Semantic communication method and related apparatus

Abstract

Embodiments of the present application propose a semantic communication method and a related apparatus. The method comprises: sending semantic transformation mode information to an intermediate device, the semantic transformation mode information being used for indicating a semantic transformation model and / or a semantic transformation knowledge base used by the intermediate device, and the intermediate device being used for forwarding encoded data of a sending end to a receiving end; sending the semantic transformation mode information to the sending end; and sending the semantic transformation mode information to the receiving end. When the semantic knowledge base or the semantic model is mismatched between the sending end and the receiving end, the semantic communication quality between the sending end and the receiving end is improved by means of semantic transformation of the intermediate device.

Description

A semantic communication method and related device

[0001] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office on December 19, 2023, with application number 202311762490.4 and application name “A semantic communication method and related device”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of communication technology, and in particular to a semantic communication method and related devices. Background Art

[0003] With the evolution of communication technology, a new capability has been proposed in the Sixth Generation (6G) network architecture: semantic communication. Semantic communication is a new architecture that can integrate user needs and information meaning into the communication process, significantly improving transmission efficiency by exploring semantic information. In recent years, artificial intelligence technology has continued to develop, with tremendous progress in algorithms, computing power, and data, enabling the accurate and efficient extraction of semantic information such as images, text, or voice, making semantic communication possible at the engineering level. Compared to traditional communication methods driven by data fidelity, semantic communication extracts semantic information from the source at the semantic level to achieve "meaning preservation", which can significantly reduce the required transmission channel bandwidth.

[0004] The current semantic communication architecture is as follows: After the sender performs semantic extraction on the source data, it combines the sender's local encoding knowledge base (also called the encoded semantic encoding knowledge base) and the encoding model to perform semantic encoding. After receiving the encoded data, the receiver combines the local decoding knowledge base (also called the decoded semantic encoding knowledge base) and the decoding model to perform semantic decoding and semantic recovery to obtain the source data.

[0005] However, currently, due to the mismatch between the encoding knowledge base and / or encoding model at the transmitting end and the decoding knowledge base and / or decoding model at the receiving end, there is a problem of low semantic recovery accuracy. Summary of the Invention

[0006] In the first aspect, an embodiment of the present application proposes a semantic communication method, which is applied to a core network device, and the method includes: sending semantic conversion mode information to an intermediate device, wherein the semantic conversion mode information is used to indicate a semantic conversion model and / or a semantic conversion knowledge base used by the intermediate device, and the intermediate device is used to forward the encoded data of the sending end to the receiving end; sending the semantic conversion mode information to the sending end; and sending the semantic conversion mode information to the receiving end.

[0007] In an embodiment of the present application, a core network device sends semantic conversion mode information to an intermediate device, a transmitter, and a receiver, so that the semantic conversion model and semantic conversion knowledge base used by the intermediate device match the semantic encoding model and semantic encoding knowledge base of the transmitter, and the semantic conversion model and semantic conversion knowledge base used by the intermediate device match the semantic decoding model and semantic decoding knowledge base of the receiver. Therefore, in the event that the semantic knowledge bases or semantic models between the transmitter and the receiver do not match, the semantic conversion performed in the intermediate device improves the quality of semantic communication between the transmitter and the receiver.

[0008] In combination with the first aspect, in a possible implementation of the first aspect, the semantic conversion capability information of the sender is received, the semantic conversion capability information is used to indicate the semantic coding model and / or semantic coding knowledge base supported by the sender; and the semantic conversion mode information is determined based on the semantic conversion capability information of the sender, wherein the semantic conversion model matches the semantic coding model supported by the sender, and the semantic conversion knowledge base matches the semantic coding knowledge base supported by the sender. The sender reports the semantic conversion capability information to the core network device, and the core network device determines the semantic conversion mode information based on the capability information, ensuring that the semantic coding model and / or semantic coding knowledge base indicated by the semantic conversion mode information matches the semantic coding model and / or semantic coding knowledge base supported by the sender, thereby improving the quality of semantic communication between the sender and the receiver.

[0009] In conjunction with the first aspect, in a possible implementation of the first aspect, the method further includes: determining the semantic conversion mode information based on a quality of service requirement for semantic communication between the transmitter and the receiver, where the quality of service requirement for semantic communication includes any one or more of the following: semantic decoding accuracy, semantic similarity, semantic clarity, guaranteed bit rate, packet transmission delay budget, or packet error rate. Determining the semantic conversion mode information based on the quality of service requirement for semantic communication improves the implementation flexibility of the solution.

[0010] In conjunction with the first aspect, in one possible implementation of the first aspect, the semantic conversion model includes: a semantic conversion encoding model and a semantic conversion decoding model; and the semantic conversion knowledge base includes: a semantic conversion encoding knowledge base and a semantic conversion decoding knowledge base. Optionally, the semantic conversion model may also include executing semantic encoding and semantic decoding functions, thereby increasing the implementation flexibility of the solution.

[0011] In conjunction with the first aspect, in a possible implementation of the first aspect, the semantic conversion pattern information includes any one or more of the following information: information about the semantic conversion model, information about the semantic conversion knowledge base, information about the semantic conversion encoding model, information about the semantic conversion encoding knowledge base, information about the semantic conversion decoding model, or information about the semantic conversion decoding knowledge base. This information includes, but is not limited to, identification information, an index, or complete model information or complete knowledge base information.

[0012] In combination with the first aspect, in a possible implementation of the first aspect, the semantic conversion capability information includes any one or more of the following: type information of the semantic coding model, size of the semantic coding model, identification information of the semantic coding model, type information of the semantic coding knowledge base, size of the semantic coding knowledge base, or identification information of the semantic coding knowledge base. The sending end may report to the core network device the relevant information of the semantic coding model supported by the sending end and / or the relevant information of the semantic coding knowledge base supported by the sending end. So that the core network device can determine the corresponding semantic conversion capability information based on the semantic conversion capability information.

[0013] In a second aspect, an embodiment of the present application proposes a semantic communication method, which is applied to an intermediate device, and the method includes: receiving semantic conversion mode information sent by a core network device, wherein the semantic conversion mode information is used to indicate a semantic conversion model and / or a semantic conversion knowledge base used by the intermediate device; determining the semantic conversion model and / or the semantic conversion knowledge base based on the semantic conversion mode information; receiving first encoded data sent by a sending end, wherein the first encoded data is data encoded by the sending end using a semantic encoding model and / or a semantic encoding knowledge base; processing the first encoded data using the semantic conversion model and the semantic conversion knowledge base to obtain second encoded data; and sending the second encoded data to the receiving end.

[0014] In this embodiment of the present application, the intermediate device determines the semantic conversion model and / or semantic conversion knowledge base used to perform the semantic conversion based on the semantic conversion mode information sent by the core network device, thereby ensuring that the second encoded data sent to the receiving end can be successfully decoded by the receiving end. This improves the quality of semantic communication between the sending end and the receiving end.

[0015] In conjunction with the second aspect, in one possible implementation of the second aspect, the semantic conversion model includes: a semantic conversion encoding model and a semantic conversion decoding model; and the semantic conversion knowledge base includes: a semantic conversion encoding knowledge base and a semantic conversion decoding knowledge base. Optionally, the semantic conversion model may also include executing semantic encoding and semantic decoding functions, thereby increasing the implementation flexibility of the solution.

[0016] In conjunction with the second aspect, in a possible implementation of the second aspect, the semantic conversion pattern information includes any one or more of the following information: information about the semantic conversion model, information about the semantic conversion knowledge base, information about the semantic conversion encoding model, information about the semantic conversion encoding knowledge base, information about the semantic conversion decoding model, or information about the semantic conversion decoding knowledge base. This information includes, but is not limited to, identification information, an index, or complete model information or complete knowledge base information.

[0017] In combination with the second aspect, in a possible implementation of the second aspect, the semantic conversion model and the semantic conversion knowledge base are used to process the first coded data to obtain the second coded data, including: using the semantic conversion decoding model and the semantic conversion decoding knowledge base to decode the first coded data to generate intermediate data; using the semantic conversion encoding model and the semantic conversion encoding knowledge base to encode the intermediate data to generate the second coded data. Specifically, the intermediate device performs semantic conversion processing on the first coded data according to the semantic conversion model and the semantic conversion knowledge base to obtain the second coded data. Specifically, the semantic conversion processing includes: first, semantically decoding and semantically restoring the first coded data according to the semantic conversion model and the semantic conversion knowledge base to generate intermediate data, and then semantically extracting and semantically encoding the intermediate data according to the semantic conversion model and the semantic conversion knowledge base to obtain the second coded data.

[0018] In combination with the second aspect, in a possible implementation of the second aspect, the intermediate device includes a first intermediate device and a second intermediate device, wherein the first intermediate device provides services for the sending end, and the second intermediate device provides services for the receiving end, and uses the semantic conversion model and the semantic conversion knowledge base to process the first encoded data to obtain the second encoded data, including: the first intermediate device uses the semantic conversion decoding model and the semantic conversion decoding knowledge base to decode the first encoded data to generate intermediate data; the first intermediate device sends the intermediate data to the second intermediate device; the second intermediate device uses the semantic conversion encoding model and the semantic conversion encoding knowledge base to encode the intermediate data to generate the second encoded data; and sending the second encoded data to the receiving end includes: the second intermediate device sends the second encoded data to the receiving end.

[0019] The first intermediate device performs semantic decoding and semantic recovery on the first coded data based on the semantic transformation decoding model and the semantic transformation decoding knowledge base to generate intermediate data. The first intermediate device then sends the intermediate data to the second intermediate device, which performs semantic extraction and semantic encoding on the intermediate data based on the semantic transformation encoding model and the semantic transformation encoding knowledge base to obtain second coded data.

[0020] In a third aspect, an embodiment of the present application provides a semantic communication method, which is applied to a sending end and includes:

[0021] Receiving semantic conversion mode information sent by a core network device, where the semantic conversion mode information is used to indicate a semantic conversion model and / or a semantic conversion knowledge base used by an intermediate device, where the intermediate device is used to forward the encoded data from the sending end to the receiving end;

[0022] Determining a semantic encoding model and / or a semantic encoding knowledge base according to the semantic conversion mode information, wherein the semantic encoding model matches the semantic conversion model, and the semantic encoding knowledge base matches the semantic conversion knowledge base;

[0023] Using the semantic encoding knowledge base and the semantic encoding knowledge base to encode the source data to generate first encoded data;

[0024] The first encoded data is sent to the intermediate device.

[0025] In an embodiment of the present application, the sending end determines a semantic coding model and / or a semantic coding knowledge base that matches the semantic conversion model and / or the semantic conversion knowledge base that performs semantic conversion on the intermediate device based on the semantic conversion mode information sent by the core network device. Then, the sending end encodes the source data according to the semantic coding model and the semantic coding knowledge base to generate first encoded data. Ensure that the second encoded data generated by the intermediate device based on the first encoded data can be successfully decoded by the receiving end. Improve the quality of semantic communication between the sending end and the receiving end.

[0026] In combination with the third aspect, in a possible implementation of the third aspect, the method further includes: sending semantic conversion capability information to the core network device, where the semantic conversion capability information is used to indicate the semantic coding model and / or semantic coding knowledge base supported by the sender. The sender can report relevant information of the semantic coding model supported by the sender and / or relevant information of the semantic coding knowledge base supported by the sender to the core network device. This allows the core network device to determine corresponding semantic conversion capability information based on the semantic conversion capability information.

[0027] In combination with the third aspect, in a possible implementation of the third aspect, the semantic conversion capability information includes any one or more of the following: type information of the semantic coding model, size of the semantic coding model, identification information of the semantic coding model, type information of the semantic coding knowledge base, size of the semantic coding knowledge base, or identification information of the semantic coding knowledge base.

[0028] In a fourth aspect, an embodiment of the present application provides a semantic communication method, which is applied to a receiving end and includes:

[0029] Receiving semantic conversion mode information sent by a core network device, where the semantic conversion mode information is used to indicate a semantic conversion model and / or a semantic conversion knowledge base used by an intermediate device, where the intermediate device is used to forward the encoded data of the sending end to the receiving end;

[0030] Determining a semantic decoding model and / or a semantic decoding knowledge base according to the semantic conversion mode information, wherein the semantic decoding model matches the semantic conversion model, and the semantic decoding knowledge base matches the semantic conversion knowledge base;

[0031] receiving second encoded data sent by the intermediate device;

[0032] The second encoded data is decoded using the semantic decoding knowledge base and the semantic decoding knowledge base to generate target data.

[0033] In an embodiment of the present application, the receiving end determines a semantic decoding model and / or a semantic decoding knowledge base that matches the semantic conversion model and / or the semantic conversion knowledge base that performs semantic conversion on the intermediate device based on the semantic conversion mode information sent by the core network device. Then, the receiving end decodes the second encoded data according to the semantic decoding model and the semantic decoding knowledge base to generate target data. Since the semantic decoding model and / or the semantic decoding knowledge base used by the receiving end is indicated by the intermediate device, it can be ensured that the receiving end successfully decodes the second encoded data. The quality of semantic communication between the sending end and the receiving end is improved.

[0034] In combination with the fourth aspect, in a possible implementation of the fourth aspect, the semantic conversion pattern information includes any one or more of the following information: information about the semantic conversion model, information about the semantic conversion knowledge base, information about the semantic conversion encoding model, information about the semantic conversion encoding knowledge base, information about the semantic conversion decoding model, or information about the semantic conversion decoding knowledge base.

[0035] In a fifth aspect, an embodiment of the present application provides a communication device, which is applied to a core network device, and includes:

[0036] a transceiver module, configured to send semantic conversion mode information to an intermediate device, wherein the semantic conversion mode information is used to indicate a semantic conversion model and / or a semantic conversion knowledge base used by the intermediate device, and the intermediate device is used to forward the encoded data from the sending end to the receiving end;

[0037] The transceiver module is further configured to send the semantic conversion mode information to the sending end;

[0038] The transceiver module is further configured to send the semantic conversion mode information to the receiving end.

[0039] In one possible implementation,

[0040] The transceiver module is further configured to receive semantic conversion capability information of the sender, where the semantic conversion capability information is used to indicate a semantic coding model and / or a semantic coding knowledge base supported by the sender;

[0041] A processing module is used to determine the semantic conversion mode information based on the semantic conversion capability information of the sending end, wherein the semantic conversion model matches the semantic encoding model supported by the sending end, and the semantic conversion knowledge base matches the semantic encoding knowledge base supported by the sending end.

[0042] In one possible implementation,

[0043] The processing module is also used to determine the semantic conversion mode information based on the service quality requirements of the semantic communication between the sending end and the receiving end, and the service quality requirements of the semantic communication include any one or more of the following: semantic decoding accuracy, semantic similarity, semantic clarity, guaranteed bit rate, packet transmission delay budget, or packet error rate.

[0044] In a possible implementation, the semantic conversion model includes: a semantic conversion encoding model and a semantic conversion decoding model, and the semantic conversion knowledge base includes: a semantic conversion encoding knowledge base and a semantic conversion decoding knowledge base.

[0045] In one possible implementation, the semantic conversion pattern information includes any one or more of the following information: information about the semantic conversion model, information about the semantic conversion knowledge base, information about the semantic conversion encoding model, information about the semantic conversion encoding knowledge base, information about the semantic conversion decoding model, or information about the semantic conversion decoding knowledge base.

[0046] In one possible implementation, the semantic conversion capability information includes any one or more of the following: type information of the semantic coding model, size of the semantic coding model, identification information of the semantic coding model, type information of the semantic coding knowledge base, size of the semantic coding knowledge base, or identification information of the semantic coding knowledge base.

[0047] In a sixth aspect, an embodiment of the present application provides a communication device, which is applied to an intermediate device, and includes:

[0048] The transceiver module is further configured to receive semantic conversion mode information sent by a core network device, wherein the semantic conversion mode information is used to indicate a semantic conversion model and / or a semantic conversion knowledge base used by the intermediate device;

[0049] The processing module is further configured to determine the semantic conversion model and / or the semantic conversion knowledge base according to the semantic conversion mode information;

[0050] The transceiver module is further configured to receive first coded data sent by a sending end, where the first coded data is data encoded by the sending end using a semantic coding model and / or a semantic coding knowledge base;

[0051] The processing module is further configured to process the first coded data using the semantic conversion model and the semantic conversion knowledge base to obtain second coded data;

[0052] The transceiver module is further configured to send the second coded data to a receiving end.

[0053] In a possible implementation, the semantic conversion model includes: a semantic conversion encoding model and a semantic conversion decoding model, and the semantic conversion knowledge base includes: a semantic conversion encoding knowledge base and a semantic conversion decoding knowledge base.

[0054] In one possible implementation, the semantic conversion pattern information includes any one or more of the following information: information about the semantic conversion model, information about the semantic conversion knowledge base, information about the semantic conversion encoding model, information about the semantic conversion encoding knowledge base, information about the semantic conversion decoding model, or information about the semantic conversion decoding knowledge base.

[0055] In one possible implementation,

[0056] The processing module is further configured to decode the first encoded data using the semantic conversion decoding model and the semantic conversion decoding knowledge base to generate intermediate data;

[0057] The processing module is further configured to perform encoding processing on the intermediate data using the semantic conversion encoding model and the semantic conversion encoding knowledge base to generate the second encoded data.

[0058] In a possible implementation, the intermediate device includes a first intermediate device and a second intermediate device, wherein the first intermediate device provides services for the sending end, and the second intermediate device provides services for the receiving end.

[0059] The processing module is further configured to decode the first encoded data using the semantic conversion decoding model and the semantic conversion decoding knowledge base to generate intermediate data;

[0060] The transceiver module is further configured to send the intermediate data to the second intermediate device;

[0061] The processing module is further configured to perform encoding processing on the intermediate data using the semantic conversion encoding model and the semantic conversion encoding knowledge base to generate the second encoded data;

[0062] The transceiver module is further configured to send the second coded data to the receiving end.

[0063] In a seventh aspect, an embodiment of the present application provides a semantic communication method, wherein the communication device is applied to a sending end, and the communication device includes:

[0064] The transceiver module is further configured to receive semantic conversion mode information sent by a core network device, wherein the semantic conversion mode information is used to indicate a semantic conversion model and / or a semantic conversion knowledge base used by an intermediate device, and the intermediate device is configured to forward the encoded data of the sending end to the receiving end;

[0065] The processing module is further configured to determine a semantic encoding model and / or a semantic encoding knowledge base based on the semantic conversion mode information, wherein the semantic encoding model matches the semantic conversion model, and the semantic encoding knowledge base matches the semantic conversion knowledge base;

[0066] The processing module is further configured to perform encoding processing on the source data using the semantic encoding knowledge base and the semantic encoding knowledge base to generate first encoded data;

[0067] The transceiver module is further configured to send the first coded data to the intermediate device.

[0068] In one possible implementation,

[0069] The transceiver module is further used to send semantic conversion capability information to the core network device, where the semantic conversion capability information is used to indicate the semantic coding model and / or semantic coding knowledge base supported by the sending end.

[0070] In one possible implementation, the semantic conversion capability information includes any one or more of the following: type information of the semantic coding model, size of the semantic coding model, identification information of the semantic coding model, type information of the semantic coding knowledge base, size of the semantic coding knowledge base, or identification information of the semantic coding knowledge base.

[0071] In an eighth aspect, an embodiment of the present application provides a semantic communication method, wherein the communication device is applied to a receiving end, and the communication device includes:

[0072] The transceiver module is further configured to receive semantic conversion mode information sent by a core network device, wherein the semantic conversion mode information is used to indicate a semantic conversion model and / or a semantic conversion knowledge base used by an intermediate device, and the intermediate device is used to forward the encoded data of the sending end to the receiving end;

[0073] The processing module is further configured to determine a semantic decoding model and / or a semantic decoding knowledge base based on the semantic conversion mode information, wherein the semantic decoding model matches the semantic conversion model, and the semantic decoding knowledge base matches the semantic conversion knowledge base;

[0074] The transceiver module is further configured to receive second coded data sent by the intermediate device;

[0075] The processing module is further configured to use the semantic decoding knowledge base and the semantic decoding knowledge base to perform decoding processing on the second encoded data to generate target data.

[0076] In a possible implementation, the semantic conversion mode information includes any one or more of the following information:

[0077] The information of the semantic conversion model, the information of the semantic conversion knowledge base, the information of the semantic conversion encoding model, the information of the semantic conversion encoding knowledge base, the information of the semantic conversion decoding model, or the information of the semantic conversion decoding knowledge base.

[0078] In a ninth aspect of the present application, a communication device is provided, which can implement the method in the first aspect or any possible implementation of the first aspect. The device includes corresponding units or modules for executing the above method. The units or modules included in the device can be implemented by software and / or hardware. For example, the device can be a core network device, or the device can be a component in the core network device (such as a processor, chip or chip system, etc.), or the device can also be a logical module or software that can implement all or part of the core network device. Among them, the communication device includes a transceiver module and a processing module. For example, the communication device is a server with a core network device.

[0079] The tenth aspect of the present application provides a communication device, which can implement the method in the above-mentioned second aspect or any possible implementation of the second aspect. The device includes corresponding units or modules for executing the above-mentioned method. The units or modules included in the device can be implemented by software and / or hardware. For example, the device can be an intermediate device, or the device can be a component in the intermediate device (such as a processor, chip or chip system, etc.), or the device can also be a logic module or software that can implement all or part of the intermediate device. Among them, the communication device includes a transceiver module and a processing module.

[0080] In an eleventh aspect of the present application, a communication device is provided, which can implement the method in the third aspect or any possible implementation of the third aspect. The device includes corresponding units or modules for executing the above method. The units or modules included in the device can be implemented by software and / or hardware. For example, the device can be a transmitting end, or the device can be a component in the transmitting end (such as a processor, chip or chip system, etc.), or the device can also be a logic module or software that can implement all or part of the transmitting end. Among them, the communication device includes a transceiver module and a processing module.

[0081] The twelfth aspect of the present application provides a communication device, which can implement the method in the fourth aspect or any possible implementation of the fourth aspect. The device includes corresponding units or modules for executing the above method. The units or modules included in the device can be implemented by software and / or hardware. For example, the device can be a receiving end, or the device can be a component in the receiving end (such as a processor, chip or chip system, etc.), or the device can also be a logic module or software that can implement all or part of the receiving end. Among them, the communication device includes a transceiver module and a processing module.

[0082] A thirteenth aspect of an embodiment of the present application provides a communication device, comprising at least one processor, which is coupled to a memory; the memory is used to store programs or instructions; the at least one processor is used to execute the program or instructions so that the device implements any possible implementation method of the first to fourth aspects mentioned above.

[0083] A fourteenth aspect of an embodiment of the present application provides a communication device, comprising a communication interface for inputting and / or outputting signaling or data; and a processor for executing a computer-executable program so that the device implements any possible implementation method of the first to fourth aspects mentioned above.

[0084] A fifteenth aspect of an embodiment of the present application provides a communication device, comprising at least one logic circuit and an input / output interface; the input / output interface is used to input or output information; the logic circuit is used to execute the method as any possible implementation method in the first to fourth aspects mentioned above.

[0085] A sixteenth aspect of an embodiment of the present application provides a computer program product (or computer program). When the computer program product is executed by the processor, the processor executes the above-mentioned first to fourth aspects, and any possible implementation method.

[0086] A seventeenth aspect of an embodiment of the present application provides a chip system, which includes at least one processor for supporting a communication device to implement the above-mentioned first to fourth aspects, and any possible implementation method.

[0087] In one possible design, the chip system may further include a memory for storing program instructions and data necessary for the communication device. The chip system may be composed of a chip or may include a chip and other discrete components. Optionally, the chip system may further include an interface circuit for providing program instructions and / or data to the at least one processor.

[0088] An eighteenth aspect of an embodiment of the present application provides a communication system, which includes the communication device of the fifth aspect, the communication device of the sixth aspect, the communication device of the seventh aspect and / or the communication device of the eighth aspect.

[0089] Among them, the technical effects brought about by any design method in the fifth to eighteenth aspects can be referred to the technical effects brought about by the different implementation methods in the above-mentioned first to fourth aspects, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0090] FIG1 is a schematic diagram of a communication system according to an embodiment of the present application;

[0091] Figure 2 is a schematic diagram of semantic communication;

[0092] FIG3 is a schematic diagram of a semantic communication scenario;

[0093] FIG4 is a schematic diagram of a communication scenario involved in an embodiment of the present application;

[0094] FIG5 is a schematic diagram of an embodiment of a semantic communication method proposed in an embodiment of the present application;

[0095] FIG6 is a schematic diagram of a network protocol stack architecture according to an embodiment of the present application;

[0096] FIG7 is a schematic diagram of an embodiment of a semantic communication method proposed in an embodiment of the present application;

[0097] FIG8 is a schematic diagram of an embodiment of a semantic communication method proposed in an embodiment of the present application;

[0098] FIG9 is a schematic diagram of an embodiment of a semantic communication method proposed in an embodiment of the present application;

[0099] FIG10 is a schematic diagram of an embodiment of a semantic communication method proposed in an embodiment of the present application;

[0100] FIG11 is a schematic diagram of a communication device provided by the present application;

[0101] FIG12 is another schematic diagram of a communication device provided by the present application;

[0102] FIG13 is another schematic diagram of the communication device provided by the present application;

[0103] FIG14 is another schematic diagram of the communication device provided in this application. DETAILED DESCRIPTION

[0104] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all of the embodiments. The terms "first", "second" and corresponding terminology labels in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the terms used in this way are interchangeable where appropriate, and this is merely a way of distinguishing objects of the same properties when describing the embodiments of the present application. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, so that a process, method, system, product or device that includes a series of units is not necessarily limited to those units, but may include other units that are not clearly listed or inherent to these processes, methods, products or devices.

[0105] In the description of this application, unless otherwise specified, " / " means or, for example, A / B can mean A or B; "and / or" in this application is merely a description of the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of this application, "at least one" refers to one or more items, and "multiple items" refers to two or more items. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0106] 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), world-wide interoperability for microwave access (WiMAX) communication system, fifth generation (5G) system, new generation (NR) communication system or future sixth generation communication system, etc.

[0107] The part of various communication systems operated by operators can be called an operator network. The operator network can also be called a public land mobile network (PLMN) network, which is a network established and operated by the government or an operator approved by the government for the purpose of providing land mobile communication services to the public. It is mainly a public network in which mobile network operators (MNOs) provide mobile broadband access services to users. The operator network or PLMN network described in the embodiments of the present application can be a network that meets the requirements of the third generation partnership project (3GPP) standards, referred to as a 3GPP network. Usually, 3GPP networks are operated by operators, including but not limited to fifth-generation (5G) mobile communication networks, fourth-generation (4G) mobile communication networks or third-generation (3G) mobile communication technology networks. It also includes the future sixth-generation (6G) mobile communication network.

[0108] Please refer to Figure 1, which is a schematic diagram of a communication system in an embodiment of the present application. As shown in Figure 1, the communication system includes an access and mobility management function (AMF), a session management function (SMF), a unified data management (UDM), a radio access network (RAN), a policy control function (PCF), terminal equipment, a user plane function (UPF), a network exposure function (NEF), an application function (AF), and a data network (DN), etc.

[0109] The following is a brief introduction to each network function (or network element) shown in FIG1 .

[0110] Terminal equipment: can be called user equipment (UE), access terminal, subscriber unit, subscriber station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent or user device.

[0111] The terminal device can be a device that provides voice / data to users, for example, a handheld device or vehicle-mounted device with a wireless connection function. At present, some examples of terminals include: mobile phones, tablet computers, laptop computers, PDAs, mobile internet devices (MIDs), wearable devices, virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals in industrial control, wireless terminals in self-driving, wireless terminals in remote medical surgery, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, wireless terminals in smart homes, cellular phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), handheld devices with wireless communication capabilities, computing devices or other processing devices connected to wireless modems, wearable devices, terminal devices in 5G networks or terminal devices in future evolved public land mobile communication networks, etc. The embodiments of the present application are not limited to this.

[0112] As an example and not a limitation, in the embodiment of the present application, the terminal device may also be a wearable device. Wearable devices may also be called wearable smart devices, which are a general term for wearable devices that are intelligently designed and developed using wearable technology for daily wear, such as glasses, gloves, watches, clothing, and shoes. A wearable device is a portable device that is worn directly on the body or integrated into the user's clothes or accessories. Wearable devices are not only hardware devices, but also achieve powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include those that are fully functional, large in size, and can achieve complete or partial functions without relying on smartphones, such as smart watches or smart glasses, as well as those that only focus on a certain type of application function and need to be used in conjunction with other devices such as smartphones, such as various smart bracelets and smart jewelry for vital sign monitoring.

[0113] In addition, in the embodiment of the present application, the terminal device can also be a terminal device in the Internet of Things (IoT) system. IoT is an important part of the future development of information technology. Its main technical feature is to connect objects to the network through communication technology, thereby realizing an intelligent network of human-machine interconnection and object-to-object interconnection.

[0114] It should be noted that the terminal device and the access network device can communicate with each other using a certain air interface technology (such as NR or LTE technology). The terminal devices can also communicate with each other using a certain air interface technology (such as NR or LTE technology).

[0115] In the embodiments of the present application, the terminal device may be replaced by a device for implementing the functions of the terminal device, or a device capable of supporting the terminal device to implement the functions, such as a chip system or chip, which may be installed in the terminal device. In addition, the chip system may be composed of a chip or may include a chip and other discrete devices.

[0116] An access network device (also known as a wireless access network) may be a device with wireless transceiver functions. The access network device may be a device that provides wireless communication function services, usually located on the network side, including but not limited to: a next-generation base station (gNodeB, gNB) in a fifth-generation communication system, a next-generation base station in a sixth-generation (mobile communication system), a base station in a future mobile communication system or an access node in a WiFi system, etc., an evolved node B (eNB) in an LTE system, a radio network controller (RNC), a node B (NB), a base station controller (BSC), a home base station (e.g., home evolved NodeB, or home Node B, HNB), a wireless access point, a base band unit (BBU), a transmission reception point (TRP), a transmitting point (TP), a base transceiver station (BTS), etc. In a network structure, the access network device may include a centralized unit (CU) node, or a distributed unit (CU) node. The access network device provides services for a cell. The user equipment communicates with the base station through the transmission resources used by the cell (for example, frequency domain resources, or spectrum resources). The cell can be a cell corresponding to a base station (for example, a base station). The cell can belong to a macro base station or a base station corresponding to a small cell. The small cells here can include: metro cells, micro cells, pico cells, femto cells, etc. These small cells have the characteristics of small coverage and low transmission power and are suitable for providing high-speed data transmission services. The access network device can be a macro base station, a micro base station or an indoor station (or a relay node or donor node), a device that provides wireless communication services to user equipment in a V2X communication system, a wireless controller in a cloud radio access network (CRAN) scenario, a relay station, a vehicle-mounted device, a wearable device, and a network device in a future evolution network.The access network device may also be wireless access equipment such as Integrated Access and Backhaul (IAB) and Network-controlled Repeater (NCR).

[0117] The embodiments of the present application do not limit the specific technology and specific device form adopted by the access network device.

[0118] The unified data management network element (also known as the unified data management network element, unified data management network element entity, data management device, or unified data management network element device) is a core network device that primarily processes terminal device identification, access authentication, registration, and mobility management. The unified data management is a control plane device.

[0119] Policy control function (also known as policy control network element, policy control function network element, policy control equipment, policy control function network element entity, etc.): mainly responsible for billing at the session and service flow level, service quality bandwidth guarantee and mobility management, terminal device policy decision-making and other policy control function network elements.

[0120] Session management function (also called session management function network element): mainly performs session management, execution of control policies issued by PCF, selection of UPF, allocation of Internet Protocol addresses for terminal devices, etc.

[0121] The access and mobility management function (also known as access and mobility management function entity, access and mobility management device, access and mobility management function network element, access management device, mobility management device) is a type of core network equipment, mainly used for mobility management and access management, etc. It can be used to implement other functions of the mobility management entity (MME) in addition to session management, such as lawful interception, or access authorization (or authentication), user equipment registration, mobility management, tracking area update process, reachability detection, selection of session management function network element, mobile state transition management, etc.

[0122] User plane functions (also known as user plane equipment, user plane functional network element, user plane functional network element, user plane functional entity): mainly include the following functions: data packet routing and transmission, packet detection, service usage reporting, QoS processing, uplink packet detection, downlink data packet storage and other user plane related functions.

[0123] The application function (AF) is similar to an application server, interacting with other 5G core network control planes (NFs) to provide business services. AFs can exist for different application services and can be owned by operators or trusted third parties. For example, this network element's primary function is to communicate the PCF with the latest third-party enterprise business requirements for a particular application. Based on these requirements, the PCF generates corresponding quality of service (QoS) rules to ensure that the services provided by the network meet the third-party's requirements.

[0124] It should be noted that the application server in the embodiment of the present application includes an application function (AF) and / or an application server (AS) or other devices (or functions or network elements, etc.) that can support or provide application services (or business services), and the embodiment of the present application is not limited to this. For example, the application server can be a mobile edge computing (MEC) node or base station.

[0125] Network Exposure Function (NEF) can also be referred to as network exposure equipment, network exposure functional entity, network exposure function network element, network capability exposure functional entity, network capability exposure functional equipment, network capability exposure function network element, or network capability exposure equipment. NEF is primarily used to support the exposure of capabilities and events, such as securely exposing services and capabilities provided by 3GPP network functions to the outside world.

[0126] It should be understood that the RAN, SMF, PCF or AF in the embodiments of the present application may also be referred to as a communication device or communication equipment, which may be a general device or a dedicated device, and the present application does not make any specific limitations on this.

[0127] It should also be understood that the above naming is only used to distinguish different functions, and does not mean that these devices are independent physical devices. This application does not limit the specific form of the above devices. For example, they can be integrated into the same physical device, or they can be different physical devices. In actual deployment, network functions (or simply referred to as functions), network elements or devices can be combined. For example, the access and mobility management function network element can be combined with the session management function network element; the session management function network element can be combined with the user plane function network element. When two functions are combined, the interaction between the two functions provided in the embodiment of the present application becomes the internal operation of the combined function or can be omitted.

[0128] It is understandable that the above functions can be network elements in hardware devices, software functions running on dedicated hardware, or a combination of hardware and software, or virtualized functions instantiated on a platform (e.g., a cloud platform).

[0129] It should be noted that the naming of each device in Figure 1 (such as AF, SMF, PCF, AMF, etc.) is only a name, and the name does not limit the function of the device itself. In 5G networks and other future networks, the above-mentioned devices may also have other names, and this application does not specifically limit this. For example, in a 6G network, some or all of the above-mentioned network elements may use the terminology in 5G, or may be other names, etc., which are uniformly explained here and will not be repeated below.

[0130] It should be noted that the exemplary examples mentioned in this application do not represent the optimal ones; the first, second, etc. mentioned in this application are only used to distinguish different information, messages or other objects, and do not represent a sequential relationship; in addition, the various embodiments in this application can refer to and learn from each other, and the same or similar steps or nouns will not be repeated one by one.

[0131] In the embodiment of the present application, the direction from the terminal device to the application server (or the user plane functional network element) is called the uplink direction, and correspondingly, the direction from the application server (or the user plane functional network element) to the terminal device is called the downlink direction.

[0132] The following describes the technical concepts related to the embodiments of this application:

[0133] 1. Semantic communication.

[0134] Compared to traditional communication methods driven by data fidelity, semantic communication extracts semantic information from the source to achieve "meaning preservation," significantly reducing the required transmission channel bandwidth. For easier understanding, please refer to Figure 2, which shows a schematic diagram of semantic communication. On the transmitter side, the original source information generated by the source is first fed into the semantic extraction module, which generates a semantic representation sequence based on the original source information. Next, the semantic representation sequence is fed into the semantic source encoder, which compresses and encodes the semantic feature sequence. The compressed semantic feature sequence is then fed into the channel encoder, which performs channel coding on the semantic feature sequence. Finally, the transmitter transmits the channel-coded semantic feature sequence onto the transmission channel. On the receiver side, the received data (i.e., the channel-coded semantic feature sequence) is first channel-decoded (decoding can also be replaced by decoding), followed by semantic decoding to obtain a semantic representation sequence. The semantic representation sequence is then fed into the semantic recovery and reconstruction module, ultimately recovering the source data. In semantic communication, performance is typically evaluated using task completion quality or semantic accuracy. Compared to traditional communication, semantic communication requires a knowledge base for both the transmitter and receiver. This base contains raw data samples and their corresponding semantic labels. The semantic encoding and decoding modules utilize this massive data base and train deep learning networks on it to fit semantic features, effectively extracting and reconstructing semantic information.

[0135] For example, a possible semantic communication scenario is shown in Figure 3, which is a schematic diagram of a semantic communication scenario. A semantic communication function is deployed on the UE and network side, supporting operations such as semantic extraction, semantic encoding, semantic decoding, and semantic recovery based on a knowledge base (also known as a semantic knowledge base).

[0136] Semantic communication requires that the knowledge bases of the sender and receiver match each other in order to achieve high accuracy of semantic recovery. For different types of applications (such as text, pictures, or audio and video, etc.), different application scenarios (industrial manufacturing or personal entertainment, etc.), or different preferences of the sender and receiver, the knowledge bases required for semantic communication between the sender and receiver are also different. Limited by the size of the knowledge base, it requires a large communication overhead for the sender and receiver to obtain each other's knowledge base. In addition, the sender and receiver often obtain each other's knowledge base. There are privacy issues. Since the encoding knowledge base and / or encoding model of the sender may not match the decoding knowledge base and / or decoding model of the receiver, there is a problem of low semantic recovery accuracy.

[0137] Based on this, an embodiment of the present application proposes a semantic communication method, in which a core network device sends semantic conversion mode information to an intermediate device, the semantic conversion mode information is used to indicate the semantic conversion model and / or semantic conversion knowledge base used by the intermediate device, and the intermediate device is used to forward the encoded data of the sender to the receiver; the core network device sends the semantic conversion mode information to the sender; and the core network device sends the semantic conversion mode information to the receiver. The core network device sends the semantic conversion mode information to the intermediate device, the sender, and the receiver, so that the semantic conversion model and semantic conversion knowledge base used by the intermediate device match the semantic encoding model and semantic encoding knowledge base of the sender, and the semantic conversion model and semantic conversion knowledge base used by the intermediate device match the semantic decoding model and semantic decoding knowledge base of the receiver. In the case where the semantic knowledge base or semantic model between the sender and the receiver does not match, the semantic conversion in the intermediate device improves the semantic recovery accuracy and improves the semantic communication quality between the sender and the receiver.

[0138] Next, the embodiments of the present application are introduced in conjunction with the accompanying drawings. First, the communication scenarios involved in the embodiments of the present application are introduced. Please refer to Figure 4, which is a schematic diagram of the communication scenarios involved in the embodiments of the present application. The communication scenarios involved in the embodiments of the present application include: 1. Peer-to-peer (P2P) mode communication scenario, that is, semantic communication is carried out between UE and UE, and the sending UE and the receiving UE can transmit data through the radio access network (Radio Access Network, RAN), the core network (Core Network, CN) and the data network (Data network, DN); 2. Client-server (CS) mode communication scenario, that is, semantic communication is carried out between UE and application server (or cloud server), UE and cloud server can act as receiving end or sending end to each other, and transmit data through RAN and CN.

[0139] The intermediate devices in the embodiments of the present application include: user plane devices or access network devices. In other words, the devices performing semantic transformation processing can be terminal devices and user plane devices, or terminal devices and access network devices. For ease of understanding, please refer to Figure 6, which is a schematic diagram of a network protocol stack architecture in the embodiments of the present application. In the embodiments of the present application, the protocol layer performing semantic transformation processing is referred to as the semantic transformation protocol layer (STL). Adding a semantic transformation protocol layer on the core network side can be done by integrating the semantic transformation protocol layer into the existing core network protocol layer, adding an independent semantic transformation protocol layer on top of the existing core network protocol layer, or adding an independent semantic transformation function (STF) on the existing core network side, which executes the STL layer protocol. In one example, the STL layer can be integrated into the protocol data unit (PDU) protocol function of the UPF. In another example, the STL layer is added below the PDU layer of the UPF. Uu is an interface between a UE and a base station in a 3GPP system, and TN L2&L1 are Layer 2 (L2) and Layer 1 (L1) protocols of a transport network (TN).

[0140] Adding a semantic transformation protocol layer to the access network can involve integrating the semantic transformation protocol layer into the existing access network protocol layer, adding an independent semantic transformation protocol layer on top of the existing access network protocol layer, or adding an independent semantic transformation function (STF) on the existing access network side. This STF function executes the STL layer protocol. In one example, the STF layer can be integrated into the Service Data Adaptation Protocol (SDAP) protocol function of the base station (gNB), or the STL layer can be added on top of the SDAP layer.

[0141] In one possible implementation, the semantic conversion protocol layer (or semantic conversion function) has the ability to perform semantic encoding and decoding across semantic knowledge bases, and the semantic conversion protocol layer (or semantic conversion function) can perform semantic conversion on the information of the sending end. The semantic conversion protocol layer (or semantic conversion function) on the sending end side semantically converts the information that has been semantically extracted and semantically encoded on the sending end side to obtain encoded information. The encoded information is information that matches the semantic decoding model and semantic decoding knowledge base of the semantic conversion protocol layer (or semantic conversion function) on the receiving end side, and the receiving end side can perform semantic decoding and semantic recovery on the encoded information. The semantic conversion protocol layer (or semantic conversion function) can obtain the semantic encoding model and semantic encoding knowledge base on the sending end side, and can also obtain the semantic decoding model and semantic decoding knowledge base on the receiving end side. The semantic conversion protocol layer (or semantic conversion function) on the sending end side can be deployed on the terminal device that performs the sending end function, or it can be deployed on an intermediate device that provides services to the sending end, such as an access network device or a user plane device.

[0142] In another possible implementation, the semantic conversion protocol layer (or semantic conversion function) on the sending side is used to obtain the semantic encoding model and the semantic encoding knowledge base, and the semantic conversion protocol layer (or semantic conversion function) on the receiving side is used to obtain the semantic decoding model and the semantic decoding knowledge base.

[0143] Please refer to Figure 5, which is a flow chart of an embodiment of a semantic communication method proposed in an embodiment of the present application. The semantic communication method proposed in an embodiment of the present application includes:

[0144] S1. The sending end sends semantic conversion capability information to the core network device.

[0145] In step S1, the sending end sends semantic conversion capability information to the core network device, where the semantic conversion capability information is used to indicate the semantic coding model and / or semantic coding knowledge base supported by the sending end. Exemplarily, the semantic conversion capability information includes any one or more of the following: type information of the semantic coding model, size of the semantic coding model, identification information of the semantic coding model, type information of the semantic coding knowledge base, size of the semantic coding knowledge base, or identification information of the semantic coding knowledge base.

[0146] Specifically, the type information of the semantic coding knowledge base indicates the type of the semantic coding knowledge base, and the types of the semantic coding knowledge base include but are not limited to: a semantic coding knowledge base for image type data, a semantic coding knowledge base for speech type data, a semantic coding knowledge base for video type data, or a semantic coding knowledge base for text type data. The type information of the semantic coding model indicates the type of the semantic coding model, and the types of the semantic coding model include but are not limited to: a semantic coding model for image type data, a semantic coding model for speech type data, a semantic coding model for video type data, or a semantic coding model for text type data.

[0147] The size of the semantic coding model may be the number of parameters of the semantic coding model or the size of the storage space occupied by the semantic coding model. For example, the semantic coding model includes 10 million parameters or the semantic coding model occupies 1 Gbyte of storage space.

[0148] The identification information of the semantic coding model includes but is not limited to: an indicator (ID) or an index (index). For example, index 0 indicates that the semantic coding model is "Autoencoder", and index 1 indicates that the semantic coding model is "transformer".

[0149] The identification information of the semantic encoding knowledge base includes, but is not limited to, an indicator (ID) or an index. For example, index 3 indicates that the semantic encoding knowledge base includes the "MINIST" dataset, and index 4 indicates that the semantic encoding knowledge base includes the "CIFAR-10" dataset.

[0150] Optionally, the sending end carries the semantic conversion capability information in a PDU session establishment or modification request sent to the core network device.

[0151] For example, the sending end may be a terminal device or an application server. For ease of description, the terminal device on the sending end side is referred to as a source terminal device.

[0152] S2. The core network device determines the semantic conversion mode information based on the semantic conversion capability information.

[0153] In step S2, the core network device determines semantic conversion mode information based on the semantic conversion capability information reported by the sender. The semantic conversion mode information is used to indicate the semantic conversion model and / or semantic conversion knowledge base used by the intermediate device, which is used to forward the encoded data from the sender to the receiver.

[0154] The semantic conversion mode information includes any one or more of the following: identification information (or index) of the semantic conversion model and identification information (or index) of the semantic conversion knowledge base.

[0155] Optionally, the semantic conversion mode information includes any one or more of the following: identification information (or index) of the semantic conversion encoding model, identification information (or index) of the semantic conversion encoding knowledge base, identification information (or index) of the semantic conversion decoding model corresponding to the semantic conversion encoding model, and identification information (or index) of the semantic conversion decoding knowledge base.

[0156] Optionally, the semantic conversion mode information sent by the core network device to different devices may be different. For example, the semantic conversion mode information sent by the core network device to the sending end may be the identification information (or index) of the semantic coding model and / or the identification information (or index) of the semantic coding knowledge base; the semantic conversion mode information sent by the core network device to the intermediate device may be the identification information (or index) of the semantic conversion model and / or the identification information (or index) of the semantic conversion knowledge base, or, the semantic conversion mode information sent by the core network device to the intermediate device may be the identification information (or index) of the semantic conversion coding model, the identification information (or index) of the semantic conversion coding knowledge base, the identification information (or index) of the semantic conversion decoding model, and / or the identification information (or index) of the semantic conversion decoding knowledge base; the semantic conversion mode information sent by the core network device to the receiving end may be the identification information (or index) of the semantic decoding model and / or the identification information (or index) of the semantic decoding knowledge base.

[0157] In one possible implementation, a core network device determines the semantic coding model and / or semantic coding knowledge base supported by the sender based on the semantic conversion capability information. The core network device then determines a semantic conversion model and / or semantic conversion knowledge base that matches the semantic coding model and / or semantic coding knowledge base supported by the sender. Exemplarily, the core network device may be an access and mobility management network element.

[0158] In another possible implementation, the core network device obtains the quality of service (QoS) requirements of the semantic communication between the sending end and the receiving end. Then, the semantic conversion mode information is determined based on the quality of service requirements of the semantic communication. The quality of service requirements of the semantic communication include any one or more of the following: semantic decoding accuracy, semantic similarity, semantic clarity, guaranteed bit rate, packet transmission delay budget, or packet error rate. Exemplarily, the core network device configures one or more semantic conversion modes, and each semantic conversion mode includes the quality of service of the semantic communication that can be achieved by adopting the semantic conversion mode. After the core network device selects a certain semantic conversion mode, it sends the semantic conversion mode information corresponding to the semantic conversion mode to the sending end, the receiving end and / or the intermediate device, so that the quality of service requirements of the semantic communication are met.

[0159] In another example, the core network device may include a session management network element. The session management network element may locally obtain the quality of service requirements for semantic communication and negotiate with the policy control function to obtain the quality of service requirements for the semantic communication. Optionally, the sender may include the quality of service requirements for the semantic communication in a PDU session establishment or modification request sent to the core network device.

[0160] Furthermore, the core network device determines the semantic decoding model and / or semantic decoding knowledge base used by the receiving end based on the semantic conversion mode information, and the semantic decoding model and / or semantic decoding knowledge base used by the receiving end matches the semantic conversion model and / or semantic conversion knowledge base.

[0161] S3. The core network device sends semantic conversion mode information to the intermediate device.

[0162] After step S2, step S3 is executed.

[0163] In step S3, the core network device sends semantic conversion mode information to the intermediate device. The semantic conversion mode information includes: information about the semantic conversion model and / or information about the semantic conversion knowledge base. For example, the information about the semantic conversion model may be information indicating the semantic conversion model, and the information about the semantic conversion knowledge base may be information indicating the semantic conversion knowledge base.

[0164] Since the semantic conversion model can include: a semantic conversion encoding model and a semantic conversion decoding model, the semantic conversion knowledge base can include: a semantic conversion encoding knowledge base and a semantic conversion decoding knowledge base. Therefore, the semantic conversion pattern information includes any one or more of the following information: information about the semantic conversion model, information about the semantic conversion knowledge base, information about the semantic conversion encoding model, information about the semantic conversion encoding knowledge base, information about the semantic conversion decoding model, or information about the semantic conversion decoding knowledge base. Regarding the semantic conversion pattern information, you can also refer to the semantic conversion pattern information described in the aforementioned step S2, which will not be repeated here.

[0165] Exemplarily, the intermediate device may be an intermediate device on the transmitting end side, or an intermediate device on the receiving end side. The intermediate device may further include a first intermediate device on the transmitting end side and a second intermediate device on the receiving end side. The intermediate device includes, but is not limited to, an access network device or a user plane device.

[0166] In one example, after the intermediate device receives the semantic conversion mode information, the STL layer of the intermediate device processes the semantic conversion mode information.

[0167] For example, the receiving end includes but is not limited to: a terminal device or an application server. For ease of description, the terminal device on the receiving end side is referred to as a target terminal device.

[0168] Exemplarily, the core network device includes a core network device that provides services to a sending end and a receiving end, and may also include a source core network device that provides services to a sending end and a target core network device that provides services to a receiving end.

[0169] S4. The core network device sends semantic conversion mode information to the sending end.

[0170] In step S4, the core network device sends semantic conversion mode information to the sending end.

[0171] In a possible implementation, the semantic conversion pattern information includes: information of a semantic conversion model and / or information of a semantic conversion knowledge base.

[0172] In another possible implementation, the semantic conversion mode information includes: information of a semantic encoding model and / or information of a semantic encoding knowledge base.

[0173] Exemplarily, the core network device sends the semantic conversion mode information to the access network device, and the access network device sends the semantic conversion mode information to the transmitter. The semantic conversion mode information is carried in downlink control information (DCI), MAC control element (MAC CE), packet data convergence protocol (PDCP) control PDU or radio resource control (RRC) message.

[0174] In another example, the core network device sends a PDU session establishment response or a PDU session modification response to the sending end, and the PDU session establishment response or the PDU session modification response carries semantic conversion mode information.

[0175] In a possible implementation, after step S2, step S4 is performed.

[0176] In another possible implementation, when the intermediate device includes an access network device, step S4 is performed after step S3.

[0177] S5. The core network device sends semantic conversion mode information to the receiving end.

[0178] After step S2, step S5 is executed.

[0179] In step S5, the core network device sends semantic conversion mode information to the receiving end.

[0180] In one possible implementation, the semantic conversion pattern information includes: information about a semantic conversion model and / or information about a semantic conversion knowledge base. The receiving end determines, based on the information about the semantic conversion model included in the semantic conversion pattern information, a semantic decoding model corresponding to the semantic conversion model from the semantic decoding models supported by the receiving end. Alternatively, the receiving end determines, based on the information about the semantic conversion knowledge base included in the semantic conversion pattern information, a semantic decoding knowledge base corresponding to the semantic conversion knowledge base from the semantic decoding knowledge bases supported by the receiving end.

[0181] In another possible implementation, the semantic conversion mode information includes: information about a semantic decoding model, and / or information about a semantic decoding knowledge base.

[0182] Exemplarily, the core network device sends the semantic conversion mode information to the access network device, and the access network device sends the semantic conversion mode information to the receiving end. The semantic conversion mode information is carried in downlink control information (DCI), MAC control element (MAC CE), packet data convergence protocol (PDCP) control PDU or radio resource control (RRC) message.

[0183] In another example, the core network device sends a PDU session establishment response or a PDU session modification response to the receiving end, and the PDU session establishment response or the PDU session modification response carries semantic conversion mode information.

[0184] It should be noted that the semantic coding model configured by the core network device to the sending end and the semantic decoding model configured by the core network device to the receiving end need to be adapted to each other. Mutual adaptation means that the semantic coding model and the semantic decoding model can meet certain quality assurance of semantic communication or accuracy assurance of semantic recovery.

[0185] S6. The sending end determines a semantic coding model and / or a semantic coding knowledge base according to the semantic conversion mode information.

[0186] In step S6, when the semantic conversion pattern information includes: information about the semantic conversion model and / or information about the semantic conversion knowledge base, the sending end determines a semantic encoding model corresponding to the semantic conversion model from the semantic encoding models supported by the sending end based on the information about the semantic conversion model included in the semantic conversion pattern information. Alternatively, the sending end determines a semantic encoding knowledge base corresponding to the semantic conversion knowledge base from the semantic encoding knowledge bases supported by the sending end based on the information about the semantic conversion knowledge base included in the semantic conversion pattern information.

[0187] When the semantic conversion mode information includes: information of a semantic coding model and / or information of a semantic coding knowledge base, the sending end directly determines the semantic coding model and / or the semantic coding knowledge base according to the semantic conversion mode information.

[0188] In a possible implementation, the sending end locally configures the semantic encoding model and determines the semantic encoding knowledge base according to the semantic conversion pattern information.

[0189] In another possible implementation, the sending end locally configures a semantic coding knowledge base and determines a semantic coding model according to the semantic conversion pattern information.

[0190] In another possible implementation, the sending end determines the semantic coding model and the semantic coding knowledge base according to the semantic conversion mode information.

[0191] In one example, the STL layer at the sending end determines the semantic encoding model and / or the semantic encoding knowledge base according to the semantic conversion mode information.

[0192] S7. The sending end encodes the source data according to the semantic coding model and the semantic coding knowledge base to generate first encoded data.

[0193] Step S7 is executed after step S6.

[0194] In step S7, the sending end performs semantic extraction, semantic coding and / or source-channel joint coding processing on the source data according to the semantic coding model and the semantic coding knowledge base to generate first coded data.

[0195] In one example, the STL layer at the sending end encodes the source data according to the semantic coding model and the semantic coding knowledge base to generate first encoded data.

[0196] S8. The sending end sends the first encoded data to the intermediate device.

[0197] S9. The intermediate device determines a semantic conversion model and / or a semantic conversion knowledge base according to the semantic conversion pattern information.

[0198] After step S3, step S9 is executed.

[0199] In step S9, in a possible implementation, the intermediate device locally configures the semantic conversion model, and the intermediate device determines the semantic conversion knowledge base according to the semantic conversion mode information.

[0200] In another possible implementation, the intermediate device locally configures a semantic conversion knowledge base, and the intermediate device determines a semantic conversion model according to the semantic conversion pattern information.

[0201] In another possible implementation, the intermediate device determines the semantic conversion model and the semantic conversion knowledge base according to the semantic conversion pattern information.

[0202] Furthermore, when the semantic conversion model includes a semantic conversion encoding model and a semantic conversion decoding model, the intermediate device may further determine the semantic conversion encoding model and the semantic conversion decoding model based on the semantic conversion pattern information. When the semantic conversion knowledge base includes a semantic conversion encoding knowledge base and a semantic conversion decoding knowledge base, the intermediate device may further determine the semantic conversion encoding knowledge base and the semantic conversion decoding knowledge base based on the semantic conversion pattern information.

[0203] In one example, the STL layer of the middleware determines the semantic conversion model and / or the semantic conversion knowledge base according to the semantic conversion mode information.

[0204] S10. The intermediate device processes the first coded data to generate second coded data according to the semantic conversion model and the semantic conversion knowledge base.

[0205] In step S10, one possible implementation is for the intermediate device to perform semantic conversion processing on the first encoded data based on the semantic conversion model and the semantic conversion knowledge base to obtain second encoded data. Specifically, the semantic conversion processing includes: first, performing semantic decoding and semantic recovery on the first encoded data based on the semantic conversion model and the semantic conversion knowledge base to generate intermediate data; then, performing semantic extraction and semantic encoding on the intermediate data based on the semantic conversion model and the semantic conversion knowledge base to obtain second encoded data.

[0206] In another possible implementation, the intermediate device performs semantic decoding and semantic recovery on the first coded data based on the semantic transformation decoding model and the semantic transformation decoding knowledge base to generate intermediate data. The intermediate device then performs semantic extraction and semantic encoding on the intermediate data based on the semantic transformation encoding model and the semantic transformation encoding knowledge base to obtain second coded data.

[0207] In one example, the STL layer of the intermediate device processes the first encoded data to generate the second encoded data according to the semantic conversion model and the semantic conversion knowledge base.

[0208] S11. The intermediate device sends second encoded data to the receiving end.

[0209] S12. The receiving end determines a semantic decoding model and / or a semantic decoding knowledge base according to the semantic conversion mode information.

[0210] After step S5, step S12 is executed.

[0211] In step S12, when the semantic conversion pattern information includes: information about the semantic conversion model and / or information about the semantic conversion knowledge base, the receiving end determines a semantic decoding model corresponding to the semantic conversion model from the semantic decoding models supported by the receiving end based on the information about the semantic conversion model included in the semantic conversion pattern information. Alternatively, the receiving end determines a semantic decoding knowledge base corresponding to the semantic conversion knowledge base from the semantic decoding knowledge bases supported by the receiving end based on the information about the semantic conversion knowledge base included in the semantic conversion pattern information.

[0212] When the semantic conversion mode information includes: information of a semantic decoding model and / or information of a semantic decoding knowledge base, the receiving end directly determines the semantic decoding model and / or the semantic decoding knowledge base according to the semantic conversion mode information.

[0213] In a possible implementation, the receiving end locally configures a semantic decoding model, and determines a semantic decoding knowledge base according to the semantic conversion pattern information.

[0214] In another possible implementation, the receiving end locally configures a semantic decoding knowledge base, and determines a semantic decoding model according to the semantic conversion pattern information.

[0215] In another possible implementation, the receiving end determines the semantic decoding model and the semantic decoding knowledge base according to the semantic conversion mode information.

[0216] In one example, the STL layer at the receiving end determines the semantic decoding model and / or the semantic decoding knowledge base according to the semantic conversion mode information.

[0217] S13. The receiving end decodes the second encoded data according to the semantic decoding model and the semantic decoding knowledge base to generate target data.

[0218] In step S13, the receiving end performs semantic decoding, semantic recovery and / or source-channel joint decoding processing on the second coded data according to the semantic decoding model and the semantic decoding knowledge base to generate target data.

[0219] In one example, the STL layer at the receiving end decodes the second encoded data according to the semantic decoding model and the semantic decoding knowledge base to generate target data.

[0220] It should be noted that this embodiment uses the PDU session establishment or modification process as an example to introduce the application process of the semantic communication method. In addition to the PDU session establishment or modification process, the semantic communication method proposed in this embodiment of the application can also be applied to other service processes, and this embodiment of the application does not limit this. For example, the message carried by the semantic conversion capability information or the semantic conversion mode information is not limited in this embodiment of the application.

[0221] In an embodiment of the present application, a core network device sends semantic conversion mode information to an intermediate device, a transmitter, and a receiver, so that the semantic conversion model and semantic conversion knowledge base used by the intermediate device match the semantic encoding model and semantic encoding knowledge base of the transmitter, and the semantic conversion model and semantic conversion knowledge base used by the intermediate device match the semantic decoding model and semantic decoding knowledge base of the receiver. Therefore, in the event that the semantic knowledge bases or semantic models between the transmitter and the receiver do not match, the semantic conversion performed in the intermediate device improves the accuracy of semantic recovery and the quality of semantic communication between the transmitter and the receiver.

[0222] In conjunction with the above embodiments, an application scenario proposed in an embodiment of the present application is described below. The sending end is a source terminal device, the receiving end is a target terminal device, and the intermediate device is an access network device or a user plane device. This application scenario is shown in Figure 7. Please refer to Figure 7, which is a flow chart of an embodiment of a semantic communication method proposed in an embodiment of the present application. A semantic communication method proposed in an embodiment of the present application includes:

[0223] D1. The source terminal device sends semantic conversion capability information to the core network device.

[0224] Step D1 is similar to the aforementioned step S1 and will not be described in detail here.

[0225] D2. The core network device determines the semantic conversion mode information based on the semantic conversion capability information.

[0226] Step D2 is similar to the aforementioned step S2 and will not be described in detail here.

[0227] D3. The core network device sends semantic conversion mode information to the access network device or the user plane device.

[0228] Step D3 is similar to the aforementioned step S3 and will not be described in detail here.

[0229] D4. The core network device sends semantic conversion mode information to the source terminal device.

[0230] Step D4 is similar to the aforementioned step S4 and will not be described in detail here.

[0231] D5. The core network device sends semantic conversion mode information to the target terminal device.

[0232] Step D5 is similar to the aforementioned step S5 and will not be described in detail here.

[0233] D6. The source terminal device determines a semantic coding model and / or a semantic coding knowledge base based on the semantic conversion mode information.

[0234] Step D6 is similar to the aforementioned step S6 and will not be described in detail here.

[0235] D7. The source terminal device encodes the source data according to the semantic coding model and the semantic coding knowledge base to generate first encoded data.

[0236] Step D7 is similar to the aforementioned step S7 and will not be described in detail here.

[0237] D8. The source terminal device sends the first encoded data to the access network device or the user plane device.

[0238] Step D8 is similar to the aforementioned step S8 and will not be described in detail here.

[0239] D9. The access network device or the user plane device determines a semantic conversion model and / or a semantic conversion knowledge base according to the semantic conversion mode information.

[0240] Step D9 is similar to the aforementioned step S9 and will not be described in detail here.

[0241] D10. The access network device or the user plane device processes the first coded data according to the semantic conversion model and the semantic conversion knowledge base to generate second coded data.

[0242] Step D10 is similar to the aforementioned step S10 and will not be described in detail here.

[0243] D11. The access network device or the user plane device sends the second encoded data to the target terminal device.

[0244] Step D11 is similar to the aforementioned step S11 and will not be described in detail here.

[0245] D12. The target terminal device determines a semantic decoding model and / or a semantic decoding knowledge base based on the semantic conversion mode information.

[0246] Step D12 is similar to the aforementioned step S12 and will not be described in detail here.

[0247] D13. The target terminal device decodes the second encoded data according to the semantic decoding model and the semantic decoding knowledge base to generate target data.

[0248] Step D13 is similar to the aforementioned step S13 and will not be described in detail here.

[0249] In combination with the foregoing embodiments, an application scenario proposed in an embodiment of the present application is introduced below. The sending end is a source terminal device, the receiving end is a target terminal device, and the intermediate device includes a first intermediate device that provides services for the sending end and a second intermediate device that provides services for the receiving end, wherein the first intermediate device includes a source access network device or a source user plane device, and the second intermediate device includes a target access network device or a target user plane device. The core network device includes a source core network device that provides services for the sending end or the first intermediate device, and a target core network device that provides services for the receiving end or the second intermediate device. It can be understood that the source core network device and the target core network device can be the same device or two independent devices. The application scenario is shown in Figure 8. Please refer to Figure 8, which is a flow chart of an embodiment of a semantic communication method proposed in an embodiment of the present application. A semantic communication method proposed in an embodiment of the present application includes:

[0250] F1. The source terminal device sends semantic conversion capability information to the source core network device.

[0251] Step F1 is similar to the aforementioned step S1 and will not be described in detail here.

[0252] Optionally, the target terminal device may also send semantic conversion capability information to the target core network device.

[0253] F2. The source core network device and the target core network device determine semantic conversion mode information based on the semantic conversion capability information.

[0254] In step F2, first, a semantic conversion pattern information set that is supported by both the source terminal device and the target terminal device is pre-configured between the source core network device and the target core network device. The semantic conversion pattern information set includes: index or identification information of one or more semantic pattern information, each semantic pattern information corresponds to a set of association relationships, and the association relationships include: a semantic conversion encoding model, a semantic conversion encoding knowledge base, a semantic conversion decoding model, and a semantic conversion decoding knowledge base. For example, the semantic pattern information includes the index or identification information of the semantic conversion encoding model, the index or identification information of the semantic conversion encoding knowledge base, the index or identification information of the semantic conversion decoding model, and the index or identification information of the semantic conversion decoding knowledge base.

[0255] Exemplarily, the semantic model information of a source core network device includes information about a semantic conversion encoding model and a semantic conversion encoding knowledge base. The semantic model information of a source core network device may also include information about a semantic encoding model and a semantic encoding knowledge base. The semantic model information of a target core network device includes information about a semantic conversion decoding model and a semantic conversion decoding knowledge base. The semantic model information of a target core network device may also include information about a semantic decoding model and a semantic decoding knowledge base.

[0256] Secondly, the source core network device determines the semantic conversion mode information that matches the semantic conversion capability information of the source terminal device from the semantic conversion mode information set based on the semantic conversion capability information of the source terminal device, and notifies the target core network device of the semantic conversion mode information.

[0257] Optionally, the source core network device may also notify the target core network device of multiple candidate semantic conversion mode information. The multiple candidate semantic conversion mode information sent by the source core network device to the target core network device includes any one or more of the following: information about the semantic conversion encoding model, information about the semantic conversion encoding knowledge base, information about the semantic encoding model and information about the semantic encoding knowledge base, information about the semantic conversion decoding model, information about the semantic conversion decoding knowledge base, information about the semantic decoding model, or information about the semantic decoding knowledge base.

[0258] The target core network device queries the local semantic conversion mode information set based on the received semantic conversion mode information, determines the semantic conversion mode information that matches the semantic conversion capability information of the target terminal device, and replies with a confirmation message to the source core network device. The confirmation message indicates that the target core network device agrees to use the semantic conversion decoding model and / or semantic conversion decoding knowledge base indicated by the semantic conversion mode information. Optionally, if the source core network device sends multiple candidate semantic conversion mode information to the target core network device, the target core network device determines the semantic conversion mode information to be used from the multiple candidate semantic conversion mode information, and then the confirmation message sent by the target core network device to the source core network device includes the semantic conversion mode information determined to be used by the target core network device.

[0259] In another possible implementation, if the source core network device and the target core network device are the same core network device, step F2 may not be performed, and the core network device sends semantic conversion mode information to the first intermediate device, the source terminal device, the second intermediate device, and the target terminal device respectively.

[0260] F3. The source core network device sends semantic conversion mode information to the first intermediate device.

[0261] Step F3 is similar to the aforementioned step S3 and will not be described in detail here.

[0262] In step F3, a possible implementation method is that the semantic conversion mode information sent by the source core network device to the first intermediate device includes indication information (or index) of the semantic conversion decoding model and / or indication information (or index) of the semantic conversion decoding knowledge base.

[0263] F4. The source core network device sends semantic conversion mode information to the source terminal device.

[0264] Step F4 is similar to the aforementioned step S4 and will not be described in detail here.

[0265] F5. The target core network device sends semantic conversion mode information to the second intermediate device.

[0266] Step F5 is similar to the aforementioned step S3 and will not be described in detail here.

[0267] In step F5, a possible implementation method is that the semantic conversion mode information sent by the target core network device to the second intermediate device includes indication information (or index) of the semantic conversion coding model and / or indication information (or index) of the semantic conversion coding knowledge base.

[0268] F6. The target core network device sends semantic conversion mode information to the target terminal device.

[0269] Step F6 is similar to the aforementioned step S5 and will not be described in detail here.

[0270] F7. The source terminal device determines a semantic coding model and / or a semantic coding knowledge base based on the semantic conversion mode information.

[0271] Step F7 is similar to the aforementioned step S6 and will not be described in detail here.

[0272] F8. The source terminal device encodes the source data according to the semantic coding model and the semantic coding knowledge base to generate first encoded data.

[0273] Step F8 is similar to the aforementioned step S7 and will not be described in detail here.

[0274] F9. The source terminal device sends the first encoded data to the first intermediate device.

[0275] F10. The first intermediate device determines a semantic conversion decoding model and / or a semantic conversion decoding knowledge base according to the semantic conversion mode information.

[0276] Step F10 is similar to the aforementioned step S9 and will not be described in detail here.

[0277] F11. The first intermediate device decodes the first encoded data according to the semantic conversion decoding model and the semantic conversion decoding knowledge base to generate intermediate data.

[0278] In step F11 , the first intermediate device performs semantic decoding and semantic restoration on the first coded data according to the semantic conversion decoding model and the semantic conversion decoding knowledge base to generate intermediate data.

[0279] F12. The first intermediate device sends intermediate data to the second intermediate device.

[0280] F13. The second intermediate device determines a semantic conversion coding model and / or a semantic conversion coding knowledge base according to the semantic conversion mode information.

[0281] F14. The second intermediate device encodes the intermediate data according to the semantic conversion coding model and the semantic conversion coding knowledge base to generate second encoded data.

[0282] In step F14 , the intermediate device performs semantic extraction and semantic encoding on the intermediate data according to the semantic transformation encoding model and the semantic transformation encoding knowledge base to obtain second encoded data.

[0283] F15. The second intermediate device sends the second encoded data to the target terminal device.

[0284] F16. The target terminal device determines a semantic decoding model and / or a semantic decoding knowledge base based on the semantic conversion mode information.

[0285] F17. The target terminal device decodes the second encoded data according to the semantic decoding model and the semantic decoding knowledge base to generate target data.

[0286] Steps F16 to F17 are similar to the aforementioned steps S12 to S13 and are not described in detail here.

[0287] In combination with the above embodiments, an application scenario proposed in an embodiment of the present application is introduced below. The sending end is a terminal device, the receiving end is an application server, and the intermediate device includes an access network device or a user plane device. The intermediate device performs the semantic conversion of the uplink data, and the uplink direction refers to the direction from the terminal device to the application server. The application scenario is shown in Figure 9. Please refer to Figure 9, which is a flow chart of an embodiment of a semantic communication method proposed in an embodiment of the present application. A semantic communication method proposed in an embodiment of the present application includes:

[0288] G1. The terminal device sends semantic conversion capability information to the core network device.

[0289] G2. The core network device determines the semantic conversion mode information based on the semantic conversion capability information.

[0290] In step G2, the core network device determines the uplink semantic conversion mode information from the terminal device to the application server based on the semantic conversion capability information reported by the terminal device. The uplink semantic conversion mode information includes: information on the semantic coding model for uplink semantic conversion, information on the semantic coding knowledge base for uplink semantic conversion, information on the semantic decoding model for uplink semantic conversion, information on the semantic decoding knowledge base for uplink semantic conversion, information on the semantic conversion decoding model for uplink semantic conversion, information on the semantic conversion decoding knowledge base for uplink semantic conversion, information on the semantic conversion coding model for uplink semantic conversion, and / or information on the semantic conversion coding knowledge base for uplink semantic conversion.

[0291] G3. The core network device sends semantic conversion mode information to the access network device or user plane device.

[0292] G4. The core network device sends semantic conversion mode information to the terminal device.

[0293] Exemplarily, the uplink semantic conversion mode information sent by the core network device to the terminal device includes: information on the semantic decoding model used for uplink semantic conversion, and / or information on the semantic decoding knowledge base used for uplink semantic conversion.

[0294] G5. The core network device sends semantic conversion mode information to the application server.

[0295] Exemplarily, the uplink semantic conversion mode information sent by the core network device to the application server includes: information of a semantic coding model for uplink semantic conversion, and / or information of a semantic coding knowledge base for uplink semantic conversion.

[0296] G6. The terminal device determines a semantic coding model and / or a semantic coding knowledge base based on the semantic conversion mode information.

[0297] G7. The terminal device encodes the source data according to the semantic coding model and the semantic coding knowledge base to generate first encoded data.

[0298] G8. The terminal device sends the first coded data to the access network device or the user plane device.

[0299] G9. The access network device or the user plane device determines a semantic conversion model and / or a semantic conversion knowledge base according to the semantic conversion mode information.

[0300] G10, the access network device or the user plane device processes the first coded data according to the semantic conversion model and the semantic conversion knowledge base to generate second coded data.

[0301] G11. The access network device or the user plane device sends the second encoded data to the application server.

[0302] G12. The application server determines a semantic decoding model and / or a semantic decoding knowledge base based on the semantic conversion mode information.

[0303] G13. The application server decodes the second encoded data according to the semantic decoding model and the semantic decoding knowledge base to generate target data.

[0304] Steps G1 to G13 are similar to the aforementioned steps S1 to S13 and are not described in detail here.

[0305] In combination with the above embodiments, an application scenario proposed in an embodiment of the present application is introduced below. The sending end is an application server, the receiving end is a terminal device, and the intermediate device includes an access network device or a user plane device. The intermediate device performs the semantic conversion of downlink data, and the downlink direction refers to the direction from the application server to the terminal device. The application scenario is shown in Figure 10. Please refer to Figure 10, which is a flow chart of an embodiment of a semantic communication method proposed in an embodiment of the present application. A semantic communication method proposed in an embodiment of the present application includes:

[0306] H1. The application server sends semantic conversion capability information to the core network device.

[0307] H2. The core network device determines the semantic conversion mode information based on the semantic conversion capability information.

[0308] In step H2, the core network device determines the downlink semantic conversion mode information from the application server to the terminal device based on the semantic conversion capability information reported by the application server. The downlink semantic conversion mode information includes: information on the semantic coding model for downlink semantic conversion, information on the semantic coding knowledge base for downlink semantic conversion, information on the semantic decoding model for downlink semantic conversion, information on the semantic decoding knowledge base for downlink semantic conversion, a semantic conversion decoding model for downlink semantic conversion, a semantic conversion decoding knowledge base for downlink semantic conversion, a semantic conversion coding model for downlink semantic conversion, and / or a semantic conversion coding knowledge base for downlink semantic conversion.

[0309] H3. The core network device sends semantic conversion mode information to the access network device or user plane device.

[0310] H4. The core network device sends semantic conversion mode information to the application server.

[0311] Exemplarily, the downlink semantic conversion mode information sent by the core network device to the application server includes: information of the semantic decoding model used for downlink semantic conversion, and / or information of the semantic decoding knowledge base used for downlink semantic conversion.

[0312] H5. The core network device sends semantic conversion mode information to the terminal device.

[0313] Exemplarily, the downlink semantic conversion mode information sent by the core network device to the terminal device includes: information of a semantic coding model for downlink semantic conversion, and / or information of a semantic coding knowledge base for downlink semantic conversion.

[0314] H6. The application server determines the semantic coding model and / or semantic coding knowledge base according to the semantic conversion mode information.

[0315] H7. The application server encodes the source data according to the semantic coding model and the semantic coding knowledge base to generate first encoded data.

[0316] H8. The application server sends the first coded data to the access network device or the user plane device.

[0317] H9. The access network device or the user plane device determines a semantic conversion model and / or a semantic conversion knowledge base according to the semantic conversion mode information.

[0318] H10. The access network device or the user plane device processes the first coded data according to the semantic conversion model and the semantic conversion knowledge base to generate second coded data.

[0319] H11. The access network device or the user plane device sends the second coded data to the terminal device.

[0320] H12. The terminal device determines a semantic decoding model and / or a semantic decoding knowledge base based on the semantic conversion mode information.

[0321] H13. The terminal device decodes the second encoded data according to the semantic decoding model and the semantic decoding knowledge base to generate target data.

[0322] Steps H1 to H13 are similar to the aforementioned steps S1 to S13 and are not described in detail here.

[0323] It should be noted that the embodiment illustrated in FIG9 and the embodiment illustrated in FIG10 can be combined. In other words, the core network device determines the semantic conversion mode information for uplink semantic conversion based on the semantic conversion capability information reported by the terminal device; the core network device determines the semantic conversion mode information for downlink semantic conversion based on the semantic conversion capability information reported by the application server. Then, the intermediate device performs semantic conversion in the uplink direction based on the semantic conversion mode information for uplink semantic conversion and performs semantic conversion in the downlink direction based on the semantic conversion mode information for downlink semantic conversion.

[0324] The present application is described above from the perspective of method, and other embodiments provided in the present application will be further described below.

[0325] Please refer to Figure 11, which is a schematic diagram of an implementation of the communication device provided in this application. The communication device 1100 includes a processing module 1101 and a transceiver module 1102. The communication device 1100 can implement the functions of the communication device (including the transmitting end, intermediate equipment, core network equipment and / or receiving end, etc.) in the above-mentioned method embodiment, and therefore can also achieve the beneficial effects possessed by the above-mentioned method embodiment. In the embodiment of the present application, the communication device 1100 can be a transmitting end, an intermediate equipment, a core network equipment and / or a receiving end, or it can be an integrated circuit or component inside the transmitting end, the intermediate equipment, the core network equipment and / or the receiving end, such as a chip, or it can be an integrated circuit or component integrated with the transmitting end, the intermediate equipment, the core network equipment and / or the receiving end.

[0326] Please refer to Fig. 12, which is another schematic structural diagram of a communication device 1200 provided in this application. The communication device 1200 at least includes an input and output interface 1202. The communication device 1200 may be a chip or an integrated circuit.

[0327] Optionally, the communication device further includes a logic circuit 1201 .

[0328] The transceiver module 1102 shown in FIG11 may be a communication interface, which may be the input / output interface 1202 in FIG12 , which may include an input interface and an output interface. Alternatively, the communication interface may be a transceiver circuit, which may include an input interface circuit and an output interface circuit.

[0329] Optionally, when the communication device 1200 is the sending end, intermediate device, core network device and / or receiving end in the aforementioned embodiment, the input and output interface 1202 is used to input and output information; the logic circuit 1201 is used to execute the method executed by the sending end, intermediate device, core network device and / or receiving end in the aforementioned embodiment.

[0330] The logic circuit 1201 and the input / output interface 1202 may also execute other steps executed by the communication device in any embodiment and achieve corresponding beneficial effects, which will not be described in detail here.

[0331] In a possible implementation, the processing module 1101 shown in FIG. 11 may be the logic circuit 1201 in FIG. 12 .

[0332] Optionally, the logic circuit 1201 may be a processing device, and the functions of the processing device may be partially or entirely implemented by software. The functions of the processing device may be partially or entirely implemented by software.

[0333] Optionally, the processing device may include a memory and a processor, wherein the memory is used to store a computer program, and the processor reads and executes the computer program stored in the memory to perform corresponding processing and / or steps in any one of the method embodiments.

[0334] Alternatively, the processing device may include only a processor. A memory for storing the computer program is located outside the processing device, and the processor is connected to the memory via circuits / wires to read and execute the computer program stored in the memory. The memory and processor may be integrated or physically separate.

[0335] Optionally, the processing device may be one or more chips, or one or more integrated circuits. For example, the processing device may be one or more field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), system-on-chips (SoCs), central processor units (CPUs), network processors (NPs), digital signal processors (DSPs), microcontroller units (MCUs), programmable logic devices (PLDs), or other integrated chips, or any combination of the above chips or processors.

[0336] Please refer to Figure 13, which shows a communication device 1300 involved in the above embodiments provided in an embodiment of the present application. The communication device 1300 can specifically be a communication device serving as a sending end, intermediate device, core network device and / or receiving end in the above embodiments.

[0337] Herein, a possible logical structure diagram of the communication device 1300 is shown. The communication device 1300 may include but is not limited to at least one processor 1301 and a communication port 1302 .

[0338] Further optionally, the device may also include at least one of a memory 1303 and a bus 1304. In an embodiment of the present application, the at least one processor 1301 is used to control and process the actions of the communication device 1300.

[0339] In addition, the processor 1301 can be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a transistor logic device, a hardware component, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. The processor can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a digital signal processor and a microprocessor, and so on. Those skilled in the art will clearly understand that for the sake of 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.

[0340] It should be noted that the communication device 1300 shown in Figure 13 can be specifically used to implement the steps implemented by the sending end, intermediate equipment, core network equipment and / or receiving end in the aforementioned method embodiments, and to achieve the corresponding technical effects of the sending end, intermediate equipment, core network equipment and / or receiving end. The specific implementation methods of the communication device shown in Figure 13 can refer to the description in the aforementioned method embodiments, and will not be repeated here one by one.

[0341] Please refer to Figure 14, which is a schematic diagram of the structure of a communication device 1400 involved in the above-mentioned embodiments provided in an embodiment of the present application. The communication device 1400 may specifically be a communication device serving as a transmitting end, an intermediate device, a core network device, and / or a receiving end in the above-mentioned embodiments. The structure of the communication device may refer to the structure shown in Figure 14.

[0342] The communication device 1400 includes at least one processor 1401 and at least one network interface 1404. Further optionally, the communication device also includes at least one memory 1402, at least one transceiver 1403 and one or more antennas 1405. The processor 1401, the memory 1402, the transceiver 1403 and the network interface 1404 are connected, for example, via a bus. In an embodiment of the present application, the connection may include various interfaces, transmission lines or buses, etc., which are not limited in this embodiment. The antenna 1405 is connected to the transceiver 1403. The network interface 1404 is used to enable the communication device to communicate with other communication devices through a communication link. For example, the network interface 1404 may include a network interface between the communication device and the core network device, such as an S1 interface, and the network interface may include a network interface between the communication device and other communication devices (such as other radio access networks or core network devices), such as an X2 or Xn interface.

[0343] Processor 1401 is primarily used to process communication protocols and communication data, control the entire communication device, execute software programs, and process software program data, for example, to support the communication device in performing the actions described in the embodiments. The communication device may include a baseband processor and a central processing unit. The baseband processor is primarily used to process communication protocols and communication data, while the central processing unit is primarily used to control the entire terminal device, execute software programs, and process software program data. Processor 1401 in Figure 14 may integrate the functions of both a baseband processor and a central processing unit. Those skilled in the art will appreciate that the baseband processor and the central processing unit may also be independent processors interconnected via a bus or other technology. Those skilled in the art will appreciate that a terminal device may include multiple baseband processors to accommodate different network standards, multiple central processing units to enhance its processing capabilities, and various components of the terminal device may be connected via various buses. The baseband processor may also be referred to as a baseband processing circuit or a baseband processing chip. The central processing unit may also be referred to as a central processing circuit or a central processing chip. The functionality for processing communication protocols and communication data may be built into the processor or stored in memory as a software program, which is executed by the processor to implement the baseband processing functionality.

[0344] The memory is primarily used to store software programs and data. Memory 1402 can exist independently and be connected to processor 1401. Alternatively, memory 1402 can be integrated with processor 1401, for example, within a single chip. Memory 1402 can store program code for executing the technical solutions of the embodiments of the present application, and execution is controlled by processor 1401. The various computer program codes executed can also be considered drivers for processor 1401.

[0345] Figure 14 shows only one memory and one processor. In an actual terminal device, there may be multiple processors and multiple memories. The memory may also be referred to as a storage medium or a storage device. The memory may be a storage element on the same chip as the processor, i.e., an on-chip storage element, or an independent storage element, which is not limited in the present embodiment.

[0346] The transceiver 1403 can be used to support the reception or transmission of radio frequency signals between the communication device and the terminal. The transceiver 1403 can be connected to the antenna 1405. The transceiver 1403 includes a transmitter Tx and a receiver Rx. Specifically, one or more antennas 1405 can receive radio frequency signals. The receiver Rx of the transceiver 1403 is used to receive the radio frequency signal from the antenna, convert the radio frequency signal into a digital baseband signal or a digital intermediate frequency signal, and provide the digital baseband signal or digital intermediate frequency signal to the processor 1401 so that the processor 1401 can further process the digital baseband signal or digital intermediate frequency signal, such as demodulation and decoding. In addition, the transmitter Tx in the transceiver 1403 is also used to receive a modulated digital baseband signal or digital intermediate frequency signal from the processor 1401, convert the modulated digital baseband signal or digital intermediate frequency signal into a radio frequency signal, and transmit the radio frequency signal through one or more antennas 1405. Specifically, the receiver Rx can selectively perform one or more stages of down-mixing and analog-to-digital conversion on the RF signal to obtain a digital baseband signal or a digital intermediate frequency signal. The order of the down-mixing and analog-to-digital conversion processes is adjustable. The transmitter Tx can selectively perform one or more stages of up-mixing and digital-to-analog conversion on the modulated digital baseband signal or digital intermediate frequency signal to obtain a RF signal. The order of the up-mixing and digital-to-analog conversion processes is adjustable. The digital baseband signal and the digital intermediate frequency signal may be collectively referred to as digital signals.

[0347] The transceiver 1403 may also be referred to as a transceiver module, a transceiver, a transceiver device, etc. Optionally, a device in the transceiver module that implements a receiving function may be referred to as a receiving unit, and a device in the transceiver module that implements a transmitting function may be referred to as a transmitting unit. That is, the transceiver module includes a receiving unit and a transmitting unit. The receiving unit may also be referred to as a receiver, an input port, a receiving circuit, etc., and the transmitting unit may be referred to as a transmitter, a transmitter, or a transmitting circuit, etc.

[0348] It should be noted that the communication device 1400 shown in Figure 14 can be specifically used to implement the steps implemented by the sending end, intermediate equipment, core network equipment and / or receiving end in the aforementioned method embodiments, and to achieve the corresponding technical effects of the sending end, intermediate equipment, core network equipment and / or receiving end. The specific implementation methods of the communication device 1400 shown in Figure 14 can refer to the description in the aforementioned method embodiments, and will not be repeated here one by one.

[0349] An embodiment of the present application also provides a computer-readable storage medium storing one or more computer-executable instructions. When the computer-executable instructions are executed by a processor, the processor executes the method as may be implemented by the sending end, intermediate device, core network device and / or receiving end in the aforementioned embodiment.

[0350] An embodiment of the present application also provides a computer program product (or computer program) that stores one or more computers. When the computer program product is executed by the processor, the processor executes the method of the possible implementation method of the above-mentioned sending end, intermediate device, core network device and / or receiving end.

[0351] An embodiment of the present application also provides a chip system, which includes at least one processor for supporting a communication device to implement the functions involved in the possible implementation methods of the above-mentioned communication device. Optionally, the chip system also includes an interface circuit, which provides program instructions and / or data to the at least one processor. In one possible design, the chip system may also include a memory, which is used to store the necessary program instructions and data for the communication device. The chip system can be composed of chips, or it can include chips and other discrete devices, wherein the communication device can specifically be the sending end, intermediate device, core network device and / or receiving end in the aforementioned method embodiment.

[0352] An embodiment of the present application also provides a communication system, which includes the sending end, intermediate device, core network device and / or receiving end in any of the above embodiments.

[0353] In the several embodiments provided in this 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 merely schematic. For example, the division of the unit is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0354] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of the solution of this embodiment according to actual needs.

[0355] In addition, the functional units in the various embodiments of the present application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit. 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 contributing part 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 several instructions for enabling a computer device (which can be a personal computer, a server, or a wireless access network, etc.) to execute all or part of the steps of the method of each embodiment of the present application. The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

Claims

1. A semantic communication method, characterized in that: The method is applied to a core network device, and the method includes: Sending semantic conversion mode information to an intermediate device, wherein the semantic conversion mode information is used to indicate a semantic conversion model and / or a semantic conversion knowledge base used by the intermediate device, and the intermediate device is used to forward the encoded data of the sending end to the receiving end; Sending the semantic conversion mode information to the sending end; The semantic conversion mode information is sent to the receiving end.

2. The method according to claim 1, characterized in that The method further comprises: Receiving semantic conversion capability information of the sending end, where the semantic conversion capability information is used to indicate a semantic coding model and / or a semantic coding knowledge base supported by the sending end; The semantic conversion mode information is determined according to the semantic conversion capability information of the sending end, wherein the semantic conversion model matches the semantic encoding model supported by the sending end, and the semantic conversion knowledge base matches the semantic encoding knowledge base supported by the sending end.

3. The method according to claim 1, characterized in that: The method further comprises: The semantic conversion mode information is determined according to a quality of service requirement of semantic communication between the sending end and the receiving end, where the quality of service requirement of semantic communication includes any one or more of the following: Semantic decoding accuracy, semantic similarity, semantic clarity, guaranteed bit rate, packet transmission delay budget, or packet error rate.

4. The method according to any one of claims 1 to 3, characterized in that The semantic conversion model includes: a semantic conversion encoding model and a semantic conversion decoding model. The semantic conversion knowledge base includes: a semantic conversion encoding knowledge base and a semantic conversion decoding knowledge base.

5. The method according to claim 4, characterized in that The semantic conversion mode information includes any one or more of the following information: The information of the semantic conversion model, the information of the semantic conversion knowledge base, the information of the semantic conversion encoding model, the information of the semantic conversion encoding knowledge base, the information of the semantic conversion decoding model, or the information of the semantic conversion decoding knowledge base.

6. The method according to any one of claims 2 to 5, characterized in that: The semantic conversion capability information includes any one or more of the following: The type information of the semantic coding model, the size of the semantic coding model, the identification information of the semantic coding model, the type information of the semantic coding knowledge base, the size of the semantic coding knowledge base, or the identification information of the semantic coding knowledge base.

7. A semantic communication method, characterized in that: The method is applied to an intermediate device, and the method comprises: Receiving semantic conversion mode information sent by a core network device, where the semantic conversion mode information is used to indicate a semantic conversion model and / or a semantic conversion knowledge base used by the intermediate device; Determining the semantic conversion model and / or the semantic conversion knowledge base according to the semantic conversion mode information; Receiving first coded data sent by a sending end, where the first coded data is data obtained by encoding by the sending end using a semantic coding model and / or a semantic coding knowledge base; Processing the first coded data using the semantic conversion model and the semantic conversion knowledge base to obtain second coded data; The second encoded data is sent to a receiving end.

8. The method according to claim 7, characterized in that The semantic conversion model includes: a semantic conversion encoding model and a semantic conversion decoding model. The semantic conversion knowledge base includes: a semantic conversion encoding knowledge base and a semantic conversion decoding knowledge base.

9. The method according to claim 8, characterized in that The semantic conversion mode information includes any one or more of the following information: The information of the semantic conversion model, the information of the semantic conversion knowledge base, the information of the semantic conversion encoding model, the information of the semantic conversion encoding knowledge base, the information of the semantic conversion decoding model, or the information of the semantic conversion decoding knowledge base.

10. The method according to claim 8 or 9, characterized in that: The first coded data is processed using the semantic conversion model and the semantic conversion knowledge base to obtain the second coded data, including: Using the semantic conversion decoding model and the semantic conversion decoding knowledge base to decode the first encoded data to generate intermediate data; The intermediate data is encoded using the semantic transformation encoding model and the semantic transformation encoding knowledge base to generate the second encoded data.

11. The method according to claim 8 or 9, characterized in that: The intermediate device includes a first intermediate device and a second intermediate device, wherein the first intermediate device provides services for the sending end, and the second intermediate device provides services for the receiving end, and the semantic conversion model and the semantic conversion knowledge base are used to process the first coded data to obtain the second coded data, including: The first intermediate device uses the semantic conversion decoding model and the semantic conversion decoding knowledge base to decode the first encoded data to generate intermediate data; The first intermediate device sends the intermediate data to the second intermediate device; The second intermediate device uses the semantic conversion coding model and the semantic conversion coding knowledge base to encode the intermediate data to generate the second encoded data; Sending the second coded data to the receiving end includes: The second intermediate device sends the second encoded data to the receiving end.

12. A semantic communication method, characterized in that: The method is applied to a transmitting end, and the method comprises: Receiving semantic conversion mode information sent by a core network device, wherein the semantic conversion mode information is used to indicate a semantic conversion model and / or a semantic conversion knowledge base used by an intermediate device, wherein the intermediate device is used to forward the encoded data of the sending end to the receiving end; Determine a semantic encoding model and / or a semantic encoding knowledge base according to the semantic conversion mode information, wherein the semantic encoding model matches the semantic conversion model, and the semantic encoding knowledge base matches the semantic conversion knowledge base; Using the semantic encoding knowledge base and the semantic encoding knowledge base to encode the source data to generate first encoded data; The first encoded data is sent to the intermediate device.

13. The method according to claim 12, characterized in that The method further comprises: The semantic conversion capability information is sent to the core network device, where the semantic conversion capability information is used to indicate the semantic coding model and / or semantic coding knowledge base supported by the sending end.

14. The method according to claim 13, characterized in that The semantic conversion capability information includes any one or more of the following: The type information of the semantic coding model, the size of the semantic coding model, the identification information of the semantic coding model, the type information of the semantic coding knowledge base, the size of the semantic coding knowledge base, or the identification information of the semantic coding knowledge base.

15. A semantic communication method, characterized in that: The method is applied to a receiving end, and the method comprises: Receiving semantic conversion mode information sent by a core network device, wherein the semantic conversion mode information is used to indicate a semantic conversion model and / or a semantic conversion knowledge base used by an intermediate device, wherein the intermediate device is used to forward the encoded data of the sending end to the receiving end; Determine a semantic decoding model and / or a semantic decoding knowledge base according to the semantic conversion mode information, wherein the semantic decoding model matches the semantic conversion model, and the semantic decoding knowledge base matches the semantic conversion knowledge base; Receiving second encoded data sent by the intermediate device; The second encoded data is decoded using the semantic decoding knowledge base and the semantic decoding knowledge base to generate target data.

16. The method according to claim 15, characterized in that The semantic conversion mode information includes any one or more of the following information: The information of the semantic conversion model, the information of the semantic conversion knowledge base, the information of the semantic conversion encoding model, the information of the semantic conversion encoding knowledge base, the information of the semantic conversion decoding model, or the information of the semantic conversion decoding knowledge base.

17. A communication device, characterized in that: Including communication interface and processor: The communication interface is used to input and / or output signaling or data; The processor is used to execute a computer executable program so that the method described in any one of claims 1 to 6 is executed, or the method described in any one of claims 7 to 11 is executed, or the method described in any one of claims 12 to 14 is executed, or the method described in any one of claims 15 to 16 is executed.

18. A communication device, characterized in that: including a processor and memory, The memory is used to store computer programs or instructions; The processor is used to execute the computer program or instructions in the memory, so that the method described in any one of claims 1 to 6 is executed, or the method described in any one of claims 7 to 11 is executed, or the method described in any one of claims 12 to 14 is executed, or the method described in any one of claims 15 to 16 is executed.

19. A computer-readable storage medium comprising instructions, characterized in that: When the instructions are executed by a processor, the method of any one of claims 1-6, or claims 7-11, or claims 12-14, or claims 15-16 is implemented.

20. A computer program product comprising a program, characterized in that When the program is executed by a processor, the method of any one of claims 1-6, or claims 7-11, or claims 12-14, or claims 15-16 is implemented.

21. A chip system, characterized in that: The chip system includes at least one processor, and when the program instructions are executed in the at least one processor, the method described in any one of claims 1-6, or claims 7-11, or claims 12-14, or claims 15-16 is implemented.

22. A communication system, characterized in that: It includes a communication device for executing the method described in any one of claims 1 to 6, a communication device for executing the method described in any one of claims 7 to 11, a communication device for executing the method described in any one of claims 12 to 14, and a communication device for executing the method described in any one of claims 15 to 16.

Images