Data transmission method, communication apparatus, and related product

Abstract

Embodiments of the present application provide a data transmission method, a communication apparatus, and a related product. By means of distributing a plurality of services in periodic time periods to different time periods for transmission, contention of the plurality of services for communication resources in the periodic time periods can be reduced, thereby improving the overall transmission performance of the plurality of services. The data transmission method provided in the embodiments of the present application comprises: receiving first information, the first information indicating at least two time periods within each periodic time period and quality of service (QoS) respectively corresponding to the at least two time periods; and, determining a target transmission time period for data transmission, the target transmission time period being comprised in the at least two time periods.

Description

A data transmission method, communication device and related products

[0001] This application claims priority to Chinese Patent Application No. 202411998731.X, filed with the State Intellectual Property Office of China on December 31, 2024, entitled “A Data Transmission Method, Communication Device and Related Products”, the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of wireless communication, and more particularly to a data transmission method, communication device, and related products. Background Technology

[0003] In wireless communication networks, the radio access network (RAN) provides wireless access services to terminals, enabling communication between terminals and the core network, servers, etc. Access network equipment is used to implement the specific functions of the RAN.

[0004] When multiple services arrive at the data transmitter at approximately the same time (e.g., downlink to the access network device and uplink to the terminal), the access network device needs to allocate communication resources for these services with similar arrival times. Since the access network device has limited communication resources, when a large number of services arrive at the data transmitter at approximately the same time, competition for communication resources arises among these services, leading to a decrease in the transmission rate of multiple services and consequently, increased service latency.

[0005] Some services have high latency requirements, and there is an urgent need for a method to improve the overall transmission performance of multiple services when they compete for communication resources. Summary of the Invention

[0006] This application provides a data transmission method, communication device, and related products. By diverting multiple services within a periodic time period to different time periods for transmission, the competition for communication resources among multiple services within the periodic time period is reduced, thereby improving the overall transmission performance of multiple services.

[0007] Firstly, embodiments of this application provide a data transmission method. This method can be applied to the terminal side, such as a terminal or a communication / computing module within the terminal, or circuits or chips 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 circuits or chips in the terminal responsible for computing functions (such as a graphics processing unit (GPU), an artificial intelligence (AI) processor, or an application-specific integrated circuit (ASIC)), or logical nodes, logical modules, or software capable of implementing all or part of the terminal's functions. Taking the application of this method to a terminal as an example, in this method, the terminal acts as the uplink service data sender. The terminal receives first information, which indicates at least two time periods within each periodic time period and the Quality of Service (QoS) corresponding to each of the at least two time periods. The terminal determines a target transmission period for data transmission, the target transmission period being contained within at least two time periods.

[0008] Using the above method, the data transmission unit is refined from a periodic time period to time slots within that periodic time period. Services with different uplink directions can choose from at least two time slots within the periodic time period for data transmission. Compared to different services starting transmission at the beginning of the periodic time period, in this embodiment, some services can choose to transmit data in a later time slot within the periodic time period. This achieves distributed transmission of different services, reduces the probability of different services transmitting data at the same time, lowers the probability of different services competing for communication resources, and improves the overall transmission performance of multiple services.

[0009] In one possible design, at least two time periods correspond to different QoS.

[0010] Using the above method, different services may have different data transmission requirements. This allows different time periods to correspond to different QoS levels, and the QoS levels in different time periods may meet the data transmission requirements of different services; for example, the QoS level in time period A meets the requirements of service A, while the QoS level in time period B meets the requirements of service B. This distributes different services to different time periods with different QoS levels, achieving service-specific transmission. This reduces the probability of different services competing for communication resources and improves the overall transmission performance of multiple services.

[0011] In one possible design, within each periodic period, there are at least two periods including a first period and a second period, the second period being later than the first period, and the QoS corresponding to the second period being better than the QoS corresponding to the first period.

[0012] In conventional data transmission methods, different services arrive at the data sender near the start of a periodic timeframe. The method described above improves QoS in later segments of the periodic timeframe, encouraging high-demand services (those with high transmission requirements, such as those with strict latency and speed requirements) to choose later segments for data transmission. This guides high-demand services to adjust their transmission times later within the periodic timeframe, diverting high-demand and low-demand services across different segments of the periodic timeframe. This reduces competition for communication resources between high-demand and low-demand services, improving the overall transmission performance of multiple services.

[0013] In one possible design, it also includes: the terminal sending a second message indicating the target transmission period.

[0014] By using the above method, after receiving the second information, the access network device can reserve corresponding communication resources (i.e., communication resources for each target transmission period) for one or more terminals corresponding to multiple services in advance, ensuring the transmission of corresponding data and thus improving the efficiency of data transmission.

[0015] In one possible design, the duration of the periodic time is configured by the access network equipment.

[0016] Resources are configured by the access network equipment. Using the above method, the access network equipment can more flexibly configure the duration of periodic time slots based on the actual resource allocation. For example, the duration of periodic time slots corresponding to the service to be transmitted can be configured.

[0017] In one possible design, the target transmission period is used for data transmission of distributed inference and / or training tasks. The terminal can also determine target segmentation points for the distributed inference and / or training tasks corresponding to the target transmission period.

[0018] By employing the above method, the transmission time of distributed inference and / or training tasks is refined into time periods within a cycle, providing flexibility for shifting the segmentation point. Generally speaking, the later the segmentation point, the smaller the corresponding data transmission volume. Therefore, shifting the segmentation point on the terminal side in the uplink direction can reduce the data transmission volume on the terminal side, reduce communication latency, thereby reducing the overall end-to-end latency and improving user satisfaction.

[0019] In one possible design, the terminal can also send a third message indicating the target split point.

[0020] Distributed inference and / or training tasks are performed by multiple terminals, including servers and terminals. Using the method described above, the terminal sends third-party information, enabling other computing terminals (servers / terminals) to determine the adjusted target segmentation point A2 for distributed inference task A (and optionally, a second amount of transmitted data corresponding to A2). Other computing terminals can then select appropriate segmentation points to align with the terminal's segmentation point, thereby improving computational accuracy and user satisfaction.

[0021] In one possible design, the first message is carried in the Real-Time Transport Protocol (RTP) header.

[0022] Using the above method, the server obtains the first information while parsing the RTP packet header, thereby determining whether to adjust the service.

[0023] In one possible design, the first information is carried in the Media Access Control Unit (MAC CE), and the recommended bit rate field of the MAC CE indicates the QoS corresponding to at least two time periods.

[0024] Using the above method, the terminal can obtain QoS information corresponding to at least two time periods in a timely manner, thereby determining whether to adjust the service.

[0025] Secondly, embodiments of this application provide a data transmission method. This method can be applied to the server side, such as a server or a communication / computing module within the server, or a circuit or chip within the server responsible for communication functions, or a circuit or chip within the server responsible for computing functions (such as a graphics processing unit (GPU), artificial intelligence (AI) processor, or application-specific integrated circuit (ASIC)), or a logical node, logical module, or software capable of implementing all or part of the server's functions. Taking the application of this method to a server as an example, in this method, the server acts as the sender of service data in the downlink direction. The server receives first information, which indicates at least two time periods within each periodic time period and the Quality of Service (QoS) corresponding to each of the at least two time periods. The server determines a target transmission period for data transmission, the target transmission period being contained within at least two time periods.

[0026] Using the above method, the data transmission unit is refined from a periodic time period to time slots within that periodic time period. Services with different downlink directions can choose from at least two time slots within the periodic time period for data transmission. Compared to different services starting transmission at the beginning of the periodic time period, in this embodiment, some services can choose to transmit data in a later time slot within the periodic time period. This achieves distributed transmission of different services, reduces the probability of different services transmitting data at the same time, lowers the probability of different services competing for communication resources, and improves the overall transmission performance of multiple services.

[0027] In one possible design, at least two time periods correspond to different QoS.

[0028] In one possible design, within each periodic period, there are at least two periods including a first period and a second period, the second period being later than the first period, and the QoS corresponding to the second period being better than the QoS corresponding to the first period.

[0029] In one possible design, it also includes: the server sending a second message indicating the target transmission period.

[0030] By using the above method, after receiving the second information, the access network device can reserve corresponding communication resources (i.e., communication resources for each target transmission period) for one or more servers corresponding to multiple services in advance, ensuring the transmission of corresponding data and thus improving the efficiency of data transmission.

[0031] In one possible design, the duration of the periodic time is configured by the access network equipment.

[0032] In one possible design, the target transmission period is used for data transmission of distributed inference and / or training tasks. The server can also determine the target split point for the distributed inference and / or training tasks corresponding to the target transmission period.

[0033] By employing the above method, the transmission time of distributed inference and / or training tasks is refined into time periods within a periodic timeframe, providing flexibility for shifting the segmentation point. Shifting the server-side segmentation point in the downlink direction allows the terminal-side segmentation point to follow suit, reducing the computational load on the terminal side and thus reducing computational latency. This reduces the overall end-to-end latency and improves user satisfaction.

[0034] In one possible design, the server can also send a third message indicating the target split point.

[0035] Distributed inference and / or training tasks are performed by multiple terminals, including servers and endpoints. Using the method described above, the server sends third-party information, enabling other terminals (terminals / servers) to determine the adjusted target segmentation point for the distributed inference task. These other terminals can then choose appropriate segmentation points to align with the server's segmentation point, thereby improving computational accuracy and user satisfaction.

[0036] In one possible design, the first message is carried in the Real-Time Transport Protocol (RTP) header.

[0037] In one possible design, the first information is carried in the Media Access Control Unit (MAC CE), and the recommended bit rate field of the MAC CE indicates the QoS corresponding to the at least two time periods respectively.

[0038] Thirdly, this method can be applied to the network side, such as access network devices, modules (e.g., circuits, chips, or chip systems) within these devices, or logical nodes, modules, or software that can implement all or part of the functions of the access network devices, or circuits or chips (e.g., GPUs, AI processors, or ASICs) responsible for computational functions within the access network devices. Taking the application of this method to access network devices as an example, in this method, the access network device sends first information, which indicates at least two time periods within each periodic time period and the Quality of Service (QoS) corresponding to each of the at least two time periods.

[0039] In one possible design, at least two time periods correspond to different QoS.

[0040] In one possible design, within each periodic period, there are at least two periods including a first period and a second period, the second period being later than the first period, and the QoS corresponding to the second period being better than the QoS corresponding to the first period.

[0041] In one possible design, the access network device may also receive second information indicating a target transmission period for data transmission, the target transmission period being comprised of at least two time periods.

[0042] In one possible design, the duration of the periodic time is configured by the access network equipment.

[0043] In one possible design, the target transmission period is used for data transmission of distributed inference and / or training tasks, and the access network device can also receive third information indicating the segmentation of distributed inference and / or training tasks.

[0044] In one possible design, the first message is carried in the Real-Time Transport Protocol (RTP) header.

[0045] In one possible design, the first information is carried in the Media Access Control Unit (MAC CE), and the recommended bit rate field of the MAC CE indicates the QoS corresponding to at least two time periods.

[0046] The beneficial effects in the second and third aspects are described in the first aspect and will not be repeated here.

[0047] Fourthly, this application provides a communication device that has the functions of the first aspect described above. For example, the communication device includes modules, units, or means that perform the operations involved in the first aspect. These modules, units, or means can be implemented by software, hardware, or a combination of software and hardware.

[0048] Fifthly, this application provides a communication device that has the functions of the second aspect above. For example, the communication device includes modules, units, or means that perform the operations involved in the second aspect above. These modules, units, or means can be implemented by software, hardware, or a combination of software and hardware.

[0049] Sixthly, this application provides a communication device that has the functions of the third aspect above. For example, the communication device includes modules, units, or means that perform the operations involved in the second aspect above. These modules, units, or means can be implemented by software, hardware, or a combination of software and hardware.

[0050] In a seventh aspect, this application provides a communication device including an interface circuit and one or more processors. The one or more processors are coupled to a memory. The memory stores part or all of the necessary computer program or instructions for implementing the functions described in the first aspect. The one or more processors are executable to carry out the computer program or instructions, causing the communication device to implement the methods in any possible design or implementation of the first aspect. 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.

[0051] In one possible design, the processor is used to communicate with other devices or components through the interface circuit.

[0052] In one possible design, the communication device may also include the memory.

[0053] 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.

[0054] Eighthly, this application provides a communication device including an interface circuit and one or more processors. The one or more processors are coupled to a memory. The memory stores part or all of the necessary computer program or instructions for implementing the functions described in the second aspect above. The one or more processors are executable to carry out the computer program or instructions, causing the communication device to implement the methods in any possible design or implementation of the second aspect above. The interface circuit is used to implement the communication functions within the communication device and / or the communication functions between the communication device and other devices or components.

[0055] In one possible design, the processor is used to communicate with other devices or components through the interface circuit.

[0056] In one possible design, the communication device may also include the memory.

[0057] The aforementioned communication device may be a server, or a communication / computing module in a server, or a circuit or chip in a server responsible for communication functions, or a circuit or chip in a server responsible for computing functions (such as a GPU, AI processor, or ASIC), or a logical node or logical module capable of implementing all or part of the server functions.

[0058] Ninthly, this application provides a communication device including an interface circuit and one or more processors. The one or more processors are coupled to a memory. The memory stores part or all of the computer program or instructions necessary to implement the functions described in the 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.

[0059] In one possible design, the processor is used to communicate with other devices or components through the interface circuit.

[0060] In one possible design, the communication device may also include the memory.

[0061] The aforementioned communication device may be an access network device, or a module (e.g., a circuit, chip, or chip system) in the access network device, or a circuit or chip (e.g., a GPU, AI processor, or ASIC) in the 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.

[0062] In a tenth aspect, this application provides a communication system comprising a terminal, a server, and an access network device. The terminal is used to implement the method in any possible design or implementation of the first aspect. The server is used to implement the method in any possible design or implementation of the second aspect. The access network device is used to implement the method in any possible design or implementation of the third aspect.

[0063] Eleventhly, this application provides a computer-readable storage medium storing computer-readable instructions, which, 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.

[0064] In a twelfth aspect, this application provides a computer program product that, when read and executed by a computer, causes the computer to perform any of the possible designs in the first to third aspects described above. Attached Figure Description

[0065] Figure 1a is a schematic diagram of a wireless communication system provided in this application;

[0066] Figure 1b is a schematic diagram of a wireless communication system with AI nodes provided in this application;

[0067] Figure 1c is a schematic diagram of an application framework of the wireless communication system with AI nodes provided in this application;

[0068] Figure 2 is a flowchart of a data transmission method provided in an embodiment of this application;

[0069] Figure 3 is a schematic diagram showing the time when data arrives at the data sending end for different services provided in the embodiments of this application;

[0070] Figures 4 and 6 are schematic diagrams of multiple time periods within a periodic time period provided in the embodiments of this application;

[0071] Figure 5 is a schematic diagram of the transmission of different services during different time periods within a periodic time period provided in the embodiments of this application;

[0072] Figure 7 is a schematic diagram of the header structure of a GTP-U message provided in an embodiment of this application;

[0073] Figure 8 is a schematic diagram of the split point adjustment of the distributed inference / training task provided in an embodiment of this application;

[0074] Figure 9 is a schematic diagram of the message structure of the MAC CE provided in the embodiment of this application;

[0075] Figure 10 is a possible exemplary block diagram of a communication device provided in an embodiment of this application;

[0076] Figure 11 is an exemplary structural diagram of the terminal provided in an embodiment of this application. Detailed Implementation

[0077] The embodiments of this application will now be described with reference to the accompanying drawings. Those skilled in the art will recognize that, with technological advancements and the emergence of new scenarios, the technical solutions provided in the embodiments of this application are equally applicable to similar technical problems.

[0078] Figure 1a is a schematic diagram illustrating one possible, non-limiting system. As shown in Figure 1a, the communication system 10 includes a radio access network (RAN) 100 and a core network (CN) 200. RAN 100 includes at least one RAN node (110a and 110b in Figure 1a, collectively referred to as 110) and at least one terminal (120a-120j in Figure 1a, collectively referred to as 120). RAN 100 may also include other RAN nodes, such as wireless relay devices and / or wireless backhaul devices (not shown in Figure 1a). Terminal 120 is wirelessly connected to RAN node 110. RAN node 110 is wirelessly or wired connected to core network 200. The core network equipment in core network 200 and RAN node 110 in RAN 100 can be different physical devices, or they can be the same physical device integrating core network logical functions and radio access network logical functions.

[0079] 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.

[0080] RAN node 110, sometimes also referred to as access network equipment, RAN entity, or access node, constitutes part of the communication system and is used to help terminals achieve wireless access. Multiple RAN nodes 110 in communication system 10 can be of the same type or different types. In some scenarios, the roles of RAN node 110 and terminal 120 are relative. For example, in Figure 1a, network element 120i can be a helicopter or drone, which can be configured as a mobile base station. For terminals 120j accessing RAN 100 through network element 120i, network element 120i is a base station; but for base station 110a, network element 120i is a terminal. RAN node 110 and terminal 120 are sometimes both referred to as communication devices. For example, in Figure 1a, network elements 110a and 110b can be understood as communication devices with base station functions, and network elements 120a-120j can be understood as communication devices with terminal functions.

[0081] 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 1a, 110a), a micro base station or indoor station (as shown in Figure 1a, 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.

[0082] In another possible scenario, multiple RAN nodes collaborate to assist terminals in achieving wireless access, with different RAN nodes 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). CUs and DUs can be separate entities or included in the same network element, such as a baseband unit (BBU). RUs can be included in radio frequency equipment or radio frequency units, such as remote radio units (RRUs), active antenna units (AAUs), or remote radio heads (RRHs). Furthermore, RAN nodes can also be computing units, providing computational 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).

[0083] 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.

[0084] In the embodiments of this application, the RAN node can also be described in different ways, such as an access network device. Unless otherwise specified, the term "access network device" will be used throughout this application.

[0085] 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.

[0086] To support artificial intelligence (AI) technology in wireless networks, AI nodes may also be introduced into the network.

[0087] 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.

[0088] It is understood that this application does not limit the number of AI nodes. For example, when there are multiple AI nodes, they can be divided based on function, such as different AI nodes being responsible for different functions.

[0089] 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.

[0090] AI nodes can be AI network elements or AI modules.

[0091] Figure 1b is a schematic diagram of a possible application framework in a communication system. As shown in Figure 1b, network elements in the communication system are connected through 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 1b for clarity). Access network nodes can be single RAN nodes or can include multiple RAN nodes, for example, including CU and DU. The CU and / or DU can also be equipped with one or more AI modules. The CU can also be split into CU-CP and CU-UP, and one or more AI modules are installed in the CU-CP and / or CU-UP.

[0092] 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.

[0093] 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).

[0094] 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.

[0095] 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.

[0096] 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.

[0097] 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.

[0098] 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.

[0099] Figure 1c illustrates a possible application framework in a communication system. As shown in Figure 1c, the communication system includes a RAN intelligent controller (RIC). For example, the RIC can be the AI ​​modules 117 and 118 shown in Figure 1b, 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.

[0100] 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, compute nodes, 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.

[0101] 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, compute nodes, 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.

[0102] 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, compute nodes), while non-real-time RICs can be set in OAM, cloud servers, core network devices, or other network devices.

[0103] In wireless communication networks, if multiple services arrive at the data transmitter at approximately the same time, the access network device needs to allocate communication resources for these services to achieve data transmission. Since the access network device has limited communication resources, when a large number of services arrive at the data transmitter at approximately the same time (e.g., the access network device in the downlink direction and the terminal in the uplink direction), communication resource competition will occur among these services, leading to a decrease in transmission rate and an increase in service latency.

[0104] To address the aforementioned issues, this application provides a data transmission method that divides the data transmission period into at least two time periods and sets QoS for each time period, thereby guiding multiple services to be diverted to different time periods for data transmission, thus reducing the probability of resource contention and improving the overall transmission performance of multiple services.

[0105] In this application, "sending information" can be understood as one device sending information to another device, or it can also be understood as one logical module within a device sending information to another logical module. For example, "access network device sending information" can be understood as the access network device sending information to another device (such as a terminal), or it can be understood as logical module 1 in the access network device sending information to logical module 2 in the access network device.

[0106] In this application, "receiving information" can be understood as one device receiving information from another device, or it can also be understood as a logical module within a device receiving information from another logical module. For example, "access network device receiving information" can be understood as the access network device receiving information from another device (such as a terminal), or it can be understood as logical module 1 in the access network device receiving information from logical module 2 in the access network device.

[0107] 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.

[0108] The data transmission method and apparatus provided in the embodiments of this application will be further described below with reference to the accompanying drawings. It is understood that this application uses access network equipment, a server, and a terminal as examples of the execution entities in the interactive illustration, but this application does not limit the execution entities in the interactive illustration. For example, the method executed by the access network equipment in this application can also be implemented by modules (e.g., circuits, chips, or chip systems) in the access network equipment, or by logical nodes, logical modules, or software that can implement all or part of the functions of the access network equipment, or by circuits or chips (e.g., GPUs, AI processors, or ASICs) in the access network equipment 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 server in this application can also be implemented by a communication module / computing module in the server, or a circuit or chip in the server responsible for communication functions, or a circuit or chip in the server responsible for computing functions (such as a GPU, AI processor, or ASIC), or a logical node, logical module, or software that can implement all or part of the server functions.

[0109] Figure 2 is a flowchart of the data transmission method provided in an embodiment of this application. As shown in Figure 2, the data transmission method provided in an embodiment of this application includes:

[0110] 201. Access network equipment receives service request messages for different services.

[0111] Access network devices can receive service request messages from different services. These service request messages can come from the same or different devices (e.g., terminals / servers). If the service request messages from different services come from the same device, they may also carry service request information for different services within the same service request message.

[0112] Access network equipment can determine or estimate information such as the arrival time and service cycle of data for each service based on service request messages. This sending end is the data sender. The arrival time of data from different services at the sending end may be the same or similar. In the uplink direction, the data sender is the terminal; in the downlink direction, the data sender is the access network equipment.

[0113] Access network devices transmit data in periods of X. If the time difference between the arrival times of data from multiple services at the sending end (data sending end) is approximately 0 or approximately an integer multiple of X, the access network device should transmit the data of these multiple services within the same period of X.

[0114] For example, as shown in Figure 3, the access network device determines that data for services A, B, and C will arrive at the sending end at times t1, t2, and t3, respectively. t2 and t3 are close, and their time difference from t1 is approximately one period X. The access network device configures the data for services A, B, and C to be transmitted within period X2, X3, ... Starting from period X2, data for services A, B, and C are transmitted in each period.

[0115] Optionally, the duration of the periodic period is related to the business cycle. For example, the duration of the periodic period can be the business cycle of business A; if business A is a video business, the duration of the periodic period can be the video frame cycle of business A.

[0116] Optionally, the duration of the periodic time segment can be configured by the access network device. For example, optionally, before step 201, the access network device sends a configuration message indicating the duration of the periodic time segment X and the reference time T.

[0117] 202. The terminal / server receives first information, which indicates at least two time periods within each period and the quality of service (QoS) corresponding to each of the at least two time periods.

[0118] The access network device can determine at least two time periods within each periodic time period X. These at least two time periods are independent of each other in time, but may partially overlap; this application does not impose any limitations on this. The unit of data transmission is refined from the periodic time period X into the time periods within the periodic time period X.

[0119] The at least two time periods determined by the access network device can be, as shown in Figure 4, sequentially connected time periods within a periodic time period, and the sum of the at least two time periods is a periodic time period. Alternatively, the sum of the at least two time periods can be a part of a periodic time period; this application does not limit this to either.

[0120] The access network equipment determines the Quality of Service (QoS) for different time periods within the periodic time period X. The QoS for different time periods within the periodic time period X may be the same or different; this application does not impose any limitation on this.

[0121] After determining the above information, the access network device can send first information, which indicates at least two time periods within each periodic time period X and the QoS corresponding to each of the at least two time periods.

[0122] Therefore, the terminal / server can receive the first information. If the terminal / server has established a communication connection with the access network device, the terminal / server can directly receive the first information from the access network device; if the terminal / server communicates with the access network device through a relay device (e.g., UPF), the terminal / server can receive the first information from the access network device through the relay device.

[0123] It is worth noting that the communication resources of access network equipment include uplink and downlink communication resources. If the uplink and downlink communication resources are independent of each other, the time period within a periodic time interval X and the corresponding QoS for each time period can be determined separately for the uplink and downlink directions. The determination of the time period and the QoS determination for the uplink and downlink directions do not affect each other.

[0124] If the allocation of uplink and downlink communication resources affects each other, then the uplink and downlink communication resources can be coordinated to determine the periodic time X in the uplink and downlink directions and the corresponding QoS of the periodic time.

[0125] 203. The terminal / server determines the target transmission period for data transmission, which is contained in at least two periods within the periodic period.

[0126] The terminal / server can communicate with the access network equipment to realize data transmission of service A and service B. Based on the first information, the terminal / server can select, from at least two time periods within the periodic time period, the target transmission time period A for data transmission of service A and the target transmission time period B for data transmission of service B.

[0127] The terminal / server can select the target transmission period based on the QoS corresponding to at least two time periods.

[0128] If at least two time periods correspond to the same QoS, the terminal / server randomly selects the target transmission time period for different services from the at least two time periods. If at least two time periods correspond to different QoS, the terminal / server can select the target transmission time period that meets the QoS requirements of each service from the at least two time periods based on the QoS requirements of different services.

[0129] In one example, the time period indicated by the first information and the corresponding QoS are shown in Figure 4. Time period 1, time period 2, and time period 3 within the periodic time period correspond to QoS1, QoS2, and QoS3, respectively. If the QoS requirement of service A is QoS1 and the QoS requirement of service B is QoS2, then the terminal / server can select time period 1 as the target transmission time period A and time period 2 as the target transmission time period B.

[0130] 204. The terminal / server transmits the corresponding service data with the access network equipment during the target transmission period.

[0131] Once the target transmission period for data transmission is determined, the terminal / server can communicate with the access point device during target transmission period A to transmit data for service A; and communicate with the access network device during target transmission period B to transmit data for service B.

[0132] It is worth noting that steps 203 and 204 are illustrated using the example of different services being transmitted by the same terminal / server. If different services are transmitted by different terminals / servers, then in step 203, multiple terminals / servers determine the target transmission period for data transmission of the corresponding service from at least two time periods in the periodic time period; in step 204, multiple terminals / servers transmit the data of the corresponding service with the access network device during their respective target transmission periods.

[0133] In this embodiment, the data transmission unit is refined from a periodic time period to time slots within that periodic time period. Different services can select at least two time slots within the periodic time period for data transmission. Compared to different services starting transmission at the beginning of the periodic time period, in this embodiment, some services can choose to transmit data in a later time slot within the periodic time period. This reduces the probability of different services transmitting data at the same time, lowers the probability of different services competing for communication resources, and improves the overall transmission performance of multiple services.

[0134] Furthermore, by setting QoS for different time periods, terminals / servers corresponding to multiple services can be guided to select different time periods within the cycle for data transmission. This further reduces the probability of different services transmitting data at the same time, thereby improving the overall transmission performance of multiple services.

[0135] For example, as shown in Figure 5, different terminals (UEs) have different transmission requirements for their services. QoS2 corresponding to time period 1 can meet the transmission requirements of UE1's services, QoS2 corresponding to time period 2 can meet the transmission requirements of UE2's services, and QoS3 corresponding to time period 3 can meet the transmission requirements of UE3's services. Therefore, UE1 chooses time period 1 to transmit data, UE2 chooses time period 2 to transmit data, and UE3 chooses time period 3 to transmit data, thus achieving traffic splitting for different services. After traffic splitting, the competition for communication resources among various services decreases, and the performance of latency, transmission rate, etc., within each time period is improved, achieving transmission performance improvements such as reduced end-to-end latency and increased transmission rate. (Adjusting the application offset duration in Figure 5 means adjusting the start time of data transmission to the corresponding time period based on the selection of the time period; the offset duration refers to the offset duration between the start time of the periodic time period and the start time of transmission.)

[0136] In the embodiments of this application, the QoS settings for different time periods in step 202 can be based on the default setting; or based on the transmission requirements of the service; or a combination of the transmission requirements of the service and the default setting. This application does not limit this.

[0137] Method 1 for setting QoS for different time periods:

[0138] In the default mode 1, different time periods correspond to the same QoS. Therefore, in step 203, different services randomly select the target transmission time period from multiple time periods within the periodic time period.

[0139] Method 2 for setting QoS for different time periods:

[0140] The default method 2 ensures that, within at least two time periods in a periodic period, the QoS of the later second time period is better than the QoS of the earlier first time period. For example, in Figure 4, the periodic period includes time period 1 and time period 2. Time period 2 (the second time period) is later than time period 1 (the first time period), and the QoS2 corresponding to time period 2 is better than the QoS1 corresponding to time period 1.

[0141] In addition to the first and second time periods, the periodic time period may include more time periods (for example, the periodic time period in Figure 4 also includes time period 3). This application does not limit the relationship between the QoS corresponding to other time periods and the QoS corresponding to the first and second time periods. For example, in Figure 4, QoS3 corresponding to time period 3 may be better than QoS2, better than QoS1, or the same as QoS2 / QoS1, or QoS1 may be better than QoS23; this application does not limit this.

[0142] In the embodiments of this application, QoS may include information such as recommended bit rate, priority level, latency level, reliability level, and throughput, etc., and this application does not limit this. The comparison of the merits of QoS can be based on one or more of the above dimensions. For example, the recommended bit rates of QoS1, QoS2, and QoS3 can be sorted from low to high; or, the recommended bit rates and priority levels of QoS1, QoS2, and QoS3 can both be sorted from low to high.

[0143] In this embodiment, different services arrive at the data transmitter near the start time of the periodic time. This results in better QoS in later periods of the periodic time, and high-demand services (services with high transmission requirements, such as those with high latency and speed requirements) tend to choose later periods for data transmission. This guides high-demand services to adjust their transmission time later within the periodic time, thus diverting high-demand and low-demand services to different periods within the periodic time for data transmission, reducing communication resource competition between high-demand and low-demand services, and improving the overall transmission performance of multiple services.

[0144] Optionally, if the service requires data processing, the service latency includes communication latency and computation latency. The terminal / server can confirm the service's communication latency and, based on the latency dimension information of QoS for each time period within the periodic time frame, select a time period from at least two time periods within the periodic time frame that meets the service's communication latency requirements.

[0145] Method 3 for setting QoS for different time periods:

[0146] The method of setting QoS for different time periods based on service transmission requirements: In step 201, the access network device determines the transmission requirements of each service. For example, the transmission rate of service A is not less than 10Mbps, and the latency of service B is not less than 20Mbps. Then, in step 202, the access network device can set the QoS for different time periods to match the QoS requirements of different services. For example, the recommended bit rate of QoS1 corresponding to time period 1 is set to 10Mbps, and the latency level of QoS2 corresponding to time period 2 is set to 20Mbps.

[0147] It is worth noting that the transmission requirements of different services in the above examples correspond to different dimensions of QoS. Furthermore, different QoS levels can be set for different time periods based on the varying requirements of different services for the same QoS dimension. For example, if different services have different latency requirements, different QoS latency levels can be set for different time periods within the periodic time frame.

[0148] Optionally, the transmission requirements of a service can include requirements in one or more dimensions, such as transmission rate, latency, and throughput. The QoS for different time periods is then set to match the service's requirements in one or more of these dimensions.

[0149] In the embodiments of this application, QoS is set for different time periods based on the needs of different services, thereby diverting services with different needs to different time periods of the periodic time for data transmission, reducing communication resource competition between services with different needs, and improving the overall transmission performance of multiple services.

[0150] In this embodiment, besides guiding different services to select different target transmission periods based on QoS settings for different time periods, the access network device can also directly recommend different time periods for data transmission to different services. For example, the first information sent in step 202 may also include the time periods recommended by the access network device. For instance, in step 201, the access network device can determine services A and B transmitted within the same periodic time, and determine the terminal / server A and terminal / server B corresponding to services A and B. In step 202, the access network device selects different recommended time periods (time period A and time period B) for services A and B from at least two time periods within the periodic time. When sending the first information in step 202, the access network device carries time period A in the first information with the destination address of terminal / server A, and carries time period B in the first information with the destination address of terminal / server B. If services A and B are transmitted by the same terminal / server, the first message in step 202 may also include the recommended time period A for service A and the recommended time period B for service B.

[0151] In this embodiment, step 201 is the triggering step for step 202. It is worth noting that step 201 is optional, and step 202 can also be triggered based on other conditions, such as the access network device determining a periodic time period, a new service request coming online during the periodic time period, or receiving a service request message for a specific service, etc. This application does not limit this.

[0152] The data transmission method provided in this application is applicable to data transmission in either the uplink or downlink direction, and will be described in detail below:

[0153] I. Data transmission in the downlink direction.

[0154] 1.1 Downlink data transmission process.

[0155] Based on the process framework shown in Figure 2, the downlink data transmission process specifically includes:

[0156] In step 201, the server sends a service request message for the downlink service.

[0157] The server can send service request messages for downlink services to the access network equipment. In this embodiment, the downlink service is a service that transmits data from the server to the terminal, such as video projection services or extended reality (XR) services.

[0158] Different downlink service request messages can originate from the same or different servers. For example, server A sends a service request message to the access network device, requesting data transmission for multiple downlink services (e.g., video projection service A and XR service B); or server A sends multiple downlink service request messages to the access network device at approximately the same time; or server A and server B send different downlink service request messages to the access network device at approximately the same time, for example, terminal A sends a video projection service request message, and terminal B sends an XR service B request message.

[0159] In the downlink direction, the data is sent by the access network device. The access network device can determine or estimate the arrival time of data for each service based on the service request messages of different services, thereby determining that the data of multiple services will be transmitted in the same period X.

[0160] In step 202, the access network device sends the first information to the server through the user plane function (UPF) network element.

[0161] Specifically, after determining the first information, the access network device sends a GPRS tunneling protocol (GTP)-U message to the UPF, which carries the first information. The UPF parses the GTP-U message, determines the first information, and then sends real-time transport protocol (RTP) messages / API interface messages to the servers corresponding to multiple services, which also carry the first information.

[0162] In the GTP-U message sent to the UPF, the first information can be carried in the header of the GTP-U message, specifically in the QoS extension field (e.g., the QoS index field) of the header.

[0163] In this embodiment of the application, the first information includes information from at least two time periods within the periodic time period, and the QoS corresponding to each of the at least two time periods.

[0164] The information includes at least two time periods within the periodic period, such as the index number of each time period and the length of each time period.

[0165] As shown in Figure 6, the periodic time period includes 3 time periods, and the numbering of these 3 time periods in sequence is the index number of each time period.

[0166] The length of each time period needs to be determined by a reference time T. The reference time T is the start time of the periodic time period and also the reference time for alignment between the access network device and the terminal / server. For example, the reference time T can be the burst arrival time (BAT). BAT represents the expected arrival time of the first packet of a data burst in a QoS flow. For instance, the reference time can be the BAT of downlink service A in step 201, or the BAT of downlink service B, or the BAT of a historical downlink service; this application does not limit this.

[0167] Optionally, if the access network devices, terminals, and servers align their times via slots, the BAT can indicate the Reference SFN-And Slot, representing the uplink timing of the most recent system frame number (SFN) and slot of the primary cell (PCell) with that number.

[0168] Optionally, access network devices, terminals, and servers can also align their time using absolute time, which BAT then indicates.

[0169] The length of at least two time periods within a periodic period can include the duration between the start time of each of the at least two time periods and the reference time T. For example, in Figure 6, if t1, t2, and t3 are the start times of time periods 1, 2, and 3, respectively, then the length of each time period can be represented by the offset duration from T to t1 (offset1, corresponding to QoS1), the offset2 from T to t2 (corresponding to QoS2), and the offset3 from T to t3 (corresponding to QoS3). The corresponding header structure of the GTP-U message is shown in Figure 7. Line 13 includes multiple pairs of QoS & offset, i.e., the QoS and offset of each of the multiple time periods, such as QoS1 & offset1, QoS2 & offset2, and QoS3 & offset3.

[0170] Alternatively, the length of at least two time periods within a periodic period can include: the duration of each time period within the at least two time periods, and the duration between the start time of the first time period and the reference time within the at least two time periods. For example, in Figure 6, time periods 1 to 3 are consecutive time periods, t1 is the start time of time period 1, and t2-t1, t3-t2, and t4-t3 are the durations of time periods 1, 2, and 3, respectively. The length of each time period can then be represented by the offset from T to t1, and by t2-t1, t3-t2, and t4-t3.

[0171] Optionally, if the periodic time period is divided into multiple time periods, the different time periods and their corresponding QoS can be represented by the index number of each time period and its corresponding QoS. In this case, the first information includes the number of time periods N in the periodic time period, the index number of each of the N time periods, and the QoS corresponding to each index number.

[0172] Upon receiving a GTP-U message, the UPF parses the QoS extension field in the GTP-U message header to determine the first information. If multiple services transmitted within a period are processed by the same server, the access network device sends an RTP / API interface message carrying the first information to that server; if multiple services transmitted within a period are processed by different servers, the access network device sends RTP / API interface messages carrying the first information to those servers.

[0173] If the server is not on the UPF, the UPF will carry the first information in the header of the RTP message and send the RTP message to the server. If the server is on the UPF, the UPF will transmit the first information to the server through the API interface between the two servers.

[0174] In step 203, one or more servers determine the target transmission period for data transmission from at least two periods in the periodic time period.

[0175] If different services are processed by the same server, then in step 203, the server selects the target transmission period for each service from at least two time periods within the periodic time period based on the first information. If different services are processed by different servers, then in step 203, multiple servers determine the target transmission period for data transmission of their respective services from at least two time periods within the periodic time period.

[0176] Between steps 203 and 204, the server may also send a second message indicating the target transmission period.

[0177] After determining the target transmission period for the corresponding downlink service data transmission, the server can send second information to the access network device. Optionally, the second information may include an index number of the target transmission period within a periodic time, indicating the target transmission period through the index number.

[0178] The server can send second information to the access network device via the UPF. Specifically, the server indicates the target transmission period to the UPF through RTP messages / API interface messages. After receiving and parsing the RTP messages / API interface messages, the UPF determines the second information. The UPF carries the second information in the QoS extension field of the GTP-U message header and sends the GTP-U message to the access network device.

[0179] Step 204 is described in the foregoing embodiment and will not be repeated here.

[0180] In this embodiment of the application, after receiving the second information, the access network device can reserve corresponding communication resources (i.e., communication resources for each target transmission period) for one or more servers corresponding to multiple services in advance to ensure the transmission of corresponding data, thereby improving the efficiency of data transmission.

[0181] It is worth noting that the step of the server sending the second information to the access network device is optional, and step 204 can be executed directly after step 203. This application does not limit this.

[0182] It is worth noting that the step of the server sending the second information is optional. The server may also choose not to send the second information and directly execute step 204 after step 203. This application does not limit this.

[0183] The data transmission method provided in this application embodiment can realize data transmission for various types of services, including AI services, such as distributed inference and / or training tasks.

[0184] 1.2 Data transmission flow for distributed inference and / or training tasks in the downlink direction.

[0185] The following example, using business A as a distributed inference task, illustrates the data transmission method when a business within a given time period is a distributed inference and / or training task. Based on the downlink data transmission process described in 1.1 above, this method includes:

[0186] Optionally, prior to step 201, the server determines the default split point A1 for distributed inference task A.

[0187] Distributed inference tasks divide the model into different sub-models and run them on different terminals / servers, processing the output data of each sub-model. The distributed inference task is achieved through the interaction of output data between different terminals / servers.

[0188] For a sub-model task assigned to a server, the split point may differ for different data transmission periods. Different split points can correspond to different end-to-end latencies, which include communication latency and computation latency. The server can determine the default split point A1 for distributed inference task A. Optionally, the default split point A1 can be the optimal split point, i.e., the split point that minimizes end-to-end latency.

[0189] It is worth noting that the default split point A1 of the distributed inference task A can be determined by the server A running task A, or by other devices, such as other terminals / servers running distributed inference task A, the central control server / terminal of distributed inference task A, the terminal / server that initiates distributed inference task A, etc. This application does not limit this.

[0190] In step 201, the server sends a service request message for the downlink distributed inference task.

[0191] Optionally, different downlink service request messages can be partially or entirely service request messages for distributed inference tasks. For example, server A sends a service request message to the access network device, requesting data transmission of distributed inference task A and distributed inference task B in the downlink direction; or, server A sends a service request message to the access network device, requesting data transmission of distributed inference task A and service B (non-distributed inference task) in the downlink direction; or, server A sends a service request message for distributed inference task A to the access network device, and server B sends a service request message for service B (non-distributed inference task) to the access network device; or, server A and server B send service request messages for different distributed inference tasks to the access network device.

[0192] Optionally, the business request message of the distributed inference task may also include the default split point of the distributed inference task, such as the default split point A1 of the distributed inference task A.

[0193] In step 202, the access network device sends the first information to the server through the UPF network element.

[0194] Specifically, the access network device sends a GTP-U message to the UPF, which carries the first information. The UPF then sends an RTP message / API interface message to the server, which also carries the first information. For details, please refer to the aforementioned embodiments, which will not be repeated here.

[0195] In step 203, the server determines the target transmission period for data transmission from at least two periods within the periodic time period.

[0196] Steps 202 and 203 are described in the foregoing embodiments and will not be repeated here. In one or more servers in step 203, server A is used to process distributed inference task A, and the target transmission period A determined by server A is used for data transmission of distributed inference task A.

[0197] Optionally, between steps 203 and 204, the server may also send second information to the access network device, the second information indicating the target transmission period for the corresponding service data transmission determined by the server.

[0198] For details on sending the second message, please refer to the description of the foregoing embodiments, which will not be repeated here.

[0199] Optionally, between steps 203 and 204, the server used to process the distributed inference task can also determine the target segmentation point corresponding to the target transmission period determined in step 203.

[0200] For example, server A is used to process distributed inference task A, and the corresponding default split point A1 is split point T1 in Figure 8. As shown in Figure 8, the distributed inference task includes multiple sub-models (shown by multiple gray boxes in Figure 8), and these sub-models have a sequential relationship. After determining the split point, the server runs the sub-model before the split point, obtains the corresponding business data, and transmits the business data to the terminal through the access network equipment.

[0201] Alternatively, the segmentation point can be determined based on the division of functional levels. The multiple gray boxes in Figure 8 represent different functional level stages. For example, a distributed video reasoning task includes video understanding, reasoning, and other functional level stages arranged sequentially.

[0202] Before step 201, the default split point of server A is the split point T1 in Figure 8. The service data obtained by performing calculations based on the sub-model located before the split point T1 in the distributed inference task A will arrive at the access network device at T1'.

[0203] In step 203, server A selects the target transmission period A for distributed inference task A from multiple periods within the periodic time period. The start time of the target transmission period A may be later than the start time of the periodic time period, allowing for the possible shifting of the split point of distributed inference task A. Server A can select a target split point (split point A2) before the start time of the target period, where the corresponding transmission requirements (e.g., transmission rate) can be satisfied by the QoS of the target transmission period, thereby adjusting the split point of distributed inference task A.

[0204] In one example, if the target transmission period is period 2 in Figure 8, and the start time of period 2 is t2, then data is allowed to arrive at the access network device before or near t2, for example, at time T2'. The segmentation point corresponding to time T2' is T2. If the transmission requirement 2 of the service data processed based on segmentation point T2 can be satisfied by the target transmission period A (period 2), then the segmentation point of the distributed inference task A can be adjusted to segmentation point T2. If the transmission requirement 2 cannot be satisfied by period 2, then the target segmentation point A2 is T1 (i.e., the target segmentation point A2 is the same as the default segmentation point A1).

[0205] An example of the data transmission requirement corresponding to the split point A2 is the transmission rate. Based on the amount of service data generated at the split point A2, the transmission rate requirement for this service data in time period 2 can be determined. As long as the transmission rate can meet the transmission rate requirement in the QoS of time period 2, the target split point A2 can be T2 corresponding to time period 2.

[0206] In the embodiments of this application, the data transmission requirements corresponding to the split point can be determined based on information such as the expected output data volume, transmission rate (corresponding to communication latency), and server computing power (corresponding to computing latency), and this application does not limit this.

[0207] In another example, if the target transmission period is period 3 in Figure 8, and the start time of period 3 is t3, then data is allowed to arrive at the access network device before or near t3, such as at times T2', T3', or T4'. The segmentation points corresponding to times T2', T3', and T4' are T2, T3, and T4, respectively. The server can determine the transmission requirement 2, transmission requirement 3, and transmission requirement 4 corresponding to each segmentation point T2, T3, and T4.

[0208] If the QoS of time period 3 satisfies one of transmission requirements 2, 3 and 4, then the target split point A2 can be identified as the split point whose transmission requirements are met.

[0209] If the QoS of time period 3 satisfies multiple of transmission requirements 2, 3, and 4, then the target segmentation point A2 can be identified as the later segmentation point among the multiple segmentation points that satisfy the transmission requirements. For example, if the QoS of time period 3 satisfies the transmission requirements of segmentation points T2 and T3, and T3 is later, then the target segmentation point A2 can be identified as the later segmentation point T3.

[0210] If the QoS of time period 3 does not meet any of the transmission requirements 2, 3 and 4, then the target split point A2 is the same as the default split point A1, and the split point of the distributed inference task is still T1 as shown by the default split point A1.

[0211] In this embodiment, the transmission time of distributed inference and / or training tasks is refined into time periods within a periodic time frame, providing flexibility for shifting the segmentation point. Shifting the server-side segmentation point in the downlink direction causes the terminal-side segmentation point to shift subsequently, reducing the computational load on the terminal side and thus reducing computational latency. This reduces the overall end-to-end latency and improves user satisfaction.

[0212] Optionally, server A can also determine the second amount of data transmitted for the distributed inference task A corresponding to the target split point A2. If the target split point A2 is later than the default split point A1, then the second amount of data transmitted is less than the first amount of data transmitted corresponding to the default split point A1.

[0213] Optionally, before step 204, the server used to process the distributed inference task may also send third information indicating the target split point A2 to the access network device, the server / terminal related to the distributed inference task, and other devices.

[0214] The third information indicates the target segmentation point A2 after the target transmission period adjustment for distributed inference task A. Optionally, the third information may also include the second transmission data volume corresponding to the target segmentation point A2.

[0215] Server A, corresponding to distributed inference task A, can send third-party information to the access network device via UPF. Specifically, server A sends an RTP message / API interface message carrying the third-party information to the UPF, and the UPF sends a GTP-U message carrying the third-party information to the access network device. Optionally, the access network device can send the third-party information to servers / terminals or other devices related to the distributed inference task.

[0216] Optionally, the third information and the second information can be transmitted in the same message, that is, between steps 203 and 204, the second information and the third information are transmitted in the same message. The RTP message / API interface message sent by the server to the UPF, and the GTP-U message sent by the UPF to the access network device, include both the second information and the third information.

[0217] Step 204 is described in the foregoing embodiment and will not be repeated here.

[0218] In this embodiment, the distributed inference and / or training tasks are performed by multiple terminals, including servers and terminals. The server sends third information, enabling other processing terminals (terminals / servers) to determine the adjusted target segmentation point A2 for distributed inference task A (and optionally, a second amount of transmitted data corresponding to A2). Other processing terminals can then select appropriate segmentation points to align with the server's segmentation point, thereby improving computational accuracy and user satisfaction.

[0219] It is worth noting that the steps of the server sending the second and third information are optional. The server may also choose not to send the second and third information and directly execute step 204 after step 203; or, the second and / or third information may be sent between steps 203 and 204. This application does not limit this.

[0220] The above embodiments use a distributed inference task as an example to illustrate the adjustment of the split point. The same applies to the distributed training task, and will not be repeated here. That is, the distributed inference task mentioned above can also be replaced by a distributed training task, or a distributed inference and training task, and this application does not limit this.

[0221] II. Data transmission process in the uplink direction.

[0222] 2.1 Data transmission process in the uplink direction.

[0223] Based on the process framework shown in Figure 2, the data transmission process in the uplink direction specifically includes:

[0224] In step 201, the terminal sends a service request message for the uplink service.

[0225] The terminal can send uplink service request messages to the access network equipment. In this embodiment, the uplink service is a service that transmits data from the terminal to the server, such as video upload service or data analysis service.

[0226] In the uplink direction, the data sender is the terminal. The access network device can determine that the data of multiple services are transmitted in the same period X based on the time when the data of different services arrives at the radio link control (RLC) buffer of the corresponding terminal.

[0227] In step 202, the access network device can send the first information to the terminal via a medium access control unit (MAC CE) message.

[0228] If multiple services transmitted within a period are processed by the same terminal, the access network device sends a MAC CE carrying the first information to that terminal; if multiple services transmitted within a period are processed by different terminals, the access network device sends a MAC CE carrying the first information to those multiple terminals.

[0229] The first piece of information can be carried in the header of the MAC CE packet, specifically in the recommended bit rate field of the header.

[0230] In the embodiments of this application, the MAC CE can be an existing or newly added MAC CE, and this application does not limit it.

[0231] In one example, the message format of MAC CE is shown in Figure 9. Here, for bitrate and offset, bitrate represents the data transmission rate that can be guaranteed for the corresponding time period, or it can represent other QoS for the time period. Offset represents the duration between the start time of the corresponding time period and the reference time T.

[0232] Optionally, in addition to the bitrate and offset mentioned above, the MAC CE may also include other information, such as M lines of information representing the parameters corresponding to the M rates. To reduce the amount of message data, parameters in the same line can be reused for multiple rates if the parameters corresponding to multiple rates are consistent. Examples of parameters include data transmission direction and transmission rate.

[0233] For the content of the first information, please refer to the description of the foregoing embodiments, which will not be repeated here.

[0234] In step 203, one or more terminals determine the target transmission period for data transmission from at least two of the periodic time periods.

[0235] If different services are processed by the same terminal, then in step 203, the terminal selects the target transmission period for each service from at least two time periods within the periodic time period based on the first information. If different services are processed by different terminals, then in step 203, multiple terminals determine the target transmission period for data transmission of their respective services from at least two time periods within the periodic time period.

[0236] Between steps 203 and 204, the terminal may also send a second message indicating the target transmission period.

[0237] After determining the target transmission period for data transmission of the corresponding uplink service, the terminal can send second information to the access network device. The second information indicates the target transmission period selected by the terminal for data transmission of the corresponding service. Optionally, the second information may include an index number of the target transmission period within a periodic time, indicating the target transmission period through the index number.

[0238] Step 204 is described in the foregoing embodiment and will not be repeated here.

[0239] In this embodiment of the application, after receiving the second information, the access network device can reserve corresponding communication resources (i.e., communication resources for each target transmission period) for one or more terminals corresponding to multiple services in advance to ensure the transmission of corresponding data, thereby improving the efficiency of data transmission.

[0240] It is worth noting that the step of the terminal sending the second information is optional. The terminal may also choose not to send the second information and directly execute step 204 after step 203. This application does not limit this.

[0241] The upstream services may also include distributed inference and / or training tasks.

[0242] 2.2 Data transmission flow for distributed inference and / or training tasks in the uplink direction.

[0243] Taking business A as a distributed inference task as an example, based on the uplink data transmission process described in section 2.1 above, when a certain business within a period is a distributed inference and / or training task, the corresponding data transmission method includes:

[0244] Optionally, before step 201, the terminal determines the split point A1 of the distributed inference task A.

[0245] Distributed inference tasks divide the model into different sub-models and run them on different terminals / servers, processing the output data of each sub-model. Distributed inference tasks are achieved through the interaction of output data between different terminals.

[0246] For a sub-model task assigned to a terminal, different data transmission periods may correspond to different split points. The earlier the split point, the earlier the data is sent, and the larger the corresponding amount of data transmitted. The terminal can determine the default split point A1 for distributed inference task A.

[0247] It is worth noting that the default split point A1 of the distributed inference task A can be determined by the terminal running task A or by other devices, such as the central control server / terminal of the distributed inference task A, the terminal / server that initiates the distributed inference task A, etc. This application does not limit this.

[0248] In step 201, the terminal sends a service request message for the uplink distributed inference task.

[0249] Optionally, different uplink service request messages can be partially or entirely service request messages for distributed inference tasks. For example, terminal A sends a service request message to the access network device, requesting data transmission of uplink distributed inference task A and distributed inference task B; or, terminal A sends a service request message to the access network device, requesting data transmission of uplink distributed inference task A and service B (non-distributed inference task); or, terminal A sends a service request message for distributed inference task A to the access network device, and terminal B sends a service request message for service B (non-distributed inference task) to the access network device; or, terminal A and terminal B send service request messages for different distributed inference tasks to the access network device.

[0250] Optionally, the business request message of the distributed inference task may also include the default split point of the distributed inference task, such as the default split point A1 of the distributed inference task A.

[0251] In step 202, the access network device sends the first information to the terminal.

[0252] Specifically, the access network device can send the first information to the terminal through MAC CE.

[0253] In step 203, the terminal determines the target transmission period for data transmission from at least two time periods in the periodic time period.

[0254] Steps 202 and 203 are described in the foregoing embodiments and will not be repeated here. In one or more terminals in step 203, if terminal A is used to process distributed inference task A, then the target transmission period A determined by terminal A is used for data transmission of distributed inference task A.

[0255] Optionally, between steps 203 and 204, the terminal may also send second information to the access network device, the second information indicating the target transmission period for the corresponding service data transmission determined by the terminal.

[0256] For details on sending the second message, please refer to the description of the foregoing embodiments, which will not be repeated here.

[0257] Optionally, between steps 203 and 204, the terminal used to process the distributed inference task can also determine the target segmentation point corresponding to the target transmission period for the distributed inference task based on the target transmission period determined in step 203.

[0258] For an explanation of the target split point, please refer to the description of the embodiment in Figure 8, which will not be repeated here. Since the data sender in the uplink direction is the terminal rather than the access point device (corresponding to the downlink direction), this embodiment needs to change "time t to reach the access point device" in Figure 8 to "time t to reach the RLC buffer of the terminal".

[0259] In this embodiment, the transmission time of distributed inference and / or training tasks is refined into time periods within a periodic time frame, providing flexibility for shifting the segmentation point. Generally speaking, the later the segmentation point, the smaller the corresponding data transmission volume. Therefore, shifting the segmentation point on the terminal side in the uplink direction can reduce the data transmission volume on the terminal side, reduce communication latency, thereby reducing the overall end-to-end latency and improving user satisfaction.

[0260] Optionally, the terminal can also determine the second amount of data transmitted for the distributed inference task corresponding to the target split point A2. If the target split point A2 is later than the default split point A1, then the second amount of data transmitted is less than the first amount of data transmitted corresponding to the default split point A1.

[0261] Optionally, before step 204, the terminal used to process the distributed inference task may also send third information indicating the target split point A2 to the access network device, the server / terminal related to the distributed inference task, and other devices.

[0262] The third information indicates that the distributed inference task is based on the target segmentation point A2 after adjustment of the target transmission period. Optionally, the third information may also include the second transmission data volume corresponding to the target segmentation point A2.

[0263] Terminal A, corresponding to distributed inference task A, can send a MAC CE carrying the third information to the access network device. Optionally, the access network device can send the third information to devices such as servers / terminals related to the distributed inference task.

[0264] Optionally, the third information and the second information can be transmitted in the same message. That is, between steps 203 and 204, the terminal sends the second information and the third information in the same message to the access network device.

[0265] Step 204 is described in the foregoing embodiment and will not be repeated here.

[0266] In this embodiment, the distributed inference and / or training tasks are performed by multiple terminals, including servers and terminals. The terminal sends third information, enabling other processing terminals (servers / terminals) to determine the adjusted target segmentation point A2 for the distributed inference task A (and optionally, a second amount of transmitted data corresponding to A2). Other processing terminals can then select appropriate segmentation points to align with the terminal's segmentation point, thereby improving computational accuracy and user satisfaction.

[0267] It is worth noting that the steps of the terminal sending the second and third information are optional. The terminal may also choose not to send the second and third information and directly execute step 204 after step 203; or, the second and / or third information may be sent between steps 203 and 204. This application does not limit this.

[0268] The above embodiments use a distributed inference task as an example to illustrate the adjustment of the split point. The same applies to the distributed training task, and will not be repeated here. That is, the distributed inference task mentioned above can also be replaced by a distributed training task, or a distributed inference and training task, and this application does not limit this.

[0269] 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 900 may include modules or units for implementing the methods described above. In one possible design, the communication device 900 includes a processing unit 902 and a communication unit 903. Optionally, the communication device 900 may further include a storage unit 901 for storing device program code and / or data.

[0270] The communication device 900 can be a terminal-side device in the above embodiments, such as a terminal or a communication module in a terminal, or a circuit or chip in a terminal that is responsible for communication functions.

[0271] For example, in one embodiment, the communication unit 903 is configured to: receive first information, the first information indicating at least two time periods within each periodic time period and the Quality of Service (QoS) corresponding to each of the at least two time periods; and the processing unit 902 is configured to: determine a target transmission time period for data transmission, the target transmission time period being contained in at least two time periods.

[0272] In one possible design, at least two time periods correspond to different QoS.

[0273] In one possible design, within each periodic time period, the at least two time periods include a first time period and a second time period, wherein the second time period is later than the first time period, and the QoS corresponding to the second time period is better than the QoS corresponding to the first time period.

[0274] In one possible design, the communication unit 903 is used to: send second information, the second information indicating the target transmission period.

[0275] In one possible design, the duration of the periodic time is configured by the access network device.

[0276] In one possible design, the target transmission period is used for data transmission of distributed inference and / or training tasks. Processing unit 902 is specifically configured to: determine a target segmentation point for the distributed inference and / or training task corresponding to the target transmission period.

[0277] In one possible design, the communication unit 903 is used to: send third information, the third information indicating the target segmentation point.

[0278] In one possible design, the first message is carried in the Real-Time Transport Protocol (RTP) header.

[0279] In one possible design, the first information is carried in a Media Access Control Unit (MAC CE), and the recommended bit rate field of the MAC CE indicates the QoS corresponding to the at least two time periods respectively.

[0280] In one possible design, when the communication device 900 is a terminal or a communication module within a terminal, the function of the processing unit 902 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 903 can be implemented by transceiver circuitry.

[0281] In one possible design, when the communication device 900 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 902 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 903 can be implemented by an interface circuit or data transceiver circuit on the aforementioned chip.

[0282] In one possible design, when the communication device 900 is a terminal or a computing module within a terminal, the functionality of the processing unit 902 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 903 can be implemented by transceiver circuitry.

[0283] In one possible design, when the communication device 900 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 902 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 903 can be implemented by interface circuitry or data transceiver circuitry on the aforementioned chip.

[0284] The communication device 900 can be the server-side device in the above embodiments.

[0285] For example, in one embodiment, the communication unit 903 is configured to: receive first information, the first information indicating at least two time periods within each periodic time period and the Quality of Service (QoS) corresponding to each of the at least two time periods; and the processing unit 902 is configured to: determine a target transmission time period for data transmission, the target transmission time period being contained in at least two time periods.

[0286] In one possible design, at least two time periods correspond to different QoS.

[0287] In one possible design, within each periodic time period, the at least two time periods include a first time period and a second time period, wherein the second time period is later than the first time period, and the QoS corresponding to the second time period is better than the QoS corresponding to the first time period.

[0288] In one possible design, the communication unit 903 is used to: send second information, the second information indicating the target transmission period.

[0289] In one possible design, the duration of the periodic time is configured by the access network device.

[0290] In one possible design, the target transmission period is used for data transmission of distributed inference and / or training tasks. Processing unit 902 is specifically configured to: determine a target segmentation point for the distributed inference and / or training task corresponding to the target transmission period.

[0291] In one possible design, the communication unit 903 is used to: send third information, the third information indicating the target segmentation point.

[0292] In one possible design, the first message is carried in the Real-Time Transport Protocol (RTP) header.

[0293] In one possible design, the first information is carried in a Media Access Control Unit (MAC CE), and the recommended bit rate field of the MAC CE indicates the QoS corresponding to the at least two time periods respectively.

[0294] In one possible design, when the communication device 900 is a server or a computing module within a server, the functionality of the processing unit 902 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 903 can be implemented by transceiver circuitry.

[0295] In one possible design, when the communication device 900 is a circuit or chip in a server 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 902 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 903 can be implemented by interface circuits or data transceiver circuits on the aforementioned chip.

[0296] The communication device 900 can be a network-side device as described in the above embodiments.

[0297] For example, in one embodiment, the communication unit 903 is configured to send first information, the first information indicating at least two time periods within each periodic time period and the Quality of Service (QoS) corresponding to the at least two time periods respectively;

[0298] In one possible design, the at least two time periods correspond to different QoS.

[0299] In one possible design, within each periodic time period, the at least two time periods include a first time period and a second time period, wherein the second time period is later than the first time period, and the QoS corresponding to the second time period is better than the QoS corresponding to the first time period.

[0300] In one possible design, the communication unit 903 is used to receive second information, which indicates the target transmission period.

[0301] In one possible design, the duration of the periodic time is configured by the access network device.

[0302] In one possible design, the target transmission period is used for data transmission of distributed inference and / or training tasks. Processing unit 902 is configured to determine a target segmentation point for the distributed inference and / or training task corresponding to the target transmission period.

[0303] In one possible design, the communication unit 903 is used to send third information indicating the target segmentation point.

[0304] In one possible design, the first message is carried in the Real-Time Transport Protocol (RTP) header.

[0305] In one possible design, the first information is carried in a Media Access Control Unit (MAC CE), and the recommended bit rate field of the MAC CE indicates the QoS corresponding to the at least two time periods respectively.

[0306] 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.

[0307] 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.

[0308] In one example, storage unit 901 may include random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory and / or registers, etc.

[0309] Referring to Figure 11, which is a structural schematic diagram of a terminal 1000 provided in an embodiment of this application, the terminal 1000 can correspond to the terminals shown in Figures 1a-9 and is used to implement the operation of the terminals in the above embodiments. As shown in Figure 11, the terminal includes: one or more antennas 1010, a radio frequency processing system 1020, and a processor system 1030.

[0310] In the downlink or sidelink direction, the RF processing system 1020 receives RF signals through the antenna 1010 and sends the RF-processed signals to the processor system 1030 for further processing. In the uplink or sidelink direction, the processor system 1030 processes the terminal-side information and sends it to the RF processing system 1020, which then processes the signal and transmits it through the antenna 1010.

[0311] In one example, the RF processing system 1020 serves as the communication interface for external communication of the terminal and may include an RF front end (RFFE) 1021 and an RF transceiver 1022. The RFFE 1021 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 1021 can be a circuit system composed of multiple discrete devices or integrated into one or more chips. The RF transceiver 1022 processes the RF signals received by the RFFE into baseband / IF signals for further processing by the processor system 1030, and processes the baseband / IF signals provided by the processor system 1030 into RF signals for transmission to the RFFE 1021. The baseband / IF signals transmitted between the RF transceiver 1022 and the processor system 1030 can be digital or analog signals. The radio frequency transceiver 1022 can be implemented by one or more chips, which are commonly referred to as radio frequency chips (RFICs).

[0312] In one example, processor system 1030 may include one or more processors for processing signals and executing one or more communication protocols. Optionally, processor system 1030 may also include memory 1036. In one example, the one or more processors include at least one baseband processor 1031 (also known as a modem processor). Memory 1036 is used to store data and / or computer program instructions. Optionally, processor system 1030 may also include one or more application processors 1032 for implementing processing of the terminal operating system and application layer. Application processor 1032 may include, for example, a GPU, AI processor, or ASIC. Optionally, processor system 1030 may also include one or more of a voice subsystem 1033, a multimedia subsystem 1034, or an interface circuit 1035. The voice subsystem 1033 is used to process voice signals, the multimedia subsystem 1034 is used to handle multimedia-related operations, such as video encoding / decoding, image processing, etc., and the interface circuit 1035 is used to implement communication with other terminal components, such as a display 1040, an input device 1050, memory 1060, etc. The aforementioned components in the processor system 1030 can communicate with each other via a bus or communication interface circuit.

[0313] In one example, the processor system 1030 can be packaged as a single processor chip, such as a SoC chip or a SIP chip. In another example, the processor system 1030 can be a system composed of multiple chips, for example, the baseband processor 1031 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.

[0314] In one example, memory 1036 can be on-chip memory, i.e., located on the processor system 1030 chip. In another example, memory 1060 can be off-chip memory, i.e. located outside the processor system 1030 chip.

[0315] In one example, the baseband processor 1031 may include one or more processor cores 10311 and interface circuitry 10314. The one or more processor cores 10311 are used to process signals and execute one or more communication protocols. Optionally, the baseband processor 1031 may also include a memory 10312 for storing at least a portion of the corresponding computer program instructions and / or data. In one example, the one or more processor cores 10311 execute the computer program instructions stored in the memory 10312 to implement the relevant operations in the above method embodiments (operations performed by the terminal, server, or access network device in the embodiments shown in Figures 2-9). In this disclosure, memory 10312 is used to store corresponding computer program instructions and / or data. This can mean that memory 10312 stores all corresponding computer program instructions and / or data for execution by processor core 10311; or it can mean that memory 10312 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 10311. Memory 10312 can store different portions of computer program instructions and / or data multiple times for execution by processor core 10311 to implement the relevant operations in the above method embodiments. Interface circuit 10314 serves as a communication interface for communication with other components, such as transmitting signals with radio frequency processing system 1020, communicating with other subsystems and related components of processor system 1030 via bus, such as transmitting data control signals with application processor 1032, and transmitting data or computer program instructions with memory 1036 or memory 1060. Optionally, in order to reduce the load on the processor core, a baseband signal processing circuit 10313 can be set to perform at least some baseband signal processing, including one or more of signal demodulation, modulation, encoding or decoding.

[0316] In one example, the communication device provided in this application may be a terminal 1000, a communication module including a processor system 1030 and a radio frequency system 1020, or a baseband processor 1031.

[0317] 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).

[0318] 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 in non-volatile memory, such as at least a portion of the aforementioned memory 1060 (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 1036 and / or memory 10312 (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.

[0319] In one example, the RF transceiver 1022 and the RF front-end 1021 can also be packaged in a single chip. In another example, the RF transceiver 1022, the RF front-end 1021, and the baseband processor 1031 can also be packaged in a single chip.

[0320] The terms "system" and "network" in this application embodiment are used interchangeably. "At least one" refers to one or more, and "multiple" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, "at least one of A, B, or C" includes A, B, C, AB, AC, BC, or ABC; "at least one of A, B, and C" can also be understood as including A, B, C, AB, AC, BC, or ABC. Furthermore, unless otherwise specified, the ordinal numbers such as "first" and "second" mentioned in this application embodiment are used to distinguish multiple objects and are not used to limit the order, sequence, priority, or importance of multiple objects. It should be understood that the terms used in this way can be used interchangeably where appropriate, and this is merely a way of distinguishing objects with the same attributes in the description of embodiments of this application. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion, so that a process, method, system, product, or apparatus that comprises a list of elements is not necessarily limited to those elements, but may include other elements not expressly listed or inherent to those processes, methods, products, or apparatuses.

[0321] 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.

[0322] 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.

[0323] 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.

[0324] 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.

[0325] 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 an indirect coupling or communication connection between apparatuses or units through some interfaces, and may be electrical, mechanical, or other forms.

[0326] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

Claims

1. A data transmission method, characterized in that, include: Receive first information, the first information indicating at least two time periods within each period and the Quality of Service (QoS) corresponding to the at least two time periods respectively; A target transmission period for data transmission is determined, the target transmission period being included in the at least two time periods.

2. The method according to claim 1, characterized in that, The at least two time periods each correspond to a different QoS.

3. The method according to claim 1 or 2, characterized in that, Within each periodic time period, the at least two time periods include a first time period and a second time period, wherein the second time period is later than the first time period, and the QoS corresponding to the second time period is better than the QoS corresponding to the first time period.

4. The method according to any one of claims 1 to 3, characterized in that, The method further includes: Send a second message, which indicates the target transmission period.

5. The method according to any one of claims 1 to 4, characterized in that, The duration of the periodic time is configured by the access network equipment.

6. The method according to any one of claims 1 to 5, characterized in that, The target transmission period is used for data transmission in distributed inference and / or training tasks, and the method further includes: Determine the target segmentation point corresponding to the target transmission period for the distributed inference and / or training task.

7. The method according to claim 6, characterized in that, The method further includes: Send a third message, which indicates the target segmentation point.

8. The method according to any one of claims 1 to 7, characterized in that, The first message is carried in the Real-Time Transport Protocol (RTP) header.

9. The method according to any one of claims 1 to 7, characterized in that, The first information is carried in the Media Access Control Unit (MAC CE), and the recommended bit rate field of the MAC CE indicates the QoS corresponding to the at least two time periods respectively.

10. The method according to any one of claims 1 to 9, characterized in that, The method is applied to the terminal side or the server side.

11. A data transmission method, characterized in that, include: Send a first message, which indicates at least two time periods within each periodic period and the Quality of Service (QoS) corresponding to each of the at least two time periods.

12. The method according to claim 11, characterized in that, The at least two time periods each correspond to a different QoS.

13. The method according to claim 11 or 12, characterized in that, Within each periodic time period, the at least two time periods include a first time period and a second time period, wherein the second time period is later than the first time period, and the QoS corresponding to the second time period is better than the QoS corresponding to the first time period.

14. The method according to any one of claims 11 to 13, characterized in that, The method further includes: Receive second information, which indicates the target transmission period.

15. The method according to any one of claims 11 to 14, characterized in that, The method further includes: Configure the duration of the periodic time.

16. The method according to any one of claims 11 to 15, characterized in that, The target transmission period is used for data transmission in distributed inference and / or training tasks, and the method further includes: Receive third information, which indicates the segmentation of distributed inference and / or training tasks.

17. The method according to any one of claims 11 to 16, characterized in that, The first message is carried in the Real-Time Transport Protocol (RTP) header.

18. The method according to any one of claims 11 to 16, characterized in that, The first information is carried in the Media Access Control Unit (MAC CE), and the recommended bit rate field of the MAC CE indicates the QoS corresponding to the at least two time periods respectively.

19. A communication device, characterized in that, It includes a unit for performing the method as described in any one of claims 1 to 9, or includes a unit for performing the method as described in any one of claims 11 to 18.

20. A communication device, characterized in that, Includes at least one processor, said at least one processor being coupled to memory; The memory is used to store computer programs or instructions; When the at least one processor executes the computer program or instructions, the device performs the method as claimed in any one of claims 1 to 9; or, when the at least one processor executes the computer program or instructions, the device performs the method as claimed in any one of claims 11 to 18.

21. The communication device according to claim 20, characterized in that, The communication device further includes an interface circuit, through which the processor communicates with other devices or components.

22. A communication system, characterized in that, It includes a communication device for performing the method as described in any one of claims 1 to 9, and a communication device for performing the method as described in any one of claims 11 to 18.

23. A communication system, characterized in that, It includes a terminal, a server, and an access network device, wherein the terminal or server is used to perform the method as described in any one of claims 1 to 9, and the access network device is used to perform the method as described in any one of claims 11 to 18.

24. A computer-readable storage medium, characterized in that, The computer-readable storage medium contains a program or instructions that, when executed, cause the method as described in any one of claims 1 to 9 to be performed, or cause the method as described in any one of claims 11 to 18 to be performed.

25. A computer program product, characterized in that, When the computer program product is executed on a computer, it causes the method as described in any one of claims 1 to 9 to be performed, or causes the method as described in any one of claims 11 to 18 to be performed.

Images