Method, device, electronic device and medium for channel transmission

Abstract

The application discloses a channel transmission method, device, electronic equipment and medium. Through the application of the technical solutions, on the one hand, the semantic key can be obtained through the BLEU score in the field of machine translation, and the method for encrypting the semantic transmission information in the DLCS system is used, so that not only the safety of semantic communication is ensured, but also the problem of low key generation efficiency in a static fading environment caused by the PSK encryption technology in the related art is improved. On the other hand, the transmission subcarrier level confusion can be realized by adding dynamic false data in the transmission subcarrier, and the transmission information reliability of the DLCS system is also protected.

Description

TECHNICAL FIELD

[0001] The present application relates to a wireless communication processing technology, in particular to a channel transmission method and device, electronic equipment and medium. BACKGROUND

[0002] In the related art, a DNN-based End-to-End Communication System (DLCS) constructed using a deep neural network can effectively learn and utilize semantic information in the transmitted content, so that its communication performance in the same channel environment far exceeds that of a traditional communication system, meeting the requirements of semantic communication.

[0003] Although the DLCS exhibits strong semantic communication capabilities, it also has the problem that the information transmission is easily attacked. In the related art, a physical layer key (PLK) scheme is usually used to encrypt the transmitted information. However, due to the channel fading of the wireless channel of the communication system over time, for example, in the same static fading environment, such as an indoor Internet of Things network, the key generation rate is often very low. SUMMARY

[0004] The embodiments of the present application provide a channel transmission method, device, electronic equipment and medium. To solve the problem of low key production rate caused by using a physical layer key to encrypt the transmitted information in a DLCS system in the related art.

[0005] According to an aspect of the embodiments of the present application, a channel transmission method is provided, applied to a deep learning-based end-to-end communication system DLCS, comprising:

[0006] Obtaining to-be-sent data, and generating a semantic key for the to-be-sent data using a BLEU algorithm of bilingual evaluation understudy;

[0007] At the sending end of the DLCS, performing data encryption on the to-be-sent data based on the semantic key to obtain encrypted sending data;

[0008] Transmitting the encrypted sending data and a plurality of confusion data to the receiving end of the DLCS.

[0009] Optionally, in another embodiment based on the above-mentioned method of the present application, the BLEU algorithm of bilingual evaluation understudy is used to generate a semantic key for the to-be-sent data, comprising:

[0010] Generating a physical layer key (PLK) and using the PLK to generate an initial key stream; and using the BLEU algorithm to generate a corresponding evaluation score for the to-be-sent data;

[0011] According to the initial key stream and the evaluation score, the semantic key is generated for the to-be-sent data.

[0012] Optionally, in another embodiment based on the above method of the application, the generating the semantic key for the to-be-sent data according to the initial key stream and the evaluation score comprises:

[0013] A weight coefficient is generated for the evaluation score by using the initial key stream;

[0014] A hash value of the product of the weight coefficient and the evaluation score is calculated, and the calculation result is taken as the semantic key.

[0015] Optionally, in another embodiment based on the above method of the application, the data encryption of the to-be-sent data based on the semantic key to obtain encrypted sending data comprises:

[0016] According to the semantic key and the PLK of the DLCS, an encryption key stream and a decryption key stream are generated;

[0017] The to-be-sent data is data-encrypted by using the encryption key stream to obtain the encrypted sending data

[0018] Optionally, in another embodiment based on the above method of the application, the common transmission of the encrypted sending data and the plurality of obfuscated data to the receiving end of the DLCS comprises:

[0019] A first number of encrypted sending data matching the semantic key is selected; and a second number of obfuscated data matching the semantic key is selected;

[0020] The first number of encrypted sending data and the second number of obfuscated data are commonly transmitted to the receiving end of the DLCS.

[0021] According to yet another aspect of the embodiments of the application, a channel transmission device is provided, which is applied to a deep learning-based end-to-end communication system (DLCS) and comprises:

[0022] An acquisition module is configured to acquire to-be-sent data and generate a semantic key for the to-be-sent data by using a bilingual evaluation research (BLEU) algorithm;

[0023] A generation module is configured to, at a sending end of the DLCS, data-encrypt the to-be-sent data based on the semantic key to obtain encrypted sending data;

[0024] A transmission module is configured to commonly transmit the encrypted sending data and a plurality of obfuscated data to a receiving end of the DLCS.

[0025] According to another aspect of the embodiments of this application, an electronic device is provided, comprising:

[0026] Memory, used to store executable instructions; and

[0027] A display for operation with the memory to execute the executable instructions to complete any of the methods described above for channel transmission.

[0028] According to another aspect of the embodiments of this application, a computer-readable storage medium is provided for storing computer-readable instructions, which, when executed, perform the operation of any of the channel transmission methods described above.

[0029] In this application, data to be transmitted can be acquired, and a semantic key can be generated for the data using the BLEU algorithm from a bilingual evaluation study. At the transmitting end of the DLCS, the data to be transmitted is encrypted based on the semantic key to obtain encrypted transmission data. The encrypted transmission data and multiple obfuscated data are then transmitted to the receiving end of the DLCS. By applying the technical solution of this application, on the one hand, a method can be used to obtain a semantic key from the BLEU score in the field of machine translation and encrypt the semantic transmission information in the DLCS system. This not only ensures the security of semantic communication but also improves the problem of low key generation efficiency in static fading environments caused by the use of PSK encryption technology in related technologies. On the other hand, dynamic dummy data can be added to the transmission subcarriers to achieve obfuscation at the transmission subcarrier level, thereby protecting the reliability of the transmission information of the DLCS system.

[0030] The technical solution of this application will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0031] The accompanying drawings, which form part of this specification, illustrate embodiments of this application and, together with the description, serve to explain the principles of this application.

[0032] This application can be more clearly understood with reference to the accompanying drawings and the following detailed description, wherein:

[0033] Figure 1 A schematic diagram of a channel transmission method provided in an embodiment of this application is shown;

[0034] Figure 2 A schematic flowchart of a channel transmission method provided in an embodiment of this application is shown;

[0035] Figure 3 This illustration shows a schematic diagram of generating a physical layer key PLK in a DLCS system according to an embodiment of this application;

[0036] Figure 4 Fig. 8 shows a schematic diagram of encrypting data in a DLCS system according to an embodiment of the present application;

[0037] Figure 5 Fig. 9 shows a schematic diagram of implementing semantic obfuscation process in a DLCS system according to an embodiment of the present application;

[0038] Figure 6 Fig. 10 shows a schematic diagram of an electronic device according to an embodiment of the present application;

[0039] Figure 7 Fig. 11 shows a schematic diagram of an electronic device according to an embodiment of the present application;

[0040] Figure 8 Fig. 12 shows a schematic diagram of a storage medium according to an embodiment of the present application. DETAILED DESCRIPTION

[0041] Various exemplary embodiments of the present application will now be described in detail with reference to the accompanying drawings. It should be noted that the relative arrangement of the components and steps set forth in the embodiments, numerical expressions, and numerical values set forth in the embodiments are not limitations on the scope of the present application unless otherwise specifically stated.

[0042] It should be understood that the sizes of the various portions shown in the drawings are shown for the purpose of convenience and are not necessarily drawn to scale.

[0043] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the scope of the application or its application or uses.

[0044] Techniques, methods, and devices known to those of ordinary skill in the relevant art can not be discussed in detail herein. However, where appropriate, such techniques, methods, and devices can be presumed to be a part of the specification.

[0045] It should be noted that like numbers and letters refer to like items throughout the drawings, and that, as such, no further discussion on such items is required.

[0046] In addition, the technical solutions among various embodiments of the present application can be combined with each other, but it must be based on the fact that a person of ordinary skill in the art can realize the combination, and when the combination of technical solutions contradicts each other or cannot be realized, it should be considered that the combination of technical solutions does not exist, nor is it within the scope of protection required by the present application.

[0047] It should be noted that all directionality indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present application are only used to explain the relative position relationship, motion condition, etc. between components in a certain posture (as shown in the drawings), and if the certain posture changes, the directionality indications will also change accordingly.

[0048] The method for performing channel transmission according to the exemplary embodiments of the present application will be described below in conjunction with Figures 1-5 It should be noted that the following application scenarios are only shown for the purpose of facilitating the understanding of the spirit and principles of the present application, and the embodiments of the present application are not limited in this respect. On the contrary, the embodiments of the present application can be applied to any applicable scenario.

[0049] The present application also proposes a method and device for channel transmission, an electronic device and a medium.

[0050] Figure 1 The flowchart of the method for performing channel transmission according to the embodiments of the present application is schematically shown, which is applied to a deep learning based end-to-end communication system (DLCS) and includes the following steps.

[0051] In S101, the data to be sent is obtained, and a BLEU algorithm is used to generate a semantic key for the data to be sent.

[0052] In S102, the data to be sent is encrypted based on the semantic key at the sending end of the DLCS to obtain encrypted sending data.

[0053] In S103, the encrypted sending data and a plurality of confusion data are jointly transmitted to the receiving end of the DLCS.

[0054] In the related art, a deep learning based semantic communication (DLSC) shows great potential in improving communication efficiency by merging one or more modules in traditional systems. It transmits the semantics conveyed by the source, rather than simply transmitting each single symbol or bit accurately. Such a novel communication mode greatly promotes emerging mobile applications that require high throughput and low latency, such as VR / AR and human-to-human communication.

[0055] Specifically, the transmitter of the DLSC system relies on a neural network to extract semantic information from the input, and then sends the encoded symbols to the wireless channel. Next, the receiver uses a neural model to reconstruct the received semantic information semantically and interprets the semantics to make intelligent decisions.

[0056] Among them, compared with the traditional wireless communication system, the DLSC system (deep learning based semantic communication system) may suffer more security problems, and the reasons are as follows:

[0057] First, the openness of the wireless channel greatly increases the risk of semantic data confidentiality of the DLSC system being attacked maliciously.

[0058] Second, due to the vulnerability of deep neural networks, the DLSC system is more susceptible to eavesdropping, tampering, and deception.

[0059] Based on the above problems, the encryption scheme of symmetric key or asymmetric key is usually used in the related art to protect information. In order to reduce the calculation and communication overhead, a physical layer key (PLK) scheme is proposed. The PLK scheme explores the reciprocity of the channel between two legitimate users, and realizes efficient encryption and decryption. From the perspective of information theory security, PLK enables wireless communication to achieve Shannon's perfect secrecy. However, due to the fact that the wireless channel may not always be guaranteed over time (because PLK mainly uses additional relays or super-intelligent surfaces (RIS) to inject randomness into the wireless channel by manipulating signals in a static environment), this also leads to a low key generation rate in static fading environments, such as indoor Internet of Things networks.

[0060] In order to solve the above problems, a new physical layer encryption confusion scheme is proposed, which aims to enhance the security of the DLSC system by exploring the randomness of the reconstructed sentence of the deep learning based semantic communication system and the subcarrier confusion.

[0061] Further, as shown in Figure 2 The method of channel transmission proposed by the present application is specifically described as follows:

[0062] Step 1, obtaining the data to be sent.

[0063] Step 2, generating a physical layer key (PLK) and using the PLK to generate an initial key stream; and using the BLEU algorithm to generate a corresponding evaluation score for the data to be sent.

[0064] In combination with Figure 3 As shown in the figure, how to generate a semantic key for the i-th group of data (i.e. the data to be sent) at the sending end of the DLCS proposed by the embodiment of the present application is shown. As can be seen from the figure, first, the embodiment of the present application needs to generate a physical layer key (PLK) for the DLCS system.

[0065] In one way, the generation of the physical layer key (PLK) can include the steps of channel sounding, quantization, information negotiation and privacy amplification in sequence.

[0066] In one way, the central idea of BLEU is to evaluate the difference between the machine translation result and the standard translation result. That is, according to the numerical value of a measure, the closeness of machine translation to one or more reference translations is measured to judge the quality of machine translation.

[0067] Further, the embodiment of the present application can also use the PLK to generate the initial key stream k stream ; and by inputting the semantic information of the data to be sent to the semantic decoder deployed on the transmitting end, the evaluation score corresponding to the data to be sent is obtained. As an example, it can be represented as s = [s i-1 ,s i-2 ,s i-3 ,s i-4..... ].

[0068] Step 3, using the initial key stream to generate the weight coefficient for the evaluation score.

[0069] Step 4, calculating the hash value of the product of the weight coefficient and the evaluation score, and taking the calculation result as the semantic key.

[0070] Further, the embodiment of the present application can use the initial key stream k stream to generate the weight for each BLUE score. So that the semantic key Skey is generated by inputting the weighted BLUE score subsequently.

[0071] As an example, the generation formula of Skey can be represented as:

[0072] Skey = HASH [W x BLEU (data real , data predicted )].

[0073] Wherein, W represents the BLEU score weight, BLEU represents the calculation of the BLEU score, and HASH refers to a lightweight hash algorithm.

[0074] Step 5, on the transmitting end of the DLCS, generating the encryption key stream and the decryption key stream according to the semantic key and the PLK of the DLCS.

[0075] Further, as shown in Figure 4 , the schematic diagram of how to encrypt the data to be sent according to the embodiment of the present application. As can be seen from the figure, the embodiment of the present application can first obtain the seed key through the semantic key SKey and the PLK of the DLCS, and then generate the encryption and decryption key stream with the seed key to encrypt the data to be sent, and generate u'i in the semantic encryption module of the transmitter.

[0076] In one way, the skey in the embodiment of the present application will be encrypted using the key stream generated by the traditional PLK, and then sent to the legitimate receiver to realize the key exchange.

[0077] Step 6, encrypting the data to be sent by using the encryption key stream to obtain the encrypted sending data.

[0078] In one aspect, the embodiments of the present application generate a semantic key (SKey) by calculating the BLEU score of the transmitted data and the corresponding weight coefficient, and use the semantic key to achieve encrypted transmission of the transmission information.

[0079] It can be understood that, due to the deviation of semantic information reconstruction, the encryption method using BLEU algorithm for bilingual evaluation research can naturally involve randomness in the key generation process, which can appropriately alleviate the problems existing in the static fading environment.

[0080] Step 7, selecting a first number of encrypted transmission data matched with the semantic key; and selecting a second number of confusion data matched with the semantic key.

[0081] In one aspect, in order to make the encrypted OFDM symbol data more random and secure, the present application can take the first number of data as a data unit (the first number is s), and select a second number of subcarriers to carry false data (i.e. confusion data, the second number is k) through the semantic key. This encryption method is represented as [s, k].

[0082] Further, the embodiments of the present application can confuse the real data by inserting false data between the encrypted semantic data. It should be noted that, in order to avoid the disadvantage that the long-term use of a fixed number of true and false data for confusion transmission can be easily cracked by malicious users. The first number and the second number (i.e. k and s) in the present application are not fixed.

[0083] In one aspect, the values of the first number and the second number can be calculated by the key, which can also achieve that [s, k] of each group of transmission data is different, and can better protect the data security.

[0084] As an example, in the process of calculating the first number and the second number, the embodiments of the present application can respectively convert one of the 01 bit sequences of the semantic key into a binary number (one 01 bit sequence is used to generate the first number, and the other 01 bit sequence is used to generate the second number), so as to obtain a 10 field respectively, and take the two 10 fields as the first number and the second number respectively.

[0085] In one aspect, the embodiments of the present application can also set an upper limit for the first number and the second number (for example, denoted as k max and s max ). Thus, the purpose of balancing the transmission efficiency and the security performance is achieved.

[0086] Step 8, transmitting the first number of encrypted transmission data and the second number of confusion data to the receiving end of the DLCS together.

[0087] Further, in combinationFigure 5 As shown, it is the adding process of semantic confusion proposed by the embodiment of the application. As can be seen from the figure, it includes 3 subcarriers carrying real semantic data (i.e. encrypted sending data) and 4 subcarriers carrying confusion data in the transmission process.

[0088] In the present application, the to-be-sent data can be obtained, and a bilingual evaluation research BLEU algorithm is used to generate a semantic key for the to-be-sent data; at the sending end of the DLCS, the to-be-sent data is encrypted based on the semantic key to obtain encrypted sending data; and the encrypted sending data and a plurality of confusion data are jointly transmitted to the receiving end of the DLCS.

[0089] By applying the technical solution of the present application, on the one hand, the semantic key can be obtained by the BLEU score in the field of machine translation, and the method of encrypting the semantic transmission information in the DLCS system is used, so as to not only ensure the security of semantic communication, but also improve the problem of low key generation efficiency in a static fading environment caused by the PSK encryption technology in the related art. On the other hand, the transmission subcarrier level confusion can also be realized by adding dynamic false data in the transmission subcarrier, thereby protecting the transmission information reliability of the DLCS system.

[0090] Optionally, in another embodiment based on the above method of the present application, the bilingual evaluation research algorithm BLEU is used to generate a semantic key for the to-be-sent data, comprising:

[0091] generating a physical layer key PLK and using the PLK to generate an initial key stream; and using the BLEU algorithm to generate a corresponding evaluation score for the to-be-sent data;

[0092] generating a semantic key for the to-be-sent data according to the initial key stream and the evaluation score.

[0093] Optionally, in another embodiment based on the above method of the present application, the semantic key for the to-be-sent data is generated according to the initial key stream and the evaluation score, comprising:

[0094] using the initial key stream to generate a weight coefficient for the evaluation score;

[0095] calculating the hash value of the product of the weight coefficient and the evaluation score, and taking the calculation result as the semantic key.

[0096] Optionally, in another embodiment based on the above method of the present application, the to-be-sent data is encrypted based on the semantic key to obtain encrypted sending data, comprising:

[0097] generating an encryption key stream and a decryption key stream according to the semantic key and the PLK of the DLCS;

[0098] Data encryption is performed on the to-be-sent data using an encryption key stream to obtain encrypted sending data

[0099] Optionally, in another embodiment based on the method described above, the encrypted sending data and the plurality of obfuscated data are jointly transmitted to a receiving end of the DLCS, including:

[0100] A first number of encrypted sending data matching the semantic key is selected, and a second number of obfuscated data matching the semantic key is selected;

[0101] The first number of encrypted sending data and the second number of obfuscated data are jointly transmitted to the receiving end of the DLCS.

[0102] Optionally, in another embodiment of the present application, as shown in Figure 6 The present application also provides a channel transmission device. Applied to a deep learning-based end-to-end communication system (DLCS), the device includes:

[0103] The obtaining module 201 is configured to obtain to-be-sent data and generate a semantic key for the to-be-sent data using a bilingual evaluation understudy BLEU algorithm;

[0104] The generating module 202 is configured to perform data encryption on the to-be-sent data based on the semantic key at a sending end of the DLCS to obtain encrypted sending data;

[0105] The transmission module 203 is configured to jointly transmit the encrypted sending data and a plurality of obfuscated data to a receiving end of the DLCS.

[0106] By applying the technical solution of the present application, on the one hand, the BLEU score in the field of machine translation can be used to obtain a semantic key and encrypt semantic transmission information in a DLCS system, thereby not only ensuring the security of semantic communication but also improving the problem of low key generation efficiency in a static fading environment caused by the use of PSK encryption technology in related technologies. On the other hand, transmission subcarrier-level obfuscation can also be achieved by adding dynamic fake data in the transmission subcarrier, thereby protecting the transmission information reliability of the DLCS system.

[0107] In another embodiment of the present application, the generating module 202 is configured to perform the following steps:

[0108] Generate a physical layer key (PLK) and an initial key stream using the PLK, and generate a corresponding evaluation score for the to-be-sent data using the BLEU algorithm;

[0109] Generate the semantic key for the to-be-sent data according to the initial key stream and the evaluation score.

[0110] In another embodiment of the present application, the generating module 202 is configured to perform the following steps:

[0111] generating a weight coefficient for the evaluation score using the initial key stream;

[0112] calculating a hash value of the product of the weight coefficient and the evaluation score, and taking the calculation result as the semantic key.

[0113] In another embodiment of the present application, the generating module 202 is configured to perform the following steps:

[0114] generating an encryption key stream and a decryption key stream according to the semantic key and the PLK of the DLCS;

[0115] performing data encryption on the to-be-sent data using the encryption key stream to obtain the encrypted sending data.

[0116] In another embodiment of the present application, the generating module 202 is configured to perform the following steps:

[0117] selecting a first number of encrypted sending data matching the semantic key, and selecting a second number of obfuscated data matching the semantic key;

[0118] transmitting the first number of encrypted sending data and the second number of obfuscated data to the receiving end of the DLCS together.

[0119] The embodiments of the present application also provide an electronic device for executing the channel transmission method described above. Please refer to Figure 7 which shows a schematic diagram of an electronic device provided by some embodiments of the present application. As shown in Figure 7 the electronic device 3 comprises a processor 300, a memory 301, a bus 302 and a communication interface 303, the processor 300, the communication interface 303 and the memory 301 are connected through the bus 302; the memory 301 stores a computer program which can run on the processor 300, and the processor 300 runs the computer program to execute the channel transmission method provided by any of the preceding embodiments of the present application.

[0120] Among them, the memory 301 can contain a high-speed random access memory (RAM: Random Access Memory), and can also include a non-volatile memory, such as at least one disk memory. The communication connection between the device network element and at least one other network element is realized through at least one communication interface 303 (which can be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. can be used.

[0121] The bus 302 can be an ISA bus, a PCI bus, or an EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. The memory 301 is configured to store a program, and the processor 300 executes the program after receiving an execution instruction. The data recognition method disclosed in any of the embodiments of the present application can be applied to the processor 300 or implemented by the processor 300.

[0122] The processor 300 can be an integrated circuit chip with a processing capability of signals. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor 300 or an instruction in the form of software. The processor 300 described above can be a general-purpose processor, including a processor (CPU), a network processor (NP), etc.; can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a ready-to-use programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. Each method, step and logic block diagram disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as a hardware coding processor for execution, or a combination of hardware and software modules in the coding processor for execution. The software module can be located in a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, or other mature storage media in the art. The storage medium is located in the memory 301, and the processor 300 reads the information in the memory 301 and combines the hardware to complete the steps of the above method.

[0123] The electronic device provided by the embodiments of the present application and the channel transmission method provided by the embodiments of the present application have the same beneficial effects as the method they adopt, run or implement.

[0124] The embodiments of the present application also provide a computer readable storage medium corresponding to the channel transmission method provided in the foregoing embodiments. Please refer to Figure 8 The computer readable storage medium shown is an optical disc 40, and a computer program (i.e. program product) is stored on the optical disc 40. When the computer program is run by a processor, the channel transmission method provided in any of the foregoing embodiments is executed.

[0125] It is to be noted that examples of the computer-readable storage medium can also 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 optical, magnetic storage mediums, and the like, which are not listed one by one here.

[0126] The computer-readable storage medium provided by the above embodiments of the present application has the same beneficial effects as the method adopted, run or implemented by the application program stored therein.

[0127] It should be noted that:

[0128] In the specification provided herein, a large number of specific details are described. However, it can be understood that the embodiments of the present application can be practiced without these specific details. In some instances, well-known structures and technologies are not shown in detail in order not to obscure the understanding of the present specification.

[0129] Similarly, it is to be understood that, in the above description of exemplary embodiments of the present application, various features of the present application are sometimes grouped together in a single embodiment, figure, or description of a related aspect. This method of disclosure, however, is not to be interpreted as reflecting an intention that the claimed application requires more features than are explicitly recited in each claim. Rather, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following, in this application are hereby expressly incorporated into this detailed description, with each claim acting as a separate embodiment of the present application. The claims are not to be construed as reflecting an intention that the application requires more features than are explicitly recited in each claim.

[0130] Furthermore, those skilled in the art will recognize that references in the specification to "one embodiment", "an embodiment", "an example embodiment", means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the application. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment, and some embodiments can be widely different from other embodiments. In addition, it is to be understood that the phraseology "cause to be" and variations thereof, as used herein is expressly not intended to refer to a cause and effect relationship, but instead, should be understood to mean that one or more devices or systems are causing an action to be taken, or causing a function to be performed, even if the action or function is not directly related to the device or system in question.

[0131] The above descriptions are merely specific embodiments of the present application, and the protection scope of the present application is not limited thereto, and any changes or substitutions easily conceived by those skilled in the art within the technical scope disclosed by the present application shall be covered by the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method of channel transmission, characterized by, Applications to DLCS (Deep Learning-Based End-to-End Communication System) include: Acquire the data to be sent, and use the bilingual evaluation study BLEU algorithm to generate a semantic key for the data to be sent; At the sending end of the DLCS, the data to be sent is encrypted based on the semantic key to obtain encrypted data to be sent. The encrypted data and multiple obfuscated data are transmitted together to the receiving end of the DLCS; The step of generating a semantic key for the data to be sent using the Bilingual Evaluation and Research Algorithm (BLEU) includes: Generate a physical layer key PLK and use the PLK to generate an initial key stream; and use the BLEU algorithm to generate a corresponding evaluation score for the data to be sent; generate the semantic key for the data to be sent based on the initial key stream and the evaluation score. The step of transmitting the encrypted data and multiple obfuscated data together to the receiving end of the DLCS includes: Select a first number of encrypted data that matches the semantic key; and select a second number of obfuscated data that matches the semantic key; and transmit the first number of encrypted data and the second number of obfuscated data together to the receiving end of the DLCS.

2. The method as described in claim 1, characterized in that, The step of generating the semantic key for the data to be sent based on the initial key stream and the evaluation score includes: The initial key stream is used to generate weighting coefficients for the evaluation score; Calculate the hash value of the product of the weight coefficient and the evaluation score, and use the calculation result as the semantic key.

3. The method as described in claim 1, characterized in that, The step of encrypting the data to be sent based on the semantic key to obtain encrypted data for transmission includes: Based on the semantic key and the PLK of the DLCS, an encryption key stream and a decryption key stream are generated; The data to be sent is encrypted using the encryption key stream to obtain the encrypted data to be sent.

4. A channel transmission apparatus, characterized in that, Applications to DLCS (Deep Learning-Based End-to-End Communication System) include: The acquisition module is configured to acquire the data to be sent and generate a semantic key for the data to be sent using the bilingual evaluation study BLEU algorithm; The generation module is configured to encrypt the data to be sent based on the semantic key at the sending end of the DLCS to obtain encrypted data to be sent. The transmission module is configured to transmit the encrypted transmission data and multiple obfuscated data together to the receiving end of the DLCS; The acquisition module is further configured to generate a semantic key for the data to be sent using the bilingual evaluation research algorithm BLEU in the following manner: Generate a physical layer key PLK and use the PLK to generate an initial key stream; and use the BLEU algorithm to generate a corresponding evaluation score for the data to be sent; generate the semantic key for the data to be sent based on the initial key stream and the evaluation score. The generation module is further configured to transmit the encrypted data and multiple obfuscated data to the receiving end of the DLCS in the following manner: Select a first number of encrypted data that matches the semantic key; and select a second number of obfuscated data that matches the semantic key; and transmit the first number of encrypted data and the second number of obfuscated data together to the receiving end of the DLCS.

5. An electronic device, characterized in that, include: Memory, used to store executable instructions; as well as, A processor for executing the executable instructions with the memory to perform the operation of the channel transmission method according to any one of claims 1-3.

6. A computer-readable storage medium for storing computer-readable instructions, characterized in that, When the instruction is executed, it performs the operation of the channel transmission method according to any one of claims 1-3.

Images