Communication method and apparatus, and storage medium and program product

Abstract

The present application relates to the technical field of communications. Disclosed are a communication method and apparatus, and a storage medium and a program product. The method comprises: a first terminal sending first encoded data to a network device, wherein the first encoded data is obtained by means of encoding first pilot data on the basis of a first encoding model, and the first encoding model corresponds to a first task; the network device sending first information to the first terminal, wherein the first information indicates a first time-frequency resource; and the first terminal sending second encoded data to the network device, wherein the first time-frequency resource is used for mapping the second encoded data, and the second encoded data is obtained by means of encoding first communication data on the basis of the first encoding model. On the basis of first encoded data, a network device may accurately determine the performance of a first encoding model under the influence of wireless transmission, and indicate a first time-frequency resource, and second encoded data that a terminal subsequently obtains by means of encoding first communication data on the basis of the first encoding model is mapped onto the first time-frequency resource, thereby improving the communication reliability.

Description

Communication methods, devices, storage media and software products

[0001] This application claims priority to Chinese Patent Application No. 202411725188.6, filed on November 27, 2024, entitled "Communication Method, Apparatus, Storage Medium and Program Product", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of communication technology, and in particular to a communication method, apparatus, storage medium, and program product. Background Technology

[0003] Applying artificial intelligence (AI) to communication systems, and using AI models to intelligently analyze and process data, can improve network performance and user experience.

[0004] When deploying AI encoding / decoding models in practical wireless communication systems, different models have varying requirements for the transmission quality of the transmitter's encoding to ensure the decoding performance of the receiver. Therefore, how to more accurately determine the performance of AI models under the influence of wireless transmission has become an urgent problem to be solved. Summary of the Invention

[0005] This application provides a communication method, apparatus, storage medium, and program product to accurately determine the performance of an encoding / decoding model (AI model) under the influence of wireless transmission.

[0006] In a first aspect, embodiments of this application provide a communication method that can be applied to a terminal side, such as a terminal or a communication module / processing module within a terminal, or a circuit or chip in the terminal responsible for communication functions (such as a modem chip, also known as a baseband chip, or a system-on-a-chip (SoC) chip containing a modem core, or a system-in-package (SIP) chip), or a circuit or chip in the terminal responsible for processing functions (such as a graphics processing unit (GPU), an AI processor, or an application-specific integrated circuit (ASIC)). Taking the application of this method to a terminal as an example, in this method, a first terminal sends first coded data, which is obtained by encoding first pilot data based on a first encoding model, the first encoding model corresponding to a first task; receives first information, which indicates first time-frequency resources; and sends second coded data, where the first time-frequency resources are used to map the second coded data, and the second coded data is obtained by encoding first communication data based on the first encoding model.

[0007] Using the above method, the terminal sends first coded data obtained by encoding the first pilot data based on the first coding model, so that the network device can accurately determine the performance of the first coding model under the influence of wireless transmission based on the first coded data and indicate the first time-frequency resource. Subsequently, the terminal maps the second coded data obtained by encoding the first communication data based on the first coding model onto the first time-frequency resource, thereby improving the reliability of communication.

[0008] In one possible design, the aforementioned first information also indicates a first coding model.

[0009] With this design, the network device also instructs the first terminal on the first encoding model, that is, the first encoding model is associated with the first time-frequency resource, so that when the first terminal transmits the first communication data on the first time-frequency resource, it uses the first encoding model to encode the first communication data to reduce interference between users.

[0010] In another possible design, the method further includes: a first terminal sending second information indicating at least one of the following: an identifier of a first coding model, and tag information corresponding to the first pilot data.

[0011] With this design, the first terminal notifies the network device of its first coding model and / or tag information corresponding to the first pilot data, so that the network device can accurately determine the performance of the first coding model under the influence of wireless transmission.

[0012] In another possible design, the method further includes: a first terminal receiving third information; sending first encoded data, including: sending the first encoded data based on the third information.

[0013] With this design, the first terminal, triggered by receiving third information from the network device, sends first encoded data obtained by encoding the first pilot data based on the first encoding model, so that the network device can accurately determine the performance of the first encoding model under the influence of wireless transmission based on the first encoded data.

[0014] In another possible design, the aforementioned first time-frequency resource is also used to map the encoded data of at least one second terminal.

[0015] With this design, network devices can accurately determine the performance of the first coding model under the influence of wireless transmission based on the first coding data, enabling the first terminal and at least one second terminal to reuse the first time-frequency resources, thereby improving resource utilization.

[0016] Secondly, this method can be applied to the network side, such as access network devices, modules (e.g., circuits, chips, or chip systems) within the access network devices, circuits or chips responsible for processing functions within the access network devices (e.g., GPUs, AI processors, or ASICs), or logical nodes, logical modules, or software that can implement all or part of the functions of the access network devices. Taking the application of this method to an access network device as an example, in this method, the access network device receives first coded data from a first terminal, which is obtained by encoding first pilot data based on a first coding model; sends first information to the first terminal, which indicates first time-frequency resources; and receives second coded data from the first terminal, where the first time-frequency resources are used to map the second coded data, and the second coded data is obtained by encoding first communication data based on the first coding model.

[0017] Using the above method, the network device can receive first encoded data from the first terminal, which is obtained by encoding the first pilot data based on the first encoding model. Based on the first encoded data, the network device can determine the performance of the first encoding model under the influence of wireless transmission and indicate the first time-frequency resource. The second encoded data obtained by the subsequent terminal encoding the first communication data based on the first encoding model is then mapped onto the first time-frequency resource, thereby improving the reliability of communication.

[0018] In one possible design, the aforementioned first information also indicates a first coding model.

[0019] In another possible design, the method further includes: the access network device receiving second information from the first terminal, the second information indicating at least one of the following: an identifier of a first coding model, tag information corresponding to the first pilot data; obtaining a first decoding model corresponding to the identifier of the first coding model; decoding the first coded data based on the first decoding model to obtain a first decoding result; determining the decoding performance corresponding to the first coded data based on the first decoding result and the tag information; and determining a first time-frequency resource based on the decoding performance corresponding to the first coded data.

[0020] In another possible design, the method further includes: the access network device sending third information to the first terminal; receiving first encoded data from the first terminal, including: the access network device receiving the first encoded data from the first terminal based on the third information.

[0021] In another possible design, the aforementioned first time-frequency resource is also used to map the encoded data of at least one second terminal.

[0022] Thirdly, embodiments of this application provide a communication method that can be applied to a terminal side, such as a terminal or a communication module / processing module in the terminal, or a circuit or chip in the terminal responsible for communication functions (such as a modem chip, also known as a baseband chip, or a SoC chip or SIP chip containing a modem core, or a circuit or chip in the terminal responsible for processing functions (such as a GPU, AI processor, or ASIC)). Taking the application of this method to a terminal as an example, in this method, a third terminal decodes the first data based on a second decoding model to obtain a second decoding result, the second decoding model corresponding to a second task; sends a fourth message based on the second decoding result, the fourth message indicating the decoding performance corresponding to the first data, the decoding performance corresponding to the first data being used to determine the second time-frequency resources; receives a fifth message, the fifth message indicating the second time-frequency resources; and receives second data, the second time-frequency resources being used to map the second data.

[0023] Using this method, the third terminal decodes the first data based on the second decoding model to obtain the second decoding result, and indicates the decoding performance corresponding to the first data to the network device based on the second decoding result. This allows the network device to determine the performance of the second decoding model under the influence of wireless transmission based on the decoding performance corresponding to the first data, and to indicate the second time-frequency resource. Subsequent terminals can then map the second data onto the second time-frequency resource, thereby improving the reliability of communication.

[0024] In one possible design, the aforementioned fifth piece of information also indicates a second decoding model.

[0025] With this design, the fifth information simultaneously indicates the second time-frequency resource and the second decoding model. There is a correlation between the second time-frequency resource and the second decoding model. When the network device schedules the second terminal to transmit data on the second time-frequency resource, it needs to use the second decoding model to decode the received data in order to ensure transmission performance in the wireless environment.

[0026] In another possible design, the method further includes: a third terminal sending a sixth message indicating the identifier of the second decoding model.

[0027] Using this design, different encoding / decoding models can perform different intelligent tasks, such as image classification and speech recognition, with each encoding / decoding model corresponding to a specific task. The third terminal indicates the second decoding model to the network device, which then selects the appropriate second encoding model for encoding.

[0028] In another possible design, the method further includes: a third terminal receiving seventh information indicating tag information corresponding to the first data, the tag information corresponding to the first data being used to determine the second decoding result.

[0029] In another possible design, the aforementioned second time-frequency resource is also used to map data from at least one fourth terminal.

[0030] Using this design, the network device can also schedule at least one fourth terminal to receive second data on the same time-frequency resource as the third terminal, and obtain the decoding performance of the third terminal and at least one fourth terminal based on their respective decoding results. If the decoding performance of the third terminal and at least one fourth terminal both meet the performance indicators, or if the weighted sum of their decoding performance meets the performance indicators, then the network device can configure the second time-frequency resource for both the third terminal and at least one fourth terminal (this second time-frequency resource is also used to map the data of at least one fourth terminal), that is, schedule the third terminal and at least one fourth terminal to transmit subsequent communication data on the same time-frequency resource.

[0031] Fourthly, this method can be applied to the network side, such as access network devices, modules (e.g., circuits, chips, or chip systems) within the access network devices, circuits or chips responsible for processing functions within the access network devices (e.g., GPUs, AI processors, or ASICs), or logical nodes, logical modules, or software capable of implementing all or part of the functions of the access network devices. Taking the application of this method to an access network device as an example, in this method, the access network device receives fourth information from a third terminal, which indicates the decoding performance corresponding to the first data; determines a second time-frequency resource based on the decoding performance corresponding to the first data; sends fifth information to the third terminal, which indicates the second time-frequency resource; and sends second data to the third terminal, whereby the second time-frequency resource is used to map the second data.

[0032] Using this method, the network device receives the decoding performance corresponding to the first data sent by the third terminal, enabling the network device to determine the performance of the second decoding model under the influence of wireless transmission based on the decoding performance corresponding to the first data, and to indicate the second time-frequency resource. Subsequent terminals can then map the second data onto the second time-frequency resource, thereby improving the reliability of communication.

[0033] In one possible design, the aforementioned fifth piece of information also indicates a second decoding model.

[0034] In another possible design, the method further includes: the access network device receiving sixth information from the first terminal, the sixth information indicating the identifier of the second decoding model.

[0035] In another possible design, the method further includes: the access network device sending a seventh message to the first terminal, the seventh message indicating tag information corresponding to the first data.

[0036] In another possible design, the aforementioned second time-frequency resource is also used to map data from at least one fourth terminal.

[0037] Fifthly, this application provides a communication device that has the functions of the first aspect described above. For example, the communication device includes modules, units, or means that perform the operations involved in the first aspect. These modules, units, or means can be implemented by software, hardware, or a combination of software and hardware.

[0038] For example, the communication device includes a communication unit, and may further include a processing unit and a storage unit; wherein:

[0039] The communication unit is configured to transmit first coded data, which is obtained by encoding first pilot data based on a first coding model, the first coding model corresponding to a first task; the communication unit is also configured to receive first information, which indicates a first time-frequency resource; and the communication unit is also configured to transmit second coded data, which is obtained by encoding first communication data based on the first coding model.

[0040] In one possible design, the aforementioned first information also indicates a first coding model.

[0041] In another possible design, the communication unit is also used to transmit second information indicating at least one of the following: an identifier of the first coding model, and tag information corresponding to the first pilot data.

[0042] In another possible design, the communication unit is also used to receive third information; and the communication unit is also used to send first coded data based on the third information.

[0043] In another possible design, the aforementioned first time-frequency resource is also used to map the encoded data of at least one second terminal.

[0044] Sixthly, this application provides a communication device that has the functions of the second aspect above. For example, the communication device includes a module, unit, or means for performing the operations involved in the second aspect above. The module, unit, or means can be implemented by software, hardware, or a combination of software and hardware.

[0045] For example, the communication device includes a communication unit, and may further include a processing unit and a storage unit; wherein:

[0046] The communication unit is configured to receive first coded data from a first terminal, the first coded data being obtained by encoding first pilot data based on a first coded model; the communication unit is also configured to send first information to the first terminal, the first information indicating first time-frequency resources; and the communication unit is also configured to receive second coded data from the first terminal, the first time-frequency resources being used to map the second coded data, and the second coded data being obtained by encoding first communication data based on the first coded model.

[0047] In one possible design, the aforementioned first information also indicates a first coding model.

[0048] In another possible design, the communication unit is further configured to receive second information from the first terminal, the second information indicating at least one of the following: an identifier of a first encoding model, and tag information corresponding to the first pilot data; the processing unit is configured to acquire a first decoding model corresponding to the identifier of the first encoding model; the processing unit is further configured to decode the first encoded data based on the first decoding model to obtain a first decoding result; the processing unit is further configured to determine the decoding performance corresponding to the first encoded data based on the first decoding result and the tag information; and the processing unit is further configured to determine a first time-frequency resource based on the decoding performance corresponding to the first encoded data.

[0049] In another possible design, the communication unit is also used to send third information to the first terminal; and the communication unit is also used to receive first coded data from the first terminal based on the third information.

[0050] In another possible design, the aforementioned first time-frequency resource is also used to map the encoded data of at least one second terminal.

[0051] Seventhly, this application provides a communication device that has the functions of the third aspect above. For example, the communication device includes a module, unit, or means for performing the operations involved in the third aspect above. The module, unit, or means can be implemented by software, hardware, or a combination of software and hardware.

[0052] For example, the communication device includes a communication unit, and may further include a processing unit and a storage unit; wherein:

[0053] The processing unit is configured to decode the first data based on the second decoding model to obtain a second decoding result, wherein the second decoding model corresponds to the second task; the communication unit is configured to send fourth information based on the second decoding result, wherein the fourth information indicates the decoding performance corresponding to the first data, and the decoding performance corresponding to the first data is used to determine the second time-frequency resources; the communication unit is also configured to receive fifth information, wherein the fifth information indicates the second time-frequency resources; and the communication unit is also configured to receive second data, wherein the second time-frequency resources are used to map the second data.

[0054] In one possible design, the aforementioned fifth piece of information also indicates a second decoding model.

[0055] In another possible design, the communication unit is also used to send a sixth message that indicates the identifier of the second decoding model.

[0056] In another possible design, the communication unit is also used to receive seventh information, which indicates tag information corresponding to the first data, and the tag information corresponding to the first data is used to determine the second decoding result.

[0057] In another possible design, the aforementioned second time-frequency resource is also used to map data from at least one fourth terminal.

[0058] Eighthly, this application provides a communication device that has the functions of the fourth aspect above. For example, the communication device includes a module, unit, or means for performing the operations involved in the fourth aspect above. The module, unit, or means can be implemented by software, hardware, or a combination of software and hardware.

[0059] For example, the communication device includes a communication unit, and may further include a processing unit and a storage unit; wherein:

[0060] The communication unit is configured to receive fourth information from a third terminal, the fourth information indicating the decoding performance corresponding to the first data; the processing unit is configured to determine a second time-frequency resource based on the decoding performance corresponding to the first data; the communication unit is further configured to send fifth information to the third terminal, the fifth information indicating the second time-frequency resource; and the communication unit is further configured to send second data to the third terminal, the second time-frequency resource being used to map the second data.

[0061] In one possible design, the aforementioned fifth piece of information also indicates a second decoding model.

[0062] In another possible design, the communication unit is also used to receive sixth information from the first terminal, which indicates the identifier of the second decoding model.

[0063] In another possible design, the communication unit is also used to send a seventh message to the first terminal, the seventh message indicating the tag information corresponding to the first data.

[0064] In another possible design, the aforementioned second time-frequency resource is also used to map data from at least one fourth terminal.

[0065] Ninthly, this application provides a communication device including an interface circuit and one or more processors. The one or more processors are coupled to a memory. The memory stores part or all of the computer program or instructions necessary to implement the functions described in the first aspect above. The one or more processors are executable to carry out the computer program or instructions, causing the communication device to implement the methods in any possible design or implementation of the first aspect above. The interface circuit is used to implement the communication functions within the communication device and / or the communication functions between the communication device and other devices or components.

[0066] In one possible design, the processor is used to communicate with other devices or components through the interface circuit.

[0067] In one possible design, the communication device may also include the memory.

[0068] The aforementioned communication device may be a terminal, or a communication / processing module in the terminal, or a chip in the terminal responsible for communication functions such as a modem chip (also known as a baseband chip) or a SoC or SIP chip containing a modem module, or a circuit or chip in the terminal responsible for processing functions (such as a GPU, AI processor, or ASIC).

[0069] Tenthly, this application provides a communication device including an interface circuit and one or more processors. The one or more processors are coupled to a memory. The memory stores part or all of the necessary computer program or instructions for implementing the functions described in the second aspect above. The one or more processors are executable to carry out the computer program or instructions, causing the communication device to implement the methods in any possible design or implementation of the second aspect above. The interface circuit is used to implement the communication functions within the communication device and / or the communication functions between the communication device and other devices or components.

[0070] In one possible design, the processor is used to communicate with other devices or components through the interface circuit.

[0071] In one possible design, the communication device may also include the memory.

[0072] The aforementioned communication device may be an access network device, a module (e.g., a circuit, chip, or chip system) in the access network device, a circuit or chip (e.g., a GPU, AI processor, or ASIC) in the access network device responsible for processing functions, or a logical node, logical module, or software that can implement all or part of the functions of the access network device.

[0073] Eleventhly, this application provides a communication device including an interface circuit and one or more processors. The one or more processors are coupled to a memory. The memory stores part or all of the necessary computer program or instructions for implementing the functions described in the third aspect above. The one or more processors can execute the computer program or instructions, causing the communication device to implement the methods in any possible design or implementation of the first aspect above when executed. The interface circuit is used to implement the communication functions within the communication device and / or the communication functions between the communication device and other devices or components.

[0074] In one possible design, the processor is used to communicate with other devices or components through the interface circuit.

[0075] In one possible design, the communication device may also include the memory.

[0076] The aforementioned communication device may be a terminal, or a communication / processing module in the terminal, or a chip in the terminal responsible for communication functions such as a modem chip (also known as a baseband chip) or a SoC or SIP chip containing a modem module, or a circuit or chip in the terminal responsible for processing functions (such as a GPU, AI processor, or ASIC).

[0077] In a twelfth aspect, this application provides a communication device including an interface circuit and one or more processors. The one or more processors are coupled to a memory. The memory stores part or all of a computer program or instructions necessary for implementing the functions described in the fourth aspect above. The one or more processors are executable to carry out the computer program or instructions, causing the communication device to implement any possible design or implementation method described in the second aspect above. The interface circuit is used to implement communication functions within the communication device and / or communication functions between the communication device and other devices or components.

[0078] In one possible design, the processor is used to communicate with other devices or components through the interface circuit.

[0079] In one possible design, the communication device may also include the memory.

[0080] The aforementioned communication device may be an access network device, a module (e.g., a circuit, chip, or chip system) in the access network device, a circuit or chip (e.g., a GPU, AI processor, or ASIC) in the access network device responsible for processing functions, or a logical node, logical module, or software that can implement all or part of the functions of the access network device.

[0081] In a thirteenth aspect, this application provides a communication system, including a communication device in the fifth aspect or any of the designs in the fifth aspect, and a communication device in the sixth aspect or any of the designs in the sixth aspect.

[0082] In a fourteenth aspect, this application provides a communication system, including a communication device in the seventh aspect or any of the designs in the seventh aspect, and a communication device in the eighth aspect or any of the designs in the eighth aspect.

[0083] In a fifteenth aspect, this application provides a computer-readable storage medium storing computer-readable instructions that, when read and executed by a computer, cause the computer to perform any of the possible designs in the first to fourth aspects described above.

[0084] In a sixteenth aspect, this application provides a computer program product that, when read and executed by a computer, causes the computer to perform any of the possible designs in the first to fourth aspects described above.

[0085] The beneficial effects of the above-mentioned aspects or various designs can be found in the descriptions of the corresponding sections above. Attached Figure Description

[0086] Figure 1 is a schematic diagram of a possible, non-limiting system;

[0087] Figures 2 and 3 are schematic diagrams of possible application frameworks in a communication system;

[0088] Figures 4, 7, 8, and 10–12 are schematic flowcharts of the communication method provided in the embodiments of this application;

[0089] Figure 5 is a schematic diagram of the semantic communication system;

[0090] Figure 6 is a schematic diagram of the uplink transmission process of modular multiplexing;

[0091] Figure 9 is a schematic diagram showing the correspondence between the encoding / decoding model and the task in an example of an embodiment of this application;

[0092] Figure 13 is a possible exemplary block diagram of the communication device involved in the embodiments of this application;

[0093] Figure 14 is a schematic diagram of the structure of a terminal provided in an embodiment of this application. Detailed Implementation

[0094] Figure 1 illustrates a possible, non-limiting system diagram. As shown in Figure 1, the communication system 10 includes a radio access network (RAN) 100 and a core network (CN) 200. RAN 100 includes at least one RAN node (110a and 110b in Figure 1, collectively referred to as 110) and at least one terminal (120a-120j in Figure 1, collectively referred to as 120). RAN 100 may also include other RAN nodes, such as wireless relay devices and / or wireless backhaul devices (not shown in Figure 1). Terminal 120 is wirelessly connected to RAN node 110. RAN node 110 is connected to core network 200 wirelessly or via wired connection. The core network equipment in core network 200 and RAN node 110 in RAN 100 can be different physical devices, or they can be the same physical device integrating core network logical functions and radio access network logical functions. RAN 100 and core network 200 can also be connected to the Internet 300.

[0095] RAN100 can be used for the third-generation partner program (3 rd Cellular systems related to the Generation Partnership Project (3GPP), such as fourth-generation (4G) cellular systems. th generation, 4G), fifth generation (5G) th RAN 100 can be a generation (5G) mobile communication system, or a future-oriented evolution system. It can also be an open RAN (O-RAN or ORAN), a cloud radio access network (CRAN), an artificial intelligence radio access network (AI RAN), or a wireless fidelity (WiFi) system. RAN 100 can also be a communication system that integrates two or more of the above systems.

[0096] RAN node 110, sometimes also referred to as access network equipment, RAN entity, or access node, constitutes part of the communication system and is used to help terminals achieve wireless access. Multiple RAN nodes 110 in communication system 10 can be of the same type or different types. In some scenarios, the roles of RAN node 110 and terminal 120 are relative. For example, network element 120i in Figure 1 can be a helicopter or drone, which can be configured as a mobile base station. For terminals 120j accessing RAN 100 through network element 120i, network element 120i is a base station; but for base station 110a, network element 120i is a terminal. RAN node 110 and terminal 120 are sometimes both referred to as communication devices. For example, network elements 110a and 110b in Figure 1 can be understood as communication devices with base station functions, and network elements 120a-120j can be understood as communication devices with terminal functions.

[0097] In one possible scenario, the RAN node can be a base station, an evolved NodeB (eNodeB), an access point (AP), a transmission reception point (TRP), a next-generation NodeB (gNB), a base station in a future mobile communication system, or an access node in a WiFi system. The RAN node can be a macro base station (as shown in Figure 1, 110a), a micro base station or indoor station (as shown in Figure 1, 110b), a relay node or donor node, or a radio controller in a CRAN scenario. Optionally, the RAN node can also be a server, wearable device, vehicle, or in-vehicle equipment. For example, the access network equipment in vehicle-to-everything (V2X) technology can be a roadside unit (RSU). All or part of the functions of the RAN node in this application can also be implemented through software functions running on hardware, or through virtualization functions instantiated on a platform (e.g., a cloud platform). The RAN node can also be equipped with communication modules, circuits, or chips that perform corresponding communication functions. The RAN node can also be configured with program instructions for performing corresponding communication functions, as well as corresponding program instructions. The RAN node in this application can also be a logical node, logical module, or software capable of implementing all or part of the RAN node's functions.

[0098] In another possible scenario, multiple RAN nodes collaborate to assist the terminal in achieving wireless access, with different RAN nodes each implementing a portion of the base station's functions. For example, RAN nodes can be centralized units (CUs), distributed units (DUs), CU-control plane (CPs), CU-user plane (UPs), or radio units (RUs), etc. CUs and DUs can be set up separately or included in the same network element, such as a baseband unit (BBU). RUs can be included in radio frequency equipment or radio frequency units, such as remote radio units (RRUs), active antenna units (AAUs), or remote radio heads (RRHs).

[0099] In different systems, CU (or CU-CP and CU-UP), DU, or RU may have different names, but those skilled in the art will understand their meaning. For example, in an ORAN system, CU can also be called O-CU (open CU), DU can also be called O-DU, CU-CP can also be called O-CU-CP, CU-UP can also be called O-CU-UP, and RU can also be called O-RU. For ease of description, this application uses CU, CU-CP, CU-UP, DU, and RU as examples. Any of the units among CU (or CU-CP, CU-UP), DU, and RU in this application can be implemented through software modules, hardware modules, or a combination of software and hardware modules.

[0100] A terminal can be a device or module that accesses the aforementioned communication system and has corresponding communication functions. A terminal can also be called a terminal device, user equipment (UE), mobile station, mobile terminal, etc. Terminals can be widely used in various scenarios, such as device-to-device (D2D), vehicle-to-everything (V2X) communication, machine-type communication (MTC), Internet of Things (IoT), virtual reality, augmented reality, industrial control, autonomous driving, telemedicine, smart grids, smart furniture, smart offices, smart wearables, smart transportation, smart cities, etc. Terminals can be mobile phones, tablets, computers with wireless transceiver capabilities, wearable devices, vehicles, drones, helicopters, airplanes, ships, robots, robotic arms, smart home devices, transportation vehicles with wireless communication capabilities, communication modules, etc. The embodiments of this application do not limit the device form of the terminal. A terminal typically contains a communication module, circuit, or chip that performs the corresponding communication function. The terminal can also be configured with program instructions for performing the corresponding communication function.

[0101] To support AI technology in wireless networks, AI nodes may also be introduced into the network.

[0102] AI nodes can be deployed in one or more of the following locations within the communication system: access network nodes (RAN nodes), terminals, or core network equipment. Alternatively, AI nodes can be deployed independently, for example, in a location other than any of the above-mentioned devices, such as in the host or cloud server of an over-the-top (OTT) system. AI nodes can communicate with other devices in the communication system, which can be one or more of the following: network devices, terminals, or core network elements.

[0103] It is understood that this application does not limit the number of AI nodes. For example, when there are multiple AI nodes, these nodes can be divided based on function, such as different AI nodes being responsible for different functions.

[0104] It can also be understood that AI nodes can be independent devices, or they can be integrated into the same device to achieve different functions. Alternatively, they can be network elements in hardware devices, software functions running on dedicated hardware, or virtualization functions instantiated on a platform (e.g., a cloud platform). This application does not limit the specific form of the aforementioned AI nodes.

[0105] AI nodes can be AI network elements or AI modules.

[0106] Figure 2 illustrates a possible application framework in a communication system. As shown in Figure 2, network elements in the communication system are connected via interfaces (e.g., NG, Xn) or air interfaces. These network element nodes, such as core network equipment, access network nodes (RAN nodes), terminals, or one or more devices in operations administration and maintenance (OAM), are equipped with one or more AI modules (only one is shown in Figure 2 for clarity). An access network node can be a single RAN node or can include multiple RAN nodes, for example, including CUs and DUs. The CUs and / or DUs can also be equipped with one or more AI modules. A CU can also be split into CU-CPs and CU-UPs, with one or more AI modules configured in the CU-CP and / or CU-UP.

[0107] AI modules are used to implement corresponding AI functions. AI modules deployed in different network elements can be the same or different. The models of AI modules can achieve different functions depending on the parameter configurations. The models of AI modules can be configured based on one or more of the following parameters: structural parameters (e.g., at least one of the following: number of neural network layers, neural network width, inter-layer connections, neuron weights, neuron activation function, or biases in the activation function), input parameters (e.g., the type and / or dimension of the input parameters), or output parameters (e.g., the type and / or dimension of the output parameters). The biases in the activation function can also be referred to as the biases of the neural network.

[0108] In one example, the neural network mentioned above can be a deep neural network (DNN), a convolutional neural network (CNN), a recurrent neural network (RNN), or a generative adversarial network (GAN).

[0109] Deep Neural Networks (DNNs) are artificial neural network architectures with multiple layers of nonlinear transformation units stacked in a hierarchical structure to form deep computational models. Compared to shallow neural networks, deep neural networks have more hidden layers, allowing the network model to capture more complex data structures and higher-level abstract features.

[0110] A CNN is a deep neural network with a convolutional structure. A CNN contains a feature extractor consisting of convolutional layers and subsampling layers. This feature extractor can be viewed as a filter, and the convolution process can be seen as performing convolution between a trainable filter and an input image or a convolutional feature map.

[0111] RNN is a type of recursive neural network that takes sequence data as input, recursively moves along the direction of sequence evolution, and connects all nodes (recurrent units) in a chain-like manner.

[0112] GAN is a deep learning model. It consists of a generator and a discriminator, and is trained through adversarial learning. Its purpose is to estimate the potential distribution of data samples and generate new data samples.

[0113] An AI module can have one or more models. A model can infer an output, which includes one or more parameters. The learning, training, or inference processes of different models can be deployed on different nodes or devices, or they can be deployed on the same node or device.

[0114] Figure 3 illustrates another possible application framework in a communication system. As shown in Figure 3, the communication system includes a RAN intelligent controller (RIC). For example, the RIC can be the AI ​​module shown in Figure 2, used to implement AI-related functions. RICs include near-real-time RICs (near-RT RICs) and non-real-time RICs (non-RT RICs). Non-real-time RICs primarily process non-real-time information, such as data that is not sensitive to latency, with latency in the order of seconds. Real-time RICs primarily process near-real-time information, such as data that is relatively sensitive to latency, with latency in the order of tens of milliseconds.

[0115] Near real-time (NRT) RICs are used for model training and inference. For example, they are used to train AI models and then use those models for inference. NRT RICs can obtain network-side and / or terminal-side information from RAN nodes (e.g., CUs, CU-CPs, CU-UPs, DUs, and / or RUs) and / or terminals. This information can be used as training data or inference data. NRT RICs can deliver inference results to RAN nodes and / or terminals. Inference results can be exchanged between CUs and DUs, and / or between DUs and RUs. For example, a NRT RIC delivers an inference result to a DU, which then forwards it to an RU.

[0116] Non-real-time RICs are also used for model training and inference. For example, they are used to train AI models and then use those models for inference. Non-real-time RICs can obtain network-side and / or terminal-side information from RAN nodes (e.g., CUs, CU-CPs, CU-UPs, DUs, and / or RUs) and / or terminals. This information can be used as training data or inference data, and the inference results can be delivered to RAN nodes and / or terminals. Inference results can be exchanged between CUs and DUs, and / or between DUs and RUs; for example, a non-real-time RIC delivers inference results to a DU, which then forwards them to an RU.

[0117] Near real-time RICs and non-real-time RICs can also be configured as separate network elements. Near real-time RICs and non-real-time RICs can also be part of other devices. For example, near real-time RICs can be set in RAN nodes (e.g., CU, DU), while non-real-time RICs can be set in OAM, cloud servers, core network devices, or other network devices.

[0118] In recent years, with the continuous development of 5G mobile communication systems, data transmission latency has been continuously reduced and transmission capacity has been increasing. 5G communication systems have gradually penetrated into some multimedia services with strong real-time requirements and large data capacity requirements, such as video transmission, extended reality (XR), and autonomous driving.

[0119] With the rapid increase in communication transmission speeds, real-time video transmission services have gradually become one of the core services in current networks. For example, high-definition video calling services, represented by 5G New Voice, aim to leverage 5G's high speed, low latency, and high reliability to provide users with an extremely clear and smooth voice and video call experience. It also includes a series of enhanced functions such as real-time translation, screen sharing, and XR integration, greatly improving the user's call experience and enriching their interaction methods. In the future, 5G New Voice is expected to become a new communication service standard, serving not only individual users but also playing a crucial role in commercial applications such as telemedicine, online education, and emergency services. 5G New Voice services require communication systems to have the ability to simultaneously transmit high-definition video or XR data from a large number of users in real time, posing a significant challenge to system throughput.

[0120] For example, in autonomous driving, the aim is to achieve autonomous navigation and control of vehicles through onboard sensors, cameras, radar, and advanced AI algorithms, enabling them to drive safely on roads without direct human intervention. In the future, autonomous driving technology is expected to fundamentally change the way people travel, improve road safety, reduce traffic congestion, and provide passengers with a more convenient and comfortable travel experience. Furthermore, the development of autonomous driving technology may also have a profound impact on industries such as logistics, taxis, and public transportation, bringing about increased efficiency and reduced costs. In autonomous driving operations, due to regulatory and safety requirements, a large number of vehicles need to report real-time monitoring videos and operational status, which also demands that the communication system possess both massive connectivity and high-speed capabilities.

[0121] Therefore, in order to popularize and promote emerging multimedia services such as high-definition video calls and autonomous driving, how to make full use of limited time and frequency resources, maximize the throughput of communication systems, and achieve high-speed data transmission for multiple users has become a key research issue.

[0122] Applying AI to communication systems and using AI models to intelligently analyze and process data can improve network performance and user experience.

[0123] When deploying AI encoding / decoding models in practical wireless communication systems, different models have varying requirements for the transmission quality of the transmitter's encoding to ensure the decoding performance of the receiver. Therefore, how to more accurately determine the performance of AI models under the influence of wireless transmission has become an urgent problem to be solved.

[0124] In view of this, for uplink transmission, this application provides a communication scheme in which the terminal sends first encoded data obtained by encoding the first pilot data based on the first encoding model, so that the network device determines the performance of the first encoding model under the influence of wireless transmission based on the first encoded data and indicates the first time-frequency resource. Subsequently, the terminal maps the second encoded data obtained by encoding the first communication data based on the first encoding model onto the first time-frequency resource, thereby improving the reliability of communication.

[0125] The communication method and apparatus will be further described below with reference to the accompanying drawings. It is understood that this application uses network devices and terminals as examples of the entities executing the interaction, but this application does not limit the entities executing the interaction. For example, the method executed by the network device in this application can also be implemented by modules (e.g., circuits, chips, or chip systems) in the network device, circuits or chips responsible for processing functions in the network device (e.g., GPUs, AI processors, or ASICs), or logical nodes, logical modules, or software capable of implementing all or part of the network device's functions; similarly, the method executed by the terminal in this application can also be implemented by a communication / processing module in the terminal or circuits or chips responsible for communication / processing functions in the terminal (e.g., modem chips (also known as baseband chips), or SoC chips containing modem cores, or SIP chips, or GPUs, or AI processors, or ASICs).

[0126] Figure 4 shows a flowchart of a communication method provided in an embodiment of this application. Exemplarily, the method may include the following steps:

[0127] S401. The first terminal sends the first encoded data to the network device.

[0128] Accordingly, the network device receives the first encoded data.

[0129] In this embodiment, the network device needs to determine the performance of the first coding model under the influence of wireless transmission.

[0130] The first terminal device selects a set of task pilots (first pilot data) based on its own task type, which is a typical set of (data-label) pairs. For example, an image classification task selects several images with known categories, and a speech recognition task selects several audio segments with known text content.

[0131] The first terminal encodes the selected first pilot data based on the first coding model to obtain the first coded data. That is, the first coded data is obtained by encoding the first pilot data based on the first coding model.

[0132] The first encoding model corresponds to the first task. For example, encoding model 1 is selected for the image classification task, and encoding model 2 is selected for the speech recognition task.

[0133] After generating the first encoded data, the first terminal sends the first encoded data to the network device.

[0134] Furthermore, prior to step S401, the method further includes the following step: the network device sends third information to the first terminal. This third information is used to trigger or configure the first terminal to send first encoded data. The first terminal can then send the first encoded data based on the third information.

[0135] Further, prior to step S401, the method includes the following steps: the first terminal sends second information to the network device, the second information indicating at least one of the following: an identifier of a first encoding model, and tag information corresponding to the first pilot data. Different encoding / decoding models can perform different intelligent tasks, such as image classification and speech recognition, and the encoding / decoding models correspond to the tasks. The first terminal sends the identifier of the first encoding model to the network device, so that the network device can select the corresponding first decoding model for decoding. After selecting the first pilot data according to the first task, the first terminal sends the tag information corresponding to the first pilot data to the network device, so that the network device can obtain the first decoding performance corresponding to the first terminal. For example, the identifier of the first encoding model and the tag information corresponding to the first pilot data can also be predefined by the protocol, or configured to the network device through operation administration and maintenance (OAM) or other means.

[0136] S402. The network device sends the first information to the first terminal.

[0137] Accordingly, the first terminal receives the first information.

[0138] After receiving the first encoded data, the network device decodes the first encoded data using a first decoding model corresponding to the identifier of the first encoding model, obtaining a first decoding result. Then, the first decoding result is compared with the received tag information to obtain the first decoding performance corresponding to the first terminal. Different tasks have different decoding performances; for example, for image classification, the corresponding decoding performance is the image classification accuracy; for semantic recognition, the corresponding decoding performance is the semantic recognition accuracy; and for video restoration, the corresponding decoding performance is the mean opinion score (MOS) of the video restoration.

[0139] After obtaining the first decoding performance, if the network device achieves the performance indicators (e.g., the accuracy of image classification is higher than or equal to threshold 1, and the accuracy of semantic recognition is higher than or equal to threshold 2), it indicates that the performance of the data encoded by the first terminal using the first encoding model in the wireless environment meets the requirements (e.g., the interference from other terminals is within an acceptable range). Then, the network device generates first information. This first information indicates the first time-frequency resource. The network device then sends the aforementioned first information to the first terminal.

[0140] Furthermore, the first information also indicates a first encoding model. The first information simultaneously indicates a first time-frequency resource and a first encoding model. There is a correlation between the first time-frequency resource and the first encoding model. When the network device schedules the first terminal to transmit data on the first time-frequency resource, it needs to use the first encoding model to encode the data to be transmitted in order to ensure transmission performance in the wireless environment.

[0141] S403. The first terminal sends the second encoded data to the network device.

[0142] Accordingly, the network device receives the second encoded data.

[0143] After receiving the first information, the first terminal encodes the first communication data based on the first encoding model to obtain second encoded data (i.e., the second encoded data is obtained by encoding the first communication data based on the first encoding model), and sends the second encoded data to the network device. The first time-frequency resource is used to map the second encoded data.

[0144] Furthermore, the network device can also schedule at least one second terminal to transmit the first encoded data on the same time-frequency resource as the first terminal, and obtain the decoding performance of the first terminal and at least one second terminal based on their respective decoding results. If the decoding performance of the first terminal and at least one second terminal both reach the performance index, or if the weighted sum of the decoding performance of the first terminal and at least one second terminal reaches the performance index, then the network device can configure the first time-frequency resource for both the first terminal and at least one second terminal (the first time-frequency resource is also used to map the encoded data of at least one second terminal), that is, schedule the first terminal and at least one second terminal to transmit subsequent communication data on the same time-frequency resource, and indicate the corresponding encoding model to at least one second terminal.

[0145] According to an embodiment of this application, a communication method is provided in which a terminal sends first encoded data obtained by encoding first pilot data based on a first encoding model, so that a network device determines the performance of the first encoding model under the influence of wireless transmission based on the first encoded data and indicates a first time-frequency resource. Subsequently, the terminal maps second encoded data obtained by encoding first communication data based on the first encoding model onto the first time-frequency resource, thereby improving the reliability of communication.

[0146] Compared to traditional Shannon communication, semantic communication does not require precise recovery at the bit level, but rather pursues accurate semantic transmission, thus greatly improving communication efficiency. Figure 5 shows a general schematic diagram of a semantic communication system. Input data (e.g., image 1, about a woman wearing a hat) typically first passes through an AI-based semantic encoder (AI source encoder) to extract key semantic features (feature stream) relevant to the task. These features are then transmitted to the receiver via a wireless channel after channel coding, modulation, and other steps. Correspondingly, after demodulation and channel decoding at the receiver, a semantic decoder (AI source decoder) can execute intelligent tasks based on the semantic features. For example, in an image restoration task, the output is image 2, which is the restored image of image 1; in another example, in an image-to-text task, the output is the text: "A woman wearing a hat." Furthermore, compared to the traditional separate architecture, the AI-based source-channel joint encoding and decoding architecture can further improve the performance of semantic feature extraction and transmission.

[0147] Within the framework of semantic communication, modular multiplexing (MDM) technology mines new multi-user multiplexing degrees of freedom from the semantic feature space, thereby significantly improving the system's throughput. Figure 6 illustrates the uplink transmission process of MDM; the downlink transmission process is similar. Specifically, multiple users first encode their own data (such as images, text, and speech) (x1, x2, and x3 in Figure 6, where x1 is image 3a; x2 is image 4a; and x3 is speech 1a) (x1 and x2 are input into the encoding model f). e (;θ i Output respectively and x3 input encoding model f e (;θ j Output ),Then, and After superposition, encoding and transmission are performed simultaneously on the same time-frequency resources; and After superposition, the encoded data is transmitted simultaneously on the same time-frequency resources. During uplink transmission, to eliminate the impact of different channel fading differences among users and to ensure compatibility with digital communication systems, technologies such as digital domain aerial computing are also required. Utilizing the semantic orthogonality between users, interference from other users' encodings can be effectively suppressed. The base station directly inputs the received multi-user codes superimposed into the decoders corresponding to each user to recover the original data of each user or perform corresponding tasks. For example, in Figure 6, the receiver receives the superimposed... and Input it into the decoding model f d (;θ i The receiver outputs image 3b and image 4b ​​respectively; the receiving end receives the superimposed image. and Input it into the decoding model f d (;θ j ), outputting voice 1b. Where, f d (;θ i Perform image restoration tasks; d (;θ j Perform the voice recovery task.

[0148] Semantic orthogonality between users is crucial for ensuring the reception performance of multi-user applications under modular division multiplexing (MDF). Specifically, semantic orthogonality can be determined using methods such as singular vector canonical correlation analysis (SVCCA). By extracting and analyzing the principal components of the semantic feature sets of two users, SVCCA yields a maximum correlation factor between 0 and 1. The smaller this factor, the higher the orthogonality, the better the suppression of semantic interference between users, and the better the multi-user reception performance. Conversely, when this factor is large, the orthogonality is insufficient, and using MDF transmission will lead to a decrease in the performance of data recovery or task execution for each user.

[0149] The effectiveness of modular division multiplexing (MDD) is highly correlated with the semantic orthogonality among users. Semantic orthogonality is related to factors such as the data distribution and encoding / decoding models of each user, and may change over time. A reasonable multiplexing technology selection strategy should be to use MMD multiplexing only for users with high orthogonality and good MMD performance to improve system throughput; for users with low orthogonality and poor MMD performance, traditional multiplexing techniques should still be used to avoid strong mutual interference leading to a significant performance degradation. However, in existing technologies, base stations do not know the performance that each user can achieve using MMD transmission. Therefore, it is impossible to determine when to activate MMD multiplexing, making it difficult to maximize system throughput.

[0150] Furthermore, this application also provides the following communication methods:

[0151] Figures 7 and 8 are schematic flowcharts of another communication method provided in an embodiment of this application. Exemplarily, the method may include the following steps:

[0152] S701a and S701b. Each terminal (UE1 and UE2 are illustrated in Figures 7 and 8) sends the identifier of its respective encoding model to the network device.

[0153] Different encoding / decoding models can perform different intelligent tasks, such as image classification and speech recognition, with each model corresponding to a specific task. A terminal can use different encoding / decoding models for different intelligent tasks. Figure 9 illustrates the correspondence between encoding / decoding models and tasks in an example of an embodiment of this application. For instance, in a semantic communication system, the transmitting end extracts key features of the source data using an encoding model; the receiving end executes a specific task based on these source features using a decoding model. For the same pilot data, the encoding / decoding models and tags corresponding to different tasks are all different. For example, if the task pilot data is an image (such as image 5a in Figure 9, which is, for example, a woman wearing a hat), and the receiver needs to perform an image restoration task, then the transmitter and receiver should use decoding model 1 and encoding model 1 respectively, with label 1 being image 5b, and performance metrics such as peak signal-to-noise ratio (PSNR). If the receiver needs to perform an image-to-text task, then the transmitter and receiver should use decoding model 2 and encoding model 2 respectively, with label 2 being a text description of the image (such as "a woman wearing a hat"), and performance metrics such as block error rate (BLER).

[0154] UE1 and UE2 report their respective encoding model identifiers (e.g., UE1 performs task 1 using encoding model 1; UE2 performs task 2 using encoding model 2) to the network device. The network device then selects the appropriate decoding model for decoding. UE1 sends the identifier of encoding model 1 to the network device; UE2 sends the identifier of encoding model 2 to the network device. UE1 and UE2 can perform the same intelligent task (e.g., both perform image classification) and report the same encoding model identifier to the network device; or they can perform different intelligent tasks (e.g., UE1 performs image classification, UE2 performs speech recognition) and report different encoding model identifiers to the network device.

[0155] UE1 and UE2 can report their respective coding model identifiers through the 3GPP protocol layer. For example, UE1 and UE2 can carry their respective coding model identifiers through radio resource control (RRC) messages or medium access control control elements (MAC CE). For example, a new RRC field, ModelID, can be added to carry their respective coding model identifiers. UE1 and UE2 can also report their respective coding model identifiers through non-3GPP protocol layers.

[0156] Optionally, the identifiers of the encoding models of UE1 and UE2 can be predefined or pre-stored in the network device (e.g., the encoding models of UE1 and UE2 are unique). Therefore, the above steps S701a and S701b are optional, and are shown as dashed lines in Figure 7.

[0157] S702a and S702b.UE1 and UE2 respectively send tag information corresponding to the pilot data they selected to the network device.

[0158] UE1 and UE2 each select a set of task pilots based on their respective task types, which are typically (data-label) pairs. For example, an image classification task selects several images with known categories, while a speech recognition task selects several audio segments with known text content. To ensure the reliability of the modular performance measurement results, the data distribution in the task pilots should closely resemble the distribution of data in the current scenario, and the label distribution should have the highest possible diversity. Then, UE1 and UE2 report the label information corresponding to their respective selected pilot data to the network device. For example, if UE1 selects pilot data 1, UE1 reports label information 1; if UE2 selects pilot data 2, UE2 reports label information 2.

[0159] UE1 and UE2 can report the aforementioned tag information through the 3GPP protocol layer. For example, UE1 and UE2 can carry the aforementioned tag information through RRC messages or MAC CE. For example, a Tag field can be added to carry the aforementioned tag information. UE1 and UE2 can also report the aforementioned tag information through non-3GPP protocol layers.

[0160] For example, each terminal can report its own coding model identifier and the tag information corresponding to its own pilot data in the same message; or it can report its own coding model identifier and the tag information corresponding to its own pilot data in different messages.

[0161] Optionally, the tag information corresponding to the pilot data of UE1 and UE2 can be predefined or pre-stored in the network device (for example, the tag information corresponding to the pilot data of UE1 and UE2 is unique). Therefore, the above steps S702a and S702b are optional, and are shown as dashed lines in Figure 7.

[0162] S703. The network device sends information 1 to UE1 and UE2.

[0163] Accordingly, UE1 and UE2 receive this information 1.

[0164] The network device sends the transmission configuration of the encoded data (obtained by encoding the selected pilot data based on the encoding model of each terminal) to each terminal. The transmission of the encoded data can be periodic. The network device then sends information 1 to UE1 and UE2, where information 1 configures at least one of the following: the transmission period of the encoded data (PilotPeriod), and the offset of the starting time domain position of the encoded data relative to the system time (PilotOffset). After receiving information 1, each terminal generates encoded data according to information 1 and sends the encoded data to the network device. For example, information 1 can be carried in RRC signaling. The transmission period and offset can also be predefined by the protocol.

[0165] For example, the above configuration can also be semi-static. Further, the network device can also send information 4 to UE1 and UE2, which instructs UE1 and UE2 to activate or deactivate their respective coded data transmission based on the aforementioned transmission period and / or offset value. For instance, after the transmission period and / or offset value are configured by RRC signaling, the network device can activate or deactivate the aforementioned transmission period and / or offset value through MAC CE or downlink control information (DCI), i.e., instructing the activation or deactivation of periodic transmission behavior.

[0166] For example, the above configuration can also be dynamic; for instance, each terminal sends encoded data once it receives an instruction from the network device.

[0167] Optionally, the above-mentioned transmission period and offset value can also be predefined. Therefore, the above-mentioned step S703 is optional, and is shown as a dashed line in Figure 7.

[0168] S704a and S704b. Network devices send DCI1 to UE1 and UE2 respectively.

[0169] DCI1 indicates time-frequency resource 1, which is used to map the coded data of UE1 and UE2 respectively, that is, coded data 1 and coded data 2 are transmitted on the same time-frequency resource 1.

[0170] S705a and S705b. UE1 sends encoded data 1 to the network device, and UE2 sends encoded data 2 to the network device.

[0171] Accordingly, the network device receives the aforementioned encoded data 1 and encoded data 2.

[0172] After receiving the aforementioned Information 1 and DCI 1, UE1 encodes the selected pilot data 1 based on coding model 1 to obtain coded data 1 (i.e., coded data 1 is obtained by encoding the pilot data 1 selected by UE1 based on coding model 1); and after receiving the aforementioned Information 1 and DCI 1, UE2 encodes the selected pilot data 2 based on coding model 2 to obtain coded data 2 (i.e., coded data 2 is obtained by encoding the pilot data 2 selected by UE2 based on coding model 2). Then, UE1 sends coded data 1 to the network device, and UE2 sends coded data 2 to the network device. The coded data 1 and coded data 2 are superimposed over the air interface.

[0173] S706. The network device decodes the superimposed encoded data based on decoding model 1 and decoding model 2 respectively.

[0174] In steps S701a and S701b, the network device receives information 1 and obtains the encoding model 1 reported by UE1 and the encoding model 2 reported by UE2. The network device then obtains the decoding model 1 corresponding to the encoding model 1 and uses the decoding model 1 to decode the received overlay encoded data to obtain the decoding result 1 corresponding to the encoded data 1. The network device also obtains the decoding model 2 corresponding to the encoding model 2 and uses the decoding model 2 to decode the received overlay encoded data to obtain the decoding result 2 corresponding to the encoded data 2.

[0175] S707. The network device obtains decoding performance 1 based on tag information 1 and decoding result 1; and obtains decoding performance 2 based on tag information 2 and decoding result 2.

[0176] After the network device decodes the encoded data 1 to obtain decoding result 1, it compares decoding result 1 with tag information 1 to obtain decoding performance 1 for UE1. After the network device decodes the encoded data 2 to obtain decoding result 2, it compares decoding result 2 with tag information 2 to obtain decoding performance 2 for UE2. Different tasks have different decoding performances. For example, for image classification, the corresponding decoding performance is the image classification accuracy; for semantic recognition, the corresponding decoding performance is the semantic recognition accuracy; and for video restoration, the corresponding decoding performance is the MOS score of video restoration.

[0177] S708a and S708b. Network devices send information 3 to UE1 and information 4 to UE2.

[0178] Accordingly, UE1 and UE2 receive the aforementioned information 3 and information 4 respectively.

[0179] After obtaining the decoding performance of UE1 and UE2 respectively, the network device determines the time-frequency resources corresponding to UE1 and UE2 based on the aforementioned decoding performance 1 and decoding performance 2. If both decoding performance 1 and decoding performance 2 meet the performance indicators (e.g., the accuracy of image classification is higher than or equal to threshold 1, and the accuracy of semantic recognition is higher than or equal to threshold 2), or if the weighted sum of decoding performance 1 and decoding performance 2 meets the performance indicators, then UE1 and UE2 can be scheduled for modular multiplication (MM / MM) transmission. The network device sends information 3 to UE1 and information 4 to UE2. Information 3 and information 4 indicate time-frequency resource 2. Information 3 and information 4 are obtained based on the aforementioned decoding performance 1 and decoding performance 2. That is, UE1 and UE2 are scheduled to transmit data on the same time-frequency resource 2 to improve system throughput.

[0180] Furthermore, when scheduling UE1 and UE2 to transmit data on the same time-frequency resource 2, information 3 also indicates encoding model 1, and information 4 also indicates encoding model 2. Subsequently, UE1 uses encoding model 1 to encode the data to be transmitted, and UE2 uses encoding model 2 to encode the data to be transmitted, so as to ensure the performance of modulus multiplexing.

[0181] If the decoding performance of UE1 or UE2 does not meet the performance target, or if the weighted sum of the above decoding performance 1 and decoding performance 2 does not meet the performance target, then traditional multiplexing techniques (such as frequency division multiplexing, time division multiplexing, code division multiplexing) are used to schedule UE1 and UE2 to transmit data on different time and frequency resources to avoid mutual interference.

[0182] According to an embodiment of this application, a communication method is provided in which a network device schedules each terminal to send the encoded pilot data on the same time-frequency resources. Based on the received superimposed encoded data and the decoding network of each terminal, the decoding performance of each terminal is obtained to measure the modulus division multiplexing effect. Then, it is determined whether each terminal can be scheduled to perform subsequent data transmission on the same time-frequency resources, thereby improving resource utilization efficiency and system throughput. This solves the problem in the prior art that it is difficult to determine the timing of modulus division multiplexing transmission.

[0183] The above describes how network devices determine the performance of the first coding model under the influence of wireless transmission during uplink transmission. The following describes how network devices determine the performance of the first coding model under the influence of wireless transmission during downlink transmission:

[0184] Figure 10 shows a flowchart illustrating another communication method provided in an embodiment of this application. Exemplarily, the method may include the following steps:

[0185] S1001. The third terminal decodes the first data based on the second decoding model to obtain the second decoding result.

[0186] In this embodiment, the network device needs to determine the performance of the second codec model under the influence of wireless transmission.

[0187] Network devices can select a set of task pilots (second pilot data) for the third terminal to perform a task, which is a typical set of (data-label) pairs. For example, for image classification tasks, several images with known categories are selected, and for speech recognition tasks, several audio segments with known text content are selected.

[0188] In one example, the network device uses a second coding model to encode the selected second pilot data to obtain the first data. That is, the first data is obtained by encoding the second pilot data based on the second coding model. This second coding model corresponds to the second decoding model.

[0189] In another example, the first data could also be the original second pilot data.

[0190] The network device sends the first data to the third terminal. The third terminal receives the first data from the network device.

[0191] After receiving the first data, the third terminal decodes the first data based on the second decoding model to obtain the second decoding result.

[0192] The second encoding / decoding model corresponds to the second task. For example, encoding model 3 is selected for the image classification task, and encoding model 4 is selected for the speech recognition task.

[0193] Further, prior to step S1001, the method may also include the following steps: the third terminal sends a sixth piece of information to the network device. This sixth piece of information indicates the identifier of the second decoding model. Different encoding and decoding models can perform different intelligent tasks, such as image classification and speech recognition, and the encoding and decoding models correspond to the tasks. The third terminal sends the identifier of the second decoding model to the network device, so that the network device can select the corresponding second encoding model for encoding.

[0194] S1002. The third terminal sends the fourth information to the network device based on the second decoding result.

[0195] Accordingly, the network device receives this fourth piece of information.

[0196] After obtaining the second decoding result, the third terminal sends fourth information to the network device based on the second decoding result. This fourth information indicates the decoding performance corresponding to the first data. For example, the third terminal compares the second decoding result with the tag information corresponding to the first data to obtain the decoding performance corresponding to the first data. Different tasks have different decoding performances; for example, for image classification tasks, the corresponding decoding performance is the image classification accuracy; for semantic recognition tasks, the corresponding decoding performance is the semantic recognition accuracy; and for video restoration tasks, the corresponding decoding performance is the MOS score of the video restoration.

[0197] Furthermore, prior to step S1002, the method may further include the following step: the network device sends seventh information to the third terminal. This seventh information indicates tag information corresponding to the first data, and the tag information corresponding to the first data is used to determine the second decoding result.

[0198] S1003. The network device determines the second time-frequency resource based on the decoding performance corresponding to the first data.

[0199] After obtaining the decoding performance corresponding to the first data, if the network device finds that the decoding performance meets the performance indicators (e.g., the accuracy of image classification is higher than or equal to threshold 1, and the accuracy of semantic recognition is higher than or equal to threshold 2), it indicates that the performance of the data encoded and decoded using the second encoding and decoding model in a wireless environment meets the requirements (e.g., the interference from other terminals is within an acceptable range). Therefore, the network device can determine the second time-frequency resource based on the decoding performance corresponding to the first data. In other words, the decoding performance corresponding to the first data is used to determine the second time-frequency resource.

[0200] S1004. The network device sends the fifth information to the third terminal.

[0201] Accordingly, the third terminal receives the fifth piece of information.

[0202] After determining the second time-frequency resource, the network device generates fifth information and sends it to the third terminal. This fifth information indicates the second time-frequency resource.

[0203] Furthermore, the fifth information also indicates the second decoding model. The fifth information simultaneously indicates the second time-frequency resource and the second decoding model. There is a correlation between the second time-frequency resource and the second decoding model. When the network device schedules the second terminal to transmit data on the second time-frequency resource, it needs to use the second decoding model to decode the received data to ensure transmission performance in the wireless environment.

[0204] S1005. The network device sends second data to the third terminal.

[0205] Accordingly, the third terminal receives the second data.

[0206] After determining the second time-frequency resource, the network device sends the second data to the third terminal. This second time-frequency resource is used to map the aforementioned second data.

[0207] Furthermore, the network device can also schedule at least one fourth terminal to receive second data on the same time-frequency resource as the third terminal, and obtain the decoding performance of the third terminal and at least one fourth terminal based on their respective decoding results. If the decoding performance of the third terminal and at least one fourth terminal both meet the performance index, or if the weighted sum of the decoding performance of the third terminal and at least one fourth terminal meets the performance index, then the network device can configure the second time-frequency resource for both the third terminal and at least one fourth terminal (the second time-frequency resource is also used to map the data of at least one fourth terminal), that is, schedule the third terminal and at least one fourth terminal to transmit subsequent communication data on the same time-frequency resource, and indicate the corresponding decoding model to at least one fourth terminal.

[0208] According to a communication method provided in an embodiment of this application, a third terminal decodes first data based on a second decoding model to obtain a second decoding result, and indicates the decoding performance corresponding to the first data to a network device based on the second decoding result. This enables the network device to determine the performance of the second decoding model under the influence of wireless transmission based on the decoding performance corresponding to the first data, and to indicate a second time-frequency resource. Subsequently, the terminal can map the second data onto the second time-frequency resource, thereby improving the reliability of communication.

[0209] The above scheme can be applied to multi-user modular division multiplexing, enabling network devices to understand the performance achieved by each user using modular division transmission, thereby maximizing system throughput. The following description, in conjunction with an embodiment, illustrates this:

[0210] Figures 11 and 12 show a flowchart illustrating another communication method provided in an embodiment of this application. Exemplarily, the method may include the following steps:

[0211] S1101a and S1101b. Each terminal (UE3 and UE4 are examples in Figures 11 and 12) sends the identifier of the decoding model corresponding to each terminal to the network device.

[0212] Different encoding and decoding models can perform different intelligent tasks, such as image classification and speech recognition, and the encoding and decoding models correspond to the tasks.

[0213] Each terminal reports its own decoding model identifier to the network device, which then selects the appropriate encoding model for encoding. The network device can schedule each terminal to perform the same task, in which case each terminal can report the same decoding model; alternatively, the network device can schedule each terminal to perform different tasks, in which case each terminal can report different decoding models. For example, in this embodiment, UE3 reports the identifier of decoding model 3, and UE4 reports the identifier of decoding model 4.

[0214] UE3 and UE4 can report their respective decoding model identifiers through the 3GPP protocol layer. For example, UE3 and UE4 can carry their respective decoding model identifiers through a message without RRC or a MAC CE. For example, they can add an RRC field ModelID to carry their respective decoding model identifiers. UE3 and UE4 can also report their respective decoding model identifiers through non-3GPP protocol layers.

[0215] Optionally, the identifiers of the decoding models of UE1 and UE2 can be predefined or pre-stored in the network device (e.g., the decoding models of UE1 and UE2 are unique). Therefore, the above steps S1101a and S1101b are optional, and are shown as dashed lines in Figure 11.

[0216] S1102a and S1102b. The network devices send the tag information corresponding to the pilot data selected for each terminal to UE3 and UE4, respectively.

[0217] The network device selects a set of task pilots, i.e., a typical set of (data-label) pairs, based on the task type of each terminal. For example, for image classification tasks, several images with known categories are selected; for speech recognition tasks, several segments of speech with known text content are selected. To ensure the reliability of the modular performance measurement results, the data distribution in the task pilots should be as close as possible to the distribution of data in the current scene, and the label distribution should have the highest possible diversity. Then, the network device sends the label information corresponding to the pilot data selected for each terminal to UE3 and UE4, respectively. For example, the network device selects pilot data 3 for UE3 and sends label information 3 to UE3; the network device selects pilot data 4 for UE4 and sends label information 4 to UE4.

[0218] Network devices can send the aforementioned tag information via 3GPP protocols. For example, network devices can carry the tag information via RRC messages or MAC CEs. For instance, a new Tag field can be added to carry the tag information. Network devices can also send the aforementioned tag information via non-3GPP protocol layers.

[0219] Optionally, the tag information corresponding to the pilot data can be predefined or pre-stored in UE1 and UE2 (for example, the tag information corresponding to the pilot data of UE1 and UE2 is unique). Therefore, the above steps S1102a and S1102b are optional, and are shown as dashed lines in Figure 11.

[0220] S1103. The network device encodes the pilot data 3 based on the coding model 3 to obtain coded data 3; and encodes the pilot data 4 based on the coding model 4 to obtain coded data 4.

[0221] The network device obtains the corresponding encoding model 3 based on the decoding model 3 reported by UE3, and encodes the pilot data 3 selected for UE3 based on the encoding model 3 to obtain encoded data 3; the network device obtains the corresponding encoding model 4 based on the decoding model 4 reported by UE4, and encodes the pilot data 4 selected for UE4 based on the encoding model 4 to obtain encoded data 4.

[0222] S1104. The network device superimposes encoded data 3 and encoded data 4 to obtain superimposed encoded data.

[0223] After the network device obtains encoded data 3 and encoded data 4, it superimposes encoded data 3 and encoded data 4 to obtain superimposed encoded data.

[0224] S1105. Encoded data after overlay of broadcast data from network devices.

[0225] The superimposed encoded data is a superposition of encoded data 3 and encoded data 4.

[0226] Network devices broadcast superimposed encoded data via wireless channels.

[0227] Optionally, before step S1105, the network device may also send DCI2 to UE3 and UE4 respectively. DCI2 indicates time-frequency resource 3, used to map the superimposed encoded data. The network device schedules UE3 and UE4 to receive the superimposed encoded data on the same time-frequency resource. UE3 and UE4 receive the superimposed encoded data on the time-frequency resource 3 indicated by the network device.

[0228] S1106a.UE3 decodes the superimposed encoded data based on decoding model 3 to obtain decoding result 3, and obtains decoding performance 3 based on tag information 3 and decoding result 3.

[0229] After receiving the superimposed encoded data, UE3 decodes the superimposed encoded data based on decoding model 3 to obtain decoding result 3. Then, it compares decoding result 3 with tag information 3 to obtain the decoding performance 3 of UE3.

[0230] S1106b.UE4 decodes the superimposed encoded data based on decoding model 4 to obtain decoding result 4, and obtains decoding performance 4 based on tag information 4 and decoding result 4.

[0231] After receiving the superimposed encoded data, UE4 decodes the superimposed encoded data based on decoding model 4 to obtain decoding result 4. Then, decoding result 4 is compared with tag information 4 to obtain the decoding performance 4 of UE4.

[0232] S1107a and S1107b.UE3 and UE4 respectively send decoding performance 3 and decoding performance 4 to the network device.

[0233] After obtaining decoding performance 3 and decoding performance 4 respectively, UE3 and UE4 report decoding performance 3 and decoding performance 4 to the network device respectively.

[0234] For example, UE3 and UE4 can report decoding performance 3 and decoding performance 4 through signaling such as RRC signaling, MAC CE or uplink control information (UCI).

[0235] S1108a and S1108b. Network devices send information 5 and information 6 to UE3 and UE4 respectively, with information 5 and information 6 indicating time and frequency resource 4.

[0236] After obtaining the decoding performance of UE3 and UE4 respectively, the network device determines the time-frequency resources corresponding to UE3 and UE4 based on the aforementioned decoding performance 3 and decoding performance 4. If both decoding performance 3 and decoding performance 4 meet the performance indicators (e.g., the accuracy of image classification is higher than or equal to threshold 1, and the accuracy of semantic recognition is higher than or equal to threshold 2), or if the weighted sum of decoding performance 3 and decoding performance 4 meets the performance indicators, then UE3 and UE4 can be scheduled for modular multiplication (MM / DM) transmission. The network device sends information 5 to UE3 and information 6 to UE4. Information 5 and information 6 indicate time-frequency resource 4. Information 5 and information 6 are obtained based on the aforementioned decoding performance 3 and decoding performance 4. That is, UE3 and UE4 are scheduled to transmit data on the same time-frequency resource 4 to improve system throughput.

[0237] Furthermore, when scheduling UE3 and UE4 to transmit data on the same time-frequency resource 4, information 5 also indicates encoding model 3, and information 6 also indicates encoding model 4. Subsequently, UE3 uses encoding model 3 to encode the data to be transmitted, and UE4 uses encoding model 4 to encode the data to be transmitted, so as to ensure the performance of modulus multiplexing.

[0238] If the decoding performance of UE3 or UE4 does not meet the performance target, or if the weighted sum of the decoding performance 3 and decoding performance 4 does not meet the performance target, then traditional multiplexing techniques (such as frequency division multiplexing, time division multiplexing, code division multiplexing) are used to schedule UE3 and UE4 to transmit data on different time and frequency resources to avoid mutual interference.

[0239] According to an embodiment of this application, a communication method is provided in which a network device sends superimposed encoded data to each terminal on the same time-frequency resources. The superimposed encoded data is a superposition of the encodings of the pilot data corresponding to each terminal. Each terminal decodes the superimposed encoded data based on its own decoding model and reports its decoding performance. The network device measures the modulus-division multiplexing effect based on the decoding performance of each terminal, and then decides whether to schedule each terminal to perform subsequent data transmission on the same time-frequency resources, thereby improving resource utilization efficiency and system throughput, and solving the problem in the prior art that it is difficult to determine the timing of modulus-division multiplexing transmission.

[0240] In this application, "sending information" can be understood as one device sending information to another device, or it can also be understood as one logical module within a device sending information to another logical module. For example, "access network device sending information" can be understood as the access network device sending information to another device (such as a terminal), or it can be understood as logical module 1 in the access network device sending information to logical module 2 in the access network device.

[0241] In this application, "receiving information" can be understood as one device receiving information from another device, or it can also be understood as a logical module within a device receiving information from another logical module. For example, "access network device receiving information" can be understood as the access network device receiving information from another device (such as a terminal), or it can be understood as logical module 1 in the access network device receiving information from logical module 2 in the access network device.

[0242] In this application, phrases such as "sending information to... (e.g., a terminal)" or related illustrations in the accompanying drawings can be understood as indicating that the destination of the information is a terminal. This can include sending information directly or indirectly to a terminal. Similarly, phrases such as "receiving information from... (e.g., a terminal)," "receiving information from... (e.g., a terminal)," or "receiving information sent by (e.g., a terminal)," or related illustrations in the accompanying drawings, can be understood as indicating that the source of the information is a terminal. This can include receiving information directly or indirectly from a terminal. Information may undergo necessary processing between the source and destination, such as format changes, but the destination can understand the valid information from the source. Similar expressions in this application can be interpreted similarly and will not be elaborated further here.

[0243] Figure 13 illustrates a possible exemplary block diagram of the communication device involved in the embodiments of this application. As shown in Figure 13, the communication device 1300 may include modules or units for implementing the method embodiments described above. In one possible design, the communication device 1300 includes a processing unit 1302 and a communication unit 1303. Optionally, the communication device 1300 may further include a storage unit 1301 for storing device program code and / or data.

[0244] The communication device 1300 can be a terminal-side device in the above embodiments, such as a terminal or a communication module in a terminal, or a circuit or chip in a terminal that is responsible for communication functions.

[0245] For example, in one embodiment, the communication unit 1303 is used to send first coded data, which is obtained by encoding first pilot data based on a first coding model, and the first coding model corresponds to a first task; the communication unit 1303 is also used to receive first information, which indicates a first time-frequency resource; and the communication unit 1303 is also used to send second coded data, which is used to map the second coded data, and the second coded data is obtained by encoding the first communication data based on the first coding model.

[0246] Furthermore, the communication unit 1303 is also used to send second information, the second information indicating at least one of the following: an identifier of the first coding model, and tag information corresponding to the first pilot data.

[0247] Furthermore, the communication unit 1303 is also used to receive third information; and the communication unit 1303 is also used to send first coded data based on the third information.

[0248] For example, in another embodiment, the processing unit 1302 is used to decode the first data based on the second decoding model to obtain a second decoding result, the second decoding model corresponding to the second task; the communication unit 1303 is used to send fourth information based on the second decoding result, the fourth information indicating the decoding performance corresponding to the first data, the decoding performance corresponding to the first data being used to determine the second time-frequency resources; the communication unit 1303 is also used to receive fifth information, the fifth information indicating the second time-frequency resources; and the communication unit 1303 is also used to receive second data, the second time-frequency resources being used to map the second data.

[0249] Furthermore, the communication unit 1303 is also used to send a sixth message, which indicates the identifier of the second decoding model.

[0250] Furthermore, the communication unit 1303 is also used to receive seventh information, which indicates tag information corresponding to the first data, and the tag information corresponding to the first data is used to determine the second decoding result.

[0251] The communication device 1300 can be a network-side device in the above embodiments, such as an access network device or a communication module in the access network device, or a circuit or chip in the access network device responsible for communication functions.

[0252] For example, in one embodiment, the communication unit 1303 is configured to receive first encoded data from a first terminal, the first encoded data being obtained by encoding first pilot data based on a first encoding model; the communication unit 1303 is also configured to send first information to the first terminal, the first information indicating first time-frequency resources; and the communication unit 1303 is also configured to receive second encoded data from the first terminal, the first time-frequency resources being used to map the second encoded data, and the second encoded data being obtained by encoding first communication data based on the first encoding model.

[0253] Furthermore, the communication unit 1303 is also configured to receive second information from the first terminal, the second information indicating at least one of the following: an identifier of the first encoding model, and tag information corresponding to the first pilot data; the processing unit 1302 is configured to acquire a first decoding model corresponding to the identifier of the first encoding model; the processing unit 1302 is also configured to decode the first encoded data based on the first decoding model to obtain a first decoding result; the processing unit 1302 is also configured to determine the decoding performance corresponding to the first encoded data based on the first decoding result and the tag information; and the processing unit 1302 is also configured to determine a first time-frequency resource based on the decoding performance corresponding to the first encoded data.

[0254] Furthermore, the communication unit 1303 is also used to send third information to the first terminal; and the communication unit 1303 is also used to receive first encoded data from the first terminal based on the third information.

[0255] For example, in another embodiment, the communication unit 1303 is configured to receive fourth information from a third terminal, the fourth information indicating the decoding performance corresponding to the first data; the processing unit 1302 is configured to determine a second time-frequency resource based on the decoding performance corresponding to the first data; the communication unit 1303 is further configured to send fifth information to the third terminal, the fifth information indicating the second time-frequency resource; and the communication unit 1303 is further configured to send second data to the third terminal, the second time-frequency resource being used to map the second data.

[0256] Furthermore, the communication unit 1303 is also used to receive sixth information from the first terminal, which indicates the identifier of the second decoding model.

[0257] Furthermore, the communication unit 1303 is also used to send seventh information to the first terminal, the seventh information indicating the tag information corresponding to the first data.

[0258] In one possible design, when the communication device 1300 is a terminal or a communication module within a terminal, the function of the processing unit 1302 can be implemented by one or more processors. Specifically, the processor may include a modem chip, or a system-on-a-chip (SoC) chip or a SIP chip containing a modem core. The function of the communication unit 1303 can be implemented by transceiver circuitry.

[0259] In one possible design, when the communication device 1300 is a circuit or chip in a terminal responsible for communication functions, such as a modem chip or a system-on-a-chip (SoC) or SIP chip containing a modem core, the function of the processing unit 1302 can be implemented by a circuit system in the aforementioned chip that includes one or more processors or processor cores. The function of the communication unit 1303 can be implemented by an interface circuit or data transceiver circuit on the aforementioned chip.

[0260] In one possible design, when the communication device 1300 is a terminal or a processing module within a terminal, the functionality of the processing unit 1302 can be implemented by one or more processors. Specifically, the processor may include a GPU, or a system-on-a-chip (SoC) or SIP chip containing a GPU. The functionality of the communication unit 1303 can be implemented by transceiver circuitry.

[0261] In one possible design, when the communication device 1300 is a circuit or chip in the terminal responsible for processing functions, such as a GPU or a system-on-a-chip (SoC) or SIP chip containing a GPU, the function of the processing unit 1302 can be implemented by a circuit system in the aforementioned chip that includes one or more processors or processor cores. The function of the communication unit 1303 can be implemented by interface circuitry or data transceiver circuitry on the aforementioned chip.

[0262] It is understood that the division of units in the above-described device is merely a logical functional division. One function can correspond to one functional unit, or two or more functions can be integrated into one functional unit. In actual implementation, all or some units can be integrated onto a single physical entity, or distributed across different physical entities. Furthermore, the aforementioned functional units can be implemented in hardware, software, or a combination of both. Whether a function is executed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for specific applications, but such implementations should not be considered beyond the scope of this application.

[0263] In one example, the functional unit in any of the above devices may be one or more integrated circuits configured to implement the above methods, such as: one or more application-specific integrated circuits (ASICs), or one or more central processing units (CPUs), one or more microcontroller units (MCUs), one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms.

[0264] In one example, storage unit 1301 may include random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory and / or registers, etc.

[0265] Referring to Figure 14, which is a schematic diagram of the structure of a terminal provided in an embodiment of this application, the terminal 1400 can correspond to the terminal shown in Figures 4, 7, 10 or 11, and is used to implement the operation of the terminal in the above embodiments. As shown in Figure 14, the terminal includes: one or more antennas 1410, a radio frequency processing system 1420, and a processor system 1430.

[0266] In the downlink or sidelink direction, the RF processing system 1420 receives RF signals through the antenna 1410 and sends the RF-processed signals to the processor system 1430 for further processing. In the uplink or sidelink direction, the processor system 1430 processes the terminal-side information and sends it to the RF processing system 1420, which then processes the signal and transmits it through the antenna 1410.

[0267] In one example, the radio frequency (RF) processing system 1420 serves as the communication interface for external communication of the terminal and may include an RF front end (RFFE) 1421 and an RF transceiver 1422. The RFFE 1421 is primarily used for one or more processing operations, such as shaping, passband selection, or gain adjustment, on the RF signals received by the antenna or those to be transmitted through the antenna. It may include one or more components such as RF switches, duplexers, filters, power amplifiers, antenna tuners, and low-noise amplifiers. The RFFE 1421 can be a circuit system composed of multiple discrete components or integrated into one or more chips. The RF transceiver 1422 processes the RF signals received by the RFFE into baseband / IF signals for further processing by the processor system 1430, and processes the baseband / IF signals provided by the processor system 1430 into RF signals for transmission to the RFFE 1421. The baseband / IF signals transmitted between the RF transceiver 1422 and the processor system 1430 can be digital or analog signals. The radio frequency transceiver 1422 can be implemented by one or more chips, which are commonly referred to as radio frequency integrated circuits (RFICs).

[0268] In one example, processor system 1430 may include one or more processors for processing signals and executing one or more communication protocols. Optionally, processor system 1430 may also include memory 1436. In one example, the one or more processors include at least one baseband processor 1431 (also known as a modem processor). Memory 1436 is used to store data and / or computer program instructions. Optionally, processor system 1430 may also include one or more application processors 1432 for implementing processing of the terminal operating system and application layer. Application processor 1432 may include, for example, a GPU. Optionally, processor system 1430 may also include one or more of a voice subsystem 1433, a multimedia subsystem 1434, or an interface circuit 1435. The voice subsystem 1433 is used to process voice signals, the multimedia subsystem 1434 is used to handle multimedia-related operations, such as video encoding / decoding, image processing, etc., and the interface circuit 1435 is used to implement communication with other terminal components, such as a display 1440, an input device 1450, memory 1460, etc. The aforementioned components in the processor system 1430 can communicate with each other via a bus or communication interface circuit.

[0269] In one example, the processor system 1430 can be packaged as a single processor chip, such as a SoC chip or a SIP chip. In another example, the processor system 1430 can be a system composed of multiple chips; for example, the baseband processor 1431 can be packaged as a single chip, or packaged with part or all of the circuitry of the radio frequency processing system into a single chip.

[0270] In one example, memory 1436 can be on-chip memory, i.e., located on the processor system 1430 chip. In another example, memory 1460 can be off-chip memory, i.e. located outside the processor system 1430 chip.

[0271] In one example, the baseband processor 1431 may include one or more processor cores 14311 and interface circuitry 14314. The one or more processor cores 14311 are used to process signals and execute one or more communication protocols. Optionally, the baseband processor 1431 may also include a memory 14312 for storing at least a portion of the corresponding computer program instructions and / or data. In one example, the one or more processor cores 14311 execute the computer program instructions stored in the memory 14312 to implement the relevant operations in the above method embodiments (such as controlling one or more antennas 1410 to receive third information, the third information indicating transmission control information for first data, the transmission control information being obtained based on first transmission parameters and an AI model, the transmission control information indicating time information for submitting the first data to the application layer; and submitting the first data to the application layer based on the transmission control information). In this disclosure, memory 14312 is used to store corresponding computer program instructions and / or data. This can mean that memory 14312 stores all corresponding computer program instructions and / or data for execution by processor core 14311; or it can mean that memory 14312 stores a portion of corresponding computer program instructions and / or data, including the computer program instructions and / or data currently required to be executed by processor core 14311. Memory 14312 can store different portions of computer program instructions and / or data multiple times for execution by processor core 14311 to implement the relevant operations in the above method embodiments. Interface circuit 14314 serves as a communication interface for communication with other components, such as transmitting signals with radio frequency processing system 1420, communicating with other subsystems and related components of processor system 1430 via bus, such as transmitting data control signals with application processor 1432, and transmitting data or computer program instructions with memory 1436 or memory 1460. Optionally, in order to reduce the load on the processor core, a baseband signal processing circuit 14313 can be set to perform at least some baseband signal processing, including one or more of signal demodulation, modulation, encoding or decoding.

[0272] In one example, the communication device provided in this application may be a terminal 1400, a communication module including a processor system 1430 and a radio frequency processing system 1420, or a baseband processor 1431.

[0273] The processor, processor system, application processor, baseband processor, processor circuit, or processor core mentioned above can be collectively referred to as a processor. The processor may include one or more of the following: central processing unit (CPU), digital signal processor (DSP), microprocessor unit (MPU), microcontroller unit (MCU), graphics processing unit (GPU), field programmable gate array (FPGA), artificial intelligence processor (AI processor), or neural processing unit (NPU).

[0274] The aforementioned memory may include one or more of the following storage media: random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), phase-change memory (PCM), resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), cache, register, read-only memory (ROM), flash memory, erasable programmable read-only memory (EPROM), hard disk, etc. In one example, computer program instructions for executing the above embodiments may be stored on non-volatile memory, such as at least a portion of the aforementioned memory 1460 (e.g., one or more of ROM, flash memory, EPROM, or hard disk). When the terminal is running, the corresponding computer program instructions may be partially or wholly loaded onto a memory with a faster transfer speed than the processor, such as at least a portion of memory 1436 and / or memory 14312 (e.g., one or more of RAM, SRAM, DRAM, PCM, RERAM, MRAM, FRAM, cache, or register), for the processor to execute in order to implement the steps in the above method embodiments.

[0275] In one example, the RF transceiver 1422 and the RF front-end 1421 can also be packaged in a single chip. In another example, the RF transceiver 1422, the RF front-end 1421, and the baseband processor 1431 can also be packaged in a single chip.

[0276] The terms "system" and "network" in this application embodiment are used interchangeably. "At least one" refers to one or more, and "multiple" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, "at least one of A, B, or C" includes A, B, C, AB, AC, BC, or ABC; "at least one of A, B, and C" can also be understood as including A, B, C, AB, AC, BC, or ABC. Furthermore, unless otherwise specified, the ordinal numbers such as "first" and "second" mentioned in this application embodiment are used to distinguish multiple objects and are not used to limit the order, sequence, priority, or importance of multiple objects.

[0277] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, etc.) containing computer-usable program code.

[0278] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in one or more blocks of the flowchart illustrations and / or one or more blocks of the block diagrams.

[0279] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means that implement the functions specified in one or more flowcharts and / or one or more block diagrams.

[0280] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, such that the instructions, which execute on the computer or other programmable apparatus, provide steps for implementing the functions specified in one or more flowcharts and / or one or more block diagrams.

[0281] It is understood that in this application, "instruction" can include direct instruction, indirect instruction, explicit instruction, and implicit instruction. When describing a certain instruction information to indicate A, it can be understood that the instruction information carries A, directly indicates A, or indirectly indicates A. In this application, the information indicated by the instruction information is called the information to be instructed. In specific implementation, there are many ways to indicate the information to be instructed, such as, but not limited to, directly indicating the information to be instructed, such as the information to be instructed itself or its index, or indirectly indicating the information to be instructed by indicating other information, wherein there is an association between the other information and the information to be instructed. It is also possible to indicate only a part of the information to be instructed, while the other parts of the information to be instructed are known or agreed upon in advance. For example, the instruction of specific information can also be achieved by using the arrangement order of various information in advance (e.g., as specified by a protocol), thereby reducing the instruction overhead to a certain extent. The information to be instructed can be sent as a whole or divided into multiple sub-information to be sent separately, and the sending period and / or sending time of these sub-information can be the same or different. This application does not limit the specific sending method. The sending period and / or timing of these sub-information messages can be predefined, for example, according to a protocol, or configured by the transmitting device by sending configuration information to the receiving device.

Claims

1. A communication method, characterized in that, The method includes: Send first encoded data, which is obtained by encoding the first pilot data based on the first encoding model, and the first encoding model corresponds to the first task; Receive first information, the first information indicating a first time-frequency resource; Send second encoded data, wherein the first time-frequency resource is used to map the second encoded data, and the second encoded data is obtained by encoding the first communication data based on the first encoding model.

2. The method of claim 1, wherein, The first information also indicates the first encoding model.

3. The method of claim 1 or 2, wherein, The method further includes: Send a second message, which indicates at least one of the following: the identifier of the first coding model, and the tag information corresponding to the first pilot data.

4. The method according to any one of claims 1-3, characterized in that, The method further includes: Receive third-party information; Sending the first encoded data includes: sending the first encoded data based on the third information.

5. The method of any one of claims 1-4, wherein, The method is applied to the first terminal side, and the first time-frequency resource is also used to map the encoded data of at least one second terminal.

6. A communication method characterized by comprising: The method includes: Receive first encoded data, which is obtained by encoding first pilot data based on a first encoding model, and the first encoding model corresponds to the first task; Send a first message, the first message indicating a first time-frequency resource; The second encoded data is received, the first time-frequency resource is used to map the second encoded data, and the second encoded data is obtained by encoding the first communication data based on the first encoding model.

7. The method of claim 6, wherein, The first information also indicates the first encoding model.

8. The method as described in claim 6 or 7, characterized in that, The method further includes: Receive second information, the second information indicating at least one of the following: the identifier of the first coding model, and the tag information corresponding to the first pilot data.

9. The method of any one of claims 6-8, wherein, The method further includes: Send a third message; Receiving the first encoded data includes: receiving the first encoded data based on the third information.

10. The method of any one of claims 6-9, wherein, The first time-frequency resource is also used to map the encoded data of at least one second terminal.

11. A communication method, characterized in that, The method includes: The first data is decoded based on the second decoding model to obtain the second decoding result. The second decoding model corresponds to the second task. Based on the second decoding result, a fourth message is sent, the fourth message indicating the decoding performance corresponding to the first data, and the decoding performance corresponding to the first data is used to determine the second time-frequency resource; Receive fifth information, the fifth information indicating the second time-frequency resource; Receive the second data, and use the second time-frequency resource to map the second data.

12. The method of claim 11, wherein, The fifth piece of information also indicates the second decoding model.

13. The method as described in claim 11 or 12, characterized in that, The method further includes: Send a sixth message, which indicates the identifier of the second decoding model.

14. The method of any one of claims 11-13, wherein, The method further includes: A seventh message is received, which indicates the tag information corresponding to the first data. The tag information corresponding to the first data is used to determine the second decoding result.

15. The method according to any one of claims 11-14, characterized in that, The method is applied to the third terminal side, and the second time-frequency resource is also used to map data from at least one fourth terminal.

16. A method of communication, comprising: The method includes: Receive fourth information from a third terminal, the fourth information indicating the decoding performance corresponding to the first data; Based on the decoding performance corresponding to the first data, the second time-frequency resource is determined; Send a fifth message to the third terminal, the fifth message indicating a second time-frequency resource; The second data is sent to the third terminal, and the second time-frequency resource is used to map the second data.

17. The method as described in claim 16, characterized in that, The fifth piece of information also indicates the second decoding model.

18. The method as described in claim 17, characterized in that, The method further includes: The sixth information is received from the first terminal, the sixth information indicating the identifier of the second decoding model.

19. The method according to any one of claims 16-19, characterized in that, The method further includes: A seventh message is sent to the first terminal, the seventh message indicating the tag information corresponding to the first data.

20. The method according to any one of claims 16-19, characterized in that, The second time-frequency resource is also used to map data from at least one fourth terminal.

21. A communication device, characterized in that, Includes modules or units for implementing the method as described in any one of claims 1-20.

22. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions that, when executed, cause the method as described in any one of claims 1-20 to be performed.

23. A computer program product, characterized in that, The system stores instructions that, when executed, cause the method as described in any one of claims 1-20 to be performed.

24. A communication device, characterized in that, The device includes one or more processors and interface circuitry, wherein the one or more processors are coupled to a memory for storing computer programs or instructions, which, when executed by the one or more processors, cause the device to perform the method as described in any one of claims 1-20.

25. The apparatus according to claim 24, characterized in that, The interface circuit is used to implement communication functions within the device and / or communication functions between the device and other devices or components.

Images