Data transmission method and related apparatus

Abstract

The present application relates to the technical field of communications. Provided in the present application are a data transmission method and a related apparatus, which are conducive to improving the flexibility of data transmission and improving the accuracy of model inference and / or a training task. The method comprises: an access network device sending first indication information to a terminal, wherein the first indication information is used for indicating a transmission condition and / or a transmission rule, the transmission rule is first in first out (FIFO) or last in first out (LIFO) of data in an LCH, and the transmission condition comprises at least one of the following: the remaining scheduling delay of the data is within a first delay range, the priority of the LCH where the data is located is greater than or equal to a first priority, the priority of an LCG where the data is located is greater than or equal to a second priority, the LCH where the data is located is a first LCH, or the LCG where the data is located is a first LCG; and performing data transmission on the basis of the transmission condition and / or the transmission rule.

Description

Data transmission method and related devices

[0001] This application claims priority to Chinese Patent Application No. 202411999769.9, filed with the China National Intellectual Property Administration on December 31, 2024, entitled “Data Transmission Method and Related Apparatus”, the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of communications, and more particularly to a data transmission method and related apparatus. Background Technology

[0003] Computing nodes can perform model inference based on the input data of artificial intelligence (AI) models. In this case, the terminal can obtain the input data of the AI ​​model and send the input data of the AI ​​model to the computing node, so that the computing node can perform model inference based on the input data.

[0004] The terminal can periodically acquire and transmit input data of the AI ​​model. If the data packet latency budget is greater than the transmission period, the terminal may have multiple untransmitted input data. When multiple input data are stacked on the terminal side, the terminal can transmit data according to the first-in-first-out (FIFO) rule.

[0005] However, before a computing node can perform model inference, it may not receive new input data, which can affect the accuracy of model inference. Summary of the Invention

[0006] This application provides a data transmission method and related apparatus, which helps to improve the accuracy of model reasoning.

[0007] In a first aspect, embodiments of this application provide a data transmission method that can be applied to the terminal side, such as a terminal or a communication / computing 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 system-on-chip (SoC) chip containing a modem core or a system-in-package (SIP) chip), or a circuit or chip in the terminal responsible for computing functions (such as a graphics processing unit (GPU), an AI processor, or an application-specific integrated circuit (ASIC)), or a logic node, logic module, or software that can implement all or part of the terminal functions. Taking the application of this method to a terminal as an example, in this method, the terminal receives first indication information, which is used to indicate transmission conditions and / or transmission rules. The transmission rules are data FIFO or last-in-first-out (LIFO) in a logical channel (LCH). The transmission conditions include at least one of the following: the remaining scheduling delay of the data is within the first delay range; the priority of the LCH where the data is located is greater than or equal to the first priority; the priority of the logical channel group (LCG) where the data is located is greater than or equal to the second priority; the LCH where the data is located is the first LCH; or the LCG where the data is located is the first LCG. The terminal performs data transmission based on the transmission conditions and / or transmission rules.

[0008] Using the above method, the terminal can transmit data based on the transmission conditions and / or transmission rules indicated by the first indication information. If the first indication information indicates transmission conditions, the terminal can transmit data that meets the transmission conditions. If the first information indicates transmission rules, the terminal can transmit data according to the transmission rules. If the first information indicates both transmission conditions and transmission rules, the terminal can transmit data that meets the transmission conditions and can transmit data according to the transmission rules. In this way, before the model inference and / or training task begins, the terminal can transmit the data acquired later, facilitating the computing node to perform model inference and / or training tasks, improving the flexibility of data transmission, and improving the accuracy of model inference and / or training tasks. It should be understood that the data acquired later is newer, and the data acquired earlier is older. The computing node performs model inference and / or training tasks based on the newer data, which helps improve the accuracy of model inference and / or training tasks.

[0009] In one possible design, the first delay range is related to the following information: the arrival time of the data and the data packet delay budget, or the remaining scheduling delay of the data; and the start time information of the model inference and / or training tasks. In this way, the access network device can instruct the terminal to transmit specified data based on the first delay range, improving the flexibility of data transmission and the accuracy of model inference and / or training tasks.

[0010] In one possible design, the start time information indicates the start time of the model inference and / or training task, or the duration between the start time of the model inference and / or training task and the current time. This allows the access network device to accurately determine the start time of the model inference and / or training task and, based on the start time, accurately instruct the terminal to transmit data, thereby improving the accuracy of data transmission.

[0011] In one possible design, the terminal can also send request information to request model inference and / or training tasks, with the data being the input data for these tasks. This allows computing nodes to allocate computing resources on demand, improving resource utilization.

[0012] In one possible design, the terminal can also receive output data from model inference and / or training tasks. This allows the terminal to acquire output data promptly and make quick decisions, reducing latency.

[0013] In this embodiment, the terminal can determine the data to be transmitted based on the transmission conditions and / or transmission rules indicated by the first indication information. Before the model inference and / or training task begins, if the terminal can transmit the data acquired after completion, the terminal can transmit the data acquired later. If the terminal cannot transmit the data acquired after completion, the terminal can transmit the data acquired earlier. This is beneficial to improving the flexibility of data transmission and improving the accuracy of model inference and / or training tasks.

[0014] Secondly, embodiments of this application provide a communication method that can be applied to the network side, such as an access network device, a module (e.g., a circuit, chip, or chip system) within the access network device, or a logical node, logical module, or software capable of implementing all or part of the functions of the access network device, or a circuit or chip (e.g., a GPU, AI processor, or ASIC) responsible for computational functions within the access network device. Taking the application of this method to an access network device as an example, in this method, the access network device can receive second indication information. The second indication information is used to indicate the start time of a model inference and / or training task, or the duration between the start time of the model inference and / or training task and the current time. The start time or duration is used to determine the input data for the model inference and / or training task. The access network device can send first indication information and receive data, which is the input data for the model inference and / or training task, based on the second indication information.

[0015] Using the above method, the access network device can determine whether the terminal can complete the transmission of the acquired data before the start of the model inference and / or training task, based on the start time of the model inference and / or training task, or the duration between the start time of the model inference and / or training task and the current time. If yes, the access network device can instruct the terminal to transmit the acquired data afterward based on the first instruction information. If no, the access network device can instruct the terminal to transmit the acquired data first based on the first instruction information. This helps to improve the flexibility of data transmission and the accuracy of the model inference and / or training task.

[0016] In one possible design, the first indication information is used to indicate transmission conditions and / or transmission rules, the transmission rules being data FIFO or LIFO in the LCH, and the transmission conditions including at least one of the following: the remaining scheduling delay of the data is within the first delay range, the priority of the LCH where the data is located is greater than or equal to the first priority, the priority of the LCG where the data is located is greater than or equal to the second priority, the LCH where the data is located is the first LCH, or the LCG where the data is located is the first LCG.

[0017] In one possible design, the first latency range is related to the following information: the arrival time of the data and the data packet latency budget, or the remaining scheduling latency of the data; and the start time information of the model inference and / or training tasks.

[0018] In one possible design, the start time information indicates the start time of the model inference and / or training task, or the duration between the start time of the model inference and / or training task and the current time.

[0019] In one possible design, the access network device can also receive and send request information, which is used to request model inference and / or training tasks, and the data is the input data for the model inference and / or training tasks.

[0020] In one possible design, the access network device can also receive and send input data for model inference and / or training tasks, and can also receive and send output data for model inference and / or training tasks. In this way, the access network device can act as a data transmission relay station, improving the flexibility and efficiency of data transmission.

[0021] In this embodiment, the access network device can determine whether the terminal can complete the transmission of acquired data before the model inference and / or training task begins, based on the second instruction information. Based on the determination result, it sends the first instruction information to instruct the terminal to transmit the data acquired later or the data acquired earlier. Thus, if the terminal can complete the transmission of acquired data before the model inference and / or training task begins, the access network device can instruct the terminal to transmit the data acquired later; if the terminal cannot complete the transmission of acquired data, the access network device can instruct the terminal to transmit the data acquired earlier. This improves the flexibility of data transmission and enhances the accuracy of the model inference and / or training task.

[0022] Thirdly, embodiments of this application provide a communication method that can be applied to a computing node. The computing node includes, for example, a radio access network (RAN) node, a core network node, an edge computing node, or a cloud service node. The method can be applied to a computing node, or a module within a computing node (e.g., a circuit, chip, or chip system), or a logic node, logic module, or software capable of implementing all or part of the functions of the computing node, or a circuit or chip (e.g., a GPU, AI processor, or ASIC) responsible for computing functions within a computing node. Taking the application of this method to a RAN node as an example, in this method, the RAN node can send second indication information, which indicates the start time of a model inference and / or training task, or the duration between the start time of the model inference and / or training task and the current time. The start time or duration is used to determine the input data for the model inference and / or training task, and the RAN node can execute the model inference and / or training task based on the input data.

[0023] Using the above method, the RAN node can send a second indication message so that the access network device can determine whether the terminal can transmit the subsequently acquired data to the RAN node before the model inference and / or training task begins. This can improve the flexibility of data transmission, and the RAN node can perform model inference and / or training tasks based on the subsequently acquired data, thereby improving the accuracy of the model inference and / or training tasks.

[0024] In one possible design, RAN nodes can also receive request information for requesting model inference and / or training tasks. This allows compute nodes to allocate computing resources on demand, improving resource utilization.

[0025] In one possible design, the computing node includes at least one of the following: a radio access network (RAN) node, a core network node, an edge computing node, or a cloud service node.

[0026] In one possible design, RAN nodes can also send output data for model inference and / or training tasks.

[0027] In this embodiment, the RAN node can send a second indication message to assist the access network device in sending the first indication message. Furthermore, if the terminal cannot transmit the subsequently acquired data to the RAN node before the model inference and / or training task begins, the access network device can instruct the terminal to transmit the previously acquired data. If the terminal can transmit the subsequently acquired data to the RAN node, the access network device can instruct the terminal to transmit the subsequently acquired data, so that the RAN node can perform model inference and / or training tasks based on the subsequently acquired data, which is beneficial to improving the accuracy of model inference and / or training tasks.

[0028] Fourthly, embodiments of this application provide a communication device that has the functions of the first aspect described above. For example, the communication device includes modules, units, or means corresponding to 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.

[0029] Fifthly, embodiments of this application provide a communication device that has the functions of the second aspect described above. For example, the communication device includes modules, units, or means corresponding to the operations involved in the second aspect described above. These modules, units, or means can be implemented by software, hardware, or a combination of software and hardware.

[0030] Sixthly, embodiments of this application provide a communication device that has the functions of the third aspect described above. For example, the communication device includes modules, units, or means that perform the operations involved in the second aspect described above. These modules, units, or means can be implemented by software, hardware, or a combination of software and hardware.

[0031] In a seventh aspect, embodiments of this application provide 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 first aspect. 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. 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.

[0032] In one possible design, the processor is used to communicate with other devices or components through the interface circuit.

[0033] In one possible design, the communication device may also include the memory.

[0034] The aforementioned communication device may be a terminal, or a communication / computing 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 computing functions (such as a GPU, AI processor, or ASIC), or a logic node or logic module that can implement all or part of the terminal functions.

[0035] Eighthly, embodiments of this application provide 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 can execute the computer program or instructions, causing the communication device to implement the methods in any possible design or implementation of the second 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.

[0036] In one possible design, the processor is used to communicate with other devices or components through the interface circuit.

[0037] In one possible design, the communication device may also include the memory.

[0038] The aforementioned communication device may be an access network device, or a communication / computing module in an access network device, or a module (e.g., a circuit, chip, or chip system) in an access network device, or a circuit or chip (e.g., a GPU, AI processor, or ASIC) in an access network device that is responsible for computing functions, or a logical node or logical module that can implement all or part of the functions of the access network device.

[0039] Ninthly, embodiments of this application provide 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 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 third 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.

[0040] In one possible design, the processor is used to communicate with other devices or components through the interface circuit.

[0041] In one possible design, the communication device may also include the memory.

[0042] The aforementioned communication device may be a computing node, or a communication / computing module in a computing node, or a module (e.g., a circuit, chip, or chip system) in a computing node, or a circuit or chip (e.g., a GPU, AI processor, or ASIC) in a computing node that is responsible for computing functions, or a logic node or logic module that can implement all or part of the functions of a computing node.

[0043] In a tenth aspect, embodiments of this application provide 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 third aspects described above.

[0044] In one aspect, embodiments of this application provide 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 third aspects described above.

[0045] In a twelfth aspect, this application provides a communication system, including a terminal for implementing the first aspect and any possible design of the first aspect, an access network device for implementing the second aspect and any possible design of the second aspect, and a computing node for implementing the third aspect and any possible design of the third aspect.

[0046] In a thirteenth aspect, this application provides a communication system including a terminal for implementing the methods of the first aspect and any possible design of the first aspect, and an access network device for implementing the methods of any possible design of the second to third aspects.

[0047] It should be understood that the fourth to thirteenth aspects of the embodiments of this application correspond to the technical solutions of the first to third aspects of this application, and the beneficial effects achieved by each aspect and the corresponding feasible implementation are similar, and will not be described again. Attached Figure Description

[0048] Figure 1 is a schematic diagram of a communication system applicable to an embodiment of this application;

[0049] Figures 2 and 3 are schematic diagrams of possible application frameworks for the communication system;

[0050] Figure 4 is a schematic diagram of a FIFO provided in an embodiment of this application;

[0051] Figure 5 is a schematic diagram of a LIFO provided in an embodiment of this application;

[0052] Figure 6 is a schematic diagram of data transmission provided in an embodiment of this application;

[0053] Figures 7-9 are schematic flowcharts of the communication method provided in the embodiments of this application;

[0054] Figure 10 shows a possible exemplary block diagram of the communication device involved in the embodiments of this application;

[0055] Figure 11 is a structural schematic diagram of a terminal 1100 provided in an embodiment of this application. Detailed Implementation

[0056] To facilitate understanding of the embodiments of this application, the following points will be explained first:

[0057] In this application, "instruction" can include direct instruction, indirect instruction, explicit instruction, and implicit instruction. When describing a certain instruction information for the purpose of instructing A, it can be understood that the instruction information carries A, directly instructs A, or indirectly instructs A.

[0058] In this application, "and / or" can be used to describe three relationships between related objects. For example, A and / or B can represent three cases: A exists alone, A and B exist simultaneously, and B exists alone. A and B can be singular or plural.

[0059] In this application, "at least one" means one or more, and "more than one" means two or more, such as three, four, or more. Similar expressions (such as at least one, at least one, etc.) are used in the same way. "At least one of the following," "one or more of the following," or similar expressions refer to any combination of these items, which may include only a single item or a combination of multiple items. For example, at least one of a, b, or c can mean: a, or b, or c; a and b; or a and c; or b and c; or a, b, and c. Where a, b, and c can be single or multiple.

[0060] In this application, for the convenience of describing the technical solutions of the embodiments of this application, the terms "first" and "second" may be used to distinguish them. The terms "first" and "second" do not limit the quantity or execution order, and the terms "first" and "second" are not necessarily different.

[0061] In this application, the words "exemplary," "example," or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary," "example," or "for example" should not be construed as being more preferred or advantageous than other embodiments or designs. The use of the words "exemplary," "example," or "for example" is intended to present the relevant concepts in a specific manner to facilitate understanding.

[0062] In this application, "sending information / data" can be understood as one device sending information / data to another device, or it can also be understood as one logical module within a device sending information / data 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.

[0063] In this application, "receiving information / data" can be understood as one device receiving information / data from another device, or it can also be understood as a logical module within a device receiving information / data 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.

[0064] 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.

[0065] In the embodiments shown below, the terms and abbreviations, such as Logical Channel (LCH), Logical Channel Group (LCG), First-In-First-Out (FIFO), Last-In-First-Out (LIFO), etc., are merely exemplary examples given for ease of description and should not constitute any limitation on this application. This application does not preclude the possibility of defining other terms that can achieve the same or similar functions in existing or future protocols.

[0066] The technical solutions of this application can be applied to various communication systems, such as Long Term Evolution (LTE) systems, 5th Generation (5G) communication systems, satellite communication systems, Wireless Fidelity (WiFi) systems, and the solutions provided in this application can also be applied to future communication systems or other communication systems. This application does not limit these applications.

[0067] The technical solutions in this application will now be described with reference to the accompanying drawings.

[0068] Figure 1 is a schematic diagram of a communication system applicable to an embodiment of this application. Figure 1 illustrates a possible, non-limiting system. As shown in Figure 1, the communication system 10 includes a RAN 100 and a core network (CN) 200. The 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). The RAN 100 may also include other RAN nodes, such as wireless relay devices and / or wireless backhaul devices (not shown in Figure 1). The terminal 120 is wirelessly connected to the RAN node 110. The RAN node 110 is wirelessly or wiredly connected to the core network 200. The core network devices in the core network 200 and the RAN node 110 in the RAN 100 can be different physical devices, or they can be the same physical device integrating core network logical functions and wireless access network logical functions.

[0069] RAN 100 can be a cellular system related to the 3rd Generation Partnership Project (3GPP), such as 4G, 5G mobile communication systems, or future-oriented evolution systems. RAN 100 can also be an open RAN (O-RAN or ORAN), cloud RAN (CRAN), virtualized RAN (vRAN), artificial intelligence RAN (AI RAN), or wireless fidelity (WiFi) system. RAN 100 can also be a communication system that integrates two or more of the above systems.

[0070] RAN node 110, sometimes referred to as access network equipment, RAN entity, or access node, constitutes part of the communication system and assists terminals in achieving 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; however, 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.

[0071] 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.

[0072] In another possible scenario, multiple RAN nodes collaborate to assist terminals in achieving wireless access, with different RAN nodes each implementing some of the base station's functions. For example, RAN nodes can be central units (CUs), distributed units (DUs), CU-control plane (CPs), CU-user plane (UPs), or radio units (RUs), etc. CUs, DUs, and SUs can be set up separately or included in the same network element, such as a baseband unit (BBU). RUs can be included in radio equipment or radio units, such as remote radio units (RRUs), active antenna units (AAUs), or remote radio heads (RRHs). Furthermore, RAN nodes can also be computing units, providing computing power for tasks (such as model inference and / or model training), and can also be used to implement one or more of the following: task partitioning, scheduling, and orchestration. The functionality of a computing unit can be implemented by a separate module independent of other units (e.g., CU, DU, RU), or by one or more other units (e.g., one or more of CU, DU, RU).

[0073] In different systems, CU (or CU-CP and CU-UP), DU, computing unit, 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, computing unit, and RU as examples. Any of the units among CU (or CU-CP, CU-UP), DU, computing unit, and RU in this application can be implemented through software modules, hardware modules, or a combination of software modules and hardware modules.

[0074] 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.

[0075] To support AI technology in wireless networks, AI nodes may also be introduced into the network.

[0076] AI nodes can be deployed in one or more of the following locations within the communication system: access network nodes (RAN nodes), terminal devices, or core network devices. Alternatively, AI nodes can be deployed independently, for example, in a location other than any of the aforementioned 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, terminal devices, or core network elements.

[0077] 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.

[0078] 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.

[0079] AI nodes can be AI network elements or AI modules.

[0080] 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 CU and DU. CU and / or DU can also be equipped with one or more AI modules. A CU can also be split into CU-CP and CU-UP, with one or more AI modules configured in CU-CP and / or CU-UP.

[0081] 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.

[0082] 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).

[0083] 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.

[0084] 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.

[0085] 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.

[0086] 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.

[0087] 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.

[0088] 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 ​​modules 117 and 118 shown in Figure 1, 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.

[0089] 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.

[0090] 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.

[0091] 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.

[0092] It should be understood that the system architecture described in this application is for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and does not constitute a limitation on the technical solutions provided in the embodiments of this application.

[0093] To better understand the methods provided in the embodiments of this application, the relevant technologies and concepts involved in this application are briefly described below.

[0094] 1. Logical Channel (LCH)

[0095] The LCH (Local Channel) is a service provided by the Media Access Control (MAC) sublayer to higher layers to represent the content carried. The MAC layer can provide data transmission services on the LCH. For example, the LCH can include control channels and service channels. Control channels can be used to transmit signaling or synchronization data, such as control information and system messages, while service channels can be used to transmit user data, such as voice data.

[0096] 2. Logical Channel Group (LCG)

[0097] LCGs are groups of logical channels divided to optimize uplink channel overhead. For example, a communication system can divide multiple uplink LCHs of a terminal into multiple LCGs, and different LCGs can have different priorities.

[0098] 3. First-In, First-Out (FIFO)

[0099] FIFO means that in a data structure or task queue, the data that arrives first will be processed or removed first. This ensures the order of data processing, so that data that arrives earlier can be processed with relative priority.

[0100] Figure 4 is a schematic diagram of a FIFO provided in an embodiment of this application. As shown in Figure 4, the terminal can acquire data 1 and data 2, and fill data 1 into the LCH first, followed by data 2. When the terminal transmits data in the LCH based on the FIFO, since data 1 enters the LCH first and data 2 enters the LCH later, the terminal can transmit data 1 first and then data 2.

[0101] 4. Last-In-First-Out (LIFO)

[0102] LIFO means that in a data structure or task queue, the data that enters last is processed or removed first. This ensures the real-time nature of data processing and allows newly acquired data to be processed with relative priority.

[0103] Figure 5 is a schematic diagram of a LIFO provided in an embodiment of this application. As shown in Figure 5, the terminal can acquire data 1 and data 2, and fill data 1 into the LCH first, followed by data 2. When the terminal transmits data in the LCH based on LIFO, since data 1 enters the LCH first and data 2 enters the LCH later, the terminal can transmit data 2 first and then data 1.

[0104] 5. Data packet latency budget.

[0105] The packet delay budget (PDB) represents the maximum allowable delay a data packet can experience during transmission. For example, a PDB of 160ms means that the maximum allowable delay for the data packet during transmission is 160ms. The data packet can be transmitted within 160ms, such as at 20ms, 50ms, 100ms, or 160ms. If the transmission delay exceeds 160ms, the data packet transmission fails. The PDB can be a pre-set value, such as 160ms, or it can be dynamically adjusted based on network load to adapt to network changes.

[0106] 6. Remaining scheduling delay.

[0107] The remaining scheduling delay indicates the remaining time a data packet is allowed to experience during transmission. For example, a remaining scheduling delay of 100ms means that the data packet is allowed to experience 100ms of remaining time during transmission, and the data packet can be transmitted within 100ms, such as at 20ms, 30ms, 50ms, or 100ms. If the data packet transmission exceeds 100ms, the data packet transmission fails. The remaining scheduling delay can be determined based on the PDB (Program Data Base). For example, if the PDB is 160ms, and the data packet has been acquired or transmitted for 40ms, then the corresponding remaining scheduling delay is 120ms (160ms - 40ms), meaning the data packet can be transmitted within 120ms; if it exceeds 120ms, the data packet transmission fails.

[0108] In related technologies, the terminal can be an intelligent robot. After acquiring an image, the intelligent robot can transmit the image to a computing node. The computing node performs model inference and / or training tasks based on the image and obtains control commands from the intelligent robot. The computing node can transmit control commands to the intelligent robot. Therefore, if the computing node performs model inference and / or training tasks based on the newly acquired image of the intelligent robot, the accuracy of the intelligent robot's control can be improved.

[0109] Figure 6 is a schematic diagram of data transmission provided in an embodiment of this application. As shown in Figure 6, the terminal can acquire data 1 at 0ms and data 2 at 100ms, and the computing node can start computing at 200ms. Since the PDB is 160ms, the terminal may not have transmitted data 1 at 100ms. The data to be transmitted in the terminal may include data 1 and data 2. The terminal can transmit data 1 first and then data 2 according to the FIFO rule. However, since the PDB is 160ms, the terminal may not have transmitted data 2 at the start of computing (200ms), or data 2 may not have been transmitted completely. The computing node can only perform computing based on data 1, which will affect the accuracy of model inference and / or training tasks.

[0110] To improve the accuracy of inference and / or training tasks, this application provides a communication method in which an access network device can determine, based on the start time information of the model inference and / or computation task, whether the terminal can transmit the data acquired after completion before the start of the model inference and / or computation task. If yes, the access network device can instruct the terminal to transmit the data acquired after completion based on a first indication. If no, the access network device can instruct the terminal to transmit the data acquired first based on the first indication. In this way, the computing node can perform model inference and / or training tasks based on the data acquired later, which helps to improve the flexibility of data transmission and improve the accuracy of model inference and / or training tasks.

[0111] The methods provided in the embodiments of this application will be described in detail below with reference to the accompanying drawings. It is understood that this application uses access network devices, terminals, and computing nodes as examples of the execution subjects in the interactive illustration, but this application does not limit the execution subjects of the interactive illustration. For example, the method executed by the access network device in this application can also be implemented by modules (e.g., circuits, chips, or chip systems) in the access network device, or by logical nodes, logical modules, or software that can implement all or part of the functions of the access network device, or by circuits or chips (e.g., GPUs, AI processors, or ASICs) in the access network device responsible for computing functions. Similarly, the method executed by the terminal in this application can also be implemented by a communication / computing module in the terminal, or by circuits or chips (e.g., modem chips (also known as baseband chips), or SoC chips / SIP chips containing modem cores, or GPUs / AI processors / ASICs) in the terminal responsible for communication / computing functions, or by logical nodes, logical modules, or software that can implement all or part of the terminal functions. The method executed by the computing node in this application can also be implemented by a communication module / computing module in the computing node, or a circuit or chip in the computing node responsible for communication functions, or a circuit or chip in the computing node responsible for computing functions (such as a GPU, AI processor, or ASIC), or a logic node, logic module, or software that can implement all or part of the computing node functions.

[0112] Figure 7 is a schematic flowchart of a communication method 700 provided in an embodiment of this application.

[0113] Method 700 includes steps S701 to S702, and each step will be described in detail below.

[0114] S701, the access network device sends a first indication information; correspondingly, the terminal receives the first indication information, which is used to indicate transmission conditions and / or transmission rules. The transmission rules are data FIFO or LIFO in LCH, and the transmission conditions include at least one of the following: the remaining scheduling delay of the data is within the first delay range, the priority of the LCH where the data is located is greater than or equal to the first priority, the priority of the LCG where the data is located is greater than or equal to the second priority, the LCH where the data is located is the first LCH, or the LCG where the data is located is the first LCG.

[0115] The first indication information can instruct the terminal to perform data transmission. For example, when the first indication information indicates transmission conditions, the terminal can transmit data that meets the transmission conditions; when the first indication information indicates transmission rules, the terminal can transmit data according to the transmission rules; when the first indication information indicates both transmission conditions and transmission rules, the terminal can transmit data that meets the transmission conditions and transmit data according to the transmission rules.

[0116] The transmission rule is either FIFO or LIFO for data in LCH.

[0117] Transmission conditions may include at least one of the following:

[0118] The remaining scheduling delay of the data is within the first delay range;

[0119] The priority of the LCH containing the data is greater than or equal to the first priority, or the priority of the LCH containing the data is greater than the first priority;

[0120] The priority of the LCG containing the data is greater than or equal to the second priority, or the priority of the LCG containing the data is greater than the second priority;

[0121] The LCH containing the data is the first LCH; or,

[0122] The LCG containing the data is the first LCG.

[0123] In some embodiments, the first delay range is related to the following information:

[0124] Data arrival time and data packet delay budget, or, the remaining scheduling delay of the data; and,

[0125] Start time information for model inference and / or training tasks.

[0126] The start time information for the model inference and / or training task can indicate the start time of the model inference and / or training task, or the duration between the start time of the model inference and / or training task and the current time. For example, the start time information can indicate at least one time, which can be the start time of the model inference and / or training task. For example, the start time information can indicate a duration, which can be the duration between the start time of the model inference and / or training task and the current time.

[0127] It should be understood that the start time of the model inference and / or training task, and the duration between the start time of the model inference and / or training task and the current time, can be an absolute time unit, such as seconds, milliseconds, or microseconds, or a time measurement unit of communication systems such as time slots, symbols, frames, subframes, or miniframes, or an absolute value.

[0128] Optionally, the first delay range can be determined based on the data arrival time, the data packet delay budget, and the start time information. For example, the data arrival time can be the data acquisition time. The access network device can determine the remaining scheduling delay of the data based on the data acquisition time, the current time, and the data packet delay budget, and determine the first delay range based on the remaining scheduling delay and the start time information. For example, if the data arrival time is 100ms, the current time is 120ms, the PDB is 160ms, and the access network device determines the remaining scheduling delay to be 140ms (160ms-120ms+100ms), when the access network device determines that the terminal should transmit the data based on the start time information, the access network device can determine the first delay range based on the remaining scheduling delay. The first delay range can be 120ms-150ms, that is, ensuring that the remaining scheduling delay of the data is within the first delay range determined by the access network device, so that the terminal can transmit the data.

[0129] Optionally, the first latency range can be determined based on the remaining scheduling latency of the data and the start time information of the model inference and / or training tasks. For example, the start time information is the duration between the start time of the model inference and / or training tasks and the current time. When the access network device determines that the terminal should transmit the data based on this duration, the access network device can determine the first latency range based on the remaining scheduling latency of the data. For example, if the remaining scheduling latency of the data is 30ms, and the access network device instructs the terminal to transmit the data, the first latency range can be 10ms-40ms.

[0130] The priority of the LCH can be the transmission priority of the data within the LCH. For example, the higher the priority of the LCH, the higher the transmission priority of the data within the LCH, and vice versa. For instance, when the priority of LCH1 is higher than the priority of LCH2, the terminal transmits the data in LCH1 with relative priority; when the priority of LCH1 is lower than the priority of LCH2, the terminal transmits the data in LCH2 with relative priority.

[0131] The priority of an LCG can be the transmission priority of the LCH within that LCG. For example, the higher the priority of an LCG, the higher the transmission priority of the LCH within that LCG; conversely, the lower the priority of an LCG, the lower the transmission priority of the LCH within that LCG. For instance, when the priority of LCG1 is higher than that of LCG2, the terminal transmits the LCH data in LCG1 with relative priority; when the priority of LCG1 is lower than that of LCG2, the terminal transmits the LCH data in LCG2 with relative priority.

[0132] The first priority can be the priority of LCH. For example, the priority of LCH can include low, medium, and high levels, and the first priority can be any one of these levels. The second priority can be the priority of LCG. For example, the priority of LCG can include low, medium, and high levels, and the second priority can be any one of these levels.

[0133] It should be understood that the priority of LCH and the priority of LCG can be a priority predetermined by the access network device, a priority sent to the access network device by the terminal after determination, or a priority agreed upon in advance by the access network device and the terminal.

[0134] The first LCH can be a specified LCH. For example, the access network device can instruct the terminal to transmit data in a specified LCH according to the first indication information, and the specified LCH can be the first LCH.

[0135] The first LCG can be a designated LCG. For example, the access network device can instruct the terminal to transmit LCH data in a designated LCG based on the first indication information, and the designated LCG can be the first LCG.

[0136] It is understood that the transmission rules in the embodiments of this application can also be the reading rules of the buffer queue, such as the data FIFO or LIFO in the buffer queue.

[0137] It is understood that in the embodiments of this application, the access network device may pre-configure an LCH that can perform FIFO and LIFO switching. The access network device may also pre-configure an LCH with FIFO transmission rules and an LCH with LIFO transmission rules in an LCG. It should be understood that the information pre-configured by the access network device may also be pre-agreed upon by the access network device and the terminal. The embodiments of this application do not limit this.

[0138] S702, the terminal transmits data based on transmission conditions and / or transmission rules; correspondingly, the access network equipment receives the transmitted data.

[0139] It should be understood that data transmission by the terminal can refer to air interface transmission of data, or to transmission of data between modules within the terminal, or to preparation and / or preprocessing of data before transmission. This application embodiment does not limit this.

[0140] When the first indication information includes a transmission rule, the terminal can transmit data based on the transmission rule. When the transmission rule is FIFO of data in LCH, the terminal can transmit the data that enters LCH first with relative priority, according to the order in which the data enters LCH. When the transmission rule is LIFO of data in LCH, the terminal can transmit the data that enters LCH later with relative priority, according to the order in which the data enters LCH.

[0141] When the first indication information includes transmission conditions, the terminal can transmit data that meets the transmission conditions.

[0142] In some embodiments, when the remaining scheduling delay of the data is within a first delay range, the terminal can transmit data whose remaining scheduling delay is within the first delay range. For example, the terminal includes data 1 and data 2, where the remaining scheduling delay of data 1 is 40ms and the remaining scheduling delay of data 2 is 120ms. When the first delay range is 10ms-50ms, the terminal can transmit data 1; when the first delay range is 100ms-120ms, the terminal can transmit data 2.

[0143] In some embodiments, when the transmission condition is that the priority of the LCH containing the data is greater than or equal to the first priority, the terminal can transmit data in the LCH with a priority greater than or equal to the first priority. For example, the terminal includes LCH1 and LCH2, where LCH1 has a low priority and LCH2 has a medium priority. If the first priority is medium, the terminal can transmit data in LCH2.

[0144] In some embodiments, when the transmission condition is that the priority of the LCH containing the data is greater than the first priority, the terminal can transmit data from the LCH with a higher priority than the first priority. For example, the terminal includes LCH1 and LCH2, where LCH1 has a medium priority and LCH2 has a high priority. If the first priority is medium, the terminal can transmit data from LCH2.

[0145] In some embodiments, when the transmission condition is that the priority of the LCG containing the data is greater than or equal to the second priority, the terminal can transmit the LCH data in the LCG with a priority greater than or equal to the second priority. For example, the terminal includes LCG1 and LCG2, where LCG1 has a low priority and LCG2 has a medium priority. If the second priority is medium, the terminal can transmit the LCH data in LCG2.

[0146] In some embodiments, when the transmission condition is that the priority of the LCG containing the data is greater than the second priority, the terminal can transmit the LCH data in the LCG with a priority greater than the second priority. For example, the terminal includes LCG1 and LCG2, where LCG1 has a medium priority and LCG2 has a high priority. If the second priority is medium, the terminal can transmit the LCH data in LCG2.

[0147] In some embodiments, when the transmission condition is that the LCH containing the data is the first LCH, the terminal can transmit the data in the first LCH. For example, the terminal may include LCH1 and LCH2. If the first LCH in the transmission condition is LCH1, the terminal can transmit the data in LCH1; if the first LCH in the transmission condition is LCH2, the terminal can transmit the data in LCH2.

[0148] In some embodiments, when the transmission condition is that the LCG containing the data is the first LCG, the terminal can transmit the LCH data in the first LCG. For example, the terminal may include LCG1 and LCG2. If the first LCG in the transmission condition is LCG1, the terminal can transmit the LCH data in LCG1. If the first LCG in the transmission condition is LCG2, the terminal can transmit the LCH data in LCG2.

[0149] In some embodiments, the transmission condition can be the remaining scheduling delay of the data within a first delay range, and the transmission rule can be LIFO or FIFO for the data in the LCH. The terminal can transmit data according to the transmission condition and transmission rule. For example, the terminal includes multiple data items with remaining scheduling delays within the first delay range, and these multiple data items are in the same LCH. The terminal can transmit these multiple data items according to the LIFO or FIFO rule. For example, the terminal includes LCH1 and LCH2. When the transmission rule is LIFO or FIFO, the transmission of the two data items (one data item in LCH1 and one data item in LCH2) will overlap. Therefore, the terminal can transmit the data items with remaining scheduling delays within the first delay range. In this way, the terminal can dynamically adjust the data transmission order according to the remaining scheduling delay, and when data transmission overlaps, the terminal can sort and transmit multiple data items according to the LIFO or FIFO rule, improving data transmission efficiency and reducing data transmission latency.

[0150] In some embodiments, the transmission condition can be that the LCH containing the data has a priority greater than the first priority, or that the LCH containing the data has a priority greater than or equal to the first priority. The transmission rule can be LIFO or FIFO, and the terminal can transmit data according to the transmission condition and transmission rule. For example, if an LCH with a priority greater than the first priority contains multiple data items, the terminal can transmit the multiple data items according to the LIFO or FIFO rule. For example, if the LCH has a priority greater than the first priority and contains data 1 and data 2, with data 1 entering first and data 2 entering later, if the transmission rule is FIFO, the terminal will transmit data 1 with relative priority; if the transmission rule is LIFO, the terminal will transmit data 2 with relative priority. In this way, the terminal can transmit higher-priority data with relative priority, reducing the data transmission delay in higher-priority LCHs. Furthermore, when a higher-priority LCH contains multiple data items, the terminal can flexibly transmit data according to the LIFO or FIFO rule, improving the efficiency of data transmission.

[0151] In some embodiments, the transmission condition can be that the priority of the LCG containing the data is greater than the second priority, or that the priority of the LCG containing the data is greater than or equal to the second priority. The transmission rule can be LIFO or FIFO, and the terminal can transmit data according to the transmission condition and transmission rule. For example, if an LCG with a priority greater than the second priority includes an LCH, and the LCH includes multiple data, the terminal can transmit multiple data according to the LIFO or FIFO rule. For example, if the LCG has a priority greater than the second priority, and the LCG includes an LCH, with data 1 entering first and data 2 entering later in the LCH, if the transmission rule is FIFO, the terminal transmits data 1 with relative priority; if the transmission rule is LIFO, the terminal transmits data 2 with relative priority. Since the priority of the LCG can precisely control the order of data transmission in different LCHs, the complexity of the communication system's management logic channel can be reduced, as can the complexity of data transmission.

[0152] In some embodiments, the transmission conditions can be that the LCH containing the data is the first LCH, and the transmission rules can be LIFO or FIFO. The terminal can transmit data according to the transmission conditions and transmission rules. For example, when the first LCH includes multiple data items, the terminal can transmit data based on the LIFO or FIFO rules. In this way, the terminal can transmit data in the LCH indicated by the access network device with relatively priority, improving the flexibility of data transmission. Furthermore, when the first LCH includes multiple data items, the terminal can sort and transmit the multiple data items according to the LIFO or FIFO rules, improving the efficiency of data transmission and reducing the latency of data transmission.

[0153] In some embodiments, the transmission conditions can be that the LCG containing the data is the first LCG, and the transmission rules can be LIFO or FIFO. The terminal can transmit data according to the transmission conditions and transmission rules. For example, when the first LCG includes an LCH, and the LCH includes multiple data, the terminal can transmit multiple data in the LCH based on the LIFO or FIFO rules. In this way, the access network device can manage the data transmission in the LCH according to the LCG, reducing the management complexity of data transmission and improving the efficiency of data transmission.

[0154] In some embodiments, the transmission conditions can be that the priority of the LCG containing the data is greater than the second priority, or the priority of the LCG containing the data is greater than or equal to the second priority, and the priority of the LCH containing the data is greater than the first priority, or the priority of the LCH containing the data is greater than or equal to the first priority. The terminal can transmit data according to the transmission conditions. For example, if the LCG with a priority greater than the second priority includes multiple LCHs, the terminal can determine the LCH with a priority greater than the first priority among the multiple LCHs and transmit the data in that LCH with relative priority. If the LCH contains multiple data and the first indication information does not indicate a transmission rule, the terminal transmits the multiple data based on the default transmission rule. If the LCH contains multiple data and the first indication information indicates a transmission rule, the terminal transmits the multiple data based on the transmission rule. In this way, data transmission is jointly determined by the priority of the LCG and the priority of the LCH. The access network device can flexibly manage the priority of data transmission at different levels and reasonably allocate transmission resources, thereby improving the flexibility and efficiency of data transmission.

[0155] In some embodiments, the transmission conditions may be that the remaining scheduling delay of the data is within a first delay range, and the priority of the LCH containing the data is greater than the first priority, or the priority of the LCH containing the data is greater than or equal to the first priority. The terminal can transmit data based on the transmission conditions. For example, if the remaining scheduling delay of multiple data items is within the first delay range and the multiple data items are in multiple LCHs, the terminal can transmit data in LCHs with a priority greater than the first priority. When LCHs with a priority greater than the first priority also contain multiple data items, if the first indication information includes transmission rules, the terminal transmits the multiple data items according to the transmission rules. If the first indication information does not include transmission rules, the terminal can transmit data with a larger or smaller remaining scheduling delay. For example, a terminal includes LCH4 and LCH5. The remaining scheduling delays of data 1, data 2, and data 3 in the terminal are within a first delay range. Data 1 and data 2 are in LCH4, with data 1 entering LCH4 first and data 2 entering LCH4 later. Data 3 is in LCH5. When the priority of LCH4 is higher than the first priority and the priority of LCH5 is lower than the first priority, the terminal can transmit data 1 and data 2 from LCH4. When the transmission rule is FIFO, the terminal transmits data 1 with relative priority. When the transmission rule is LIFO, the terminal transmits data 2 with relative priority. When the first indication information does not indicate a transmission rule, and the remaining scheduling delay of data 1 is relatively large, the terminal can transmit data 1 with relative priority. In this way, data transmission is jointly determined by the remaining scheduling delay, the priority of LCH, and the transmission rule. While ensuring the transmission of higher priority data, the newness of the data can also be considered when transmitting data, improving the accuracy and flexibility of data transmission.

[0156] In some embodiments, the transmission conditions can be that the remaining scheduling delay of the data is within a first delay range, and the LCH where the data is located is a first LCH. The terminal can transmit data based on the transmission conditions. For example, the terminal includes multiple data items with remaining scheduling delays within the first delay range, and these multiple data items are located in multiple LCHs. The terminal can transmit data in the first LCH. For example, the first LCH includes multiple data items, and the terminal can transmit data items with remaining scheduling delays within the first delay range. For example, the first LCH includes data 1 and data 2. When the remaining scheduling delay of data 1 is within the first delay range, the terminal can transmit data 1 with relative priority. When the remaining scheduling delay of data 2 is within the first delay range, the terminal can transmit data 2 with relative priority. When the remaining scheduling delays of both data 1 and data 2 are within the first delay range, if the first indication information includes transmission rules, the terminal can transmit data 1 and data 2 according to the transmission rules. If the first indication information does not include transmission rules, the terminal can transmit data items with larger or smaller remaining scheduling delays with relative priority. In this way, the terminal can accurately determine the data to be transmitted based on the remaining scheduling delay of the data and the LCH where the data is located, thereby improving the accuracy of data transmission.

[0157] In some embodiments, the transmission conditions can be that the LCG containing the data is the first LCG, and the LCH containing the data has a priority greater than the first priority, or the LCH containing the data has a priority greater than or equal to the first priority. The transmission rule can be LIFO or FIFO for the data in the LCH. The terminal can transmit data based on the transmission conditions and transmission rules. For example, the first LCG may include multiple LCHs. The terminal can transmit data in LCHs with a priority greater than the first priority. When an LCH with a priority greater than the first priority also includes multiple data, the terminal can transmit multiple data based on the LIFO or FIFO rule. For example, the first LCG includes LCH4 and LCH5, where LCH4 includes data 1 and data 2, with data 1 entering LCH4 first and data 2 entering LCH4 later. LCH5 includes data 3. When the priority of LCH4 is greater than the first priority and the priority of LCH5 is less than the first priority, the terminal can transmit data 1 and data 2 in LCH4. When the transmission rule is FIFO, the terminal transmits data 1 with relative priority; when the transmission rule is LIFO, the terminal transmits data 2 with relative priority. In this way, the terminal can transmit data according to the priority of LCG and LCH, which improves the flexibility of data transmission. Furthermore, this data transmission method can support diverse application scenarios and meet the requirements of different application scenarios for data flexibility and controllability.

[0158] In some embodiments, the transmission conditions can be that the LCG containing the data is the first LCG, the LCH containing the data is the first LCH, and the transmission rule can be LIFO or FIFO for the data in the LCH. The terminal can transmit data based on the transmission conditions and transmission rules. For example, the first LCG may include multiple LCHs, and the terminal can transmit data in the first LCH. When the first LCH also includes multiple data, the terminal can transmit multiple data based on the LIFO or FIFO rule. For example, the first LCG includes LCH4 and LCH5, where LCH4 includes data 1 and data 2, with data 1 entering LCH4 first and data 2 entering LCH4 later, and LCH5 includes data 3. When LCH4 is the first LCH, the terminal can transmit data 1 and data 2 in LCH4. When the transmission rule is FIFO, the terminal transmits data 1 with relative priority; when the transmission rule is LIFO, the terminal transmits data 2 with relative priority. In this way, the terminal can transmit data in the first LCG and the first LCH, achieving fine-grained management of data transmission and improving the accuracy and controllability of data transmission.

[0159] In the embodiment described in conjunction with method 700 above, the access network device can send first indication information to the terminal, and the terminal can perform data transmission according to the first indication information. When the first indication information indicates transmission conditions, the terminal can transmit data that meets the transmission conditions; when the first information indicates transmission rules, the terminal can transmit data according to the transmission rules; when the first information indicates both transmission conditions and transmission rules, the terminal can transmit data that meets the transmission conditions and can transmit data according to the transmission rules. In this way, before model inference begins, the terminal can transmit the data acquired later, facilitating model inference by the computing nodes, improving the flexibility of data transmission, and improving the accuracy of model inference.

[0160] Based on the embodiments described in method 700, model inference and / or training tasks can be performed in the access network device. Hereinafter, with reference to Figure 8, another communication method will be described in detail.

[0161] Figure 8 is a schematic flowchart of another communication method 800 provided in an embodiment of this application.

[0162] Method 800 includes S801 to S806.

[0163] S801, The terminal sends a request message, which is used to request model inference and / or training tasks; accordingly, the access network device receives the request message.

[0164] The terminal can send a request message to the access network device, which can then prepare to execute model inference and / or training tasks. The data transmitted by the terminal can be the input data for the model inference and / or training tasks.

[0165] S802. The access network device determines first indication information, which is used to indicate transmission conditions and / or transmission rules. The transmission rules are data FIFO or LIFO in LCH, and the transmission conditions include at least one of the following:

[0166] The remaining scheduling delay of the data is within the first delay range;

[0167] The priority of the LCH containing the data is greater than or equal to the first priority, or the priority of the LCH containing the data is greater than the first priority;

[0168] The priority of the LCG containing the data is greater than or equal to the second priority, or the priority of the LCG containing the data is greater than the second priority;

[0169] The LCH containing the data is the first LCH; or,

[0170] The LCG containing the data is the first LCG.

[0171] The access network device can determine the start time information of the model inference and / or training task and the arrival time of the data subsequently acquired in the terminal, and determine the first indication information based on the start time information of the model inference and / or training task and the arrival time of the data subsequently acquired in the terminal.

[0172] In some embodiments, the access network device can determine whether the terminal can transmit the subsequently acquired data to the access network device before the start of the model inference and / or training task, based on the start time information of the model inference and / or training task and the arrival time of the subsequently acquired data in the terminal, and determine the first indication information based on the determination result. For example, the access network device can determine the duration between the start time of the model inference and / or training task and the current time based on the start time information, and determine whether the terminal can complete the transmission of the acquired data within that duration. For example, if the start time of the model inference and / or training task is 150ms, and the terminal acquires new data at 100ms, the access network device can determine whether the terminal can complete the transmission of the new data within 50ms after scheduling communication resources, and determine the first indication information based on the determination result.

[0173] It should be understood that after acquiring data, the terminal can transmit data information to the access network device. This data information may include at least one of the following: the data acquisition time, the LCH (Local Chronology Center) where the data is located, the LCG (Local Group) where the data is located, the priority of the LCH where the data is located, and the priority of the LCG where the data is located. In this way, the access network device can determine the data acquired by the terminal and the LCH or LCG where the data is located, thus enabling the access network device to accurately determine the first indication information. For example, after acquiring data, the terminal can transmit data information to the access network device. The terminal can also acquire multiple data sets before transmitting data information to the access network device. The access network device can determine the data acquisition period of the terminal. Thus, after the terminal transmits data information once, the access network device can determine the data acquired by the terminal based on this period. For example, if the terminal acquires data every 100ms, and transmits data to the access network device at 0ms, the access network device can determine at 230ms that the terminal acquired data at 100ms and 200ms.

[0174] In some embodiments, if the access network device determines that the terminal can complete data transmission before the start of the model inference and / or training task, the first indication information determined by the access network device is used to indicate the data to be acquired after the terminal transmits the data.

[0175] For example, the first indication information can be used to indicate a transmission rule, which can be LIFO.

[0176] For example, the first indication information can be used to indicate transmission conditions, which can be the remaining scheduling delay of the data within the first delay range, or it can be understood as the remaining scheduling delay of the data acquired by the terminal within the first delay range.

[0177] For example, the first indication information can be used to indicate transmission conditions, which can be that the LCH containing the data has a higher priority than the first priority, or that the LCH containing the data has a higher priority than or equal to the first priority. Alternatively, it can be understood that the LCH containing the data first acquired by the terminal has a higher priority than the first priority, or that the LCH containing the data first acquired by the terminal has a higher priority than or equal to the second priority.

[0178] For example, the first indication information can be used to indicate transmission conditions, which can be that the LCG containing the data has a higher priority than the second priority, or that the LCG containing the data has a higher priority than or equal to the second priority. Alternatively, it can be understood that the LCG containing the data acquired after the terminal has a higher priority than the second priority, or that the LCG containing the data acquired after the terminal has a higher priority than or equal to the second priority.

[0179] For example, the first indication information can be used to indicate transmission conditions, which can be that the LCH where the data is located is the first LCH. Alternatively, it can be understood that the LCH where the data obtained later by the terminal is located is the first LCH in the transmission conditions.

[0180] For example, the first indication information can be used to indicate transmission conditions, which can be that the LCG where the data is located is the first LCG. Alternatively, it can be understood that the LCG where the data acquired by the terminal is located is the first LCG in the transmission conditions.

[0181] It should be understood that the first indication information can be used to indicate transmission conditions and transmission rules. The transmission conditions can include any of the above conditions, and the transmission rules can be LIFO. In this way, the terminal can transmit newly acquired data, enabling the access network device to perform model inference and / or training tasks based on the newly acquired data, thereby improving the accuracy of model inference and / or training tasks.

[0182] In some embodiments, if the access network device determines that the terminal cannot complete data transmission before the start of the model inference and / or training task, the first indication information determined by the access network device is used to instruct the terminal to transmit the data acquired first.

[0183] For example, the first indication information can be used to indicate a transmission rule, which can be a FIFO.

[0184] For example, the first indication information can be used to indicate transmission conditions, which can be the remaining scheduling delay of the data within the first delay range, or it can be understood as the remaining scheduling delay of the data first acquired by the terminal being within the first delay range.

[0185] For example, the first indication information can be used to indicate transmission conditions, which can be that the LCH containing the data has a higher priority than the first priority, or that the LCH containing the data has a higher priority than or equal to the first priority. Alternatively, it can be understood that the LCH containing the data first acquired by the terminal has a higher priority than the first priority, or that the LCH containing the data first acquired by the terminal has a higher priority than or equal to the first priority.

[0186] For example, the first indication information can be used to indicate transmission conditions, which can be that the LCG containing the data has a higher priority than the second priority, or that the LCG containing the data has a higher priority than or equal to the second priority. Alternatively, it can be understood that the LCG containing the data first acquired by the terminal has a higher priority than the second priority, or that the LCG containing the data first acquired by the terminal has a higher priority than or equal to the second priority.

[0187] For example, the first indication information can be used to indicate transmission conditions, which can be that the LCH where the data is located is the first LCH. Alternatively, it can be understood that the LCH where the data first acquired by the terminal is located is the first LCH in the transmission conditions.

[0188] For example, the first indication information can be used to indicate transmission conditions, which can be that the LCG where the data is located is the first LCG. Alternatively, it can be understood that the LCG where the data first acquired by the terminal is located is the first LCG in the transmission conditions.

[0189] It should be understood that the first indication information can be used to indicate transmission conditions and transmission rules. The transmission conditions can include any of the above conditions, and the transmission rules can be FIFO. In this way, the terminal can transmit the data acquired first, ensuring that the access network device can perform model inference and / or training tasks, thereby improving the robustness of model inference and / or training tasks.

[0190] S803, the access network device sends the first instruction information; correspondingly, the terminal receives the first instruction information.

[0191] S804. The terminal transmits data based on transmission conditions and / or transmission rules, and the data is input data for model inference and / or training tasks; correspondingly, the access network device receives the input data.

[0192] S805. The access network device performs model inference and / or training tasks based on the input data to obtain the output data of the model inference and / or training tasks.

[0193] The access network device can process the input data according to the model to obtain the output data of the model inference and / or training tasks. The model involved in the model inference and / or training tasks can be an AI model. The process by which the access network device performs AI model inference and / or training tasks will not be described in detail in this embodiment.

[0194] S806. The access network device sends the output data of the model inference and / or training tasks; correspondingly, the terminal receives the output data of the model inference and / or training tasks.

[0195] Output data can be the model's inference results on the input data and / or the training results of the training task. These inference and / or training results can serve as control commands or instruction control commands. The terminal can perform related operations based on these inference and / or training results. For example, if the terminal's input data is an image, and the access network device's output data is a control command, the terminal can perform related operations according to this control command. For instance, when a smart robot grasps an object, it can send a captured image to the access network device. The access network device can then obtain a control command based on this image. This control command can control the smart robot's robotic arm to move to the left. When the smart robot receives this control command, it can control its robotic arm to move to the left.

[0196] In the embodiment described in conjunction with method 800 above, the access network device can determine first indication information and send it to the terminal. The terminal can transmit data according to the first indication information. The access network device can perform model inference and / or training tasks based on the data transmitted by the terminal, obtain output data, and send the output data to the terminal. The terminal can perform related operations based on the output data. The access network device can determine whether the terminal can complete the transmission of the acquired data before the model inference and / or training tasks begin. If so, the first indication information determined by the access network device instructs the terminal to transmit the acquired data afterward. If not, the first indication information determined by the access network device instructs the terminal to transmit the acquired data first. This improves the flexibility of data transmission and the accuracy of model inference.

[0197] It should be noted that the various processing steps (S801-S806) shown in the embodiment of FIG8 do not constitute a specific limitation on the communication method. In other embodiments of this application, the communication method may include more or fewer steps than in the embodiment of FIG8. For example, the communication method may include some of the steps in the embodiment of FIG8, or some steps in the embodiment of FIG8 may be replaced by steps with the same function, or some steps in the embodiment of FIG8 may be split into multiple steps, etc.

[0198] For example, in the embodiment shown in FIG8, S801 can be an optional step. In this case, the access network device can determine the first indication information independently of the request information sent by the terminal. For example, the access network device can determine the first indication information periodically, or the access network device can determine the first indication information triggered by other events.

[0199] For example, in the embodiment shown in FIG8, S806 can be an optional step. In this case, after the access network device obtains the output data, it can store the output data, etc.

[0200] Based on the embodiments described in methods 700 and 800, model inference and / or training tasks can be performed in computing nodes. Below, with reference to Figure 9, another communication method will be described in detail.

[0201] Figure 9 is a schematic flowchart of another communication method 900 provided in an embodiment of this application.

[0202] Method 900 includes S901 to S910.

[0203] S901, The terminal sends a request message, which is used to request model inference and / or training tasks; accordingly, the access network device receives the request message.

[0204] The terminal can send a request message to the access network device, and the access network device can forward the request message to the computing node to request the computing node to prepare to execute model inference and / or training tasks. The data transmitted by the terminal can be the input data for the model inference and / or training tasks.

[0205] S902, the access network device sends a request message; correspondingly, the computing node receives the request message.

[0206] Access network devices can forward request information.

[0207] A computing node includes at least one of the following: a Radio Access Network (RAN) node, a core network node, an edge computing node, or a cloud service node. For example, a computing node can be an RAN node or a device within an RAN node that performs model inference and / or training tasks. For example, a computing node can be a core network node or a device within a core network node that performs model inference and / or training tasks. For example, a computing node can be an edge computing node, a device within an edge computing node that performs model inference and / or training tasks, a mobile edge computing node, or a device within a mobile edge computing node that performs model inference and / or training tasks. For example, a computing node can be a cloud service node, a device within a cloud service node that performs model inference and / or training tasks, a cloud server node, or a device within a cloud server node that performs model inference and / or training tasks. For example, a computing node may also include a distributed computing node, an Internet of Things (IoT) node, etc.

[0208] S903, the computing node sends a second indication information, which is used to indicate the start time of the model inference and / or training task, or the duration between the start time of the model inference and / or training task and the current time; accordingly, the access network device receives the second indication information.

[0209] The second indication information may indicate at least one time, which may be the start time of the model inference and / or training task. The second indication information may also indicate a duration, which may be the duration from the current time to the start of the model inference and / or training task.

[0210] The start time or duration can be used to determine the input data for model inference and / or training tasks. For example, the access network device can send a first indication message to the terminal based on the start time or duration, and the terminal can transmit the input data for model inference and / or training tasks based on the first indication message. The specific process can be referred to the method in the above embodiments, and will not be repeated here.

[0211] In some embodiments, when the computing node is a RAN node, the RAN includes SU, CU and DU, and the second indication information can be transmitted based on the interface between SU, CU and DU.

[0212] In some embodiments, when the computing node is a core network node, the second indication information can be transmitted based on the control plane or the user plane.

[0213] In some embodiments, when the computing node is an edge computing node or a cloud service node, the second indication information can be transmitted based on the IP header.

[0214] In some embodiments, when the number of computing nodes is greater than 1, multiple computing nodes need to be synchronized, or the synchronization error is less than a preset error, which is small and can be at the millisecond level.

[0215] S904. The access network device determines the first indication information based on the second indication information. The first indication information is used to indicate transmission conditions and / or transmission rules. The transmission rules are data FIFO or LIFO in LCH. The transmission conditions include at least one of the following:

[0216] The remaining scheduling delay of the data is within the first delay range;

[0217] The priority of the LCH containing the data is greater than or equal to the first priority, or the priority of the LCH containing the data is greater than the first priority;

[0218] The priority of the LCG containing the data is greater than or equal to the second priority, or the priority of the LCG containing the data is greater than the second priority;

[0219] The LCH containing the data is the first LCH; or

[0220] The LCG containing the data is the first LCG.

[0221] S905, the access network device sends the first instruction information; correspondingly, the terminal receives the first instruction information.

[0222] S906. The terminal transmits data based on transmission conditions and / or transmission rules, and the data is input data for model inference and / or training tasks; correspondingly, the access network equipment receives the input data.

[0223] S907: The access network device sends input data; correspondingly, the computing node receives the input data.

[0224] S908, the computing node performs model inference and / or training tasks based on the input data to obtain the output data of the model inference and / or training tasks.

[0225] S909, the computing node sends the output data of the model inference and / or training tasks; correspondingly, the access network device receives the output data of the model inference and / or training tasks.

[0226] S910, the access network device sends the output data of the model inference and / or training tasks; correspondingly, the terminal receives the output data of the model inference and / or training tasks.

[0227] In the embodiment described in conjunction with method 900 above, the terminal can send a request message to the access network device, the access network device can forward the request message to the computing node, the computing node can send a second indication message to the access network device, the access network device can determine a first indication message based on the second indication message, and send the first indication message to the terminal, the terminal sends data to the access network device based on the first indication message, the access network device can send the data to the computing node, the computing node performs model inference and / or training tasks based on the data, obtains the output data of the model inference and / or training tasks, and sends the output data to the access network device, the access network device can forward the output data to the terminal, and the terminal can perform related operations based on the output data. This makes reasonable use of computing resources and avoids waste of computing resources. Furthermore, the access network device can flexibly instruct the terminal to perform data transmission, improving the flexibility of data transmission. Moreover, if the terminal can complete the transmission of new data before the start of the model inference and / or training task, the access network device can instruct the terminal to transmit new data so that the model inference and / or training task can be executed based on the new data, improving the accuracy of the model inference and / or training task.

[0228] It should be noted that the various processing steps (S901-S910) shown in the embodiment of FIG9 do not constitute a specific limitation on the communication method. In other embodiments of this application, the communication method may include more or fewer steps than that in the embodiment of FIG9. For example, the communication method may include some of the steps in the embodiment of FIG9, or some steps in the embodiment of FIG9 may be replaced by steps with the same function, or some steps in the embodiment of FIG9 may be split into multiple steps, etc.

[0229] For example, in the embodiment shown in Figure 9, steps S901 and S902 can be optional. In this case, the computing node can send the second indication information without relying on the request information forwarded by the access network device. For example, the computing node can send the second indication information periodically, or the computing node can send the second indication information triggered by other events.

[0230] For example, in the embodiment shown in Figure 9, S909 and S910 can be optional steps. In this case, after the computing node obtains the output data, it can store the output data, etc.

[0231] The communication method according to the embodiments of this application has been described in detail above with reference to Figures 7, 8 and 9. The communication device according to the embodiments of this application will be described in detail below with reference to Figures 10 and 11.

[0232] Figure 10 illustrates a possible exemplary block diagram of the communication device involved in the embodiments of this application. As shown in Figure 10, the communication device 1000 may include modules or units for implementing the methods described above. In one possible design, the communication device 1000 includes a processing unit 1002 and a communication unit 1003. Optionally, the communication device 1000 may further include a storage unit 1001 for storing device program code and / or data.

[0233] The communication device 1000 can be a terminal-side device as described 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.

[0234] For example, in one embodiment, the communication unit 1003 is configured to: receive first indication information, the first indication information being used to indicate transmission conditions and / or transmission rules, the transmission rules being either FIFO or LIFO for data in the LCH, and the transmission conditions including at least one of the following: the remaining scheduling delay of the data is within a first delay range, the priority of the LCH where the data is located is greater than or equal to a first priority, the priority of the logical channel group (LCG) where the data is located is greater than or equal to a second priority, the LCH where the data is located is a first LCH, or the LCG where the data is located is a first LCG; the processing unit 1001 is configured to: perform data transmission based on the transmission conditions and / or transmission rules.

[0235] In one possible design, the first delay range is related to the following information:

[0236] Data arrival time and data packet delay budget, or, the remaining scheduling delay of the data; and,

[0237] Start time information for model inference and / or training tasks.

[0238] In one possible design, the start time information indicates the start time of the model inference and / or training task, or the duration between the start time of the model inference and / or training task and the current time.

[0239] In one possible design, the communication unit 1003 is also used to: send request information, the request information being used to request model inference and / or training tasks, the data being input data for the model inference and / or training tasks.

[0240] In one possible design, the communication unit 1003 is also used to receive output data from model inference and / or training tasks.

[0241] In one possible design, when the communication device 1000 is a terminal or a communication module within a terminal, the function of the processing unit 1002 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 1003 can be implemented by transceiver circuitry.

[0242] In one possible design, when the communication device 1000 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 1002 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 1003 can be implemented by the interface circuitry or data transceiver circuitry on the aforementioned chip.

[0243] In one possible design, when the communication device 1000 is a terminal or a computing module within a terminal, the functionality of the processing unit 1002 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. Alternatively, the processor may include an AI processor, or a SoC or SIP chip containing an AI processor. Or, the processor may include an ASIC, or a SoC or SIP chip containing an ASIC. The functionality of the communication unit 1003 can be implemented by transceiver circuitry.

[0244] In one possible design, when the communication device 1000 is a circuit or chip in a terminal responsible for computing functions, such as a GPU or a system-on-a-chip (SoC) or SIP chip containing a GPU, an AI processor or a SoC or SIP chip containing an AI processor, or an ASIC or a SoC or SIP chip containing an ASIC, the function of the processing unit 1002 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 1003 can be implemented by interface circuits or data transceiver circuits on the aforementioned chip.

[0245] The communication device 1000 can be a network-side device as described in the above embodiments. For example, the communication device can be a communication module in an access network device, or a circuit or chip in an access network device responsible for communication functions.

[0246] For example, in one embodiment, the communication unit 1003 is configured to: receive second indication information, the second indication information being used to indicate the start time of the model inference and / or training task, or the duration between the start time of the model inference and / or training task and the current time, the start time or duration being used to determine the input data of the model inference and / or training task; the processing unit 1001 is configured to: send first indication information according to the second indication information; the communication unit 1003 is further configured to receive data, the data being the input data of the model inference and / or training task.

[0247] In one possible design, the first indication information is used to indicate transmission conditions and / or transmission rules, the transmission rules being data FIFO or LIFO in the LCH, and the transmission conditions including at least one of the following: the remaining scheduling delay of the data is within the first delay range, the priority of the LCH where the data is located is greater than or equal to the first priority, the priority of the LCG where the data is located is greater than or equal to the second priority, the LCH where the data is located is the first LCH, or the LCG where the data is located is the first LCG.

[0248] In one possible design, the first latency range is related to the following information: the arrival time of the data and the data packet latency budget, or the remaining scheduling latency of the data; and the start time information of the model inference and / or training tasks.

[0249] In one possible design, the start time information indicates the start time of the model inference and / or training task, or the duration between the start time of the model inference and / or training task and the current time.

[0250] In one possible design, the communication unit 1003 is further configured to: receive request information and send request information, wherein the request information is used to request model inference and / or training tasks, and the data is input data for the model inference and / or training tasks.

[0251] In one possible design, the communication unit 1003 is further configured to: receive input data for the model inference and / or training task and send the input data for the model inference and / or training task; receive output data for the model inference and / or training task and send the output data for the model inference and / or training task.

[0252] In one possible design, when the communication device 1000 is a communication module in a network-side or access network device, the function of the processing unit 1002 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 1003 can be implemented by a transceiver circuit.

[0253] In one possible design, when the communication device 1000 is a circuit or chip responsible for communication functions in an access network device, 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 1002 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 1003 can be implemented by interface circuits or data transceiver circuits on the aforementioned chip.

[0254] In one possible design, when the communication device 1000 is a computing module in a network-side or access network device, the function of the processing unit 1002 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. Alternatively, the processor may include an AI processor, or a SoC or SIP chip containing an AI processor. Or, the processor may include an ASIC, or a SoC or SIP chip containing an ASIC. The function of the communication unit 1003 can be implemented by transceiver circuitry.

[0255] In one possible design, when the communication device 1000 is a circuit or chip responsible for computing functions in an access network device, such as a GPU or a system-on-a-chip (SoC) or SIP chip containing a GPU, an AI processor or a SoC or SIP chip containing an AI processor, or an ASIC or a SoC or SIP chip containing an ASIC, the function of the processing unit 1002 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 1003 can be implemented by interface circuits or data transceiver circuits on the aforementioned chip.

[0256] The communication device 1000 can be a computing node-side device as described in the above embodiments. For example, the communication device can be a communication module in a computing node, or a circuit or chip in a computing node responsible for communication functions.

[0257] For example, in one embodiment, the communication unit 1003 is used to: send second indication information, the second indication information being used to indicate the start time of the model inference and / or training task, or the duration between the start time of the model inference and / or training task and the current time, the start time or duration being used to determine the input data of the model inference and / or training task; the processing unit 1001 is used to: perform the model inference and / or training task based on the input data.

[0258] In one possible design, the computing node includes at least one of the following: a radio access network (RAN) node, a core network node, an edge computing node, or a cloud service node.

[0259] In one possible design, the communication unit 1003 is also used to: receive request information, which is used to request model inference and / or training tasks.

[0260] In one possible design, the communication unit 1003 is also used to: send output data for model inference and / or training tasks.

[0261] In one possible design, when the communication device 1000 is a communication module in a computing node, the function of the processing unit 1002 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 1003 can be implemented by transceiver circuitry.

[0262] In one possible design, when the communication device 1000 is a circuit or chip responsible for communication functions in a computing node, 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 1002 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 1003 can be implemented by interface circuits or data transceiver circuits on the aforementioned chip.

[0263] In one possible design, when the communication device 1000 is a computing module in a computing node, the functionality of the processing unit 1002 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. Alternatively, the processor may include an AI processor, or a SoC or SIP chip containing an AI processor. Or, the processor may include an ASIC, or a SoC or SIP chip containing an ASIC. The functionality of the communication unit 1003 can be implemented by transceiver circuitry.

[0264] In one possible design, when the communication device 1000 is a circuit or chip responsible for computing functions in a computing node, such as a GPU or a system-on-a-chip (SoC) or SIP chip containing a GPU, an AI processor or a SoC or SIP chip containing an AI processor, or an ASIC or a SoC or SIP chip containing an ASIC, the function of the processing unit 1002 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 1003 can be implemented by interface circuits or data transceiver circuits on the aforementioned chip.

[0265] 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.

[0266] 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.

[0267] In one example, storage unit 1001 may include random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory and / or registers, etc.

[0268] For a more detailed description of each step, please refer to the relevant descriptions in the method embodiments above, which will not be repeated here.

[0269] Figure 11 is a schematic diagram of the structure of a terminal 1100 provided in an embodiment of this application. The terminal 1100 corresponds to the terminal shown in Figure 1 and is used to implement the operation of the terminal in the above embodiments. As shown in Figure 11, the terminal includes: one or more antennas 1111, a radio frequency processing system 1120, and a processor system 1130.

[0270] In the downlink or sidelink direction, the RF processing system 1120 receives RF signals through the antenna 1111 and sends the RF-processed signals to the processor system 1130 for further processing. In the uplink or sidelink direction, the processor system 1130 processes the terminal-side information and sends it to the RF processing system 1120, which then processes the signal and transmits it through the antenna 1111.

[0271] In one example, the radio frequency (RF) processing system 1120 serves as the communication interface for external communication of the terminal and may include an RF front end (RFFE) 1121 and an RF transceiver 1122. The RFFE 1121 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 1121 can be a circuit system composed of multiple discrete devices or integrated into one or more chips. The RF transceiver 1122 processes the RF signals received by the RFFE into baseband / IF signals for further processing by the processor system 1130, and processes the baseband / IF signals provided by the processor system 1130 into RF signals for transmission to the RFFE 1121. The baseband / IF signals transmitted between the RF transceiver 1122 and the processor system 1130 can be digital or analog signals. The radio frequency transceiver 1122 can be implemented by one or more chips, which are commonly referred to as radio frequency chips (RFICs).

[0272] In one example, processor system 1130 may include one or more processors for processing signals and executing one or more communication protocols. Optionally, processor system 1130 may also include memory 1136. In one example, the one or more processors include at least one baseband processor 1131 (also known as a modem processor). Memory 1136 is used to store data and / or computer program instructions. Optionally, processor system 1130 may also include one or more application processors 1132 for implementing processing of the terminal operating system and application layer. Application processor 1132 may include, for example, a GPU, AI processor, or ASIC. Optionally, processor system 1130 may also include one or more of a voice subsystem 1133, a multimedia subsystem 1134, or an interface circuit 1135. The voice subsystem 1133 is used to process voice signals, the multimedia subsystem 1134 is used to handle multimedia-related operations, such as video encoding / decoding, image processing, etc., and the interface circuit 1135 is used to implement communication with other terminal components, such as a display 1140, an input device 1150, memory 1160, etc. The aforementioned components in the processor system 1130 can communicate with each other via a bus or communication interface circuit.

[0273] In one example, processor system 1130 can be packaged as a single processor chip, such as a SoC chip or a SIP chip. In another example, processor system 1130 can be a system of multiple chips, for example, the baseband processor 1131 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.

[0274] In one example, memory 1136 can be on-chip memory, i.e., located on the processor system 1130 chip. In another example, memory 1160 can be off-chip memory, i.e. located outside the processor system 1130 chip.

[0275] In one example, the baseband processor 1131 may include one or more processor cores 11311 and interface circuitry 11314. The one or more processor cores 11311 are used to process signals and execute one or more communication protocols. Optionally, the baseband processor 1131 may also include a memory 11312 for storing at least a portion of the corresponding computer program instructions and / or data. In one example, the one or more processor cores 11311 execute the computer program instructions stored in the memory 11312 to perform the relevant operations in the above method embodiments (such as receiving first indication information; performing data transmission based on the transmission conditions and / or transmission rules indicated by the first indication information). In this disclosure, memory 11312 is used to store corresponding computer program instructions and / or data. This can mean that memory 11312 stores all corresponding computer program instructions and / or data for execution by processor core 11311; or it can mean that memory 11312 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 11311. Memory 11312 can store different portions of computer program instructions and / or data multiple times for execution by processor core 11311 to implement the relevant operations in the above method embodiments. Interface circuit 11314 serves as a communication interface for communication with other components, such as transmitting signals with radio frequency processing system 1120, communicating with other subsystems and related components of processor system 1130 via a bus, such as transmitting data control signals with application processor 1132, and transmitting data or computer program instructions with memory 1136 or memory 1160. Optionally, in order to reduce the load on the processor core, a baseband signal processing circuit 11313 can be set to perform at least some baseband signal processing, including one or more of signal demodulation, modulation, encoding or decoding.

[0276] In one example, the communication device provided in this application may be a terminal 1100, a communication module including a processor system 1130 and a radio frequency system 1120, or a baseband processor 1131.

[0277] 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), application specific integrated circuit (ASIC), artificial intelligence processor (AI processor), or neural processing unit (NPU).

[0278] 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 1160 (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 1136 and / or memory 11312 (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.

[0279] In one example, the RF transceiver 1122 and the RF front-end 1121 can also be packaged in a single chip. In another example, the RF transceiver 1122, the RF front-end 1121, and the baseband processor 1131 can also be packaged in a single chip.

[0280] This application also provides a chip system including at least one processor for supporting the implementation of the functions of the terminal, access network device or computing node involved in any of the above method embodiments, such as sending, receiving or processing the information involved in the above methods.

[0281] In one possible design, the chip system also includes a memory for storing computer program instructions and data, which may be located inside or outside the processor.

[0282] The chip system can consist of chips or include chips and other discrete components.

[0283] This application also provides a computer program product, which includes: a computer program (also referred to as code or instructions), which, when the computer program is run, executes the method executed by the terminal in the embodiments shown in FIG7, FIG8 or FIG9, or executes the method executed by the access network device, or executes the method executed by the computing node.

[0284] This application also provides a computer-readable storage medium storing a computer program (also referred to as code or instructions). When the computer program is run, the method executed by the terminal in the embodiments shown in FIG. 7, FIG. 8 or FIG. 9 is executed, or the method executed by the access network device is executed, or the method executed by the computing node is executed.

[0285] This application also provides a communication system, which includes the aforementioned terminal and access network equipment.

[0286] This application also provides a communication system, which includes the aforementioned terminal, access network equipment, and computing node.

[0287] The methods provided in the above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any combination thereof. When implemented in software, they can be implemented, in whole or in part, in the form of a computer program product. This computer program product may include one or more computer instructions. When these computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic disk), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0288] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented 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 each specific application, but such implementation should not be considered beyond the scope of this application.

[0289] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0290] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0291] The unit described as a separate component may or may not be physically separate. The component shown as a unit may or may not be a physical unit; that is, it may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0292] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0293] If this function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, or part of it, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory, random access memory, magnetic disks, or optical disks.

[0294] In the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of different embodiments are consistent and can be referenced by each other. The technical features of different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0295] The terms "system" and "network" used in the embodiments of this application are interchangeable. 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.

[0296] 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.

[0297] 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.

[0298] 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.

Claims

1. A data transmission method, characterized in that, The method includes: Receive first indication information, the first indication information is used to indicate transmission conditions and / or transmission rules, the transmission rules are data in logical channel LCH first-in-first-out FIFO or last-in-first-out LIFO, the transmission conditions include at least one of the following: the remaining scheduling delay of the data is within the first delay range, the priority of the LCH where the data is located is greater than or equal to the first priority, the priority of the logical channel group LCG where the data is located is greater than or equal to the second priority, the LCH where the data is located is the first LCH, or the LCG where the data is located is the first LCG; Data transmission is performed based on the transmission conditions and / or the transmission rules.

2. The method according to claim 1, characterized in that, The first delay range is related to the following information: The arrival time of the data, the data packet delay budget, or the remaining scheduling delay of the data; and Start time information for model inference and / or training tasks.

3. The method according to claim 2, characterized in that, The start time information indicates the start time of the model inference and / or training task, or the duration between the start time of the model inference and / or training task and the current time.

4. The method according to any one of claims 1-3, characterized in that, The method further includes: Send a request message, the request message being used to request a model inference and / or training task, the data being the input data for the model inference and / or training task.

5. The method according to any one of claims 1-4, characterized in that, The method further includes: Receive output data from model inference and / or training tasks.

6. A data transmission method, characterized in that, Applied to the computing node side, the method includes: Send a second instruction message, which is used to indicate the start time of the model inference and / or training task, or the duration between the start time of the model inference and / or training task and the current time, wherein the start time or the duration is used to determine the input data of the model inference and / or training task; The model inference and / or training tasks are performed based on the input data.

7. The method according to claim 6, characterized in that, The method further includes: Receive request information, which is used to request the model inference and / or training tasks.

8. The method according to claim 6 or 7, characterized in that, The computing node includes at least one of the following: Radio access network (RAN) nodes, core network nodes, edge computing nodes, or cloud service nodes.

9. The method according to claim 6 or 7, characterized in that, The method further includes: Send the output data of the model inference and / or training tasks.

10. A data transmission method, characterized in that, Applied to the network side, the method includes: Receive second indication information, the second indication information being used to indicate the start time of the model inference and / or training task, or the duration between the start time of the model inference and / or training task and the current time, the start time or the duration being used to determine the input data of the model inference and / or training task; According to the second instruction information, send the first instruction information and receive data, which is the input data for model inference and / or training tasks.

11. The method according to claim 10, characterized in that, The first indication information is used to indicate transmission conditions and / or transmission rules. The transmission rules are either first-in-first-out (FIFO) or last-in-first-out (LIFO) data in the logical channel (LCH). The transmission conditions include at least one of the following: the remaining scheduling delay of the data is within a first delay range; the priority of the LCH where the data is located is greater than or equal to the first priority; the priority of the logical channel group (LCG) where the data is located is greater than or equal to the second priority; the LCH where the data is located is the first LCH; or the LCG where the data is located is the first LCG.

12. The method according to claim 11, characterized in that, The first delay range is related to the following information: The arrival time of the data, the data packet delay budget, or the remaining scheduling delay of the data; and Start time information for model inference and / or training tasks.

13. The method according to claim 12, characterized in that, The start time information indicates the start time of the model inference and / or training task, or the duration between the start time of the model inference and / or training task and the current time.

14. The method according to any one of claims 10-13, characterized in that, The method further includes: Receive request information, the request information being used to request the model inference and / or the training task; Send request information.

15. The method according to any one of claims 10-13, characterized in that, The method further includes: Receive input data for model inference and / or training tasks, and send input data for model inference and / or training tasks; Receive and send the output data of the model inference and / or training tasks.

16. A communication device, characterized in that, Includes modules for implementing the method as described in any one of claims 1 to 5.

17. A communication device, characterized in that, Includes modules for implementing the method as described in any one of claims 6 to 9.

18. A communication device, characterized in that, Includes modules for implementing the method as described in any one of claims 10 to 15.

19. A computer-readable storage medium, characterized in that, Used to store computer programs or instructions that, when run, cause the method as described in any one of claims 1 to 5 to be performed, or cause the method as described in any one of claims 6 to 9 to be performed, or cause the method as described in any one of claims 10 to 15 to be performed.

20. A computer program product, characterized in that, include: A computer program or instruction that, when executed, causes the method as described in any one of claims 1 to 5 to be performed, or causes the method as described in any one of claims 6 to 9 to be performed, or causes the method as described in any one of claims 10 to 15 to be performed.

Images