Semantic-based multi-user information transmission method and related apparatus

Abstract

The present disclosure provides a multi-user information transmission method based on a semantic base and related devices. When applied to a base station, the method comprises: determining a plurality of source information to be sent to a plurality of user terminals; performing semantic feature extraction on each source information based on a plurality of semantic feature extraction methods to obtain a first semantic feature set corresponding to each source information; rearranging a plurality of semantic features in a plurality of first semantic feature sets based on the differences between the plurality of semantic features in the first semantic feature sets to obtain a second semantic feature set; superimposing the plurality of first semantic feature sets and the plurality of second semantic feature sets to obtain a superimposed semantic feature set, and sending the superimposed semantic feature set to the plurality of user terminals. The semantic base comprises a corresponding relationship between the semantic feature extraction method and the semantic feature. The superimposed transmission of the rearranged semantic features and the unrearranged semantic features suppresses the mutual interference of semantics between different users.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of communication, and in particular, to a multi-user information transmission method based on semantic bases and related apparatuses. BACKGROUND

[0002] This section is intended to provide background or context to the embodiments of the disclosure recited in the claims. The description herein does not constitute admission that the prior art is prior art nor does it constitute an admission of any description in this section as prior art to an application.

[0003] The semantic communication technology significantly improves the communication efficiency by extracting and transmitting semantic information related to the communication intention, compared with the communication technology based on syntax information in the related art.

[0004] However, the semantic communication scheme in the related art has the problem of semantic mutual interference between users when facing non-orthogonal transmission of information of multiple users. SUMMARY

[0005] Therefore, the purpose of the present disclosure is to provide a multi-user information transmission method based on semantic bases and related apparatuses, which at least solves one of the technical problems in the related art to some extent.

[0006] To achieve the above purpose, a first aspect of an exemplary embodiment of the present disclosure provides a multi-user information transmission method based on semantic bases, applied to a base station, the method comprising:

[0007] determining a plurality of source information to be sent to a plurality of user terminals;

[0008] performing semantic feature extraction on each of the source information based on a plurality of semantic feature extraction manners, to obtain a first semantic feature set corresponding to each of the source information, the first semantic feature set comprising a plurality of semantic features obtained based on the plurality of semantic feature extraction manners;

[0009] performing rearrangement on the plurality of semantic features in the first semantic feature set based on the differences between the plurality of semantic features, to obtain a second semantic feature set;

[0010] superimposing the plurality of first semantic feature sets and the plurality of second semantic feature sets to obtain a superimposed semantic feature set, and sending the superimposed semantic feature set to the plurality of user terminals.

[0011] Based on the same inventive concept, a second aspect of an exemplary embodiment of the present disclosure provides a multi-user information transmission method based on semantic bases, applied to a user terminal, the method comprising:

[0012] receiving a superimposed semantic feature set sent by a base station;

[0013] in response to determining that the user terminal corresponds to the first decoding order, decoding the superimposed semantic feature set to obtain source information corresponding to the user terminal;

[0014] or,

[0015] in response to determining that the user terminal does not correspond to the first decoding order, performing serial interference cancellation on the superimposed semantic feature set to obtain a semantic feature set corresponding to the user terminal, and decoding the semantic feature set to obtain source information corresponding to the user terminal.

[0016] Based on the same inventive concept, a third aspect of the exemplary embodiments of the present disclosure provides a semantic-based multi-user information transmission method applied to a user terminal, the method comprising:

[0017] determining source information to be sent to a base station;

[0018] performing semantic feature extraction on the source information based on a plurality of semantic feature extraction manners to obtain a third semantic feature set corresponding to the source information, the third semantic feature set including a plurality of semantic features obtained based on the plurality of semantic feature extraction manners;

[0019] in response to determining that the user terminal does not participate in rearrangement, sending the third semantic feature set to the base station;

[0020] or,

[0021] in response to determining that the user terminal participates in rearrangement, rearranging the plurality of semantic features in the third semantic feature set based on differences between the plurality of semantic features to obtain a fourth semantic feature set, and sending the fourth semantic feature set to the base station.

[0022] Based on the same inventive concept, a fourth aspect of the exemplary embodiments of the present disclosure provides a semantic-based multi-user information transmission method applied to a base station, the method comprising:

[0023] receiving superimposed semantic feature sets sent by a plurality of user terminals;

[0024] determining a decoding order of the plurality of user terminals according to channel parameters of the plurality of user terminals;

[0025] based on the decoding order, performing serial interference cancellation on the superimposed semantic feature sets to obtain a plurality of semantic feature sets, and decoding the semantic feature sets to obtain source information corresponding to the semantic feature sets.

[0026] Based on the same inventive concept, the fifth aspect of the exemplary embodiments of the present disclosure provides a semantic-based multi-user information transmission device applied to a base station, the device comprising:

[0027] A first source information determination module configured to determine a plurality of source information to be sent to a plurality of user terminals;

[0028] A first semantic feature extraction module configured to extract semantic features of each of the source information based on a plurality of semantic feature extraction manners, to obtain a first semantic feature set corresponding to each of the source information, the first semantic feature set comprising a plurality of semantic features obtained based on the plurality of semantic feature extraction manners;

[0029] A first semantic feature rearrangement module configured to rearrange the plurality of semantic features in a plurality of the first semantic feature sets based on the differences between the plurality of semantic features, to obtain a second semantic feature set;

[0030] A first semantic feature sending module configured to superimpose a plurality of the first semantic feature sets and a plurality of the second semantic feature sets, to obtain a superimposed semantic feature set, and send the superimposed semantic feature set to the plurality of user terminals.

[0031] Based on the same inventive concept, the sixth aspect of the exemplary embodiments of the present disclosure provides a semantic-based multi-user information transmission device applied to a user terminal, the device comprising:

[0032] A first semantic feature receiving module configured to receive a superimposed semantic feature set sent by a base station;

[0033] A first semantic feature decoding module configured to decode the superimposed semantic feature set to obtain source information corresponding to the user terminal in response to determining that a decoding order corresponding to the user terminal is in the first place;

[0034] A first serial interference cancellation module configured to perform serial interference cancellation on the superimposed semantic feature set to obtain a semantic feature set corresponding to the user terminal in response to determining that a decoding order corresponding to the user terminal is not in the first place, and decode the semantic feature set to obtain source information corresponding to the user terminal.

[0035] Based on the same inventive concept, the seventh aspect of the exemplary embodiments of the present disclosure provides a semantic-based multi-user information transmission device applied to a user terminal, the device comprising:

[0036] A second source information determination module configured to determine source information to be sent to a base station;

[0037] The second semantic feature extraction module is configured to perform semantic feature extraction on the source information based on a plurality of semantic feature extraction manners to obtain a third semantic feature set corresponding to the source information, the third semantic feature set including a plurality of semantic features obtained based on the plurality of semantic feature extraction manners;

[0038] The second semantic feature sending module is configured to send the third semantic feature set to the base station in response to determining that the user terminal does not participate in rearrangement.

[0039] The second semantic feature rearrangement module is configured to rearrange the plurality of semantic features in the third semantic feature set based on differences between the plurality of semantic features in the third semantic feature set in response to determining that the user terminal participates in rearrangement, to obtain a fourth semantic feature set, and send the fourth semantic feature set to the base station.

[0040] Based on the same inventive concept, the eighth aspect of the exemplary embodiments of the present disclosure provides a semantic base-based multi-user information transmission device applied to a base station, the device comprising:

[0041] The second semantic feature receiving module is configured to receive a superimposed semantic feature set sent by a plurality of user terminals.

[0042] The second semantic feature decoding module is configured to determine a decoding order of the plurality of user terminals according to channel parameters of the plurality of user terminals.

[0043] The second serial interference cancellation module is configured to perform serial interference cancellation on the superimposed semantic feature set based on the decoding order to obtain a plurality of semantic feature sets, and decode the semantic feature sets to obtain source information corresponding to the semantic feature sets.

[0044] Based on the same inventive concept, the ninth aspect of the exemplary embodiments of the present disclosure provides a semantic base-based multi-user information transmission system, comprising a base station and a user terminal.

[0045] When the base station device is configured to perform the method of the first aspect, the user terminal is configured to perform the method of the second aspect.

[0046] When the user terminal is configured to perform the method of the third aspect, the base station device is configured to perform the method of the fourth aspect.

[0047] Based on the same inventive concept, the eleventh aspect of the exemplary embodiments of the present disclosure provides a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the method of the first aspect or the method of the second aspect or the method of the third aspect or the method of the fourth aspect.

[0048] Based on the same inventive concept, the eleventh aspect of the exemplary embodiments of the present disclosure provides a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the method of the first aspect or the method of the second aspect or the method of the third aspect or the method of the fourth aspect.

[0049] Based on the same inventive concept, the eleventh aspect of the exemplary embodiments of the present disclosure provides a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the method of the first aspect or the method of the second aspect or the method of the third aspect or the method of the fourth aspect.

[0050] As can be seen from the above, the method for transmitting information based on a semantic base and the related device provided by the embodiments of the present disclosure, when applied to a base station, the method comprises: determining a plurality of source information to be sent to a plurality of user terminals; performing semantic feature extraction on each of the source information based on a plurality of semantic feature extraction methods to obtain a first semantic feature set corresponding to each of the source information, the first semantic feature set comprising a plurality of semantic features obtained based on the plurality of semantic feature extraction methods; rearranging the plurality of semantic features in the plurality of first semantic feature sets based on the differences between the plurality of semantic features in the first semantic feature sets to obtain a second semantic feature set; superimposing the plurality of first semantic feature sets and the plurality of second semantic feature sets to obtain a superimposed semantic feature set, and sending the superimposed semantic feature set to the plurality of user terminals. The semantic base comprises a corresponding relationship between the semantic feature extraction method and the semantic feature, and the superimposed transmission of the rearranged semantic features and the unrearranged semantic features suppresses the mutual interference of the semantics between different users. BRIEF DESCRIPTION OF DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the present disclosure or the related art, brief introductions will be given below to the drawings needed to be used in the embodiments or the related art descriptions. Obviously, the drawings in the following description are only embodiments of the present disclosure, and for those skilled in the art, other drawings can also be obtained without creative labor based on these drawings.

[0052] Figure 1 An application scenario schematic diagram of the semantic-based multi-user information transmission system provided by the exemplary embodiments of the present disclosure is provided;

[0053] Figure 2 A flow schematic diagram of the semantic-based multi-user information transmission method provided by the exemplary embodiments of the present disclosure is provided;

[0054] Figure 3 An application scenario schematic diagram of the semantic-based multi-user information transmission method provided by the exemplary embodiments of the present disclosure is provided;

[0055] Figure 4 A flow schematic diagram of the feature rearrangement manner provided by the exemplary embodiments of the present disclosure is provided;

[0056] Figure 5 Another flow schematic diagram of the semantic-based multi-user information transmission method provided by the exemplary embodiments of the present disclosure is provided;

[0057] Figure 6 Another flow schematic diagram of the semantic-based multi-user information transmission method provided by the exemplary embodiments of the present disclosure is provided;

[0058] Figure 7 Another flow schematic diagram of the semantic-based multi-user information transmission method provided by the exemplary embodiments of the present disclosure is provided;

[0059] Figure 8 Another flow schematic diagram of the semantic-based multi-user information transmission method provided by the exemplary embodiments of the present disclosure is provided;

[0060] Figure 9 Another application scenario schematic diagram of the semantic-based multi-user information transmission system provided by the exemplary embodiments of the present disclosure is provided;

[0061] Figure 10 A structure schematic diagram of the semantic-based multi-user information transmission device provided by the exemplary embodiments of the present disclosure is provided;

[0062] Figure 11 Another structure schematic diagram of the semantic-based multi-user information transmission device provided by the exemplary embodiments of the present disclosure is provided;

[0063] Figure 12 Another structure schematic diagram of the semantic-based multi-user information transmission device provided by the exemplary embodiments of the present disclosure is provided;

[0064] Figure 13 Another structure schematic diagram of the semantic-based multi-user information transmission device provided by the exemplary embodiments of the present disclosure is provided;

[0065] Figure 14 A structural schematic diagram of an electronic device provided for an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0066] It can be understood that, before using the technical solutions disclosed in the embodiments of the present application, the type, use range, use scenario, etc. of the personal information involved in the present application should be informed to the user and the authorization of the user should be obtained through appropriate means according to relevant laws and regulations.

[0067] For example, in response to receiving the active request of the user, the prompt information is sent to the user to explicitly prompt the user that the operation requested to be performed will require the acquisition and use of the personal information of the user. Thus, the user can voluntarily choose whether to provide the personal information to the electronic device, application program, server or storage medium, etc. software or hardware performing the operation of the technical solutions of the present application according to the prompt information.

[0068] As an optional but non-limiting implementation manner, in response to receiving the active request of the user, the manner of sending the prompt information to the user may, for example, be a pop-up window manner, and the prompt information may be presented in the form of text in the pop-up window. In addition, the pop-up window may also carry a selection control for the user to select "agree" or "disagree" to provide the personal information to the electronic device.

[0069] It can be understood that the above notification and user authorization process is only illustrative, and does not limit the implementation manner of the present application, and other manners meeting the relevant laws and regulations can also be applied to the implementation manner of the present application.

[0070] It can be understood that the data involved in the present technical solutions (including but not limited to the data itself, the acquisition or use of the data) should comply with the requirements of the relevant laws and regulations and the relevant provisions.

[0071] In order to make the purpose, technical solutions and advantages of the present disclosure clearer and more apparent, the principles and spirits of the present disclosure will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are only given to enable those skilled in the art to better understand and implement the present disclosure, and do not limit the scope of the present disclosure in any way. On the contrary, these embodiments are provided to make the present disclosure more thorough and complete, and to fully convey the scope of the present disclosure to those skilled in the art.

[0072] In this document, it should be understood that any number of elements in the drawings are used for illustration and not limitation, and any naming is only for differentiation and does not have any limiting meaning.

[0073] It should be noted that, unless otherwise defined, technical terms or scientific terms used in the embodiments of the present disclosure shall have the common meaning understood by one of ordinary skill in the art to which the present disclosure belongs. The terms "first", "second", and similar terms used in the embodiments of the present disclosure do not denote any order, quantity, or importance, but are used to distinguish different components. The terms "include", "contain", and similar terms mean that the elements or objects before the terms encompass the elements or objects listed after the terms and their equivalents, and do not exclude other elements or objects. The terms "connect" or "connected" or similar terms are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. The terms "upper", "lower", "left", "right", and the like are used only to represent relative positional relationships, and when the absolute positions of the described objects are changed, the relative positional relationships can also be changed accordingly. The article "a" or "an" before an element does not exclude the presence of multiple such elements.

[0074] The principles and spirits of the present disclosure will be explained in detail below with reference to several representative embodiments of the present disclosure.

[0075] As described in the background, the semantic communication technology significantly improves the communication efficiency by extracting and transmitting semantic information related to the communication intention, compared with the communication technology based on syntax information in the related art.

[0076] However, the inventors of the present disclosure found that the semantic communication scheme in the related art has the problem of semantic mutual interference between users when facing non-orthogonal transmission of information by multiple users.

[0077] To solve the above problem, the present disclosure provides a semantic base-based multi-user information transmission scheme, when applied to a base station, specifically comprising: determining a plurality of source information to be sent to a plurality of user terminals; performing semantic feature extraction on each of the source information based on a plurality of semantic feature extraction methods to obtain a first semantic feature set corresponding to each of the source information, the first semantic feature set including a plurality of semantic features obtained based on the plurality of semantic feature extraction methods; rearranging the plurality of semantic features in the plurality of first semantic feature sets based on the differences between the plurality of semantic features in the first semantic feature sets to obtain a second semantic feature set; superimposing the plurality of first semantic feature sets and the plurality of second semantic feature sets to obtain a superimposed semantic feature set, and sending the superimposed semantic feature set to the plurality of user terminals. Wherein the semantic base includes the correspondence between the semantic feature extraction method and the semantic feature, and the superimposed transmission of the rearranged semantic features and the unrearranged semantic features suppresses the mutual interference of the semantics between different users.

[0078] Specifically, the serial interference cancellation method adopted by the existing syntax information-oriented non-orthogonal communication technology cannot be directly used to detect the superimposed semantic features, because the existing modulation and demodulation mode is designed for syntax communication, and is used to form and detect discrete constellation point symbols; and the semantic features are usually extracted by a deep neural network, and are continuous floating-point numbers, so that the traditional modulation and demodulation method directly used to estimate the continuous semantic features will result in poor detection performance, and further reduce the performance of serial interference cancellation. In the existing semantic feature-oriented non-orthogonal transmission scheme, there is generally no serial interference cancellation method designed for superimposed semantic features, but a deep learning-based multi-user joint decoder is used to simultaneously interpret the information of multiple users, but after the decoder is trained, it is only applicable to the same number of users, and cannot be directly extended to more user scenarios, and each time a user is added, the decoder needs to be redesigned and trained, and the scalability is poor in actual multi-user communication scenarios. At the same time, these works only process the interference between multiple users at the syntax level, i.e., direct interference at the symbol level, ignoring the interference of superimposed symbols at the semantic level. Due to the continuity of semantic features, the interference cannot be perfectly eliminated at the syntax level, and the residual semantic interference will affect the performance of semantic level decoding, and the above works do not consider this problem, resulting in a decrease in the efficiency of non-orthogonal semantic transmission.

[0079] In the present disclosure, a semantic basis-based multi-user semantic information non-orthogonal transmission scheme is proposed, and an efficient joint semantic channel coding method and transmission strategy are realized based on the semantic basis, which is used to carry simultaneous same-frequency transmission of multiple semantic features, thereby improving the semantic information transmission efficiency between the base station and multiple semantic users. Among them, the base station uses a joint semantic channel encoder to extract multiple semantic features and robustly encodes them, and transmits them to multiple semantic users in a non-orthogonal manner, and uses a joint semantic channel decoder to complete the reconstruction of the source information based on the semantic features. To reduce the semantic interference between users in non-orthogonal transmission, the present disclosure proposes a semantic feature rearrangement method based on the difference between semantic bases, which calculates the distance between different user semantic bases at the base station side, superimposes the features with large semantic base differences for transmission, so that at each semantic user, the joint semantic channel decoder can only detect the semantic features matched with the decoding semantic base, and the semantic features of other users causing interference cannot be identified by the decoder, thereby suppressing semantic interference from the transmitting end. At the semantic user side of the receiving end, the present disclosure proposes a serial interference cancellation method based on the difference between semantic bases, which decodes and regenerates the semantic features causing interference using the semantic bases, and suppresses the expression of the features of other semantic users using the difference between semantic bases, so that the interference can be more accurately estimated and subtracted from the received signal, further reducing the semantic interference, improving the decoding accuracy of the target semantic features, and further improving the overall semantic feature transmission efficiency of the multi-user semantic communication system.

[0080] After introducing the basic principles of the present disclosure, the various non-limiting embodiments of the present disclosure are specifically introduced as follows.

[0081] Reference Figure 1 FIG. 1 is a schematic diagram of an application scenario of a semantic-based multi-user information transmission system according to an exemplary embodiment of the present disclosure.

[0082] In the application scenario, a base station and a plurality of user terminals (semantic users) are included. The application scenario is a downlink scenario, in which the base station is a sending end and the user terminals are receiving ends.

[0083] The base station and the user terminals can be connected through a wired or wireless communication network to realize data interaction.

[0084] The user terminal can be an electronic device close to a user side with data transmission and multimedia input / output functions, including but not limited to a desktop computer, a mobile phone, a mobile computer, a tablet computer, a media player, a smart wearable device, a personal digital assistant (PDA), or other electronic devices capable of realizing the above functions, etc. The electronic device can include a processor and a display screen with touch input function, the display screen being used to present a graphical user interface, and the graphical user interface being used to display an application interface, the processor being used to process application data, generate a graphical user interface, and control the display of the graphical user interface on the display screen.

[0085] When the semantic-based multi-user information transmission method is run on the base station, the base station is used to provide a semantic-based multi-user information transmission service for users of user terminals. The base station determines a plurality of source information to be sent to a plurality of user terminals; performs semantic feature extraction on each of the source information based on a plurality of semantic feature extraction manners to obtain a first semantic feature set corresponding to each of the source information, the first semantic feature set including a plurality of semantic features obtained based on the plurality of semantic feature extraction manners; rearranges the plurality of semantic features in the first semantic feature sets based on the differences between the plurality of semantic features to obtain a second semantic feature set; superimposes the plurality of first semantic feature sets and the plurality of second semantic feature sets to obtain a superimposed semantic feature set, and sends the superimposed semantic feature set to the plurality of user terminals.

[0086] In some exemplary embodiments, a user terminal receives a superimposed set of semantic features sent by a base station; in response to determining that the decoding order corresponding to the user terminal is first, the superimposed set of semantic features is decoded to obtain source information corresponding to the user terminal; or, in response to determining that the decoding order corresponding to the user terminal is not first, serial interference cancellation is performed on the superimposed set of semantic features to obtain a set of semantic features corresponding to the user terminal, and the set of semantic features is decoded to obtain source information corresponding to the user terminal. The user terminal has a client installed that communicates with the base station, and the client displays the source information to the user.

[0087] The following is combined Figure 1 The above application scenarios are used to describe the semantic-based multi-user information transmission method according to exemplary embodiments of this disclosure. It should be noted that the above application scenarios are shown only to facilitate understanding of the spirit and principles of this disclosure, and the embodiments of this disclosure are not limited in any way. Rather, the embodiments of this disclosure can be applied to any applicable scenario.

[0088] Below, we will combine Figure 1 This paper introduces a semantic basis-based multi-user information transmission method implemented in downlink scenarios, where the base station is the transmitter and the user terminal is the receiver.

[0089] refer to Figure 2 When the base station is the transmitting end, the semantic basis-based multi-user information transmission method implemented by the base station includes the following steps:

[0090] Step S210: Determine several information sources to be sent to several user terminals.

[0091] In some exemplary embodiments, there are several user terminals, which are sorted in ascending order of distance based on the distance between the user terminals and the base station.

[0092] As a concrete example, suppose there are N user terminals. If we sort the user terminals in ascending order of distance, resulting in user terminal 1, user terminal 2, ..., user terminal N, then there exists d1. <d2<…<d N , where d i This represents the distance between the i-th user terminal and the base station.

[0093] In practical implementation, since the user terminal is used to implement the multi-user information transmission method based on semantic base, the user terminal is also referred to as a semantic user in this disclosure.

[0094] In some exemplary embodiments, determining the source information to be sent to a plurality of user terminals includes:

[0095] The source information to be sent to different user terminals is different.

[0096] In a specific implementation, the source information to be sent to different user terminals is not specifically associated, that is, the source information to be sent to different user terminals is independent of each other. In this case, the source information to be sent to different user terminals can be the same or different, but is usually different.

[0097] In some example embodiments, the source information includes at least one of:

[0098] Text source information, speech source information, image source information, digital source information.

[0099] In a specific implementation, the source is an entity that generates various types of information. The symbol given by the source is uncertain and can be described by a random variable and its statistical characteristics. Information is abstract, and the source is specific. For example, people talking, the human vocal system is a speech source; people reading books and newspapers, the books and newspapers illuminated by light are text sources; common sources also include image sources, digital sources, and so on.

[0100] In step S220, semantic feature extraction is performed on each of the source information based on a plurality of semantic feature extraction methods, to obtain a first semantic feature set corresponding to each of the source information, wherein the first semantic feature set includes a plurality of semantic features obtained based on the plurality of semantic feature extraction methods.

[0101] In some example embodiments, the semantic feature extraction method includes an encoding function.

[0102] The semantic feature extraction is performed on each of the source information based on a plurality of semantic feature extraction methods, to obtain a first semantic feature set corresponding to each of the source information, wherein the first semantic feature set includes a plurality of semantic features obtained based on the plurality of semantic feature extraction methods, including:

[0103] The semantic feature extraction is performed on each of the source information based on a plurality of semantic feature extraction methods, to obtain a first semantic feature set corresponding to each of the source information, wherein the first semantic feature set includes a plurality of semantic features obtained based on the plurality of semantic feature extraction methods, including:

[0104] In some example embodiments, the first semantic feature set includes a plurality of semantic features obtained based on the plurality of semantic feature extraction methods, including:

[0105] The semantic features obtained based on different semantic feature extraction methods are different.

[0106] As a specific example:

[0107] The module that implements semantic feature extraction is called the joint semantic channel encoder.

[0108] In practice, the joint semantic channel encoder is implemented by a deep neural network. The specific network structure can be flexibly adjusted according to the specific source modality and transmission requirements, such as the Transformer structure for text transmission and the convolutional neural network structure for image transmission.

[0109] In practice, the joint semantic channel encoder contains multiple coding functions used to extract various semantic features related to the reconstruction of the original information from the information to be transmitted. This process is represented as follows:

[0110]

[0111] Among them, s i For the original information of user i, x i Let i be the semantic features of user i. Let represent the transfer function of the joint semantic channel encoder, where α is the set of parameters of the encoder neural network. x corresponds to multiple encoding functions in the joint semantic channel encoder. i =[x i,1 ,…,x i,C' Each semantic feature x in ] i,c It also needs to be decoded by the corresponding decoding function at the receiving end. The semantic base contains the correspondence between this encoding / decoding function and semantic features.

[0112] Step S230: Based on the differences between the semantic features in the first semantic feature set, rearrange the semantic features in the first semantic feature set to obtain a second semantic feature set.

[0113] In some exemplary embodiments, the step of rearranging the semantic features in the first semantic feature set based on the differences between the semantic features in the first semantic feature set to obtain a second semantic feature set includes:

[0114] Determine the difference parameters among the semantic features in the first semantic feature set, and obtain the difference parameter matrix based on the difference parameters;

[0115] Based on the difference parameter matrix, pairing is performed with the aim of maximizing the difference parameter between two semantic features to obtain the sequence number of the paired semantic features;

[0116] Based on the sequence number of the semantic features of the pairing, a rearranged sequence number is obtained;

[0117] rearrange the order of the semantic features in the first semantic feature set to be rearranged based on the rearranged sequence number series, to obtain the second semantic feature set.

[0118] In some example embodiments, the rearranging the order of the semantic features in the first semantic feature set to be rearranged based on the rearranged sequence number series, to obtain the second semantic feature set, comprises:

[0119] determining the sequence numbers of the semantic features in the first semantic feature set to be rearranged;

[0120] rearranging the order of the semantic features based on the rearranged sequence number series, to obtain the second semantic feature set.

[0121] In some example embodiments, the rearranging the semantic features in the first semantic feature set based on the difference between the semantic features in the first semantic feature set, to obtain the second semantic feature set, comprises:

[0122] for N first semantic feature sets:

[0123] rearranging the semantic features in the N-1 first semantic feature set based on the difference between the semantic features in the N first semantic feature set, to obtain a first second semantic feature set;

[0124] rearranging the semantic features in the N-3 first semantic feature set based on the difference between the semantic features in the N-2 first semantic feature set, to obtain a second second semantic feature set;

[0125] repeating the above steps until the rearranging is completed.

[0126] Reference Figure 3 In actual implementation, the base station extracts semantic features of original information of N users, and first evaluates semantic base difference. Since the N users share the same joint semantic channel encoder, the extracted semantic features have the same corresponding relationship with the encoding function, i.e. under the same type of information source, the semantic base does not change with the change of the information source, so the evaluation of the semantic base difference can be completed based on the semantic features of a single user, and the obtained semantic base difference is used to rearrange the semantic features of multiple users. For example, the semantic base difference can be evaluated by using the semantic features of semantic user 1, and in actual use, the semantic features of other users can also be selected to complete this process.

[0127] Reference Figure 4, as a specific example, the rearrangement process, specifically comprising the following steps:

[0128] Step 1: Calculate the distance between and and form a semantic feature rearrangement matrix D of C'x C', denoted as:

[0129]

[0130] Step 2: Select the pair of features with the maximum distance from D, and record the corresponding channel order number;

[0131] Step 3: Delete the row and column where the selected feature pair is located from D;

[0132] Step 4: Repeat steps 2 and 3 until all features are paired.

[0133] After the above steps are completed, given the channel order number {1, …, C'} of the semantic feature, the channel order number of the paired feature with the largest semantic base difference is c r ={c1, …, c C}. For a user's semantic feature x i =[x i,1 ,…,x i,C' ], rearrange the semantic features of other users according to c r , then x i Each channel feature is paired with a semantic feature with the largest semantic base difference.

[0134] For semantic users 1, …, N, the semantic feature rearrangement will be performed alternately between semantic users, i.e. given x N , rearrange x N-1 ; given x N-2 , rearrange x N-3 ; until x1. The rearranged semantic features are denoted as where r represents whether the rearrangement is performed, if r = 0, it represents that no rearrangement is performed, otherwise it represents that the rearrangement is performed, and the rule followed is: for semantic feature

[0135] r i = 0, if N is even, i is even; if N is odd, i is odd;

[0136] r i = 1, if N is odd, i is even; if N is even, i is odd.

[0137] ​Step S240, superimposing the first semantic feature sets and the second semantic feature sets to obtain superimposed semantic feature sets, and sending the superimposed semantic feature sets to the user terminals.

[0138] In some example embodiments, the superimposing the first semantic feature sets and the second semantic feature sets to obtain superimposed semantic feature sets, and sending the superimposed semantic feature sets to the user terminals comprises:

[0139] Determining a decoding order of the user terminals according to channel parameters of the user terminals;

[0140] Allocating transmission power for the first semantic feature sets and the second semantic feature sets based on the decoding order;

[0141] Superimposing the first semantic feature sets and the second semantic feature sets to obtain the superimposed semantic feature sets based on the transmission power;

[0142] Sending the superimposed semantic feature sets to the user terminals based on the transmission power.

[0143] In implementation, the superimposed transmission of the rearranged features and the unrearranged semantic features can suppress semantic interference. Whether to rearrange and the original order before rearrangement are informed to each semantic user through other links, and it is assumed that the transmission is reliable.

[0144] As a specific example:

[0145] The semantic features of each user are first subjected to power normalization processing, and the access point divides the total power into N parts and allocates them to N users. To achieve efficient serial interference cancellation at the receiving end, the base station determines the decoding order of the receiving end according to the channel conditions of each user, and allocates different powers to the information of different users accordingly. The channel gain of semantic user i to the base station is represented as wherein the path loss PL(d i ) and the small-scale fading g i are included. The path loss is specifically modeled as:

[0146]

[0147] wherein ρ0 is the path loss at a reference distance d0 = 1 m, and l is the path loss factor. The small-scale fading is modeled as a Rice distribution, and it is assumed that the small-scale fading of all semantic users to the base station is the same. As can be seen from the above, the greater the distance between the semantic user and the base station, the greater the path loss and the smaller the channel gain. Under the assumption of d1 < d2 < … < d N , it can be obtained that |h1| 2 | < |h2|2 >…>|h N | 2 Definition of an auxiliary item for indicating the decoding order of the receiving end, denoted as

[0148]

[0149] Wherein, σ 2 represents the noise power, it is usually assumed that the noise power at each user is the same, so the decoding order auxiliary item relationship is G1>G2>…>G N . G i is smaller, indicating that the decoding order is earlier, so the decoding order of each user at the receiving end is π=[N,…,1], the user number indicating the earlier decoding, the order will be synchronized to each user by the base station. Based on the decoding order list π, the power allocated to different semantic users satisfies P1<P2<…<P N , so the signal transmitted by the base station is represented as:

[0150]

[0151] It should be noted that for semantic features x N Although the x N-2 is not rearranged based on the semantic base difference, but because the power allocated to this feature is low, the semantic interference from x N-2 to x1 and other non-rearranged semantic features is small, and the semantic interference from x N-1 is still the main interference, using the proposed feature rearrangement method based on semantic base difference to suppress the main interference, that is, to improve the decoding performance of x N , and further improve the decoding performance of subsequent other semantic features.

[0152] In the downlink scenario, the base station is the sending end and the user terminal is the receiving end. In the above exemplary embodiment, the semantic base-based multi-user information transmission method based on the base station is introduced. When the base station is the sending end, the following will introduce the semantic base-based multi-user information transmission method based on the user terminal when the user terminal is the receiving end.

[0153] Reference Figure 5 When the user terminal is the receiving end, the semantic base-based multi-user information transmission method based on the user terminal includes the following steps:

[0154] Step S510, receiving the superimposed semantic feature set sent by the base station.

[0155] In specific implementation:

[0156] At the receiving end, the signal received by each semantic user is represented as:

[0157]

[0158] z i is a Gaussian white noise.

[0159] Step S520, in response to determining that the decoding order corresponding to the user terminal is ranked first, decoding the superimposed semantic feature set to obtain the source information corresponding to the user terminal.

[0160] Step S530, in response to determining that the decoding order corresponding to the user terminal is not ranked first, performing serial interference cancellation on the superimposed semantic feature set to obtain a semantic feature set corresponding to the user terminal, and decoding the semantic feature set to obtain the source information corresponding to the user terminal.

[0161] In some example embodiments, the decoding of the semantic feature set to obtain the source information corresponding to the user terminal comprises:

[0162] In response to determining that the semantic feature set has been processed by rearrangement, restoring the semantic feature set to obtain a restored semantic feature set;

[0163] Decoding the restored semantic feature set to obtain the source information corresponding to the user terminal.

[0164] As a specific example:

[0165] N users adopt different signal detection strategies. Semantic user N has the worst channel condition, but the highest transmission power, so the interference from other N-1 semantic user symbols can be regarded as noise, and the joint semantic channel decoder can be directly used for decoding the information of itself. The joint semantic channel decoder is also composed of a deep neural network, which is similar to the joint semantic encoder, and the specific neural network structure is determined by the source mode and transmission demand. The decoding process is represented as:

[0166]

[0167] The transfer function of the joint semantic channel decoder is represented, and β is a set of decoder neural network parameters. The channel condition of semantic user N-1 is better than that of semantic user N, and the power is the second highest, so it is strongly interfered by semantic user N. The interference of semantic user N needs to be eliminated first by using the serial interference cancellation method, and then the symbol of itself is interpreted. The symbols of the remaining N-2 semantic users are regarded as noise. The remaining semantic users follow the same principle and sequentially eliminate the semantic interference of the semantic user with higher power, and then interpret the symbol of itself. However, due to the continuity of the semantic characteristics, the demodulation-remodulation-elimination idea adopted by the existing serial interference cancellation method cannot be implemented. Therefore, the present scheme realizes the serial interference cancellation of the semantic characteristics of the source information based on the semantic basis, estimates and interprets the interference and target semantic characteristics by using the difference of the semantic basis, and suppresses the expression of other non-target semantic characteristics in the process, thereby improving the decoding accuracy of the to-be-decoded semantic characteristics, and then realizing the elimination of interference. At semantic user i, 1≤i<N, the serial interference cancellation process for the semantic characteristics of the source information is shown in Figure 6 , and specifically:

[0168] Step 1: Detecting the received signal y i , obtaining j is the user number at the top of the current decoding order list;

[0169] Step 2: Determine whether user i is the first decoded user. If yes, directly decode; otherwise, the decoding of user j needs to be completed first.

[0170] Step 3: Determine whether is rearranged based on the difference of the semantic basis at the sending end. If r j =1, first restore to the original order, that is, , and then use the joint semantic channel decoder to reconstruct the source information sent to user j, that is,

[0171] Step 4: Use the joint semantic channel encoder to map the reconstructed information of user j to the semantic characteristics to estimate the interference from user j. If r j =1, rearrangement also needs to be performed at this step, which is represented as

[0172] Step 5: Subtract from the received signal y i to obtain

[0173]

[0174] Step 6: User j is deleted from the decoding order list, and the updated user sequence number is the first in the current list, if user i is not the first decoded user, steps 3 to 5 are continued to be executed, otherwise, the symbol of user i is decoded;

[0175] Step 7: If r i = 1, the original order is restored first, that is, Based on The information sent to user i is reconstructed by using a joint semantic channel decoder, that is,

[0176] In summary, the specific transmission process of the downlink scenario is as follows:

[0177] Step 1: The base station extracts semantic features from the source information of each semantic user by using a joint semantic channel encoder;

[0178] Step 2: The base station evaluates the semantic feature based on the semantic base difference by using a semantic feature rearrangement module based on the semantic base difference, and rearranges the features of part of the semantic users according to the semantic base difference, and records the semantic feature rearrangement information;

[0179] Step 3: The decoding order of the receiving end is determined according to the channel state of the semantic user, and different powers are allocated to the semantic features of each user, which are superimposed and transmitted to each user, at the same time, the semantic feature rearrangement information and the decoding order are reliably transmitted to the user by using other links;

[0180] Step 4: The semantic user performs a serial interference cancellation process based on the semantic base difference based on the semantic feature rearrangement information and the decoding order, to obtain the semantic features of each user;

[0181] Step 5: The semantic user recovers the source information based on the separated semantic features by using a joint semantic channel decoder.

[0182] In the above exemplary embodiment, a semantic base based multi-user information transmission method implemented in a downlink scenario is introduced, in which the base station is the sending end and the user terminal is the receiving end. In the following, a semantic base based multi-user information transmission method implemented in an uplink scenario is introduced, in which the user terminal is the sending end and the base station is the receiving end.

[0183] Referring to Figure 7 When the user terminal is the sending end, the semantic base based multi-user information transmission method implemented based on the user terminal includes the following steps:

[0184] Step S710, determining the source information to be sent to the base station.

[0185] ​In step S720, semantic feature extraction is performed on the source information based on a plurality of semantic feature extraction manners to obtain a third semantic feature set corresponding to the source information, wherein the third semantic feature set includes a plurality of semantic features obtained based on the plurality of semantic feature extraction manners.

[0186] In step S730, the third semantic feature set is sent to the base station in response to determining that the user terminal does not participate in rearrangement.

[0187] In step S740, the plurality of semantic features in the third semantic feature set are rearranged based on the differences between the plurality of semantic features in the third semantic feature set in response to determining that the user terminal participates in rearrangement, to obtain a fourth semantic feature set, and the fourth semantic feature set is sent to the base station.

[0188] Reference Figure 8 When the base station is a receiving end, a semantic base-based multi-user information transmission method implemented by the base station includes the following steps:

[0189] In step S810, a superimposed semantic feature set sent by a plurality of user terminals is received.

[0190] In step S820, a decoding order of the plurality of user terminals is determined according to channel parameters of the plurality of user terminals.

[0191] In step S830, a plurality of semantic feature sets are obtained by performing serial interference cancellation on the superimposed semantic feature set based on the decoding order, and source information corresponding to the semantic feature sets is obtained by decoding the semantic feature sets.

[0192] As a specific example, the present disclosure implements semantic base-based uplink information transmission by using the system framework shown in Figure 9 The distance between the user and the base station satisfies d1<d2<…<d N Wherein, the joint semantic channel encoder and the semantic feature rearrangement module based on semantic base difference are deployed at each semantic user of the sending end, and the specific semantic information encoding process is the same as that in the downlink transmission scenario, which uses the joint semantic channel encoder to extract the semantic features x i of the source information. The base station determines the semantic user sequence number that needs to participate in rearrangement based on the number N of users, and the specific rule is the same as that used in the downlink scenario, and the corresponding user is notified before uplink communication. Since the semantic base does not change with the change of the source information under the same type of source, the evaluation of the semantic base difference can be completed based on the semantic features of a single user, so the semantic user participating in rearrangement can evaluate the differences between the semantic bases based on its own semantic features, and complete the rearrangement of its own semantic information accordingly. The specific rearrangement manner is similar to that in the downlink scenario, which is as follows: Figure 9As shown. The semantic feature rearrangement information of the users participating in the rearrangement is represented as follows: During uplink transmission, each user performs power constraint processing on the rearranged and unrearranged semantic features using their own power and then transmits them. The semantic features of each user are superimposed into a single information stream in the wireless channel; simultaneously, the rearranged information... It is also synchronized to the base station via other links, and is assumed to be orthogonal and reliable transmission.

[0193] At the base station side of the receiving end, based on the channel conditions |h1| of each semantic user... 2 >|h2| 2 >…>|h N | 2 The relationship of the corresponding decoding order auxiliary terms is G. N >G N-1 >…>G1. Unlike the downlink scenario, in the uplink scenario, the receiver first needs to decode and remove users with better channel conditions from the received signal to ensure that the channels of users with poorer channel quality can be correctly decoded. Therefore, the decoding order in the uplink scenario is π = [1,…,N], which is determined by the base station and does not need to be synchronized with each user. The signal received by the base station is represented as…

[0194]

[0195] Semantic feature rearrangement information based on the decoding sequence list π synchronized with the user Base stations can be used Figure 6 The serial interference cancellation method based on semantic basis difference shown iteratively separates the semantic features of each semantic user and uses a joint semantic channel decoder to reconstruct the corresponding source information.

[0196] In summary, the specific transmission process for the uplink scenario is as follows:

[0197] Step 1: The base station determines the semantic user sequence number that needs to participate in the reordering and notifies the corresponding semantic user;

[0198] Step 2: Each semantic user extracts semantic features from the source information using the joint semantic channel encoder;

[0199] Step 3: Semantic users who need to participate in the reordering use the semantic feature reordering module based on semantic basis differences to evaluate the semantic basis differences between their own semantic features, rearrange the features accordingly, and record the semantic feature reordering information.

[0200] Step 4: Each user transmits semantic features at its own power, while the semantic feature rearrangement information is reliably transmitted to the base station using other links;

[0201] Step 5: The base station determines the decoding order according to the channel state of each user, and performs a semantic-based difference-based serial interference cancellation process based on the semantic feature rearrangement information to obtain the semantic features of each user;

[0202] Step 6: The base station uses a joint semantic channel decoder to recover the source information based on the separated semantic features.

[0203] The proposed semantic-based difference-based non-orthogonal semantic information transmission method is implemented based on a neural network and needs to be trained offline based on a large amount of data, so that the joint semantic channel encoder and decoder learns an efficient and robust semantic feature encoding and decoding strategy under the non-orthogonal transmission condition. The loss function used for training is the weighted sum of the average absolute error of the reconstruction of the semantic source information of all semantic users, which is represented as:

[0204]

[0205] The training of the joint semantic channel encoder and decoder adopts an end-to-end manner, and the semantic feature rearrangement based on semantic-based difference and the serial interference cancellation process based on semantic-based difference are included in the training, so that the joint semantic channel encoder and decoder can more directly understand the differences between the semantic features and the interference between the users, and further learn a more efficient, comprehensive and robust semantic feature extraction method and decoding strategy. When the training is completed, the joint semantic channel encoder and decoder are respectively deployed at the base station side and each user, and the semantic feature rearrangement module based on semantic-based difference does not need to be trained, and only needs to be deployed in the corresponding manner at the base station and the semantic users.

[0206] In the present disclosure, a non-orthogonal communication method for multiple user source semantic features is proposed, which significantly improves the efficiency of multi-user semantic transmission.

[0207] In the present disclosure, a semantic feature rearrangement method based on semantic-based difference is proposed, which effectively suppresses the semantic interference between multiple semantic users.

[0208] In the present disclosure, a serial interference cancellation method based on semantic-based difference is proposed, which further reduces the semantic interference between multiple semantic users.

[0209] Compared with other non-orthogonal semantic communication design schemes, the present disclosure designs a semantic feature rearrangement method based on semantic-based difference and a serial interference cancellation method based on semantic-based difference.

[0210] Firstly, the semantic-based non-orthogonal source semantic feature encoding and decoding method proposed in the present disclosure can realize efficient and robust semantic feature extraction and interpretation under semantic interference, and only needs to train one set of encoder and decoder for multiple users, which is suitable for point-to-point communication and multi-user non-orthogonal communication and has stronger scalability.

[0211] Secondly, the semantic feature rearrangement method based on semantic base difference provided by the present disclosure effectively suppresses the semantic interference between the semantic features of multiple users by using the difference between the semantic bases to construct the misplacement on the semantic coding, thereby improving the reconstruction quality of the source information and the semantic transmission efficiency of the multi-user semantic communication system.

[0212] Finally, the serial interference cancellation method based on semantic base difference provided by the present disclosure can realize the serial cancellation of the semantic interference between the semantic features by using the semantic coding and decoding functions of the semantic bases and the difference between the semantic bases according to the continuous characteristics of the semantic features, thereby providing effective support for the multi-user detection of the non-orthogonal semantic communication system.

[0213] It should be noted that the method of the present disclosure can be executed by a single device, such as a computer or a server. The method of the present disclosure can also be applied to a distributed scenario and completed by multiple devices in cooperation. In the case of such a distributed scenario, one of the multiple devices can only execute one or more steps in the method of the present disclosure, and the multiple devices can interact with each other to complete the method.

[0214] It should be noted that some embodiments of the present disclosure have been described above. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in a different order than the order described above and still achieve the desired result. In addition, the processes depicted in the figures do not necessarily require the particular order shown or sequential order to achieve the desired results. In certain implementations, multitasking and parallel processing can be advantageous or required.

[0215] Based on the same inventive concept, the present disclosure also provides a semantic base based multi-user information transmission device corresponding to the method of any of the above embodiments.

[0216] Reference Figure 10 The semantic base based multi-user information transmission device is applied to a base station, and the device comprises the following modules:

[0217] The first source information determination module 1010 is configured to determine a plurality of source information to be sent to a plurality of user terminals;

[0218] The first semantic feature extraction module 1020 is configured to perform semantic feature extraction on each of the source information based on a plurality of semantic feature extraction manners, to obtain a first semantic feature set corresponding to each of the source information, wherein the first semantic feature set comprises a plurality of semantic features obtained based on the plurality of semantic feature extraction manners;

[0219] The first semantic feature rearranging module 1030 is configured to rearrange the semantic features in the first semantic feature set based on the differences between the semantic features in the first semantic feature set, to obtain a second semantic feature set.

[0220] The first semantic feature sending module 1040 is configured to superimpose the first semantic feature set and the second semantic feature set to obtain a superimposed semantic feature set, and send the superimposed semantic feature set to the user terminal.

[0221] In some example embodiments, the first semantic feature rearranging module 1030 is specifically configured to:

[0222] For N first semantic feature sets, the first semantic feature sets are sorted in ascending order of the distances between the user terminals corresponding to the first semantic feature sets and the base station;

[0223] The semantic features in the N-1th first semantic feature set are rearranged based on the differences between the semantic features in the N-1th first semantic feature set, to obtain a first second semantic feature set;

[0224] The semantic features in the N-2th first semantic feature set are rearranged based on the differences between the semantic features in the N-2th first semantic feature set, to obtain a second second semantic feature set;

[0225] The above steps are repeated until there is no first semantic feature set to be rearranged, to obtain a plurality of second semantic feature sets.

[0226] In some example embodiments, the first semantic feature rearranging module 1030 is specifically configured to:

[0227] Determine the sequence number of each semantic feature in the first semantic feature set;

[0228] Determine the difference parameter between each two semantic features in the first semantic feature set;

[0229] Pair the semantic features with the purpose of maximizing the difference parameter between the two semantic features, and determine the sequence number of the paired semantic features;

[0230] Rearrange the sequence number sequence composed of the sequence number of each semantic feature in the first semantic feature set based on the sequence number of the paired semantic features, to obtain a rearranged sequence number sequence;

[0231] rearrange the order of the plurality of semantic features in the first semantic feature set to be rearranged based on the rearranged sequence of serial numbers, to obtain the second semantic feature set.

[0232] In some example embodiments, the first semantic feature rearranging module 1030 is specifically configured to:

[0233] determine a serial number of each of the plurality of semantic features in the first semantic feature set to be rearranged;

[0234] rearrange the order of the plurality of semantic features in the first semantic feature set to be rearranged based on the rearranged sequence of serial numbers, to obtain the second semantic feature set.

[0235] In some example embodiments, the first semantic feature sending module 1040 is specifically configured to:

[0236] determine a decoding order of the plurality of user terminals based on the channel parameters of the plurality of user terminals;

[0237] assign transmission power to the first semantic feature set and the second semantic feature set based on the decoding order;

[0238] superimpose a plurality of the first semantic feature sets and a plurality of the second semantic feature sets based on the transmission power, to obtain the superimposed semantic feature set;

[0239] send the superimposed semantic feature set to the plurality of user terminals based on the transmission power.

[0240] In some example embodiments, the source information to be sent to different user terminals is different.

[0241] In some example embodiments, the semantic feature extraction manner includes an encoding function, and the first semantic feature extracting module 1020 is specifically configured to:

[0242] extract semantic features from each of the source information based on a plurality of the encoding functions, to obtain the first semantic feature set corresponding to each of the source information, the first semantic feature set including a plurality of semantic features obtained based on a plurality of the encoding functions.

[0243] In some example embodiments, the semantic features obtained based on different semantic feature extraction manners are different.

[0244] Reference Figure 11 A semantic base-based multi-user information transmission device applied to a user terminal, the device comprising the following modules:

[0245] The first semantic feature receiving module 1110 is configured to receive the superimposed semantic feature set sent by the base station.

[0246] The first semantic feature decoding module 1120 is configured to, in response to determining that the decoding order corresponding to the user terminal is ranked first, decode the superimposed semantic feature set to obtain the source information corresponding to the user terminal.

[0247] The first serial interference cancellation module 1130 is configured to, in response to determining that the decoding order corresponding to the user terminal is not ranked first, perform serial interference cancellation on the superimposed semantic feature set to obtain a semantic feature set corresponding to the user terminal, and decode the semantic feature set to obtain the source information corresponding to the user terminal.

[0248] In some example embodiments, the first serial interference cancellation module 1130 is specifically configured to:

[0249] in response to determining that the semantic feature set has been processed by rearrangement, restore the semantic feature set to obtain a restored semantic feature set;

[0250] decode the restored semantic feature set to obtain the source information corresponding to the user terminal.

[0251] Reference Figure 12 The semantic base-based multi-user information transmission device is applied to a user terminal, and the device comprises the following modules:

[0252] The second source information determining module 1210 is configured to determine source information to be sent to a base station.

[0253] The second semantic feature extraction module 1220 is configured to perform semantic feature extraction on the source information based on a plurality of semantic feature extraction manners to obtain a third semantic feature set corresponding to the source information, the third semantic feature set comprising a plurality of semantic features obtained based on the plurality of semantic feature extraction manners.

[0254] The second semantic feature sending module 1230 is configured to, in response to determining that the user terminal does not participate in rearrangement, send the third semantic feature set to the base station.

[0255] The second semantic feature rearrangement module 1240 is configured to, in response to determining that the user terminal participates in rearrangement, rearrange the plurality of semantic features in the third semantic feature set based on the differences between the plurality of semantic features to obtain a fourth semantic feature set, and send the fourth semantic feature set to the base station.

[0256] ReferenceFigure 13 The semantic base-based multi-user information transmission device is applied to a base station, and comprises the following modules:

[0257] The second semantic feature receiving module 1310 is configured to receive a superimposed semantic feature set sent by a plurality of user terminals.

[0258] The second semantic feature decoding module 1320 is configured to determine a decoding order of the plurality of user terminals according to channel parameters of the plurality of user terminals.

[0259] The second serial interference cancellation module 1330 is configured to perform serial interference cancellation on the superimposed semantic feature set based on the decoding order, to obtain a plurality of semantic feature sets, and decode the semantic feature sets to obtain source information corresponding to the semantic feature sets.

[0260] For the convenience of description, the above device is described in various modules according to functions. Of course, the functions of the modules can be implemented in one or more software and / or hardware when the present disclosure is implemented.

[0261] The device of the above embodiment is used to implement the corresponding semantic base-based multi-user information transmission method in any of the above embodiments, and has the beneficial effects of the corresponding method embodiments, which are not described here again.

[0262] Based on the same inventive concept, the present disclosure also provides an electronic device corresponding to the method of any of the above embodiments, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the semantic base-based multi-user information transmission method of any of the above embodiments when executing the program.

[0263] Figure 14 A more specific hardware structure of an electronic device is shown, which can include a processor 1410, a memory 1420, an input / output interface 1430, a communication interface 1440, and a bus 1450. The processor 1410, the memory 1420, the input / output interface 1430, and the communication interface 1440 are connected to each other through the bus 1450 for communication within the device.

[0264] The processor 1410 can be implemented in the form of a general-purpose CPU (Central Processing Unit), a microprocessor, an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits, etc., for executing related programs to implement the technical solutions provided by the embodiments of the present disclosure.

[0265] The memory 1420 can be implemented in the form of a ROM (Read Only Memory), a RAM (Random Access Memory), a static storage device, a dynamic storage device, etc. The memory 1420 can store an operating system and other application programs, and when the technical solutions provided by the embodiments of the present specification are implemented by software or firmware, the related program codes are stored in the memory 1420 and are invoked and executed by the processor 1410.

[0266] The input / output interface 1430 is configured to connect an input / output module to realize information input and output. The input / output module can be configured as a component in the device (not shown in the figure) or can be externally connected to the device to provide corresponding functions. The input device can include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device can include a display, a speaker, a vibrator, an indicator light, etc.

[0267] The communication interface 1440 is configured to connect a communication module (not shown in the figure) to realize the communication interaction between the device and other devices. The communication module can realize communication through a wired manner (such as a USB, a network cable, etc.) or through a wireless manner (such as a mobile network, WIFI, Bluetooth, etc.).

[0268] The bus 1450 includes a channel to transmit information between various components (such as the processor 1410, the memory 1420, the input / output interface 1430, and the communication interface 1440) of the device.

[0269] It should be noted that although the above device only shows the processor 1410, the memory 1420, the input / output interface 1430, the communication interface 1440, and the bus 1450, in the specific implementation process, the device can also include other components necessary for normal operation. In addition, those skilled in the art can understand that the above device can also only include the components necessary to implement the embodiments of the present specification, and does not have to include all the components shown in the figure.

[0270] The electronic device of the above embodiments is used to implement the corresponding semantic-based multi-user information transmission method in any of the preceding embodiments, and has the beneficial effects of the corresponding method embodiments, which are not described here.

[0271] Based on the same inventive concept, the present disclosure also provides a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the semantic-based multi-user information transmission method according to any of the above embodiments.

[0272] The computer readable medium of the present embodiments includes permanent and non-permanent, removable and non-removable media can be implemented by any method or technology to store information. The information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible by a computing device.

[0273] The above non-transitory computer readable storage medium can be any available medium or data storage device that can be accessed by a computer, including but not limited to magnetic storage (e.g. floppy disk, hard disk, magnetic tape, magneto-optical disk (MO) and the like), optical storage (e.g. CD, DVD, BD, HVD and the like), and semiconductor memory (e.g. ROM, EPROM, EEPROM, non-volatile memory (NAND FLASH), solid state disk (SSD)) and the like.

[0274] The storage medium of the above embodiments stores computer instructions for causing the computer to perform the semantic-based multi-user information transmission method as described in any of the above exemplary method embodiments, and has the beneficial effects of the corresponding method embodiments, which are not repeated here.

[0275] Based on the same inventive concept, corresponding to the semantic-based multi-user information transmission method described in any of the above embodiments, the present disclosure also provides a computer program product comprising computer program instructions. In some embodiments, the computer program instructions can be executed by one or more processors of a computer to cause the computer and / or the processor to perform the semantic-based multi-user information transmission method. Corresponding to the execution subject of each step in each embodiment of the semantic-based multi-user information transmission method, the processor performing the corresponding step can belong to the corresponding execution subject.

[0276] The computer program product of the above embodiments is used to cause the computer and / or the processor to perform the semantic-based multi-user information transmission method as described in any of the above embodiments, and has the beneficial effects of the corresponding method embodiments, which are not repeated here.

[0277] Those skilled in the art will appreciate that embodiments of the disclosure can be practiced in a variety of system environments, and that the application is not limited to any particular type of computing environment. Embodiments of the application can be implemented as a method, apparatus, or computer program product. Accordingly, the application can take the form of an entirely hardware embodiment, an entirely software embodiment (including firmware, resident software, micro-code, etc.) or an embodiment combining software and hardware aspects that can all generally be referred to herein as a "circuit," "module" or "system." Furthermore, embodiments of the application can take the form of a program product embodied in one or more computer readable medium(s) having computer readable program code embodied thereon.

[0278] Any combination of one or more computer readable medium(s) can be utilized. The computer readable medium can be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In this document, the computer readable storage medium can be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

[0279] A computer readable signal medium can include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated signal can take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium can be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

[0280] Program code embodied on a computer readable medium can be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0281] Computer program code for carrying out operations of the present disclosure can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0282] It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0283] These computer program instructions can also be stored in a computer- readable medium that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable medium produce an article of manufacture including instructions which implement the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0284] The computer program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0285] Further, although the operations of the method(s) of the present disclosure are described in a particular, sequential order, this should not be understood as a requirement or interpreted as a limitation, and alternatively, the operations can be fully or partially performed in parallel, adaptations or different sequences can be employed. For example, described steps or operations can be performed in an order different than that described, two or more steps or operations can be consolidated into a single step or operation, and / or a step or operation can be separated into several sub-steps or sub-operations.

[0286] The computer program product of the present application can be a computer program embodied on a non-transitory computer readable medium. The body of computer program instructions can be a source file, object file, executable file, or any other tangible form of computer program instructions. The computer program product can be supplied on a non-transitory computer readable medium such as a floppy disk, a hard disk, a CD ROM, a DVD, a memory stick, a memory card, a RAM, a ROM, a PROM, an EPROM, an EEPROM, a FLASH memory, a magnetic or optical card, a battery, a server, a cloud, a network, or any other non-transitory computer readable medium. The computer program product can be supplied on a non-transitory computer readable medium such as a floppy disk, a hard disk, a CD ROM, a DVD, a memory stick, a memory card, a RAM, a ROM, a PROM, an EPROM, an EEPROM, a FLASH memory, a magnetic or optical card, a battery, a server, a cloud, a network, or any other non-transitory computer readable medium. The computer program product can be supplied on a non-transitory computer readable medium such as a floppy disk, a hard disk, a CD ROM, a DVD, a memory stick, a memory card, a RAM, a ROM, a PROM, an EPROM, an EEPROM, a FLASH memory, a magnetic or optical card, a battery, a server, a cloud, a network, or any other non-transitory computer readable medium.

[0287] It should be noted that although several modules or units for a device for action performance are mentioned in the above detailed description, such a division is not mandatory. Indeed, according to an embodiment of the application, the features and functionalities of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functionalities of one module or unit described above can be further divided into embodied by several modules or units.

[0288] It should be understood by those of ordinary skill in the art that the above discussion of any of the embodiments is merely exemplary in nature and not intended to imply limitations on the scope of the application, including the claims. Various modifications can be made to the embodiments and / or different combinations of technical features from different embodiments can be made within the scope of the application, steps can be implemented in any order, and there are many other variations of the different aspects of the embodiments of the application as discussed above, which are not explicitly described, but which would be apparent to those of skill in the art in light of this disclosure.

[0289] In addition, to simplify the illustration and discussion, and so as not to make the embodiments of the application difficult to understand, the known power / ground connections of integrated circuit (IC) chips and other components can or can not be shown in the provided drawings. Furthermore, devices can be shown in block diagram form in order to avoid making the embodiments of the application difficult to understand, and this also takes into account the fact that the details of implementation of these block diagram devices are highly dependent on the platform on which the embodiments of the application are to be implemented (i.e., these details should be well within the understanding of those skilled in the art). Where specific details (e.g., circuitry) are set forth in order to describe an illustrative embodiment of the application, it should be understood that the embodiment of the application can be practiced without these specific details. The description is thus to be considered in all respects as illustrative and not restrictive.

[0290] While the present application has been described in connection with certain embodiments thereof, many modifications, substitutions, and alterations, thereof, will be apparent to those of ordinary skill in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) can use the embodiments discussed.

[0291] It is intended to encompass all such alternatives, modifications, and variations that fall within the broad scope of the appended claims. Accordingly, any one or more features of any element in the drawings, or the specification, can be combined to create modifications, equivalents, or alternatives.

[0292] While the principles of the disclosure have been described above in connection with specific embodiments, it is to be understood that this disclosure is not limited to the disclosed embodiments, but is instead applicable to various modifications and equivalent arrangements. The scope of the appended claims encompasses all such alternatives, modifications and variations as fall within the scope of the claims. The claims are not to be interpreted to be limited to the features or combinations explicitly described herein. Rather, the features or combinations can be combined with each other in any manner permitted by the scopes of the claims.

Claims

1. A method for multi-user information transmission based on semantic bases, characterized in that, The method applied to a base station comprises: determining a plurality of source information to be sent to a plurality of user terminals; performing semantic feature extraction on each of the source information based on a plurality of semantic feature extraction manners to obtain a first semantic feature set corresponding to each of the source information, the first semantic feature set including a plurality of semantic features obtained based on the plurality of semantic feature extraction manners; for N first semantic feature sets, sorting the first semantic feature sets in ascending order of distance between the user terminals corresponding to the first semantic feature sets and the base station, and rearranging the semantic features in an (N-1)th first semantic feature set based on the difference between the semantic features in the (N-1)th first semantic feature set to obtain a first second semantic feature set, rearranging the semantic features in an (N-2)th first semantic feature set based on the difference between the semantic features in the (N-2)th first semantic feature set to obtain a second second semantic feature set, and repeating the above steps until there is no first semantic feature set to be rearranged to obtain a plurality of second semantic feature sets, wherein the rearranging process includes determining a serial number of each semantic feature in the first semantic feature set, determining a difference parameter between each two semantic features in the first semantic feature set, pairing the semantic features to maximize the difference parameter between the two semantic features, determining a serial number of the paired semantic features, rearranging a serial number sequence composed of the serial numbers of the semantic features in the first semantic feature set based on the serial numbers of the paired semantic features to obtain a rearranged serial number sequence, and rearranging the order of the semantic features in the first semantic feature set to be rearranged based on the rearranged serial number sequence to obtain the second semantic feature set; superimposing the first semantic feature sets that have not been rearranged and the second semantic feature sets to obtain a superimposed semantic feature set, and sending the superimposed semantic feature set to the plurality of user terminals.

2. The method of claim 1, wherein, The rearranging the order of the semantic features in the first semantic feature set to be rearranged based on the rearranged serial number sequence to obtain the second semantic feature set comprises: determining a serial number of each semantic feature in the first semantic feature set to be rearranged; rearranging the order of the semantic features in the first semantic feature set to be rearranged based on the rearranged serial number sequence to obtain the second semantic feature set.

3. The method of claim 1, wherein, The superimposing the first semantic feature sets that have not been rearranged and the second semantic feature sets to obtain a superimposed semantic feature set, and sending the superimposed semantic feature set to the plurality of user terminals comprises: determining a decoding order of the plurality of user terminals based on channel parameters of the plurality of user terminals; assigning transmission power to the first semantic feature sets and the second semantic feature sets based on the decoding order. superimpose a plurality of the first semantic feature sets and a plurality of the second semantic feature sets based on the transmission power, to obtain the superimposed semantic feature set; transmit the superimposed semantic feature set to the plurality of user terminals based on the transmission power.

4. The method of claim 1, wherein, The method comprises: The source information to be transmitted to different user terminals is different.

5. The method of claim 1, wherein, The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function.

6. The method of claim 1, wherein, The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function.

7. A method for multi-user information transmission based on semantic bases, characterized in that, The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises an encoding function. The semantic feature extraction mode comprises receive a superimposed semantic feature set sent by a base station; wherein the superimposed semantic feature set is obtained by: determining a plurality of source information to be sent to a plurality of user terminals; performing semantic feature extraction on each of the source information based on a plurality of semantic feature extraction manners to obtain a first semantic feature set corresponding to each of the source information, the first semantic feature set including a plurality of semantic features obtained based on the plurality of semantic feature extraction manners; for N first semantic feature sets, sorting the first semantic feature sets in ascending order of distance between the user terminals corresponding to the first semantic feature sets and the base station; rearranging the semantic features in an (N-1)th first semantic feature set based on the difference between the semantic features in an Nth first semantic feature set to obtain a first second semantic feature set; rearranging the semantic features in an (N-2)th first semantic feature set based on the difference between the semantic features in an (N-3)th first semantic feature set to obtain a second second semantic feature set; repeating the above steps until there is no first semantic feature set to be rearranged, to obtain a plurality of second semantic feature sets; wherein the rearrangement process includes: determining a serial number of each semantic feature in the first semantic feature set; determining a difference parameter between each two semantic features in the first semantic feature set; pairing the semantic features to maximize the difference parameter between the semantic features, and determining a serial number of the paired semantic features; rearranging a serial number sequence composed of the serial numbers of the semantic features in the first semantic feature set based on the serial numbers of the paired semantic features to obtain a rearranged serial number sequence; rearranging the order of the semantic features in the first semantic feature set to be rearranged based on the rearranged serial number sequence to obtain the second semantic feature set; superimposing the first semantic feature sets that have not been rearranged and the second semantic feature sets in a wireless channel to obtain the superimposed semantic feature set; in response to determining that the decoding order corresponding to the user terminal is the first, decoding the superimposed semantic feature set to obtain the source information corresponding to the user terminal; or, in response to determining that the decoding order corresponding to the user terminal is not the first, performing serial interference cancellation on the superimposed semantic feature set to obtain a semantic feature set corresponding to the user terminal, and decoding the semantic feature set to obtain the source information corresponding to the user terminal.

8. The method of claim 7, wherein, The decoding of the semantic feature set to obtain the source information corresponding to the user terminal includes: in response to determining that the semantic feature set has been rearranged, restoring the semantic feature set to obtain a restored semantic feature set; decoding the restored semantic feature set to obtain the source information corresponding to the user terminal.

9. A method for multi-user information transmission based on semantic bases, characterized in that, The method applied to a user terminal includes: determining source information to be sent to a base station; extracting semantic features of the source information based on a plurality of semantic feature extraction manners to obtain a third semantic feature set corresponding to the source information, the third semantic feature set including a plurality of semantic features obtained based on the plurality of semantic feature extraction manners; in response to determining that the user terminal does not participate in rearrangement, sending the third semantic feature set to the base station; in response to determining that the user terminal participates in rearrangement, wherein the process of rearrangement includes: determining the serial number of each semantic feature in the third semantic feature set; determining the difference parameter between each two semantic features in the third semantic feature set; pairing the semantic features with the purpose of maximizing the difference parameter between the two semantic features, determining the serial number of the paired semantic features; rearranging the serial number sequence composed of the serial number of each semantic feature in the third semantic feature set based on the serial number of the paired semantic features, to obtain a rearranged serial number sequence; rearranging the order of the plurality of semantic features in the third semantic feature set to be rearranged based on the rearranged serial number sequence, to obtain a fourth semantic feature set, and sending the fourth semantic feature set to the base station, wherein the serial number is obtained based on the number of users N, and the rule is: for N third semantic feature sets, the distances between the user terminals corresponding to the third semantic feature sets and the base station are sorted in ascending order; based on the difference between the plurality of semantic features in the Nth third semantic feature set, the plurality of semantic features in the N-1th third semantic feature set are rearranged to obtain a first fourth semantic feature set; based on the difference between the plurality of semantic features in the N-2th third semantic feature set, the plurality of semantic features in the N-3th third semantic feature set are rearranged to obtain a second fourth semantic feature set; repeat the above steps until there is no third semantic feature set to be rearranged.

10. A method for multi-user information transmission based on semantic bases, characterized in that, The method applied to the base station comprises: receive a superimposed semantic feature set sent by a plurality of user terminals; wherein the superimposed semantic feature set is obtained by: determining source information to be sent to a base station; performing semantic feature extraction on the source information based on a plurality of semantic feature extraction methods to obtain a third semantic feature set corresponding to the source information, the third semantic feature set including a plurality of semantic features obtained based on the plurality of semantic feature extraction methods; in response to determining that the user terminal does not participate in rearrangement, sending the third semantic feature set to the base station; in response to determining that the user terminal participates in rearrangement, wherein the rearrangement process includes: determining the sequence number of each semantic feature in the third semantic feature set; determining the difference parameter between each two semantic features in the third semantic feature set; pairing the semantic features with the purpose of maximizing the difference parameter between the two semantic features, and determining the sequence number of the paired semantic features; rearranging the sequence number sequence composed of the sequence number of each semantic feature in the third semantic feature set based on the sequence number of the paired semantic features, to obtain a rearranged sequence number sequence; rearranging the order of the plurality of semantic features in the third semantic feature set to be rearranged based on the rearranged sequence number sequence, to obtain a fourth semantic feature set, and sending the fourth semantic feature set to the base station, wherein the sequence number is obtained based on the number of users N, and the rule is: for N third semantic feature sets, sorting the third semantic feature sets in ascending order of the distance between the user terminal corresponding to the third semantic feature set and the base station; rearranging the plurality of semantic features in the N-1th third semantic feature set based on the difference between the plurality of semantic features in the Nth third semantic feature set, to obtain a first fourth semantic feature set; rearranging the plurality of semantic features in the N-3th third semantic feature set based on the difference between the plurality of semantic features in the N-2th third semantic feature set, to obtain a second fourth semantic feature set; repeating the above steps until there is no third semantic feature set to be rearranged; superimposing the third semantic feature set that has not been rearranged and the fourth semantic feature set in a wireless channel to obtain the superimposed semantic feature set; determine the decoding order of the plurality of user terminals according to the channel parameters of the plurality of user terminals; perform serial interference cancellation on the superimposed semantic feature set based on the decoding order to obtain a plurality of semantic feature sets, and decode the semantic feature sets to obtain source information corresponding to the semantic feature sets.

11. A multi-user information transmission apparatus based on a semantic basis, characterized by The application is applied to a base station, and the device comprises: a first source information determination module configured to determine a plurality of source information to be sent to a plurality of user terminals; The first semantic feature extraction module is configured to perform semantic feature extraction on each of the source information based on a plurality of semantic feature extraction manners, to obtain a first semantic feature set corresponding to each of the source information, the first semantic feature set including a plurality of semantic features obtained based on the plurality of semantic feature extraction manners; The first semantic feature rearrangement module is configured to, for N first semantic feature sets, sort the first semantic feature sets in ascending order of distance between the user terminal and the base station corresponding to the first semantic feature sets; rearrange the plurality of semantic features in an N-1th first semantic feature set based on differences between the plurality of semantic features in the N-1th first semantic feature set, to obtain a first second semantic feature set; rearrange the plurality of semantic features in an N-2th first semantic feature set based on differences between the plurality of semantic features in the N-2th first semantic feature set, to obtain a second second semantic feature set; repeat the above steps until there is no first semantic feature set to be rearranged, to obtain a plurality of second semantic feature sets; wherein the rearrangement process includes: determining a serial number of each semantic feature in the first semantic feature set; determining a difference parameter between each two semantic features in the first semantic feature set; pairing the semantic features with the purpose of maximizing the difference parameter between two semantic features, to determine a serial number of the paired semantic features; rearranging a serial number sequence composed of the serial number of each semantic feature in the first semantic feature set based on the serial number of the paired semantic features, to obtain a rearranged serial number sequence; rearranging the order of the plurality of semantic features in the first semantic feature set to be rearranged based on the rearranged serial number sequence, to obtain the second semantic feature set; The first semantic feature sending module is configured to superimpose the first semantic feature set that has not been rearranged and the second semantic feature set, to obtain a superimposed semantic feature set, and send the superimposed semantic feature set to the plurality of user terminals.

12. A multi-user information transmission apparatus based on a semantic basis, characterized by The apparatus is applied to a user terminal, and the apparatus comprises: The first semantic feature receiving module is configured to receive a superimposed semantic feature set sent by a base station; wherein the superimposed semantic feature set is obtained in the following manner: determining a plurality of source information to be sent to a plurality of user terminals; performing semantic feature extraction on each of the source information based on a plurality of semantic feature extraction manners to obtain a first semantic feature set corresponding to each of the source information, wherein the first semantic feature set includes a plurality of semantic features obtained based on the plurality of semantic feature extraction manners; for N first semantic feature sets, sorting the first semantic feature sets in ascending order of distance between the user terminals corresponding to the first semantic feature sets and the base station; rearranging the semantic features in an N-1 first semantic feature set based on the difference between the semantic features in an N first semantic feature set to obtain a first second semantic feature set; rearranging the semantic features in an N-3 first semantic feature set based on the difference between the semantic features in an N-2 first semantic feature set to obtain a second second semantic feature set; repeating the above steps until there is no first semantic feature set to be rearranged, to obtain a plurality of second semantic feature sets; wherein the rearrangement process includes: determining the serial number of each semantic feature in the first semantic feature set; determining the difference parameter between each two semantic features in the first semantic feature set; pairing the semantic features with the purpose of maximizing the difference parameter between the two semantic features to determine the serial number of the paired semantic features; rearranging the serial number sequence composed of the serial number of each semantic feature in the first semantic feature set based on the serial number of the paired semantic features to obtain a rearranged serial number sequence; rearranging the order of the semantic features in the first semantic feature set to be rearranged based on the rearranged serial number sequence to obtain the second semantic feature set; superimposing the first semantic feature sets that have not been rearranged and the second semantic feature sets in a wireless channel to obtain the superimposed semantic feature set; The first semantic feature decoding module is configured to decode the superimposed semantic feature set to obtain the source information corresponding to the user terminal in response to determining that the decoding order corresponding to the user terminal is in the first place; The first serial interference cancellation module is configured to perform serial interference cancellation on the superimposed semantic feature set to obtain a semantic feature set corresponding to the user terminal in response to determining that the decoding order corresponding to the user terminal is not in the first place, and to decode the semantic feature set to obtain the source information corresponding to the user terminal.

13. A multi-user information transmission apparatus based on a semantic basis, characterized by The apparatus is applied to a user terminal and includes: A second source information determining module is configured to determine source information to be sent to a base station; The second semantic feature extraction module is configured to perform semantic feature extraction on the source information based on a plurality of semantic feature extraction manners to obtain a third semantic feature set corresponding to the source information, the third semantic feature set including a plurality of semantic features obtained based on the plurality of semantic feature extraction manners; The second semantic feature sending module is configured to send the third semantic feature set to the base station in response to determining that the user terminal does not participate in rearrangement; The second semantic feature rearrangement module is configured to determine the sequence number of each semantic feature in the third semantic feature set in response to determining that the user terminal participates in rearrangement, determine the difference parameter between each two semantic features in the third semantic feature set, pair the semantic features with the purpose of maximizing the difference parameter between the two semantic features, determine the sequence number of the paired semantic features, rearrange the sequence number sequence composed of the sequence number of each semantic feature in the third semantic feature set based on the sequence number of the paired semantic features, obtain a rearranged sequence number sequence, rearrange the order of the plurality of semantic features in the third semantic feature set to be rearranged based on the rearranged sequence number sequence, obtain a fourth semantic feature set, and send the fourth semantic feature set to the base station, wherein the sequence number is obtained based on the number N of users, and the rule is that for N third semantic feature sets, the distances between the user terminals corresponding to the third semantic feature sets and the base station are sorted in ascending order, the plurality of semantic features in the Nth third semantic feature set are rearranged based on the differences between the plurality of semantic features in the Nth third semantic feature set, the plurality of semantic features in the N-1th third semantic feature set are rearranged to obtain a first fourth semantic feature set, the plurality of semantic features in the N-2th third semantic feature set are rearranged based on the differences between the plurality of semantic features in the N-2th third semantic feature set, the plurality of semantic features in the N-3th third semantic feature set are rearranged to obtain a second fourth semantic feature set, and the above steps are repeated until there is no third semantic feature set to be rearranged.

14. A multi-user information transmission apparatus based on a semantic basis, characterized by, The apparatus is applied to a base station, and the apparatus comprises: The second semantic feature receiving module is configured to receive a superimposed semantic feature set sent by a plurality of user terminals; wherein the superimposed semantic feature set is obtained by: determining source information to be sent to a base station; performing semantic feature extraction on the source information based on a plurality of semantic feature extraction manners to obtain a third semantic feature set corresponding to the source information, the third semantic feature set including a plurality of semantic features obtained based on the plurality of semantic feature extraction manners; in response to determining that the user terminal does not participate in rearrangement, sending the third semantic feature set to the base station; in response to determining that the user terminal participates in rearrangement, wherein the process of rearrangement includes: determining the serial numbers of each semantic feature in the third semantic feature set; determining the difference parameters between each two semantic features in the third semantic feature set; pairing the semantic features with the purpose of maximizing the difference parameters between two semantic features, and determining the serial numbers of the paired semantic features; rearranging the serial number sequence composed of the serial numbers of each semantic feature in the third semantic feature set based on the serial numbers of the paired semantic features, to obtain a rearranged serial number sequence; rearranging the order of the plurality of semantic features in the third semantic feature set to be rearranged based on the rearranged serial number sequence, to obtain a fourth semantic feature set, and sending the fourth semantic feature set to the base station, wherein the serial numbers are obtained based on the number N of users, and the rule is: for N third semantic feature sets, sorting the third semantic feature sets in ascending order of the distance between the user terminal corresponding to the third semantic feature set and the base station; rearranging the plurality of semantic features in the N-1th third semantic feature set based on the difference between the plurality of semantic features in the Nth third semantic feature set, to obtain a first fourth semantic feature set; rearranging the plurality of semantic features in the N-3th third semantic feature set based on the difference between the plurality of semantic features in the N-2th third semantic feature set, to obtain a second fourth semantic feature set; repeating the above steps until there is no third semantic feature set to be rearranged; superimposing the third semantic feature sets that have not been rearranged and the fourth semantic feature sets in a wireless channel to obtain the superimposed semantic feature set; The second semantic feature decoding module is configured to determine the decoding order of the plurality of user terminals according to the channel parameters of the plurality of user terminals; The second serial interference cancellation module is configured to perform serial interference cancellation on the superimposed semantic feature set based on the decoding order to obtain a plurality of semantic feature sets, and decode the semantic feature sets to obtain source information corresponding to the semantic feature sets.

15. A multi-user information transmission system based on a semantic base, characterized by It includes: a base station and a user terminal; the base station is configured to perform the method as claimed in any one of claims 1 to 6, and the user terminal is configured to perform the method as claimed in any one of claims 7 to 8. The user terminal, configured to perform the method of claim 9, the base station, configured to perform the method of claim 10.

16. An electronic device, comprising: A computer program product comprising a memory and a processor, wherein the processor executes a program stored on the memory to implement the method of any of claims 1 to 6 or the method of any of claims 7 to 8 or the method of claim 9 or the method of claim 10.

17. A non-transitory computer-readable storage medium, comprising: The non-transitory computer readable storage medium stores computer instructions for causing a computer to perform the method of any of claims 1 to 6 or the method of any of claims 7 to 8 or the method of claim 9 or the method of claim 10.

18. A computer program product, characterised in that, A computer program product comprising computer program instructions to make a computer perform the method of any of claims 1 to 6 or the method of any of claims 7 to 8 or the method of claim 9 or the method of claim 10 when the computer program instructions run on the computer.

Images