Semantic communication method, device and system, electronic equipment and computer storage medium

Abstract

The invention provides a semantic communication method and device, and relates to the technical field of communication, in particular to the technical fields of large models, deep learning, diversity processing and the like. The specific implementation scheme is as follows: acquiring information source data; based on the information source data, determining a semantic coding symbol sequence and an importance sorting sequence number of semantic coding symbols in the semantic coding symbol sequence; based on the importance sorting sequence number and the semantic coding symbol sequence, obtaining a target coding symbol sequence; and transmitting the target coding symbol sequence to a receiving end through different independent fading paths, so that the receiving end obtains target data corresponding to the information source data.

Description

Technical Field

[0001] The present disclosure relates to the field of computers, specifically to technical fields such as large models, deep learning, and diversity processing, and in particular to a semantic communication method and device, a semantic communication system, an electronic device, a computer-readable storage medium, and a computer program product. Background Art

[0002] Traditional communication systems treat coded symbols as equal when transmitting signals, and focus on the accurate transmission of coded symbols from transmitter to receiver. However, task-oriented semantic communication focuses on the semantic information carried in coded symbols.

[0003] The goal of semantic communication systems is to transmit semantic information, but semantic errors may occur during signal transmission, especially under low signal-to-noise ratio conditions, where noise has a greater impact on semantic symbols and will seriously affect the semantic recovery performance at the receiver. Summary of the invention

[0004] The present disclosure provides a semantic communication method and apparatus, a semantic communication system, an electronic device, a computer-readable storage medium, and a computer program product.

[0005] According to a first aspect, a semantic communication method is provided, which includes: obtaining source data; determining a semantic coding symbol sequence and an importance ranking number of the semantic coding symbols in the semantic coding symbol sequence based on the source data; obtaining a target coding symbol sequence based on the importance ranking number and the semantic coding symbol sequence; transmitting the target coding symbol sequence to a receiving end through different independent fading paths, so that the receiving end obtains target data corresponding to the source data.

[0006] According to a second aspect, another semantic communication method is provided, which includes: receiving a target coding symbol sequence transmitted through different independent fading paths; merging first semantic coding symbols with the same semantics in the target coding symbol sequence; obtaining an intermediate coding symbol sequence based on the first semantic coding symbol and a second semantic coding symbol that does not have the same semantics in the semantic coding symbol sequence; and obtaining target data corresponding to the source data based on the intermediate coding symbol sequence and the first semantic coding symbol.

[0007] According to a third aspect, a semantic communication device is provided, which includes: an acquisition unit configured to acquire source data; a determination unit configured to determine a semantic coding symbol sequence and an importance ranking number of the semantic coding symbols in the semantic coding symbol sequence based on the source data; a obtaining unit configured to obtain a target coding symbol sequence based on the importance ranking number and the semantic coding symbol sequence; and a transmission unit configured to transmit the target coding symbol sequence to a receiving end through different independent fading paths, so that the receiving end obtains target data corresponding to the source data.

[0008] According to a fourth aspect, another semantic communication device is provided, which includes: a receiving unit configured to receive a target coding symbol sequence transmitted through different independent fading paths; a merging unit configured to merge semantic coding symbols with the same semantics in the target semantic coding symbol sequence; a combining unit configured to obtain an intermediate coding symbol sequence based on a first semantic coding symbol and a second semantic coding symbol that does not have the same semantics in the target coding symbol sequence; and a restoring unit configured to obtain target data corresponding to the source data based on the intermediate coding symbol sequence and the first semantic coding symbol.

[0009] According to a fifth aspect, a semantic communication system is provided, which includes: a receiving end and a transmitting end; the transmitting end is used to obtain source data; based on the source data, determine the semantic coding symbol sequence and the importance ranking number of the semantic coding symbols in the semantic coding symbol sequence; based on the importance ranking number and the semantic coding symbol sequence, obtain a target coding symbol sequence; transmit the target coding symbol sequence to the receiving end through different independent fading paths; the receiving end is used to receive the target coding symbol sequence transmitted through different independent fading paths; merge the first semantic coding symbols with the same semantics in the target coding symbol sequence; based on the first semantic coding symbol and the second semantic coding symbol that does not have the same semantics in the target coding symbol sequence, obtain an intermediate coding symbol sequence; based on the intermediate coding symbol sequence and the first semantic coding symbol, obtain the target data corresponding to the source data.

[0010] According to the sixth aspect, an electronic device is provided, which includes: at least one processor; and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method described in any implementation of the first aspect or the second aspect.

[0011] According to a seventh aspect, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause a computer to execute the method described in any implementation of the first aspect or the second aspect.

[0012] The semantic communication method and device provided by the embodiments of the present disclosure first obtain the source data; secondly, determine the semantic coding symbol sequence and the importance ranking number of the semantic coding symbols in the semantic coding symbol sequence based on the source data; thirdly, obtain the target coding symbol sequence based on the importance ranking number and the semantic coding symbol sequence; finally, transmit the target coding symbol sequence to the receiving end through different independent fading paths, so that the receiving end obtains the target data corresponding to the source data. Therefore, combined with the importance characteristics of the semantic coding symbols, the target coding symbol sequence is determined by reordering the semantic coding symbols and allocating resources, and the target coding symbol sequence is transmitted, so as to give priority to the reliable transmission of key information, thereby improving the information recovery performance, which is particularly suitable for environments with poor channel conditions and significantly improves the reliability and accuracy of communication.

[0013] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0015] Figure 1 is a flow chart of an embodiment of a semantic communication method according to the present disclosure;

[0016] Figure 2 It is a structural diagram of a system corresponding to the semantic communication method disclosed in the present invention;

[0017] Figure 3 It is a structural schematic diagram of a transmitting end processing and transmitting a target coding symbol sequence in the present disclosure;

[0018] Figure 4 is a flow chart of another embodiment of the semantic communication method according to the present disclosure;

[0019] Figure 5 It is a structural schematic diagram of a receiving end receiving and processing a target coding symbol sequence in the present disclosure;

[0020] Figure 6 is a structural schematic diagram of an embodiment of a semantic communication device according to the present disclosure;

[0021] Figure 7 is a structural schematic diagram of an embodiment of a semantic communication device according to the present disclosure;

[0022] Figure 8 is a structural schematic diagram of an embodiment of a semantic communication system according to the present disclosure;

[0023] Fig. 9 It is a block diagram of an electronic device used to implement the semantic communication method of the embodiment of the present disclosure. DETAILED DESCRIPTION

[0024] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0025] Diversity technology in wireless communications involves sending the same data over independent fading paths. Since the probability of independent fading paths experiencing deep fading at the same time is small, proper combining can reduce the fading degree of the received signal.

[0026] In traditional semantic communication systems, each semantically encoded symbol contributes to different degrees to downstream tasks, which is significantly unequal, and semantic errors may occur during diversity transmission. To address this defect, the present disclosure proposes a semantic communication method. Figure 1 A process 100 according to an embodiment of a semantic communication method of the present disclosure is shown. The semantic communication method comprises the following steps:

[0027] Step 101, obtaining source data.

[0028] In this embodiment, the source data is the data source to be transmitted to the receiving end. The source data can be in any form, such as image, text, video point cloud, etc. In particular, the source data can be channel state information (CSI). The channel state information describes the attenuation factor of the signal on each transmission path, that is, the value of each element in the channel gain matrix, such as signal scattering (Scattering), environmental fading (Fading, multipath fading or shadowing fading), distance attenuation (Power Decay of Distance) and other information.

[0029] In the technical solution of this disclosure, the collection, storage, use, processing, transmission, provision and disclosure of source data are carried out after authorization and in compliance with relevant laws and regulations. The information related to the user in the source data is the information obtained after the user's permission.

[0030] Step 102: Determine a sequence of semantic coding symbols and importance ranking numbers of the semantic coding symbols in the sequence of semantic coding symbols based on the source data.

[0031] In this embodiment, the semantic coding symbol sequence is a sequence formed by multiple semantic coding symbols, and the semantic coding symbol is a symbol obtained after semantic encoding of a single data in the source data. The above step 102 includes: performing data preprocessing on the source data to obtain processed data; performing semantic encoding on the processed data to obtain a semantic coding symbol sequence including multiple semantic coding symbols; identifying the importance of each semantic coding symbol in the semantic coding symbol sequence in the entire sequence, and obtaining the importance ranking number of each semantic coding symbol.

[0032] In this embodiment, the importance ranking number is used to characterize the semantic importance of the semantic coding symbol. The importance ranking number can be obtained by a variety of means, for example, directly calculating the information entropy of each semantic coding symbol, sorting the information entropy of all semantic coding symbols in the semantic coding symbol sequence, and obtaining the number of each semantic coding symbol as the importance ranking number.

[0033] In this embodiment, the execution subject on which the semantic communication method runs is Figure 2 The transmitting UE shown in the figure encodes the source data Hd through the encoder in the transmitting UE to obtain a semantic coding symbol sequence, and obtains a target coding symbol sequence by sorting the semantic coding symbol sequence according to importance.

[0034] Step 103, obtaining a target coding symbol sequence based on the importance sorting sequence number and the semantic coding symbol sequence.

[0035] In this embodiment, the target coding symbol sequence is a symbol sequence to be transmitted to the receiving end (which can be directly transmitted to the receiving end through a channel), and the target data representing the semantics of the source data can be obtained by decoding the target coding symbol sequence, wherein the target data can be the entire source data or data having only part of the source data.

[0036] In this embodiment, each semantic coding symbol in the semantic coding symbol sequence is sorted in descending order of importance according to the importance sorting number, and the last-positioned semantic coding symbol in the sorted semantic coding symbol sequence is removed to obtain a target coding symbol sequence.

[0037] In this embodiment, the serial number value of the importance ranking number can represent the importance degree of each semantic coding symbol. Optionally, when the importance ranking number is larger, the higher the degree of importance it represents, the importance ranking number is sorted in descending order, the post-position importance ranking number of the sorted importance ranking number is removed, and the semantic coding symbol corresponding to the sorted importance ranking number is used as the target coding sequence.

[0038] Step 104: transmit the target coded symbol sequence to the receiving end through different independent fading paths, so that the receiving end obtains the target data corresponding to the source data.

[0039] like Figure 2 As shown, the receiving end BS receives the target coded symbol sequence transmitted through different independent fading paths, processes the target coded symbol sequence, and obtains the target data Md.

[0040] In this embodiment, each target coding symbol in the target coding symbol sequence is transmitted through different independent fading paths. When there are repeated target coding symbols in the target coding symbol sequence, the effect of diversity transmission can be achieved.

[0041] In this embodiment, the diversity technology in wireless communication involves sending the same data on independent fading paths. Since the probability of independent paths experiencing deep fading at the same time is small, the fading degree of the received signal can be reduced after appropriate merging. Diversity is a method in which the receiving end performs specific processing on the fading characteristics it receives independently to reduce the fluctuation of the signal level. Diversity refers to distributed transmission and centralized reception. Distributed transmission enables the receiving end to obtain multiple statistically independent fading signals carrying the same information. Centralized reception is that the receiver merges (selects and combines) multiple statistically independent fading signals received to reduce the impact of fading.

[0042] In this embodiment, according to the principle of signal theory, if copies of the original transmitted signal with other attenuation levels are provided to the receiver, it will help to correctly judge the received signal. This method of improving the correct judgment rate of the received signal by providing multiple copies of the transmitted signal is called diversity. Diversity technology is used to compensate for fading channel losses. It usually utilizes the uncorrelated characteristics between independent samples of the same signal in a wireless propagation environment and uses certain signal merging technologies to improve the received signal.

[0043] In this embodiment, when there are multiple semantically coded symbols with the same semantics in the target coded symbol sequence, when the target coded symbols in the target coded symbol sequence are transmitted through multiple different independent fading paths, the same effect of signal diversity transmission can be achieved. Specifically, the diversity technology involves sending the same data on independent fading paths (this is the concept of diversity, which requires independent fading paths and the same data). In this embodiment, if Figure 3Each square in the target coding symbol sequence Sd shown represents a symbol. The darker the color, the higher the importance. This is special because each symbol is transmitted through an OFDM subcarrier, so each symbol is transmitted on an independent fading path, so the important symbols at the head and tail constitute the concept of diversity transmission (but in fact, the transmission method of each symbol is the same). Since diversity transmission can resist fading, the important semantic coding symbols in the target coding symbol sequence Sd transmitted by diversity transmission play a role in ensuring the transmission of important semantic symbols, thereby ensuring the overall transmission quality.

[0044] In this embodiment, based on the distribution of target coding symbols in the target coding symbol sequence, no matter what transmission mode or technology is used later, the receiving end merging can achieve the purpose of protecting important semantic coding symbols. When the transmission mode used by the target coding symbol sequence is diversity technology transmission, the diversity technology can be divided into spatial diversity, frequency domain diversity, time diversity and other diversity modes according to the different communication resources used. Generally speaking, diversity in communication refers to spatial diversity, that is, reliability is increased by transmitting the same information between different antennas, which is usually used in MIMO (Multiple-Input Multiple-Output) systems.

[0045] In this embodiment, frequency diversity can be used to transmit the target coded symbol sequence to the receiving end. Specifically, frequency diversity uses multiple different frequency subcarriers to transmit the same information, thereby reducing the impact of frequency selective fading, that is, the independent fading path is a frequency subcarrier. The frequency diversity technology here uses multiple different frequency subcarriers to transmit the same information, thereby reducing the impact of frequency selective fading. For specific implementation, refer to Figure 3 , that is, the semantic coding symbol sequence S after being encoded by the encoder E at the transmitter, selectively discards the unimportant semantic symbols at the end of the sorting, and re-inserts the semantic coding symbols corresponding to the most important subsequence (such as Figure 3 The target coded symbol sequence Sd is obtained by OFDM mapping of the target coded symbol sequence Sd through the OFDM (Orthogonal Frequency Division Multiplexing) transmitter to obtain the OFDM symbol Os. During the transmission of the OFDM symbol Os, the vacated OFDM subcarriers will be reallocated for frequency diversity transmission of the important semantic symbols that are ranked first.

[0046] In this embodiment, the receiving end is a terminal that communicates with the execution subject on which the semantic communication method runs, that is, the execution subject and the receiving end can transmit information to each other through a channel.

[0047] In this embodiment, the target data corresponding to the source data is the data obtained after the receiving end restores the target coding symbol sequence. The target data can be the source data or part of the source data. The target data has the same importance as the source data in the data transmission task and can achieve the same effect as the source data.

[0048] The semantic communication method provided by the embodiment of the present disclosure first obtains the source data; secondly, based on the source data, determines the semantic coding symbol sequence and the importance ranking number of the semantic coding symbols in the semantic coding symbol sequence; thirdly, based on the importance ranking number and the semantic coding symbol sequence, obtains the target coding symbol sequence; finally, transmits the target coding symbol sequence to the receiving end through different independent fading paths, so that the receiving end obtains the target data corresponding to the source data. Therefore, combined with the importance characteristics of the semantic coding symbols, the target coding symbol sequence is determined by reordering the semantic coding symbols and allocating resources, and the target coding symbol sequence is transmitted in a diversity manner, so as to give priority to the reliable transmission of key information, thereby improving the information recovery performance, which is particularly suitable for environments with poor channel conditions and significantly improves the reliability and accuracy of communication.

[0049] In some optional implementations of the present disclosure, the above-mentioned determination of the semantic coding symbol sequence and the importance ranking numbers of the semantic coding symbols in the semantic coding symbol sequence based on the source data includes: determining the data type based on the source data; determining the semantic space position model based on the data type; inputting the source data into the semantic space position model to obtain the semantic coding symbol sequence output by the semantic space position model and the importance ranking numbers of the semantic coding symbols in the semantic coding symbol sequence.

[0050] In this optional implementation, data types include text, image, video, point cloud and other source data types. The purpose and purpose of determining the data type is to use the semantic encoder model corresponding to the corresponding type of source for semantic encoding and to use the semantic decoder model corresponding to the corresponding type of source for semantic decoding.

[0051] In this optional implementation, the semantic space location model may include a model for processing source data of multiple data types, and the semantic space location model for processing source data of the data type may be directly obtained through the data type of the source data.

[0052] In this optional implementation, the semantic space position model is an end-to-end trained semantic encoder model based on a masked adaptive deep coding training framework. After the semantic encoder model trained under such an adaptive deep coding training framework semantically encodes the source, the formed semantic coding symbols will naturally be arranged in descending order of importance in terms of spatial position. For this reason, the semantic space position model can directly obtain the semantic coding symbol sequence and the importance ranking number of the semantic coding symbols in the semantic coding symbol sequence.

[0053] The method for determining a semantic coding symbol sequence and the importance of a semantic coding symbol sequence provided by this optional implementation method determines the data type based on source data; determines the semantic space position model based on the data type; inputs the source data into the semantic space position model to obtain the semantic coding symbol sequence output by the semantic space position model and the importance ranking number of the semantic coding symbols in the semantic coding symbol sequence. The semantic coding symbols and the importance ranking number are directly obtained by using the semantic space position model with a defined spatial distribution. The implementation is simple and convenient, and the efficiency of obtaining the semantic coding symbol sequence and the importance of the semantic coding symbol sequence is improved.

[0054] In some optional implementations of the present disclosure, the above-mentioned determination of the semantic coding symbol sequence and the importance ranking numbers of the semantic coding symbols in the semantic coding symbol sequence based on the source data includes: determining the data type based on the source data; determining the semantic encoder based on the data type; inputting the source data into the semantic encoder to obtain the semantic coding symbol sequence of the semantic output of the semantic encoder; inputting the semantic coding symbol sequence into a preset importance ranking model to obtain the importance ranking numbers of the semantic coding symbols in the semantic coding symbol sequence output by the importance ranking model.

[0055] In this optional implementation, the semantic encoder may include an encoder that performs semantic encoding for source data of multiple data types, and the encoder that processes source data of the data type may be directly obtained through the data type of the source data.

[0056] In this optional implementation, the semantic encoder can customize different encoding strategies according to different scenarios, such as sending the most accurate message, the easiest message to generate, or the message required by the receiver, etc. Similar to the transmitter in the communication principle, the semantic encoder can handle how to reduce redundancy in the message (source coding) and how to improve the reliability of transmission (channel coding).

[0057] In this optional implementation, the semantically encoded symbol sequence is input into a preset importance ranking model, which may be an entropy model, a gradient model or other neural network for measuring semantic importance.

[0058] The method for determining a semantic coding symbol sequence and the importance of a semantic coding symbol sequence provided by this optional implementation method determines the data type based on source data; determines a semantic encoder based on the data type; inputs the source data into the semantic encoder to obtain a semantic coding symbol sequence of the semantic output of the semantic encoder; inputs the semantic coding symbol sequence into a preset importance ranking model to obtain the importance ranking number of the semantic coding symbols in the semantic coding symbol sequence output by the importance ranking model, thereby providing a reliable implementation method for obtaining the semantic coding symbol sequence and the importance of the semantic coding symbol sequence.

[0059] In some optional implementations of the present disclosure, the target coding symbol sequence is obtained based on the importance sorting number and the semantic coding symbol sequence, including: determining the second most important sub-sequence number based on the importance sorting number; removing the semantic coding symbol corresponding to the second most important sub-sequence number in the semantic coding symbol sequence to obtain an intermediate coding symbol sequence; determining the most important sub-sequence number having the same number of digits as the second most important sub-sequence number based on the importance sorting number; and adding the semantic coding symbol corresponding to the most important sub-sequence number after the intermediate coding symbol sequence to obtain the target coding symbol sequence.

[0060] In this optional implementation, the less important sub-sequence number is the number of the semantic coding symbol with less importance in the importance sorting number. There can be multiple less important sub-sequence numbers, each less important sub-sequence number corresponds to a semantic coding symbol. Removing the semantic coding symbol corresponding to the less important sub-sequence number in the semantic coding symbol sequence can make the obtained target coding symbol sequence contain only semantic coding symbols with higher importance.

[0061] In this optional implementation, the most important sub-sequence number is the number of the most important semantic coding symbol in the importance sorting number. The number of most important sub-sequence numbers can be one or more, and each most important sub-sequence number corresponds to a semantic coding symbol.

[0062] In this optional implementation, the above-mentioned determining the most important subsequence number having the same number of digits as the second most important subsequence number based on the importance ranking sequence number includes: determining the number of digits as the second most important subsequence number; and determining the most important subsequence number based on the importance ranking of the importance ranking sequence number. For example, if the number of digits of the second most important subsequence number is 3, the sequence number with the highest importance among the importance ranking sequence numbers is used as the most important subsequence number.

[0063] In this optional implementation, the target coding symbol sequence is a sequence with the same length as the semantic coding symbol sequence obtained after removing and adding semantic coding symbols to the semantic coding symbol sequence. The semantic coding symbols removed and added to the semantic coding symbol sequence can be determined based on demand. Generally, semantic coding symbols that have little impact on semantic communication transmission can be removed, while semantic coding symbols that have a very large impact on semantic communication transmission need to be added again. The semantic coding symbols in the target coding symbol sequence are also coding symbols that need to be transmitted by the semantic communication method. Since the target coding symbol sequence does not have semantic coding symbols of less importance, semantic communication can be transmitted with semantic coding symbols of higher importance; and since the target coding symbol sequence has multiple semantic coding symbols of the same higher importance, when the target coding symbol sequence is transmitted through different fading paths, the effect of diversity transmission of semantic coding symbols with the same semantics can be achieved.

[0064] The method for obtaining a target coding symbol sequence provided by this optional implementation method determines the second most important sub-sequence number based on the importance sorting number; removes the semantic coding symbols corresponding to the second most important sub-sequence number in the semantic coding symbol sequence to obtain an intermediate coding symbol sequence; determines the most important sub-sequence number having the same number of digits as the second most important sub-sequence number based on the importance sorting number; and inserts the semantic coding symbol corresponding to the most important sub-sequence number after the intermediate coding symbol sequence to obtain the target coding symbol sequence, thereby providing a reliable implementation means for obtaining the target coding symbol sequence.

[0065] Optionally, the above-mentioned obtaining the target coding symbol sequence based on the importance sorting sequence number and the semantic coding symbol sequence includes: determining the high importance sub-sequence number based on the importance sorting sequence number; selecting the semantic coding symbol corresponding to the high importance sub-sequence number in the semantic coding symbol sequence as the intermediate coding symbol sequence; determining the most important semantic coding symbol based on the number of digits of the sequence number other than the high importance sub-sequence number in the importance sorting sequence number, and adding the most important semantic coding symbol after the intermediate coding symbol sequence to obtain the target coding symbol sequence. Among them, the high importance sub-sequence number is the sequence number of the semantic coding symbol with higher importance.

[0066] In some optional implementations of the present disclosure, the determining of the less important sub-sequence number based on the importance ranking number includes: determining the proportion of non-important coding symbols based on the diversity ratio; and determining the less important sub-sequence number based on the importance ranking number and the proportion.

[0067] In this optional implementation, the diversity ratio is a ratio value set by the semantic diversity module that can be adaptively adjusted according to the current channel conditions. The diversity ratio is used to control the number of important symbols for diversity transmission and is determined by the channel conditions. The worse the channel conditions, the larger the value of the diversity ratio should be to ensure the transmission of more important symbols; when the channel conditions improve, the value of the diversity ratio decreases. In this optional implementation, the proportion is the proportion of non-important coding symbols in the semantic coding symbol sequence, that is, the proportion is equal to the ratio of the number of non-important coding symbols to the number of semantic coding symbols in the semantic coding symbol sequence. When the diversity order is larger, the proportion of non-important coding symbols in the semantic coding symbol sequence is smaller; when the diversity order is smaller, the proportion of non-important coding symbols in the semantic coding symbol sequence is larger. The correspondence between the diversity order and the proportion can be obtained through a pre-calibrated calibration table, and the proportion under the current diversity order can be obtained by querying the calibration table.

[0068] In this optional implementation, the above determination of the less important sub-sequence number based on the importance sorting number and the proportion includes: in response to the importance sorting number being sorted in ascending order of importance, removing the first proportion of the sequence numbers in the importance sorting number to obtain the less important sub-sequence number.

[0069] Optionally, the above-mentioned determination of the less important sub-sequence number based on the importance sorting sequence number and the proportion further includes: in response to the importance sorting sequence number being sorted in descending order of importance, removing the last proportion of the sequence numbers in the importance sorting sequence number to obtain the less important sub-sequence number.

[0070] The method for determining the less important sub-sequence number provided by this optional implementation method determines the proportion of non-important coding symbols based on the diversity ratio, and determines the less important sub-sequence number based on the importance sorting number and the proportion, thereby providing a reliable implementation method for obtaining the less important sub-sequence number.

[0071] Figure 4 A process 400 according to another embodiment of the semantic communication method of the present disclosure is shown. The semantic communication method includes the following steps:

[0072] Step 401: Receive a target coded symbol sequence transmitted via different independent fading paths.

[0073] In this embodiment, the independent fading path is a fading channel for independently transmitting signals. During the signal transmission process, the target coding symbol sequence transmitted through different independent fading paths has multiple fading paths. The target coding symbols with the same semantics in the target coding symbol sequence can be transmitted on different fading channels. Since the same signal has different losses on different fading channels, the receiving end can merge (select and combine) multiple statistically independent fading signals received on different fading channels to reduce the impact of the fading channel.

[0074] In this embodiment, the execution subject on which the semantic communication method of the present disclosure runs may be a receiving end.

[0075] Step 402: merge first semantic coding symbols with the same semantics in the target coding symbol sequence.

[0076] In this embodiment, an appropriate merging method can be used to merge semantic coding symbols with the same semantics, wherein the merging method can be selected according to the independent fading path adopted. The above-mentioned merging of semantic coding symbols with the same semantics refers to merging semantic coding symbols that represent the same or identical content, wherein the merging method can be different based on the independent fading path method. The merging process is a traditional processing method and will not be repeated here.

[0077] like Figure 5 As shown, the OFDM receiver in the receiving end receives the OFDM symbol Os sent by the transmitting end, performs OFDM de-mapping on the OFDM symbol Os, obtains the target coded symbol sequence Sd transmitted through different independent fading paths, and obtains the received coded symbol sequence M after processing the target coded symbol sequence Sd.

[0078] Step 403: Obtain an intermediate coding symbol sequence based on the first semantic coding symbol and a second semantic coding symbol that does not have the same semantics in the target coding symbol sequence.

[0079] like Figure 5 As shown, all semantic coding symbols expanded by curly brackets in the target coding symbol sequence Sd are first semantic coding symbols. The target coding symbol sequence Sd has two identical first semantic coding symbols. The coding symbol sequence in the target coding symbol sequence Sd that directly transitions to the received coding symbol sequence M through a straight arrow is the second semantic coding symbol. The above step 403 includes: combining the first semantic coding symbol and the second semantic coding symbol according to a pre-set semantic numbering symbol sequence to obtain an intermediate coding symbol sequence.

[0080] Step 404: Obtain target data corresponding to the source data based on the intermediate coding symbol sequence and the first semantic coding symbol.

[0081] In this embodiment, the target data corresponding to the source data is the signal actually received by the receiving end. Therefore, the target data corresponding to the source data can be the source data or data equivalent to the source data. Figure 5 As shown, the target data is the data obtained after the decoder D in the receiving end decodes the received coding symbol sequence M, wherein the received coding symbol sequence M is a sequence corresponding to the semantic coding symbol sequence obtained after encoding the target coding symbol sequence Sd.

[0082] In this embodiment, the above step 403 includes: decoding the intermediate coding symbol sequence to obtain intermediate data, adding a zero value with the same number of bits as the first semantic coding symbol after the intermediate data, and obtaining target data corresponding to the source data.

[0083] Optionally, the above step 403 also includes: padding the intermediate coding symbol sequence with zeros for the same number of bits as the first semantic coding symbol to obtain a processed coding symbol sequence; and decoding the processed coding symbol sequence to obtain target data corresponding to the source data.

[0084] The semantic communication method provided in this embodiment receives a target coding symbol sequence transmitted through different independent fading paths; merges first semantic coding symbols with the same semantics in the target coding symbol sequence; obtains a target coding symbol sequence based on the first semantic coding symbol and a second semantic coding symbol that does not have the same semantics in the target coding symbol sequence; obtains target data corresponding to the source data based on the intermediate coding symbol sequence and the first semantic coding symbol, thereby providing a reliable implementation method for obtaining the target data.

[0085] In some optional implementations of the present disclosure, the above-mentioned obtaining of intermediate data corresponding to the source data based on the intermediate coding symbol sequence and the first semantic coding symbol includes: determining non-important coding symbols based on the first semantic coding symbol; splicing non-important coding symbols with the intermediate coding symbol sequence to obtain a received coding symbol sequence; and obtaining target data corresponding to the source data based on the received coding symbol sequence.

[0086] In this optional implementation, the non-important coding symbol is a symbol that needs to be filled in the intermediate coding symbol sequence, and the value obtained after decoding the symbol can help obtain the target data. The non-important coding symbol can directly set the number of bits to zero, and the non-important coding symbol can be directly filled in the intermediate coding symbol to obtain the received coding symbol sequence.

[0087] In this optional implementation, the received coding symbol sequence is a symbol sequence obtained by splicing the non-important coding symbols with the intermediate coding symbol sequence. The splicing position of the non-important coding symbols in the intermediate coding symbol sequence can be determined based on the importance ranking order of the semantic coding symbols in the intermediate coding symbol sequence. When the importance ranking order of the semantic coding symbols in the intermediate coding symbol sequence is in descending order, the non-important coding symbols are spliced ​​at the back of the intermediate coding symbol sequence to form the received coding symbol sequence; when the importance ranking order of the semantic coding symbols in the intermediate coding symbol sequence is in ascending order, the non-important coding symbols are spliced ​​at the front of the intermediate coding symbol sequence to form the received coding symbol sequence.

[0088] Optionally, the determining of the non-significant coding symbol based on the first semantic coding symbol includes: generating the non-significant coding symbol based on the distribution of the first semantic coding symbol.

[0089] Optionally, the above-mentioned determination of unimportant coding symbols based on the first semantic coding symbol includes: inputting the first semantic coding symbol into a generative AI model (such as a GAN model, a VAE model, and a Diffusion model) to obtain unimportant coding symbols generated by the generative AI model.

[0090] In this optional implementation, the above-mentioned obtaining the target data corresponding to the source data based on the received coded symbol sequence includes: decoding the received coded symbol sequence to obtain the target data corresponding to the source data. The decoding process is a process of restoring the digital data to the content it represents or converting the electrical pulse signal, optical signal, radio wave, etc. into the information, data, etc. it represents. Decoding is the process of the recipient restoring the received symbol or code to information, which corresponds to the encoding process of the target coded symbol sequence.

[0091] As a practical application of the present disclosure, Figure 3 , Figure 5 The semantic communication process of the semantic communication method in Massive MIMO CSI feedback is demonstrated. In this process, the downlink CSI is used as the source data. The specific steps are as follows:

[0092] 1) The downlink CSI data is used as the source data. The corresponding semantic coding symbol sequence S is first obtained through the semantic encoder E. The semantic codec E uses a mask-based adaptive deep coding training framework for end-to-end training, so that the semantic encoder E actively learns and naturally sorts the importance of the semantic symbols according to their spatial positions to obtain the importance sorting sequence number.

[0093] 2) According to the importance ranking sequence, the non-important coded symbols at the back are selectively discarded, and the vacated OFDM subcarriers will be reallocated for frequency diversity transmission of the important semantic symbols at the front. This means that the same important semantic symbols will be allocated to different OFDM subcarriers for transmission to enhance their reliability.

[0094] 3) Send the target coded symbol sequence to the receiving end. In this process, important semantic symbols will be transmitted with frequency diversity, using multiple subcarriers to increase the robustness of the transmission.

[0095] 4) The receiving end receives the semantic coding symbols on the subcarriers of different frequencies through the wireless channel. The receiving end combines the semantic coding symbols with the same semantics transmitted in diversity on the subcarriers of different frequencies to obtain the target coding symbol sequence.

[0096] 5) For the previously discarded non-important coding symbols, the receiving end generates them using a zero-filling method and concatenates them with the merged important semantic symbols to form a complete received coding symbol sequence M.

[0097] 6) The receiving end recovers the received coded symbol sequence M into target data corresponding to the original CSI data based on the semantic decoder D. In this way, the receiving end can obtain more reliable CSI information than the traditional method and improve the overall recovery performance of the communication system.

[0098] Through the diversity method based on semantic importance of the present invention, in the semantic communication process of Massive MIMO CSI feedback, OFDM subcarriers are used to perform frequency diversity transmission of important semantic symbols, and data received by different frequency subcarriers are merged at the receiving end, which effectively improves the recovery degree of the receiving end, especially in the case of poor channel conditions, and its advantages can be better reflected.

[0099] Further references Figure 6 As an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of a semantic communication device, which is similar to Figure 1 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0100] like Figure 6 As shown, the semantic communication device 600 provided in this embodiment includes: an acquisition unit 601, a determination unit 602, a obtaining unit 603, and a transmission unit 604. Among them, the above-mentioned acquisition unit 601 can be configured to obtain source data. The above-mentioned determination unit 602 can be configured to determine the semantic coding symbol sequence and the importance ranking number of the semantic coding symbols in the semantic coding symbol sequence based on the source data. The above-mentioned obtaining unit 603 can be configured to obtain the target coding symbol sequence based on the importance ranking number and the semantic coding symbol sequence. The above-mentioned transmission unit 604 can be configured to transmit the target coding symbol sequence to the receiving end through different independent fading paths, so that the receiving end obtains the target data corresponding to the source data.

[0101] In this embodiment, the specific processing of the acquisition unit 601, the determination unit 602, the obtaining unit 603, and the transmission unit 604 and the technical effects thereof can be referred to respectively. Figure 1 The relevant descriptions of step 101, step 102, step 103, and step 104 in the corresponding embodiment are not repeated here.

[0102] In some optional implementations of the present embodiment, the above-mentioned determination unit 602 is configured to: determine the data type based on the source data; determine the semantic space position model based on the data type; input the source data into the semantic space position model to obtain the semantic coding symbol sequence output by the semantic space position model and the importance ranking number of the semantic coding symbols in the semantic coding symbol sequence.

[0103] In some optional implementations of the present embodiment, the above-mentioned determination unit 602 is configured to: determine the data type based on the source data; determine the semantic encoder based on the data type; input the source data into the semantic encoder to obtain a semantic coding symbol sequence of the semantic output of the semantic encoder; input the semantic coding symbol sequence into a pre-set importance ranking model to obtain the importance ranking number of the semantic coding symbols in the semantic coding symbol sequence output by the importance ranking model.

[0104] In some optional implementations of the present embodiment, the obtaining unit 603 is configured to: determine the second most important sub-sequence number based on the importance sorting number; remove the semantic coding symbol corresponding to the second most important sub-sequence number in the semantic coding symbol sequence to obtain an intermediate coding symbol sequence; determine the most important sub-sequence number having the same number of bits as the second most important sub-sequence number based on the importance sorting number; and add the semantic coding symbol corresponding to the most important sub-sequence number after the intermediate coding symbol sequence to obtain a target coding symbol sequence.

[0105] In some optional implementations of this embodiment, the obtaining unit 603 is further configured to: determine the proportion of non-important coding symbols based on the diversity ratio; and determine the less important sub-sequence number based on the importance ranking number and the proportion.

[0106] The semantic communication method provided by the embodiment of the present disclosure first obtains the source data; secondly, based on the source data, determines the semantic coding symbol sequence and the importance ranking number of the semantic coding symbols in the semantic coding symbol sequence; thirdly, based on the importance ranking number and the semantic coding symbol sequence, obtains the target coding symbol sequence; finally, transmits the target coding symbol sequence to the receiving end through different independent fading paths, so that the receiving end obtains the target data corresponding to the source data. Therefore, combined with the importance characteristics of the semantic coding symbols, the target coding symbol sequence is determined by reordering the semantic coding symbols and allocating resources, and the target coding symbol sequence is transmitted in a diversity manner, so as to give priority to the reliable transmission of key information, thereby improving the information recovery performance, which is particularly suitable for environments with poor channel conditions and significantly improves the reliability and accuracy of communication.

[0107] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0108] Further references Figure 7 As an implementation of the methods shown in the above figures, the present disclosure provides another embodiment of a semantic communication device, which is similar to Figure 4 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0109] like Figure 7 As shown, the semantic communication device 700 provided in this embodiment includes: a receiving unit 701, a merging unit 702, a combining unit 703, and a restoring unit 704. Among them, the above-mentioned receiving unit 701 can be configured to receive a target coding symbol sequence transmitted through different independent fading paths. The above-mentioned merging unit 702 can be configured to merge the first semantic coding symbols with the same semantics in the target coding symbol sequence. The above-mentioned combining unit 703 can be configured to obtain a target coding symbol sequence based on the first semantic coding symbol and the second semantic coding symbol that does not have the same semantics in the target coding symbol sequence. The above-mentioned restoring unit 704 can be configured to obtain target data corresponding to the source data based on the intermediate coding symbol sequence and the first semantic coding symbol.

[0110] In this embodiment, the specific processing of the receiving unit 701, the merging unit 702, the combining unit 703, and the restoring unit 704 and the technical effects thereof can be referred to in detail. Figure 4 The relevant descriptions of step 401, step 402, step 403, and step 404 in the corresponding embodiment are not repeated here.

[0111] In some optional implementations of this embodiment, the above-mentioned restoration unit 703 is configured to: determine non-important coding symbols based on the first semantic coding symbol; splice the non-important coding symbols with the intermediate coding symbol sequence to obtain a received coding symbol sequence; and obtain target data corresponding to the source data based on the received coding symbol sequence.

[0112] Further references Figure 8 As an implementation of the methods shown in the above figures, the present disclosure provides another embodiment of a semantic communication system. Figure 1 , Figure 4 Corresponding to the method embodiment shown, the system can be specifically applied to various electronic devices.

[0113] like Figure 8As shown, the semantic communication system 800 provided in this embodiment includes: a transmitting end 801 and a receiving end 802. The transmitting end 801 is used to obtain source data; based on the source data, determine the semantic coding symbol sequence and the importance ranking number of the semantic coding symbols in the semantic coding symbol sequence; based on the importance ranking number and the semantic coding symbol sequence, obtain the target coding symbol sequence; transmit the target coding symbol sequence to the receiving end through different independent fading paths. The receiving end 802 is used to receive the target coding symbol sequence transmitted through different independent fading paths; merge the first semantic coding symbol with the same semantics in the target coding symbol sequence; obtain the target coding symbol sequence based on the first semantic coding symbol and the second semantic coding symbol that does not have the same semantics in the target coding symbol sequence; obtain the target data corresponding to the source data based on the intermediate coding symbol sequence and the first semantic coding symbol.

[0114] In this embodiment, in the semantic communication system 800, the specific processing of the sending end 801 and the technical effects thereof can be referred to in Figure 1 The corresponding embodiments of step 101, step 102, step 103, step 104; the specific processing of the receiving end 802 and the technical effects thereof can be referred to respectively. Figure 4 The relevant descriptions of step 401, step 402, and step 403 in the corresponding embodiment are not repeated here.

[0115] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0116] Fig. 9 A schematic block diagram of an example electronic device 900 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0117] like Fig. 9As shown, the device 900 includes a computing unit 901, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 902 or a computer program loaded from a storage unit 908 into a random access memory (RAM) 903. In the RAM 903, various programs and data required for the operation of the device 900 can also be stored. The computing unit 901, the ROM 902, and the RAM 903 are connected to each other via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0118] A number of components in the device 900 are connected to the I / O interface 905, including: an input unit 906, such as a keyboard, a mouse, etc.; an output unit 907, such as various types of displays, speakers, etc.; a storage unit 908, such as a disk, an optical disk, etc.; and a communication unit 909, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 909 allows the device 900 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0119] The computing unit 901 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 901 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 901 performs the various methods and processes described above, such as the semantic communication method. For example, in some embodiments, the semantic communication method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 908. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 900 via the ROM 902 and / or the communication unit 909. When the computer program is loaded into the RAM 903 and executed by the computing unit 901, one or more steps of the semantic communication method described above may be performed. Alternatively, in other embodiments, the computing unit 901 may be configured to perform the semantic communication method in any other appropriate manner (e.g., by means of firmware).

[0120] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0121] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable semantic communication device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0122] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0123] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0124] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an information server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communications network). Examples of communications networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0125] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0126] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0127] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A semantic communication method, the method comprising: Obtain source data; Determine, based on the source data, a sequence of semantic coding symbols and an order of importance of the semantic coding symbols in the sequence of semantic coding symbols; Based on the importance ranking sequence and the semantic coding symbol sequence, a target coding symbol sequence is obtained; The target coded symbol sequence is transmitted to a receiving end through different independent fading paths, so that the receiving end obtains target data corresponding to the source data.

2. The method according to claim 1, wherein: The determining, based on the source data, a sequence of semantic coding symbols and importance ranking numbers of the semantic coding symbols in the sequence of semantic coding symbols comprises: Determine a data type based on the source data; Based on the data type, determining a semantic space location model; The source data is input into the semantic space position model to obtain a semantic coding symbol sequence output by the semantic space position model and an importance ranking number of the semantic coding symbols in the semantic coding symbol sequence.

3. The method according to claim 1, wherein: The determining, based on the source data, a sequence of semantic coding symbols and importance ranking numbers of the semantic coding symbols in the sequence of semantic coding symbols comprises: Determine a data type based on the source data; Based on the data type, determining a semantic encoder; Inputting the source data into the semantic encoder to obtain a semantic encoding symbol sequence of the semantic output output by the semantic encoder; The semantic coding symbol sequence is input into a preset importance ranking model to obtain importance ranking numbers of the semantic coding symbols in the semantic coding symbol sequence output by the importance ranking model.

4. The method according to claim 1, wherein: The obtaining of a target coding symbol sequence based on the importance sorting sequence number and the semantic coding symbol sequence comprises: Based on the importance ranking sequence number, determining a less important sub-sequence number; Removing the semantic coding symbol corresponding to the less important sub-sequence number from the semantic coding symbol sequence to obtain an intermediate coding symbol sequence; Based on the importance ranking sequence number, determining the most important sub-sequence number having the same number of digits as the less important sub-sequence number; The semantic coding symbol corresponding to the most important sub-sequence number is added after the intermediate coding symbol sequence to obtain a target coding symbol sequence.

5. The method according to claim 4, wherein: The determining of the less important sub-sequence number based on the importance ranking sequence number comprises: Based on the diversity ratio, determining the proportion of unimportant coded symbols; Based on the importance ranking number and the proportion, a less important sub-number is determined.

6. A semantic communication method, the method comprising: receiving a target coded symbol sequence transmitted via different independent fading paths; Merging first semantic coding symbols having the same semantics in the target coding symbol sequence; Obtaining an intermediate coding symbol sequence based on the first semantic coding symbol and a second semantic coding symbol that does not have the same semantics in the target coding symbol sequence; Based on the intermediate coding symbol sequence and the first semantic coding symbol, target data corresponding to the source data is obtained.

7. The method according to claim 6, wherein: The obtaining, based on the intermediate coding symbol sequence and the first semantic coding symbol, target data corresponding to the source data comprises: Determining a non-significant coding symbol based on the first semantic coding symbol; splicing the non-significant coding symbols with the intermediate coding symbol sequence to obtain a received coding symbol sequence; Based on the received coded symbol sequence, target data corresponding to the source data is obtained.

8. A semantic communication device, comprising: An acquisition unit, configured to acquire source data; A determination unit, configured to determine a sequence of semantic coding symbols and importance ranking numbers of the semantic coding symbols in the sequence of semantic coding symbols based on the source data; An obtaining unit is configured to obtain a target coding symbol sequence based on the importance sorting sequence number and the semantic coding symbol sequence; The transmission unit is configured to transmit the target coded symbol sequence to a receiving end through different independent fading paths, so that the receiving end obtains target data corresponding to the source data.

9. A semantic communication device, comprising: a receiving unit configured to receive a target coded symbol sequence transmitted via different independent fading paths; a merging unit, configured to merge first semantic coding symbols having the same semantics in the target coding symbol sequence; a combining unit configured to obtain an intermediate coding symbol sequence based on the first semantic coding symbol and a second semantic coding symbol that does not have the same semantics in the target coding symbol sequence; The restoration unit is configured to obtain target data corresponding to the source data based on the intermediate coding symbol sequence and the first semantic coding symbol.

10. A semantic communication system, comprising: Receiver and sender; The sending end is used to obtain source data; Determine, based on the source data, a sequence of semantic coding symbols and an order of importance of the semantic coding symbols in the sequence of semantic coding symbols; Based on the importance sorting sequence and the semantic coding symbol sequence, a target coding symbol sequence is obtained; and the target coding symbol sequence is transmitted to a receiving end through different independent fading paths; The receiving end is used to receive a target coding symbol sequence transmitted through different independent fading paths; merge first semantic coding symbols with the same semantics in the target coding symbol sequence; obtain an intermediate coding symbol sequence based on the first semantic coding symbols and second semantic coding symbols that do not have the same semantics in the target coding symbol sequence; and obtain target data corresponding to the source data based on the intermediate coding symbol sequence and the first semantic coding symbols.

11. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 7.

12. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to enable the computer to execute the method according to any one of claims 1 to 7.

Images