Image semantic communication method based on encryption algorithm and application

Abstract

The invention discloses an image semantic communication method based on an encryption algorithm and application. The method comprises the following steps: segmenting an input image into a plurality of semantic information units; based on task correlation scores provided by the task knowledge base and storage spaces of semantic information units, risk level scores of the semantic information units are calculated through a security risk discrimination algorithm, and high security risk information units and low security risk information units are classified; encrypting the high-security-risk information unit by adopting a quantum encryption algorithm, and encrypting the low-security-risk information unit by adopting a classical encryption algorithm; and transmitting the encrypted semantic information units to a receiving end through a communication channel, decrypting the semantic information units at the receiving end, and reconstructing the decrypted semantic information units into a complete image. The problems that the communication bandwidth and the transmission capacity are limited and the classical encryption algorithm is low in safety due to the fact that the quantum encryption technology is adopted in existing image semantic communication can be solved.

Description

Technical Field

[0001] The present application relates to the field of encryption communication technology, and in particular to an image semantic communication method, device, electronic device and computer-readable storage medium based on encryption algorithm. Background Art

[0002] As an emerging communication technology, semantic communication can greatly alleviate the current problem of insufficient communication bandwidth and surging data volume, and is one of the important development directions in the field of communication. Especially for image information transmission, semantic communication technology can significantly reduce the amount of data to be transmitted while ensuring the visual quality of the image, thereby improving communication efficiency. However, in areas with high security and confidentiality requirements, how to enhance encryption and improve security of image semantic communication technology is one of the key issues in promoting the development of semantic communication technology.

[0003] Quantum encryption technology represented by quantum key distribution and quantum direct secure communication is a technical means with high security in the current information security field. However, quantum encryption technology usually faces the problems of limited communication bandwidth and limited transmission capacity. Classical encryption algorithms represented by RSA algorithm have high throughput, but the current classical encryption algorithms have the security risk of being broken by quantum computing. Image semantic communication technology has the ability to analyze semantic information in images, which provides an effective way to analyze the security risks of different information in images. However, how to analyze the security risks of different information in images, effectively combine quantum encryption algorithms and classical encryption algorithms, and achieve the efficiency and security of image semantic communication at the same time is still a problem that needs to be solved urgently. Summary of the invention

[0004] In order to overcome the defects of the above-mentioned prior art, the embodiments of the present invention provide an image semantic communication method and application based on an encryption algorithm, which can solve the problem of limited communication bandwidth and transmission capacity in the existing image semantic communication using quantum encryption technology, as well as the problem of low security using classical encryption algorithms.

[0005] On the one hand, an embodiment of the present invention proposes an image semantic communication method based on an encryption algorithm, comprising: segmenting an input image into a number of semantic information units through a semantic segmentation unit, wherein the semantic information units include high security risk information units related to task objectives and low security risk information units related to backgrounds; calculating the risk level score of each of the semantic information units through a security risk discrimination algorithm based on the task relevance score provided by a task knowledge base and the storage space of the semantic information units, and classifying the high security risk information units and the low security risk information units according to the risk level scores; encrypting the high security risk information units using a quantum encryption algorithm, and encrypting the low security risk information units using a classical encryption algorithm; transmitting the encrypted semantic information units to a receiving end through a communication channel, and reconstructing the complete image after decrypting the semantic information units respectively at the receiving end.

[0006] In one embodiment of the present invention, the semantic segmentation unit includes a Yolo-World model and a SAM model, the Yolo-World model performs region extraction based on the task objectives in the task knowledge base, and the SAM model performs fine segmentation on the extracted regions to generate independent semantic information units.

[0007] In one embodiment of the present invention, the security risk identification algorithm calculates the risk level score by the following formula: ;in, is the task relevance score of the semantic information unit, The storage space size.

[0008] In one embodiment of the present invention, the quantum encryption algorithm includes quantum key distribution or quantum direct secure communication. During the encryption process, the channel is monitored in real time to see if it is eavesdropped, and the high security risk information unit is encrypted in a one-time one-pad manner.

[0009] In one embodiment of the present invention, the communication channel transmission adopts an adaptive bandwidth allocation algorithm, including: dynamically allocating communication bandwidth according to the task relevance score and storage space of the semantic information unit, and converting the semantic information unit with a lower than preset task relevance into label transmission.

[0010] In one embodiment of the present invention, the image reconstruction is based on the OpenCV framework, and the decrypted semantic information unit is fused with the three-dimensional data provided by the domain knowledge base to generate a reconstructed image with optimized visual quality.

[0011] In one embodiment of the present invention, the task knowledge base includes task target entities and task relevance scores, and the domain knowledge base includes three-dimensional data of task target entities and label-associated image data.

[0012] On the other hand, an embodiment of the present invention also proposes an image semantic communication device based on an encryption algorithm, including: an image semantic segmentation module, used to segment the input image into a number of semantic information units through a semantic segmentation unit, and the semantic information units include high security risk information units related to the task goal and low security risk information units related to the background; an information unit classification module, used to calculate the risk level score of each semantic information unit through a security risk discrimination algorithm based on the task relevance score provided by the task knowledge base and the storage space of the semantic information unit, and classify the high security risk information unit and the low security risk information unit according to the risk level score; an information unit encryption module, used to encrypt the high security risk information unit using a quantum encryption algorithm, and encrypt the low security risk information unit using a classical encryption algorithm; an image reconstruction module, used to transmit the encrypted semantic information unit to a receiving end through a communication channel, and reconstruct the semantic information unit into a complete image after decrypting the semantic information units respectively at the receiving end.

[0013] On the other hand, an embodiment of the present invention further proposes an electronic device, comprising: a memory and one or more processors connected to the memory, the memory storing a computer program, and the processor being used to execute the computer program to implement the image semantic communication method based on encryption algorithm as described in any one of the above embodiments.

[0014] On the other hand, an embodiment of the present invention further proposes a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to execute the image semantic communication method based on the encryption algorithm as described in any one of the above embodiments.

[0015] It can be seen from the above that, compared with the prior art, the above embodiments of the present invention can have at least one or more of the following beneficial effects: The present invention proposes a secure image semantic communication method combining quantum-classical encryption algorithm, specifically by analyzing the semantic information contained in the image and decoupling it into different semantic information units, analyzing the security risks of different information units, using quantum encryption algorithm to encrypt information units with high security risks, and using classical encryption algorithm to encrypt information units with low security risks, effectively combining the advantages of quantum encryption algorithm and classical encryption algorithm, avoiding the risk of loss of confidentiality caused by quantum computing faced by traditional encryption algorithms, while achieving high-efficiency and high-security image semantic communication; the proposed security risk assessment method comprehensively considers the task relevance and storage space size of the information unit, ensuring that information units with small storage space and high relevance are encrypted preferentially through quantum encryption technology, which well overcomes the limitation of low throughput of quantum encryption technology, and protects the core information in the image through limited quantum keys. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings: Figure 1 A flowchart of an image semantic communication method based on an encryption algorithm provided by an embodiment of the present invention; Figure 2 A schematic diagram of the execution logic of an image semantic communication method based on an encryption algorithm provided by an embodiment of the present invention; Figure 3 A specific implementation flow chart of an image semantic communication method based on an encryption algorithm provided by an embodiment of the present invention; Figure 4 A schematic diagram of the structure of an image semantic communication device based on an encryption algorithm provided by an embodiment of the present invention; Figure 5 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention; Figure 6 A schematic diagram of the structure of a computer-readable storage medium provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0017] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other. The present invention will be described below with reference to the accompanying drawings and in combination with the embodiments.

[0018] In order to enable ordinary technicians in the field to better understand the technical solution of the present invention, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments, and all should belong to the protection scope of the present invention.

[0019] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are applicable to distinguishing similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition. The terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or are proprietary to these processes, methods, products or devices.

[0020] It should also be noted that the division of multiple embodiments in the present invention is only for the convenience of description and should not constitute a special limitation. The features in various embodiments can be combined and referenced to each other without contradiction.

[0021] like Figure 1 As shown, the first embodiment of the present invention proposes an image semantic communication method based on an encryption algorithm, for example, including: step S1, dividing the input image into a number of semantic information units through a semantic segmentation unit, and the semantic information units include high security risk information units related to the task target and low security risk information units related to the background; step S2, based on the task relevance score provided by the task knowledge base and the storage space of the semantic information unit, the risk level score of each semantic information unit is calculated through a security risk discrimination algorithm, and the high security risk information unit and the low security risk information unit are classified according to the risk level score; step S3, using a quantum encryption algorithm to encrypt the high security risk information unit, and using a classical encryption algorithm to encrypt the low security risk information unit; step S4, transmitting the encrypted semantic information unit to the receiving end through a communication channel, and reconstructing the complete image after decrypting the semantic information units respectively at the receiving end.

[0022] Specific, combined Figure 2 As shown, the method is implemented by the functional units of semantic segmentation, information organization, encoding, decoding, information supplementation, image reconstruction, task knowledge base, domain knowledge base, classical encryption algorithm, and quantum encryption algorithm. Among them, the task knowledge base mainly includes typical tasks in application scenarios and task target entities and task relevance scores that often appear in images, and its role is to provide guidance for semantic segmentation and information organization. The domain knowledge base mainly includes task target entities and three-dimensional data that often appear in images in application scenarios, and its role is to provide complete image data based on labels for image reconstruction and improve image visual quality.

[0023] The semantic segmentation unit, for example, consists of a Yolo-World model and a Segment Anything Model (SAM) model. First, with the support of the task knowledge base, the task target (such as cars, pedestrians, houses, etc.) is embedded in Yolo-World in text form, and the area containing the task target in the image is extracted, and the coordinates of the area are obtained and input into SAM. Then, the target in the area is segmented into independent information units through SAM to obtain several semantic information units and their coordinates.

[0024] The information organization unit includes an adaptive bandwidth allocation algorithm and a security risk identification algorithm. First, the adaptive bandwidth allocation algorithm is used to allocate bandwidth to the task relevance of different information units, and the image data is compressed according to the allocated bandwidth. At the same time, information units with extremely low task relevance are converted into labels to improve the utilization of communication bandwidth. Then, different information units are divided into high security risk and low security risk according to task relevance, and input into different channels for transmission.

[0025] The coding module is the source coding / decoding and channel coding / decoding module in the communication system. This module is responsible for encoding the semantic information unit to make it an information sequence suitable for sending to the communication channel, and decoding the information sequence back to the semantic information unit at the receiving end.

[0026] Classical encryption algorithms encrypt and decrypt encoded information sequences with relatively low security risks through classical encryption algorithms represented by RSA, AED, etc. Quantum encryption algorithms encrypt and decrypt encoded information sequences with relatively high security risks through quantum cryptography represented by quantum key distribution. When conditions permit, quantum direct secure communication technology can also be used directly for confidential transmission.

[0027] The information supplement module is based on the domain knowledge base and provides the image reconstruction unit with corresponding three-dimensional image data according to the received label data.

[0028] The image reconstruction unit generates a reconstructed image based on the image fusion algorithm designed based on the OpenCV framework and the received image data and positioning data.

[0029] Therefore, the method takes image semantic communication technology as the core, quantum encryption algorithm and classical encryption algorithm as the basis, organizes information units in the image through semantic analysis, selects different encryption methods for encryption according to security risks, encrypts information units with high security risks through quantum encryption algorithm, and encrypts information units with low security risks through classical encryption algorithm. It not only realizes the transmission of high security risk information units through quantum encryption algorithm, but also overcomes the problem of low transmission efficiency of quantum encryption algorithm. It effectively combines the advantages of quantum encryption algorithm and classical encryption algorithm, and realizes high-efficiency and high-security image semantic communication.

[0030] Combine the following Figure 3 The steps shown describe the scheme and effects of this application in detail: Step (1): Initialize the task knowledge base and domain knowledge base, set the task requirements and feed forward to the semantic segmentation unit. Step (2), input the image into the semantic segmentation unit, perform semantic segmentation on the image according to the provided task objectives, decouple the image into several semantic information units, and use the segmented background as the background information unit.

[0031] Step (3) inputs all information units (including background information units) into the information organization unit, and allocates bandwidth using the product of the task relevance score provided by the task knowledge base and the storage space of the information unit as the weight. At the same time, the information units are divided into high-risk and low-risk categories according to the task relevance score. Considering that the throughput of the quantum encryption algorithm is limited, information units with high relevance and small storage space should be transmitted first. Therefore, this embodiment proposes a security risk calculation method shown in the following formula to calculate the security risk scores of all semantic information units. For example, the 50% semantic information units with the highest security risk scores are input into the quantum encryption algorithm module, and the remaining 50% are input into the classical encryption algorithm module. It should be noted that the background information unit does not contain task-related information and has no task relevance score, and is directly classified into the classical encryption algorithm.

[0032] ; In the formula, , as well as They respectively represent the relevance score of the semantic information unit (derived from the task knowledge base), the risk level score, and the storage space size.

[0033] Step (4) encodes all semantic information units to generate information sequences.

[0034] In step (5), the classic encryption algorithm module uses the RSA algorithm to output the public key to the sender and encrypt the information sequence of the low security risk semantic information unit (including the background information unit).

[0035] In step (6), the quantum encryption algorithm distributes the key to the sending end and the output end in advance through the quantum key distribution system, encrypts the information sequence of the high security risk semantic information unit in a one-time one-pad manner, and monitors in real time whether the channel is eavesdropped through the quantum key distribution process; or directly transmits the information sequence of the high security risk semantic information unit in a confidential manner through the quantum direct secure communication system.

[0036] Step (7), modulate the encrypted information sequence into a signal form suitable for transmission (such as a radio frequency signal), and send it through a communication system. If a quantum direct secure communication system is used, only the information sequence encrypted by the classical encryption algorithm needs to be transmitted.

[0037] Step (8) uses the private key of the RSA algorithm to decrypt the low security risk information sequence, and uses the key of quantum key distribution to decrypt the high security risk information sequence. If the quantum direct secure communication scheme is adopted, the decoding is completed directly through the quantum direct secure communication system.

[0038] Step (9), output the decrypted information sequence to the decoding module, and restore the information sequence to a semantic information unit.

[0039] Step (10), obtain the label data in the information sequence and extract the corresponding image data from the domain knowledge base.

[0040] Step 11, the extracted image data and the received semantic information unit are fused into the background information unit through an image fusion algorithm to generate a reconstructed image.

[0041] In summary, the first embodiment of the present invention proposes an image semantic communication method based on an encryption algorithm, which analyzes the semantic information contained in the image and decouples it into different semantic information units, analyzes the security risks of different information units, uses a quantum encryption algorithm to encrypt information units with high security risks, and uses a classical encryption algorithm to encrypt information units with low security risks. It effectively combines the advantages of quantum encryption algorithms and classical encryption algorithms, avoids the risk of loss of confidentiality caused by quantum computing faced by traditional encryption algorithms, and realizes high-efficiency and high-security image semantic communication. The proposed security risk assessment method comprehensively considers the task relevance and storage space size of the information unit, ensures that information units with small storage space and high relevance are encrypted first through quantum encryption technology, overcomes the limitation of low throughput of quantum encryption technology, and protects the core information in the image through limited quantum keys.

[0042] In addition, if Figure 4 As shown, the second embodiment of the present invention further proposes an image semantic communication device 20 based on an encryption algorithm, for example including: an image semantic segmentation module 201, an information unit classification module 202, an information unit encryption module 203 and an image reconstruction module 204.

[0043] Among them, the image semantic segmentation module 201 is used to segment the input image into several semantic information units through the semantic segmentation unit, and the semantic information units include high security risk information units related to the task goal and low security risk information units related to the background; the information unit classification module 202 is used to calculate the risk level score of each semantic information unit through a security risk discrimination algorithm based on the task relevance score provided by the task knowledge base and the storage space of the semantic information unit, and classify the high security risk information unit and the low security risk information unit according to the risk level score; the information unit encryption module 203 is used to encrypt the high security risk information unit using a quantum encryption algorithm, and to encrypt the low security risk information unit using a classical encryption algorithm; the image reconstruction module 204 is used to transmit the encrypted semantic information unit to the receiving end through a communication channel, and reconstruct the complete image after decrypting the semantic information units respectively at the receiving end.

[0044] The image semantic communication method based on encryption algorithm implemented by the image semantic communication device 20 based on encryption algorithm disclosed in the second embodiment of the present invention is as described in the first embodiment above, so it will not be described in detail here. Optionally, the various modules and the above-mentioned other operations or functions in the second embodiment are respectively for implementing the method described in the first embodiment, and the beneficial effects of the image semantic communication device 20 based on encryption algorithm provided in this embodiment are the same as the beneficial effects of the image semantic communication method based on encryption algorithm provided in the first embodiment above, and for the sake of brevity, they are not repeated here.

[0045] like Figure 5 As shown, the third embodiment of the present invention further proposes an electronic device 30, for example, including: at least one processor 31, and at least one memory 32, wherein the memory 32 stores a computer program, and when the computer program is executed by the processor 31, the processor 31 executes the method as described in the first embodiment, and the beneficial effects of the electronic device 30 provided by this embodiment are the same as the beneficial effects of the image semantic communication method based on encryption algorithm provided by the first embodiment.

[0046] like Figure 6 As shown, the fourth embodiment of the present invention further provides a computer-readable storage medium 40 on which a computer program is stored, and the program implements the steps of the above method when executed by a processor, and the beneficial effects of the computer-readable storage medium 40 provided by this embodiment are the same as the beneficial effects of the image semantic communication method based on encryption algorithm provided by the first embodiment.

[0047] Among them, computer-readable storage media may include, but are not limited to, any type of disk, including floppy disks, optical disks, DVDs, CD-ROMs, microdrives and magneto-optical disks, ROMs, RAMs, EPROMs, EEPROMs, DRAMs, VRAMs, flash memory devices, magnetic or optical cards, nanosystems (including molecular memory ICs), or any type of medium or device suitable for storing instructions and / or data.

[0048] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0049] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0050] In the several embodiments provided in the present application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0051] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0052] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0053] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, disk or optical disk and other media that can store program codes.

[0054] A person skilled in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by entering a program to instruct related hardware, and the program may be stored in a computer-readable memory, which may include a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0055] The above is only an exemplary embodiment of the present disclosure, and the scope of the present disclosure cannot be limited thereto. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the specification and practicing the disclosure here, those skilled in the art will easily think of the implementation scheme of the present disclosure. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the technical field not recorded in the present disclosure. The description and examples are regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

[0056] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0057] It will be easily understood by those skilled in the art that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An image semantic communication method based on encryption algorithm, characterized in that: include: Segmenting the input image into a plurality of semantic information units by a semantic segmentation unit, wherein the semantic information units include high security risk information units related to the task target and low security risk information units related to the background; Based on the task relevance score provided by the task knowledge base and the storage space of the semantic information unit, the risk level score of each semantic information unit is calculated by a security risk discrimination algorithm, and the high security risk information unit and the low security risk information unit are classified according to the risk level score; The high security risk information unit is encrypted using a quantum encryption algorithm, and the low security risk information unit is encrypted using a classical encryption algorithm; The encrypted semantic information units are transmitted to a receiving end through a communication channel, and the receiving end decrypts the semantic information units respectively and reconstructs them into a complete image.

2. The image semantic communication method based on encryption algorithm according to claim 1, characterized in that: The semantic segmentation unit includes a Yolo-World model and a SAM model. The Yolo-World model extracts regions based on the task objectives in the task knowledge base, and the SAM model finely segments the extracted regions to generate independent semantic information units.

3. The image semantic communication method based on encryption algorithm according to claim 1, characterized in that: The security risk identification algorithm calculates the risk level score by the following formula: ； in, is the task relevance score of the semantic information unit, The storage space size.

4. The image semantic communication method based on encryption algorithm according to claim 1, characterized in that: The quantum encryption algorithm includes quantum key distribution or quantum direct secure communication. During the encryption process, the channel is monitored in real time to see if it is eavesdropped, and the high security risk information unit is encrypted in a one-time one-pad manner.

5. The image semantic communication method based on encryption algorithm according to claim 1, characterized in that: The communication channel transmission adopts an adaptive bandwidth allocation algorithm, including: dynamically allocating communication bandwidth according to the task relevance score and storage space of the semantic information unit, and converting the semantic information unit with a lower than preset task relevance into a label transmission.

6. The image semantic communication method based on encryption algorithm according to claim 1, characterized in that: The image reconstruction is based on the OpenCV framework, and the decrypted semantic information unit is fused with the three-dimensional data provided by the domain knowledge base to generate a reconstructed image with optimized visual quality.

7. The image semantic communication method based on encryption algorithm according to claim 6 is characterized in that: The task knowledge base includes task target entities and task relevance scores, and the domain knowledge base includes three-dimensional data of task target entities and label-associated image data.

8. An image semantic communication device based on encryption algorithm, characterized in that: include: An image semantic segmentation module, used to segment an input image into a plurality of semantic information units through a semantic segmentation unit, wherein the semantic information units include high security risk information units related to the task target and low security risk information units related to the background; An information unit classification module is used to calculate the risk level score of each semantic information unit through a security risk discrimination algorithm based on the task relevance score provided by the task knowledge base and the storage space of the semantic information unit, and classify the high security risk information unit and the low security risk information unit according to the risk level score; An information unit encryption module, used to encrypt the high security risk information unit using a quantum encryption algorithm, and to encrypt the low security risk information unit using a classical encryption algorithm; The image reconstruction module is used to transmit the encrypted semantic information unit to a receiving end through a communication channel, and reconstruct the complete image after decrypting the semantic information unit at the receiving end.

9. An electronic device, characterized in that: include: A memory and one or more processors connected to the memory, the memory storing a computer program, and the processor being used to execute the computer program to implement the encryption algorithm-based image semantic communication method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable commands, and the computer-executable commands are used to execute the encryption algorithm-based image semantic communication method as described in any one of claims 1 to 7.

Images