a predicted information entropy of the coded data received by the second communication device;

[0020] Based on the first information entropy of the encoded data, second mutual information of the encoded data is determined.

[0021] In some embodiments, the first processor is configured to:

[0022] When it is determined whether the encoded data is to be transmitted for the Nth time, predicting the second information entropy of the encoded data when it is transmitted for the Nth time;

[0023] Based on the difference between the second information entropy and the third information entropy, the first information entropy of the coded data is determined; the third information entropy is the predicted second information entropy of the coded data in the N-1th transmission case.

[0024] In some embodiments, the first processor is configured to:

[0025] Based on the first probability distribution of the encoded data and the probability distribution of channel noise when the encoded data is transmitted for the Nth time, the second information entropy of the encoded data when it is transmitted for the Nth time is determined, and the first probability distribution is the probability distribution of the encoded data when no information is lost.

[0026] In some embodiments, the first processor is configured to:

[0027] Determine, based on the probability distribution of the channel noise, a fourth information entropy corresponding to the coded data, where the fourth information entropy is the information entropy of the channel noise when the coded data is transmitted for the Nth time;

[0028] Based on the first information entropy and the fourth information entropy, second mutual information of the encoded data is determined.

[0029] In some embodiments, the first processor is configured to:

[0030] For each coded data in the first coding sequence, determine fifth mutual information of the coded data, where the fifth mutual information is the mutual information of the coded data sent by the first communication device;

[0031] The first mutual information is determined based on the sum of the fifth mutual information of each encoded data in the first encoding sequence and a first threshold.

[0032] In some embodiments, the first processor is configured to:

[0033] Feedback information sent by the second communication device is received via the first transceiver, where the feedback information is used to indicate whether the first coding sequence is received successfully.

[0034] In some embodiments, the first processor is configured to:

[0035] In response to feedback information indicating that the first coding sequence was not successfully received, determining at least one target coding data from the first coding sequence;

[0036] Wherein, when the feedback information indicates that the first coding sequence is not received successfully, the feedback information further includes: third mutual information, where the third mutual information is mutual information that the second communication device has received based on the first coding sequence.

[0037] An embodiment of the present application provides a second communication device, including: a second transceiver; and

[0038] a second processor coupled to the second transceiver; the second processor being configured to:

[0039] Receiving, via a second transceiver, at least one target coded data and position information in a first coded sequence sent by a first communication device; the position information is used to indicate a position of the at least one target coded data in the first coded sequence;

[0040] Based on the position information, at least one target coded data is integrated to obtain a second coded sequence, and the second coded sequence is used to restore the first data based on semantic decoding.

[0041] In some embodiments, the second processor is configured to:

[0042] Receiving, via the second transceiver, first mutual information sent by the first communication device, the first mutual information being mutual information expected to be received by the second communication device based on the first coding sequence;

[0043] It is determined whether the first coding sequence is successfully received based on the first mutual information.

[0044] In some embodiments, the second processor is configured to:

[0045] For each target coded data in the received target coded data, based on the fifth information entropy of the target coded data and the fourth information entropy of the channel noise, determine the sixth mutual information of the target coded data, the fifth information entropy being the information entropy of the target coded data received by the second communication device, and the sixth mutual information being the mutual information of the target coded data received by the second communication device;

[0046] Determine third mutual information based on sixth mutual information of each target coded data in the received target coded data, where the third mutual information is mutual information of the second communication device based on the received target coded data;

[0047] The third mutual information is compared with the first mutual information to determine whether the first coding sequence is received successfully.

[0048] In some embodiments, the second processor is configured to:

[0049] Based on the second probability distribution of the target coded data, the probability distribution of channel noise and the number of transmissions M of the target coded data, the fifth information entropy of the target coded data is determined, and the second probability distribution is the probability distribution of the target coded data under information loss.

[0050] In some embodiments, the second processor is configured to:

[0051] Feedback information is sent to the first communication device via the second transceiver, where the feedback information is used to indicate whether the first coding sequence is received successfully.

[0052] In some embodiments, the second processor is configured to:

[0053] In the case where the feedback information indicates that the first coding sequence is not received successfully, the feedback information further includes: third mutual information, where the third mutual information is mutual information that the second communication device has received based on the first coding sequence.

[0054] The present application provides a data transmission method, including:

[0055] Performing semantic encoding on the first data to obtain a first encoding sequence; the first encoding sequence includes at least one encoding data;

[0056] Determining at least one target coded data from a first coded sequence;

[0057] transmitting at least one target encoded data to a second communication device via the first transceiver;

[0058] The position information is sent to the second communication device via the first transceiver; the position information is used to indicate the position of at least one target coded data in the first coding sequence.

[0059] In an embodiment of the present application, a first communication device includes a first transceiver and a first processor, the first processor is coupled to the first transceiver, wherein the first processor is configured to: semantically encode the first data to obtain a first coding sequence, and determine at least one target coding data from the first coding sequence, and send the at least one target coding data and position information to the second communication device via the first transceiver, respectively, wherein the position information is used to indicate the position of the target coding data in the first coding sequence. In this way, the first communication device selects appropriate target coding data from the first coding sequence and sends it to the second communication device, which, on the one hand, reduces the transmission of redundant information and optimizes the utilization of channel resources, and on the other hand, can improve the reliability of the second communication device receiving information.

[0060] It should be understood that the above general description and the following detailed description are merely exemplary and explanatory, and are not intended to limit the technical solutions of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present application and are used together with the specification to illustrate the technical solution of the present application.

[0062] Figure 1 A schematic diagram of the composition structure of a first communication device provided in an embodiment of the present application;

[0063] Figure 2 A schematic diagram of an implementation process of a data transmission method provided in an embodiment of the present application Figure 1 ;

[0064] Figure 3 A schematic diagram of the structure of a second communication device provided in an embodiment of the present application;

[0065] Figure 4 A schematic diagram of an implementation process of a data transmission method provided in an embodiment of the present application Figure 2 ;

[0066] Figure 5 A schematic diagram of a transmitting end and a receiving end model provided in an embodiment of the present application;

[0067] Figure 6 A schematic diagram of a sending end step flow diagram provided in an embodiment of the present application;

[0068] Figure 7 A schematic diagram of a receiving end step flow chart provided in an embodiment of the present application;

[0069] Figure 8 A schematic diagram of a base station and user side process provided in an embodiment of the present application;

[0070] Fig. 9 A schematic diagram of the comparison results of the image transmission success rate between the present application scheme and the related technical scheme provided in an embodiment of the present application.

[0071] Fig.10 A schematic diagram of the throughput and SNR comparison results of the solution of the present application and the related technical solution provided in an embodiment of the present application. DETAILED DESCRIPTION

[0072] In order to make the purpose, technical solutions and advantages of the present application clearer, the technical solutions of the present application are further elaborated in detail below in conjunction with the drawings and embodiments. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.

[0073] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0074] It should be pointed out that the terms "first\second\third" involved in the embodiments of the present application are merely to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged in a specific order or sequence where permitted, so that the embodiments of the present application described here can be implemented in an order other than that illustrated or described here.

[0075] It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meaning as the general understanding of those skilled in the art in the field to which the embodiments of the present application belong. It should also be understood that terms such as those defined in general dictionaries should be understood to have meanings consistent with the meanings in the context of the prior art, and will not be interpreted with idealized or overly formal meanings unless specifically defined as here.

[0076] This embodiment of the application provides a first communication device, Figure 1 A schematic diagram of the composition structure of a first communication device provided in an embodiment of the present application is shown in FIG. Figure 1 As shown, the first communication device 10 includes a first transceiver 11 and a first processor 12 coupled to the first transceiver 11 .

[0077] A data transmission method provided in an embodiment of the present application is applied to a first communication device, such as Figure 2 As shown, the following steps S201 to S204 may be included:

[0078] Step S201: semantically encode the first data to obtain a first encoding sequence; the first encoding sequence includes at least one encoding data;

[0079] Here, the first communication device can be a base station, which is used to process data and interact with the second communication device; the first communication device includes a first processor and a first transceiver, wherein the first processor is used to process data, and the first transceiver is used to receive communication information from the second communication device (such as a mobile phone, computer, etc.); or send data to the second communication device.

[0080] The first data is data to be transmitted, and the semantic content carried by the first data is what the second communication device expects to receive.

[0081] Semantic coding is to extract semantic information from the first data and convert it into a format suitable for transmission, such as a digital signal or an analog signal.

[0082] In some embodiments, semantic encoding of the first data may include but is not limited to: parsing the semantic content in the text information and converting it into a format suitable for transmission; or, understanding and classifying the image information to obtain the corresponding semantic content, and converting it into a format suitable for transmission.

[0083] In some implementations, according to the task type corresponding to the first data, a suitable semantic encoding model is selected to encode the first data, wherein the semantic encoding model may be at least one of a variational autoencoder, a large model, and the like.

[0084] Step S202: determining at least one target coding data from the first coding sequence;

[0085] In some embodiments, the target coding data may be one or more coding data in the first coding sequence. For example, the first coding sequence is abcdefg, where b and d are the target coding data, or c is the target coding data.

[0086] In some embodiments, the method of determining at least one target coded data may include but is not limited to: randomly selecting at least one target coded data from the first coded sequence, selecting at least one target coded data according to the order in which each coded data is arranged in the first coded sequence, and selecting at least one target coded data from the first coded sequence according to the second mutual information of each coded data, wherein the second mutual information is the mutual information of the coded data received by the predicted second communication device. The second communication device may be a user side device.

[0087] In some implementations, at least one target coded data may be determined from the first coding sequence based on the first mutual information and the second mutual information, wherein the first mutual information is the mutual information expected to be received by the second communication device based on the first coding sequence.

[0088] In some implementations, at least one target coded data is coded data that meets a reception requirement of the second communication device.

[0089] Step S203: sending the at least one target coded data to a second communication device via the first transceiver;

[0090] In some embodiments, at least one target encoded data is transmitted to a second communication device via a first transceiver using a first channel, wherein the first channel is a data channel and the direction is from the first communication device to the second communication device.

[0091] In some implementations, the first channel may be established by a wireless connection method.

[0092] In some embodiments, after the second communication device receives at least one target coded data sent by the first communication device, the second communication device receives at least one target coded data and performs a round of coded data transmission. The second communication device may determine feedback information based on the received target coded data and send feedback information to the second communication device. The first communication device receives the feedback information sent by the second communication device. When the feedback information indicates that the first coded sequence is successfully received, the first communication device completes the task of sending the first coded sequence; when the feedback information indicates that the first coded sequence is not successfully received, the first communication device redetermines at least one target coded data from the first coded sequence, and sends the redetermined at least one target coded data to the second communication device, performs another round of coded data transmission, and determines that the feedback information is sent to the first communication device. Wherein, when the transmission of coded data reaches the set round or feedback information indicating that the first coded sequence is successfully received is received, the first communication device stops the transmission of the coded data in the first coded data sequence.

[0093] Step S204: sending position information to the second communication device via the first transceiver; the position information is used to indicate the position of the at least one target coded data in the first coding sequence.

[0094] In some embodiments, the position information is the position of the target coded data in the first coding sequence. For example, the first coding sequence is abcdefg, where b and d are the target coded data, and the position information is 24, indicating that b is in the second position and d is in the fourth position.

[0095] In some implementations, the representation of the position information may also be a coding indicator or a coding order indicator.

[0096] After receiving the position information, the second communication device may integrate the at least one received target coding data based on the position information.

[0097] In some embodiments, at least one target coded data and location information may be sent separately to the second communication device. The present application does not limit the order in which the at least one target coded data and location information are sent. At least one target coded data and location information may also be sent together to the second communication device.

[0098] In an embodiment of the present application, a first communication device includes a first transceiver and a first processor, the first processor is coupled to the first transceiver, wherein the first processor is configured to: semantically encode the first data to obtain a first coding sequence, and determine at least one target coding data from the first coding sequence, and send the at least one target coding data and position information to the second communication device via the first transceiver, respectively, wherein the position information is used to indicate the position of the target coding data in the first coding sequence. In this way, the first communication device selects appropriate target coding data from the first coding sequence and sends it to the second communication device, which, on the one hand, reduces the transmission of redundant information and optimizes the utilization of channel resources, and on the other hand, can improve the reliability of the second communication device receiving information.

[0099] In some embodiments, the above data transmission method may include the following step S211:

[0100] Step S211: sending first mutual information to the second communication device via the first transceiver; the first mutual information is mutual information expected to be received by the second communication device based on the first coding sequence.

[0101] In some implementations, the first mutual information is sent to the second communication device using the first channel.

[0102] In some implementations, the first mutual information is used by the second communication device to determine whether the first coding sequence is successfully received based on the first mutual information.

[0103] In some embodiments, the first mutual information may be predetermined mutual information expected to be received by the second communication device. The first mutual information may be determined based on the sum of the fifth mutual information of each coded data and a preset first threshold, wherein the fifth mutual information is the mutual information of the coded data, and the first threshold is a coefficient less than 1, which is used to characterize the proportion of the mutual information expected to be received by the second communication device to the sum of the fifth mutual information of each coded data in the first coded sequence. In one example, the sum of the fifth mutual information of each coded data in the first coded sequence is 100, and the first threshold is 70% or 0.7, then the first mutual information is 70.

[0104] In the embodiment of the present application, the first mutual information is sent to the second communication device, and the first mutual information is the mutual information that the second communication device is expected to receive based on the first coding sequence. In this way, the second communication device can determine whether the first coding sequence is successfully received based on the first mutual information, so that the information transmission can be reduced as much as possible under the condition that the second communication device successfully receives the first coding sequence, thereby improving the efficiency of information transmission.

[0105] In some embodiments, the above step 102 may include the following step S221:

[0106] Step S221: Determine the at least one target coded data from the first coded sequence based on the first mutual information and the second mutual information of each coded data in the first coded sequence, wherein the second mutual information is the predicted mutual information of the coded data received by the second communication device.

[0107] Here, the first mutual information is the total mutual information that the second communication device expects to receive, and the second mutual information is the mutual information predicted when the second communication device receives each coded data.

[0108] In some implementations, the fourth mutual information is determined according to the first mutual information, and the fourth mutual information is the mutual information expected to be sent.

[0109] In some implementations, at least one target coded data may be randomly selected from the first coding sequence so that the sum of the second mutual information of the selected at least one target coded data meets the fourth mutual information requirement. For example, the first coding sequence is abcdefg, acd is randomly selected, and the sum of the second mutual information of the acd coded data meets the fourth mutual information requirement.

[0110] In some implementations, at least one target coded data may be selected according to the order in which the coded data are arranged in the first coded sequence, so that the sum of the second mutual information of the selected at least one target coded data is greater than or equal to the first mutual information. For example, if the first coded sequence is abcdefg, abcd in the front order is selected, and the sum of the second mutual information of the abcd coded data meets the fourth mutual information requirement.

[0111] In some implementations, the second mutual information of each coded data may be sorted from large to small, and at least one target coded data ranked first may be selected so that the sum of the second mutual information of the selected at least one target coded data is greater than or equal to the first mutual information. For example, the first coded sequence is abcdefg, and the coded data is sorted according to the second mutual information of each coded data, and the sorting result is bdaefg. The coded data bd ranked first is selected, and the sum of the second mutual information of bd meets the fourth mutual information requirement.

[0112] In the embodiment of the present application, at least one target coded data is determined from the first coded sequence based on the first mutual information and the second mutual information of each coded data in the first coded sequence, and the second mutual information is the mutual information of the coded data received by the predicted second communication device. In this way, based on the mutual information received by the second communication device predicted by each coded data and the first mutual information expected to be received by the second communication device, at least one target coded data that meets the receiving requirements of the second communication device can be accurately selected.

[0113] In some embodiments, the above step S221 is followed by step S231 and step S232:

[0114] Step S231: determining fourth mutual information based on the first mutual information and the third mutual information, wherein the third mutual information is the mutual information that the second communication device has received based on the first coding sequence, and the fourth mutual information is the mutual information expected to be sent;

[0115] In some embodiments, the difference between the first mutual information and the third mutual information can be determined as the fourth mutual information. For example, the first mutual information is 70. In the case of the first transmission, the receiving end has not received the mutual information, that is, the third mutual information is 0, and the fourth mutual information is 70; in the case of the second transmission, the third mutual information received by the receiving end is 60, and the fourth mutual information is 10.

[0116] Step S232: Determine the at least one target coded data from the first coded sequence based on the fourth mutual information and the second mutual information of each coded data in the first coded sequence.

[0117] In some implementations, at least one target coded data may be randomly selected from the first coding sequence so that the sum of the second mutual information of the selected at least one target coded data is greater than or equal to the fourth mutual information.

[0118] In some implementations, at least one target coded data may be selected according to the order in which the coded data are arranged in the first coded sequence, so that the sum of the second mutual information of the selected at least one target coded data is greater than or equal to the first mutual information.

[0119] In some implementations, the second mutual information of each coded data may be sorted from large to small, and at least one target coded data ranked first may be selected so that the sum of the second mutual information of the at least one selected target coded data is greater than or equal to the first mutual information.

[0120] In one example, the first mutual information is 60, and each coded data in the first coding sequence is abcdefg. The coded data are sorted from large to small according to the second mutual information of each coded data, and the sorting result is: bdaefg. The coded data bd ranked first is selected, and the sum of the second mutual information of the coded data bd is 62, that is, the coded data bd is the target coded data.

[0121] In the embodiment of the present application, the fourth mutual information expected to be sent is determined based on the first mutual information and the third mutual information already received by the second communication device, and at least one target coded data is selected based on the fourth mutual information and the second mutual information of each coded data. In this way, the target coded data that meets the receiving requirements of the second communication device can be accurately selected based on the fourth mutual information expected to be sent and the second mutual information of each coded data.

[0122] In some embodiments, the above data transmission method may further include the following steps S241 and S242:

[0123] Step S241: determining a first information entropy of the coded data, where the first information entropy is the predicted information entropy of the coded data received by the second communication device;

[0124] In some implementations, a statistical method is used to determine the probability of each coded data value in the coded data and the probability of the channel noise value, so as to determine the first information entropy of the coded data.

[0125] In some implementations, a suitable entropy model is selected according to a task type corresponding to the first data; and the first information entropy of the encoded data is determined using the entropy model according to a first probability distribution of the encoded data and a probability distribution of channel noise.

[0126] In some embodiments, the first information entropy of the encoded data is determined based on a probability density function corresponding to the first probability distribution of the encoded data and a probability density function corresponding to the probability distribution of the channel noise.

[0127] In some embodiments, when the channel is a Gaussian channel, it is assumed that the distribution of Gaussian noise is The equivalent noise distribution when the encoded data is transmitted for the Nth time is: When the channel is a Rayleigh channel, the channel obeys y = h·x + N, and the equivalent noise distribution of the coded data when it is transmitted for the Nth time is:

[0128] In some embodiments, f(x) may represent the probability distribution of the encoded data, and g(x) may represent the probability distribution of the channel noise.

[0129] In some implementations, the first information entropy of the coded data is determined based on the first probability distribution of the coded data, the probability distribution of the channel noise, and the number of transmissions corresponding to the coded data. Specifically, the second information entropy of the coded data in the Nth case is predicted based on the first probability distribution of the coded data and the probability distribution of the channel noise; the third information entropy is obtained, and the third information entropy is the second information entropy of the coded data in the N-1th transmission case; and the difference between the second information entropy and the third information entropy is determined as the first information entropy.

[0130] Step S242: Determine the second mutual information of the encoded data based on the first information entropy of the encoded data.

[0131] In some embodiments, the second mutual information of the encoded data is determined based on the first information entropy and the fourth information entropy of the encoded data, wherein the fourth information entropy is the information entropy of the channel noise of the encoded data when it is transmitted for the Nth time.

[0132] In some embodiments, the second information entropy of the encoded data in the Nth transmission case can be determined as the first information entropy, or the difference between the second information entropy and the third information entropy can be used to determine the first information entropy of the encoded data, and the third information entropy can predict the second information entropy of the encoded data in the N-1th transmission case.

[0133] In the embodiment of the present application, the first information entropy of the coded data is determined, and the first information entropy is the predicted information entropy of the coded data received by the second communication device; the second mutual information of the coded data is determined based on the first information entropy of the coded data. In this way, the second mutual information of the coded data received by the second communication device can be predicted based on the predicted information entropy of the coded data received by the second communication device, so that the second communication device can accurately obtain the information entropy improvement corresponding to the received target coded data based on the second mutual information, thereby determining whether the second communication device meets the receiving requirements.

[0134] In some embodiments, the above step S241 may include the following steps S251 and S252:

[0135] Step S251: when the coded data is determined to be transmitted for the Nth time, predicting the second information entropy of the coded data in the case of the Nth transmission;

[0136] In some embodiments, the second information entropy is the information entropy of the encoded data when it is transmitted for the Nth time, and the calculation formula can refer to formula (1), wherein the probability density function of the channel noise is determined according to the equivalent noise distribution of the encoded data when it is transmitted for the Nth time.

[0137]

[0138] In formula (1), f(x) is the probability density function of the encoded data, g(x) is the probability density function of the channel noise, represents convolution, Represents a uniform distribution between -0.5 and 0.5.

[0139] Step S252: Determine the first information entropy of the coded data based on the difference between the second information entropy and the third information entropy; the third information entropy is the predicted second information entropy of the coded data in the N-1th transmission case.

[0140] In some embodiments, when the coded data is determined to be transmitted for the Nth time, that is, the coded data has been transmitted to the second communication device N-1 times, it is known that directly using the information entropy of the coded data under the noise condition of the Nth transmission as the predicted information entropy of the coded data received by the second communication device is inaccurate, therefore, the third information entropy is obtained, and the difference between the second information entropy and the third information entropy is determined as the information entropy of the coded data received by the second communication device predicted at the Nth transmission, that is, the first information entropy. The third information entropy is the second information entropy of the predicted coded data under the N-1th transmission condition.

[0141] In one example, the first coding sequence is abcdefg, and the coded data a is judged to be transmitted for the Nth time, that is, the coded data a has been transmitted to the second communication device N-1 times; the second information entropy of the coded data a in the Nth transmission is 5, and the second information entropy of the coded data a in the N-1th transmission is 3, then the first information entropy is 2.

[0142] In one example, when the encoded data a is judged to be transmitted for the first time, that is, the encoded data a is transmitted to the second communication device for the first time, the second information entropy of the encoded data a is 5, the second information entropy of the encoded data a in the case of the N-1th transmission is 0, and the first information entropy is 5.

[0143] In some embodiments, the first information entropy H of the encoded data x is the second information entropy H x (N) and the third information entropy H x The difference between (N-1) is determined as the first information entropy of the encoded data.

[0144] In the embodiment of the present application, when the coded data is determined to be transmitted for the Nth time, the second information entropy of the coded data in the Nth transmission is predicted, and the first information entropy of the coded data is determined according to the difference between the second information entropy and the third information entropy; the third information entropy is the predicted second information entropy of the coded data in the N-1th transmission. In this way, even if the coded data is transmitted multiple times, the information entropy of the coded data received by the second communication device can be accurately predicted.

[0145] In some embodiments, the above step S251 may include the following step S261:

[0146] Step S261: Determine the second information entropy of the coded data when it is transmitted for the Nth time based on the first probability distribution of the coded data and the probability distribution of the channel noise of the coded data when it is transmitted for the Nth time, wherein the first probability distribution is the probability distribution of the coded data when no information is lost.

[0147] Here, the first probability distribution is the probability distribution of the encoded data when information is not lost, that is, the probability distribution of the encoded data in the first communication device.

[0148] In some implementations, the first probability distribution may be represented by a probability density function f(x), and the probability distribution of the channel noise may be represented by g(x).

[0149] In some embodiments, when the channel is a Gaussian channel, it is assumed that the distribution of Gaussian noise is The equivalent noise distribution when the encoded data is transmitted for the Nth time is: When the channel is a Rayleigh channel, the channel obeys y = h·x + N, and the equivalent noise distribution of the coded data when it is transmitted for the Nth time is:

[0150] When the coded data is transmitted for the Nth time, the second information entropy of the coded data in the Nth case is predicted according to the first probability distribution and the probability distribution of the channel noise. The second information entropy H x The calculation of (N) can refer to formula (1).

[0151] In the embodiment of the present application, the second information entropy of the encoded data under the Nth transmission condition is determined according to the first probability distribution of the encoded data and the probability distribution of the channel noise of the encoded data under the Nth transmission condition. In this way, the second information entropy of the encoded data under the Nth transmission condition can be accurately predicted by using the probability distribution of the channel noise of the encoded data under the Nth transmission condition.

[0152] In some embodiments, the above step S242 may include the following steps S271 and S272:

[0153] Step S271: determining a fourth information entropy corresponding to the coded data based on the probability distribution of the channel noise, where the fourth information entropy is the information entropy of the channel noise of the coded data when the coded data is transmitted for the Nth time;

[0154] In some implementations, the fourth information entropy corresponding to the encoded data is determined based on the probability distribution of the channel noise using a selected appropriate entropy model.

[0155] In some implementations, the fourth information entropy of the encoded data is determined according to a probability density function corresponding to the probability distribution of the channel noise. The fourth information entropy H z The calculation of can refer to formula (2):

[0156]

[0157] Wherein, g(x) is the probability density function corresponding to the equivalent noise distribution of the channel noise when the encoded data is transmitted for the Nth time.

[0158] Step S272: Determine the second mutual information of the encoded data based on the first information entropy and the fourth information entropy.

[0159] In some implementations, the second mutual information of the encoded data may be determined in accordance with formula (3):

[0160] I=H x -H z (3);

[0161] In the embodiment of the present application, the fourth information entropy corresponding to the coded data is determined according to the probability distribution of the channel noise, and the second mutual information of the coded data is determined according to the first information entropy and the fourth information entropy. In this way, the second mutual information of the coded data can be accurately predicted, so that the second communication device determines whether the received first coded sequence meets the reception requirement according to the second mutual information.

[0162] In some embodiments, the above data transmission method may further include the following steps S281 and S282:

[0163] Step S281: for each coded data in the first coding sequence, determine the fifth mutual information of the coded data, where the fifth mutual information is the mutual information of the coded data sent by the first communication device;

[0164] In some implementations, fifth mutual information of the coded data is determined based on a sixth information entropy and a fourth information entropy of the coded data, wherein the sixth information entropy is the information entropy of the coded data sent by the first communication device.

[0165] In some implementations, the difference between the sixth information entropy and the fourth mutual information may be determined as the fifth mutual information of the encoded data.

[0166] In some implementations, according to the first probability distribution of the encoded data, the sixth information entropy may be determined by referring to formula (4):

[0167]

[0168] Step S282: Determine first mutual information based on the sum of fifth mutual information of each of the encoded data in the first encoding sequence and a first threshold.

[0169] In some implementations, the sum of the fifth mutual information is the total mutual information of the first coding sequence, and the first mutual information is determined according to the total mutual information of the first coding sequence and the first threshold.

[0170] In some implementations, the first threshold may be a ratio of the first mutual information to the sum of the fifth mutual information. For example, the sum of the fifth mutual information is 100, the first threshold is 70% or 0.7, and the first mutual information is 70.

[0171] In the embodiment of the present application, for each coded data in the first coding sequence, the fifth mutual information of the coded data is determined, and the fifth mutual information is the mutual information of the coded data sent by the first communication device; the first mutual information is determined according to the sum of the fifth mutual information of each coded data in the first coding sequence and the first threshold. In this way, the appropriate first threshold can be flexibly set according to specific task requirements to determine the mutual information expected to be received by the second communication device.

[0172] In some embodiments, the above data transmission method may further include the following step S291:

[0173] Step S291: receiving feedback information sent by the second communication device via the first transceiver, where the feedback information is used to indicate whether the first coding sequence is received successfully.

[0174] In some embodiments, the feedback information is received using a second channel, wherein the second channel is a data channel and the direction is from the second communication device to the first communication device.

[0175] In some implementations, the second channel may be established by a wireless connection method.

[0176] In some embodiments, when the feedback information includes ACK, it indicates that the first coding sequence is received successfully and the first communication device completes the transmission of the first coding sequence; when the feedback information includes NACK and the third mutual information, it indicates that the first coding sequence is not received successfully, at least one target coding data is re-determined from the first coding sequence, and the at least one target coding data and the position information corresponding to the at least one target coding data are respectively transmitted to the second communication device.

[0177] In the embodiment of the present application, feedback information sent by the second communication device is received via the first transceiver, and the feedback information is used to indicate whether the first coding sequence is received successfully. In this way, the first communication device determines whether it is necessary to retransmit data according to the feedback information, so that the first communication device retransmits the target coded data when the second communication device fails to receive the data successfully, thereby reducing the transmission of redundant information and improving the transmission efficiency.

[0178] In some embodiments, the first processor is configured to implement the following step S292:

[0179] Step S292: In response to the feedback information indicating that the first coding sequence is not received successfully, determining the at least one target coding data from the first coding sequence;

[0180] Wherein, when the feedback information indicates that the first coding sequence is not received successfully, the feedback information further includes: third mutual information, where the third mutual information is the mutual information that the second communication device has received based on the first coding sequence.

[0181] In some implementations, at least one target coded data is re-determined from the first coded sequence based on the first mutual information and the second mutual information of each coded data.

[0182] In some implementations, the fourth mutual information is determined based on the first mutual information and the third mutual information.

[0183] In some implementations, when the coded data is transmitted for the Nth time, the second mutual information corresponding to each coded data is re-predicted, and at least one target coded data is selected according to the fourth mutual information and the second mutual information.

[0184] In some implementations, at least one target coded data and the position information corresponding to the at least one target coded data may be transmitted to the second communication device in two batches. The present application does not limit the order in which the at least one target coded data and the corresponding position information are transmitted.

[0185] In some implementations, at least one target coded data and the location information corresponding to at least one target coded data may also be transmitted to the second communication device simultaneously.

[0186] In the embodiment of the present application, feedback information indicating that the first coding sequence was not successfully received is received, and at least one target coding data is determined from the first coding sequence; wherein, when the feedback information indicates that the first coding sequence was not successfully received, the feedback information also includes: third mutual information, and the third mutual information is the mutual information that the second communication device has received based on the first coding sequence. In this way, when the first coding sequence is not successfully received, at least one target coding data is re-determined from the first coding sequence, so that the target coding data received by the second communication device meets the receiving requirements, and no redundant information is transmitted additionally, thereby improving the transmission efficiency.

[0187] The specific process of determining at least one target coded data from the first coded sequence is described below:

[0188] When determining at least one target coded data, first determine the first mutual information, the first mutual information being the mutual information expected to be received by the second communication device based on the first coded sequence; specifically, for each coded data in the first coded sequence, determine the fifth mutual information, the fifth mutual information being the mutual information of the coded data sent by the first communication device; determine the first mutual information based on the sum of the fifth mutual information of each coded data and a preset first threshold, for example, if the sum of the fifth mutual information is 100, and the mutual information expected to be received by the second communication device is 70% of the sum of the fifth mutual information, then the first mutual information is 70.

[0189] Secondly, for each coded data in the first coding sequence, the second mutual information of the coded data is determined according to the first information entropy of the coded data, the first information entropy is the information entropy of the coded data received by the predicted second communication device, and the second mutual information is the mutual information of the coded data received by the predicted second communication device, and the specific determination process is as follows:

[0190] When the coded data is transmitted for the Nth time, the second information entropy of the coded data in the Nth case is predicted, and the second information entropy H x The calculation of (N) can refer to formula (1).

[0191] In formula (1), f(x) is the probability density function of the encoded data, g(x) is the probability density function of the channel noise, represents convolution, Represents a uniform distribution between -0.5 and 0.5.

[0192] In some embodiments, when the channel is a Gaussian channel, it is assumed that the distribution of Gaussian noise is The equivalent noise distribution when the encoded data is transmitted for the Nth time is: When the channel is a Rayleigh channel, the channel obeys y = h x + n, and the equivalent noise distribution of the coded data when it is transmitted for the Nth time is:

[0193] In some embodiments, f(x) may represent the probability distribution of the encoded data, and g(x) may represent the probability distribution of the channel noise.

[0194] The first information entropy H x is the second information entropy H x (N) and the third information entropy H x (N-1), wherein the third information entropy is the second information entropy of the encoded data when it is transmitted for the N-1th time.

[0195] According to the probability distribution of the channel noise, a fourth information entropy of the coded data is determined, where the fourth information entropy is the information entropy of the channel noise when the coded data is transmitted for the Nth time.

[0196] The second mutual information I is the difference between the first information entropy and the fourth information entropy, see formula (3).

[0197] Finally, at least one target coded data is determined from the first coded sequence according to the first mutual information and the second mutual information. The specific determination process is as follows:

[0198] The first communication device receives third mutual information sent by the second communication device, where the third mutual information is mutual information that the second communication device has received based on the first coding sequence.

[0199] The difference between the first mutual information and the third mutual information is determined as the fourth mutual information, and the fourth mutual information is the mutual information expected to be sent. For example, the first mutual information is 70, and in the case of the first transmission, the receiving end has not received the mutual information, that is, the third mutual information is 0, and the fourth mutual information is 70; in the case of the second transmission, the third mutual information received by the receiving end is 60, and the fourth mutual information is 10.

[0200] In some implementations, fourth mutual information may also be received via the first transceiver.

[0201] According to the second mutual information of each coded data in the first coding sequence, the coded data are sorted from large to small, and the coded data in the previous order are selected in turn, until the sum of the second mutual information of the selected coded data is greater than the fourth mutual information, and the coded data selected at this time is the target coded data. The target coded data is the coded data that is more important for improving the information entropy received by the second communication device, that is, the target coded data is the coded data that is more important to the second communication device.

[0202] This embodiment of the application provides a second communication device, Figure 3A schematic diagram of the structure of a second communication device provided in an embodiment of the present application is shown in FIG. Figure 3 As shown, the second communication device 30 includes a second transceiver 31 and a second processor 32 coupled to the second transceiver 31 .

[0203] A data transmission method provided in an embodiment of the present application is applied to a second communication device, such as Figure 4 As shown, the following steps S401 and S402 may be included:

[0204] Step S401: receiving, via the second transceiver, at least one target coded data and position information in a first coded sequence sent by a first communication device; the position information is used to indicate the position of the at least one target coded data in the first coded sequence;

[0205] Here, the second communication device may be a user-side device, which is used to receive data sent by the first communication device to obtain data required by the user.

[0206] In some implementations, in at least one target coded data, each target coded data may be received for the first time or may be received for the Nth time.

[0207] Step S402: Based on the position information, the at least one target coded data is integrated to obtain a second coded sequence, where the second coded sequence is used to recover the first data based on semantic decoding.

[0208] In some implementations, the received target coding data is integrated according to the position information to obtain a second coding sequence. The first coding sequence is abcdef, the received target coding data is c, and the position information is 3; the target coding data received this time is bd, and the position information is 24, and at least one target coding data is integrated to obtain a second coding sequence bcd.

[0209] In some implementations, the second encoding sequence is decoded using a selected appropriate semantic decoding model to obtain the restored first data.

[0210] In an embodiment of the present application, the second communication device includes a second transceiver and a second processor, the second processor is coupled to the second transceiver, wherein the second processor is configured to: receive at least one target coded data and position information in a first coded sequence sent by the first communication device via the second transceiver; the position information is used to indicate the position of at least one target coded data in the first coded sequence; according to the position information, at least one target coded data is integrated to obtain a second coded sequence, and the second coded sequence is used to recover the first data based on semantic decoding. In this way, the receiving first communication device selects appropriate target coded data from the first coded sequence, which, on the one hand, reduces the transmission of redundant information and optimizes the utilization of channel resources, and on the other hand, can improve the reliability of the second communication device receiving information.

[0211] In some embodiments, the above data transmission method further includes the following steps S411 and S412:

[0212] Step S411: receiving, via the second transceiver, first mutual information sent by the first communication device, where the first mutual information is mutual information expected to be received by the second communication device based on the first coding sequence;

[0213] In some implementations, the first mutual information is used to determine whether the first coding sequence is received successfully.

[0214] Step S412: Determine whether the first coding sequence is received successfully based on the first mutual information.

[0215] In some implementations, it is determined whether the first coding sequence is successfully received based on the received target coded data and the first mutual information.

[0216] In some implementations, the received third mutual information is compared with the first mutual information to determine whether the first coding sequence is successfully received. If the third mutual information is greater than or equal to the first mutual information, it is determined that the first coding sequence is successfully received; if the third mutual information is less than the first mutual information, it is determined that the first coding sequence is not successfully received.

[0217] In some embodiments, when the ratio of the received third mutual information to the first mutual information is greater than or equal to a second threshold, it is determined that the first coding sequence is received successfully; when the ratio of the received third mutual information to the first mutual information is less than the second threshold, it is determined that the first coding sequence is received successfully.

[0218] In the embodiment of the present application, the first mutual information sent by the first communication device is received via the second transceiver, and the first mutual information is the mutual information expected to be received by the second communication device based on the first coding sequence; whether the first coding sequence is received successfully is determined according to the first mutual information. In this way, the second communication device determines whether the first communication device needs to transmit the first coding sequence again according to whether the reception is successful, so that the first communication device reasonably uses resources, reduces the transmission of redundant information, and thus improves the transmission efficiency.

[0219] In some embodiments, the above step S212 may include the following steps S221 to S223:

[0220] Step S421: for each target coded data in the received target coded data, based on the fifth information entropy of the target coded data and the fourth information entropy of the channel noise, determining the sixth mutual information of the target coded data, the fifth information entropy being the information entropy of the target coded data received by the second communication device, and the sixth mutual information being the mutual information of the target coded data received by the second communication device;

[0221] In some implementations, a difference between the fifth information entropy and the fourth information entropy is determined as sixth mutual information of the target encoded data.

[0222] In some implementations, the fifth information entropy may be the information entropy of each target coded data stored in the knowledge base, or may be calculated based on each target coded data.

[0223] In some implementations, the fourth information entropy is determined according to the probability distribution corresponding to the equivalent noise of the channel noise, or may be determined by the probability distribution of the channel noise.

[0224] Step S422: determining third mutual information based on sixth mutual information of each target coded data in the received target coded data, wherein the third mutual information is mutual information of the second communication device based on the received target coded data;

[0225] In some implementations, the third mutual information is the sum of the sixth mutual information of each target coded data.

[0226] Step S423: Compare the third mutual information with the first mutual information to determine whether the first coding sequence is received successfully.

[0227] In some implementations, when the third mutual information is greater than or equal to the first mutual information, it is determined that the first coding sequence is received successfully; when the third mutual information is less than the first mutual information, it is determined that the first coding sequence is not received successfully.

[0228] In some embodiments, when the ratio of the third mutual information to the first mutual information is greater than or equal to the second threshold, it is determined that the first coding sequence is received successfully; when the ratio of the third mutual information to the first mutual information is less than the second threshold, it is determined that the first coding sequence is received successfully.

[0229] In the embodiment of the present application, for each target coded data in the received target coded data, the sixth mutual information of the target coded data is determined according to the fifth information entropy of the target coded data and the fourth information entropy of the channel noise, the fifth information entropy is the information entropy of the target coded data received by the second communication device, and the sixth mutual information is the mutual information of the target coded data received by the second communication device; the third mutual information is determined based on the sixth mutual information of each target coded data in the received target coded data, the third mutual information is the mutual information of the second communication device based on the received target coded data; the third mutual information is compared with the first mutual information to determine whether the first coding sequence is successfully received. In this way, according to the mutual information that has been received and the mutual information expected to be received, it can be accurately determined whether the first coding sequence is successfully received.

[0230] In some embodiments, the above data transmission method may further include the following step S431:

[0231] Step S431: Determine the fifth information entropy of the target coded data based on the second probability distribution of the target coded data, the probability distribution of channel noise and the number of transmissions M of the target coded data, wherein the second probability distribution is the probability distribution of the target coded data under information loss.

[0232] In some embodiments, for each target coded data, a fifth information entropy of the target coded data is determined according to the second probability distribution of the target coded data, the probability distribution of the channel noise, and the number of transmissions of the target coded data M. The second probability distribution is the probability distribution of the target coded data under information loss.

[0233] In some embodiments, the value of each received coded data is obtained from a knowledge base, assuming that coded data a has been received twice, with values ​​a1 and a2 respectively, and coded data a is received again with a value a3; the median between a1, a2, and a3 is determined as the value of the target coded data, and the probability distribution of the coded data a is determined based on the value of the coded data a, and the fifth information entropy is determined based on the probability distribution of the coded data a.

[0234] In some implementations, it is assumed that the coded data a has been received twice, and the values ​​are a1 and a2 respectively, and the coded data a is received again, and the value is a3; the value of the coded data a is the average value A of a1, a2, and a3, and according to the average value A, the distribution interval of the coded data a is determined to be: (a-0.5, a+0.5);

[0235] In some implementations, the value calculation method of other coded data is the same as that of coded data a.

[0236] In the embodiment of the present application, the fifth information entropy of the target coded data is determined based on the second probability distribution of the target coded data, the probability distribution of the channel noise and the number of transmissions of the target coded data M, and the second probability distribution is the probability distribution of the target coded data under the condition of information loss. In this way, the influence of the number of transmissions of the coded data on the value of the coded data is considered, so that the fifth information entropy obtained is more accurate.

[0237] In some embodiments, the above data transmission method may further include the following step S441:

[0238] Step S441: Send feedback information to the first communication device via the second transceiver, where the feedback information is used to indicate whether the first coding sequence is received successfully.

[0239] In some embodiments, when the feedback information includes ACK, the feedback information is used to indicate that the first coding sequence is received successfully, so as to send a successful reception response to the first communication device; or, when the feedback information includes NACK and third mutual information, it is used to indicate that the first coding sequence is not received successfully, so that the first communication device determines at least one target coding data based on the third mutual information.

[0240] In the embodiment of the present application, feedback information is sent to the first communication device via the second transceiver, and the feedback information is used to indicate whether the first coding sequence is received successfully. In this way, the first communication device can determine whether the first coding sequence is received successfully according to the feedback information.

[0241] In some embodiments, the above data transmission method may further include the following step S451:

[0242] Step S451: when the feedback information indicates that the first coding sequence is not received successfully, the feedback information further includes: third mutual information, where the third mutual information is the mutual information that the second communication device has received based on the first coding sequence.

[0243] In some embodiments, when the feedback information indicates that the first coding sequence is not received successfully, the first communications device determines at least one target coding data again based on the third mutual information in the feedback information.

[0244] In some implementations, the feedback information may further include fourth mutual information, where the fourth mutual information is the mutual information expected to be sent, and the fourth mutual information is the difference between the first mutual information and the third mutual information.

[0245] In the embodiment of the present application, when the feedback information indicates that the first coding sequence is not received successfully, the feedback information also includes third mutual information, so that the first communication device determines the mutual information expected to be sent according to the third mutual information.

[0246] The following describes the application of the embodiments of the present application in actual scenarios.

[0247] As a strong competitor for the 6G standard, semantic communication is increasingly attracting widespread attention. This communication method based on the understanding of information content aims to significantly improve the efficiency and reliability of information transmission. Unlike communication methods that focus on the transmission of bit streams, semantic communication focuses on the semantic level of information and is committed to its efficient and accurate transmission and recovery. However, in complex interference environments, semantic communication also faces the risk of transmission errors.

[0248] To meet this challenge, the semantic HARQ (Hybrid Automatic Repeat reQuest) mechanism came into being, providing a new solution for processing error request retransmission at the receiving end. Unlike HARQ in related technologies, which only focuses on the reliability of bit streams, semantic HARQ integrates the advanced concept of semantic communication and aims to further optimize the efficiency and reliability of data transmission through in-depth understanding and precise analysis of information content.

[0249] Although there have been some attempts to apply semantic communication to this field, these solutions still have shortcomings. For example, some solutions adopt the strategy of retransmitting all erroneous modules, which will undoubtedly cause a waste of channel resources; while other solutions simply retransmit according to the importance of the information, but this approach cannot guarantee that the most important information is transmitted each time, thus failing to fully utilize channel resources. There is also a solution that uses the HARQ method in the related technology to transmit semantic information and relaxes the standard of HARQ retransmission, but this approach cannot ensure the importance of error coding, that is, error coding may have a greater impact on the transmission results. Therefore, how to more effectively combine semantic communication with the HARQ mechanism to achieve more efficient and reliable data transmission is still a problem that needs to be solved urgently.

[0250] Based on the above description, the purpose of the present invention is to propose a semantic HARQ scheme based on an entropy model to improve the quality of information transmission in a high-noise channel. The transmitter encodes the information through joint source channel coding, calculates the distribution of the code using the entropy model, and then calculates the increase in information entropy obtained by the receiver after each code transmission in combination with the noise size and the number of transmissions, and selects the encoded data to be transmitted accordingly. The transmitter sends a coding indicator to the receiver for data reception. The receiver determines the coding distribution through the knowledge base, determines whether the transmission is successful by calculating the information entropy, and selects whether retransmission is required accordingly. When data needs to be retransmitted, the transmitter needs to recalculate the noise distribution, update the coding indicator and send it to the receiver for data reception.

[0251] The embodiment of the present application provides a data transmission method, which encodes information (corresponding to the first data in the aforementioned embodiment) through joint source channel coding at the transmitting end (corresponding to the first communication device in the aforementioned embodiment), and uses the entropy model to accurately calculate the distribution of the code. Subsequently, in combination with the current noise level and the number of transmissions that have been performed, the transmitting end can calculate the amount of information entropy improvement that the receiving end can obtain after each coded transmission, and then select the coded data to be transmitted accordingly. In order for the receiving end (corresponding to the second communication device in the aforementioned embodiment) to correctly receive the coded data, the transmitting end will also send a coding indicator (corresponding to the position information in the aforementioned embodiment) to the receiving end. At the receiving end, with the assistance of the knowledge base, it is possible to judge the received coding distribution, and to judge whether the information is successfully transmitted by calculating the information entropy, so as to decide whether to send feedback information to the transmitting end to realize the retransmission of the coded data. If the coded data needs to be retransmitted, the transmitting end will recalculate the noise distribution, update the coding indicator, and send it to the receiving end to ensure the accurate reception of the coded data.

[0252] Figure 5 A schematic diagram of a transmitting end and a receiving end model provided in an embodiment of the present application, such as Figure 5 As shown, the specific implementation process of the method may include the following steps S1101 to S1120:

[0253] Step S1101: The sending end 500 selects a suitable semantic coding model and a corresponding entropy model 502 according to different task requirements to ensure that the selected model can effectively process a specific type of information;

[0254] The semantic coding model and entropy model 502 should be trained simultaneously. The specific training scheme is: the coding variation is regarded as a code that obeys a normal distribution, with a mean of 0 and an unknown variance σ. Another neural network is trained to predict σ of this distribution. Then the code y i The size of entropy can be found in formula (5):

[0255]

[0256] The semantic coding model may be the JSCC coding model 501 .

[0257] Step S1102: The transmitting end 500 performs encoding using the selected semantic coding model to obtain a first coding sequence; and calculates a first probability distribution of each coded data in the first coding sequence using the entropy model 502;

[0258] Here, the first coding sequence includes at least one coded data.

[0259] In some embodiments, the first probability distribution is represented by a probability density function f(x).

[0260] Step S1103: The transmitting end 500 obtains channel state information and calculates the probability distribution of channel noise;

[0261] In some embodiments, the first probability distribution is represented by a probability density function g(x).

[0262] When the channel is a Gaussian channel, the distribution of Gaussian noise is assumed to be The equivalent noise distribution when the encoded data is transmitted for the Nth time is: When the channel is a Rayleigh channel, the channel obeys y = h·x + N, and the equivalent noise distribution of the coded data when it is transmitted for the Nth time is:

[0263]

[0264] Step S1104: the transmitting end 500 predicts the mutual information of the coded data received by the receiving end, that is, the second mutual information, by using the mutual information calculation model 503 according to the first probability distribution of each coded data and the probability distribution of noise;

[0265] The specific process of determining the second mutual information is as follows:

[0266] According to the first probability distribution of each coded data and the probability distribution of noise, it is preset that when the coded data is transmitted for the Nth time, the second information entropy of the coded data in the Nth case is predicted, and the second information entropy H x The calculation of (N) can refer to formula (1).

[0267] The first information entropy H x is the second information entropy H x (N) and the third information entropy H x (N-1), wherein the third information entropy is the second information entropy of the encoded data when it is transmitted for the N-1th time.

[0268] According to the probability distribution of the channel noise, the fourth information entropy of the coded data is determined, where the fourth information entropy is the information entropy of the channel noise of the coded data when it is transmitted for the Nth time. The fourth information entropy H z Please refer to formula (2).

[0269] The second mutual information I is the difference between the first information entropy and the fourth information entropy, see formula (3).

[0270] Step S1105: The transmitting end 500 determines at least one target coded data from the first coding sequence according to the first mutual information and the second mutual information, wherein the first mutual information is the mutual information expected to be received by the second communication device based on the first coding sequence;

[0271] At least one target coded data is determined from the first coded sequence according to the first mutual information and the second mutual information. The specific determination process is as follows:

[0272] The transmitting end receives the third mutual information sent by the receiving end, where the third mutual information is the mutual information that the second communication device has received based on the first coding sequence.

[0273] The difference between the first mutual information and the third mutual information is determined as the fourth mutual information, and the fourth mutual information is the mutual information expected to be sent. For example, the first mutual information is 70, and in the case of the first transmission, the receiving end has not received the mutual information, that is, the third mutual information is 0, and the fourth mutual information is 70; in the case of the second transmission, the third mutual information received by the receiving end is 60, and the fourth mutual information is 10.

[0274] According to the second mutual information of each coded data in the first coding sequence, the coded data are sorted from large to small, and the coded data in the previous order are selected in turn, until the sum of the second mutual information of the selected coded data is greater than the fourth mutual information, and the coded data selected at this time is the target coded data. The target coded data is the coded data that is more important for improving the information entropy received by the second communication device, that is, the target coded data is the coded data that is more important to the second communication device.

[0275] Step S1106: the transmitting end 500 transmits at least one target coded data to the receiving end 410 through the first channel 507, and transmits the coding sequence indicator to the receiving end 410 in a lossless manner;

[0276] Step S1107: the receiving end 410 receives at least one target coded data and a coding order indicator, and receives the first mutual information sent by the transmitter;

[0277] Step S1107: The receiving end 410 determines third mutual information according to the second probability distribution of at least one target coded data and the probability distribution of the channel noise; the third mutual information is the mutual information of the second communication device based on the received target coded data;

[0278] The specific process of determining the third mutual information is as follows:

[0279] First, based on the knowledge in the knowledge base 504, the fifth information entropy of at least one received target coded data is determined through the entropy model 502. The fifth information entropy is the information entropy of the target coded data received by the second communication device. Specifically, for each target coded data, the fifth information entropy of the target coded data is determined according to the second probability distribution of the target coded data, the probability distribution of the channel noise and the number of transmissions M of the target coded data. Among them, the second probability distribution is the probability distribution of the target coded data under the condition of information loss. For example, assuming that the coded data a has been received twice, the values ​​are a1 and a2 respectively; the coded data a is received again, the value is a3, and the value of the coded data a is the average value A of a1, a2, and a3. According to the value A of the coded data a, the distribution interval of the coded data a is determined to be: (a-0.5, a+0.5), and the value calculation method of other coded data is the same as that of the coded data a. Therefore, the fifth information entropy of the target coded data can be determined according to the second probability distribution of the target coded data, the probability distribution of the channel noise and the value of the target coded data.

[0280] Secondly, according to the fifth information entropy of the target coded data and the fourth information entropy of the channel noise, the sixth mutual information of the target coded data is determined using the mutual information calculation model 503, where the sixth mutual information is the mutual information of the target coded data received by the second communication device.

[0281] Finally, the sum of the sixth mutual information of each target coded data is determined as the third mutual information, where the third mutual information is the mutual information of the second communication device based on the target coded data that has been received.

[0282] Step S1108: The receiving end compares the third mutual information with the first mutual information to determine whether the first coding sequence is received successfully;

[0283] The third mutual information is compared with the first mutual information to determine whether the first coding sequence is received successfully. If the third mutual information is greater than or equal to the first mutual information, it is determined that the first coding sequence is received successfully; if the third mutual information is less than the first mutual information, it is determined that the first coding sequence is not received successfully.

[0284] Step S1109: the receiving end sends feedback information to the sending end using the second channel 508;

[0285] If the first coding sequence is received successfully, an ACK indicating that the first coding sequence is received successfully; if the first coding sequence is not received successfully, a NACK indicating that the first coding sequence is not received successfully and third mutual information are provided.

[0286] Step S1110: the transmitting end receives feedback information that the first coding sequence is not successfully received, re-determines the second mutual information, and determines at least one target coding data; and sends the at least one target coding data and the corresponding coding sequence indicator to the receiving end;

[0287] In some implementations, the method for re-determining the second mutual information is the same as the method described in step S1104.

[0288] Step S1111: the receiving end receives at least one target coded data and a corresponding coding order indicator, re-determines the third mutual information, and determines whether the first coding sequence is received successfully; if the first coding sequence is not received successfully, feedback information is sent to the sending end, and the process goes to step S1109;

[0289] In some implementations, the method for re-determining the third mutual information is the same as the method described in step S1107.

[0290] Step S1112: The receiving end integrates the target coded data received multiple times according to the coding order indicator to obtain a second coded sequence, and uses the selected semantic decoding model to semantically decode the second coded sequence to recover the information required by the receiving end.

[0291] According to the position information, the target coded data received multiple times are integrated using the fusion model 505 to obtain a second coded sequence. The second coded sequence is decoded using a suitable semantic decoding model (eg, JSCC decoding model 506) to recover the information required by the receiving end.

[0292] Figure 6 A schematic diagram of a sending end step flow diagram provided in an embodiment of the present application, such as Figure 6 As shown, the following steps S601 to S607 may be included:

[0293] Step S601: Select a semantic coding model based on the data type;

[0294] Step S602: Calculate the coding distribution using an entropy model;

[0295] Step S603: Determine the channel model and noise distribution;

[0296] Step S604: predicting the size of mutual information received by each coded data receiving end;

[0297] According to the coding distribution calculated in step S602 and the probability distribution of the channel noise obtained in step S603, the size of the mutual information received by each coded data receiving end is predicted.

[0298] Step S605: Sending coded data according to the mutual information size;

[0299] Step S606: Does the receiving end feedback ACK? If yes, end; if no, proceed to step S607, and then proceed to step S604;

[0300] Step S607: Count the number of times each coded data is sent; and proceed to step S604.

[0301] Figure 7 A schematic diagram of a receiving end step flow diagram provided in an embodiment of the present application, such as Figure 7 As shown, the following steps S701 to S708 may be included:

[0302] Step S701: determine the channel model and noise distribution; and proceed to step S704;

[0303] Step S702: Determine the received data encoding; and proceed to step S704;

[0304] Step S703: Obtain the code distribution in the knowledge base; and proceed to step S704;

[0305] Step S704: The receiving end calculates the mutual information of the encoding;

[0306] Step S705: Is the reception successful? If yes, proceed to step S706; if no, proceed to step S707;

[0307] Step S706: Return ACK and integrate received information;

[0308] Step S707: return NACK;

[0309] Step S708: semantically decode the integrated received information.

[0310] Figure 8 A schematic diagram of a base station and user side process provided in an embodiment of the present application, such as Figure 8 As shown, the following steps S801 to S813 may be included:

[0311] Step S801: The base station sends a semantic task to a user / receives a semantic task from the user;

[0312] Step S802: The user uploads the semantic task to the user / receives the semantic task from the base station;

[0313] Step S803: The base station calculates the mutual information size of the coding by using the probability distribution of the coded data and the probability distribution of the channel noise;

[0314] Step S804: the base station sends the coded data of the maximum mutual information that can be received by the user;

[0315] Step S805: The user receives the coded data and calculates the mutual information of the coded data;

[0316] Step S806: The user reports ACK / NACK;

[0317] Step S807: the base station receives ACK / NACK;

[0318] Step S808: recalculate the mutual information size of the encoded data;

[0319] Step S809: the base station sends the coded data of the maximum mutual information that can be received by the user;

[0320] Step S810: The user receives the encoded data and calculates the encoded mutual information.

[0321] Step S811: The user reports ACK / NACK;

[0322] Step S812: the base station receives ACK / NACK;

[0323] Step S813: The user integrates the coded data received multiple times.

[0324] The following is an example of image semantic transmission:

[0325] First, the model in the embodiment of the present application is trained on the COCO-stuff training set. During the training process, channel noise is not considered. The batch size is 8, the image resolution is 256, and the number of training rounds is 10. The Adam optimizer is used, and the learning rate is set to 1×10 -4 .

[0326] In order to maximize the quality of the reconstructed image, the optimization objective uses the mean square error (MSE) as the main loss function, see formula (6):

[0327]

[0328] In formula (6), x i and Represent the pixel values ​​of the original image and the reconstructed image respectively.

[0329] However, relying on this loss function alone is not enough because the entropy model cannot be effectively trained. To solve this problem, another loss function is introduced to minimize the encoding entropy, see formula (7):

[0330]

[0331] Therefore, the total loss function is as follows:

[0332] loss = l mse +λl entropy (8);

[0333] In formula (8), λ controls the trade-off between MSE loss and entropy. This hyperparameter is set to 1×10 -4 , and remains unchanged during training.

[0334] Compare the simulation results of the present application and the related technical solutions. Fig. 9 and Fig.10 As shown, from Fig. 9 It can be seen that when the SNR is below 10dB, the image transmission success rate of the present application solution is much better than that of the related technical solutions; Fig.10 It can be seen that the throughput of the solution of the present application is also better than that of the related technical solutions under various SNRs.

[0335] In the embodiment of the present application, according to the second mutual information of each coded data in the first coding sequence, target coded data that is more important to the receiving end is selected, and the target coded data and the corresponding position information are sent to the receiving end, and when the receiving end fails to receive the target coded data, the receiving end sends feedback information to the sending end so that the sending end resends the target coded data. In this way, by analyzing the size of the second mutual information of each coded data, the coded data that is more urgently needed by the receiving end is selected. On the one hand, the transmission of redundant information is reduced and the utilization of channel resources is optimized. On the other hand, the reliability of the second communication device receiving information can be improved.

[0336] The present application embodiment provides a first communication device, such as Figure 1 As shown, the first communication device 10 includes a first transceiver 11; and

[0337] A first processor 12 is coupled to the first transceiver 11; the first processor 12 is configured to:

[0338] Performing semantic encoding on the first data to obtain a first encoding sequence; the first encoding sequence includes at least one encoding data;

[0339] Determining at least one target encoding data from the first encoding sequence;

[0340] transmitting the at least one target encoded data to a second communication device via the first transceiver;

[0341] The position information is sent to the second communication device via the first transceiver; the position information is used to indicate the position of the at least one target coded data in the first coding sequence.

[0342] In some embodiments, the first processor is configured to:

[0343] First mutual information is sent to the second communication device via the first transceiver; the first mutual information is mutual information expected to be received by the second communication device based on the first coding sequence.

[0344] In some embodiments, the first processor is configured to:

[0345] The at least one target coded data is determined from the first coded sequence based on the first mutual information and second mutual information of each coded data in the first coded sequence, wherein the second mutual information is predicted mutual information of the coded data received by the second communication device.

[0346] In some embodiments, the first processor is configured to:

[0347] Determine fourth mutual information based on the first mutual information and the third mutual information, wherein the third mutual information is the mutual information that the second communication device has received based on the first coding sequence, and the fourth mutual information is the mutual information expected to be sent;

[0348] Based on the fourth mutual information and the second mutual information of each of the coded data in the first coded sequence, the at least one target coded data is determined from the first coded sequence.

[0349] In some embodiments, the first processor is configured to:

[0350] Determining a first information entropy of the coded data, the first information entropy being a predicted information entropy of the coded data received by a second communication device;

[0351] Based on the first information entropy of the encoded data, second mutual information of the encoded data is determined.

[0352] In some embodiments, the first processor is configured to:

[0353] When the coded data is determined to be transmitted for the Nth time, predicting a second information entropy of the coded data when it is transmitted for the Nth time;

[0354] Based on the difference between the second information entropy and the third information entropy, a first information entropy of the coded data is determined; the third information entropy is the predicted second information entropy of the coded data in the N-1th transmission case.

[0355] In some embodiments, the first processor is configured to:

[0356] Based on the first probability distribution of the encoded data and the probability distribution of channel noise when the encoded data is transmitted for the Nth time, the second information entropy of the encoded data when it is transmitted for the Nth time is determined, wherein the first probability distribution is the probability distribution of the encoded data when no information is lost.

[0357] In some embodiments, the first processor is configured to:

[0358] Determine, based on the probability distribution of the channel noise, a fourth information entropy corresponding to the coded data, where the fourth information entropy is the information entropy of the channel noise when the coded data is transmitted for the Nth time;

[0359] Based on the first information entropy and the fourth information entropy, second mutual information of the encoded data is determined.

[0360] In some embodiments, the first processor is configured to:

[0361] For each coded data in the first coding sequence, determine fifth mutual information of the coded data, where the fifth mutual information is the mutual information of the coded data sent by the first communication device;

[0362] The first mutual information is determined based on a sum of fifth mutual information of each of the encoded data in the first encoded sequence and a first threshold.

[0363] In some embodiments, the first processor is configured to:

[0364] Feedback information sent by the second communication device is received via the first transceiver, where the feedback information is used to indicate whether the first coding sequence is received successfully.

[0365] In some embodiments, the first processor is configured to:

[0366] In response to the feedback information indicating that the first coding sequence was not successfully received, determining the at least one target coding data from the first coding sequence;

[0367] Wherein, when the feedback information indicates that the first coding sequence is not received successfully, the feedback information further includes: third mutual information, where the third mutual information is the mutual information that the second communication device has received based on the first coding sequence.

[0368] The embodiment of the present application provides a second communication device 30, wherein the second communication device 30 includes a second transceiver 31; and

[0369] A second processor 32 is coupled to the second transceiver 31; the second processor 32 is configured to:

[0370] Receiving, via the second transceiver, at least one target coded data and position information in a first coded sequence sent by a first communication device; the position information is used to indicate a position of the at least one target coded data in the first coded sequence;

[0371] Based on the position information, the at least one target coded data is integrated to obtain a second coded sequence, and the second coded sequence is used to restore the first data based on semantic decoding.

[0372] In some embodiments, the second processor is configured to:

[0373] receiving, via the second transceiver, first mutual information sent by the first communication device, where the first mutual information is mutual information expected to be received by the second communication device based on the first coding sequence;

[0374] Determine whether the first coding sequence is successfully received based on the first mutual information.

[0375] In some embodiments, the second processor is configured to:

[0376] For each target coded data in the received target coded data, determining sixth mutual information of the target coded data based on a fifth information entropy of the target coded data and a fourth information entropy of the channel noise, wherein the fifth information entropy is the information entropy of the target coded data received by the second communication device, and the sixth mutual information is the mutual information of the target coded data received by the second communication device;

[0377] Determine third mutual information based on sixth mutual information of each target coded data in the received target coded data, wherein the third mutual information is mutual information of the second communication device based on the received target coded data;

[0378] The third mutual information is compared with the first mutual information to determine whether the first coding sequence is received successfully.

[0379] In some embodiments, the second processor is configured to:

[0380] Based on the second probability distribution of the target coded data, the probability distribution of channel noise and the number of transmissions M of the target coded data, the fifth information entropy of the target coded data is determined, wherein the second probability distribution is the probability distribution of the target coded data under information loss.

[0381] In some embodiments, the second processor is configured to:

[0382] Feedback information is sent to the first communication device via the second transceiver, where the feedback information is used to indicate whether the first coding sequence is received successfully.

[0383] In some embodiments, the second processor is configured to:

[0384] Feedback information is sent to the first communication device via the second transceiver, where the feedback information is used to indicate whether the first coding sequence is received successfully.

[0385] It should be noted that in the embodiment of the present application, if the above-mentioned wireless communication method is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, which is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a U disk, a mobile hard disk, a read-only memory (ROM), a disk or an optical disk. In this way, the embodiment of the present application is not limited to any specific combination of hardware and software.

[0386] In the fifth aspect, in order to implement the above-mentioned wireless communication method, an embodiment of the present application provides an electronic device, including a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the program, it implements the steps in the wireless communication method provided in the above-mentioned embodiment.

[0387] In a sixth aspect, an embodiment of the present application provides a storage medium, that is, a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps in the wireless communication method provided in the above embodiment are implemented.

[0388] It should be noted here that the description of the above storage medium and device embodiments is similar to the description of the above method embodiments, and has similar beneficial effects as the method embodiments. For technical details not disclosed in the storage medium and device embodiments of this application, please refer to the description of the method embodiments of this application for understanding.

[0389] It should be understood that "one embodiment" or "an embodiment" mentioned throughout the specification means that specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in some embodiments" appearing throughout the specification may not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in various embodiments of the present application, the size of the sequence number of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present application. The above-mentioned sequence numbers of the embodiments of the present application are for description only and do not represent the advantages and disadvantages of the embodiments.

[0390] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0391] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0392] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0393] In addition, all functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may be a separate unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0394] A person skilled in the art can understand that all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM), magnetic disks or optical disks, etc., various media that can store program codes.

[0395] Alternatively, if the above-mentioned integrated unit of the present application is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application can be essentially or partly embodied in the form of a software product that contributes to the relevant technology. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROMs, magnetic disks, or optical disks.

[0396] The above is only an implementation method of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A first communication device, the first communication device comprising a first transceiver; and a first processor coupled to the first transceiver; the first processor being configured to: Performing semantic encoding on the first data to obtain a first encoding sequence; the first encoding sequence includes at least one encoding data; Determining at least one target encoding data from the first encoding sequence; transmitting the at least one target encoded data to a second communication device via the first transceiver; The position information is sent to the second communication device via the first transceiver; the position information is used to indicate the position of the at least one target coded data in the first coding sequence.

2. The first communication device according to claim 1, wherein the first processor is configured to: First mutual information is sent to the second communication device via the first transceiver; the first mutual information is mutual information expected to be received by the second communication device based on the first coding sequence.

3. The first communication device of claim 2, wherein the first processor is configured to: The at least one target coded data is determined from the first coded sequence based on the first mutual information and second mutual information of each coded data in the first coded sequence, wherein the second mutual information is predicted mutual information of the coded data received by the second communication device.

4. The first communication device according to claim 3, wherein the first processor is configured to: Determine fourth mutual information based on the first mutual information and the third mutual information, wherein the third mutual information is the mutual information that the second communication device has received based on the first coding sequence, and the fourth mutual information is the mutual information expected to be sent; Based on the fourth mutual information and the second mutual information of each of the coded data in the first coded sequence, the at least one target coded data is determined from the first coded sequence.

5. The first communication device according to claim 3, wherein the first processor is configured to: Determining a first information entropy of the coded data, the first information entropy being a predicted information entropy of the coded data received by a second communication device; The second mutual information of the encoded data is determined based on the first information entropy of the encoded data.

6. The first communication device according to claim 5, wherein the first processor is configured to: When the coded data is determined to be transmitted for the Nth time, predicting a second information entropy of the coded data when it is transmitted for the Nth time; Based on the difference between the second information entropy and the third information entropy, a first information entropy of the coded data is determined; the third information entropy is the predicted second information entropy of the coded data in the N-1th transmission case.

7. The first communications device of claim 5, wherein the first processor is configured to: Determine, based on the probability distribution of the channel noise, a fourth information entropy corresponding to the coded data, where the fourth information entropy is the information entropy of the channel noise of the coded data when the coded data is transmitted for the Nth time; Based on the first information entropy and the fourth information entropy, second mutual information of the encoded data is determined.

8. The first communication device according to any one of claims 2 to 7, wherein the first processor is configured to: For each coded data in the first coding sequence, determine fifth mutual information of the coded data, where the fifth mutual information is the mutual information of the coded data sent by the first communication device; The first mutual information is determined based on a sum of fifth mutual information of each of the encoded data in the first encoded sequence and a first threshold.

9. The first communication device according to any one of claims 1 to 7, wherein the first processor is configured to: Feedback information sent by the second communication device is received via the first transceiver, where the feedback information is used to indicate whether the first coding sequence is received successfully.

10. A second communication device, the second communication device comprising a second transceiver; and a second processor coupled to the second transceiver; the second processor being configured to: Receiving, via the second transceiver, at least one target coded data and position information in a first coded sequence sent by a first communication device; the position information is used to indicate a position of the at least one target coded data in the first coded sequence; Based on the position information, the at least one target coded data is integrated to obtain a second coded sequence, and the second coded sequence is used to restore the first data based on semantic decoding.

Images