Semantic communication methods, devices, electronic equipment and storage media

Abstract

This disclosure provides a semantic communication method, apparatus, electronic device, and storage medium, specifically relating to the field of semantic communication technology. The method involves: receiving superimposed features from a first user and a second user; extracting first user features and second user features from the superimposed features based on a pre-stored synchronization header sequence; restoring the original order of the first user features and second user features using a pre-stored rearrangement index to obtain sorted first user features and sorted second user features; performing data recovery on the sorted first user features and sorted second user features respectively; re-encoding and sorting the recovered data using a semantic encoder and rearrangement index corresponding to the receiving user; and then superimposing the sorted data together and sending it to the receiving end, so that the receiving user at the receiving end can recover the corresponding original image data, thereby enhancing the robustness of communication while maintaining communication accuracy.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, specifically to the field of semantic communication technology, and in particular to semantic communication methods, apparatus, electronic devices, and storage media. Background Technology

[0002] Physical layer network coding (PNC) is a technology that implements data coding at the physical layer. It allows relay nodes to directly superimpose and decode signals from different users, thereby improving the spectral efficiency of wireless communication systems. In two-way relay communication (TWRC) scenarios, PNC technology is widely used because it allows relay nodes to simultaneously receive and transmit information, reducing transmission latency and increasing system throughput. Orthogonal mode division multiple access (OMDMA) is a multi-user access technology that allows multiple users to communicate on the same time and frequency resources without interfering with each other. In TWRC systems, PNC technology can be combined with OMDMA to further improve system capacity and efficiency. OMDMA ensures the orthogonality of signals from different users, while PNC technology allows relay nodes to efficiently process these signals.

[0003] However, with the development of 6G wireless communication systems and the rise of semantic communication, existing PNC technology faces new challenges, especially in handling phase and symbol offset issues in signal transmission. These problems are particularly pronounced in high-density multi-user scenarios, potentially leading to signal distortion and affecting communication quality. Therefore, to meet the needs of semantic communication, a new solution is urgently needed to overcome the limitations of existing technologies and achieve a more efficient and robust wireless communication system. Summary of the Invention

[0004] This disclosure provides a semantic communication method, apparatus, electronic device, and storage medium.

[0005] According to one aspect of this disclosure, a semantic communication method is provided for use in a relay node, the method comprising:

[0006] The system receives superimposed features from a first user and a second user. The superimposed features include a first semantic feature and a second semantic feature. The first semantic feature is obtained by extracting semantic features from a first input image sent by the first user, rearranging the images using a preset first rearrangement index, and then adding the images to a first synchronization header sequence. The second semantic feature is obtained by extracting semantic features from a second input image sent by the second user, rearranging the images using a preset second rearrangement index, and then adding the images to a second synchronization header sequence.

[0007] Based on the pre-stored synchronization header sequence, the features corresponding to the first user and the second user are extracted from the superimposed features to obtain the features of the first user and the features of the second user.

[0008] The original order of the first user feature and the second user feature is restored using a pre-stored rearrangement index, resulting in the sorted first user feature and the sorted second user feature.

[0009] Data recovery is performed on the sorted first user features and the sorted second user features respectively. The recovered data is then re-encoded and sorted using a semantic encoder and a rearrangement index corresponding to the receiving user. The sorted data is then superimposed and sent to the receiving end so that the receiving user at the receiving end can recover the corresponding original image data.

[0010] According to another aspect of this disclosure, a semantic communication method is provided, applied at a sending end, the method comprising:

[0011] Obtain the first input image sent by the first user and the second input image sent by the second user;

[0012] Semantic features are extracted from the first input image, and the extracted features are rearranged using a preset first rearrangement index and then added to the first synchronization header sequence to obtain the first semantic features;

[0013] Semantic features are extracted from the second input image, and the extracted features are rearranged using a preset second rearrangement index and then added to the second synchronization header sequence to obtain the second semantic features;

[0014] The first semantic feature and the second semantic feature are superimposed to obtain the superimposed feature, which is then sent to the relay node. The relay node extracts the features corresponding to the first user and the second user from the superimposed feature according to the pre-stored synchronization header sequence, thus obtaining the first user feature and the second user feature. The original order of the first user feature and the second user feature is restored using the pre-stored rearrangement index, resulting in the sorted first user feature and the sorted second user feature. Data recovery is performed on the sorted first user feature and the sorted second user feature, and the recovered data is re-encoded and sorted using the semantic encoder and rearrangement index corresponding to the receiving user. The sorted data is then superimposed and sent to the receiving end so that the receiving user at the receiving end can recover the corresponding original image data.

[0015] According to a third aspect of this disclosure, a semantic communication method is provided, applied at a receiving end, the method comprising:

[0016] The system receives aliased data from a relay node. The relay node receives superimposed features from a first user and a second user. The superimposed features include a first semantic feature and a second semantic feature. The first semantic feature is obtained by extracting semantic features from a first input image sent by the first user, rearranging them using a preset first rearrangement index, and then adding a first synchronization header sequence. The second semantic feature is obtained by extracting semantic features from a second input image sent by the second user, rearranging them using a preset second rearrangement index, and then adding a second synchronization header sequence. Based on the pre-stored synchronization header sequence, features corresponding to the first user and the second user are extracted from the superimposed features to obtain first user features and second user features. The original order of the first user features and the second user features is restored using a pre-stored rearrangement index to obtain sorted first user features and sorted second user features. Data recovery is performed on the sorted first user features and the sorted second user features to obtain recovered data. The recovered data is then re-encoded and sorted using a semantic encoder and a rearrangement index corresponding to the receiving user. The sorted data is then superimposed and sent to the receiving end.

[0017] The first rearranged index is used to retrieve the data of the corresponding second user from the sorted data to obtain the second user data;

[0018] The second rearranged index is used to retrieve the data corresponding to the first user from the sorted data, thus obtaining the first user data;

[0019] The second user data is recovered using the first decoder to obtain the original image sent by the second user;

[0020] The first user data is recovered using the second decoder to obtain the original image sent by the first user.

[0021] According to a fourth aspect of this disclosure, a semantic communication method is provided, the method comprising:

[0022] The sending end acquires a first input image sent by a first user and a second input image sent by a second user; it extracts semantic features from the first input image, rearranges it using a preset first rearrangement index, and adds it to a first synchronization header sequence to obtain a first semantic feature; it extracts semantic features from the second input image, rearranges it using a preset second rearrangement index, and adds it to a second synchronization header sequence to obtain a second semantic feature; it then superimposes the first semantic feature and the second semantic feature to obtain a superimposed feature and sends it to the relay node.

[0023] The relay node receives superimposed features from a first user and a second user. Based on a pre-stored synchronization header sequence, it extracts features corresponding to the first and second users from the superimposed features, obtaining first user features and second user features. It then uses a pre-stored rearrangement index to restore the original order of the first user features and the second user features, obtaining sorted first user features and sorted second user features. It performs data recovery on the sorted first user features and the sorted second user features, and re-encodes and sorts the recovered data using a semantic encoder corresponding to the receiving user and a rearrangement index. Finally, it superimposes the sorted data and sends it to the receiving end.

[0024] The receiving end receives sorted data sent from the relay node, uses the first rearrangement index to retrieve the data corresponding to the second user, and obtains the second user data; uses the second rearrangement index to retrieve the data corresponding to the first user, and obtains the first user data; uses the second user data to perform data recovery using the first decoder, and obtains the original image sent by the second user; uses the first user data to perform data recovery using the second decoder, and obtains the original image sent by the first user.

[0025] According to a fifth aspect of this disclosure, a semantic communication apparatus is provided for use in a relay node, comprising:

[0026] The first receiving module is used to receive superimposed features from a first user and a second user. The superimposed features include a first semantic feature and a second semantic feature. The first semantic feature is obtained by extracting semantic features from a first input image sent by the first user, rearranging the images using a preset first rearrangement index, and then adding the images to a first synchronization header sequence. The second semantic feature is obtained by extracting semantic features from a second input image sent by the second user, rearranging the images using a preset second rearrangement index, and then adding the images to a second synchronization header sequence.

[0027] The extraction module is used to extract the features corresponding to the first user and the second user from the superimposed features based on the pre-stored synchronization header sequence, so as to obtain the features of the first user and the features of the second user.

[0028] The rearrangement module is used to restore the original order of the first user feature and the second user feature using a pre-stored rearrangement index, so as to obtain the sorted first user feature and the sorted second user feature.

[0029] The recovery module is used to recover data from the sorted first user features and the sorted second user features respectively, and to re-encode and sort the recovered data using a semantic encoder and a rearrangement index corresponding to the receiving user. The sorted data is then superimposed and sent to the receiving end so that the receiving user at the receiving end can recover the corresponding original image data.

[0030] According to a sixth aspect of this disclosure, a semantic communication apparatus is provided for use at a sending end, comprising:

[0031] The acquisition module is used to acquire a first input image sent by a first user and a second input image sent by a second user;

[0032] The first processing module is used to extract semantic features from the first input image, and rearrange the extracted features using a preset first rearrangement index and add them to the first synchronization header sequence to obtain the first semantic features.

[0033] The second processing module is used to extract semantic features from the second input image, and then rearrange the extracted features using a preset second rearrangement index and add them to the second synchronization header sequence to obtain the second semantic features.

[0034] The sending module is used to superimpose the first semantic feature and the second semantic feature to obtain a superimposed feature and send it to the relay node. The relay node extracts the features corresponding to the first user and the second user from the superimposed feature according to the pre-stored synchronization header sequence to obtain the first user feature and the second user feature. The original order of the first user feature and the second user feature is restored using a pre-stored rearrangement index to obtain the sorted first user feature and the sorted second user feature. Data recovery is performed on the sorted first user feature and the sorted second user feature respectively, and the recovered data is re-encoded and sorted using the semantic encoder and rearrangement index corresponding to the receiving user. The sorted data is then superimposed together and sent to the receiving end so that the receiving user at the receiving end can recover the corresponding original image data.

[0035] According to a seventh aspect of this disclosure, a semantic communication apparatus is provided for use at a receiving end, comprising:

[0036] The second receiving module is used to receive sorted data sent from a relay node. The relay node receives superimposed features from a first user and a second user. The superimposed features include a first semantic feature and a second semantic feature. The first semantic feature is obtained by extracting semantic features from a first input image sent by the first user, rearranging it using a preset first rearrangement index, and then adding a first synchronization header sequence. The second semantic feature is obtained by extracting semantic features from a second input image sent by the second user, rearranging it using a preset second rearrangement index, and then adding a second synchronization header sequence. Based on the pre-stored synchronization header sequence, features corresponding to the first user and the second user are extracted from the superimposed features to obtain first user features and second user features. The original order of the first user features and the second user features is restored using the pre-stored rearrangement index to obtain sorted first user features and sorted second user features. Data recovery is performed on the sorted first user features and the sorted second user features to obtain recovered data. The recovered data is then re-encoded and sorted using a semantic encoder and a rearrangement index corresponding to the receiving user. The sorted data is then superimposed and sent to the receiving end.

[0037] The first separation module is used to retrieve the data of the corresponding second user from the first rearranged index to obtain the second user data.

[0038] The second separation module is used to retrieve the data corresponding to the first user from the second rearranged index to obtain the first user data.

[0039] The first decoding module is used to recover the second user data using the first decoder to obtain the original image sent by the second user;

[0040] The second decoding module is used to recover the first user data using the second decoder to obtain the original image sent by the first user.

[0041] According to an eighth aspect of this disclosure, an electronic device is provided, comprising:

[0042] At least one processor; and

[0043] A memory communicatively connected to the at least one processor; wherein,

[0044] The memory stores instructions that can be executed by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the method described in any of the above technical solutions.

[0045] According to a ninth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are used to cause the computer to perform any one of the methods described above.

[0046] According to a tenth aspect of this disclosure, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the method described in any one of the above technical solutions.

[0047] This disclosure provides a semantic communication method, apparatus, device, and storage medium. The method involves receiving superimposed features from a first user and a second user. These features not only include semantic information of their respective input images but are also optimized and sorted using a pre-defined rearrangement index. A synchronization header sequence is added to the signal front-end to enhance signal synchronization. This design enables relay nodes to efficiently extract features and accurately detect synchronization headers using the synchronization header sequence, thereby accurately separating the feature signals of each user. Subsequently, the relay node uses the pre-stored rearrangement index to sort and recover the separated features. This crucial step ensures correct signal decoding, thus achieving accurate reconstruction of the original image data. Furthermore, to further improve the accuracy and reliability of data transmission, the relay node uses a semantic encoder and rearrangement index corresponding to the receiving user to re-encode and sort the recovered data. The sorted data is then superimposed and transmitted via the downlink. This process not only optimizes the performance of the bidirectional relay communication system but also significantly improves the quality and efficiency of image data recovery. In this way, this solution maintains communication accuracy while enhancing communication robustness, enabling it to remain stable in variable communication environments, thereby improving the practicality of the communication. This scheme, which integrates efficient feature extraction, accurate synchronization head detection, correct signal decoding, and high-quality image reconstruction, provides an innovative and effective communication strategy for bidirectional relay communication.

[0048] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0049] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0050] Figure 1 This is a schematic diagram of the steps of a semantic communication method in one embodiment of this disclosure;

[0051] Figure 2 This is a schematic diagram of the steps of a semantic communication method in another embodiment of this disclosure;

[0052] Figure 3 This is a schematic diagram of the steps of a semantic communication method in another embodiment of the present disclosure;

[0053] Figure 4 This is a schematic diagram of the overall process of the semantic communication method in one embodiment of this disclosure;

[0054] Figure 5 This is a workflow for data reordering and recovery using a semantic encoder and decoder and a reordering index in one embodiment of this disclosure;

[0055] Figure 6 This is a flowchart of the bidirectional relay communication system according to one embodiment of the present disclosure;

[0056] Figure 7 This is a structural block diagram of a semantic encoder according to an embodiment of the present disclosure;

[0057] Figure 8 A schematic block diagram of a semantic communication device according to an embodiment of this disclosure;

[0058] Figure 9 A schematic block diagram of a semantic communication device according to another embodiment of this disclosure;

[0059] Figure 10 A schematic block diagram of a semantic communication device in another embodiment of the present disclosure;

[0060] Figure 11 This is a block diagram of an electronic device used to implement the semantic communication method of the embodiments of this disclosure. Detailed Implementation

[0061] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0062] This disclosure provides a semantic communication method, see [link to relevant documentation] Figure 1 As shown, Figure 1 This is a schematic diagram illustrating the steps of a semantic communication method in one embodiment of this disclosure. The method is applied to a relay node and includes:

[0063] Step S101: Receive superimposed features from the first user and the second user. The superimposed features include a first semantic feature and a second semantic feature. The first semantic feature is obtained by extracting semantic features from the first input image sent by the first user, rearranging them using a preset first rearrangement index, and then adding them to the first synchronization header sequence. The second semantic feature is obtained by extracting semantic features from the second input image sent by the second user, rearranging them using a preset second rearrangement index, and then adding them to the second synchronization header sequence.

[0064] The communication strategy of this scheme aims to achieve effective data transmission between the first and second users through a relay node. Specifically, in this scheme, "overlay features" refer to a composite signal containing semantic information from two different users. This information is first obtained from their respective input images through a "semantic feature extraction" process, a technique that converts image content into transmittable data to capture key information within the image. Subsequently, each user's data is rearranged using a "preset rearrangement index," a step that optimizes transmission efficiency or meets specific communication protocol requirements by changing the original order of the data. After rearrangement, each user's data is appended with a unique "synchronization header sequence," such as the Zadoff-Chu sequence. This is a specific signal pattern used for synchronization in communication, helping the receiver accurately identify and distinguish signals from different users. Finally, these two processed semantic feature signals, namely the first and second semantic features, are overlaid to form a composite signal, which is transmitted to the relay node via a wireless channel. The relay node's task is to receive this overlay feature and extract and separate the feature signals belonging to the first and second users using pre-stored synchronization header sequence information, laying the foundation for subsequent signal processing and data recovery. This process not only improves spectrum utilization but also enhances the reliability and efficiency of communication.

[0065] Step S102: Extract the features corresponding to the first user and the second user from the superimposed features based on the pre-stored synchronization header sequence to obtain the features of the first user and the features of the second user.

[0066] Specifically, a "synchronization header sequence" refers to a specific pattern of signal appended before user data transmission. It possesses excellent autocorrelation properties and helps relay nodes identify and distinguish the signal start points of different users. The implementation process involves the relay node receiving superimposed features from the first and second users. It then uses pre-stored synchronization header sequence information—specific synchronization headers pre-installed in each user's signal—to identify and extract the feature signals belonging to the first and second users. This extraction process involves analyzing the superimposed signal. By calculating the correlation between the signal and the known synchronization header sequence, the relay node can accurately locate the start position of each user's signal. Subsequently, based on this positional information, the relay node separates the feature signals of the first and second users from the superimposed signal, namely, the "first user feature" and the "second user feature." These feature signals contain crucial information about the user's original data and are the foundation for subsequent signal processing and data recovery. In this way, this scheme achieves effective signal separation and extraction in a multi-user environment, providing crucial support for ensuring the accuracy and reliability of data transmission.

[0067] Step S103: The original sorting of the first user feature and the second user feature is restored using the pre-stored rearrangement index, respectively, to obtain the sorted first user feature and the sorted second user feature.

[0068] Specifically, a "reordering index" refers to a predefined data mapping relationship used to reorder user data during communication to optimize transmission efficiency or meet specific signal processing requirements. In the implementation process, after the relay node separates the feature signals of the first and second users from the superimposed signal, the pre-stored reordering index ensures that in a bidirectional relay communication system, the semantic features from different users, even after being scrambled during encoding, can be accurately restored to their original order at the receiving end. This avoids semantic information interference between users, thereby improving the quality of the decoded image. This restoration operation is crucial for ensuring data integrity and accuracy because it allows the relay node to correctly decode and understand information from different users, and thus accurately send the restored feature signals to the corresponding receiving users, achieving efficient data transmission and image reconstruction. In this way, this scheme not only improves the reliability of data transmission but also enhances the flexibility and effectiveness of the communication system in managing data from different users.

[0069] Step S104: Data recovery is performed on the sorted first user features and the sorted second user features respectively. The recovered data is then re-encoded and sorted using the semantic encoder and reordering index corresponding to the receiving user. The sorted data is then superimposed and sent to the receiving end so that the receiving user at the receiving end can recover the corresponding original image data.

[0070] Specifically, "data recovery" refers to the process of restoring sorted user feature signals to the original image data, while a "semantic encoder" is a device used to convert raw image data into semantic feature signals suitable for transmission. It can extract and encode key information based on image content. A "reordering index" is a parameter used to adjust the order of data, ensuring that data is arranged in a predetermined order during transmission.

[0071] The specific implementation process of this scheme includes the following steps: First, the relay node performs data recovery on the sorted first and second user features. This step involves converting the sorted feature signals back into the original image data. Then, to ensure the data can be correctly understood by the receiving user, the relay node re-encodes the recovered data using a semantic encoder corresponding to the receiving user. Next, the relay node sorts the re-encoded data using a reordering index corresponding to the receiving user to match the decoding requirements of the receiving user. Finally, the relay node superimposes the sorted data and sends it to the receiving end via the "downlink," the communication link from the relay node to the mobile terminal. In this way, the receiving user at the receiving end can recover the corresponding original image data based on the received data and their own semantic decoder, completing the entire communication process. This scheme not only improves the accuracy and reliability of data transmission but also optimizes the data recovery and re-encoding process, making communication more efficient and secure.

[0072] This disclosure provides a semantic communication method, apparatus, device, and storage medium. The method involves receiving superimposed features from a first user and a second user. These features not only include semantic information of their respective input images but are also optimized and sorted using a pre-defined rearrangement index. A synchronization header sequence is added to the signal front-end to enhance signal synchronization. This design enables relay nodes to efficiently extract features and accurately detect synchronization headers using the synchronization header sequence, thereby accurately separating the feature signals of each user. Subsequently, the relay node uses the pre-stored rearrangement index to sort and recover the separated features. This crucial step ensures correct signal decoding, thus achieving accurate reconstruction of the original image data. Furthermore, to further improve the accuracy and reliability of data transmission, the relay node uses a semantic encoder and rearrangement index corresponding to the receiving user to re-encode and sort the recovered data. The sorted data is then superimposed and transmitted via the downlink. This process not only optimizes the performance of the bidirectional relay communication system but also significantly improves the quality and efficiency of image data recovery. In this way, this solution maintains communication accuracy while enhancing communication robustness, enabling it to remain stable in variable communication environments, thereby improving the practicality of the communication. This scheme, which integrates efficient feature extraction, accurate synchronization head detection, correct signal decoding, and high-quality image reconstruction, provides an innovative and effective communication strategy for bidirectional relay communication.

[0073] In some optional embodiments, features corresponding to the first user and the second user are extracted from the superimposed features based on a pre-stored synchronization header sequence to obtain the first user features and the second user features, including:

[0074] Obtain the pre-stored first synchronization header sequence and the pre-stored second synchronization header sequence;

[0075] Based on the correlation between the pre-stored first synchronization header sequence and the superimposed features, the position of the first synchronization header sequence is identified, and the position of the first synchronization header sequence is used as the starting position to extract features of a preset length from the superimposed features to obtain the first user features.

[0076] Based on the correlation between the pre-stored second synchronization header sequence and the superimposed features, the position of the second synchronization header sequence is identified, and the position of the second synchronization header sequence is used as the starting position to extract features of a preset length from the superimposed features to obtain the second user features.

[0077] Specifically, a "synchronization header sequence" is a special signal pattern used to help the receiving end identify and distinguish the starting points of different user signals during data transmission, while "correlation" refers to the similarity measure between two signals, used to determine the position of one signal within another. The specific process of this scheme involves the relay node first acquiring two pre-stored synchronization header sequences, corresponding to the first user and the second user, respectively. Then, the relay node uses correlation detection algorithms, such as cross-correlation or autocorrelation, to calculate the correlation between the known synchronization header sequence and the received superimposed feature signal. When the correlation reaches a peak, it indicates that the position of the corresponding synchronization header sequence has been found. Using these positions as starting points, the relay node extracts a pre-defined length of feature signal from the superimposed features. This signal contains key user information, namely the "first user feature" and the "second user feature." In this way, the relay node can accurately separate feature signals belonging to different users from the superimposed signal, laying the foundation for subsequent signal processing and data recovery. This process not only improves the accuracy of signal separation but also enhances the system's robustness to asynchronous signal transmission, thereby optimizing the performance of the bidirectional relay communication system.

[0078] In this way, by utilizing the correlation between the synchronization header sequence and the superimposed features, the starting point of each user's signal is accurately located, ensuring the extraction of feature signals of a preset length from the correct location. This method not only improves the accuracy of signal extraction but also enhances the system's anti-interference capability, as the design of the synchronization header sequence helps distinguish signals from different users in complex communication environments. Furthermore, accurate signal extraction lays a solid foundation for subsequent signal processing and data recovery, enabling relay nodes to more effectively reorder and decode semantic features, thereby recovering the original image data. Ultimately, this series of precise operations optimizes the performance of the bidirectional relay communication system, improves the reliability of data transmission and the robustness of communication, and ensures the efficiency and accuracy of communication between users.

[0079] In some optional embodiments, after obtaining the first user characteristics and the second user characteristics, the method further includes:

[0080] Remove the first synchronization header sequence and the second synchronization header sequence.

[0081] Specifically, the "synchronization header sequence" is a specific signal pattern appended to the user data to assist the receiver in signal synchronization and identification. In this scheme, the step of "removing the first and second synchronization header sequences" occurs after the relay node successfully identifies and uses these sequences to extract the features of the first and second users from the superimposed signal. The specific implementation process of this scheme includes: the relay node first locates the synchronization header sequence by calculating the correlation between the superimposed feature signal and the known synchronization header sequence. Once the location is successful, the relay node precisely removes these synchronization header sequences from the extracted user feature signal. The purpose of this is to obtain clean user data, i.e., data without any additional information for synchronization. After removing the synchronization header sequences, the relay node can further process the remaining user features, such as reordering, decoding, and data recovery, to ensure that the original image data can be accurately reconstructed and sent to the target receiving user. This step is crucial for improving communication efficiency, reducing unnecessary data transmission, and improving the accuracy of signal processing. By accurately removing the synchronization header sequences, efficient data transmission and correct decoding of the data by the receiver can be ensured, thereby optimizing the entire communication process.

[0082] By removing the first and second synchronization header sequences, the purity of the user feature signals extracted from the superimposed signals is ensured, eliminating potential interference from the synchronization header sequences and thus improving the accuracy of signal processing. Secondly, removing the synchronization header sequences reduces the amount of data that needs to be transmitted, directly improving spectrum utilization and reducing bandwidth consumption, allowing more users to share limited communication resources. Furthermore, this process simplifies subsequent signal processing because relay nodes no longer need to process synchronization-related data, thereby accelerating data processing and improving overall communication efficiency. Ultimately, this series of optimizations not only enhances communication reliability but also enables users to receive high-quality image data faster and more reliably, improving the user experience.

[0083] In some optional embodiments, the original order of the first user features and the second user features is restored using a pre-stored rearrangement index, respectively, to obtain the sorted first user features and the sorted second user features, including:

[0084] Retrieve the pre-stored first rearranged index and the pre-stored second rearranged index;

[0085] The first user features are reordered using a pre-stored first reorder index to restore the original order of the features corresponding to the first user, resulting in the sorted first user features.

[0086] The second user features are reordered using a pre-stored second rearrangement index to restore the original order of the features corresponding to the second user, resulting in the sorted second user features.

[0087] Specifically, a "reordering index" refers to a set of parameters or mappings used to guide how to restore processed data to its original order. These indexes are crucial in communication systems. Using pre-stored reordering indexes ensures that in a bidirectional relay communication system, semantic features from different users, even after being scrambled during encoding, can be accurately restored to their original order at the receiving end, thus avoiding semantic interference between users and improving the quality of the decoded image. The specific implementation process involves the relay node first acquiring two pre-stored reordering indices, namely the "first reordering index" and the "second reordering index," corresponding to the first and second users, respectively. Before users send data, their data (such as the semantic features of an image) is reordered according to their respective reordering indices to reduce interference between data, thereby improving image restoration.

[0088] When a relay node receives superimposed features from two users, it uses these pre-stored rearrangement indexes to reorder the extracted user features. Specifically, the relay node uses the "first rearrangement index" to reorder the features of the first user to restore their original order, thus obtaining the "sorted first user features." Similarly, the relay node uses the "second rearrangement index" to reorder the features of the second user to restore their original order, thus obtaining the "sorted second user features." The key to this process is that the rearrangement indexes not only help the relay node correctly identify and separate data from different users, but also ensure the integrity and accuracy of the data during transmission. In this way, even in complex multi-user communication environments, efficient data recovery and accurate signal processing can be achieved, thereby improving the overall performance and reliability of the communication system.

[0089] In this way, by acquiring and applying known first and second reordering indices, semantic information interference between users is avoided, thereby improving the quality of the decoded image. Specifically, relay nodes use these predefined indices to reorder the first and second user features extracted from the superimposed signal, thus accurately restoring the original order of each user's data. This process not only ensures the integrity and accuracy of the data, but also, through precise data reordering, enables relay nodes to more effectively perform subsequent signal processing and data recovery work, including decoding and reconstructing the original image data. The implementation of this feature significantly improves the performance of the bidirectional relay communication system, optimizes data transmission efficiency, and ultimately enhances the robustness of communication, ensuring that users receive high-quality image data, thereby improving the overall communication experience.

[0090] In some optional embodiments, data recovery is performed on the sorted first user features and the sorted second user features, respectively. The recovered data is then re-encoded and sorted using a semantic encoder corresponding to the receiving user and a reordering index. The sorted data is then superimposed and sent to the receiving end, including:

[0091] The sorted first user features and the sorted second user features are decoded respectively to obtain the decoded first user features and the decoded second user features;

[0092] The decoded first user feature is encoded using a preset second encoder and rearranged using a second rearrangement index to obtain the rearranged first user feature;

[0093] The decoded second user features are encoded using a preset first encoder and rearranged using a first rearrangement index to obtain the rearranged second user features;

[0094] The rearranged first user characteristics and the rearranged second user characteristics are superimposed and then sent to the receiving end through the downlink.

[0095] Specifically, "decoding" refers to the process of converting received encoded data back to its original form, while an "encoder" is a hardware or software tool used to convert the raw data into a format suitable for transmission. The specific process of this scheme includes the relay node first decoding the first and second user features, which have already been restored to their original order based on the rearrangement index, to reconstruct the "decoded first user features" and "decoded second user features." Then, to send this feature information to the correct receiving user, the relay node re-encodes the decoded first user features using a "preset second encoder" and rearranges them again according to the "second rearrangement index" to generate the "rearranged first user features." Similarly, the decoded second user features are encoded using a "preset first encoder" and rearranged using the "first rearrangement index" to generate the "rearranged second user features." Finally, these re-encoded and rearranged features are superimposed and sent to the receiving end via the "downlink." This series of steps ensures the accuracy and security of data during transmission, while optimizing the data transmission process, improving communication efficiency, and enabling the receiving end to correctly understand and process information from the sending end, completing the end-to-end communication process.

[0096] In this way, by decoding the sorted user features, the original data is accurately recovered from the transmitted signal. Next, the decoded features are re-encoded and rearranged using a preset encoder and rearrangement index before being superimposed. This not only optimizes the data format to meet the requirements of downlink transmission but also further ensures the correct order of data through index rearrangement, thereby improving data readability and usability. Finally, the rearranged features are sent to the receiving end via the downlink, enabling the receiving user to receive and parse the data unambiguously. This feature combination achieves efficient data recovery and accurate signal transmission, reducing the need for retransmissions due to data errors or out-of-order delivery, saving communication resources, and improving communication reliability and user experience. Furthermore, this method enhances the system's flexibility, adapting to the needs of different users and different communication environments, providing an efficient and reliable solution for multi-user communication.

[0097] In some optional embodiments, the method further includes, before receiving the superimposed features from the first user and the second user:

[0098] Receive the first encoder, first decoder, first rearranged index, and first synchronization header sequence sent by the first user;

[0099] Receive the second encoder, second decoder, second rearranged index, and second synchronization header sequence sent by the second user.

[0100] Specifically, "encoder" and "decoder" are devices or algorithms used for data conversion, responsible for converting raw data (such as images) into a format suitable for transmission (encoding) and restoring received data to its original format (decoding), respectively. "Reordering index" is a parameter used to guide data reordering, ensuring that data can be correctly recovered even after reordering during transmission. "Synchronization header sequence" is a specific signal pattern appended before data transmission to help the receiving end identify and synchronize signals from different users.

[0101] The specific process of this scheme includes the relay node acting as the communication hub. First, it receives a series of information from the first user, including a first encoder for data encoding, a first decoder for data decoding, a first reordering index for data reordering, and a first synchronization header sequence for signal synchronization. Similarly, the relay node also receives corresponding information from the second user: a second encoder, a second decoder, a second reordering index, and a second synchronization header sequence. This process allows the relay node to prepare and process data for each user, ensuring the accuracy and integrity of the data during transmission. The relay node uses the encoder to encode the user's raw data into a format suitable for transmission, uses the synchronization header sequence to identify and distinguish signals from different users, manages and restores the original order of the data through the reordering index, and finally uses the decoder to restore the received encoded data to its original format. This design not only improves the efficiency and reliability of data transmission but also enhances the system's flexibility and scalability, enabling the system to adapt to the needs of different users and different communication scenarios.

[0102] In this way, by receiving encoders, decoders, rearranged indexes, and synchronization header sequences from the first and second users respectively, the relay node is provided with the necessary information and tools to ensure the correct processing and forwarding of signals from different users. Specifically, receiving the first and second encoders allows the relay node to encode signals in a user-specific manner, adapting to different data characteristics and communication needs. Receiving the corresponding decoders ensures that the relay node can accurately recover the original data from the received signals. Receiving the rearranged index allows the relay node to correctly sort and reassemble data during signal transmission, maintaining data accuracy and integrity. Finally, receiving the synchronization header sequence provides the relay node with a means to synchronize signals from different users, facilitating accurate signal identification and separation in multi-user environments. Combining these features, this scheme not only improves the reliability and accuracy of communication but also optimizes data transmission efficiency and enhances system flexibility and scalability, thus providing users with a more stable and efficient communication experience.

[0103] This disclosure provides a semantic communication method, see [link to relevant documentation] Figure 2 , Figure 2 This is a schematic diagram of the steps of a semantic communication method according to another embodiment of this disclosure. The method is applied at the sending end and includes:

[0104] Step S201: Obtain the first input image sent by the first user and the second input image sent by the second user.

[0105] Specifically, "first input image" and "second input image" refer to image data generated or selected by two different users (i.e., the first user and the second user), which are the content to be transmitted during communication. The specific process of this scheme includes acquiring the first input image sent by the first user and the second input image sent by the second user at the user's sending end.

[0106] Step S202: Extract semantic features from the first input image, rearrange the extracted features using a preset first rearrangement index, and add them to the first synchronization header sequence to obtain the first semantic features.

[0107] Specifically, "semantic feature extraction" refers to the process of analyzing and extracting key visual information from the first input image. This information represents the content and meaning of the image, while the "preset first rearrangement index" is a parameter used to guide how to rearrange these extracted feature data. The "first synchronization header sequence" is a specific signal pattern used to help the receiving end identify and synchronize signals from the first user during data transmission. The specific implementation process of this scheme includes: firstly, performing semantic feature extraction on the first input image sent by the first user. This step typically involves using advanced image processing and machine learning techniques to identify important elements in the image, such as edges, textures, and objects. Next, the extracted semantic features are rearranged according to the preset first rearrangement index. This is done to optimize data transmission efficiency or meet specific communication protocol requirements. The rearranged features are then added to the first synchronization header sequence to form a complete "first semantic feature" signal, which can then be transmitted to the relay node via a wireless channel. This process not only improves the efficiency and accuracy of data transmission, but also enhances the system's anti-interference capability because the synchronization header sequence helps distinguish signals from different users in complex communication environments, ensuring correct data decoding and reconstruction. In this way, the solution achieves effective processing and transmission of image data, providing an innovative and efficient communication strategy for bidirectional relay communication systems.

[0108] Step S203: Extract semantic features from the second input image, rearrange the extracted features using a preset second rearrangement index, and add them to the second synchronization header sequence to obtain the second semantic features.

[0109] Specifically, "semantic feature extraction" is a technical process designed to identify and extract key visual elements and content information from a second input image, information that represents the semantic meaning of the image. "Preset second rearrangement index" refers to a predefined parameter or mapping used to adjust the specific order of the extracted semantic features to optimize data transmission or meet specific encoding requirements. "Second synchronization header sequence" is a special code sequence used for signal synchronization; it is added to the beginning of the user data so that the receiving end can identify and distinguish signals from different users and perform correct synchronization processing.

[0110] The specific implementation process of this scheme includes: First, semantic feature extraction is performed on the input image of the second user. This may involve using image recognition algorithms to analyze image content and extract features such as shape, color, and texture. Then, these features are rearranged using a second rearrangement index to adjust the data order, which may help improve transmission efficiency or conform to certain transmission protocols. The rearranged feature data is then added to a second synchronization header sequence to form a complete "second semantic feature" signal. This signal is then transmitted to a relay node via a wireless channel. The relay node can use the synchronization header sequence to identify the starting point of the signal and use the rearrangement index to restore the original order of the data, thereby accurately decoding and reconstructing the original image. This feature implementation not only improves the accuracy and reliability of data transmission but also enhances the synchronization capability of the signal through the use of the synchronization header sequence, enabling effective differentiation and processing of signals from different users in a multi-user environment. Furthermore, through the extraction and rearrangement of semantic features, this scheme can adapt to different communication scenarios and needs, improving the flexibility and efficiency of the communication system.

[0111] Step S204: The first semantic feature and the second semantic feature are superimposed to obtain the superimposed feature, which is then sent to the relay node. The relay node extracts the features corresponding to the first user and the second user from the superimposed feature according to the pre-stored synchronization header sequence, thus obtaining the first user feature and the second user feature. The original order of the first user feature and the second user feature is restored using the pre-stored rearrangement index, resulting in the sorted first user feature and the sorted second user feature. Data restoration is performed on the sorted first user feature and the sorted second user feature, and the restored data is re-encoded and sorted using the semantic encoder and rearrangement index corresponding to the receiving user. The sorted data is then superimposed and sent to the receiving end so that the receiving user at the receiving end can restore the corresponding original image data.

[0112] Specifically, the "first semantic feature" and "second semantic feature" refer to the signals extracted from the input images of the first and second users, respectively, and processed by rearranging and adding synchronization header sequences. The "overlay feature" refers to merging these two semantic feature signals into a composite signal to achieve shared transmission of multi-user signals on the same time-frequency resource. The specific implementation process includes: the user transmitter first extracts semantic features from its respective input image, then rearranges these features according to a preset rearrangement index, and then adds its own synchronization header sequence to form the first and second semantic features. Next, these semantic features are overlaid together to form an overlay feature, which is then transmitted to the relay node via the wireless channel.

[0113] After receiving the superimposed features, the relay node uses pre-stored synchronization header sequence information to identify and separate the feature signals belonging to the first and second users by calculating correlation, i.e., the first user features and the second user features. Then, the relay node uses the corresponding rearrangement index to sort and recover the separated features, obtaining the sorted first user features and second user features. Next, the relay node performs data recovery on the sorted features to reconstruct near-original image data. Afterward, the relay node uses the semantic encoder corresponding to the receiving user and the rearrangement index to re-encode and sort the recovered data to meet the requirements of downlink transmission. Finally, the relay node superimposes the sorted data and sends it to the receiving end via the downlink. Upon receiving this data, the user equipment at the receiving end uses its own semantic decoder and rearrangement index to further recover the corresponding original image data. This entire process not only improves spectrum utilization and communication efficiency but also ensures the accuracy and reliability of data transmission through precise synchronization header detection, feature separation, sorting recovery, and data recovery, thereby achieving efficient multi-user bidirectional relay communication.

[0114] In this process, semantic features are extracted from the input images sent by the first and second users to identify and extract key information from the images. These features are then rearranged using a pre-defined rearrangement index to optimize data transmission efficiency, and a synchronization header sequence is added to aid relay nodes in signal identification and synchronization. Next, the processed semantic features are superimposed to form superimposed features, which are then transmitted to the relay nodes via a wireless channel. Upon receiving the superimposed features, the relay nodes accurately separate the feature signals belonging to the first and second users from the superimposed signals using pre-stored synchronization header sequence information. The separated features are then sorted and restored using the corresponding rearrangement index, ensuring the original data order is preserved. Data recovery is then performed on the sorted features, including decoding and reconstructing the original image data. Finally, the relay nodes use the semantic encoder and rearrangement index corresponding to the receiving user to re-encode and sort the recovered data to meet downlink transmission requirements, and then transmit this data to the receiving end via the downlink. This combination of features improves the accuracy and reliability of data transmission, optimizes spectrum utilization and communication efficiency, enhances the system's anti-interference capabilities, and ensures that users receive high-quality raw image data through precise signal processing and synchronization mechanisms. Furthermore, this approach enhances the flexibility and scalability of the communication system, enabling it to adapt to different communication scenarios and user needs, thereby providing users with a more stable and efficient communication experience.

[0115] In some optional embodiments, before acquiring the first input image sent by the first user and the second input image sent by the second user, the method further includes:

[0116] Obtain the first random number corresponding to the first user, and arrange the first random number according to the specified rules, and obtain the first rearranged index based on the position of the sorted elements;

[0117] Obtain the second random number corresponding to the second user, and arrange the second random number according to the specified rules. Generate the second rearranged index based on the position of the sorted elements.

[0118] Specifically, "random numbers" are a set of random number sequences independently generated by each user for data reordering, while the "reordering index" is an index obtained by processing these random numbers according to a specific sorting rule, used to guide the subsequent data reordering process. The specific process of this scheme includes: first, obtaining a set of random numbers for the first user; these numbers have no specific order; then, arranging these random numbers according to a specified sorting rule (such as ascending or descending order), the order of the arranged numbers determines the order of data reordering. Based on this sorting result, a "first reordering index" is generated, reflecting the new positions of each element after reordering. Similarly, another set of random numbers is obtained for the second user, and the same arranging and indexing process is performed to obtain a "second reordering index."

[0119] This method, based on random numbers and reordered indexes, allows each user's data to be rearranged in a unique order before transmission. This facilitates data differentiation and processing in multi-user environments, enhancing the flexibility and reliability of data transmission. Furthermore, using random numbers to generate the reordered index increases the randomness and unpredictability of the data, thereby improving communication security. When a relay node receives the reordered data, it can restore the original data order using the pre-shared reordered index, avoiding semantic information interference between users and improving the quality of the decoded image. This process not only optimizes the data transmission flow but also provides key technical support for achieving efficient bidirectional relay communication.

[0120] In this way, by obtaining random numbers corresponding to the first and second users and arranging them according to specified rules, first and second rearrangement indexes are generated. This method ensures that each user's data can be rearranged in a unique order before transmission, thereby improving data distinguishability and processing accuracy in a multi-user environment. Secondly, the rearrangement indexes generated based on random numbers increase the randomness and unpredictability of the data, which helps improve communication security and prevent potential data leakage or unauthorized access. In addition, the use of this index also optimizes the data transmission process, enabling relay nodes to accurately restore the original order of the data based on the pre-shared rearrangement index, ensuring correct data decoding and processing. Ultimately, the combination of these features not only improves the reliability and efficiency of communication but also enhances the system's flexibility and scalability, enabling it to adapt to different communication scenarios and user needs, providing users with a more stable and efficient communication experience.

[0121] In some optional embodiments, after obtaining the first and second rearranged indices, the method further includes:

[0122] Obtain the first synchronization header sequence and the second synchronization header sequence;

[0123] Obtain the first encoder, the first decoder, the second encoder, and the second decoder;

[0124] The first synchronization header sequence, the second synchronization header sequence, the first encoder, the first decoder, the second encoder and the second decoder, the first rearranged index and the second rearranged index are uploaded to the relay node.

[0125] Specifically, the "synchronization header sequence" is a specific pattern of signals used for signal synchronization, helping relay nodes identify and distinguish signals from different users. The "encoder" and "decoder" are key components of a communication system; the encoder converts raw data (such as images) into a format suitable for transmission, while the decoder restores the received encoded data back to its original form. The "reordering index" is a parameter used for data reordering, ensuring that data can be correctly recovered even after reordering during transmission.

[0126] The specific process of this scheme includes: First, acquiring two sets of synchronization header sequences, corresponding to the first and second users respectively, and two sets of encoders and decoders, each set used to process data from different users. Next, these synchronization header sequences, encoders, decoders, and pre-generated first and second rearrangement indices are uploaded to the relay node. The relay node, acting as the communication hub, uses this information to process and forward data from different users.

[0127] In this way, by acquiring and uploading the synchronization header sequences, encoders, decoders, and reordering indexes of the first and second users to the relay node, the use of the synchronization header sequence greatly improves the synchronization accuracy of the signal. This allows the relay node to accurately identify and distinguish the signals of different users, thereby reducing confusion and errors in the signal processing process. Secondly, the acquisition and uploading of the encoder and decoder provides the relay node with the necessary tools to ensure the integrity and correctness of the data during transmission, while also enabling the data to be adapted to the specific needs of the receiving user. Furthermore, the uploading of the reordering index allows the relay node to correctly sort and reorganize user data, accurately restoring the original data order even if the order is disordered during data transmission. Combining these features, this solution not only optimizes the data transmission process and improves the reliability and efficiency of communication, but also enhances the system's flexibility and scalability, enabling it to adapt to different communication scenarios and user needs, providing users with a more stable and efficient communication experience.

[0128] This disclosure provides a semantic communication method, see [link to relevant documentation] Figure 3 , Figure 3 This is a schematic diagram of the steps of a semantic communication method in another embodiment of the present disclosure. The method is applied at a receiving end and includes:

[0129] Step S301: Receive sorted data sent from the relay node. The relay node receives superimposed features from the first user and the second user. The superimposed features include a first semantic feature and a second semantic feature. The first semantic feature is obtained by extracting semantic features from the first input image sent by the first user, rearranging them using a preset first rearrangement index, and then adding a first synchronization header sequence. The second semantic feature is obtained by extracting semantic features from the second input image sent by the second user, rearranging them using a preset second rearrangement index, and then adding a second synchronization header sequence. Extract the features corresponding to the first user and the second user from the superimposed features according to the pre-stored synchronization header sequence to obtain the first user features and the second user features. Restore the original order of the first user features and the second user features using the pre-stored rearrangement index to obtain the sorted first user features and the sorted second user features. Perform data recovery on the sorted first user features and the sorted second user features to obtain the recovered data. Re-encode and sort the recovered data using the semantic encoder and rearrangement index corresponding to the receiving user, and then superimpose the sorted data together and send it to the receiving end.

[0130] Specifically, "relay nodes" play a crucial role in the communication system, responsible for receiving, processing, and forwarding data from different users. "Overlay features" refer to combining signals from the first and second users into a single composite signal for transmission over the same communication resource. "First semantic features" and "second semantic features" are extracted from the input images of the first and second users, respectively; these features contain key information about the images, such as shape, color, and texture.

[0131] The specific implementation process of this scheme includes: First, the first and second users perform "semantic feature extraction" on their respective input images. This is a process that uses image processing and machine learning techniques to identify and extract important elements from an image. The extracted semantic features are then rearranged according to preset "first rearrangement index" and "second rearrangement index," which are used to optimize data transmission or meet specific encoding requirements. The rearranged features are then added to corresponding "synchronization header sequences," which are used to help relay nodes identify and synchronize signals from different users.

[0132] Once the relay node receives the overlaid features, it uses pre-stored synchronization header sequence information to identify and separate the feature signals belonging to the first user and the second user, i.e., the first user features and the second user features. Then, the relay node uses the corresponding rearrangement index to sort and restore these features, avoiding semantic information interference between users. Next, the relay node performs "data recovery" on the sorted features, which may include decoding, denoising, and other operations to restore image data close to the original.

[0133] Finally, the relay node uses a semantic encoder corresponding to the receiving user and a reordering index to re-encode and reorder the recovered data to meet the requirements of downlink transmission. This re-encoded and reordered data, i.e., the "ordered data," is then superimposed and sent to the receiving end via the downlink. After receiving this data, the user equipment at the receiving end uses its own semantic decoder and reordering index to further recover the corresponding original image data. This entire process not only improves the accuracy and reliability of data transmission but also optimizes the efficiency and flexibility of the communication system, providing users with a more stable and efficient communication experience.

[0134] Step S302: Use the first rearrangement index to retrieve the data corresponding to the second user from the sorted data, and obtain the second user data.

[0135] Specifically, the "first reorder index" is a predefined set of parameters used to guide how to accurately extract and identify data from specific users within sorted data. This index reflects the new position of each element during the reordering process and is crucial for ensuring that data is correctly attributed to each user. "Second user data" refers to the original information or content belonging to the second user, which may have undergone encoding, reordering, or other processing steps during communication.

[0136] The specific implementation process of this scheme includes: after the relay node completes the processing of the superimposed features from the first and second users, including the removal of the synchronization header sequence, feature separation, reordering, and data recovery, it will obtain the sorted data. This data may contain information from multiple users, and further separation is needed to ensure that each user only receives the data that belongs to them.

[0137] Using the first rearrangement index, relay nodes can accurately identify and extract data belonging to the second user from the sorted data. This step is accomplished by searching for entries in the rearrangement index that correspond to the second user, indicating the specific location of the second user's data within the sorted data. In this way, relay nodes can ensure the correct attribution of data and avoid confusion or incorrect transmission of user data.

[0138] Furthermore, this process involves data security and privacy protection, as proper data extraction and attribution confirmation can prevent unauthorized access or data leakage. By using reordered indexes, this solution not only improves the accuracy and efficiency of data transmission but also enhances the security and reliability of the communication system, providing users with a safer and more efficient communication environment.

[0139] Step S303: Use the second rearranged index to retrieve the data corresponding to the first user from the sorted data to obtain the first user data.

[0140] Specifically, the "second rearrangement index" is a parameter generated and provided by the first user to guide the receiving end or relay node on how to accurately extract the data belonging to the first user from the sorted data. This index is based on specific rearrangement rules that the first user applies to its own data before sending the data, ensuring that the original data order can be restored without error even if the order changes during data transmission.

[0141] The specific implementation process of this scheme includes: After receiving the superimposed features from multiple users, the relay node uses a pre-stored synchronization header sequence to separate the features corresponding to the first and second users from these superimposed features. Subsequently, the relay node uses the first and second rearrangement indexes to sort and restore these separated features, ensuring that the original order of the data is preserved. After sorting and restoration, the relay node uses the "second rearrangement index" to extract the data corresponding to the first user from the sorted data. This step is accomplished by searching for entries in the index corresponding to the first user; these entries indicate the specific location of the first user's data in the sorted data.

[0142] In this way, relay nodes can ensure the correct attribution of data, avoiding confusion or incorrect transmission of user data. This method not only improves the accuracy and efficiency of data transmission but also enhances the system's flexibility and scalability, enabling it to adapt to different communication scenarios and user needs. Furthermore, using reordered indexes helps protect data security and privacy, preventing unauthorized access or data leakage, thus providing users with a more secure and reliable communication experience.

[0143] Step S304: The second user data is recovered using the first decoder to obtain the original image sent by the second user.

[0144] Specifically, "first decoder" refers to a decoding device or algorithm designed specifically for the first user, used to restore encoded data to its original form. "Second user data" refers to the original information or content from the second user, which may have undergone encoding, rearrangement, or other processing steps during transmission. "Data recovery" refers to the process of restoring encoded or otherwise processed data to its original form.

[0145] The specific implementation process of this scheme includes: after the relay node extracts the data corresponding to the first user from the sorted data using a second rearrangement index, it treats this data as the second user's data. To restore this data in a form that the first user can understand, the relay node uses a first decoder to decode the data, obtaining the original image sent by the second user. This process ensures that even in a multi-user environment, each user receives the correct data belonging to them. This design not only improves the accuracy and reliability of data transmission but also optimizes the efficiency of the communication system. Furthermore, this method enhances the system's flexibility and scalability, enabling it to adapt to different communication scenarios and user needs, providing users with a more stable and efficient communication experience.

[0146] Step S305: The first user data is recovered using the second decoder to obtain the original image sent by the first user.

[0147] Specifically, "first user data" refers to the raw information generated and sent by the first user, which may have undergone processing steps such as encoding, rearrangement, and the addition of synchronization header sequences to meet transmission requirements. "Second decoder" is a decoding tool or algorithm specifically designed for the second user to restore the received encoded data to its original, understandable format. "Data recovery" refers to the operation of converting encoded or encrypted data back to its original state during the decoding process.

[0148] The specific implementation process of this scheme includes: First, the relay node uses a first rearrangement index to extract the data belonging to the first user from the sorted data. This data may have been encoded and rearranged, therefore it needs to be decoded to recover it. The relay node then uses a second decoder to decode the first user's data. This decoder corresponds to the second user's encoder and can correctly reconstruct the data, thus obtaining the original image sent by the first user. This process ensures that data can be correctly transmitted and received between users, even if the data has undergone complex processing during transmission. In this way, this scheme not only improves the accuracy and reliability of data transmission but also enhances the flexibility and efficiency of the communication system. Furthermore, this method helps protect data security and privacy because only the corresponding decoder can correctly decode the data, thereby preventing unauthorized access and data leakage. Ultimately, this provides users with a secure, efficient, and reliable communication experience.

[0149] In this way, a highly efficient bidirectional communication mechanism is achieved by receiving, processing, and forwarding the superimposed features from the first and second users through relay nodes. The superimposed features include first and second semantic features that have undergone semantic feature extraction, rearrangement, and the addition of a synchronization header sequence. Relay nodes utilize pre-stored synchronization header sequences and rearrangement indexes to accurately extract and recover the features of the first and second users from the superimposed features, and then perform data recovery and re-encoding. This process not only ensures the integrity and correctness of the data but also optimizes the data transmission format and improves transmission efficiency by using semantic encoders and rearrangement indexes corresponding to the receiving users. Furthermore, relay nodes can retrieve the data corresponding to the second and first users from the sorted data based on the first and second rearrangement indexes, and then use the other party's decoder to recover the original image sent by the other party. This method not only improves the accuracy and reliability of data transmission but also enhances the system's flexibility and adaptability, enabling the system to adapt to different user needs and communication scenarios. Ultimately, this design provides users with a more stable, secure, and efficient communication experience, significantly improving the overall performance of the communication system.

[0150] The above embodiments describe in detail the processing at the sending and receiving ends. To facilitate a comprehensive understanding of the technical solution of this application, this disclosure describes the communication process of the solution as a whole. The method includes: the sending end acquiring a first input image sent by a first user and a second input image sent by a second user; extracting semantic features from the first input image, rearranging it using a preset first rearrangement index, and adding it to a first synchronization header sequence to obtain first semantic features; extracting semantic features from the second input image, rearranging it using a preset second rearrangement index, and adding it to a second synchronization header sequence to obtain second semantic features; and superimposing the first and second semantic features to obtain superimposed features, which are then sent to a relay node.

[0151] The relay node receives the superimposed features from the first user and the second user. Based on the pre-stored synchronization header sequence, it extracts the features corresponding to the first user and the second user from the superimposed features, thus obtaining the first user features and the second user features. The original order of the first user features and the second user features is restored using the pre-stored rearrangement index, resulting in the sorted first user features and the sorted second user features. The sorted first user features and the sorted second user features are then restored. The restored data is re-encoded and sorted using the semantic encoder corresponding to the receiving user and the rearrangement index, respectively. The sorted data is then superimposed and sent to the receiving end.

[0152] The receiving end receives sorted data sent from the relay node, uses a first rearrangement index to retrieve the data corresponding to the second user from the sorted data, and obtains the second user data; uses a second rearrangement index to retrieve the data corresponding to the first user from the sorted data, and obtains the first user data; uses a first decoder to recover the data from the second user data, and obtains the original image sent by the second user; uses a second decoder to recover the data from the first user data, and obtains the original image sent by the first user.

[0153] See Figure 4 , Figure 4 This is a schematic diagram of the overall process of the semantic communication method in one embodiment of this disclosure. Specifically, the process includes: First, before the communication begins, the two users (i.e., the first user and the second user) each generate a string of random numbers with a length L = 1179648. The random numbers are sorted in descending order, and the resulting indexes are the indexes index1 (also known as the first rearrangement index) and index2 (also known as the second rearrangement index) for their respective semantic information reordering.

[0154] Before communication begins, the first user and the second user upload their knowledge base information to the relay node. The first user's knowledge base includes a first semantic encoder, a first semantic decoder, a first rearranged index, and a first synchronization header sequence; the second user's knowledge base includes a second semantic encoder, a second semantic decoder, a second rearranged index, and a second synchronization header sequence.

[0155] Two users input a first input image x1 and a second input image x2, each with a size of 3×512×768. The first user transmits the image through a first semantic encoder f at the sending end. e1 Extracting first semantic features The second user uses the second semantic encoder f e2 Extracting second semantic features To reduce the resource consumption of data transmission, the system compresses semantic features, specifically by controlling the compression ratio. In this embodiment, the compression ratio of semantic features is set to 0.8, meaning that the last 20% of the extracted one-dimensional semantic features are zeroed out, thereby reducing the amount of data while retaining the main semantic information.

[0156] Next, the first user rearranges the semantic features according to the first rearranged index (i.e., index1) to obtain... The second user rearranges the semantic features based on the second rearranged index (index2) to obtain... Then each user generates their own ZC sequence as a synchronization header sequence, with a sequence length of 71. The first user embeds the first synchronization header sequence s1 into... Before The second user embeds the second synchronization header sequence s2 into... Before The first and second semantic features, after being rearranged and embedded in the synchronization header, are superimposed using physical layer network encoding. The superimposed signal is then transmitted to the relay using the same time-frequency resource. Although symbol bit offsets may occur during transmission, this system supports asynchronous signal superposition.

[0157] The relay node locates the starting position of the semantic information of two users by detecting their respective first and second synchronization header sequences, extracts semantic information of length L, and then removes the first and second synchronization header sequences to obtain... and Subsequently, the relay node restores the original order of the information based on the first and second rearrangement indices, thus obtaining... and Based on the OMDMA principle, semantic information generated by different semantic models, after being rearranged by a specific index, cannot be parsed by other semantic models. Therefore, for one user, the out-of-order information of another user will be treated as Gaussian noise and effectively filtered during the decoding process, thereby achieving accurate separation of the two users' information.

[0158] The relay node uses a pre-configured first and second semantic decoder to decode the semantic information of the two users respectively, and recover the transmitted image data. and

[0159] The relay node uses the second semantic encoder f e2 For the recovered semantic information Extracting semantic features Using the first semantic encoder f e1 For the recovered semantic information Extracting semantic features After reordering the semantic features according to the reordering index corresponding to the semantic encoder, the relay node transmits the aliased signal through the downlink. The signals are transmitted to the first user and the second user respectively. The first user recovers the received signal based on the first rearrangement index and then uses its own semantic decoder f. d1 Image data is obtained by decoding the received semantic information. The second user recovers the received signal based on the second reordering index and then uses its own second semantic decoder f. d2 Image data is obtained by decoding the received semantic information.

[0160] Regarding the reordering of the index in this scheme, it should be noted that... (See also...) Figure 5 , Figure 5This disclosure describes a workflow for data reordering and recovery using a semantic encoder and decoder, as well as a reordering index, in one embodiment. The workflow includes: a first user and a second user each generating a set of random numbers; for example, the first user generates a string of random numbers, and the second user generates a string of random numbers. Then, they sort these random numbers to generate a reordering index, resulting in a first reordering index of [4,1,3,2] and a second reordering index of [1,4,3,2].

[0161] Suppose that the first user and the second user extract semantic features from their input images using the first semantic encoder and the second semantic encoder, respectively, and assume that the initial order of the extracted features is [1,2,3,4]. Then, they reorder these features according to their respective reordering indices. The first user's features are reordered to [4,1,3,2], and the second user's features are reordered to [1,4,3,2].

[0162] The first and second users add their respective synchronization headers (s1 and s2) to the front of the rearranged features, and then transmit these signals to the relay node via the wireless channel. At the relay node, these two signals are superimposed. Upon receiving the superimposed signal, the relay node first removes the synchronization headers s1 and s2, and then extracts the feature signals belonging to the first and second users based on the position information of the synchronization headers. When the relay node performs a feature recovery operation using the rearranged indexes of the first and second users, only the first rearranged index can restore the correct original order [1,2,3,4], while using the second rearranged index results in noise. Therefore, this scheme, through this method, enables efficient data transmission and accurate data recovery even in a multi-user environment, ensuring the reliability and accuracy of communication.

[0163] See Figure 6 , Figure 6 This is a flowchart illustrating the operation of a two-way relay communication system according to one embodiment of this disclosure. The diagram shows the working principle of a two-way relay communication system involving two users (a first user and a second user) and a relay node. The detailed working principle is as follows:

[0164] The first and second users each use their respective semantic encoders (first encoder and second encoder) to extract semantic features from their input images (first input image and second input image). The extracted semantic feature signals are transmitted to a relay node via a wireless channel. At the relay node, the two signals may be affected by channel effects such as noise and fading. The figure shows the process of superimposing the two signals, where the superimposed signal contains the semantic features of both users.

[0165] Next, the relay nodes in this scheme use specific algorithms or techniques (such as Orthogonal Modular Division Multiple Access, OMDMA) to separate the superimposed signals into independent signals belonging to the first and second users. This step ensures that the data of each user can be correctly identified and processed. The separated signals are then sent to the corresponding semantic decoders (first semantic decoder and second semantic decoder) for decoding to recover the original image data.

[0166] In this way, the diagram illustrates an efficient two-way relay communication system capable of handling signals from multiple users, ensuring the correct transmission and recovery of data, and maintaining the reliability and accuracy of communication even under complex wireless channel conditions.

[0167] See Figure 7 , Figure 7 This is a block diagram of the semantic encoder in one embodiment of this disclosure. The semantic encoder of this scheme is implemented as follows: a neural network architecture consisting of an attention feature module (AF module) and a basic feature processing module (Basic block module); the AF module realizes dynamic perception and resource allocation of wireless channel conditions through a channel soft attention mechanism, and the Basic block module realizes feature dimension compression and multi-level feature extraction through multi-layer convolution. The two work in cascade to form a distributed representation of semantic features, improve the distinguishability of the feature space and reduce transmission redundancy.

[0168] Specifically, the Basic Block is the basic building block in the network, which contains a series of convolutional layers (Conv), normalization layers (such as GDN, Group Normalization), and activation functions (such as Prelude).

[0169] The AF module (short for Attention Feature Module) is an attention feature module used to enhance the network's ability to capture important features in an image. This module helps the network focus its attention on the most relevant parts of the image, thereby improving feature extraction performance.

[0170] Conv 3*3: This represents a 3x3 convolutional layer, a common layer type in convolutional neural networks, used to extract local features. Convolutional layers apply filters to the input data using a sliding window approach to identify patterns in an image.

[0171] GDN stands for Group Normalization, a normalization technique that can accelerate training and improve model stability.

[0172] Prelu: This is a parameterized ReLU (Rectified Linear Unit) activation function that allows for non-zero mapping of negative values, thus preserving some gradient information and helping to solve the "dead ReLU" problem.

[0173] Trans Conv: refers to the transposed convolution layer, which is used for upsampling operations, that is, increasing the spatial dimension of the data. It is usually used in decoders to reconstruct images.

[0174] Addition: The plus sign (⊕) in the diagram represents a skip connection, a feature of ResNet. Skip connections add the input directly to the output of the next layer, helping to alleviate the vanishing gradient problem in deep networks and promoting the flow of information.

[0175] Prelu (Sigmoid): The last layer of the network uses the Prelu activation function with Sigmoid. This can be used in the output layer to generate output values ​​between 0 and 1, which is suitable for tasks that require probabilistic outputs, such as image segmentation.

[0176] The entire network structure, through the combination of these modules and layers, achieves deep feature extraction and processing of the input image. In the encoder, these features can then be used for compression or encoding; in the decoder, these features are used to reconstruct or decode the image. The introduction of the attention module further improves the model's ability to identify important features, thereby improving the efficiency and accuracy of encoding and decoding.

[0177] The following describes an apparatus embodiment of this application, which can be used to execute the semantic communication method in the above embodiments of this application. For details not disclosed in the apparatus embodiments of this application, please refer to the embodiments of the semantic communication method described above.

[0178] This disclosure also provides a semantic communication device 800, such as Figure 8 As shown, it is applied to relay nodes and includes:

[0179] The first receiving module 801 is used to receive superimposed features from the first user and the second user. The superimposed features include a first semantic feature and a second semantic feature. The first semantic feature is obtained by extracting semantic features from the first input image sent by the first user, rearranging them using a preset first rearrangement index, and then adding them to the first synchronization header sequence. The second semantic feature is obtained by extracting semantic features from the second input image sent by the second user, rearranging them using a preset second rearrangement index, and then adding them to the second synchronization header sequence.

[0180] The extraction module 802 is used to extract the features of the first user and the second user from the superimposed features according to the pre-stored synchronization header sequence, so as to obtain the features of the first user and the features of the second user.

[0181] The rearrangement module 803 is used to restore the original order of the first user feature and the second user feature using a pre-stored rearrangement index, so as to obtain the sorted first user feature and the sorted second user feature.

[0182] The recovery module 804 is used to recover data from the sorted first user features and the sorted second user features respectively, and to re-encode and sort the recovered data using the semantic encoder and reorder index corresponding to the receiving user. The sorted data is then superimposed and sent to the receiving end so that the receiving user at the receiving end can recover the corresponding original image data.

[0183] In some optional embodiments, the extraction module 802 extracts features corresponding to the first user and the second user from the superimposed features based on the pre-stored synchronization header sequence, obtaining the first user features and the second user features, including:

[0184] Obtain the pre-stored first synchronization header sequence and the pre-stored second synchronization header sequence;

[0185] Based on the correlation between the pre-stored first synchronization header sequence and the superimposed features, the position of the first synchronization header sequence is identified, and the position of the first synchronization header sequence is used as the starting position to extract features of a preset length from the superimposed features to obtain the first user features.

[0186] Based on the correlation between the pre-stored second synchronization header sequence and the superimposed features, the position of the second synchronization header sequence is identified, and the position of the second synchronization header sequence is used as the starting position to extract features of a preset length from the superimposed features to obtain the second user features.

[0187] In some optional embodiments, after obtaining the first user feature and the second user feature, the extraction module 802 is further configured to:

[0188] Remove the first synchronization header sequence and the second synchronization header sequence.

[0189] In some optional embodiments, the rearrangement module 803 uses a pre-stored rearrangement index to restore the original order of the first user feature and the second user feature, respectively, to obtain the sorted first user feature and the sorted second user feature, including:

[0190] Retrieve the pre-stored first rearranged index and the pre-stored second rearranged index;

[0191] The first user features are reordered using a pre-stored first reorder index to restore the original order of the features corresponding to the first user, resulting in the sorted first user features.

[0192] The second user features are reordered using a pre-stored second rearrangement index to restore the original order of the features corresponding to the second user, resulting in the sorted second user features.

[0193] In some optional embodiments, the recovery module 804 performs data recovery on the sorted first user features and the sorted second user features, respectively, and re-encodes and sorts the recovered data using a semantic encoder corresponding to the receiving user and a reordering index, and then superimposes the sorted data together and sends it to the receiving end, including:

[0194] The sorted first user features and the sorted second user features are decoded respectively to obtain the decoded first user features and the decoded second user features;

[0195] The decoded first user feature is encoded using a preset second encoder and rearranged using a second rearrangement index to obtain the rearranged first user feature;

[0196] The decoded second user features are encoded using a preset first encoder and rearranged using a first rearrangement index to obtain the rearranged second user features;

[0197] The rearranged first user characteristics and the rearranged second user characteristics are superimposed and then sent to the receiving end through the downlink.

[0198] In some optional embodiments, the first receiving module 801 is further configured to:

[0199] Receive the first encoder, first decoder, first rearranged index, and first synchronization header sequence sent by the first user;

[0200] Receive the second encoder, second decoder, second rearranged index, and second synchronization header sequence sent by the second user.

[0201] This disclosure also provides a semantic communication device 900, such as Figure 9 As shown, it is applied to the sending end and includes:

[0202] The acquisition module 901 is used to acquire a first input image sent by a first user and a second input image sent by a second user;

[0203] The first processing module 902 is used to extract semantic features from the first input image, and rearrange the extracted features using a preset first rearrangement index and add them to the first synchronization header sequence to obtain the first semantic features.

[0204] The second processing module 903 is used to extract semantic features from the second input image, and then rearrange the extracted features using a preset second rearrangement index and add them to the second synchronization header sequence to obtain the second semantic features.

[0205] The sending module 904 is used to superimpose the first semantic feature and the second semantic feature to obtain the superimposed feature and send it to the relay node. The relay node extracts the features corresponding to the first user and the second user from the superimposed feature according to the pre-stored synchronization header sequence to obtain the first user feature and the second user feature. The original order of the first user feature and the second user feature is restored by using the pre-stored rearrangement index to obtain the sorted first user feature and the sorted second user feature. Data recovery is performed on the sorted first user feature and the sorted second user feature respectively. The recovered data is re-encoded and sorted by the semantic encoder and the rearrangement index corresponding to the receiving user. The sorted data is then superimposed together and sent to the receiving end so that the receiving user at the receiving end can recover the corresponding original image data.

[0206] In some optional embodiments, before acquiring the first input image sent by the first user and the second input image sent by the second user, the acquisition module 901 is further configured to:

[0207] Obtain the first random number corresponding to the first user, and arrange the first random number according to the specified rules, and obtain the first rearranged index based on the position of the sorted elements;

[0208] Obtain the second random number corresponding to the second user, and arrange the second random number according to the specified rules. Generate the second rearranged index based on the position of the sorted elements.

[0209] In some optional embodiments, after obtaining the first rearranged index and the second rearranged index, the acquisition module 901 is further configured to:

[0210] Obtain the first synchronization header sequence and the second synchronization header sequence;

[0211] Obtain the first encoder, the first decoder, the second encoder, and the second decoder;

[0212] The first synchronization header sequence, the second synchronization header sequence, the first encoder, the first decoder, the second encoder and the second decoder, the first rearranged index and the second rearranged index are uploaded to the relay node.

[0213] This disclosure also provides a semantic communication device 1000, such as Figure 10 As shown, it is applied to the receiving end and includes:

[0214] The second receiving module 1001 is used to receive sorted data sent from the relay node. The relay node receives superimposed features from the first user and the second user. The superimposed features include a first semantic feature and a second semantic feature. The first semantic feature is obtained by extracting semantic features from the first input image sent by the first user, rearranging it using a preset first rearrangement index, and then adding a first synchronization header sequence. The second semantic feature is obtained by extracting semantic features from the second input image sent by the second user, rearranging it using a preset second rearrangement index, and then adding a second synchronization header sequence. Based on the pre-stored synchronization header sequence, the features corresponding to the first user and the second user are extracted from the superimposed features to obtain the first user features and the second user features. The original order of the first user features and the second user features is restored using the pre-stored rearrangement index to obtain the sorted first user features and the sorted second user features. Data recovery is performed on the sorted first user features and the sorted second user features to obtain the recovered data. The recovered data is then re-encoded and sorted using the semantic encoder and the rearrangement index corresponding to the receiving user. The sorted data is then superimposed and sent to the receiving end.

[0215] The first separation module 1002 is used to obtain the data of the second user from the sorted data using the first rearrangement index, and thus obtain the second user data;

[0216] The second separation module 1003 is used to retrieve the data corresponding to the first user from the sorted data using the second rearrange index, and obtain the first user data.

[0217] The first decoding module 1004 is used to recover the second user data using the first decoder to obtain the original image sent by the second user;

[0218] The second decoding module 1005 is used to recover the first user data using the second decoder to obtain the original image sent by the first user.

[0219] The acquisition, storage, and application of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0220] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0221] Figure 11A schematic block diagram of an example electronic device 1100 that can be used to implement embodiments 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 may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0222] like Figure 11 As shown, the electronic device 1100 includes a computing unit 1101, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 1102 or a computer program loaded from a storage unit 1108 into a random access memory (RAM) 1103. The RAM 1103 may also store various programs and data required for the operation of the device 1100. The computing unit 1101, ROM 1102, and RAM 1103 are interconnected via a bus 1104. An input / output (I / O) interface 1105 is also connected to the bus 1104.

[0223] Multiple components in device 1100 are connected to I / O interface 1105, including: input unit 1106, such as keyboard, mouse, etc.; output unit 1107, such as various types of monitors, speakers, etc.; storage unit 1108, such as disk, optical disk, etc.; and communication unit 1109, such as network card, modem, wireless transceiver, etc. Communication unit 1109 allows device 1100 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0224] The computing unit 1101 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 1101 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 1101 performs the various methods and processes described above, such as semantic communication methods. For example, in some embodiments, the semantic communication method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 1108. In some embodiments, part or all of the computer program may be loaded and / or installed on device 1100 via ROM 1102 and / or communication unit 1109. When the computer program is loaded into RAM 1103 and executed by the computing unit 1101, one or more steps of the applet distribution described above may be performed. Alternatively, in other embodiments, the computing unit 1101 may be configured to perform semantic communication methods by any other suitable means (e.g., by means of firmware).

[0225] Various embodiments 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-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0226] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0227] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0228] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, 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 sound input, voice input, or tactile input).

[0229] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0230] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0231] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this disclosure can be achieved, and this is not limited herein.

[0232] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A semantic communication method applied to relay nodes, wherein, The method includes: The system receives superimposed features from a first user and a second user. The superimposed features include a first semantic feature and a second semantic feature. The first semantic feature is obtained by extracting semantic features from a first input image sent by the first user, rearranging the images using a preset first rearrangement index, and then adding the images to a first synchronization header sequence. The second semantic feature is obtained by extracting semantic features from a second input image sent by the second user, rearranging the images using a preset second rearrangement index, and then adding the images to a second synchronization header sequence. Based on the pre-stored synchronization header sequence, the features corresponding to the first user and the second user are extracted from the superimposed features to obtain the features of the first user and the features of the second user. The original order of the first user feature and the second user feature is restored using a pre-stored rearrangement index, resulting in the sorted first user feature and the sorted second user feature. Data recovery is performed on the sorted first user features and the sorted second user features respectively. The recovered data is then re-encoded and sorted using a semantic encoder and a rearrangement index corresponding to the receiving user. The sorted data is then superimposed and sent to the receiving end so that the receiving user at the receiving end can recover the corresponding original image data.

2. The method according to claim 1, wherein, The step of extracting features corresponding to the first user and the second user from the superimposed features based on the pre-stored synchronization header sequence to obtain the first user features and the second user features includes: Obtain the pre-stored first synchronization header sequence and the pre-stored second synchronization header sequence; Based on the correlation between the pre-stored first synchronization header sequence and the superimposed features, the position of the first synchronization header sequence is identified, and the position of the first synchronization header sequence is used as the starting position to extract features of a preset length from the superimposed features to obtain the first user feature; Based on the correlation between the pre-stored second synchronization header sequence and the superimposed features, the position of the second synchronization header sequence is identified, and the position of the second synchronization header sequence is used as the starting position to extract features of a preset length from the superimposed features to obtain the second user features.

3. The method according to claim 2, wherein, After obtaining the first user characteristics and the second user characteristics, the method further includes: Remove the first synchronization header sequence and the second synchronization header sequence.

4. The method according to claim 1, wherein, The step of restoring the original order of the first user features and the second user features using a pre-stored rearrangement index to obtain the sorted first user features and the sorted second user features includes: Retrieve the pre-stored first rearranged index and the pre-stored second rearranged index; The first user features are reordered using the pre-stored first rearrangement index to restore the original order of the features corresponding to the first user, resulting in the sorted first user features. The second user features are reordered using the pre-stored second rearrangement index to restore the original order of the features corresponding to the second user, resulting in the sorted second user features.

5. The method according to any one of claims 1 to 4, wherein, The process of recovering data from the sorted first user features and the sorted second user features, re-encoding and sorting the recovered data using a semantic encoder and a reordering index corresponding to the receiving user, and then combining the sorted data and sending it to the receiving end includes: The sorted first user features and the sorted second user features are decoded respectively to obtain the decoded first user features and the decoded second user features; The decoded first user feature is encoded using a preset second encoder and rearranged using the second rearrangement index to obtain the rearranged first user feature; The decoded second user feature is encoded using a preset first encoder and rearranged using the first rearrangement index to obtain the rearranged second user feature; The rearranged first user feature and the rearranged second user feature are superimposed and then sent to the receiving end via the downlink.

6. The method according to any one of claims 1 to 4, wherein, Before receiving the superimposed features from the first user and the second user, the method further includes: Receive the first encoder, first decoder, first rearranged index, and first synchronization header sequence sent by the first user; Receive the second encoder, second decoder, second rearranged index, and second synchronization header sequence sent by the second user.

7. A semantic communication method applied at the sending end, wherein, The method includes: Obtain the first input image sent by the first user and the second input image sent by the second user; Semantic features are extracted from the first input image, and the extracted features are rearranged using a preset first rearrangement index and then added to the first synchronization header sequence to obtain the first semantic features; Semantic features are extracted from the second input image, and the extracted features are rearranged using a preset second rearrangement index and then added to the second synchronization header sequence to obtain the second semantic features; The first semantic feature and the second semantic feature are superimposed to obtain the superimposed feature, which is then sent to the relay node. The relay node extracts the features corresponding to the first user and the second user from the superimposed feature according to the pre-stored synchronization header sequence, thus obtaining the first user feature and the second user feature. The original order of the first user feature and the second user feature is restored using the pre-stored rearrangement index, resulting in the sorted first user feature and the sorted second user feature. Data recovery is performed on the sorted first user feature and the sorted second user feature, and the recovered data is re-encoded and sorted using the semantic encoder and rearrangement index corresponding to the receiving user. The sorted data is then superimposed and sent to the receiving end so that the receiving user at the receiving end can recover the corresponding original image data.

8. The method according to claim 7, wherein, Before acquiring the first input image sent by the first user and the second input image sent by the second user, the method further includes: Obtain a first random number corresponding to the first user, and arrange the first random number according to a specified rule, and obtain a first rearranged index based on the position of the sorted elements; Obtain the second random number corresponding to the second user, and arrange the second random number according to the specified rules. Generate a second rearranged index based on the position of the sorted elements.

9. The method according to claim 8, wherein, After obtaining the first and second rearranged indices, the method further includes: Obtain the first synchronization header sequence and the second synchronization header sequence; Obtain the first encoder, the first decoder, the second encoder, and the second decoder; The first synchronization header sequence, the second synchronization header sequence, the first encoder, the first decoder, the second encoder and the second decoder, the first rearranged index and the second rearranged index are uploaded to the relay node.

10. A semantic communication method applied at a receiving end, wherein, The method includes: The system receives sorted data from a relay node. The relay node receives superimposed features from a first user and a second user. The superimposed features include a first semantic feature and a second semantic feature. The first semantic feature is obtained by extracting semantic features from a first input image sent by the first user, rearranging them using a preset first rearrangement index, and then adding a first synchronization header sequence. The second semantic feature is obtained by extracting semantic features from a second input image sent by the second user, rearranging them using a preset second rearrangement index, and then adding a second synchronization header sequence. Based on the pre-stored synchronization header sequence, features corresponding to the first user and the second user are extracted from the superimposed features to obtain first user features and second user features. The original order of the first user features and the second user features is restored using the pre-stored rearrangement index to obtain sorted first user features and sorted second user features. Data recovery is performed on the sorted first user features and the sorted second user features to obtain recovered data. The recovered data is then re-encoded and sorted using a semantic encoder and a rearrangement index corresponding to the receiving user. The sorted data is then superimposed and sent to the receiving end. The first rearranged index is used to retrieve the data of the corresponding second user from the sorted data to obtain the second user data; The second rearranged index is used to retrieve the data corresponding to the first user from the sorted data, thus obtaining the first user data; The second user data is recovered using the first decoder to obtain the original image sent by the second user; The first user data is recovered using the second decoder to obtain the original image sent by the first user.

11. A semantic communication method, wherein, The method includes: The sending end acquires a first input image sent by a first user and a second input image sent by a second user; it extracts semantic features from the first input image, rearranges it using a preset first rearrangement index, and adds it to a first synchronization header sequence to obtain a first semantic feature; it extracts semantic features from the second input image, rearranges it using a preset second rearrangement index, and adds it to a second synchronization header sequence to obtain a second semantic feature; it then superimposes the first semantic feature and the second semantic feature to obtain a superimposed feature and sends it to the relay node. The relay node receives superimposed features from a first user and a second user. Based on a pre-stored synchronization header sequence, it extracts features corresponding to the first and second users from the superimposed features, obtaining first user features and second user features. It then uses a pre-stored rearrangement index to restore the original order of the first user features and the second user features, obtaining sorted first user features and sorted second user features. It performs data recovery on the sorted first user features and the sorted second user features, and re-encodes and sorts the recovered data using a semantic encoder corresponding to the receiving user and a rearrangement index. Finally, it superimposes the sorted data and sends it to the receiving end. The receiving end receives sorted data sent from the relay node, uses the first rearrangement index to retrieve the data corresponding to the second user from the sorted data, and obtains the second user data; uses the second rearrangement index to retrieve the data corresponding to the first user from the sorted data, and obtains the first user data; uses the second user data to perform data recovery using the first decoder, and obtains the original image sent by the second user; uses the first user data to perform data recovery using the second decoder, and obtains the original image sent by the first user.

12. A semantic communication device applied to a relay node, wherein, include: The first receiving module is used to receive superimposed features from a first user and a second user. The superimposed features include a first semantic feature and a second semantic feature. The first semantic feature is obtained by extracting semantic features from a first input image sent by the first user, rearranging the images using a preset first rearrangement index, and then adding the images to a first synchronization header sequence. The second semantic feature is obtained by extracting semantic features from a second input image sent by the second user, rearranging the images using a preset second rearrangement index, and then adding the images to a second synchronization header sequence. The extraction module is used to extract the features corresponding to the first user and the second user from the superimposed features based on the pre-stored synchronization header sequence, so as to obtain the features of the first user and the features of the second user. The rearrangement module is used to restore the original order of the first user feature and the second user feature using a pre-stored rearrangement index, so as to obtain the sorted first user feature and the sorted second user feature. The recovery module is used to recover data from the sorted first user features and the sorted second user features respectively, and to re-encode and sort the recovered data using a semantic encoder and a rearrangement index corresponding to the receiving user. The sorted data is then superimposed and sent to the receiving end so that the receiving user at the receiving end can recover the corresponding original image data.

13. A semantic communication device, applied at a transmitting end, wherein, include: The acquisition module is used to acquire a first input image sent by a first user and a second input image sent by a second user; The first processing module is used to extract semantic features from the first input image, and rearrange the extracted features using a preset first rearrangement index and add them to the first synchronization header sequence to obtain the first semantic features. The second processing module is used to extract semantic features from the second input image, and then rearrange the extracted features using a preset second rearrangement index and add them to the second synchronization header sequence to obtain the second semantic features. The sending module is used to superimpose the first semantic feature and the second semantic feature to obtain a superimposed feature and send it to the relay node. The relay node extracts the features corresponding to the first user and the second user from the superimposed feature according to the pre-stored synchronization header sequence to obtain the first user feature and the second user feature. The original order of the first user feature and the second user feature is restored using a pre-stored rearrangement index to obtain the sorted first user feature and the sorted second user feature. Data recovery is performed on the sorted first user feature and the sorted second user feature respectively, and the recovered data is re-encoded and sorted using the semantic encoder and rearrangement index corresponding to the receiving user. The sorted data is then superimposed together and sent to the receiving end so that the receiving user at the receiving end can recover the corresponding original image data.

14. A semantic communication device, applied at a receiving end, wherein, include: The second receiving module is used to receive sorted data sent from a relay node. The relay node receives superimposed features from a first user and a second user. The superimposed features include a first semantic feature and a second semantic feature. The first semantic feature is obtained by extracting semantic features from a first input image sent by the first user, rearranging it using a preset first rearrangement index, and then adding a first synchronization header sequence. The second semantic feature is obtained by extracting semantic features from a second input image sent by the second user, rearranging it using a preset second rearrangement index, and then adding a second synchronization header sequence. Based on the pre-stored synchronization header sequence, features corresponding to the first user and the second user are extracted from the superimposed features to obtain first user features and second user features. The original order of the first user features and the second user features is restored using the pre-stored rearrangement index to obtain sorted first user features and sorted second user features. Data recovery is performed on the sorted first user features and the sorted second user features to obtain recovered data. The recovered data is then re-encoded and sorted using a semantic encoder and a rearrangement index corresponding to the receiving user. The sorted data is then superimposed and sent to the receiving end. The first separation module is used to retrieve the data of the corresponding second user from the sorted data using the first rearrange index, thereby obtaining the second user data. The second separation module is used to retrieve the data of the corresponding first user from the sorted data using the second rearrange index, thereby obtaining the first user data. The first decoding module is used to recover the second user data using the first decoder to obtain the original image sent by the second user; The second decoding module is used to recover the first user data using the second decoder to obtain the original image sent by the first user.

15. An electronic device, wherein, 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 to enable the at least one processor to perform the method of any one of claims 1-11.

16. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-11.

17. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-11.

Images