Data communication method, apparatus and device, and storage medium

Abstract

The present application relates to the field of communications, and discloses a data communication method, apparatus and device, and a storage medium. The method is applied to a semantic transmitter and comprises: performing semantic coding on data to be transmitted of a user to obtain coded data; transmitting the coded data to a semantic receiver corresponding to the user; and the semantic receiver determining received data on the basis of the coded data and signal transmission parameters, and performing semantic decoding on the received data to obtain target data. According to the present application, a semantic transmitter codes data to be transmitted of a user and transmits coded data to a semantic receiver, and the semantic receiver decodes the coded data to obtain target data. Compared with existing conventional methods of completely transmitting all data to be transmitted to receivers, the method in the present application can effectively reduce transmission information redundancy, thereby improving the communication efficiency.

Description

Data communication method, device, equipment and storage medium TECHNICAL FIELD

[0001] The present application relates to the technical field of communication, in particular to a data communication method, device, equipment and storage medium. BACKGROUND

[0002] With the increasing number of mobile devices and the emergence of virtual reality, metaverse and many other smart applications, new challenges are posed to the fifth generation (5G) wireless network: higher channel capacity demand and massive access demand. Due to the broadcast nature of wireless communication, in large-scale Internet of Things networking, the interference between multiple concurrent information streams is the main obstacle to limit the capacity of multi-user networks. Therefore, finding an effective multiple access (MA) scheme to manage multi-user interference is the core to achieve the goal of ultra-dense access. The key to the multiple access problem of wireless networks is to allocate wireless resources to multiple users. The existing various multiple access schemes can be divided into orthogonal multiple access (OMA) schemes and non-orthogonal multiple access (NOMA) schemes. Specifically, for the OMA scheme, the allocated resources are in orthogonal relationship in the frequency, time, coding or spatial domain. Due to the limited resources, the number of users accessing the network is limited. In order to further improve the network capacity, MA has developed towards NOMA. Through the use of superposition coding at the transmitter and serial interference cancellation (SIC) at the receiver, NOMA manages multi-user interference by forcing (at least) one user to successfully decode other users' messages (and cancel interference). However, the complexity of SIC is relatively high, and the design of the receiver is challenging.

[0003] The above-mentioned multiple access technology is based on traditional communication, and faces problems such as a large amount of data redundancy, high system complexity, limited capacity, high energy consumption, and low information transmission efficiency. Therefore, it is necessary to develop new effective multi-user interference management paradigms to improve the regional spectrum efficiency and realize the vision of large-scale intelligent connection.

[0004] The above content is only used to assist in understanding the technical solutions of the present application and does not represent the acknowledgement of the above content as prior art. SUMMARY

[0005] The main purpose of the present application is to provide a data communication method, device, equipment and storage medium, which aims to solve the technical problem of low data communication efficiency in the prior art.

[0006] To achieve the above-mentioned purpose, the present application provides a data communication method applied to a semantic transmitter, the method comprising the following steps:

[0007] Optionally, the data to be transmitted of the user is semantically encoded to obtain encoded data;

[0008] sending the coded data to a semantic receiver corresponding to the user;

[0009] The semantic receiver determines received data according to the coded data and signal transmission parameters, and performs semantic decoding on the received data to obtain target data.

[0010] Optionally, the step of performing semantic encoding on the to-be-transmitted data of the user to obtain coded data comprises:

[0011] performing semantic feature extraction on the to-be-transmitted data of the user to obtain semantic features;

[0012] quantizing the semantic features to obtain digital signals;

[0013] performing digital modulation and normalization on the digital signals to obtain coded data.

[0014] To achieve the above object, the application further provides a data communication method applied to a semantic receiver, comprising the following steps:

[0015] receiving coded data sent by a semantic transmitter, wherein the semantic transmitter performs semantic encoding on to-be-transmitted data of a user to obtain coded data, and sends the coded data to a semantic receiver;

[0016] determining received data according to the coded data and signal transmission parameters;

[0017] performing semantic decoding on the received data to obtain target data.

[0018] Optionally, the step of performing semantic decoding on the received data to obtain target data comprises:

[0019] performing channel equalization on the received data to obtain channel equalization data;

[0020] performing image reconstruction on the channel equalization data by a semantic decoder to obtain target data.

[0021] Optionally, the step of performing channel equalization on the received data to obtain channel equalization data comprises:

[0022] performing channel equalization on the received data by the following channel equalization formula to obtain channel equalization data:

[0023] wherein, y represents channel equalization data, i g represents received data, i，i gi represents channel gain from an i-th semantic transmitter to an i-th semantic receiver, and i，jH for representing the channel gain from the jth semantic transmitter to the ith semantic receiver, p i N for representing the transmit power of the ith user, N for representing the total number of users, n i H for representing the additive white Gaussian noise of the ith semantic receiver, H for representing the conjugate transpose, p j N for representing the transmit power of the jth user.

[0024] Optionally, the signal transmission parameters include the channel gain from the semantic transmitter to the semantic receiver, the transmit power of the user, and the additive white Gaussian noise of the semantic receiver.

[0025] The step of determining the received data according to the encoded data and the signal transmission parameters comprises:

[0026] The encoded data and the signal transmission parameters are brought into the following formula to obtain the received data:

[0027] wherein, x i Y for representing the encoded data, y i For representing the received data.

[0028] In addition, to achieve the above object, the present application also provides a data communication device, which comprises:

[0029] A semantic encoding module is configured to perform semantic encoding on the to-be-transmitted data of a user to obtain encoded data.

[0030] A data sending module is configured to send the encoded data to a semantic receiver corresponding to the user, and the semantic receiver is configured to determine received data according to the encoded data and signal transmission parameters, and perform semantic decoding on the received data to obtain target data.

[0031] In addition, to achieve the above object, the present application also provides a data communication device, which comprises:

[0032] A receiving module is configured to receive encoded data sent by a semantic transmitter, the semantic transmitter is configured to perform semantic encoding on to-be-transmitted data of a user to obtain the encoded data, and send the encoded data to a semantic receiver.

[0033] A determining module is configured to determine received data according to the encoded data and signal transmission parameters.

[0034] A semantic decoding module is configured to perform semantic decoding on the received data to obtain target data.

[0035] In addition, to achieve the above object, the application further provides a data communication device, comprising a memory, a processor and a data communication program stored in the memory and executable on the processor, the data communication program being configured to implement the steps of the data communication method as described above.

[0036] In addition, to achieve the above object, the application further provides a storage medium, the storage medium storing a data communication program, the data communication program being executable by a processor to implement the steps of the data communication method as described above.

[0037] The application encodes the data to be transmitted of a user to obtain encoded data, sends the encoded data to a semantic receiver corresponding to the user, and determines received data according to the encoded data and signal transmission parameters, and decodes the received data to obtain target data. Since the application encodes the data to be transmitted of a user by a semantic transmitter, transmits the encoded data to a semantic receiver, and decodes the target data by the semantic receiver, compared with the prior art of transmitting all data to be transmitted to a receiver, the above method can effectively reduce the transmission information redundancy and improve the communication efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0038] FIG. 1 is a structural schematic diagram of a data communication device of a hardware running environment related to an embodiment of the application;

[0039] FIG. 2 is a flowchart of a first embodiment of a data communication method of the application;

[0040] FIG. 3 is a feature extraction network diagram of the first embodiment of the data communication method of the application;

[0041] FIG. 4 is a multi-user semantic interference network diagram of the first embodiment of the data communication method of the application;

[0042] FIG. 5 is a flowchart of a second embodiment of a data communication method of the application;

[0043] FIG. 6 is a multi-user semantic interference communication system model diagram of the second embodiment of the data communication method of the application;

[0044] FIG. 7 is a semantic decoding network diagram of the second embodiment of the data communication method of the application;

[0045] FIG. 8 is a reconstruction performance comparison diagram of the second embodiment of the data communication method of the application;

[0046] FIG. 9 is a feature domain separation diagram of the second embodiment of the data communication method of the application;

[0047] FIG. 10 is a structural block diagram of a first embodiment of a data communication device of the application;

[0048] Fig. 11 is a structural block diagram of a second embodiment of the data communication device of the present application.

[0049] The implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0050] It should be understood that the specific embodiments described herein merely exemplify the application and do not limit the application.

[0051] Referring to Fig. 1, Fig. 1 is a structural schematic diagram of a data communication device of a hardware operating environment involved in an embodiment of the present application.

[0052] As shown in Fig. 1, the data communication device can include a processor 1001, for example, a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to realize the connection and communication among the components. The user interface 1003 can include a display, an input unit such as a keyboard, and optionally the user interface 1003 can further include a standard wired interface, a wireless interface. The network interface 1004 can optionally include a standard wired interface, a wireless interface (such as a wireless fidelity (WI-FI) interface). The memory 1005 can be a high-speed random access memory (RAM), and can also be a stable non-volatile memory (NVM), for example, a disk memory. The memory 1005 can also be an independent storage device from the aforementioned processor 1001.

[0053] Those skilled in the art can understand that the structure shown in Fig. 1 does not constitute a limitation on the data communication device, and can include more or fewer components than those shown, or combine certain components, or different component arrangements.

[0054] As shown in Fig. 1, the memory 1005 as a storage medium can include an operating system, a network communication module, a user interface module, and a data communication program.

[0055] In the data communication device shown in FIG. 1, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the data communication device can be arranged in the data communication device, and the data communication program stored in the memory 1005 is called by the processor 1001 to execute the data communication method provided in the embodiment.

[0056] Based on the above data communication device, the embodiment of the present application provides a data communication method. Referring to FIG. 2, FIG. 2 is a flowchart of a first embodiment of the data communication method of the present application.

[0057] In this embodiment, the data communication method is applied to a semantic transmitter, and includes the following steps.

[0058] Step S10: performing semantic encoding on the to-be-transmitted data of the user to obtain encoded data.

[0059] It should be noted that the execution subject of the embodiment can be a computing service device with data processing, network communication and program running functions, such as a mobile phone, a tablet computer, a personal computer, etc., or an electronic device or a semantic transmitter capable of realizing the above functions. The semantic transmitter is taken as an example in the following description of the embodiment and the subsequent embodiments.

[0060] It should be noted that the semantic transmitter can be installed on a user side and used for performing semantic encoding on to-be-transmitted data of the user. In this way, data redundancy in data transmission can be reduced, and channel interference can be avoided. The to-be-transmitted data can be data to be transmitted to a server, and specifically, the to-be-transmitted data can be image data. A semantic receiver is installed in the server and used for restoring the received encoded data to obtain original data, i.e., the to-be-transmitted data of the user. The semantic transmitter and the semantic receiver correspond to one user, and the semantic receiver can only decode the data encoded by the corresponding semantic transmitter, so that data interference can be avoided and data transmission efficiency can be improved. The semantic encoding on the to-be-transmitted data of the user can be performed by a pre-trained multi-user semantic interference communication network.

[0061] Further, in order to reduce data transmission redundancy, the step S10 can include: performing semantic feature extraction on the to-be-transmitted data of the user to obtain semantic features.

[0062] The semantic features are quantized to obtain digital signals.

[0063] The digital signals are digitally modulated and normalized to obtain encoded data.

[0064] It should be noted that the semantic feature extraction of the user's to-be-transmitted data can only extract the required semantic information, reduce data redundancy, and improve communication efficiency. The feature extraction network The semantic feature a i is extracted and encoded from the input image s i i and the to-be-transmitted data The feature extraction network is composed of three layers Layer, which can be referred to as FIG. 3, which is a schematic diagram of the feature extraction network of the first embodiment of the data communication method. Specifically, in Layer 1, the input image s is divided into H*W non-overlapping patches by the Patch Embedding Layer (PE), where H and W represent the height and width of the input image, respectively. Then, the non-overlapping patches are processed by N 1TX Swin Transformer blocks (ST) to obtain f i Specifically:

[0065] where f i represents the output of Layer 1. Then, f i is fed into Layer 2 to be down-sampled by the Patch Merge Layer (PM), and the down-sampled data is processed by N 2TX Swin Transformer blocks to obtain q i ,

[0066] where q i represents the output of Layer 2. Further, q i is processed by Layer 3, which includes a down-sampling Patch Merge layer and N 3TX Swin Transformer blocks. Finally, the semantic feature vector a i is extracted, i.e., the semantic feature:

[0067] It should be noted that the quantization of the semantic feature to obtain a digital signal can convert a continuous signal into a digital signal, realizing digital communication transmission. The feature vector a i is quantized into a bit stream b i , i.e., a digital signal, by a quantizer Q, which can be referred to as the following formula: b i = Q(a i ), i∈{1,..,N}

[0068] Specifically, by applying a linear layer and a sign function, the linear layer reduces the dimension of the feature vector a i to d, and then the sign function quantizes the feature vector a i to a bit stream.

[0069] The digital modulation and normalization of the digital signal to obtain the encoded data can be digital modulation and normalization of the digital signal. The anti-interference performance is improved, and the anti-channel loss is enhanced. Further, the quantized feature representation b i is digitally modulated and normalized (Norm) to obtain x i , x i = Norm (Θ m (b i )), i ∈ {1,..,N}

[0070] Specifically, the embodiment can regard the semantic feature extraction, quantization and modulation as a semantic encoder , that is:

[0071] wherein, denotes the semantic encoder of the i-th user, ψ i is the encoder parameter.

[0072] Step S20: transmitting the encoded data to the semantic receiver corresponding to the user; the semantic receiver determines the received data according to the encoded data and the signal transmission parameter, and performs semantic decoding on the received data to obtain the target data.

[0073] It should be noted that the signal transmission parameter can include transmission power, channel gain and other information corresponding to each user. The semantic decoding of the received data to obtain the target data can be semantic decoding of the received data by a pre-trained multi-user semantic interference communication network to obtain the target data, and the target data is the data to be transmitted by the user.

[0074] In a specific implementation, referring to FIG. 4, which is a schematic diagram of a multi-user semantic interference communication network according to the first embodiment of the data communication method of the present application; N in FIG. 4 represents the total number of users, and also represents the number of semantic receivers and semantic transmitters, the data to be transmitted is s1, and u1 is the semantic information corresponding to the data to be transmitted, denotes the semantic encoder of the i-th user, that is, the semantic transmitter, ψ i is the encoder parameter, denotes the i-th semantic decoder, that is, the semantic receiver, θ iThe trainable parameters represent a semantic decoder. The data to be transmitted by the user is encoded by a semantic encoder and then transmitted to the semantic decoder. The semantic decoder decodes the data to be transmitted by the user, thereby reducing data redundancy and multi-user interference during data transmission.

[0075] The embodiment is based on semantic communication and uses deep learning (DL) technology to explore a new resource field: semantic feature domain. A semantic feature division multiple access (SFDMA) scheme is proposed, which is different from existing multiple access schemes based on time, frequency, coding, space or power domain. Specifically, a DL-based semantic encoder extracts semantic information into discrete semantic feature representations in distinguishable semantic subspaces, and the discrete semantic feature vectors of multiple users are approximately orthogonal to each other. Then, a semantic decoder extracts and decodes the expected semantic information. Since the semantic features of multiple users are in distinguishable feature domains, the interference of multiple users is significantly reduced. It has good application value in the fields of military reconnaissance, public safety, etc.

[0076] The embodiment is applied to a semantic transmitter and includes: performing semantic encoding on data to be transmitted by a user to obtain encoded data; and sending the encoded data to a semantic receiver corresponding to the user. The semantic receiver determines received data according to the encoded data and signal transmission parameters, and performs semantic decoding on the received data to obtain target data. In the embodiment, the data to be transmitted by the user is encoded by the semantic transmitter, the encoded data is transmitted to the semantic receiver, and the semantic receiver decodes the data to obtain the target data. Compared with the existing conventional communication method of transmitting all data to be transmitted to the receiver, the above method can effectively reduce the transmission information redundancy and improve the communication efficiency.

[0077] Based on the above embodiments, the embodiment of the present application provides a data communication method. Referring to FIG. 5, FIG. 5 is a flowchart of a second embodiment of the data communication method of the present application.

[0078] In the embodiment, the data communication method is applied to a semantic receiver, and the data communication method includes the following steps:

[0079] Step S30: receiving encoded data sent by a semantic transmitter. The semantic transmitter performs semantic encoding on data to be transmitted by a user to obtain encoded data, and sends the encoded data to a semantic receiver.

[0080] It should be noted that N semantic transmitters simultaneously transmit signals x i .

[0081] Step S40: determining received data according to the encoded data and signal transmission parameters.

[0082] It should be noted that the determining the received data according to the encoded data and the signal transmission parameter can be determining the received data according to the encoded data and the signal transmission parameter by the following formula:

[0083] wherein x i is used for representing the encoded data, y i is used for representing the received data, wherein g i,i is the channel gain from the ith semantic transmitter to the ith semantic receiver, g i,j is the channel gain from the jth semantic transmitter to the ith semantic receiver, p i is the transmission power of the ith user, p j is used for representing the transmission power of the jth user, n i is used for representing the additive white Gaussian noise received by the ith semantic receiver,

[0084] Step S50: performing semantic decoding on the received data to obtain target data.

[0085] It should be noted that the performing semantic decoding on the received data to obtain target data can be performing semantic decoding on the received data by a semantic decoder to obtain target data. The semantic decoder performs semantic decoding on the received data by a pre-trained multi-user semantic interference communication network to obtain target data. Specifically, the step of performing semantic decoding on the received data to obtain target data comprises:

[0086] performing channel equalization on the received data to obtain channel equalization data;

[0087] performing image reconstruction on the channel equalization data by a semantic decoder to obtain target data.

[0088] It should be noted that the performing channel equalization on the received data to obtain channel equalization data can improve the transmission performance of a communication system in a fading channel and enhance the anti-fading performance. Assuming that the channel state information is completely known, the received data y i is equalized by the following channel equalization formula to obtain channel equalization data

[0089] wherein, is used for representing the channel equalization data, y i is used for representing the received data, g i，i is the channel gain from the ith semantic transmitter to the ith semantic receiver, g i，j is the channel gain from the jth semantic transmitter to the ith semantic receiver, p iIt is used to characterize the transmission power of the i-th user, N is used to ensure the total number of users, n i The additive white Gaussian noise used to characterize the received semantic receiver of the i-th word, H is used to characterize the conjugate transpose, p j Used to characterize the transmit power of the jth user.

[0090] It should be noted that, the image reconstruction of the channel equalization data is performed by the semantic decoder to obtain the target data, which can be semantic decoding and image reconstruction. The received signal Restore to reconstructed image

[0091] in represents the i-th semantic decoder, θ i Represents the trainable parameters of the semantic decoder.

[0092] Specifically, the feature vector (i.e. channel equalization data) first passes through N 3RX Swin Transformer blocks and a Patch Division (PD) layer are upsampled to obtain

[0093] Then, Feed to Layer 2, through N 2RX Swin Transformer blocks and an up-sampled Patch Division layer to obtain

[0094] Finally Enter N 1RX Swin Transformer blocks and an up-sampled Patch Division layer to obtain the reconstructed image

[0095] The training of a multi-user semantic interference communication network may include: users accessing the network according to the assigned feature domains and jointly training their respective anti-interference channel coding and decoding models. The training loss function of the entire semantic interference network is:

[0096] in, Used to represent the original image s i and reconstructed image mean square error between them.

[0097] In a specific implementation, referring to FIG. 6, which is a model diagram of a multi-user semantic interference communication system for image reconstruction of the second embodiment of the data communication method of the present application, it can be seen that the input image of a user is encoded into encoded data by a semantic encoder for transmission, and the encoded data is decoded by a semantic decoder to obtain the input image of the user. The user, the semantic encoder and the semantic decoder are in one-to-one correspondence, effectively preventing channel interference, reducing data redundancy in transmission, and improving communication efficiency. FIG. 7 is a schematic diagram of a semantic decoding network of the second embodiment of the data communication method of the present application.

[0098] In a specific implementation, referring to FIG. 8, which is a reconstruction performance comparison diagram of the second embodiment of the data communication method of the present application, U1 represents user 1, U2 represents user 2, Upper bound represents the upper bound of performance, Deep JSCC represents a deep joint source channel coding scheme, SFDMA represents a semantic feature division multiple access scheme, Distributed SFDMA represents a distributed semantic feature division multiple access scheme, and FIG. 9 is a feature domain separation diagram of the second embodiment of the data communication method of the present application.

[0099] The semantic transmitter encodes the to-be-transmitted data of a user to obtain encoded data, and transmits the encoded data to a semantic receiver; the receiving data is determined according to the encoded data and signal transmission parameters; and the target data is obtained by performing semantic decoding on the receiving data. Through exploration of the feature domain, the embodiment proposes an SFDMA scheme for a multi-user digital semantic communication network. The scheme is based on semantic communication, effectively reduces the redundancy of transmission information, and improves the communication efficiency. The semantic information of different users is encoded into distinguishable feature subspaces, and the semantic features of different users are approximately orthogonal, significantly reducing the interference of multiple users. In addition, the embodiment designs a multi-user semantic interference communication transmission model for image reconstruction, the semantic features of different users are approximately orthogonal, the corresponding decoder can only decode the target semantic information but cannot decode the interference information, and the confidentiality of transmission is enhanced.

[0100] Referring to FIG. 10, which is a structural block diagram of the first embodiment of the data communication device of the present application.

[0101] As shown in FIG. 10, the data communication device proposed in the embodiment of the present application comprises:

[0102] The semantic encoding module 10 is configured to encode the to-be-transmitted data of a user to obtain encoded data.

[0103] The data sending module 20 is configured to send the encoded data to a semantic receiver corresponding to the user, and the semantic receiver determines received data according to the encoded data and signal transmission parameters, and performs semantic decoding on the received data to obtain target data.

[0104] In this embodiment, the semantic encoding module 10 is further configured to perform semantic feature extraction on the data to be transmitted by the user to obtain semantic features.

[0105] The semantic features are quantized to obtain digital signals.

[0106] The digital signals are digitally modulated and normalized to obtain encoded data.

[0107] This embodiment is applied to a semantic transmitter, and includes the following steps: performing semantic encoding on data to be transmitted by a user to obtain encoded data; sending the encoded data to a semantic receiver corresponding to the user; and determining received data according to the encoded data and signal transmission parameters, and performing semantic decoding on the received data to obtain target data. In this embodiment, the data to be transmitted by the user is encoded by the semantic transmitter, the encoded data is transmitted to the semantic receiver, and the semantic receiver decodes the data to obtain target data. Compared with the conventional communication mode in which all data to be transmitted is completely transmitted to a receiver, the above mode can effectively reduce transmission information redundancy and improve communication efficiency.

[0108] Referring to FIG. 11, FIG. 11 is a structural block diagram of a second embodiment of a data communication device.

[0109] As shown in FIG. 11, the data communication device provided in this embodiment includes the following modules.

[0110] The receiving module 30 is configured to receive encoded data sent by a semantic transmitter, the semantic transmitter performs semantic encoding on data to be transmitted by a user to obtain the encoded data, and sends the encoded data to a semantic receiver.

[0111] The determining module 40 is configured to determine received data according to the encoded data and signal transmission parameters.

[0112] The semantic decoding module 50 is configured to perform semantic decoding on the received data to obtain target data.

[0113] It should be noted that the above-described workflow is merely illustrative, and does not limit the protection scope of the present application. In actual applications, a person skilled in the art can select part or all of the above-described workflow to achieve the purpose of the embodiment, and this is not limited herein.

[0114] In addition, technical details not described in detail in the present embodiment can be found in the data communication method provided by any embodiment of the present application, which will not be described here.

[0115] Based on the second embodiment of the data communication device described above, the third embodiment of the data communication device is proposed.

[0116] In the present embodiment, the semantic decoding module 50 is further configured to perform channel equalization on the received data to obtain channel equalization data.

[0117] The channel equalization data is reconstructed into target data by the semantic decoder.

[0118] Further, the semantic decoding module 50 is further configured to perform channel equalization on the received data by the following channel equalization formula to obtain channel equalization data.

[0119] wherein, y represents the channel equalization data, i g represents the received data, i，i gi represents the channel gain from the i-th semantic transmitter to the i-th semantic receiver, i，j gj represents the channel gain from the j-th semantic transmitter to the i-th semantic receiver, i Ni represents the transmission power of the i-th user, N represents the total number of users, i H represents the additive white Gaussian noise received by the i-th semantic receiver, H represents the conjugate transpose, j Nj represents the transmission power of the j-th user.

[0120] Further, the semantic decoding module 50 is further configured to bring the encoded data and signal transmission parameters into the following formula to obtain received data.

[0121] wherein, x i y represents the encoded data, i g represents the received data.

[0122] Other embodiments or specific implementations of the data communication device of the present application can refer to the above-mentioned method embodiments, which will not be described here.

[0123] In addition, the present embodiment also proposes a storage medium, which stores a data communication program. When the data communication program is executed by a processor, the steps of the data communication method described above are implemented.

[0124] It should be noted that, in this document, the terms "comprises", "comprising", or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or system. An element proceeded by "comprises a" does not, without more constraints, exclude the presence of additional identical elements in the process, method, article, or system that comprises the element.

[0125] The above-mentioned sequence numbers of the embodiments of the present application are only for description, and do not represent advantages or disadvantages of the embodiments.

[0126] From the above description of the embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be realized by means of software and necessary general hardware platforms, and of course can also be realized by hardware, but in many cases the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product in essence or in the form of a part of the prior art that makes a contribution. The computer software product is stored in a storage medium (such as a read-only memory / random access memory, a magnetic disk, or an optical disk) and includes a plurality of instructions for causing an end device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the methods described in the various embodiments of the present application.

[0127] The above is only a preferred embodiment of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation, or direct or indirect application in other related technical fields, is also included in the patent protection scope of the present application.

Claims

1. A data communication method, characterized in that: Applied to a semantic transmitter, the data communication method comprises the following steps: Perform semantic encoding on the user's data to be transmitted to obtain encoded data; Sending the encoded data to a semantic receiver corresponding to the user; The semantic receiver determines the received data according to the coded data and the signal transmission parameters, and performs semantic decoding on the received data to obtain the target data.

2. The data communication method according to claim 1, wherein: The step of semantically encoding the user's data to be transmitted to obtain encoded data includes: Extract semantic features from the user's data to be transmitted to obtain semantic features; quantizing the semantic features to obtain digital signals; The digital signal is digitally modulated and normalized to obtain coded data.

3. A data communication method, characterized in that: Applied to a semantic receiver, the data communication method comprises the following steps: Receiving coded data sent by a semantic transmitter, the semantic transmitter semantically encodes the user's data to be transmitted to obtain coded data, and sending the coded data to a semantic receiver; Determining received data based on the coded data and signal transmission parameters; The received data is semantically decoded to obtain target data.

4. The data communication method according to claim 3, wherein: The step of semantically decoding the received data to obtain target data includes: performing channel equalization on the received data to obtain channel equalized data; The channel equalization data is image reconstructed by a semantic decoder to obtain target data.

5. The data communication method according to claim 4, wherein: The step of performing channel equalization on the received data to obtain channel equalized data includes: Channel equalization is performed on the received data using the following channel equalization formula to obtain channel equalization data: in, Used to characterize channel equalization data, y i Used to represent received data, g i,i Used to characterize the channel gain from the i-th semantic transmitter to the i-th semantic receiver, g i,j Used to characterize the channel gain from the jth semantic transmitter to the ith semantic receiver, p i It is used to characterize the transmission power of the i-th user, N is used to ensure the total number of users, n i The additive white Gaussian noise used to characterize the received semantic receiver of the i-th word, H is used to characterize the conjugate transpose, p j Used to characterize the transmit power of the jth user.

6. The data communication method according to claim 5, wherein: The signal transmission parameters include the channel gain from the semantic transmitter to the semantic receiver, the user's transmission power, and the additive white Gaussian noise of the semantic receiver; The step of determining received data according to the coded data and the signal transmission parameters comprises: Substitute the coded data and signal transmission parameters into the following formula to obtain the received data: Among them, x i Used to represent the encoded data, y i Used to represent received data.

7. A data communication device, characterized in that: The data communication device comprises: A semantic encoding module is used to semantically encode the user's data to be transmitted to obtain encoded data; The data sending module is used to send the encoded data to the semantic receiver corresponding to the user. The semantic receiver determines the received data according to the encoded data and signal transmission parameters, and performs semantic decoding on the received data to obtain the target data.

8. A data communication device, characterized in that: The data communication device comprises: A receiving module is used to receive coded data sent by a semantic transmitter, wherein the semantic transmitter performs semantic coding on the user's data to be transmitted to obtain coded data, and sends the coded data to the semantic receiver; a determination module, configured to determine received data based on the coded data and signal transmission parameters; The semantic decoding module is used to perform semantic decoding on the received data to obtain target data.

9. A data communication device, characterized in that: The device includes: a memory, a processor, and a data communication program stored in the memory and executable on the processor, wherein the data communication program is configured to implement the steps of the data communication method according to any one of claims 1 to 2 and 3 to 6.

10. A storage medium, characterized in that: The storage medium stores a data communication program, which, when executed by a processor, implements the steps of the data communication method according to any one of claims 1 to 2 and 3 to 6.

Images