Semantic communication method and device
By performing semantic extraction and restoration on network devices, the problems of semantic library distribution and acquisition are solved, the burden on terminal devices is reduced, and communication success rate and security are improved.
Patent Information
- Application Number
- CN202310592117.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-05-23
- Publication Date
- 2024-11-26
AI Technical Summary
In semantic communication, how to effectively distribute and obtain semantic databases to improve communication success rate, terminal devices in the prior art need to store semantic databases and have high computing power, which affects user experience.
Semantic extraction and semantic restoration are carried out through network devices. Terminal devices do not need to store semantic libraries. They use public key encryption and private key mechanisms to ensure security, and process semantic information in a trusted execution environment to reduce the burden on terminal devices.
It improves communication success rate and user experience, reduces the processing burden of terminal devices, and enhances the security of semantic communication.
Smart Images

Figure CN119028314A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of communications, and in particular to a semantic communication method and device. Background Art
[0002] Semantic communication generally refers to the communication between different intelligent agents for the purpose of "expressing meaning". Here, "intelligent agents" can refer to humans, intelligent machines, or even other organisms. The fundamental purpose of semantic communication is to exchange information. It does not pursue the fidelity of original data or signals, but to accurately transmit semantics between the two communicating parties.
[0003] In object-oriented semantic communication, both parties need to rely on a shared semantic library to compress and restore the communication content consistently to reduce the communication bandwidth overhead. The semantic library is a set of parameters and models that can establish a certain mapping relationship with the communication content. Usually, the sender can first objectify the original data based on the semantic library, that is, extract semantics, and send the objectified semantics to the receiver. The receiver then renders and merges the objectified semantics with the corresponding model based on the semantic library to obtain the restored content.
[0004] In the process of semantic communication, how to distribute and obtain the semantic library is a technical problem that needs to be solved urgently. Summary of the invention
[0005] The present application provides a semantic communication method and device, which provides a distribution and acquisition method of a semantic library that the communicating parties rely on for semantic communication, so that the communicating parties can perform semantic communication based on the semantic library, thereby improving the communication success rate.
[0006] In a first aspect, a semantic communication method is provided, comprising: receiving a semantic communication request from a first terminal device, the semantic communication request being used to request communication with a second terminal device, the semantic communication request carrying source information of the first terminal device; performing semantic extraction on the source information based on a semantic library between the first terminal device and the second terminal device to obtain semantic key information; and sending a first ciphertext, the first ciphertext being obtained by encrypting the semantic key information and index information of the semantic library based on a public key of a second network device, the second network device being a network device providing services for the second terminal device.
[0007] The semantic communication method of the embodiment of the present application performs semantic extraction and semantic restoration in the process of semantic communication through the network devices of the communicating parties respectively, without the need for the terminal device to store the semantic library. This can reduce the burden on the terminal device and the impact on the processing performance of the terminal device, thereby improving the communication success rate and improving the user experience.
[0008] In a possible implementation manner, the method is executed by a first network device.
[0009] The above-mentioned source information can be understood as the original information used for semantic communication. The source information in the embodiment of the present application can be information that has not been semantically compressed, or it can be information that has been partially semantically compressed. That is, the source information can be compressed and transmitted, or it can be transmitted without compression. The embodiment of the present application does not limit this.
[0010] In combination with the first aspect, in certain implementations of the first aspect, the semantic extraction of the source information based on the semantic library between the first terminal device and the second terminal device includes: semantic extraction of the source information based on the semantic library between the first terminal device and the second terminal device, a first network device providing service for the first terminal device, the second network device, and a semantic communication type supported by the second terminal device.
[0011] It should be understood that semantic extraction can only be performed based on a certain semantic communication type when both the devices on the sending and receiving sides support the semantic communication type. Otherwise, the first network device on the sending side performs semantic extraction based on a certain semantic communication type, but the second network device on the receiving side may not support the semantic communication type and cannot perform semantic restoration on the received information, resulting in semantic communication failure. Therefore, before performing semantic extraction, the first network device must first determine the semantic communication types supported by the first network device, the second network device, and the second terminal device, and then perform semantic extraction according to the semantic communication types they all support, which is conducive to improving the communication success rate.
[0012] Exemplarily, semantic communication types may include source-channel joint coding, object-based semantic extraction, multimedia encoding and decoding, task segmentation, and the like.
[0013] In combination with the first aspect, in some implementations of the first aspect, the method also includes: sending a first capability report, wherein the first capability report is used to indicate the semantic communication capability of the first network device; receiving a third capability report, wherein the third capability report is used to indicate the semantic communication type supported by the first network device, the second network device, and the second terminal device.
[0014] Exemplarily, the first network device can send the first capability report to the second network device, and the second network device can also obtain the semantic communication capability of the second terminal device, that is, the second network device summarizes the information, determines the above-mentioned third capability report, and sends the third capability report to the first network device.
[0015] Exemplarily, the first network device can send the first capability report to other devices (such as other core network devices), and the other devices can also obtain the semantic communication capability of the second terminal device and the semantic communication capability of the second network device, that is, the other core network devices aggregate the information, determine the above-mentioned third capability report, and send the third capability report to the first network device.
[0016] In combination with the first aspect, in some implementations of the first aspect, the method also includes: receiving a second capability report, the second capability report is used to indicate the semantic communication capability of the second network device; receiving a capability query report, the capability query report is used to indicate the semantic communication capability of the second terminal device; based on the second capability report, the capability query report and the semantic communication capability of the first network device, determining the semantic communication type supported by the first network device, the second network device and the second terminal device.
[0017] In the above implementation, the first network device aggregates information to determine the semantic communication type commonly supported by the first network device, the second network device, and the second terminal device.
[0018] In combination with the first aspect, in certain implementations of the first aspect, the capability query report carries identification information of the semantic communication type supported by the second terminal device and computing power information of the semantic communication type supported by the second terminal device.
[0019] In combination with the first aspect, in some implementations of the first aspect, the method further includes: acquiring the semantic library and index information of the semantic library.
[0020] In combination with the first aspect, in some implementations of the first aspect, acquiring the semantic library and the index information of the semantic library includes: receiving the semantic library and the index information of the semantic library from the first terminal device.
[0021] Since the semantic library used in the embodiment of the present application can be created by the first terminal device, and the first network device is a network device that provides services for the first terminal device, the first terminal device can directly send the semantic library created by the first terminal device and the index information of the semantic library to the first network device. In addition, the first network device can also obtain the semantic library from the semantic library storage device, which is not limited in the embodiment of the present application.
[0022] In combination with the first aspect, in certain implementations of the first aspect, the index information of the semantic library is obtained by processing the encrypted information of the semantic library using a one-way derivative function, and the encrypted information of the semantic library is obtained by encrypting the information of the semantic library using the public key of the second terminal device.
[0023] In the embodiment of the present application, the encrypted information of the semantic library is obtained by encrypting the information of the semantic library using the public key of the terminal device of the semantic communication peer. Exemplarily, the first terminal device creates the above-mentioned semantic library, which is used for semantic communication between the first terminal device and the second terminal device. The first terminal device encrypts the information of the semantic library using the public key of the second terminal device, and only the device with the private key of the second terminal device can decrypt it.
[0024] The index information of the semantic library is information that uniquely identifies the semantic library. The one-way derivation function may be a hash function, but this is not limited in the embodiment of the present application.
[0025] In combination with the first aspect, in some implementations of the first aspect, the method is applied to a first network device provided with a trusted execution environment (TEE); the semantic extraction of the source information includes: performing semantic extraction of the source information in the TEE of the first network device.
[0026] Since TEE is a secure area, it can ensure that sensitive data is processed in an isolated and trusted environment. By performing semantic extraction and restoration in the TEE of network devices, it can save the memory of terminal devices while improving the security of semantic communication and protecting user privacy.
[0027] In a second aspect, another semantic communication method is provided, including: receiving a first ciphertext, wherein the first ciphertext is obtained by encrypting semantic key information and index information of the semantic library based on a public key of a second network device; decrypting the first ciphertext using a private key of the second network device to obtain the semantic key information and index information of the semantic library; acquiring the semantic library based on the index information of the semantic library; performing semantic restoration on the semantic key information based on the semantic library to obtain semantic restoration information; and sending the semantic restoration information.
[0028] In a possible implementation manner, the method is executed by the second network device.
[0029] In combination with the second aspect, in some implementations of the second aspect, the method further includes: sending a second capability report, where the second capability report is used to indicate the semantic communication capability of the second network device.
[0030] In combination with the second aspect, in certain implementations of the second aspect, the second capability report carries identification information of the semantic communication capability type supported by the second network device and computing power information of the semantic communication type supported by the second network device.
[0031] In combination with the second aspect, in certain implementations of the second aspect, obtaining the semantic library based on the index information of the semantic library includes: sending a request message to a semantic library storage device, the request message being used to request the semantic library, the request message carrying the index information of the semantic library; receiving encryption information of the semantic library from the semantic library storage device; and determining the semantic library based on the encryption information of the semantic library.
[0032] In combination with the second aspect, in certain implementations of the second aspect, the encrypted information of the semantic library is a ciphertext obtained by encrypting the information of the semantic library using the public key of the second terminal device; determining the semantic library based on the encrypted information of the semantic library includes: decrypting the encrypted information of the semantic library using the private key of the second terminal device to obtain the semantic library.
[0033] In combination with the second aspect, in certain implementations of the second aspect, the index information of the semantic library is obtained by processing the encrypted information of the semantic library using a one-way derivative function, and the encrypted information of the semantic library is obtained by encrypting the information of the semantic library using the public key of the second terminal device.
[0034] In combination with the second aspect, in certain implementations of the second aspect, the method is applied to a second network device provided with a trusted execution environment TEE; the semantic restoration of the semantic key information based on the semantic library includes: in the TEE of the second network device, the semantic key information is semantically restored based on the semantic library.
[0035] According to a third aspect, another semantic communication method is provided, comprising: creating a semantic library of a first terminal device, and determining encryption information of the semantic library and index information of the semantic library; and sending encryption information of the semantic library and index information of the semantic library.
[0036] In a possible implementation manner, the method is executed by a first terminal device.
[0037] In combination with the third aspect, in certain implementations of the third aspect, the method further includes: receiving an update request from a second terminal device, the update request being used to request an update of the semantic library; and sending an update response in response to the update request, the update response carrying an updated public key.
[0038] In combination with the third aspect, in some implementations of the third aspect, the method further includes: sending an updated private key to a third terminal device.
[0039] In a fourth aspect, a semantic communication device is provided, which is used to execute the method in any possible implementation of the above various aspects. Specifically, the device includes a module for executing the method in any possible implementation of the above various aspects.
[0040] In a fifth aspect, the present application provides another semantic communication device, including a processor, the processor is coupled to a memory, and can be used to execute instructions in the memory to implement the method in any possible implementation of the above various aspects. Optionally, the semantic communication device also includes a memory. Optionally, the semantic communication device also includes a communication interface, and the processor is coupled to the communication interface.
[0041] In one implementation, the semantic communication device is a network device. When the semantic communication device is a network device, the communication interface may be a transceiver, or an input / output interface.
[0042] In another implementation, the semantic communication device is a chip configured in a network device. When the semantic communication device is a chip configured in a network device, the communication interface may be an input / output interface.
[0043] In one implementation, the semantic communication device is a terminal device. When the semantic communication device is a terminal device, the communication interface may be a transceiver, or an input / output interface.
[0044] In another implementation, the semantic communication device is a chip configured in a terminal device. When the semantic communication device is a chip configured in a terminal device, the communication interface may be an input / output interface.
[0045] In a sixth aspect, a processor is provided, comprising: an input circuit, an output circuit, and a processing circuit. The processing circuit is used to receive a signal through the input circuit and transmit a signal through the output circuit, so that the processor executes a method in any possible implementation of the above aspects.
[0046] In the specific implementation process, the processor can be a chip, the input circuit can be an input pin, the output circuit can be an output pin, and the processing circuit can be a transistor, a gate circuit, a trigger, and various logic circuits. The input signal received by the input circuit can be, for example, but not limited to, received and input by a receiver, and the signal output by the output circuit can be, for example, but not limited to, output to a transmitter and transmitted by the transmitter, and the input circuit and the output circuit can be the same circuit, which is used as an input circuit and an output circuit at different times. The embodiments of the present application do not limit the specific implementation methods of the processor and various circuits.
[0047] In a seventh aspect, a processing device is provided, comprising a processor and a memory. The processor is used to read instructions stored in the memory, and can receive signals through a receiver and transmit signals through a transmitter to execute the method in any possible implementation of the above aspects.
[0048] Optionally, the number of the processors is one or more, and the number of the memories is one or more.
[0049] Optionally, the memory may be integrated with the processor, or the memory may be provided separately from the processor.
[0050] In the specific implementation process, the memory can be a non-transitory memory, such as a read-only memory (ROM), which can be integrated with the processor on the same chip or can be set on different chips respectively. The embodiments of the present application do not limit the type of memory and the setting method of the memory and the processor.
[0051] It should be understood that the relevant data interaction process, such as sending indication information, can be a process of outputting indication information from a processor, and receiving capability information can be a process of receiving input capability information from a processor. Specifically, the processed output data can be output to a transmitter, and the input data received by the processor can come from a receiver. Among them, the transmitter and the receiver can be collectively referred to as a transceiver.
[0052] The processing device in the seventh aspect mentioned above can be a chip. The processor can be implemented by hardware or by software. When implemented by hardware, the processor can be a logic circuit, an integrated circuit, etc.; when implemented by software, the processor can be a general-purpose processor, which is implemented by reading the software code stored in the memory. The memory can be integrated in the processor or can be located outside the processor and exist independently.
[0053] In an eighth aspect, a computer program product is provided, the computer program product comprising: a computer program (also referred to as code, or instruction), which, when executed, enables a computer to execute a method in any possible implementation of the above-mentioned aspects.
[0054] In a ninth aspect, a computer-readable storage medium is provided, which stores a computer program (also referred to as code, or instruction) which, when executed on a computer, enables the computer to execute a method in any possible implementation of the above-mentioned aspects. BRIEF DESCRIPTION OF THE DRAWINGS
[0055] Figure 1 is a schematic diagram of a communication system applicable to an embodiment of the present application;
[0056] Figure 2 is a schematic diagram of another communication system applicable to an embodiment of the present application;
[0057] Figure 3 A schematic flow chart of a semantic communication method according to an embodiment of the present application;
[0058] Figure 4 A schematic flow chart of another semantic communication method according to an embodiment of the present application;
[0059] Figure 5 A schematic flow chart of another semantic communication method according to an embodiment of the present application;
[0060] Figure 6 A schematic flow chart of another semantic communication method according to an embodiment of the present application;
[0061] Figure 7 A schematic block diagram of a semantic communication device according to an embodiment of the present application;
[0062] Figure 8 This is a schematic block diagram of another semantic communication device according to an embodiment of the present application. DETAILED DESCRIPTION
[0063] The technical solution in this application will be described below in conjunction with the accompanying drawings.
[0064] In order to clearly describe the technical solutions of the embodiments of the present application, in the embodiments of the present application, words such as "first" and "second" are used to distinguish the same or similar items with substantially the same functions and effects. Those skilled in the art can understand that words such as "first" and "second" do not limit the quantity and execution order, and words such as "first" and "second" do not necessarily limit the difference.
[0065] It should be noted that, in this application, words such as "exemplarily" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplarily" or "for example" in this application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplarily" or "for example" is intended to present related concepts in a specific way.
[0066] In addition, "at least one" means one or more, and "plurality" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c can mean: a, or b, or c, or a and b, or a and c, or b and c, or a, b and c, where a, b, c can be single or multiple.
[0067] The technical solutions of the embodiments of the present application can be applied to various communication systems, such as: long term evolution (LTE) system, LTE frequency division duplex (FDD) system, LTE time division duplex (TDD), universal mobile telecommunication system (UMTS), worldwide interoperability for microwave access (WiMAX) communication system, fifth generation (5G) system or new radio (NR), future evolved communication systems, such as sixth generation (6G) system, etc.
[0068] It should also be understood that the technical solutions of the embodiments of the present application can also be applied to various communication systems based on non-orthogonal multiple access technology, such as sparse code multiple access (SCMA) system. Of course, SCMA may also be called other names in the communication field; further, the technical solutions of the embodiments of the present application can be applied to multi-carrier transmission systems using non-orthogonal multiple access technology, such as orthogonal frequency division multiplexing (OFDM), filter bank multi-carrier (FBMC), generalized frequency division multiplexing (GFDM), filtered orthogonal frequency division multiplexing (F-OFDM) system, etc.
[0069] To facilitate understanding of the embodiments of the present application, first Figure 1 and Figure 2 A communication system applicable to an embodiment of the present application is described in detail.
[0070] Figure 1 FIG. 1 is a schematic diagram of a communication system 100 applicable to an embodiment of the present application. Figure 1 As shown, the communication system 100 may include a terminal device 110 , a terminal device 120 , a network device 130 , a network device 140 , and a semantic base storage device 150 .
[0071] Among them, the network device 130 is a network device accessed by the terminal device 110, and provides services for the terminal device 110. The network device 140 is a network device accessed by the terminal device 120, and provides services for the terminal device 120. The network device and the terminal device can communicate through a wireless link. The network device or the terminal device can be configured with multiple antennas, and the multiple antennas may include at least one transmitting antenna for sending signals and at least one receiving antenna for receiving signals. In addition, the network device or the terminal device also additionally includes a transmitter chain and a receiver chain. It can be understood by ordinary technicians in this field that they can all include multiple components related to signal transmission and reception (such as processors, modulators, multiplexers, demodulators, demultiplexers or antennas, etc.). Therefore, the network device and the terminal device can communicate through multi-antenna technology.
[0072] The above-mentioned semantic library storage device 150 is a device for storing a semantic library. The semantic library storage device 150 can be a single device or can include multiple distributed devices (such as blockchain devices), which is not limited in this embodiment of the present application. The semantic library storage device 150 can communicate with a network device (such as a network device 130 or a network device 140). The terminal device may be able to communicate directly with the semantic library storage device 150, or it may not be able to communicate directly with the semantic library storage device 150, and forwarding of the network device is required, which is not limited in this embodiment of the present application.
[0073] Figure 2 FIG. 2 shows a schematic diagram of another communication system 200 applicable to an embodiment of the present application. Figure 2 As shown, the communication system 200 may include a terminal device 210, a terminal device 220, a network device 230 provided with a trusted execution environment (TEE), a network device 240 provided with a TEE, a core network device 250, and a semantic library storage device 260.
[0074] Among them, the network device 230 can be an access network device accessed by the terminal device 210, or it can be a core network device, and the network device 240 can be an access network device accessed by the terminal device 220, or it can be another core network device, which is not limited in the embodiment of the present application. The core network device 250 includes a user plane function and a control plane function, the control plane function is used to transmit user control signaling, and the user plane function is used to transmit user data. It should be understood that when the network device 230 or the network device 240 is a core network device, the network device 230 or the network device 240 is a core network device different from the network device 250.
[0075] Both network device 230 and network device 240 are equipped with TEE, which are used to process semantic extraction and semantic restoration in the process of semantic communication respectively. It should be understood that the memory of the device can be divided into TEE and rich execution environment (REE). REE refers to the environment in which the operating system is running, and general operating systems such as Android and IOS can be run. REE is an open environment that is vulnerable to attacks. TEE is a secure area on the central processing unit that can ensure that sensitive data is processed in an isolated and trusted environment, thereby protecting it from software attacks in REE. Compared with other secure execution environments, TEE can protect the integrity and confidentiality of trusted applications (TA) end-to-end, and can provide stronger processing power and larger memory space. TEE provides an interface for the software in REE, so that the software in REE can call the data in TEE for processing, but will not leak sensitive data.
[0076] For other contents about the above-mentioned terminal devices, network devices, and semantic library storage devices, please refer to the description in the communication system 100, which will not be repeated here.
[0077] The terminal device in the embodiment of the present application can communicate with one or more core networks via a radio access network (RAN), and the terminal device can be called an access terminal, user equipment (UE), user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent or user device. The access terminal can be a cellular phone, a cordless phone, a session initiation protocol (SIP) phone, a wireless local loop (WLL) station, a personal digital assistant (PDA), a handheld device with wireless communication function, a computing device or other processing device connected to a wireless modem, a vehicle-mounted device, a wearable device, a terminal device in a future 5G network, or a terminal device in a future evolved public land mobile network (PLMN), etc.
[0078] The network device in the embodiment of the present application can be a device for communicating with a terminal device. The network device can be a base station (base transceiver station, BTS) in a global system for mobile communications (GSM) system or code division multiple access (CDMA), or a base station (NodeB, NB) in a wideband code division multiple access (WCDMA) system, or an evolved base station (evolved NodeB, eNB or eNodeB) in an LTE system, or a wireless controller in a cloud radio access network (CRAN) scenario, or the network device can be a relay station, an access point, a vehicle-mounted device, a wearable device, a network device in a future 5G network, or a network device in a future evolved PLMN network, etc. The embodiment of the present application is not limited to this. For example, a gNB in an NR system, or a transmission point (TRP or TP), one or a group of antenna panels (including multiple antenna panels) of a base station in a 5G system, or a network node constituting a gNB or a transmission point, such as a baseband unit (BBU) or a distributed unit (DU).
[0079] In some deployments, the gNB may include a centralized unit (CU) and a DU. The gNB may also include a radio unit (RU). The CU implements some functions of the gNB, and the DU implements some functions of the gNB, for example, the CU implements the functions of the radio resource control (RRC) and packet data convergence protocol (PDCP) layers, and the DU implements the functions of the radio link control (RLC) layer, the media access control (MAC) layer, and the physical (PHY) layer. Since the information of the RRC layer will eventually become the information of the PHY layer, or be converted from the information of the PHY layer, therefore, under this architecture, high-level signaling, such as RRC layer signaling, can also be considered to be sent by the DU, or by the DU+CU. It can be understood that the network device can be a CU node, a DU node, or a device including a CU node and a DU node. In addition, the CU can be divided into a network device in an access network (radio access network, RAN), and the CU can also be divided into a network device in a core network (core network, CN), which is not limited in this application.
[0080] The above-mentioned network device can also refer to the general term for all devices on the network end. For example, when multiple TRPs are used to transmit data to a terminal device, multiple TRPs can be collectively referred to as network devices.
[0081] In an embodiment of the present application, a terminal device or a network device includes a hardware layer, an operating system layer running on the hardware layer, and an application layer running on the operating system layer. The hardware layer includes hardware such as a central processing unit (CPU), a memory management unit (MMU), and a memory (also called main memory). The operating system can be any one or more computer operating systems that implement business processing through a process, such as a Linux operating system, a Unix operating system, an Android operating system, an iOS operating system, or a windows operating system. The application layer includes applications such as a browser, an address book, a word processing software, and an instant messaging software. In addition, the embodiment of the present application does not specifically limit the specific structure of the execution subject of the method provided in the embodiment of the present application, as long as it can communicate according to the method provided in the embodiment of the present application by running a program that records the code of the method provided in the embodiment of the present application, for example, the execution subject of the method provided in the embodiment of the present application can be a terminal device or a network device, or a functional module in a terminal device or a network device that can call a program and execute a program.
[0082] In addition, various aspects or features of the present application can be implemented as methods, devices or products using standard programming and / or engineering techniques. The term "product" used in this application covers computer programs that can be accessed from any computer-readable device, carrier or medium. For example, computer-readable media may include, but are not limited to: magnetic storage devices (e.g., hard disks, floppy disks or tapes, etc.), optical disks (e.g., compact discs (CDs), digital versatile discs (DVDs), etc.), smart cards and flash memory devices (e.g., erasable programmable read-only memory (EPROM), cards, sticks or key drives, etc.). In addition, the various storage media described herein may represent one or more devices and / or other machine-readable media for storing information. The term "machine-readable medium" may include, but is not limited to, wireless channels and various other media capable of storing, containing and / or carrying instructions and / or data.
[0083] To facilitate understanding, the semantic communication involved in the embodiments of the present application is first introduced below.
[0084] Semantic communication generally refers to the communication between different intelligent agents for the purpose of "expressing meaning". Here, "intelligent agents" can refer to humans, intelligent machines, or even other organisms. The fundamental purpose of semantic communication is to exchange information. It does not pursue the fidelity of original data or signals, but to accurately transmit semantics between the two communicating parties.
[0085] In object-oriented semantic communication, both parties need to rely on a shared semantic library to compress and restore the communication content consistently to reduce the communication bandwidth overhead. The semantic library is a set of parameters and models that can establish a certain mapping relationship with the communication content. Usually, the sender can first objectify the original data based on the semantic library, that is, extract semantics, and send the objectified semantics to the receiver. The receiver then renders and merges the objectified semantics with the corresponding model based on the semantic library to obtain the restored content.
[0086] At present, the terminal devices at both ends of the sending and receiving rely on a public semantic library for semantic communication. The public semantic library is stored in the server. The terminal devices at both ends of the sending and receiving need to download the public semantic library to the local storage, which will occupy the memory resources of the terminal devices and have high requirements on the computing power of the terminal devices, resulting in a heavy burden on the terminal devices and affecting the processing performance of the terminal devices.
[0087] In view of this, the present application proposes a semantic communication method and device, which provides a method for distributing and acquiring a semantic library, and a network device obtains the semantic library used for semantic communication between terminal devices. The network device performs semantic extraction and semantic restoration in the process of semantic communication, and the terminal device does not need to store the semantic library. In this way, the burden on the terminal device can be reduced, and the impact on the processing performance of the terminal device can be reduced, thereby improving the communication success rate and improving the user experience.
[0088] The semantic communication method and semantic communication device provided by the present application will be described in detail below with reference to the accompanying drawings. It should be understood that the technical solution of the present application can be applied to wireless communication systems, for example, Figure 1 The communication system 100 shown in Figure 2 The communication system 200 is shown.
[0089] If the embodiments of the present application are applied Figure 1 In the communication system 100 shown in FIG. 1 , the first terminal device is equivalent to Figure 1 The terminal device 110 in the second terminal device is equivalent to Figure 1 The terminal device 120 in the first network device is equivalent to Figure 1 The network device 130 in the second network device is equivalent to Figure 1 The network device 140 in.
[0090] If the embodiments of the present application are applied Figure 2 In the communication system 200 shown in FIG. 1 , the first terminal device is equivalent to Figure 2 The terminal device 210 in the second terminal device is equivalent to Figure 2 The terminal device 220 in the first network device is equivalent to Figure 2The network device 230 in the second network device is equivalent to Figure 2 The network device 240 in.
[0091] Figure 3 A schematic flow chart of a semantic communication method 300 provided in an embodiment of the present application is shown. The method 300 includes:
[0092] S301, a first terminal device sends a semantic communication request to a first network device, where the semantic communication request is used to request communication with a second terminal device, and the semantic communication request carries source information of the first terminal device; correspondingly, the first network device receives the semantic communication request from the first terminal device.
[0093] In an embodiment of the present application, the first terminal device and the second terminal device are the communicating parties of semantic communication, wherein the first terminal device is the sending end of the semantic communication, and the second terminal device is the receiving end of the semantic communication.
[0094] The above-mentioned source information can be understood as the original information used for semantic communication. The source information in the embodiment of the present application can be information that has not been semantically compressed, or it can be information that has been partially semantically compressed. That is, the source information can be compressed and transmitted, or it can be transmitted without compression. The embodiment of the present application does not limit this.
[0095] S302: The first network device performs semantic extraction on the source information based on the semantic library between the first terminal device and the second terminal device to obtain semantic key information.
[0096] It should be understood that the semantic library here can be a private semantic library between the first terminal device and the second terminal device, or it can be a public semantic library designated between the first terminal device and the second terminal device, and the embodiments of the present application do not limit this. Different communicating parties can establish different semantic libraries. When performing semantic communication, the semantic extraction on the sending side (for example, including the first terminal device and the first network device) and the semantic restoration on the receiving side (for example, including the second terminal device and the second network device) both rely on the semantic libraries on both ends of the sending and receiving ends (for example, the semantic library between the first terminal device and the second terminal device).
[0097] The above-mentioned semantic extraction operations include but are not limited to artificial intelligence (AI) model training of source-channel joint coding, semantic encoding and decoding based on object-oriented transmission, or other forms of task collaboration and segmentation operations.
[0098] The above-mentioned semantic key information can also be called "semantic information", which is information related to the original data (i.e., the above-mentioned source information). Semantic information may be the product of an artificial intelligence or machine language (ML) model, with descriptive content full of labels and objects. Semantic information can also be considered as instructions or maps for recovering the original data.
[0099] In the embodiment of the present application, the first network device performs the semantic extraction operation. In this way, the first network device needs to obtain and store the semantic library between the first terminal device and the second terminal device, while the first terminal device does not need to perform the semantic extraction operation or obtain and store its semantic library, thereby saving memory.
[0100] S303, the first network device sends a first ciphertext to the second network device, where the first ciphertext is obtained by encrypting the semantic key information and the index information of the semantic library based on the public key of the second network device, and the second network device is a network device that provides services for the second terminal device; correspondingly, the second network device receives the first ciphertext.
[0101] The index information of the semantic library is used to uniquely identify the semantic library between the first terminal device and the second terminal device, and the corresponding semantic library can be obtained through the index information. Therefore, the first network device can send the index information of the semantic library to the second network device, so that the second network device can obtain the semantic library according to the index information.
[0102] S304: The second network device decrypts the first ciphertext using the private key of the second network device to obtain the semantic key information and the index information of the semantic library.
[0103] It should be understood that the second network device can pre-generate a public-private key pair and send the public key to the first network device, while keeping the private key itself. The first network device can use the public key of the second network device to encrypt the semantic key information and the index information of the semantic library after semantic extraction to obtain the first ciphertext. After the second network device receives the first ciphertext, it uses its own private key to decrypt it, thereby obtaining the semantic key information and the index information of the semantic library. If other devices obtain the first ciphertext, they cannot decrypt it. This is conducive to preventing information leakage and improving the security of semantic communication.
[0104] S305: The second network device obtains the semantic library based on the index information of the semantic library.
[0105] S306: The second network device performs semantic restoration on the semantic key information based on the semantic library to obtain semantic restoration information.
[0106] The above-mentioned semantic restoration operations include but are not limited to decoding based on the combination of information source and channel, semantic restoration based on objectification, or other tasks coordination and segmentation operations.
[0107] S307, the second network device sends semantic restoration information to the second terminal device; correspondingly, the second terminal device receives the semantic restoration information.
[0108] The semantic communication method of the embodiment of the present application performs semantic extraction and semantic restoration in the process of semantic communication through the network devices of the communicating parties respectively, without the need for the terminal device to store the semantic library. This can reduce the burden on the terminal device and the impact on the processing performance of the terminal device, thereby improving the communication success rate and improving the user experience.
[0109] As an optional embodiment, the above S302 performs semantic extraction on the source information based on the semantic library between the first terminal device and the second terminal device, including: performing semantic extraction on the source information based on the semantic library between the first terminal device and the second terminal device, the first network device providing service for the first terminal device, the second network device and the semantic communication type supported by the second terminal device.
[0110] It should be understood that semantic extraction can only be performed based on a certain semantic communication type when both the devices on the sending and receiving sides support the semantic communication type. Otherwise, the first network device on the sending side performs semantic extraction based on a certain semantic communication type, but the second network device on the receiving side may not support the semantic communication type and cannot perform semantic restoration on the received information, resulting in semantic communication failure. Therefore, before performing semantic extraction, the first network device must first determine the semantic communication types supported by the first network device, the second network device, and the second terminal device, and then perform semantic extraction according to the semantic communication types they all support, which is conducive to improving the communication success rate.
[0111] Exemplarily, semantic communication types may include source-channel joint coding, object-based semantic extraction, multimedia encoding and decoding, task segmentation, and the like.
[0112] In the embodiment of the present application, the first network device can determine the semantic communication type commonly supported by the first network device, the second network device and the second terminal device in a variety of different ways, and the embodiment of the present application is not limited to this.
[0113] In one possible implementation, the first network device sends a first capability report, which is used to indicate the semantic communication capability of the first network device; the first network device receives a third capability report, which is used to indicate the semantic communication type supported by the first network device, the second network device and the second terminal device.
[0114] Exemplarily, the first network device can send the first capability report to the second network device, and the second network device can also obtain the semantic communication capability of the second terminal device, that is, the second network device summarizes the information, determines the above-mentioned third capability report, and sends the third capability report to the first network device.
[0115] Exemplarily, the first network device can send the first capability report to other devices (such as other core network devices), and the other devices can also obtain the semantic communication capability of the second terminal device and the semantic communication capability of the second network device, that is, the other core network devices aggregate the information, determine the above-mentioned third capability report, and send the third capability report to the first network device.
[0116] In another possible implementation, the first network device receives a second capability report from a second network device, where the second capability report is used to indicate the semantic communication capability of the second network device; the first network device receives a capability query report from a second terminal device, where the capability query report is used to indicate the semantic communication capability of the second terminal device; the first network device determines the semantic communication type supported by the first network device, the second network device, and the second terminal device based on the second capability report, the capability query report, and the semantic communication capability of the first network device.
[0117] In the above implementation, the first network device aggregates information to determine the semantic communication type commonly supported by the first network device, the second network device, and the second terminal device.
[0118] As an optional embodiment, the capability query report carries identification information of the semantic communication type supported by the second terminal device and computing power information of the semantic communication type supported by the second terminal device.
[0119] It should be understood that the above-mentioned first capability report, second capability report and third capability report may also carry identification information and computing power information of the corresponding semantic communication type, which will not be described in detail here.
[0120] As an optional embodiment, the method further includes: the first network device obtains the semantic library and index information of the semantic library.
[0121] Since the semantic library used in the embodiment of the present application is created by the first terminal device, and the first network device is a network device that provides services for the first terminal device, the first terminal device can optionally directly send the semantic library created by the first terminal device and the index information of the semantic library to the first network device. In addition, the first network device can also obtain the semantic library from the semantic library storage device, which is not limited in the embodiment of the present application.
[0122] As an optional embodiment, the above S305, the second network device obtains the semantic library based on the index information of the semantic library, including: the second network device sends a request message to the semantic library storage device, the request message is used to request the semantic library, and the request message carries the index information of the semantic library; correspondingly, the semantic library storage device receives the request message. The semantic library storage device searches for the encrypted information of the semantic library between the first terminal device and the second terminal device according to the index information in the request message, and sends the encrypted information of the semantic library to the second network device; correspondingly, the second network device receives the encrypted information of the semantic library. The second network device determines the semantic library based on the encrypted information of the semantic library.
[0123] It should be understood that after the semantic library is created, it is sent by the terminal device that creates the semantic library to the semantic library storage device for storage. However, what is sent here is not the semantic library itself, but the encrypted information of the semantic library. In this way, after other devices obtain the encrypted information of the semantic library, they need to decrypt it. Only after the decryption is successful can subsequent semantic restoration operations be performed, which improves the security of semantic communication.
[0124] As an optional embodiment, the index information of the semantic library is obtained by processing the encrypted information of the semantic library using a one-way derivative function, and the encrypted information of the semantic library is obtained by encrypting the information of the semantic library using the public key of the second terminal device.
[0125] The second network device determines the semantic library based on the encrypted information of the semantic library, including: the second network device decrypts the encrypted information of the semantic library using the private key of the second terminal device to obtain the semantic library.
[0126] In the embodiment of the present application, the encrypted information of the semantic library is obtained by encrypting the information of the semantic library using the public key of the terminal device of the semantic communication peer. Exemplarily, the first terminal device creates the above-mentioned semantic library, which is used for semantic communication between the first terminal device and the second terminal device. The first terminal device encrypts the information of the semantic library using the public key of the second terminal device, and only the device with the private key of the second terminal device can decrypt it.
[0127] The index information of the semantic library is information that uniquely identifies the semantic library. The one-way derivation function may be a hash function, but this is not limited in the embodiment of the present application.
[0128] As an optional embodiment, the method of the embodiment of the present application is applied to a first network device provided with TEE and a second network device provided with TEE; wherein, S302, semantic extraction of the source information is performed, including: in the TEE of the first network device, semantic extraction of the source information is performed; S306, based on the semantic library, semantic restoration of the semantic key information is performed, including: in the TEE of the second network device, based on the semantic library, semantic restoration of the semantic key information is performed.
[0129] Since TEE is a secure area, it can ensure that sensitive data is processed in an isolated and trusted environment. By performing semantic extraction and restoration in the TEE of network devices, it can save the memory of terminal devices while improving the security of semantic communication and protecting user privacy.
[0130] Figure 4 A schematic flow chart of another semantic communication method 400 provided in an embodiment of the present application is shown. The method 400 includes:
[0131] S401: A first terminal device creates a semantic library of the first terminal device, and determines encryption information of the semantic library and index information of the semantic library.
[0132] S402, the first terminal device sends the encryption information of the semantic library and the index information of the semantic library to the semantic library storage device; correspondingly, the semantic library storage device receives and stores the encryption information of the semantic library and the index information of the semantic library.
[0133] It should be understood that the above S402 assumes that the first terminal device has the ability to access the semantic library storage device, and the first terminal device can directly communicate with the semantic library storage device. If the first terminal device does not have the ability to access the semantic library storage device, the following S403 and S405 are executed.
[0134] S403, the first terminal device sends the encryption information of the semantic library and the index information of the semantic library to the first network device; correspondingly, the first network device receives the encryption information of the semantic library and the index information of the semantic library.
[0135] S404, the first network device sends the encryption information of the semantic library and the index information of the semantic library to the semantic library storage device; correspondingly, the semantic library storage device receives and stores the encryption information of the semantic library and the index information of the semantic library.
[0136] It should be understood that the encryption information of the semantic library and the index information of the semantic library can be sent together or separately, and this embodiment of the present application does not limit this.
[0137] It should also be understood that when semantic restoration is needed, the device on the receiving side (such as the above-mentioned second network device) can use the index information of the semantic library to obtain the encrypted information of the semantic library from the above-mentioned semantic library storage device, thereby obtaining the semantic library between the first terminal device and the second terminal device.
[0138] The semantic communication method of the embodiment of the present application creates a private semantic library through the terminal device itself and saves the relevant information to the semantic library storage device, which can provide personalized communication for users under privacy constraints, thereby improving the user experience.
[0139] As an optional embodiment, the method also includes: the second terminal device sends an update request to the first terminal device, the update request is used to request updating of the semantic library; correspondingly, the first terminal device receives the update request from the second terminal device; in response to the update request, the first terminal device sends an update response to the second terminal device, the update response carries an updated public key; correspondingly, the second terminal device receives the update response.
[0140] In this way, the second terminal device can subsequently use the updated public key to encrypt the updated content and send the encrypted information to the semantic library storage device.
[0141] Optionally, if the first terminal device disagrees with the second terminal device updating the semantic library, the update response sent by the first terminal device to the second terminal device is a message for indicating rejection of the update, such as a negative acknowledgment (NACK) message.
[0142] As an optional embodiment, the method further includes: the first terminal device sends an updated private key to the third terminal device; correspondingly, the third terminal device receives the updated private key.
[0143] It should be understood that the updated public key and the updated private key may be referred to as an updated public-private key pair, and the updated public-private key pair is generated by the first terminal device.
[0144] In this embodiment, if there is another terminal device that is fully trusted, that is, the third terminal device mentioned above, and the third terminal device wants to perform semantic communication with the first terminal device and the second terminal device, the first terminal device can send an updated private key to the third terminal device, so that after the third terminal device obtains the encrypted information of the updated semantic library, it can use the updated private key to decrypt the encrypted information of the updated semantic library, thereby obtaining the updated semantic library, and perform subsequent communication based on the updated semantic library.
[0145] Optionally, the first terminal device may also send the updated hash value of the semantic library to the third terminal device, the third terminal device receives the updated hash value of the semantic library, and obtains the updated encryption information of the semantic library from the semantic library storage device based on the updated hash value of the semantic library.
[0146] The above process can be understood as the first terminal device creating a semantic communication group and inviting the third terminal device to join the semantic communication group. The members of the group include the first terminal device, the second terminal device and the third terminal device, all of which are fully trusted. The first terminal device can also invite a larger number of other terminal devices to join the semantic communication group and send updated private keys to these terminal devices, which is not limited in the embodiments of the present application.
[0147] Below, without loss of generality, the semantic communication method provided by the embodiment of the present application is described in detail by taking the interaction process between devices as an example. Terminal device 1 corresponds to the first terminal device in the above method, terminal device 2 corresponds to the second terminal device in the above method, network device 1 corresponds to the first network device in the above method, and network device 2 corresponds to the second network device in the above method.
[0148] Figure 5 A schematic flow chart of a semantic communication method 500 provided in an embodiment of the present application is shown. The method 500 includes:
[0149] S501, terminal device 1 establishes an RRC connection with network device 1 based on a public-private key pair (PKu1, SKu1), and passes two-way authentication with network device 1.
[0150] It should be understood that the public-private key pair (PKu1, SKu1) is the public-private key pair of terminal device 1. After S501, a communication connection is established between terminal device 1 and network device 1, and two-way authentication is completed with the network device, which can be understood as terminal device 1 has accessed the network.
[0151] S502, terminal device 1 wants to perform semantic communication with terminal device 2, and terminal device 1 and terminal device 2 complete two-way authentication based on public key identity through network paging terminal device 2.
[0152] It should be understood that it is assumed here that the terminal device 2 is also connected to the network, so that the terminal device 2 can be paged by the network. In the embodiment of the present application, the terminal device 2 is connected to the network device 2. The public and private key pair of the terminal device 2 is (PKu2, SKu2).
[0153] In a possible implementation, terminal device 1 may send a paging request to network device 1 to request paging of terminal device 2, the paging request carries Hash (PKu2), network device 1 sends the paging request to network device 2, network device 2 sends a paging message to terminal device 2 based on the paging request, the paging message carries Hash (PKu1), indicating that terminal device 1 requests paging of terminal device 2. Terminal device 2 may choose whether to accept the paging of terminal device 1. In the case that terminal device 2 accepts the paging, terminal device 2 sends a paging response to network device 2, the paging response may be, for example, an acknowledgment (ACK) message. Next, a protocol data unit (PDU) session is established between terminal device 1 and terminal device 2, and two-way authentication is completed based on the public-private key pair of both parties.
[0154] S503, terminal device 1 creates a semantic library A (library A, LA), and uses the public key PKu2 of terminal device 2 to calculate PKu2(LA) and Hash(PKu2(LA)).
[0155] It should be understood that the semantic library LA here may be a private semantic library between the terminal device 1 and the terminal device 2 .
[0156] The above Hash(PKu2(LA)) represents the hash value obtained after performing a hash operation on PKu2(LA). Hash(PKu2(LA)) can be understood as the identification information or index information of LA derived from PKu2(LA).
[0157] The following discusses different situations according to whether the terminal device 1 has the ability to access the semantic base storage device (ie, whether the network address of the semantic base storage device is reachable to the terminal device 1).
[0158] Case 1: if the terminal device 1 has the ability to access the semantic library storage device, execute S504.
[0159] S504, terminal device 1 sends PKu2(LA), Hash(PKu2(LA)), the public key identity (identity, ID) of terminal device 1 and the public key ID of terminal device 2 to the semantic database storage device. Correspondingly, the semantic database storage device receives the above information.
[0160] It should be understood that the above-mentioned public key ID is an ID derived from the public key. The public key ID of the terminal device 1 can be, for example, the distributed identity, blockchain address, etc. of the terminal device 1, and can specifically be, for example, Hash (PKu1).
[0161] Case 2: if the terminal device 1 does not have the ability to access the semantic library storage device, then S505 and S506 are executed.
[0162] S505, terminal device 1 sends PKu2(LA), Hash(PKu2(LA)), the public key ID of terminal device 1, and the public key ID of terminal device 2 to network device 1. Correspondingly, network device 1 receives the above information.
[0163] S506, network device 1 sends PKu2(LA), Hash(PKu2(LA)), the public key ID of terminal device 1, and the public key ID of terminal device 2 to the semantic database storage device. Correspondingly, the semantic database storage device receives the above information.
[0164] It should be understood that the information in the above S504 to S506 (such as PKu2(LA), Hash(PKu2(LA)), etc.) can be sent together or separately, and this embodiment of the present application does not limit this.
[0165] S507, the semantic library storage device stores PKu2(LA), Hash(PKu2(LA)), the public key ID of terminal device 1, and the public key ID of terminal device 2.
[0166] S508, terminal device 1 sends the hash value of LA, namely the above-mentioned Hash(PKu2(LA)), to terminal device 2. Correspondingly, the terminal device receives the hash value of LA.
[0167] In an embodiment of the present application, the terminal device 2 can obtain LA from the network device 2 based on the hash value of the received LA, or it can obtain LA from the semantic library storage device (when the terminal device 2 has access to the semantic library storage device), and the embodiment of the present application is not limited to this.
[0168] In a possible implementation, S509 to S512 are executed.
[0169] S509, network device 2 sends a query request to the semantic database storage device, the query request is used to request to query the semantic database corresponding to the public key ID of terminal device 1 and the public key ID of terminal device 2. Correspondingly, the semantic database storage device receives the query request.
[0170] It should be understood that in actual applications, there may be multiple terminal devices that perform semantic communication with terminal device 2, and the number of semantic libraries corresponding to terminal device 2 is multiple. Therefore, through the public key ID of terminal device 1 and the public key ID of terminal device 2, the semantic library used for communication between terminal device 1 and terminal device 2 can be accurately found.
[0171] S510: The semantic library storage device obtains PKu2 (LA) based on the query request, and sends PKu2 (LA) to the network device 2. Correspondingly, the network device 2 receives and stores PKu2 (LA).
[0172] It should be understood that in a specific implementation, there may be multiple terminal devices connected to the network device 2. The network device 2 can obtain the semantic libraries of the multiple terminal devices from the semantic library storage device according to the public key ID of each terminal device, and store them for subsequent use by the terminal devices.
[0173] The embodiment of the present application does not limit the execution order of the above S508 and S509 to S510.
[0174] S511, terminal device 2 sends a request message to network device 2 to request to obtain LA, and the request message carries the hash value of LA. Correspondingly, network device 2 receives the request message.
[0175] S512, network device 2 sends PKu2(LA) to terminal device 2 based on the hash value of LA. Correspondingly, terminal device 2 receives PKu2(LA).
[0176] Exemplarily, when network device 2 stores semantic libraries of multiple terminal devices, network device 2 can calculate the hash value of each semantic library separately. For the semantic library LA of terminal device 2, network device 2 can use a preset hash function and PKu2(LA) obtained from the semantic library storage device to calculate Hash(PKu2(LA)), and then match the hash value of LA carried in the request message of S511 to determine the corresponding PKu2(LA) and send it to terminal device 2.
[0177] In this implementation, the network device 2 pre-caches the semantic library information locally, and the terminal device 2 can directly obtain it from the network device 2 when it is used later, which can improve the acquisition speed of the semantic library and improve the efficiency of subsequent semantic communication.
[0178] In another possible implementation, S513 and S514 are executed.
[0179] S513, the terminal device 2 sends a request message to the semantic database storage device to request to obtain LA, and the request message carries the hash value of LA. Correspondingly, the semantic database storage device receives the request message.
[0180] S514, the semantic library storage device sends PKu2 (LA) to the terminal device 2 based on the hash value of LA. Correspondingly, the terminal device 2 receives PKu2 (LA).
[0181] Optionally, in the above S512, the network device 2 may send PKu2(LA) to the terminal device 2 in the form of streaming, and in the above S514, the semantic library storage device may send PKu2(LA) to the terminal device 2 in the form of streaming. The main advantage of streaming transmission is that the user can view or listen to the received data without waiting for the download to be completed. On the one hand, it does not require a large amount of storage space, which can save the memory of the terminal device. On the other hand, the user of the terminal device 2 can download while watching, which saves the user's waiting time, thereby improving the user experience.
[0182] S515, terminal device 2 uses its own private key SKu2 to decrypt PKu2 (LA) to obtain LA.
[0183] In this way, semantic alignment is completed between terminal device 1 and terminal device 2, and subsequent semantic communication can be carried out.
[0184] Optionally, if there is new semantic information that needs to be updated to the original LA, the semantic communication method of the embodiment of the present application may further include the following steps:
[0185] S516, terminal device 2 sends an update request to terminal device 1, the update request is used to request to update LA, and the update request carries the hash value of LA. Correspondingly, terminal device 1 receives the update request.
[0186] S517, if the terminal device 1 agrees that the terminal device 2 updates the LA, the terminal device 1 creates a public-private key pair (PK LA’ , S.K. LA’ ).
[0187] S518, terminal device 1 sends an update response to terminal device 2, and the update response carries PK LA’ Correspondingly, terminal device 2 receives the update response.
[0188] S519, terminal device 2 uses the public key PK based on LA' LA’ , send the PK to the semantic library storage device LA’ The encrypted updated content and the new hash value, Hash(PK LA’ (LA')). Correspondingly, the semantic library storage device receives the above-mentioned PK LA’ The encrypted updated content and the new hash value.
[0189] S520, the semantic library storage device updates the stored LA to LA', and updates the hash value Hash(PKu2(LA)) to the new hash value Hash(PK LA’ (LA')).
[0190] Optionally, the terminal device 2 can use the new hash value Hash(PK LA’ (LA')) is sent to terminal device 1, so that terminal device 1 can subsequently obtain updated semantic library information from the semantic library storage device according to the new hash value. Optionally, terminal device 1 can also obtain updated semantic library information from the semantic library storage device according to the public key ID of terminal device 1 and the public key ID of terminal device 2. The embodiments of the present application are not limited to the above two methods.
[0191] When terminal device 1 and terminal device 2 perform semantic communication, terminal device 1 can obtain PK LA’ (LA'), and adopt SK LA’ PK LA’ (LA') is decrypted to obtain LA', and subsequent communication is carried out based on LA'.
[0192] Optionally, in the above S517, the terminal device 1 disagrees with the terminal device 2 updating the LA, and the update response sent by the terminal device 1 to the terminal device 2 is a message for indicating the rejection of the update, such as a NACK message.
[0193] Optionally, if there is another fully trusted terminal device 3, which wants to communicate semantically with terminal device 1 and terminal device 2, terminal device 1 can send the private key SK of LA' to terminal device 3. LA’ and LA's hash value Hash(PK LA’ (LA')), so that the terminal device 3 obtains PK based on the hash value of LA' LA’ (LA'), terminal device 3 can use SK LA’ PK LA’ (LA') is decrypted to obtain LA', and subsequent communication is performed based on LA'.
[0194] The above process can be understood as terminal device 1 creating a semantic communication group and inviting terminal device 3 to join the semantic communication group. The members of the group include terminal device 1, terminal device 2 and terminal device 3, all of which are fully trusted.
[0195] The embodiments of the present application support encrypted storage, sharing and updating of semantic libraries by individuals or groups. When each user initiates a semantic call through a terminal device, the network can match the semantic library, thereby reducing the latency in acquiring the semantic library. At the same time, users are allowed to update the models and parameters of private semantic libraries in an end-to-end scenario, thereby reducing privacy exposure.
[0196] Combined with the above Figure 5The method 500 shown introduces the process of semantic distribution between terminal device 1 and terminal device 2. In the above process, the network side needs to assist the terminal device in caching and updating the semantic library according to the index information of the semantic library to provide lower interaction delay.
[0197] Next, combine Figure 6 The process of semantic communication between terminal device 1 and terminal device 2 is introduced.
[0198] In this process, network device 1 may perform a semantic extraction operation in the TEE of network device 1 (abbreviated as TEE 1), and network device 2 may perform a semantic restoration operation in the TEE of network device 2 (abbreviated as TEE 2).
[0199] Figure 6 A schematic flow chart of another semantic communication method 600 provided in an embodiment of the present application is shown. The method 600 includes:
[0200] S601, terminal device 1 performs two-way authentication with TEE 1 in network device 1 based on the public-private key pair (PKu1, SKu1).
[0201] S602, terminal device 1 sends a semantic communication request to the control plane of network device 3, requesting semantic communication with terminal device 2, the semantic communication request carries the public key ID of terminal device 2. Correspondingly, the control plane of network device 3 receives the semantic communication request.
[0202] It should be understood that the above-mentioned public key ID is an ID derived from the public key. The public key ID of the terminal device 2 can be, for example, the distributed identity, blockchain address, etc. of the terminal device 2, and can specifically be, for example, Hash (PKu2).
[0203] It should also be understood that it is assumed here that terminal device 1 and network device 3 have performed a two-way authentication based on a public key, and that terminal device 1 and terminal device 2 have performed a two-way authentication based on a public key, which is not shown in the figure.
[0204] S603, terminal device 1 creates LA, and sends LA and the hash value Hash(PKu2(LA)) of LA to TEE 1 of network device 1. Correspondingly, TEE 1 of network device 1 receives and stores the LA and the hash value of LA.
[0205] S604, terminal device 1 sends PKu2(LA) and the hash value Hash(PKu2(LA)) of LA to the semantic library storage device. Correspondingly, the semantic library storage device receives and stores PKu2(LA) and the hash value Hash(PKu2(LA)) of LA.
[0206] S605, the control surface of the network device 3 sends a capability query request to the terminal device 2, the capability query request carrying capability type information, to query whether the terminal device 2 supports the capability corresponding to the capability type information. Correspondingly, the terminal device 2 receives the capability query request.
[0207] Exemplarily, the capability type information may include an identifier of at least one of the following capability types:
[0208] Capability type 1: the terminal device has the capability to perform source-channel joint coding;
[0209] Capability type 2: the terminal device has the ability to extract semantics based on objects;
[0210] Capability type 3: the terminal device has multimedia encoding and decoding capabilities;
[0211] Capability type 4: the terminal device has no semantic capabilities;
[0212] Capability type 5: The terminal device has the ability to select task segmentation.
[0213] S606, the terminal device 2 sends a capability query response to the control plane of the network device 3, where the capability query response is used to indicate the support status of the capability queried in the capability query request by the terminal device 2. Correspondingly, the control plane receives the capability query response.
[0214] Optionally, the capability query response carries an identifier of at least one capability type in the capability query request and information indicating whether the terminal device 2 supports each capability type in the at least one capability type.
[0215] In a possible implementation, the information used to indicate whether the terminal device 2 supports each capability type in the at least one capability type is ACK or NACK. For example, ACK indicates that the terminal device 2 supports the corresponding capability, and NACK indicates that the terminal device 2 does not support the corresponding capability.
[0216] In another possible implementation, the information used to indicate whether the terminal device 2 supports each capability type in the at least one capability type is 0 or 1, for example, 1 indicates that the terminal device 2 supports the corresponding capability, and 0 indicates that the terminal device 2 does not support the corresponding capability, or 0 indicates that the terminal device 2 supports the corresponding capability, and 1 indicates that the terminal device 2 does not support the corresponding capability.
[0217] In another possible implementation, the information used to indicate whether the terminal device 2 supports each capability type in the at least one capability type is 0, 1 or 2. For example, 1 indicates that the terminal device 2 has the corresponding capability without network assistance, 2 indicates that the terminal device 2 has the corresponding capability with network assistance, and 0 indicates that the terminal device 2 has no response capability.
[0218] It should be understood that there are other possible situations for the above information used to indicate whether the terminal device 2 supports each capability type in the at least one capability type, which are not listed here one by one.
[0219] S607, the terminal device 2 and the network device 3 perform a two-way authentication based on the public key.
[0220] S608, terminal device 2 sends the public key PKu2 of terminal device 2 to TEE 2 of network device 2. Correspondingly, TEE 2 receives the public key PKu2.
[0221] S609, TEE 2 of network device 2 uses the public key PKu2 of terminal device 2 to initialize TEE, and uses the public key PKu2 of terminal device 2 to perform remote attestation (RA) to ensure that the computing environment is secure.
[0222] It should be understood that the remote attestation here is used to determine whether the platform for interaction between the TEE 2 of the network device 2 and the terminal device 2 is credible throughout the process. The remote attestation process between the TEE 2 of the network device 2 and the terminal device 2 can be equivalent to a two-way authentication between the network device 2 and the terminal device 2.
[0223] S610, TEE 1 of network device 1 sends a first capability report to the control plane of network device 3, indicating the support of semantic communication capability by TEE 1. Correspondingly, the control plane of network device 3 receives the first capability report. Exemplarily, the first capability report carries the capability type identifier of the capability supported by TEE 1.
[0224] In the embodiment of the present application, S603 and S604 may be executed after S602 and before S610. The embodiment of the present application does not limit the execution order of S603 and S604 and S604 to S609.
[0225] S611, the control surface of the network device 3 sends the first capability report to the TEE 2 of the network device 2. Correspondingly, the TEE 2 of the network device 2 receives the first capability report.
[0226] S612, TEE 2 of network device 2 sends a second capability report to the control plane of network device 3, which is used to indicate TEE 2's support for semantic communication capabilities, or to indicate TEE 2's support for capabilities corresponding to the capability type identifier carried in the first capability report. Correspondingly, the control plane of network device 3 receives the second capability report. Exemplarily, the second capability report carries the capability type identifier of the capabilities supported by TEE 2, or the second capability report carries the capability type identifier in the first capability report and information indicating whether TEE 2 supports the capability type corresponding to the capability type identifier.
[0227] Optionally, the second capability report also carries computing power information of each capability type supported by TEE 2.
[0228] S613, the control plane of network device 3 determines the capability types commonly supported by TEE 1, TEE 2 and terminal device 2 according to the information obtained in S606 and S612.
[0229] S614, the control surface of network device 3 sends a third capability report to TEE 1 of network device 1, which is used to indicate the support of voice communication capability by TEE 1, TEE 2 and terminal device 2. The third capability report carries the identifier of the capability type supported by TEE 1, TEE 2 and terminal device 2. Correspondingly, TEE 1 of network device 1 receives the third capability report.
[0230] Optionally, if the second capability report of S611 carries computing power information of each capability type supported by TEE 2, the third capability report also carries computing power information of each capability type supported by TEE 2.
[0231] It should be understood that the above S610~S614 can be understood as the process of semantic alignment on the network device side. When the capabilities of TEE 1, TEE 2 and terminal device 2 all support the corresponding semantic communication type, subsequent semantic communication is performed to ensure that the semantic communication can proceed smoothly.
[0232] S615, terminal device 1 sends its own information source, that is, original information for semantic communication, to TEE 1 of network device 1. Correspondingly, TEE 1 of network device 1 receives the information source of terminal device 1.
[0233] It should be understood that the above information source may be information without semantic compression or information after partial semantic compression, which is not limited in the embodiments of the present application. The information may be transmitted after compression or without compression, which is not limited in the embodiments of the present application.
[0234] Optionally, in order to support source-channel joint coding, the terminal device 1 may also send raw data for source-channel joint encoder AI model training to the TEE 1 of the network device 1. The TEE 1 may train the raw data and provide the trained source-channel joint encoder to the terminal device 1.
[0235] S616, TEE 1 of network device 1 performs a semantic extraction operation on the source received in S615 based on the LA obtained in S603 to obtain semantic key information.
[0236] The above-mentioned semantic extraction operation is not limited to AI model training of source-channel joint coding, semantic encoding and decoding based on object-oriented transmission, and other forms of task collaboration and segmentation, which are not limited in the embodiments of the present application.
[0237] S617, TEE 1 of network device 1 sends encrypted information to the user plane of network device 3, and the encrypted information is encrypted using the public key PK of TEE 2 T2 The semantic key information and the hash value of LA are encrypted.
[0238] S618, the user of network device 3 sends the above encrypted information to TEE 2 of network device 2.
[0239] S619, TEE 2 of network device 2 uses its own private key SK T2 Decrypt the above encrypted information to obtain the semantic key information and the hash value of LA.
[0240] S620, TEE 2 of network device 2 sends a first request message to the semantic library storage device to request to obtain the semantic library LA of terminal device 1, and the first request message carries the hash value Hash(PKu2(LA)) of LA. Correspondingly, the semantic library storage device receives the first request message.
[0241] S621, the semantic base storage device sends PKu2(LA) to TEE 2 of network device 2 based on the first request message. Correspondingly, TEE 2 of network device 2 receives PKu2(LA).
[0242] S622, TEE 2 of network device 2 sends a second request message to terminal device 2, requesting to obtain private key SKu2 of terminal device 2. Correspondingly, terminal device 2 receives the second request message.
[0243] S623, based on the second request message, the terminal device 2 sends the private key SKu2 of the terminal device 2 to the TEE 2 of the network device 2. Correspondingly, the TEE 2 of the network device 2 receives the private key SKu2 of the terminal device 2.
[0244] S624, TEE 2 of network device 2 uses private key SKu2 of terminal device 2 to decrypt PKu2 (LA) to obtain LA.
[0245] S625, TEE 2 of network device 2 performs semantic restoration on the semantic key information obtained in S619 based on LA to obtain restored content.
[0246] The semantic restoration here is not limited to decoding based on source-channel union, semantic restoration based on objectification, or other task coordination and segmentation methods.
[0247] S626, TEE 2 of network device 2 sends the semantically restored content to the user plane of network device 3. Correspondingly, the user plane of network device 3 receives the semantically restored content.
[0248] S627, the user of the network device 3 sends the semantically restored content to the terminal device 2. Correspondingly, the terminal device 2 receives the semantically restored content.
[0249] The semantic communication method of the embodiment of the present application performs semantic extraction and semantic restoration in the process of semantic communication through the network devices of the communicating parties respectively, without the need for the terminal device to store the semantic library. This can reduce the burden on the terminal device and the impact on the processing performance of the terminal device, thereby improving the communication success rate and improving the user experience.
[0250] It should be understood that in other possible implementations, network device 2 can directly send semantic key information to the user side of network device 3 without restoring it. The user side of network device 3 sends the semantic key information to terminal device 2, and terminal device 2 obtains the semantic library and restores the semantic key information by itself. The embodiments of the present application are not limited to this.
[0251] It should be understood that the sequence numbers of the above processes do not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
[0252] Combined with the above Figures 1 to 6 , describes in detail the semantic communication method according to the embodiment of the present application, and will now be combined with Figure 7 and Figure 8 , a semantic communication device according to an embodiment of the present application is described in detail.
[0253] Figure 7 The communication device 700 provided in the embodiment of the present application is shown. The device 700 includes: a transceiver unit 710 and a processing unit 720.
[0254] In one design, the apparatus 700 may be a first network device or a chip in the first network device.
[0255] Among them, the transceiver unit 710 is used to: receive a semantic communication request from a first terminal device, the semantic communication request is used to request communication with a second terminal device, and the semantic communication request carries source information of the first terminal device; the processing unit 720 is used to: based on the semantic library between the first terminal device and the second terminal device, perform semantic extraction on the source information to obtain semantic key information; the transceiver unit 710 is also used to: send a first ciphertext, the first ciphertext is obtained by encrypting the semantic key information and the index information of the semantic library based on the public key of the second network device, and the second network device is a network device that provides services for the second terminal device.
[0256] Optionally, the processing unit 720 is specifically used to: perform semantic extraction on the source information based on a semantic library between the first terminal device and the second terminal device, a semantic communication type supported by the device, the second network device and the second terminal device.
[0257] Optionally, the transceiver unit 710 is also used to: send a first capability report, wherein the first capability report is used to indicate the semantic communication capability of the device; and receive a third capability report, wherein the third capability report is used to indicate the semantic communication type supported by the device, the second network device, and the second terminal device.
[0258] Optionally, the transceiver unit 710 is also used to: receive a second capability report, wherein the second capability report is used to indicate the semantic communication capability of the second network device; receive a capability query report, wherein the capability query report is used to indicate the semantic communication capability of the second terminal device; and the processing unit 720 is also used to: determine the semantic communication type supported by the device, the second network device and the second terminal device based on the second capability report, the capability query report and the semantic communication capability of the device.
[0259] Optionally, the capability query report carries identification information of the semantic communication type supported by the second terminal device and computing power information of the semantic communication type supported by the second terminal device.
[0260] Optionally, the processing unit 720 is further configured to: obtain the semantic library and index information of the semantic library.
[0261] Optionally, the transceiver unit 710 is further used to: receive a semantic library and index information of the semantic library from the first terminal device.
[0262] Optionally, the index information of the semantic library is obtained by processing the encrypted information of the semantic library using a one-way derivative function, and the encrypted information of the semantic library is obtained by encrypting the information of the semantic library using the public key of the second terminal device.
[0263] Optionally, the device 700 is provided with a trusted execution environment TEE; the processing unit 720 is further used to: perform semantic extraction on the source information in the TEE.
[0264] In another design, the apparatus 700 may be a second network device, or a chip in the second network device.
[0265] Among them, the transceiver unit 710 is used to: receive a first ciphertext, which is obtained by encrypting the semantic key information and the index information of the semantic library based on the public key of the device; the processing unit 720 is used to: use the private key of the device to decrypt the first ciphertext to obtain the semantic key information and the index information of the semantic library; obtain the semantic library based on the index information of the semantic library; based on the semantic library, semantically restore the semantic key information to obtain semantic restoration information; the transceiver unit 710 is also used to: send the semantic restoration information.
[0266] Optionally, the transceiver unit 710 is further used to: send a second capability report, where the second capability report is used to indicate the semantic communication capability of the device.
[0267] Optionally, the second capability report carries identification information of the semantic communication capability type supported by the device and computing power information of the semantic communication type supported by the device.
[0268] Optionally, the transceiver unit 710 is also used to: send a request message to a semantic library storage device, the request message is used to request the semantic library, the request message carries index information of the semantic library; receive encryption information of the semantic library from the semantic library storage device; the processing unit 720 is also used to: determine the semantic library based on the encryption information of the semantic library.
[0269] Optionally, the encrypted information of the semantic library is a ciphertext obtained by encrypting the information of the semantic library using the public key of the second terminal device; the processing unit 720 is specifically used to: decrypt the encrypted information of the semantic library using the private key of the second terminal device to obtain the semantic library.
[0270] Optionally, the index information of the semantic library is obtained by processing the encrypted information of the semantic library using a one-way derivative function, and the encrypted information of the semantic library is obtained by encrypting the information of the semantic library using a public key of the second terminal device.
[0271] Optionally, the device 700 is provided with a trusted execution environment TEE; the processing unit is specifically used to: in the TEE, based on the semantic library, perform semantic restoration on the semantic key information.
[0272] In yet another design, the apparatus 700 may be a first terminal device, or may be a chip in the first terminal device.
[0273] The processing unit 720 is used to create a semantic library of the first terminal device and determine encryption information of the semantic library and index information of the semantic library; the transceiver unit 710 is used to send encryption information of the semantic library and index information of the semantic library.
[0274] Optionally, the transceiver unit 710 is further used to: receive an update request from a second terminal device, the update request being used to request an update of the semantic library; and send an update response in response to the update request, the update response carrying an updated public key.
[0275] Optionally, the transceiver unit 710 is further used to: send an updated private key to a third terminal device.
[0276] It should be understood that the device 700 here is embodied in the form of a functional unit. The term "unit" here may refer to an application specific integrated circuit (ASIC), an electronic circuit, a processor (e.g., a shared processor, a proprietary processor, or a group processor, etc.) and a memory for executing one or more software or firmware programs, a merged logic circuit, and / or other suitable components that support the described functions. In an optional example, those skilled in the art will understand that the device 700 may be specifically the first network device, the second network device, or the first terminal device in the above-mentioned embodiment, and the device 700 may be used to execute the various processes and / or steps corresponding to the first network device, the second network device, or the first terminal device in the above-mentioned method embodiment, and to avoid repetition, it will not be repeated here.
[0277] The device 700 of each of the above schemes has the function of implementing the corresponding steps performed by the first network device, the second network device or the first terminal device in the above method; the function can be implemented by hardware, or by hardware executing the corresponding software implementation. The hardware or software includes one or more modules corresponding to the above functions. For example, the above transceiver unit 710 may include a sending unit and a receiving unit, the sending unit can be used to implement the various steps and / or processes for performing the sending action corresponding to the above transceiver unit, and the receiving unit can be used to implement the various steps and / or processes for performing the receiving action corresponding to the above transceiver unit. The sending unit can be replaced by a transmitter, and the receiving unit can be replaced by a receiver, respectively performing the sending and receiving operations and related processing operations in each method embodiment.
[0278] In the embodiments of the present application, Figure 7 The device 700 in the embodiment may also be a chip or a chip system, such as a system on chip (SoC). Correspondingly, the transceiver unit 710 may be a transceiver circuit of the chip, which is not limited here.
[0279] Figure 8 Another semantic communication device 800 provided by an embodiment of the present application is shown. The device 800 includes a processor 810, a transceiver 820, and a memory 830. The processor 810, the transceiver 820, and the memory 830 communicate with each other through an internal connection path, the memory 830 is used to store instructions, and the processor 810 is used to execute the instructions stored in the memory 830 to control the transceiver 820 to send signals and / or receive signals.
[0280] It should be understood that the device 800 can be specifically the first network device, the second network device or the first terminal device in the above embodiment, and can be used to execute the various steps and / or processes corresponding to the first network device, the second network device or the first terminal device in the above method embodiment. Optionally, the memory 830 may include a read-only memory and a random access memory, and provide instructions and data to the processor. A part of the memory may also include a non-volatile random access memory. For example, the memory may also store information about the device type. The processor 810 may be used to execute instructions stored in the memory, and when the processor 810 executes the instructions stored in the memory, the processor 810 is used to execute the various steps and / or processes of the above method embodiment corresponding to the first network device. The transceiver 820 may include a transmitter and a receiver, the transmitter may be used to implement the various steps and / or processes corresponding to the above transceiver for performing the sending action, and the receiver may be used to implement the various steps and / or processes corresponding to the above transceiver for performing the receiving action.
[0281] It should be understood that in the embodiments of the present application, the processor of the above-mentioned device may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.
[0282] In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in a processor or an instruction in the form of software. The steps of the method disclosed in conjunction with the embodiment of the present application can be directly embodied as a hardware processor for execution, or a combination of hardware and software units in a processor for execution. The software unit can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in a memory, and the processor executes the instructions in the memory, and completes the steps of the above method in conjunction with its hardware. To avoid repetition, it is not described in detail here.
[0283] Those of ordinary skill in the art will appreciate that the various method steps and units described in the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the steps and components of each embodiment have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Those of ordinary skill in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0284] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0285] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units 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. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, or it can be an electrical, mechanical or other form of connection.
[0286] The units described as separate components may or may not be physically separated, and the components displayed 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 embodiments of the present application.
[0287] 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.
[0288] 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 storage medium. Based on this understanding, the technical solution of the present application is essentially 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, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program code.
[0289] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.
Claims
1. A semantic communication method, characterized in that: include: Receiving a semantic communication request from a first terminal device, the semantic communication request being used to request communication with a second terminal device, the semantic communication request carrying information source information of the first terminal device; Based on the semantic library between the first terminal device and the second terminal device, semantic extraction is performed on the source information to obtain semantic key information; A first ciphertext is sent, where the first ciphertext is obtained by encrypting the semantic key information and the index information of the semantic library based on a public key of a second network device, where the second network device is a network device that provides services for the second terminal device.
2. The method according to claim 1, characterized in that The performing semantic extraction on the source information based on the semantic library between the first terminal device and the second terminal device includes: The source information is semantically extracted based on a semantic library between the first terminal device and the second terminal device, and a semantic communication type supported by a first network device providing service for the first terminal device, the second network device, and the second terminal device.
3. The method according to claim 2, characterized in that The method further comprises: Sending a first capability report, where the first capability report is used to indicate a semantic communication capability of the first network device; A third capability report is received, where the third capability report is used to indicate a semantic communication type supported by the first network device, the second network device, and the second terminal device.
4. The method according to claim 2, characterized in that: The method further comprises: receiving a second capability report, where the second capability report is used to indicate a semantic communication capability of the second network device; receiving a capability query report, where the capability query report is used to indicate a semantic communication capability of the second terminal device; Based on the second capability report, the capability query report, and the semantic communication capability of the first network device, determine the semantic communication type supported by the first network device, the second network device, and the second terminal device.
5. The method according to claim 4, characterized in that The capability query report carries identification information of the semantic communication type supported by the second terminal device and computing power information of the semantic communication type supported by the second terminal device.
6. The method according to any one of claims 1 to 5, characterized in that The method further comprises: The semantic library and index information of the semantic library are obtained.
7. The method according to claim 6, characterized in that The acquiring of the semantic library and the index information of the semantic library includes: A semantic library and index information of the semantic library are received from the first terminal device.
8. The method according to any one of claims 1 to 7, characterized in that The index information of the semantic library is obtained by processing the encrypted information of the semantic library using a one-way derivative function, and the encrypted information of the semantic library is obtained by encrypting the information of the semantic library using the public key of the second terminal device.
9. The method according to any one of claims 1 to 8, characterized in that The method is applied to a first network device provided with a trusted execution environment TEE; The semantic extraction of the source information includes: In the TEE of the first network device, semantic extraction is performed on the source information.
10. A semantic communication method, characterized in that: include: receiving a first ciphertext, where the first ciphertext is obtained by encrypting semantic key information and index information of the semantic library based on a public key of a second network device; Decrypting the first ciphertext using the private key of the second network device to obtain the semantic key information and index information of the semantic library; Based on the index information of the semantic library, acquiring the semantic library; Based on the semantic library, semantically restore the semantic key information to obtain semantically restored information; The semantic restoration information is sent.
11. The method according to claim 10, characterized in that The method further comprises: A second capability report is sent, where the second capability report is used to indicate the semantic communication capability of the second network device.
12. The method according to claim 11, characterized in that The second capability report carries identification information of the semantic communication capability type supported by the second network device and computing power information of the semantic communication type supported by the second network device.
13. The method according to any one of claims 10 to 12, characterized in that The acquiring the semantic library based on the index information of the semantic library comprises: Sending a request message to a semantic library storage device, wherein the request message is used to request the semantic library, and the request message carries index information of the semantic library; receiving encrypted information of the semantic library from the semantic library storage device; The semantic library is determined based on the encrypted information of the semantic library.
14. The method according to claim 13, characterized in that The encrypted information of the semantic library is a ciphertext obtained by encrypting the information of the semantic library using the public key of the second terminal device; The step of determining the semantic library based on the encrypted information of the semantic library comprises: The encrypted information of the semantic library is decrypted using the private key of the second terminal device to obtain the semantic library.
15. The method according to any one of claims 10 to 14, characterized in that The index information of the semantic library is obtained by processing the encrypted information of the semantic library using a one-way derivative function, and the encrypted information of the semantic library is obtained by encrypting the information of the semantic library using the public key of the second terminal device.
16. The method according to any one of claims 10 to 15, characterized in that The method is applied to a second network device provided with a trusted execution environment TEE; The performing semantic restoration on the semantic key information based on the semantic library includes: In the TEE of the second network device, the semantic key information is semantically restored based on the semantic library.
17. A semantic communication method, characterized in that: include: Creating a semantic library of the first terminal device, and determining encryption information of the semantic library and index information of the semantic library; The encrypted information of the semantic library and the index information of the semantic library are sent.
18. The method according to claim 17, characterized in that The method further comprises: receiving an update request from a second terminal device, wherein the update request is used to request an update of the semantic library; In response to the update request, an update response is sent, where the update response carries the updated public key.
19. The method according to claim 18, characterized in that The method further comprises: The updated private key is sent to the third terminal device.
20. A semantic communication device, characterized in that: include: A transceiver unit, configured to receive a semantic communication request from a first terminal device, wherein the semantic communication request is used to request communication with a second terminal device, and the semantic communication request carries information about a source of the first terminal device; A processing unit, configured to perform semantic extraction on the source information based on a semantic library between the first terminal device and the second terminal device to obtain semantic key information; The transceiver unit is also used for: A first ciphertext is sent, where the first ciphertext is obtained by encrypting the semantic key information and the index information of the semantic library based on a public key of a second network device, where the second network device is a network device that provides services for the second terminal device.
21. The device according to claim 20, characterized in that The processing unit is specifically used for: Based on the semantic library between the first terminal device and the second terminal device, the device, the second network device and the semantic communication type supported by the second terminal device, the source information is semantically extracted.
22. The device according to claim 21, characterized in that The transceiver unit is also used for: sending a first capability report, the first capability report being used to indicate a semantic communication capability of the device; A third capability report is received, where the third capability report is used to indicate a semantic communication type supported by the apparatus, the second network device, and the second terminal device.
23. The device according to claim 21, characterized in that The transceiver unit is also used for: receiving a second capability report, where the second capability report is used to indicate a semantic communication capability of the second network device; receiving a capability query report, where the capability query report is used to indicate a semantic communication capability of the second terminal device; The processing unit is also used for: Based on the second capability report, the capability query report and the semantic communication capability of the device, determine the semantic communication type supported by the device, the second network device and the second terminal device.
24. The device according to claim 23, characterized in that The capability query report carries identification information of the semantic communication type supported by the second terminal device and computing power information of the semantic communication type supported by the second terminal device.
25. The device according to any one of claims 20 to 24, characterized in that The processing unit is also used for: The semantic library and index information of the semantic library are obtained.
26. The device according to claim 25, characterized in that The transceiver unit is also used for: A semantic library and index information of the semantic library are received from the first terminal device.
27. The device according to any one of claims 20 to 26, characterized in that The index information of the semantic library is obtained by processing the encrypted information of the semantic library using a one-way derivative function, and the encrypted information of the semantic library is obtained by encrypting the information of the semantic library using the public key of the second terminal device.
28. The device according to any one of claims 20 to 27, characterized in that The device is provided with a trusted execution environment TEE; The processing unit is also used for: In the TEE, semantic extraction is performed on the source information.
29. A semantic communication device, characterized in that: include: A transceiver unit, configured to receive a first ciphertext, wherein the first ciphertext is obtained by encrypting semantic key information and index information of the semantic library based on a public key of the device; A processing unit, configured to decrypt the first ciphertext using a private key of the device to obtain the semantic key information and index information of the semantic library; Based on the index information of the semantic library, the semantic library is acquired; based on the semantic library, semantic restoration is performed on the semantic key information to obtain semantic restoration information; The transceiver unit is further used to send the semantic restoration information.
30. The device according to claim 29, characterized in that The transceiver unit is also used for: A second capability report is sent, where the second capability report is used to indicate the semantic communication capability of the device.
31. The device according to claim 30, characterized in that The second capability report carries identification information of the semantic communication capability type supported by the device and computing power information of the semantic communication type supported by the device.
32. The device according to any one of claims 29 to 31, characterized in that The transceiver unit is also used for: Sending a request message to a semantic library storage device, wherein the request message is used to request the semantic library, and the request message carries index information of the semantic library; receiving encrypted information of the semantic library from the semantic library storage device; The processing unit is also used for: The semantic library is determined based on the encrypted information of the semantic library.
33. The device according to claim 32, characterized in that The encrypted information of the semantic library is a ciphertext obtained by encrypting the information of the semantic library using the public key of the second terminal device; The processing unit is specifically used for: The encrypted information of the semantic library is decrypted using the private key of the second terminal device to obtain the semantic library.
34. The device according to any one of claims 29 to 33, characterized in that The index information of the semantic library is obtained by processing the encrypted information of the semantic library using a one-way derivative function, and the encrypted information of the semantic library is obtained by encrypting the information of the semantic library using the public key of the second terminal device.
35. The device according to any one of claims 29 to 34, characterized in that The device is provided with a trusted execution environment TEE; The processing unit is specifically used for: In the TEE, the semantic key information is semantically restored based on the semantic library.
36. A semantic communication device, characterized in that: include: A processing unit, configured to create a semantic library of the first terminal device, and determine encryption information of the semantic library and index information of the semantic library; The transceiver unit is used to send the encryption information of the semantic library and the index information of the semantic library.
37. The device according to claim 36, characterized in that The transceiver unit is also used for: receiving an update request from a second terminal device, wherein the update request is used to request an update of the semantic library; In response to the update request, an update response is sent, where the update response carries the updated public key.
38. The device according to claim 37, characterized in that The transceiver unit is also used for: The updated private key is sent to the third terminal device.
39. A semantic communication device, characterized in that: include: A processor, wherein the processor is coupled to a memory, wherein the memory is used to store a computer program, and when the processor calls the computer program, the device is caused to execute the method according to any one of claims 1 to 19.
40. A computer-readable storage medium, characterized in that Used to store a computer program, the computer program comprising instructions for implementing the method according to any one of claims 1 to 19.
41. A computer program product, comprising instructions, characterized in that: When the instructions are executed on a computer, the computer is caused to implement the method according to any one of claims 1 to 19.
