Data transmission method and apparatus, and communication system

Abstract

A data transmission method and apparatus, and a communication system, which are used for improving the transmission efficiency of data packets between a server and a terminal. On the basis of the method, a server predicts a first parameter, the first parameter being used for representing the size of a data packet to be transmitted at a second time point, and sends the first parameter to an access network device, the second time point being determined on the basis of a first time point and a first offset, and the first offset and the first time point being pre-negotiated by the server and the access network device. On the basis of the first parameter and channel state information at the second time point, the access network device sends the data packet to a terminal at the second time point, so that the channel state information at the second time point matches the size of the data packet to be transmitted, thereby improving the transmission efficiency of the data packet.

Description

A data transmission method, apparatus and communication system

[0001] Cross-reference to related applications

[0002] This application claims priority to Chinese Patent Application No. 202411989702.7, filed with the State Intellectual Property Office of the People's Republic of China on December 31, 2024, entitled "A Data Transmission Method and Apparatus", the entire contents of which are incorporated herein by reference. Technical Field

[0003] This application relates to the field of wireless communication, and more particularly to a data transmission method, apparatus, and communication system. Background Technology

[0004] In recent years, with the continuous development of 5G mobile communication systems, data transmission latency has been continuously reduced and transmission capacity has been increasing. 5G communication systems are gradually penetrating multimedia services that require high real-time performance and large data volumes. These multimedia services include video transmission, cloud gaming (CG), and extended reality (XR) services. XR services further include virtual reality (VR) and augmented reality (AR) services.

[0005] Taking downlink transmission in XR services as an example, the data packet transmission path is typically from the server to the access network device, and then from the access network device to the terminal. The channel status between the access network device and the terminal usually affects the data packet transmission efficiency. For example, at a certain point in time, the channel capacity between the access network device and the terminal may not be able to support the size of the data packets generated by the server. In this case, the data packets generated by the server cannot be transmitted completely to the terminal over the air interface, resulting in reduced transmission efficiency and affecting the user experience.

[0006] Improving the transmission efficiency of data packets between servers and terminals is a pressing technical problem that needs to be solved. Summary of the Invention

[0007] This application provides a data transmission method, apparatus, and communication system for improving the transmission efficiency of data packets between a server and a terminal.

[0008] In a first aspect, this application provides a data transmission method, which can be executed by a first communication device, which may be an access network device or a module in the access network device, such as a chip.

[0009] When the first communication device is an access network device, it can send information to the server; or, it can receive information from the server. When the first communication device is a module within the access network device, it can send information to other modules (such as a radio frequency module or antenna) within the access network device, for example, information sent by the access network device to the server; or, it can receive information from other modules (such as a radio frequency module or antenna) within the access network device, for example, information sent by the server to the access network device. For ease of description, the following explanation uses an access network device as an example.

[0010] The access network device receives a first parameter from the server at a first time point. This first parameter is predicted by the server based on a first service prediction model. The first parameter indicates the size of the data packet the access network device will send to the terminal at a second time point. The second time point is located after the first time point and is determined based on the first time point and a first offset, which indicates the time deviation. Based on the first parameter and the channel state information at the second time point, the access network device sends the data packet to the terminal at the second time point.

[0011] In the above technical solution, the server predicts a first parameter, which characterizes the size of the data packet to be transmitted at the second time point, and sends the first parameter to the access network device. Based on the first parameter and the channel state information at the second time point, the access network device sends a data packet to the terminal at the second time point, thereby matching the channel state information at the second time point with the size of the data packet to be transmitted, improving the data packet transmission efficiency.

[0012] In one possible implementation, when the access network device sends a data packet to the terminal at the second time point based on the first parameter and the channel state information at the second time point, specifically, the access network device determines the channel state information at the second time point based on the channel state model, and then predicts the size of the data packet (equivalent to the data packet to be transmitted) to be sent to the terminal at the second time point based on the channel state information at the second time point, the first parameter, and the second service prediction model. Subsequently, the access network device sends the data packet to the terminal based on the size of the data packet sent to the terminal at the second time point and the channel state information at the second time point.

[0013] In the above technical solution, the access network device first predicts the channel state information at the second time point, and then predicts the size of the data packet sent by the access network device to the terminal at the second time point based on the channel state information at the second time point, the first parameter, and the second service prediction model. This helps to improve the accuracy of the predicted data packet size, and thus helps to improve the data packet transmission efficiency.

[0014] In one possible implementation, when the access network device sends data packets to the terminal based on the size of the data packets sent by the access network device to the terminal at the second time point and the channel state information at the second time point, specifically, the access network device determines the transmission demand at the second time point based on the size of the data packets sent by the access network device to the terminal at the second time point. If the access network device determines that the channel state information at the second time point does not match the transmission demand at the second time point, it adjusts the transmission strategy. The access network device receives data packets from the server and sends data packets to the terminal at the second time point according to the adjusted transmission strategy.

[0015] In the above technical solution, if the access network device determines that the channel state information at the second time point does not match the transmission requirements at the second time point, it adjusts the transmission strategy. After the access network device adjusts the transmission strategy, the channel state information at the second time point matches the transmission requirements at the second time point, thereby helping to improve the transmission efficiency of data packets.

[0016] In one possible implementation, the access network device further sends a first bias or an index of the first bias to the server. For example, the access network device also receives acknowledgment information from the server, which characterizes the server's ability to perform parameter prediction based on the first bias.

[0017] In the above technical solution, the access network device and the server negotiate a first offset, and then both the access network device and the server can determine the effective time of the first parameter (i.e., the second time point) based on the first offset and the first time point. The access network device, based on the first parameter and the channel state information at the second time point, determines how to transmit data packets at the second time point, thereby helping to improve the transmission efficiency of data packets.

[0018] In one possible implementation, the first parameter and the acknowledgment information are carried in the same message, with the first parameter occupying the message's payload field and the acknowledgment information occupying the message's header field. The above provides a method for the access network device and the server to negotiate the first bias, and this method can reduce the number of signaling interactions between the server and the access network device.

[0019] In one possible implementation, the access network device further determines a first bias based on one or more of the following parameters: the duration required to adjust the transmission strategy; the predictive capability of the channel state model; and / or the future time period that the channel state model can predict.

[0020] In the above technical solution, the access network device determines the first bias based on its own model capabilities and other parameters, thereby making fuller use of the first parameter and thus helping to improve the transmission efficiency of data packets.

[0021] In one possible implementation, the first offset is one or more milliseconds, or the first offset is one or more frames, or the first offset is one or more sets of protocol data units, or the first offset is one or more data packets. The above provides various representations of the first offset.

[0022] Secondly, this application provides a data transmission method, which can be executed by a second communication device, which may be a server or a module in the server, such as a chip.

[0023] When the second communication device is a server, it can send information to the access network device; or, it can receive information from the access network device. When the second communication device is a module within the server, it can send information to other modules within the server (such as a radio frequency module or antenna), for example, information sent by the server to the access network device; or, it can receive information from other modules within the server (such as a radio frequency module or antenna), for example, information sent by the access network device to the server.

[0024] For ease of description, the following explanation uses a server as an example.

[0025] The server predicts a first parameter based on the first service prediction model. The first parameter indicates the size of the data packet sent by the access network device to the terminal at a second time point. The second time point is after the first time point and is determined based on the first time point and a first offset. The first offset indicates the time deviation. The server sends the first parameter to the access network device. The first time point is the time when the access network device receives the first parameter. The first parameter is used by the access network device to send the data packet to the terminal at the second time point.

[0026] In one possible implementation, the server also receives a first bias or an index of the first bias from the access network device.

[0027] In one possible implementation, the server also sends an acknowledgment message to the access network device, the acknowledgment message being used to characterize the server's ability to predict parameters based on the first bias.

[0028] In one possible implementation, the first parameter and the acknowledgment information are carried in the same message, with the first parameter occupying the message's payload field and the acknowledgment information occupying the message's header field.

[0029] In one possible implementation, the first offset is one or more milliseconds, or the first offset is one or more frames, or the first offset is one or more sets of protocol data units, or the first offset is one or more data packets.

[0030] Thirdly, embodiments of this application provide a communication device that has the function of implementing the access network device in the first aspect or any possible implementation of the first aspect. The device can be an access network device or a module (such as a chip) in the access network device.

[0031] The communication device may also have the function of a server in implementing the second aspect or any possible implementation of the second aspect. The device may be a server or a module (such as a chip) in a server.

[0032] The functions of the aforementioned communication device can be implemented by hardware or by hardware executing corresponding software. The hardware or software includes one or more modules, units, or means corresponding to the aforementioned functions.

[0033] In one possible implementation, the device includes a processing module and a communication module. The processing module is configured to support the device in performing the functions of the access network device in the first aspect or any implementation thereof, or to perform the functions of the server in the second aspect or any implementation thereof. The communication module supports communication between the device and other communication devices; for example, when the device is an access network device, it can receive first parameters from the server. The communication device may also include a storage module coupled to the processing module, which stores the necessary program instructions and data of the device. As an example, the processing module may be a processor, the communication module may be a transceiver, and the storage module may be a memory, which may be integrated with the processor or separated from it.

[0034] In another possible implementation, the device includes a processor and may also include a memory. The processor is coupled to the memory and can be used to execute computer program instructions stored in the memory to cause the device to perform the methods in the first aspect or any possible implementation thereof, or to perform the methods in the second aspect or any possible implementation thereof. Optionally, the device also includes a communication interface, with the processor coupled to the communication interface. When the device is an access network device or a server, the communication interface may be a transceiver or an input / output interface; when the device is a chip included in an access network device or a chip included in a server, the communication interface may be the chip's input / output interface. Optionally, the transceiver may be a transceiver circuit, and the input / output interface may be an input / output circuit.

[0035] Fourthly, embodiments of this application provide a chip system, including: a processor and a memory, the processor being coupled to the memory, the memory being used to store programs or instructions, and when the program or instructions are executed by the processor, causing the chip system to implement the methods in the first aspect or any possible implementation of the first aspect, or to implement the methods in the second aspect or any possible implementation of the second aspect.

[0036] Optionally, the chip system also includes an interface circuit for exchanging code instructions with the processor.

[0037] Optionally, the chip system may include one or more processors, which can be implemented in hardware or software. When implemented in hardware, the processor may be a logic circuit, integrated circuit, etc. When implemented in software, the processor may be a general-purpose processor that reads software code stored in memory.

[0038] Optionally, the chip system may contain one or more memories. These memories may be integrated with the processor or disposed separately. For example, the memory may be a non-transitory processor, such as read-only memory (ROM), which may be integrated with the processor on the same chip or disposed on separate chips.

[0039] Fifthly, this application provides a computer-readable storage medium storing a computer program or instructions that, when executed by a communication device, cause the communication device to perform the method of the first aspect or any possible implementation thereof, or cause the communication device to perform the method of the second aspect or any possible implementation thereof.

[0040] Sixthly, this application provides a computer program product comprising a computer program or instructions that, when executed by a communication device, implement the method in the first aspect or any possible implementation thereof, or implement the method in the second aspect or any possible implementation thereof.

[0041] In a seventh aspect, embodiments of this application provide a communication system including an access network device and a server. The access network device is used to execute the method described in the first aspect or any possible implementation thereof, and the server is used to execute the method described in the second aspect or any possible implementation thereof.

[0042] The technical effects that can be achieved by any of the second to seventh aspects mentioned above can be referred to the description of the beneficial effects in the first aspect mentioned above, and will not be repeated here. Attached Figure Description

[0043] Figure 1 is a schematic diagram of a data frame transmission;

[0044] Figure 2 is a schematic diagram of a communication system;

[0045] Figure 3 is a schematic diagram of an application framework of AI in a communication system;

[0046] Figure 4 is a schematic diagram of another application framework of AI in a communication system;

[0047] Figure 5 is a schematic diagram of a data transmission path;

[0048] Figure 6 is a flowchart illustrating a data transmission method provided in this application;

[0049] Figure 7 is a schematic diagram of the process by which an access network device sends data packets to a terminal, as provided in this application.

[0050] Figure 8 is a schematic diagram of the deployment of a business forecasting model provided in this application;

[0051] Figure 9 is a flowchart illustrating a data transmission method in a specific scenario provided in this application;

[0052] Figure 10 is a flowchart illustrating another specific scenario of the data transmission method provided in this application;

[0053] Figure 11 is a flowchart illustrating another specific scenario of the data transmission method provided in this application;

[0054] Figure 12 is a schematic diagram of the structure of a communication device provided in this application;

[0055] Figure 13 is a schematic diagram of another communication device provided in this application. Detailed Implementation

[0056] The relevant technical features involved in the embodiments of this application will be explained below. It should be noted that these explanations are for the purpose of making the embodiments of this application easier to understand, and should not be regarded as a limitation on the scope of protection claimed by this application.

[0057] I. Video Encoding Methods

[0058] Bit rate refers to the number of bits transmitted per second. The unit is bits per second (bps). The higher the bit rate, the faster the data transmission speed. In audio, bit rate refers to the amount of binary data transmitted per unit time after converting an analog audio signal into a digital audio signal; it is an indirect indicator of audio quality. The principle of bit rate (also known as bit depth) in video is the same as in audio; it refers to the amount of binary data transmitted per unit time after converting an analog signal into a digital signal.

[0059] There are various video coding methods, mainly including constant bit rate (CBR) video coding and variable bit rate (VBR) video coding. CBR and VBR determine how the bit rate is allocated during the encoding process of a video file. These two coding methods are described below:

[0060] 1. CBR-based video encoding method

[0061] The bitrate of a video file remains essentially constant throughout the file, meaning that the data stream rate is relatively fixed regardless of the complexity of the scene. CBR-based video encoding is suitable for network transmission, especially for applications requiring a stable data stream, such as video conferencing or real-time streaming.

[0062] CBR-based video coding methods have the following advantages:

[0063] 1) Stability: Since the bit rate is relatively constant, CBR-based video encoding is a good choice for applications that require stable transmission.

[0064] 2) Easy to control: Since the bit rate is known, the allocation and management of network bandwidth becomes easier.

[0065] CBR-based video encoding methods have the following disadvantages:

[0066] Low efficiency: When scene complexity changes, CBR may not effectively utilize the bit rate, leading to fluctuations in video quality. That is, if the video bit rate remains constant when facing scenes of different complexities, scenes with high complexity will have lower image quality.

[0067] 2. VBR-based video encoding method

[0068] The bitrate of a video file can dynamically change according to the complexity of the scene. In complex scenes (such as action scenes), VBR-based video coding allocates more bitrate to maintain video quality; in simple scenes, it allocates less bitrate.

[0069] VBR-based video coding methods have the following advantages:

[0070] 1) Higher efficiency: The bit rate is dynamically adjusted according to the complexity of the scene, thereby reducing the file size while maintaining video quality.

[0071] 2) Better video quality: Bitrate is allocated as needed, thus maintaining higher video quality in complex scenes.

[0072] VBR-based video coding methods have the following disadvantages:

[0073] 1) Network transmission issues: Due to bit rate fluctuations, this video encoding method may not be suitable for applications that require a stable data stream.

[0074] 2) Encoding and decoding are more complex: More complex algorithms are needed to determine the bit rate allocation for different scenarios.

[0075] II. Data Frame Transmission Period

[0076] For XR and similar services, data frames can be video frames, audio frames, or other possible frames. Taking video frames as an example, video can be understood as a series of consecutive images (or pictures, photos, etc.) played continuously. Each image is a video frame. When at least 24 images are played rapidly per second, the human eye perceives it as a continuous sequence of images, i.e., video. Frame rate refers to the number of images played per second. For example, a frame rate of 30 frames per second (FPS) means 30 images are played per second, a frame rate of 60 FPS means 60 images are played per second, and so on.

[0077] Taking XR services as an example, the service model typically involves data frames arriving periodically based on the frame rate. In other words, the transmission period of a data frame is related to the frame rate. Referring to Figure 1, when the frame rate is 60 FPS, the transmission period of a data frame is 1000 / 60 = 50 / 3 milliseconds (ms), approximately 16.67 ms. Theoretically, a data frame arrives every 16.67 ms. Furthermore, considering the latency during data frame transmission, such as the latency between the terminal and the XR service server, a packet delay budget (PDB) can be configured for the XR service. This allows for a delay in the arrival time of data frames beyond their theoretical arrival time. Figure 1 uses a PDB of 10 ms as an example; data frames may arrive within the time frame corresponding to the matrix area shown in Figure 1.

[0078] III. Radio Resource Management (RRM) Measurement

[0079] In mobile communication networks, when a terminal moves from one cell to another, a handover between cells is required. Before the handover, the terminal needs to measure the signals of neighboring cells and determine the handover timing based on the measurement results. RRM (Remote Signal Management) measurements can be divided into intra-frequency measurements and inter-frequency measurements. Intra-frequency measurements refer to the terminal's serving cell (i.e., the cell the terminal is currently in) and the target cell being measured being on the same carrier frequency (center frequency). Inter-frequency measurements refer to the terminal's serving cell and the target cell being measured being on different carrier frequencies.

[0080] IV. Sending and Receiving

[0081] "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. Similar expressions in this application can be understood in a similar way, and will not be elaborated further here.

[0082] "Receiving information" can be understood as one device receiving information from another device, or it can 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. Similar expressions in this application can be understood in a similar way, and will not be elaborated further here.

[0083] The phrase "sending information to... (e.g., a terminal)" or the related illustrations in the accompanying drawings can be understood as the destination of the information being a terminal. This can include sending information directly or indirectly to a terminal. Similarly, the phrase "receiving information from... (e.g., a terminal)," "receiving information from... (e.g., a terminal)," or "receiving information sent (e.g., by a terminal)," or the related illustrations in the accompanying drawings, can be understood as the source of the information being 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.

[0084] Figure 2 is a schematic diagram illustrating a possible, non-limiting communication system. As shown in Figure 2, the communication system 10 includes a radio access network (RAN) 100 and a core network (CN) 200.

[0085] RAN 100 includes at least one access network device (110a and 110b in Figure 2, collectively referred to as 110) and at least one terminal (120a-120j in Figure 2, collectively referred to as 120). RAN 100 may also include other access network devices, such as wireless relay devices and / or wireless backhaul devices (not shown in Figure 2). Terminal 120 is wirelessly connected to access network device 110. Access network device 110 is wirelessly or wired connected to core network 200. The core network device in core network 200 and access network device 110 in RAN 100 can be different physical devices, or they can be the same physical device integrating core network logical functions and wireless access network logical functions.

[0086] 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), a cloud radio access network (CRAN), or a wireless fidelity (WiFi) system. RAN 100 can also be a communication system that integrates two or more of the above systems.

[0087] Access network device 110, sometimes referred to as RAN node, RAN entity, or access node, constitutes part of the communication system and is used to help terminals achieve wireless access. Multiple access network devices 110 in communication system 10 can be nodes of the same type or different types. In some scenarios, the roles of access network device 110 and terminal 120 are relative. For example, network element 120i in Figure 2 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.

[0088] Access network device 110 and terminal 120 are sometimes referred to as communication devices. For example, network elements 110a and 110b in Figure 2 can be understood as communication devices with base station functions, and network elements 120a-120j can be understood as communication devices with terminal functions.

[0089] In one possible scenario, the access network device 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 access network device can be a macro base station (as shown in Figure 2, 110a), a micro base station or indoor station (as shown in Figure 2, 110b), a relay node or donor node, or a radio controller in a CRAN scenario. Optionally, the access network device can also be a server, wearable device, vehicle, or in-vehicle equipment. For example, the access network device in vehicle-to-everything (V2X) technology can be a roadside unit (RSU). All or part of the functions of the access network device 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 access network device can also be equipped with communication modules, circuits, or chips that perform corresponding communication functions. The access network device may also be configured with program instructions for performing corresponding communication functions, as well as corresponding program instructions. The access network device in this application may also be a logical node, logical module, or software capable of implementing all or part of the functions of an access network device.

[0090] In another possible scenario, multiple access network devices collaborate to assist the terminal in achieving wireless access, with each device performing a portion of the base station's functions. For example, the access network devices can be a central unit (CU), a distributed unit (DU), a CU-control plane (CP), a CU-user plane (UP), or a radio unit (RU). The CU and DU can be separate entities or included in the same network element, such as a baseband unit (BBU). The RU can be included in radio frequency equipment or radio frequency units, such as a remote radio unit (RRU), an active antenna unit (AAU), or a remote radio head (RRH).

[0091] In different systems, CU (or CU-CP and CU-UP), DU, or RU may have different names, but those skilled in the art will understand their meaning. For example, in an ORAN system, CU can also be called O-CU (open CU), DU can also be called O-DU, CU-CP can also be called O-CU-CP, CU-UP can also be called O-CU-UP, and RU can also be called O-RU. For ease of description, this application uses CU, CU-CP, CU-UP, DU, and RU as examples. Any of the units among CU (or CU-CP, CU-UP), DU, and RU in this application can be implemented through software modules, hardware modules, or a combination of software and hardware modules.

[0092] 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.

[0093] To support artificial intelligence (AI) technology in wireless networks, AI nodes may also be introduced into the network.

[0094] AI nodes can be deployed in one or more of the following locations within the communication system: access network devices, terminals, or core network devices, etc. 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: access network devices, terminals, or core network devices, etc.

[0095] It is understood that this application does not limit the number of AI nodes. For example, when there are multiple AI nodes, these nodes can be divided based on function, such as different AI nodes being responsible for different functions.

[0096] 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.

[0097] AI nodes can be AI network elements or AI modules.

[0098] Figure 3 illustrates a possible application framework in a communication system. As shown in Figure 3, network elements in the communication system are connected via interfaces (e.g., NG, Xn) or air interfaces. These network element nodes, such as core network equipment, access network equipment, terminals, or one or more devices in operations administration and maintenance (OAM), are equipped with one or more AI modules (for clarity, only one AI module is shown in Figure 3). Access network equipment can be a single access network device or can include multiple access network devices, 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.

[0099] 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.

[0100] 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), a generative adversarial network (GAN), or a long short-term memory (LSTM) network.

[0101] 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.

[0102] 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.

[0103] 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.

[0104] 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.

[0105] 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.

[0106] Figure 4 illustrates a possible application framework in a communication system. As shown in Figure 4, the communication system includes a RAN intelligent controller (RIC) to implement AI-related functions. RICs include near-real-time (near-RT) RICs and non-real-time (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).

[0107] 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 access network devices (e.g., CUs, CU-CPs, CU-UPs, DUs, and / or RUs) and / or terminals. This information can be used as training data or inference data. NRT RICs can deliver inference results to access network devices 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.

[0108] 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 access network devices (e.g., CU, CU-CP, CU-UP, DU, and / or RU) and / or terminals. This information can be used as training data or inference data, and the inference results can be delivered to the access network devices 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.

[0109] 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 access network devices (e.g., CU, DU), while non-real-time RICs can be set in OAM, cloud servers, core network devices, or other network devices.

[0110] Figure 5 is a schematic diagram of a data transmission path provided in this application, which specifically includes a data network (DN) (e.g., a fixed network) → a core network (e.g., a user plane function (UPF)) → an access network device → a terminal.

[0111] The DN provides services such as operator services, Internet access, or third-party services. The DN contains a server (also known as a source), which is used to implement video source encoding, rendering, etc.

[0112] The core network performs three main functions: registration, connection, and session management. It primarily includes the network exposure function (NEF), policy control function (PCF), application function (AF), access and mobility management function (AMF), session management function (SMF), and UPF. Furthermore, the UPF, as the interface with the data network, performs functions such as user plane data forwarding, session / flow-based billing and statistics, and bandwidth limiting.

[0113] Terminal devices include XR head-mounted displays, video players, and holographic projectors.

[0114] This application provides a data transmission method, apparatus, and communication system. In the method, a server predicts a first parameter representing the size of a data packet to be transmitted at a future point in time based on a user instruction, and sends the first parameter to an access network device. The access network device predicts the size of the data packet to be transmitted at that future point in time based on the first parameter, thereby allowing the access network device to adjust its transmission strategy in advance according to the channel state and the size of the data packet to be transmitted at that future point in time. This helps to match the channel state with the data packet size, improving the data packet transmission efficiency.

[0115] The following description, in conjunction with the accompanying drawings, further illustrates a data transmission method, apparatus, and communication system. It is understood that this application uses a server, access network equipment, and a terminal as examples of the entities executing the interactive illustration, but this application does not limit the entities executing 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) within the access network equipment, or by logical nodes, logical modules, or software capable of implementing all or part of the access network equipment's functions; the method executed by the server in this application can also be implemented by modules (e.g., circuits, chips, or chip systems) within the server, or by logical nodes, logical modules, or software capable of implementing all or part of the server's functions; the method executed by the terminal in this application can also be implemented by a communication / processing module within the terminal, or by circuits or chips (such as modem chips (also known as baseband chips), or SoC chips / SIP chips containing modem cores, or GPU / AI processors / ASICs) within the terminal responsible for communication / processing functions.

[0116] For ease of description, the aforementioned future time point can be referred to as the second time point. The server and the access network device can each determine the second time point based on the reference time point. The reference time point is the time when the access network device receives the first parameter, and the reference time point can be referred to as the first time point.

[0117] Figure 6 is a flowchart illustrating a data transmission method provided in this application.

[0118] Step 601: The server predicts the first parameter based on the first business prediction model.

[0119] For example, the first business forecasting model can be deployed in the application layer on the server side.

[0120] The first parameter indicates the size of the data packet (equivalent to the data packet to be transmitted) sent by the access network device to the terminal at the second time point. The data packet sent by the access network device to the terminal originates from the server; that is, the server first sends the data packet to the access network device, and then the access network device sends the data packet to the terminal.

[0121] For example, the first parameter may include one or more of the following: screen complexity, instruction complexity, and screen change conditions. The first parameter may also be referred to as an intermediate parameter, intermediate model parameter, token model parameter, etc.

[0122] The second time point is located after the first time point, which is the time when the access network device receives the first parameter. The second time point is determined based on the first time point and a first offset. This means that in step 602 below, when the server sends the first parameter to the access network device, the server can predict the time when the access network device will receive the first parameter (i.e., the first time point). Further, when determining the first time point, the server can specifically predict the first time point when the access network device receives the first parameter based on a preset duration and the time when the server sends the first parameter. The preset duration can be determined by the server based on the duration of previous parameter transmissions to the access network device.

[0123] For example, before predicting the first parameter, the server can also obtain user instructions from the terminal. These user instructions can be understood as application-layer information, which includes at least one or more of the following: user pose control information, user operation instructions, and video fast-forward information. For example, the user can perform operations on the terminal side; correspondingly, the terminal responds to the user operation by generating user instructions, which are then transmitted to the server via the user plane. The server receives the user instructions from the terminal.

[0124] When the server predicts the first parameter based on the first business prediction model, there are several possible implementations. For example, the server determines a second time point based on a first time point and a first bias, inputs the second time point and user instructions into the first business prediction model, and the first business prediction model outputs the first parameter. Another example is that the server inputs the first time point, the first bias, and user instructions into the first business prediction model, and the first business prediction model outputs the first parameter. Yet another example is that the first business prediction model is trained to predict parameters at a future time point based on the current time point and a preset duration; in this case, the server can input user instructions into the first business prediction model, and the first business prediction model outputs the parameters at the future time point (equivalent to the first parameter).

[0125] For example, the first offset is used to indicate a time deviation. For instance, the second time point is equal to the sum of the first time point and the time deviation indicated by the first offset. Alternatively, the first offset is used to indicate the effective time of the first parameter, which means that the access network device starts timing at the time point when it receives the first parameter, and the first parameter becomes effective when the timing reaches the time deviation indicated by the first offset.

[0126] Based on the manifestation of the first bias, the following is a method provided for the server to determine the second time point based on the first time point and the first bias.

[0127] (1) The first bias is one or more milliseconds (ms).

[0128] For example, if the first bias is 10 milliseconds and the first time point is 20ms, then the server can determine the second time point as 30ms based on the first time point of 20ms and the first bias of 10ms.

[0129] (2) The first bias is one frame or more frames.

[0130] For example, the server determines a first time point when the access network device receives the first parameter, and the data frame received by the access network device at the first time point (denoted as the first data frame). Then, the server determines a second data frame based on the first data frame and a first offset. The second data frame corresponds to a second time point; that is, the time point at which the access network device receives the second data frame is the second time point. For example, if the first offset is 10 frames and the first data frame is the 20th frame, then the second data frame is the 30th frame. Accordingly, the server determines that the access network device receives the 20th frame at the first time point, and determines that the time point at which the access network device receives the 30th frame is the second time point based on the first offset.

[0131] For example, the server determines the first time point at which the access network device receives the first parameter, and the data frame sent by the server at the first time point (denoted as the first data frame). Then, the server determines the second data frame based on the first data frame and a first offset. The second data frame corresponds to the second time point; that is, the time point at which the server sends the second data frame is the second time point. For example, if the first offset is 10 frames and the first data frame is the 20th frame, then the second data frame is the 30th frame. Accordingly, the server determines that it sent the 20th frame at the first time point, and determines that the time point at which it sends the 30th frame is the second time point based on the first offset.

[0132] (3) The first bias is one or more protocol data unit sets (PDU sets).

[0133] For example, the server determines the first time point at which the access network device receives the first parameter, and the PDU set received at the first time point (denoted as the first PDU set). Then, the server determines the second PDU set based on the first PDU set and a first offset. The second PDU set corresponds to the second time point; that is, the time point at which the access network device receives the second PDU set is the second time point. For example, if the first offset is 10 PDU sets, and the first PDU set is the 20th PDU set, then the second PDU set is the 30th PDU set. Accordingly, the server determines that the access network device receives the 20th PDU set at the first time point, and determines the time point at which the access network device receives the 30th PDU set based on the first offset as the second time point.

[0134] For example, the server determines the first time point at which the access network device receives the first parameter, and at the first time point, the server sends a PDU set (denoted as the first PDU set). Subsequently, the server determines a second PDU set based on the first PDU set and a first offset. The second PDU set corresponds to a second time point; that is, the time point at which the server sends the second PDU set is the second time point. For example, if the first offset is 10 PDU sets, and the first PDU set is the 20th PDU set, then the second PDU set is the 30th PDU set. Accordingly, the server determines that it sends the 20th PDU set at the first time point, and determines that the time point at which the server sends the 30th PDU set is the second time point based on the first offset.

[0135] (4) The first bias is one or more data packets.

[0136] For example, the server determines the first time point at which the access network device receives the first parameter, and the data packet received at the first time point (denoted as the first data packet). Then, the server determines the second data packet based on the first data packet and a first offset. The second data packet corresponds to the second time point; that is, the time point at which the access network device receives the second data packet is the second time point. For example, if the first offset is 10 data packets, and the first data packet is the 20th data packet, then the second data packet is the 30th data packet. Accordingly, the server determines that the access network device received the 20th data packet at the first time point, and determines the time point at which the access network device received the 30th data packet based on the first offset as the second time point.

[0137] For example, the server determines the first time point at which the access network device receives the first parameter, and the data packet sent by the server at the first time point (denoted as the first data packet). Then, the server determines the second data packet based on the first data packet and a first offset. The second data packet corresponds to the second time point; that is, the time point at which the server sends the second data packet is the second time point. For example, if the first offset is 10 data packets, and the first data packet is the 20th data packet, then the second data packet is the 30th data packet. Accordingly, the server determines that it sent the 20th data packet at the first time point, and determines that the time point at which the server sends the 30th data packet is the second time point based on the first offset.

[0138] Of course, there are other examples of the first bias, which will not be explained one by one.

[0139] Step 602: The server sends the first parameter to the access network device.

[0140] Correspondingly, the access network device receives the first parameter from the server at the first point in time.

[0141] For example, the server sends the first parameter to the access network device via the control plane. For instance, the server sends the first parameter to the UPF, and the UPF then sends the first parameter to the access network device.

[0142] Step 603: The access network device sends a data packet to the terminal at the second time point based on the first parameter and the channel state information at the second time point.

[0143] For a detailed explanation of step 603, please refer to the flowchart shown in Figure 7, which illustrates the process of an access network device sending data packets to a terminal.

[0144] Step 701: The access network device determines the channel state information at the second time point based on the channel state model.

[0145] Channel state information is used to indicate the channel state, which can affect the efficiency of data transmission between access network devices and terminals. Channel state information includes, for example, channel state information (CSI), which includes at least one or more of the following: channel quality indicator (CQI), rank indicator (RI), precoding matrix indicator (PMI), and channel state information reference signal resource indicator (CRI).

[0146] For example, the access network device determines the channel state information at the second time point based on the channel state model, channel state information from historical time periods, information characterizing key channel states, and the terminal's location information. The channel state information from historical time periods can be determined by the terminal receiving channel state information reference signals from the access network device during those historical time periods and reported to the access network device. The information characterizing key channel states includes, for example, one or more of the following: reference signal received power (RSRP), received signal strength indication (RSSI), or signal to interference and noise ratio (SINR). The terminal's location information can include the terminal's absolute location information and / or relative location information.

[0147] In one possible example, before determining the channel state information at the second time point based on the channel state model, the access network device can first determine the second time point based on the first time point and the first offset. The determination method can be found in the description of step 601 above; "server" can be replaced with "access network device" for better understanding. The access network device inputs the channel state information of historical time periods, information used to characterize key channel states, terminal location information, and the second time point into the channel state model, and the channel state model outputs the channel state information at the second time point.

[0148] In another possible example, the access network device inputs the channel state information of historical time periods, information used to characterize the key channel state, the terminal location information, the first time, and the first bias into the channel state model, and the channel state model outputs the channel state information at the second time point.

[0149] In another possible example, the channel state model is trained to predict the channel state information at a future time point based on the current time point and a preset duration. In this case, the server can input the channel state information of historical time periods, information used to characterize key channel states, and the location information of the terminal into the channel state model, and the channel state model outputs the channel state at the second time point.

[0150] Of course, the input and output parameters of the channel state model may also take other forms, which are not limited in this application.

[0151] Step 702: The access network device predicts the size of the data packet to be sent to the terminal at the second time point based on the channel state information at the second time point, the first parameter, and the second service prediction model.

[0152] For example, the second service prediction model can be deployed in the MAC layer of the access network device.

[0153] For example, the access network device inputs the channel state information at the second time point and the first parameter into the second service prediction model, and the second service prediction model outputs the size of the data packet sent by the access network device to the terminal at the second time point. As another example, the channel state model is concatenated with the second service prediction model, and the channel state information at the second time point output by the channel state model can be used as the input to the second service prediction model.

[0154] For example, the access network device can also predict a confidence interval (or confidence level) for the size of the data packets. For instance, the output of the second service prediction model may also include a confidence interval (or confidence level) for the size of the data packets.

[0155] Step 703: The access network device sends a data packet to the terminal based on the size of the data packet sent by the access network device to the terminal at the second time point and the channel state information at the second time point.

[0156] Specifically, this may include the following steps a through d:

[0157] Step a: The access network device determines the transmission requirements at the second time point based on the size of the data packets sent by the access network device to the terminal at the second time point. For example, the access network device includes a transmission requirement model, which indicates the mapping relationship between data packet sizes and transmission requirements. In model inference, the access network device can input the size of the data packets sent by the access network device to the terminal at the second time point into the transmission requirement model, and the transmission requirement model outputs the transmission requirements corresponding to that data packet size.

[0158] Step b: If the access network device determines that the channel state information at the second time point does not match the transmission requirements at the second time point, it adjusts the transmission strategy.

[0159] The transmission strategy is a strategy used for data transmission between access network devices and terminals. Examples of transmission strategies include RRM measurement limits for terminals, the number of component carriers (CCs) configured for terminals, and multi-user pairing algorithm optimization. For instance, multi-user pairing algorithm optimization involves pairing multiple users based on the different amounts of data to be transmitted, ensuring that successfully paired users use the same resource block to transmit data.

[0160] Furthermore, adjusting transmission strategies could involve adjusting the CC (Control Channel) used for data transmission for the terminal, or adjusting the RRM (Remote Link Regulator) measurement limits for the terminal. For example, if the access network device determines that the channel state at a second time point cannot meet the transmission requirements at that time point, it can increase (enable) the CC used for data transmission for the terminal, and / or relax the RRM measurement limits for the terminal. Relaxing the RRM measurement limits can be achieved, for example, by skipping the RRM measurement time slot using downlink control information (DCI), enabling more uplink / downlink transmission opportunities. As another example, if the access network device determines that the channel state at a second time point meets the transmission requirements and there are still remaining transmission resources, it can disable the CC used for data transmission for the terminal, and / or increase the RRM measurement limits for the terminal.

[0161] In step c, the server generates a data packet and sends it to the access network device. Correspondingly, the access network device receives the data packet from the server; this data packet is the one the access network device needs to send to the terminal at the next point in time.

[0162] Step d: The access network device sends data packets to the terminal at the second time point according to the adjusted transmission strategy.

[0163] It is understandable that the access network device predicts in advance the size of the data packets it needs to send to the terminal at the second time point, as well as the channel state information at that time point. If the access network device determines that the two do not match, it adjusts the transmission strategy in advance so that the channel state information at the second time point can match the size of the data packets to be transmitted, thereby improving transmission efficiency.

[0164] The method of this application may also include: step 600 (not shown in Figure 6), in which the server and the access network device negotiate a first bias.

[0165] In one possible implementation, the value of the first bias is determined by the access network device. For example, the access network device determines the value of the first bias based on one or more of the following parameters (1) and (2).

[0166] (1) The time required for access network equipment to adjust transmission strategies.

[0167] For example, adjusting the transmission strategy involves skipping the RRM measurement time slot via DCI. The access network device needs to determine the time that DCI needs to be sent in advance based on the measurement time slot to be skipped, and then determine the duration required for the access network device to adjust the transmission strategy based on that time.

[0168] (2) Predictive capability of channel state model.

[0169] For example, a channel state model can predict the channel state at a fourth time point based on input at a third time point. The difference between the third and fourth time points is the first prediction duration, which characterizes the predictive capability of the channel prediction model. For instance, if the third time point is 10ms and the fourth time point is 30ms, the channel state model can predict the channel state at 30ms based on input at 10ms. That is, the first prediction duration is 20ms, or in other words, the predictive capability of the channel prediction model is 20ms.

[0170] For another example, a channel state model can predict channel state information at any point in a future period. The start time of this future period is the third time point input by the channel state model, and the end time of this future period is the latest time point that the channel state model can predict (e.g., the fourth time point). The difference between the third time point and the fourth time point is the first prediction duration, which characterizes the predictive capability of the channel prediction model. The third time point can specifically be the current time point when the channel state model makes its prediction. For example, the third time point is 10ms, and the fourth time point is 30ms. Based on the input at 10ms, the channel state model can predict the channel state at any time between 10ms and 30ms. That is, the first prediction duration is 20ms, or, in other words, the predictive capability of the channel prediction model is 20ms.

[0171] Furthermore, the predictive power of the channel state model is related to the future time periods that the channel state model can predict.

[0172] In one possible example, after determining the first offset, the access network device sends the first offset to the server, and the server receives the first offset from the access network device, thereby completing the negotiation of the first offset.

[0173] In another possible example, the access network device and the server each store a mapping between offsets and indices. The access network device determines the index of the first offset based on the mapping and the first offset. Correspondingly, the server receives the index of the first offset from the access network device, and then determines the first offset based on the index and the mapping, thus completing the negotiation of the first offset. For example, the access network device and the server each store a mapping between offsets and indices as shown in Table 1. The access network device determines to use offset1, and therefore determines index1 based on the mapping and offset1. The access network device sends index1 to the server, and the server receives index1 from the access network device. The server determines offset1 based on index1 and the mapping. That is, the server and the access network device negotiate to use offset1 as the first offset.

[0174] Table 1

[0175] For example, the first bias is included in the request information, or the index of the first bias is included in the request information. There are two possible ways for the access network device to send request information to the server: Example 1: The access network device sends request information to the AMF through the control plane N2 interface, and the AMF then sends request information to the server. Example 2: A new entity for deploying the first service prediction model is added to the server, a new control plane interface is added between the access network device and this entity, and the access network device sends request information to the new entity through this new control plane interface.

[0176] In addition, after receiving the first bias, the server can also determine whether it supports the first bias, that is, whether it has the ability to perform parameter prediction based on the first bias, or whether it has the ability to perform parameter prediction based on the first bias and the first time point.

[0177] In one possible example, the server confirms the second prediction duration, which is interpreted as follows: the first business prediction model can predict the parameters at the sixth time point based on the input at the fifth time point, where the difference between the fifth and sixth time points is the second prediction duration; or it can be interpreted as follows: the first business prediction model can predict the parameters at any time point in a future period, where the start time point of the future period is the fifth time point input by the first business prediction model, and the end time point of the future period is the latest time point that the first business prediction model can predict (e.g., the sixth time point), where the difference between the fifth and sixth time points is the second prediction duration. This second prediction duration characterizes the predictive capability of the first business prediction model. Specifically, the fifth time point can be the current time point at which the first business prediction model makes its prediction.

[0178] Furthermore, if the second prediction duration is greater than or equal to the duration of the time deviation indicated by the first bias, the server determines that it has the ability to perform parameter prediction based on the first bias; if the second prediction duration is less than the duration of the time deviation indicated by the first bias, the server determines that it does not have the ability to perform parameter prediction based on the first bias.

[0179] The server can also send confirmation information to the access network device, which indicates whether the server has the ability to predict parameters based on the first bias.

[0180] For example, the confirmation information is a 1-bit indication. When the indication is 1, it indicates that the server has the ability to predict parameters based on the first bias; when the indication is 0, it indicates that the server does not have the ability to predict parameters based on the first bias.

[0181] For example, the confirmation information is a second bias or an index of the second bias. The second bias is determined based on the second prediction duration. Accordingly, when the second bias is greater than or equal to the first bias, it indicates that the server has the ability to perform parameter prediction based on the first bias; when the second bias is less than the first bias, it indicates that the server does not have the ability to perform parameter prediction based on the first bias.

[0182] Of course, the confirmation information may also include indication information and a second bias, or an index of indication information and a second bias. When the indication information is 1 and the second bias is greater than or equal to the first bias, the server indicates that it has the ability to predict parameters based on the first bias. When the indication information is 0 and the second bias is less than the first bias, the server indicates that it does not have the ability to predict parameters based on the first bias.

[0183] The second offset is used to indicate the time deviation. Specifically, the second offset can be one or more milliseconds, one or more frames, one or more PDU sets, or one or more data packets. For an explanation of how the server sends the second offset or its index to the access network device, please refer to the above explanation of the first offset.

[0184] Of course, if the server does not have the ability to predict parameters based on the first bias, the server may also not send an acknowledgment message to the access network device. That is, if the access network device does not receive an acknowledgment message within a preset time period, it is determined that the server does not have the ability to predict parameters based on the first bias.

[0185] Furthermore, when the server lacks the ability to predict parameters based on the first bias, the access network device and the server can renegotiate the first bias or use the second bias for parameter prediction.

[0186] There are two possible ways for the server to send acknowledgment information to the access network device: Example 1: The server sends acknowledgment information to the AMF (Advanced Management Function), and the AMF sends the acknowledgment information to the access network device through the control plane N2 interface. Example 2: A new entity is added to the server for deploying the first service prediction model, and this entity sends acknowledgment information to the access network device through the newly added control plane interface.

[0187] Furthermore, when the access network device and the server negotiate the first parameter, specifically, the access network device may request the configuration of the first parameter from the server. For example, before step 601, the access network device sends a prediction capability information configuration request to the server, and correspondingly, the server sends a prediction capability information configuration confirmation (or prediction capability information configuration response) to the access network device. The prediction capability information configuration confirmation is a response to the prediction capability information configuration request. The prediction capability information configuration request includes request information, and the prediction capability information configuration confirmation includes confirmation information.

[0188] Alternatively, during the negotiation of the first parameter between the access network device and the server, specifically, the access network device may request the server to modify the first parameter. For example, after step 603, the access network device sends a prediction capability information modification request to the server. Correspondingly, the server sends a prediction capability information modification confirmation (or prediction capability information configuration response) to the access network device. The prediction capability information modification confirmation is a response to the prediction capability information modification request. The prediction capability information modification request includes request information, and the prediction capability information modification confirmation includes confirmation information.

[0189] In this application, the confirmation information can be transmitted via the control plane between the access network device and the server, or via the data plane between the access network device and the server. In the latter case, the confirmation information and the first parameter can be sent in a single message. For example, the first parameter occupies the payload field of the message, and the confirmation information occupies the header field of the message. Alternatively, the confirmation information and the data packet can be sent in a single message. It can be understood that the server will send multiple data packets to the access network device. The data packet in step c can be referred to as the first data packet. That is, the first parameter is used to indicate the size of the first data packet. The server can carry the confirmation information and the data packet to be sent (referred to as the second data packet) in the same message and send them together. For example, the second data packet occupies the payload field of the message, the confirmation information occupies the header field of the message, and the second data packet is sent before the first data packet.

[0190] It should also be added that the aforementioned first service prediction model can also be deployed on the terminal side. Correspondingly, the actions executed by the server can be executed by the terminal. The difference is that the terminal can directly obtain user instructions and predict the first parameter based on the user instructions and the first service prediction model. Furthermore, when the terminal sends confirmation information to the access network device, it can send it through the control plane or, when sending it through the user plane, the confirmation information and the first parameter are sent in a single message.

[0191] Figure 8 is a schematic diagram of a service prediction model provided in this application. This service prediction model is a dual-end deployment model (or a two-sided deployment model, twin deployment model, etc.), in which the first service prediction model is deployed at the application layer on the server side, and the second service prediction model is deployed at the MAC layer on the access network device side. The specific process is as follows:

[0192] Operation 1: The terminal transmits user commands to the server through the user plane.

[0193] Operation 2: The server receives user instructions from the terminal and inputs these instructions into the first service prediction model. Correspondingly, the first service prediction model outputs a first parameter. This first parameter is used to predict the size of the data packets sent from the access network device to the terminal at the second time point. The server sends the first parameter to the UPF, which then sends it to the access network device.

[0194] Operation 3: The access network device receives the first parameter, inputs the channel state information at the second time point and the first parameter into the second service prediction model, and correspondingly, the second service prediction model outputs the second parameter. The second parameter includes the size of the data packet sent by the access network device to the terminal at the second time point. For example, the second parameter also includes the confidence interval (or confidence level) of the data packet size.

[0195] Operation 4: The access network device then determines whether to adjust the transmission strategy based on the channel state information and the second parameter at the second time point. For example, the access network device determines its transmission requirement to send data packets to the terminal at the second time point based on the second parameter. If the access network device determines that the channel state at the second time point does not match the transmission requirement, it adjusts the transmission strategy; if the access network device determines that the channel state at the second time point matches the transmission requirement, no adjustment of the transmission strategy is needed.

[0196] Figure 9 is a flowchart illustrating a data transmission method in a specific scenario provided by this application. A first service prediction model is deployed on the server side, and a second service prediction model is deployed on the access network device side. The access network device sends a first bias to the server through control, and the first bias is used to indicate the effective time of the first parameter.

[0197] Step 901: The access network device sends a prediction capability information configuration request to the server.

[0198] Correspondingly, the server receives a configuration request for prediction capability information from the access network device.

[0199] The prediction capability information configuration request includes a first bias, which can be one or more milliseconds, one or more frames, one or more PDU sets, or one or more data packets.

[0200] Step 902: The server sends a configuration confirmation of the prediction capability information to the access network device.

[0201] Correspondingly, the access network device receives the prediction capability information configuration confirmation from the server.

[0202] In one possible example, the prediction capability information configuration confirmation includes confirmation information that indicates whether the server responds to the access network device's request, that is, whether the server has the capability to predict parameters based on a first bias.

[0203] Step 903: The terminal sends a user instruction to the server. Correspondingly, the server receives the user instruction from the terminal.

[0204] Step 904: The server determines the first parameter based on the user instruction and the first business prediction model.

[0205] Step 905: The server sends the first parameter to the access network device.

[0206] Correspondingly, the access network device receives the first parameter from the server at the first point in time.

[0207] Step 906: The access network device predicts the channel state information at the second time point based on the channel prediction model.

[0208] Step 907: The access network device determines the data packet size at the second time point based on the first parameter, the channel state information at the second time point, and the second service prediction model.

[0209] Step 908: The access network device adjusts the transmission strategy based on the channel state information and the data packet size at the second time point.

[0210] Step 909: The server sends data packets to the access network devices.

[0211] This data packet is the data packet that the access network device needs to send to the terminal at the second point in time.

[0212] Step 910: The access network device sends data packets to the terminal at the second time point according to the adjusted transmission strategy.

[0213] It should be noted that for the contents not described in detail in steps 901 and 902, please refer to step 600; for the contents not described in detail in steps 903 and 904, please refer to step 601; for the contents not described in detail in step 905, please refer to step 602; for the contents not described in detail in steps 906 to 910, please refer to step 603.

[0214] Figure 10 is a flowchart illustrating another specific scenario of the data transmission method provided in this application. A first service prediction model is deployed on the terminal side, and a second service prediction model is deployed on the access network device side. The access network device sends a first bias to the terminal through control. The first bias is used to indicate the effective time of the first parameter.

[0215] Step 1001: The access network device sends a prediction capability information configuration request to the terminal.

[0216] Correspondingly, the terminal receives a configuration request for predictive capability information from the access network device.

[0217] The prediction capability information configuration request includes a first bias, which can be one or more milliseconds, one or more frames, one or more PDU sets, or one or more data packets.

[0218] Step 1002: The terminal sends a prediction capability information configuration confirmation to the access network device.

[0219] Correspondingly, the access network device receives the prediction capability information configuration confirmation from the terminal.

[0220] In one possible example, the prediction capability information configuration confirmation includes confirmation information that indicates whether the terminal responds to the access network device's request, that is, whether the terminal has the ability to predict parameters based on a first bias.

[0221] Step 1003: The terminal determines the first parameter based on the user instruction and the first service prediction model.

[0222] Step 1004: The terminal sends the first parameter to the access network device.

[0223] Correspondingly, the access network device receives the first parameter from the terminal at the first point in time.

[0224] Step 1005: The access network device predicts the channel state information at the second time point based on the channel prediction model.

[0225] Step 1006: The access network device determines the data packet size at the second time point based on the first parameter, the channel state information at the second time point, and the second service prediction model.

[0226] Step 1007: The access network device adjusts the transmission strategy based on the channel state information and the data packet size at the second time point.

[0227] Step 1008: The server sends data packets to the access network devices.

[0228] This data packet is the data packet that the access network device needs to send to the terminal at the second point in time.

[0229] Step 1009: The access network device sends data packets to the terminal at the second time point according to the adjusted transmission strategy.

[0230] It should be noted that for the content not described in detail in steps 1001 and 1002, please refer to step 600; for the content not described in detail in step 1003, please refer to step 601, and you can understand it by replacing "server" with "terminal" in step 601; for the content not described in detail in step 1004, please refer to step 602; for the content not described in detail in steps 1005 to 1009, please refer to step 603, and you can understand it by replacing "server" with "terminal" in step 603.

[0231] Figure 11 is a flowchart illustrating another specific scenario of the data transmission method provided in this application. In this method, a first service prediction model is deployed on the server side, and a second service prediction model is deployed on the access network device side. The access network device sends a first bias to the server via control, the first bias indicating the effective time of a first parameter. The first parameter and an acknowledgment message are sent to the access network device in a single message.

[0232] Step 1101: The access network device sends a prediction capability information configuration request to the server.

[0233] Correspondingly, the server receives a configuration request for prediction capability information from the access network device.

[0234] Step 1102: The terminal sends a user instruction to the server. Correspondingly, the server receives the user instruction from the terminal.

[0235] Step 1103: The server determines the first parameter based on the user instruction and the first business prediction model.

[0236] Step 1104: The server sends the first parameter and confirmation information to the access network device. For example, the first parameter and confirmation information are contained in a single message. For example, the confirmation information occupies the header field of the message, and the first parameter occupies the payload field of the message.

[0237] Step 1105: The access network device predicts the channel state information at the second time point based on the channel prediction model.

[0238] Step 1106: The access network device determines the data packet size at the second time point based on the first parameter, the channel state information at the second time point, and the second service prediction model.

[0239] Step 1107: The access network device adjusts the transmission strategy based on the channel state information and the data packet size at the second time point.

[0240] Step 1108: The server sends data packets to the access network devices.

[0241] This data packet is the data packet that the access network device needs to send to the terminal at the second point in time.

[0242] Step 1109: The access network device sends data packets to the terminal at the second time point according to the adjusted transmission strategy.

[0243] It should be noted that for the contents not described in detail in steps 1101 and 1104, please refer to steps 600 and 602; for the contents not described in detail in steps 1102 and 1103, please refer to step 601; for the contents not described in detail in steps 1105 to 1109, please refer to step 603.

[0244] It should also be noted that the definition of the first time point (or reference time point) mentioned above refers to the time point at which the access network device receives the first parameter. However, in other examples, the first time point can also be the time point at which the server sends the first parameter. Accordingly, the access network device can determine the time point at which the server sends the first parameter based on the time point at which it receives the first parameter and a preset duration. The preset duration can be determined by the access network device based on the duration of previous parameters received from the server. Alternatively, when the server sends the first parameter to the access network device, it also carries a timestamp of the first parameter's transmission, allowing the access network device to determine the time point at which the server sends the first parameter based on the timestamp. Of course, the first time point (or reference time point) can also have other definitions, which will not be listed in detail in this application.

[0245] This application also provides a data transmission method in which a server predicts a first parameter based on a first service prediction model. The first parameter indicates the size of the data packet sent by the access network device to the terminal at a second time point. The second time point is located after the first time point and is determined based on the first time point and a first offset, whereby the first offset indicates the time deviation. The server sends the first parameter to the access network device, and correspondingly, the access network device receives the first parameter from the server and, based on the first parameter and the channel state information at the second time point, sends a data packet to the terminal at the second time point. The first time point is a reference time point negotiated between the server and the access network device, such as the time when the server sends the first parameter or the time when the access network device receives the first parameter, etc. For details not described in this method, please refer to the descriptions in the relevant embodiments shown in Figures 6 to 11 above, the difference being the different definitions of the first time point.

[0246] It is understood that the step numbers in the above flowcharts are merely examples of the execution flow and do not constitute a restriction on the order of step execution. In this embodiment, there is no strict execution order between steps that do not have temporal dependencies. Not all steps shown in the flowcharts are mandatory. Some steps can be deleted from the flowcharts as needed, or other possible steps can be added to the flowcharts as needed.

[0247] The above focuses on describing the differences between different embodiments. Apart from the differences, the embodiments can be referred to each other. In addition, different implementations or different examples in the same embodiment can also be referred to each other.

[0248] Figure 12 shows a possible exemplary block diagram of the communication device involved in the embodiments of this application. As shown in Figure 12, the communication device 1200 may include units or modules for implementing the method embodiments described above.

[0249] In one possible implementation, the communication device 1200 includes a processing module 1202 and a communication module 1203. Optionally, the communication device 1200 may further include a storage module 1201 for storing device program code and / or data.

[0250] The communication device 1200 can be a device on the access network equipment side in the above embodiments.

[0251] The communication module 1203 is used to receive a first parameter from the server at a first time point. The first parameter is predicted by the server according to a first service prediction model. The first parameter is used to indicate the size of the data packet sent by the access network device to the terminal at a second time point. The second time point is located after the first time point and is determined based on the first time point and a first offset. The first offset is used to indicate the time deviation.

[0252] The processing module 1202 is used to control the communication module 1203 to send data packets to the terminal at the second time point based on the first parameter and the channel state information at the second time point.

[0253] In one possible implementation, when the processing module 1202 controls the communication module 1203 to send data packets to the terminal at the second time point based on the first parameter and the channel state information at the second time point, it is specifically used to: determine the channel state information at the second time point based on the channel state model; predict the size of the data packets sent by the access network device to the terminal at the second time point based on the channel state information at the second time point, the first parameter, and the second service prediction model; and control the communication module 1203 to send data packets to the terminal based on the size of the data packets sent by the access network device to the terminal at the second time point and the channel state information at the second time point.

[0254] In one possible implementation, when the processing module 1202 controls the communication module 1203 to send data packets to the terminal based on the size of the data packets sent by the access network device to the terminal at the second time point and the channel state information at the second time point, it is specifically used to: determine the transmission requirements at the second time point based on the size of the data packets sent by the access network device to the terminal at the second time point; adjust the transmission strategy if it is determined that the channel state information at the second time point does not match the transmission requirements at the second time point; control the communication module 1203 to receive data packets from the server; and control the communication module 1203 to send data packets to the terminal at the second time point according to the adjusted transmission strategy.

[0255] In one possible implementation, the communication module 1203 is further configured to: send a first bias or an index of the first bias to the server.

[0256] In one possible implementation, the communication module 1203 is further configured to: receive confirmation information from the server, the confirmation information being used to characterize the server's ability to predict parameters based on a first bias.

[0257] In one possible implementation, the processing module 1202 is further configured to: determine a first bias based on one or more of the following parameters: the duration required to adjust the transmission strategy; the predictive capability of the channel state model; and / or the future time period that the channel state model can predict.

[0258] The communication device 1200 can be the server-side device in the above embodiments.

[0259] The processing module 1202 is used to predict a first parameter according to a first service prediction model. The first parameter is used to indicate the size of the data packet sent by the access network device to the terminal at a second time point. The second time point is located after the first time point and is determined based on the first time point and a first offset. The first offset is used to indicate the time deviation.

[0260] The communication module 1203 is used to send a first parameter to the access network device. The first time point is the time point at which the access network device receives the first parameter. The first parameter is used by the access network device to send data packets to the terminal at a second time point.

[0261] In one possible implementation, the communication module 1203 is further configured to receive a first bias or an index of the first bias from the access network device.

[0262] In one possible implementation, the communication module 1203 is also used to send acknowledgment information to the access network device, the acknowledgment information being used to characterize the server's ability to predict parameters based on the first bias.

[0263] It is understood that the module division in the above-described device is merely a logical functional division; one function may correspond to one functional module, or two or more functions may be integrated into one functional module. In actual implementation, all or some modules may be integrated into one physical entity, or they may be distributed across different physical entities. Furthermore, the aforementioned functional modules 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.

[0264] In one example, the functional module 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.

[0265] In one example, storage module 1201 may include random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory and / or registers, etc.

[0266] Figure 13 shows the apparatus 1300 provided in an embodiment of this application. The apparatus shown in Figure 13 can be a hardware circuit implementation of the apparatus shown in Figure 12. This apparatus can be applied to the flowcharts shown above to perform the functions of the access network device or server in the above method embodiments.

[0267] For ease of explanation, Figure 13 only shows the main components of the device.

[0268] The device 1300 shown in Figure 13 includes a communication interface 1310, a processor 1320, and a memory 1330, wherein the memory 1330 is used to store program instructions and / or data. The processor 1320 may operate in conjunction with the memory 1330. The processor 1320 may execute the program instructions stored in the memory 1330. When the instructions or program stored in the memory 1330 are executed, the processor 1320 is used to perform the operations performed by the processing module 1202 in the above embodiments, and the communication interface 1310 is used to perform the operations performed by the communication module 1203 in the above embodiments.

[0269] The memory 1330 and the processor 1320 are coupled. The coupling in this embodiment is an indirect coupling or communication connection between devices, units, or modules, and can be electrical, mechanical, or other forms, used for information exchange between devices, units, or modules. At least one of the memories 1330 may be included in the processor 1320.

[0270] In this embodiment, the communication interface can be a transceiver, circuit, bus, module, or other type of communication interface. In this embodiment, when the communication interface is a transceiver, the transceiver can include an independent receiver, an independent transmitter, or a transceiver integrating transceiver functions, or simply a communication interface.

[0271] Device 1300 may also include a communication line 1340. The communication interface 1310, processor 1320, and memory 1330 can be interconnected via the communication line 1340. The communication line 1340 can be a peripheral component interconnect (PCI) bus 1340 or an extended industry standard architecture (EISA) bus 1340, etc. The communication line 1340 can be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is used in Figure 13, but this does not indicate that there is only one bus or one type of bus.

[0272] This application provides a chip (or chip system) including a processor for implementing any of the above-described method embodiments.

[0273] This application provides a computer-readable storage medium storing a computer program or instructions that, when executed, implement any of the above-described method embodiments.

[0274] This application provides a computer program product, which includes a computer program or instructions that, when executed, implement any of the above-described method embodiments.

[0275] This application provides a communication system, including the server and access network device described in the above method embodiments. Furthermore, it may also include the terminal described in the above method embodiments.

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

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

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

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

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

[0281] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A data transmission method, characterized in that, Applied to the access network equipment side, including: At a first time point, a first parameter is received from the server. The first parameter is predicted by the server according to a first service prediction model. The first parameter is used to indicate the size of the data packet sent by the access network device to the terminal at a second time point. The second time point is located after the first time point and is determined based on the first time point and a first offset. The first offset is used to indicate the time deviation. Based on the first parameter and the channel state information at the second time point, the data packet is sent to the terminal at the second time point.

2. The method as described in claim 1, characterized in that, The step of sending the data packet to the terminal at the second time point based on the first parameter and the channel state information at the second time point includes: Based on the channel state model, determine the channel state information at the second time point; Based on the channel state information at the second time point, the first parameter, and the second service prediction model, the size of the data packet sent by the access network device to the terminal at the second time point is predicted. The data packet is sent to the terminal based on the size of the data packet sent by the access network device to the terminal at the second time point and the channel state information at the second time point.

3. The method as described in claim 2, characterized in that, The step of sending the data packet to the terminal based on the size of the data packet sent by the access network device to the terminal at the second time point and the channel state information at the second time point includes: The transmission requirements at the second time point are determined based on the size of the data packets sent from the access network device to the terminal at the second time point. If it is determined that the channel state information at the second time point does not match the transmission requirements at the second time point, the transmission strategy is adjusted. Receive the data packet from the server; According to the adjusted transmission strategy, the data packet is sent to the terminal at the second time point.

4. The method as described in claim 2 or 3, characterized in that, The step of determining the channel state information at the second time point based on the channel state model includes: The channel state information at the second time point is determined based on one or more of the following: the channel state model, channel state information for historical time periods, reference signal received power, received signal strength, signal-to-interference-plus-noise ratio, and the location information of the terminal.

5. The method according to any one of claims 1-4, characterized in that, Also includes: Send the first bias or the index of the first bias to the server.

6. The method as described in claim 5, characterized in that, Also includes: Receive confirmation information from the server, the confirmation information being used to characterize the server's ability to perform parameter prediction based on the first bias.

7. The method as described in claim 6, characterized in that, The first parameter and the confirmation information are carried in the same message. The first parameter occupies the payload field of the message, and the confirmation information occupies the header field of the message.

8. The method according to any one of claims 1-7, characterized in that, Also includes: The first bias is determined based on one or more of the following parameters: The time required to adjust the transmission strategy; Predictive capability of channel state models.

9. The method according to any one of claims 1-8, characterized in that, The first offset is one or more milliseconds, or the first offset is one or more frames, or the first offset is one or more sets of protocol data units, or the first offset is one or more data packets.

10. The method according to any one of claims 1-9, characterized in that, The first parameter includes one or more of the following: screen complexity, instruction complexity, and screen change conditions.

11. A data transmission method, characterized in that, Applied to the access network equipment side, including: A first parameter is received from the terminal at a first time point. The first parameter is predicted by the terminal according to a first service prediction model. The first parameter is used to indicate the size of the data packet sent by the access network device to the terminal at a second time point. The second time point is located after the first time point and is determined based on the first time point and a first offset. The first offset is used to indicate the time deviation. Based on the first parameter and the channel state information at the second time point, the data packet is sent to the terminal at the second time point.

12. The method as described in claim 11, characterized in that, The step of sending the data packet to the terminal at the second time point based on the first parameter and the channel state information at the second time point includes: Based on the channel state model, determine the channel state information at the second time point; Based on the channel state information at the second time point, the first parameter, and the second service prediction model, the size of the data packet sent by the access network device to the terminal at the second time point is predicted. The data packet is sent to the terminal based on the size of the data packet sent by the access network device to the terminal at the second time point and the channel state information at the second time point.

13. The method as described in claim 12, characterized in that, The step of sending the data packet to the terminal based on the size of the data packet sent by the access network device to the terminal at the second time point and the channel state information at the second time point includes: The transmission requirements at the second time point are determined based on the size of the data packets sent from the access network device to the terminal at the second time point. If it is determined that the channel state information at the second time point does not match the transmission requirements at the second time point, the transmission strategy is adjusted. Receive the data packet from the server; According to the adjusted transmission strategy, the data packet is sent to the terminal at the second time point.

14. The method as described in claim 12 or 13, characterized in that, The step of determining the channel state information at the second time point based on the channel state model includes: The channel state information at the second time point is determined based on one or more of the following: the channel state model, channel state information for historical time periods, reference signal received power, received signal strength or signal-to-interference-plus-noise ratio, and the location information of the terminal.

15. The method according to any one of claims 11-14, characterized in that, Also includes: Send the first bias or the index of the first bias to the terminal.

16. The method as described in claim 15, characterized in that, Also includes: The terminal receives confirmation information, which characterizes the terminal's ability to predict parameters based on the first bias.

17. The method as described in claim 16, characterized in that, The first parameter and the confirmation information are carried in the same message. The first parameter occupies the payload field of the message, and the confirmation information occupies the header field of the message.

18. The method according to any one of claims 11-17, characterized in that, Also includes: The first bias is determined based on one or more of the following parameters: The time required to adjust the transmission strategy; Predictive capability of channel state models.

19. The method according to any one of claims 11-18, characterized in that, The first offset is one or more milliseconds, or the first offset is one or more frames, or the first offset is one or more sets of protocol data units, or the first offset is one or more data packets.

20. The method according to any one of claims 11-19, characterized in that, The first parameter includes one or more of the following: screen complexity, instruction complexity, and screen change conditions.

21. A data transmission method, characterized in that, Applied to the server side, including: According to the first service prediction model, a first parameter is predicted. The first parameter is used to indicate the size of the data packet sent by the access network device to the terminal at a second time point. The second time point is located after the first time point. The second time point is determined based on the first time point and a first offset. The first offset is used to indicate the time deviation. The first parameter is sent to the access network device, where the first time point is the time point at which the access network device receives the first parameter, and the first parameter is used by the access network device to send the data packet to the terminal at the second time point.

22. The method as described in claim 21, characterized in that, Also includes: Receive the first offset or the index of the first offset from the access network device.

23. The method as described in claim 22, characterized in that, Also includes: Send an acknowledgment message to the access network device, the acknowledgment message being used to characterize that the server has the ability to predict parameters based on the first bias.

24. The method as described in claim 23, characterized in that, The first parameter and the confirmation information are carried in the same message. The first parameter occupies the payload field of the message, and the confirmation information occupies the header field of the message.

25. The method according to any one of claims 21-24, characterized in that, The first offset is one or more milliseconds, or the first offset is one or more frames, or the first offset is one or more sets of protocol data units, or the first offset is one or more data packets.

26. The method according to any one of claims 21-25, characterized in that, Before predicting the first parameter according to the first business prediction model, the method further includes: Obtain application layer information, which includes one or more of user gesture control information, user operation commands, and video fast-forward information; The step of predicting the first parameter according to the first business prediction model includes: The second time point and the application layer information are input into the first business prediction model to obtain the first parameter.

27. The method according to any one of claims 21-26, characterized in that, The first parameter includes one or more of the following: screen complexity, instruction complexity, and screen change conditions.

28. A communication device, characterized in that, It includes a module for performing the method as described in any one of claims 1-10, or a module for performing the method as described in any one of claims 11-20, or a module for performing the method as described in any one of claims 21-27.

29. A communication device, characterized in that, The device includes a processor and an interface circuit. The interface circuit is used to receive signals from other communication devices besides the communication device and transmit them to the processor, or to send signals from the processor to other communication devices besides the communication device. The processor is used to implement the method as described in any one of claims 1-10 through logic circuits or executable code instructions, or the processor is used to implement the method as described in any one of claims 11-20 through logic circuits or executable code instructions, or the processor is used to implement the method as described in any one of claims 21-27 through logic circuits or executable code instructions.

30. A computer-readable storage medium, characterized in that, The storage medium stores a computer program or instructions that, when executed by a communication device, implement the method as described in any one of claims 1-10, or the method as described in any one of claims 11-20, or the method as described in any one of claims 21-27.

31. A computer program product, characterized in that, The computer program product includes a computer program or instructions that, when executed by a communication device, implement the method as described in any one of claims 1-10, or implement the method as described in any one of claims 11-20, or implement the method as described in any one of claims 21-27.

32. A chip system, characterized in that, include: A processor and a memory, wherein the processor is coupled to the memory, and the memory is used to store programs or instructions; When the program or instructions are executed by the processor, the chip system implements the method as described in any one of claims 1-10, or the method as described in any one of claims 11-20, or the method as described in any one of claims 21-27.

33. A communication system, characterized in that, It includes an access network device for implementing the method of any one of claims 1-10, and a server for implementing the method of any one of claims 11-20.

Images