Uplink transmission method for video data, and communication apparatus

Abstract

Provided in the present application are an uplink transmission method for video data, and a communication apparatus. The method comprises: a terminal sending first video data to an access network device by means of a first quality of service (QoS) flow, and the access network device receiving the first video data, wherein the resolution of the first video data is a first resolution, and delay budget information corresponding to the first QoS flow is at least related to a computing delay budget, the computing delay budget being a processing delay budget for converting low-resolution video data into high-resolution video data; the access network device converting the first video data into second video data, wherein the resolution of the second video data is a second resolution, the second resolution being higher than the first resolution; and the access network device sending the second video data to a server. The method facilitates a terminal in uploading video data in a timely manner.

Description

Method for uplink transmission of video data and communication device

[0001] The present application claims priority to the Chinese patent application No. 202410544765.5, filed on April 30, 2024, with the State Intellectual Property Office of China, and entitled "Method for uplink transmission of video data and communication device", the whole content of which is incorporated herein by reference. TECHNICAL FIELD

[0002] The present application relates to the technical field of wireless communication, and in particular to AI processing technology for images or videos in wireless communication. BACKGROUND

[0003] In recent years, with the continuous development of the fifth generation (5G) communication system, the data transmission delay is continuously reduced, and the transmission capacity is increasingly large, and the 5G communication system gradually penetrates into some multimedia services with strong real-time performance and large data capacity requirements, such as video transmission, cloud gaming (CG) and extended reality (XR) and the like. XR includes virtual reality (VR) and augmented reality (AR), as well as mixed reality (MR).

[0004] With the development of XR technology, the demand of XR services for uplink transmission rate is also increasingly high. For example, AR services often need to transmit video data. According to industry evaluation, the uplink transmission rate required to meet the primary experience of AR is about 2 Mbps, and the uplink transmission rate required to meet the advanced experience is as high as 20 Mbps. The terminal located at the edge of the network is far away, and the large-scale fading is relatively large, and the transmission power of the terminal is limited, so the signal to interference and noise ratio (SINR) of the terminal located at the edge of the network is low, which causes the terminal to be unable to upload video data in time. SUMMARY

[0005] The present application provides a data transmission method and a communication device, which are beneficial to timely uploading of video data by the terminal.

[0006] In a first aspect, an embodiment of the present application provides a data transmission method, which comprises: a terminal sending first video data to an access network device through a first quality of service (QoS) flow, the access network device receiving the first video data, the resolution of the first video data being a first resolution; the time delay budget information corresponding to the first QoS flow being related to at least a calculation time delay budget, the calculation time delay budget being a processing time delay budget for converting low-resolution video data into high-resolution video data; the access network device converting the first video data into second video data, the resolution of the second video data being a second resolution, the second resolution being higher than the first resolution; and the access network device sending the second video data to a server.

[0007] It can be seen that, based on the method described in the first aspect, the terminal can upload low-resolution video data, and the access network device can convert the low-resolution video data into high-resolution video data and send the high-resolution video data to the server. By making the terminal upload low-resolution video data, the amount of data that needs to be transmitted over the air interface can be reduced as much as possible, so as to reduce the air interface transmission time delay of the video data. Therefore, based on the method described in the first aspect, the terminal can upload video data in time.

[0008] In a possible design, the access network device can further send indication information to the terminal, and the terminal can further receive the indication information, the indication information being used to instruct the terminal to upload video data of the first resolution. Based on this possible design, the access network device can flexibly instruct the terminal to upload video data of a resolution, which is conducive to improving the transmission performance of the video data.

[0009] In a possible design, the access network device sending the indication information to the terminal comprises: the access network device sending the indication information to the terminal based on one or more of the following information: channel state information, computing power information of the access network device, or time delay budget information corresponding to the first QoS flow. Based on this possible design, the access network device can more reasonably instruct the terminal to upload video data of a resolution, which is conducive to improving the transmission performance of the video data.

[0010] In a possible design, the access network device converting the first video data into the second video data comprises: the access network device converting the first video data into the second video data based on a neural network model.

[0011] The terminal can further send training video data to the access network device; correspondingly, the access network device can receive the training video data, the resolution of the training video data being the second resolution; and the access network device can train the neural network model based on the training video data.

[0012] Based on this possible design, the access network device can optimize the neural network model based on high-resolution video data, which is conducive to improving the performance of the neural network model.

[0013] In a possible design, the QoS of the first video data and the training video data is different. Based on the possible design, it is beneficial to meet the QoS requirement of video data for different uses.

[0014] In a possible design, the QoS of the first video data and the training video data is different.

[0015] In a possible design, the terminal can further send, to the access network device, training video data, the resolution of the training video data being the second resolution, the training video data being used for training of a neural network model, and the neural network model being used for conversion of the first video data to the second resolution video data.

[0016] In a possible design, the QoS of the first video data and the training video data is different.

[0017] In a possible design, the QoS of the first video data and the training video data is different.

[0018] In a possible design, the access network device can further send indication information to the terminal, where the indication information is used to indicate the terminal to upload the video data at the first resolution.

[0019] In a possible design, the access network device sends the indication information to the terminal based on one or more of the following information: channel state information, computing power information of the access network device, or time delay budget information corresponding to the first QoS flow.

[0020] In a possible design, the access network device converts the first video data into the second video data based on a neural network model.

[0021] The access network device can receive training video data from the terminal, where the training video data is at a second resolution; and the access network device trains the neural network model based on the training video data.

[0022] In a possible design, the first video data and the training video data have different QoS.

[0023] The advantages of the second and third aspects can be refer to the advantages of the first aspect, and are not described herein.

[0024] In the fourth aspect, an embodiment of the present application provides a data transmission method, which includes: a terminal sending first video data to an access network device through a first quality of service (QoS) flow, where the access network device receives the first video data, the first video data is at a first resolution, and a transmission time delay budget of the first video data and the first resolution have a first correspondence relationship; and the access network device sending the first video data to a server.

[0025] It can be seen that, based on the method described in the fourth aspect, the terminal can upload low-resolution video data, the access network device sends the low-resolution video data to the server, and the server converts the low-resolution video data into high-resolution video data. By making the terminal upload low-resolution video data, the amount of data that needs to be transmitted over the air interface can be reduced as much as possible, so as to reduce the air interface transmission time delay of the video data. Therefore, based on the method described in the fourth aspect, the terminal can upload video data in time.

[0026] In a possible design, the access network device can further receive configuration information from a core network element, where the configuration information is used to configure the first correspondence relationship. Based on this possible design, the correspondence relationship between the resolution and the transmission time delay budget can be configured more flexibly.

[0027] In a possible design, the configuration information is configuration information of the first QoS flow. Based on this possible design, it is beneficial to guarantee the end-to-end latency requirement of the first QoS flow.

[0028] In a possible design, the first correspondence relationship is determined based on a second correspondence relationship, the second correspondence relationship being a correspondence relationship between a first calculation latency and a first resolution, the first calculation latency being a processing latency of the server in converting the video data of the first resolution into video data of a second resolution, the second resolution being higher than the first resolution. Based on this possible design, the first correspondence relationship can be determined more accurately.

[0029] In a possible design, the access network device can further send indication information to the terminal; correspondingly, the terminal can further receive the indication information, the indication information being used to instruct the terminal to upload the video data of the first resolution. Based on this possible design, the access network device can flexibly instruct the terminal to upload the resolution of the video data, which is beneficial to improving the transmission performance of the video data.

[0030] In a possible design, the access network device sending the indication information to the terminal comprises: the access network device sending the indication information to the terminal based on one or more of the following information: channel state information or a transmission latency budget corresponding to the first QoS flow. Based on this possible design, the access network device can more reasonably instruct the terminal to upload the resolution of the video data, which is beneficial to improving the transmission performance of the video data.

[0031] In a possible design, the terminal can further send training video data to the access network device; correspondingly, the access network device can further receive the training video data, the resolution of the training video data being the second resolution.

[0032] The access network device can further send the training video data to the server, the second resolution being higher than the first resolution, the training video data being used for training of a neural network model, the neural network model being used for conversion of the first video data into video data of the second resolution.

[0033] Based on this possible design, the server can optimize the neural network model based on the video data of the high resolution, which is beneficial to improving the performance of the neural network model.

[0034] In a possible design, the QoS of the first video data and the training video data is different. Based on this possible design, it is beneficial to meet the QoS requirement of the video data of different uses.

[0035] In a fifth aspect, an embodiment of the present application provides a data transmission method, which can be applied to a network side, for example, an access network device of the network side, a module (for example, a circuit, a chip or a chip system, etc.) in the access network device, or a logic node, a logic module or software capable of realizing all or part of the function of the access network device. Taking the case where the method is applied to the access network device, in the method: the access network device receives first video data from a terminal through a first quality of service (QoS) flow, the first video data has a first resolution, and there is a first correspondence between a transmission delay budget of the first video data and the first resolution; and the access network device sends the first video data to a server.

[0036] In a possible design, the access network device can further receive configuration information from a core network element, where the configuration information is used to configure the first correspondence.

[0037] In a possible design, the configuration information is configuration information of the first QoS flow.

[0038] In a possible design, the first correspondence is determined based on a second correspondence, where the second correspondence is a correspondence between a first calculation delay and the first resolution, and the first calculation delay is a processing delay of the server in converting video data of the first resolution into video data of a second resolution, and the second resolution is higher than the first resolution.

[0039] In a possible design, the access network device can further send indication information to the terminal, where the indication information is used to instruct the terminal to upload video data of the first resolution.

[0040] In a possible design, the access network device sending the indication information to the terminal includes: the access network device sending the indication information to the terminal based on one or more of the following information: channel state information or a transmission delay budget corresponding to the first QoS flow.

[0041] In a possible design, the access network device can further receive training video data from the terminal, where the training video data has the second resolution.

[0042] The access network device can further send the training video data to the server, where the second resolution is higher than the first resolution, and the training video data is used for training of a neural network model, and the neural network model is used for conversion of the first video data into video data of the second resolution.

[0043] In a possible design, the first video data and the training video data have different QoSs.

[0044] The beneficial effects of the fifth aspect can be referred to the beneficial effects of the first aspect, and are not described herein.

[0045] In a sixth aspect, the present application provides a communication apparatus, which has the functions of the second aspect or the third aspect or the fifth aspect, e.g., the communication apparatus includes modules or units or means corresponding to the operations of the second aspect or the third aspect or the fifth aspect, which can be implemented by software or by hardware or by a combination of software and hardware.

[0046] In a seventh aspect, the present application provides a communication apparatus, which includes an interface circuit and one or more processors. The one or more processors are coupled to a memory. The memory is used to store part or all of the necessary computer programs or instructions for implementing the functions of the second aspect or the third aspect or the fifth aspect. The one or more processors can execute the computer programs or instructions, which, when executed, cause the communication apparatus to implement the method in any possible design or implementation manner of the second aspect or the third aspect or the fifth aspect. The interface circuit is used to implement the communication function within the communication apparatus and / or the communication function between the communication apparatus and other apparatuses or components.

[0047] In a possible design, the processor is configured to communicate with other apparatuses or components via the interface circuit.

[0048] In a possible design, the communication apparatus can further include the memory.

[0049] The communication apparatus can be a terminal, or a communication / processing module in a terminal, or a chip responsible for communication function (e.g., a modem chip, also referred to as a baseband chip) or an SoC or SIP chip containing a modem module in a terminal, or a circuit or chip responsible for processing function (e.g., a GPU) in a terminal. Alternatively, the communication apparatus can be an access network device, or a module (e.g., a circuit, a chip or a chip system, etc.) in an access network device, or a logic node, a logic module or software capable of implementing all or part of the functions of an access network device.

[0050] In an eighth aspect, the present application provides a communication system including a terminal and an access network device. The terminal and the access network device can perform the method described in the first aspect, or the terminal and the access network device can perform the method described in the fourth aspect.

[0051] In a ninth aspect, the present application provides a computer readable storage medium, which stores computer readable instructions. When a computer reads and executes the computer readable instructions, the computer performs the method in any possible design of the second aspect or the third aspect or the fifth aspect.

[0052] In a tenth aspect, the present application provides a computer program product, which, when executed by a computer, causes the computer to perform the method in any possible design of the second aspect or the third aspect or the fifth aspect. BRIEF DESCRIPTION OF DRAWINGS

[0053] FIG. 1 is a possible, non-limiting system diagram according to an embodiment of the present application;

[0054] FIG. 2a and FIG. 2b are possible application framework diagrams in a communication system according to an embodiment of the present application;

[0055] FIG. 3a-FIG. 3c are system architecture diagrams of several scenarios according to an embodiment of the present application;

[0056] FIG. 4a is a QoS flow diagram according to an embodiment of the present application;

[0057] FIG. 4b is a data packet transmission diagram according to an embodiment of the present application;

[0058] FIG. 5 and FIG. 7 are flow diagrams of data transmission methods according to an embodiment of the present application;

[0059] FIG. 6 and FIG. 8 are video data transmission diagrams according to an embodiment of the present application;

[0060] FIG. 9 is a possible exemplary block diagram of a communication device according to an embodiment of the present application;

[0061] FIG. 10 is a structure diagram of a terminal 1000 according to an embodiment of the present application. DETAILED DESCRIPTION

[0062] The present application will be further described below in conjunction with the accompanying drawings.

[0063] The terms “first” and “second” and the like in the specification, claims and drawings of the present application are used to distinguish different objects, and are not used to describe a particular order. In addition, the terms “include” and “have” and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units is not limited to the listed steps or units, but can optionally include other steps or units not listed, or can optionally include other steps or units inherent to the process, method, product or device.

[0064] Reference to "an embodiment" herein means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase "in an embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are they necessarily all referring to a common set of embodiments, although they can. Those skilled in the art will appreciate that the embodiments described herein can be combined with other embodiments in various ways.

[0065] In this application, "at least one", "multiple", "two or more", "at least two", "and / or" are used to describe the relationship between associated objects, which means that there can be three relationships, for example, "A and / or B" can mean: only A, only B, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects. "At least one" or similar expressions refer to any combination of these items, including any combination of single or multiple items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0066] In this application, "sending information" can be understood as one device sending information to another device, or also can be understood as one logical module in a device sending information to another logical module. For example, "the access network device sending information" can be understood as the access network device sending information to another device (such as a terminal), or can be understood as logical module 1 in the access network device sending information to logical module 2 in the access network device.

[0067] In this application, "receiving information" can be understood as one device receiving information from another device, or also can be understood as one logical module in a device receiving information from another logical module. For example, "the access network device receiving information" can be understood as the access network device receiving information from another device (such as a terminal), or can be understood as logical module 1 in the access network device receiving information from logical module 2 in the access network device.

[0068] In the present application, "sending information to (for example, a terminal)" or related illustrations in the drawings can be understood as that the destination of the information is the terminal. It can include direct or indirect sending information to the terminal. "Receiving information from (for example, a terminal)" or "receiving information from (for example, a terminal)" or "receiving information sent by (for example, a terminal)", or related illustrations in the drawings can be understood as that the source of the information is the terminal, and it can include direct or indirect receiving information from the terminal. The information can be processed between the source and the destination of the information sending, for example, format change, etc., but the destination can understand the effective information from the source. Similar expressions in the present application can be understood similarly, and will not be repeated here.

[0069] In order to better understand the embodiments of the present application, first, the system architecture related to the embodiments of the present application will be introduced as follows:

[0070] The embodiments of the present application can be applied to long term evolution (LTE) system, 5th generation mobile communication (5G) system, 6th generation mobile communication (6G) system and other communication systems evolved after 5G, satellite communication and short-range wireless communication system. Among them, the wireless communication system mentioned in the embodiments of the present application includes but is not limited to: three application scenarios of 5G / 6G mobile communication system: enhanced mobile broadband (eMBB), ultra reliable low latency communication (URLLC) and massive machine type of communication (mMTC), long range (LoRa) system or vehicle networking system. The wireless communication system can include one or more access network devices and one or more terminal devices.

[0071] FIG. 1 is a possible and non-limiting system schematic diagram provided by the embodiments of the present application. As shown in FIG. 1, the communication system 10 includes a radio access network (RAN) 100, a core network (CN) 200 and a data network (DN) 300.

[0072] I. The RAN 100 includes at least one RAN node (e.g., 110a and 110b in FIG. 1, collectively referred to as 110) and at least one terminal (e.g., 120a-120j in FIG. 1, collectively referred to as 120). Other RAN nodes, such as wireless relay devices and / or wireless backhaul devices (not shown in FIG. 1), etc., can also be included in the RAN 100. The terminals 120 are wirelessly connected to the RAN nodes 110. The RAN nodes 110 are connected to the core network 200 through wireless or wired means. The core network devices in the core network 200 and the RAN nodes 110 in the RAN 100 can be different physical devices, respectively, or can be the same physical device integrated with the logical functions of the core network and the logical functions of the wireless access network.

[0073] The RAN 100 can be a 3rd generation partnership project (3GPP) related cellular system, such as a 4G, 5G mobile communication system, or a future-oriented evolved system (e.g., a 6G mobile communication system). The RAN 100 can also be an open radio access network (O-RAN or ORAN), a cloud radio access network (CRAN), or a wireless fidelity (WiFi) system. The RAN 100 can also be a communication system that combines two or more of the above systems. The RAN can also be referred to as an access network (AN).

[0074] 1. RAN node 110

[0075] The RAN node 110, which can also be referred to as an access network device, a RAN entity, or an access node or access point or network device, etc., forms part of the communication system and helps terminals to access the wireless access. The RAN nodes 110 in the communication system 10 can be of the same type or of different types. In some scenarios, the roles of the RAN node 110 and the terminal 120 are relative, e.g., the network element 120i in FIG. 1 can be a helicopter or a drone, which can be configured as a mobile base station. For a terminal 120j that accesses the RAN 100 through the network element 120i, the network element 120i is a base station; but for the base station 110a, the network element 120i is a terminal. The RAN nodes 110 and the terminals 120 are sometimes referred to as communication apparatuses, e.g., the network elements 110a and 110b in FIG. 1 can be understood as communication apparatuses with base station functions, and the network elements 120a-120j can be understood as communication apparatuses with terminal functions.

[0076] In one possible scenario, the RAN node 110 can be a base station, an evolved Node B (eNodeB), an access point (AP), a transmission reception point (TRP), a next generation NodeB (gNB), a next generation base station in a 6th generation (6G) mobile communication system, a base station in a future mobile communication system, or an access node in a WiFi system, etc. The RAN node 110 can be a macro base station (e.g., 110a in Figure 1), a micro base station or an indoor station (e.g., 110b in Figure 1), a relay node or a donor node, or a wireless controller in a CRAN scenario. In one possible embodiment, the RAN node 110 can also be a server, a wearable device, a vehicle or a vehicle-mounted device, etc. For example, an access network device in a vehicle to everything (V2X) technology can be a road side unit (RSU). All or part of the functions of the RAN node 110 in this application can also be implemented by software functions running on hardware, or by virtualized functions instantiated on a platform such as a cloud platform. The RAN node 110 in this application can also be a logical node, a logical module or software that can implement all or part of the functions of the RAN node 110.

[0077] In another possible scenario, a terminal is assisted by multiple RAN nodes 110 cooperating to implement wireless access, and different RAN nodes 110 respectively implement part of the functions of a base station. For example, the RAN node 110 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), etc. The CU and the DU can be separately arranged, or can be included in the same network element, such as a baseband unit (BBU). The RU can be included in a radio frequency device or a radio frequency unit, such as a remote radio unit (RRU), an active antenna processing unit (AAU), or a remote radio head (RRH).

[0078] In different systems, the CU (or CU-CP and CU-UP), DU or RU can also have different names, but those skilled in the art can understand their meanings. For example, in the ORAN system, the CU can also be referred to as O-CU (open CU), the DU can also be referred to as O-DU, the CU-CP can also be referred to as O-CU-CP, the CU-UP can also be referred to as O-CU-UP, and the RU can also be referred to as O-RU. For the convenience of description, the CU, CU-CP, CU-UP, DU and RU are taken as examples for description in this application. Any one of the CU (or CU-CP, CU-UP), DU and RU in this application can be implemented by a software module, a hardware module, or a combination of a software module and a hardware module.

[0079] In the embodiments of the present application, the form of the RAN node 110 is not limited, and the device for implementing the function of the RAN node 110 can be the RAN node 110; or can be a device capable of supporting the RAN node 110 to implement the function, such as a chip system. The device can be installed in the RAN node 110 or used in combination with the RAN node 110.

[0080] For the convenience of description, the RAN node 110 will be described as an access network device hereinafter.

[0081] 2. Terminal

[0082] The terminal can be a device or module with corresponding communication functions for accessing the above-mentioned communication system. The terminal can also be referred to as a terminal device, a user equipment (UE), a mobile station, a mobile terminal, etc. The terminal can be widely used in various scenarios, such as device-to-device (D2D) communication, vehicle to everything (V2X) communication, machine-type communication (MTC), internet of things (IOT), virtual reality, augmented reality, industrial control, autonomous driving, remote medical treatment, smart power grid, smart furniture, smart office, smart wear, smart transportation, smart city, etc. The terminal can be a mobile phone, a tablet computer, a computer with wireless transceiver function, a wearable device, a vehicle, a drone, a helicopter, an airplane, a ship, a robot, a mechanical arm, a smart home device, a transport vehicle with wireless communication function, a communication module, a head-mounted XR glasses, a video player, a holographic projector, etc. The embodiments of the present application do not limit the device form of the terminal. The terminal is usually provided with a communication module, circuit or chip for executing corresponding communication functions, and is also configured with program instructions for executing corresponding communication functions.

[0083] II. Core network 200

[0084] The core network 200 has three major functions of registration, connection and session management. The core network 200 mainly includes a network exposure function (NEF) network element, a policy control function (PCF) network element, an application function (AF) network element, an access and mobility management function (AMF) network element, a session management function (SMF) network element, a user plane function (UPF) network element and the like.

[0085] The NEF network element is used to expose the services and capabilities of the 3GPP network function to the AF network element, and also allows the AF network element to provide information to the 3GPP network function.

[0086] The PCF network element is used for policy management of charging policy and QoS policy.

[0087] The AF network element is mainly used to deliver the requirements of the application side to the network side.

[0088] The AMF network element is mainly used for mobility management, access authentication / authorization and the like. In addition, it is also responsible for transferring user policies between the UE and the PCF.

[0089] The SMF network element is used to complete the session management functions such as UE IP address allocation, UPF selection, charging and QoS policy control.

[0090] The UPF network element is used as an interface with the data network to complete the functions of user plane data forwarding, session / stream level-based charging statistics, bandwidth limitation and the like.

[0091] III. Data network 300

[0092] The data network 300 can provide fixed network, Internet, operator services or third-party services and the like.

[0093] To support artificial intelligence (AI) technology in a wireless network, AI nodes can also be introduced in the network. An AI node can be deployed in one or more of the following locations in the communication system: an access network device, a terminal, or a core network element, etc. Alternatively, an AI node can also be deployed separately, e.g., in a location other than any of the above-mentioned devices, such as in a host or a cloud server of an over the top (OTT) system. An AI node can communicate with other devices in the communication system, which can be one or more of the following: an access network device, a terminal, or a core network element, etc.

[0094] It can be understood that the present application does not limit the number of AI nodes. For example, when there are multiple AI nodes, the multiple AI nodes can be divided based on functions, e.g., different AI nodes are responsible for different functions.

[0095] It can also be understood that an AI node can be a separate device, or can be integrated into the same device to implement different functions, or can be a network element in a hardware device, or can be a software function running on a dedicated hardware, or a virtualized function instantiated on a platform (e.g., a cloud platform), and the present application does not limit the specific form of the AI node. An AI node can be an AI element or an AI module.

[0096] FIG. 2a is a schematic diagram of a possible application framework in a communication system according to an embodiment of the present application. As shown in FIG. 2a, the network elements in the communication system are connected through interfaces (e.g., NG, Xn), or air interfaces. One or more AI modules (only one is shown in FIG. 2a for clarity) are provided in one or more of the following network element nodes: a core network element, an access network device, a terminal, or one or more devices in operations administration and maintenance (OAM). The access network device can be a separate RAN node, or can include multiple RAN nodes, e.g., including a CU and a DU. The CU and / or the DU can also be provided with one or more AI modules. The CU can also be split into a CU-CP and a CU-UP, and the CU-CP and / or the CU-UP can be provided with one or more AI modules.

[0097] The AI module is configured to implement a corresponding AI function. AI modules deployed in different network elements can be the same or different. The model of the AI module can implement different functions according to different parameter configurations. The model of the AI module can be configured based on one or more of the following parameters: a structure parameter (for example, at least one of a number of neural network layers, a width of a neural network, a connection relationship between layers, a weight of a neuron, an activation function of a neuron, or a bias in the activation function), an input parameter (for example, a type of input parameter and / or a dimension of the input parameter), or an output parameter (for example, a type of output parameter and / or a dimension of the output parameter). The bias in the activation function can also be referred to as a bias of the neural network.

[0098] In one example, the neural network described above can be a deep neural network (DNN), a convolutional neuron network (CNN), a recurrent neural network (RNN), or a generative adversarial network (GAN).

[0099] A DNN is an artificial neural network architecture that has multiple layers of nonlinear transformation units stacked together in a hierarchical structure, forming a deep computational model. Compared with a shallow neural network, a deep neural network has more hidden layers, allowing the network model to capture more complex internal structures of data and high-level abstract features.

[0100] A CNN is a deep neural network with a convolutional structure. The CNN includes a feature extractor composed of convolutional layers and subsampling layers. The feature extractor can be regarded as a filter, and the convolution process can be regarded as using a trainable filter to convolve an input image or a convolution feature plane.

[0101] An RNN is a type of recursive neural network that takes sequence data as input, performs recursion in the evolution direction of the sequence, and connects all nodes (recurrent units) in a chain.

[0102] A GAN is a deep learning model. It is composed of a generator and a discriminator, and is trained through adversarial learning. The purpose is to estimate the latent distribution of data samples and generate new data samples.

[0103] An AI module can have one or more models. A model can infer an output including one or more parameters. The learning process, training process, or inference process of different models can be deployed in different nodes or devices, or can be deployed in the same node or device.

[0104] FIG. 2b is a schematic diagram of a possible application framework in a communication system according to an embodiment of the present application. As shown in FIG. 2b, the communication system includes a RAN intelligent controller (RIC). The RIC can be an AI module shown in FIG. 2a, for example, to implement AI-related functions. The RIC includes a near-real time RIC (near-RT RIC) and a non-real time RIC (Non-RT RIC). The non-real time RIC mainly processes non-real time information, such as data that is not sensitive to latency, which can be in the order of seconds. The real time RIC mainly processes near-real time information, such as data that is relatively sensitive to latency, which can be in the order of tens of milliseconds.

[0105] The near-real time RIC is used for model training and inference. For example, for training an AI model, and using the AI model for inference. The near-real time RIC can obtain network side and / or terminal side information from RAN nodes (such as CUs, CU-CPs, CU-UPs, DUs, and / or RUs) and / or terminals. The information can be used as training data or inference data. The inference result can be submitted to the RAN nodes and / or terminals. The inference result can be exchanged between CUs and DUs, and / or between DUs and RUs. For example, the near-real time RIC submits the inference result to the DU, which is sent to the RU by the DU.

[0106] The non-real time RIC is also used for model training and inference. For example, for training an AI model, and using the model for inference. The non-real time RIC can obtain network side and / or terminal side information from RAN nodes (such as CUs, CU-CPs, CU-UPs, DUs, and / or RUs) and / or terminals. The information can be used as training data or inference data, and the inference result can be submitted to the RAN nodes and / or terminals. The inference result can be exchanged between CUs and DUs, and / or between DUs and RUs. For example, the non-real time RIC submits the inference result to the DU, which is sent to the RU by the DU.

[0107] The near-real-time RIC and the non-real-time RIC can also be separately set as a network element. The near-real-time RIC and the non-real-time RIC can also be part of other devices, for example, the near-real-time RIC is set in the RAN node (for example, in the CU, DU), and the non-real-time RIC is set in the OAM, the cloud server, the core network element, or other network devices.

[0108] The following introduces several application scenarios to which the embodiments of the present application can be applied.

[0109] Scenario 1: Server-network-terminal architecture scenario

[0110] Please refer to FIG. 3a, which is a schematic diagram of the system architecture of scenario 1 provided by the embodiments of the present application. As shown in FIG. 3a, the server is responsible for the encoding and decoding of the video source, rendering, etc. The video data, such as the video data of the XR service, is transmitted between the server and the terminal through the network. The network includes the DN, the core network, and the RAN.

[0111] Scenario 2: Terminal-network-terminal architecture scenario

[0112] Please refer to FIG. 3b, which is a schematic diagram of the system architecture of scenario 2 provided by the embodiments of the present application. Scenario 2 can be applied to the tactile internet. Compared with the traditional internet for transmitting audio and video information, the tactile internet envisages transmitting not only audio and video information but also touch and driving information. It mainly includes a master domain, a network, and a controlled domain. One terminal in FIG. 3b can be a device in the master domain, and the other terminal can be a device in the controlled domain. The master domain is generally composed of a human operator (tactile user) and a human system interface (HSI), which is responsible for converting human input into tactile data using appropriate tactile coding technology. The tactile data generated by the HSI is transmitted to the controlled domain through the network. The network includes the core network and the RAN. The controlled domain includes a remotely controlled robot or a remote operator, which is directly controlled by the master domain through various command signals. Then, the controlled domain feeds back the feedback signals to the master domain. In addition to the tactile feedback signals, the master domain can also receive audio / video feedback signals from the controlled domain. The master domain and the controlled domain are connected through the bidirectional communication link on the network domain with the help of various command and feedback signals, thereby forming a global control loop.

[0113] Scenario 3: WiFi scenario

[0114] Please refer to FIG. 3c, which is a schematic diagram of the system architecture of scenario 3 provided by the embodiments of the present application. As shown in FIG. 3c, the server is responsible for the encoding and decoding of the video source, rendering, etc. The video data, such as the video data of the XR service, is transmitted between the server and the terminal through the fixed network, the WiFi router / AP / set-top box.

[0115] The following explanations of some terms used in the embodiments of this application are provided to facilitate understanding by those skilled in the art. These explanations are for illustrative purposes only and should not be construed as a disclosure or specific limitation of the technical solution of this application.

[0116] 1. XR

[0117] XR refers to the use of computers to combine the real and virtual worlds, creating a virtual environment that allows for human-computer interaction. XR includes VR and AR, and typically XR services require low packet loss and low latency transmission.

[0118] 2. Quality of Service Flow (QoS Flow)

[0119] Within a Protocol Data Unit (PDU) session, a QoS flow is the smallest unit distinguishing QoS levels. In 5G systems, QoS flows are identified using QoS flow identifiers (QFIs), and each QFI must be unique within a PDU session. For example, as shown in Figure 4a, a PDU session can have multiple (e.g., up to 64) QoS flows. However, each QoS flow has a different QFI. Within a PDU session, user plane service flows with the same QFI use the same service forwarding processing method (e.g., scheduling). At the configuration granularity, a PDU session can correspond to multiple radio bearers (RBs), and services on the same radio bearer can use different service levels; that is, a radio bearer can contain multiple QoS flows.

[0120] In a 5G system (5GS), QoS flows are controlled by the core network's session management function (SMF) module, which can be pre-configured or established and modified through PDU sessions. QoS configuration is at the QoS flow level. A QoS flow is characterized by three parts:

[0121] 1) QoS configuration (QoS profile) on the access network device side: These configurations are provided to the access network device by the SMF network element through the N2 interface, or are pre-configured in the access network device.

[0122] 2) QoS rules on the terminal side: These rules can be provided to the terminal by the SMF network element through N1, or derived by the terminal through the reflection QoS mechanism.

[0123] 3) Uplink and downlink packet detection rules (PDRs) at the UPF network element side: These PDRs are provided by the SMF network element to the UPF network element through the N4 interface.

[0124] QoS configuration is used for the access network device to perform QoS control. QoS rules are used to indicate the mapping between uplink data and QoS flows. PDRs are used to indicate the mapping between downlink data and QoS flows. For example, as shown in FIG. 4b, for uplink data, the terminal matches the data packet according to the QoS rules, and the data packet is transmitted upwards on the QoS flow on which the data packet is matched and the access network channel corresponding to the QoS flow; for downlink data, the UPF network element matches the data packet according to the PDRs, and the data packet is transmitted downwards on the QoS flow on which the data packet is matched and the access network channel corresponding to the QoS flow. If a data packet does not match any QoS rule (uplink) or PDR (downlink), the data packet will be discarded by the terminal or the UPF network element.

[0125] 3. QoS configuration

[0126] The feature information about a certain QoS flow sent by the core network element to the access network device is called QoS configuration. For example, the QoS configuration includes 5G quality identity (5G qulitydentity, 5QI), allocation and retention priority (ARP), etc.

[0127] 4. 5QI

[0128] 5QI is a scalar, and 5QI is used to index a 5G QoS characteristic, which represents the radio characteristics of the QoS flow. Each QoS flow has a 5QI. For example, the 5G QoS characteristics indexed by the existing 5QI can include resource type, priority, packet delay budget (PDB), etc. PDB represents the upper limit of the time that a data packet can be delayed between the terminal and the UPF network element. GBR QoS flow: under the premise of meeting GFBR, the maximum delay of the transmission delay between the terminal and the UPF that 98% of the data packets should not exceed; under the premise of meeting GFBR, the data packet whose transmission delay between the terminal and the UPF exceeds the PDB is considered to have been lost.

[0129] 5. Super resolution

[0130] Super-resolution technology refers to a method of improving the resolution of an image (or video frame) through hardware or software, and a process of obtaining a high-resolution image from a low-resolution image. In recent years, deep learning-based methods have made significant progress in super-resolution technology. Deep learning-based methods use techniques such as deep convolutional neural networks (CNNs) to learn the features and mapping relationships of a large amount of training data, enabling mapping from low-resolution images to high-resolution images. After training on a large video dataset, a super-resolution neural network can learn more complex image features and generate more realistic high-resolution images. Super-resolution technology can also convert low-resolution images to high-resolution images based on other methods, for example, low-resolution images can be converted to high-resolution images through interpolation algorithms. Interpolation algorithms are a method based on pixel interpolation, and commonly used interpolation algorithms include nearest neighbor interpolation, bilinear interpolation, and bicubic interpolation. These algorithms estimate the values of pixels in high-resolution images by interpolating the pixels in low-resolution images.

[0131] To facilitate terminals located at the edge of the network to meet the uplink transmission delay requirement of XR services, an embodiment of the present application provides a data transmission method and a communication device.

[0132] The data transmission method and the communication device will be further described below with reference to the accompanying drawings. It can be understood that the terminal, the access network device and the server are taken as an example to illustrate the execution subject of the interaction in the present application, but the present application does not limit the execution subject of the interaction. For example, the method performed by the terminal in the present application can also be implemented by a communication / processing module or a circuit or chip (such as a modem chip (also known as a baseband chip), or a SoC chip containing a modem core, or a SIP chip, or a GPU) responsible for communication / processing functions in the terminal. The method performed by the access network device in the present application can also be implemented by a module (such as a circuit, a chip or a chip system, etc.) in the access network device, or a logic node, a logic module or software capable of implementing all or part of the function of the access network device; the method performed by the server in the present application can also be implemented by a module (such as a circuit, a chip or a chip system, etc.) in the server, or a logic node, a logic module or software capable of implementing all or part of the function of the server.

[0133] Please refer to FIG. 5, which is a flowchart of a data transmission method provided by an embodiment of the present application, wherein:

[0134] 501、The terminal sends first video data to the access network device through a first QoS flow. Correspondingly, the access network device can receive the first video data. The resolution of the first video data is a first resolution. The time delay budget information corresponding to the first QoS flow is at least related to a calculation time delay budget, which is a processing time delay budget for converting low-resolution video data into high-resolution video data.

[0135] In the embodiments of the present application, the video data can be a video frame. Alternatively, one video frame can be divided into multiple image blocks, and the video data can be an image block. Optionally, the video data can be video data of XR service, or the video data can also be video data of other services, which is not limited in the embodiments of the present application. In the embodiments of the present application, the video can also be replaced by an image, that is, the solutions provided in the embodiments of the present application can be used not only for transmission and processing of video data, but also for transmission and processing of images.

[0136] In the embodiments of the present application, the time delay budget information corresponding to the first QoS flow can also be understood as the time delay budget information of the video data transmitted on the first QoS flow. The QoS configuration corresponding to the first QoS flow includes the 5QI of the first QoS flow. Optionally, the time delay budget information corresponding to the first QoS flow can be the time delay budget information included in the 5G QoS characteristics indexed by the 5QI of the first QoS flow.

[0137] In a possible embodiment, the processing time delay budget for converting low-resolution video data into high-resolution video data can be understood as follows: the calculation time delay budget is an upper limit of the processing time delay for converting low-resolution video data into high-resolution video data, that is, the actual processing time delay for converting low-resolution video data into high-resolution video data can be less than the processing time delay budget; or the calculation time delay budget is an upper limit of the average processing time delay for converting low-resolution video data into high-resolution video data, that is, the average processing time delay for converting low-resolution video data into high-resolution video data can be less than the processing time delay budget.

[0138] In the embodiments of the present application, the time delay budget information corresponding to the first QoS flow being at least related to the calculation time delay budget has the following two possible embodiments:

[0139] 1) The time delay budget information corresponding to the first QoS flow includes the calculation time delay budget and the transmission time delay budget.

[0140] That is, two latency budgets can be configured for the first QoS flow, one is the computation latency budget, and the other is the transmission latency budget. The transmission latency budget can be a transmission latency budget of the video data between the terminal and the UPF network element. For example, the transmission latency budget can be an upper limit of the transmission latency of the video data between the terminal and the UPF network element, or the transmission latency budget can be an upper limit of the average transmission latency of the video data between the terminal and the UPF network element. Optionally, the transmission latency budget can be referred to as PDB, or TDB (total delay budget), or other names, and the embodiments of the present application are not limited.

[0141] For example, as shown in Table 1 below, the 5G QoS characteristics indexed by the 5QI of the first QoS flow can include the transmission latency budget and the computation latency budget. The 5G QoS characteristics indexed by the 5QI of the first QoS flow can also include other contents, such as resource type, priority, etc., and the embodiments of the present application are not limited.

[0142] Table 1

[0143] 2) The latency budget information corresponding to the first QoS flow is the sum of the computation latency budget and the transmission latency budget.

[0144] That is, one total latency budget can be configured for the first QoS flow, and the total latency budget is the sum of the computation latency budget and the transmission latency budget, that is, the time limit of the sum of the computation latency and the transmission latency of the video data. For the transmission latency budget, refer to the description in the foregoing, which is not repeated here.

[0145] In a possible embodiment, the access network device can receive configuration information sent by a core network element (such as an SMF network element), and the configuration information is used to configure the latency budget information corresponding to the first QoS flow. For example, the configuration information can be the QoS configuration of the first QoS flow.

[0146] For example, taking the case that the latency budget information corresponding to the first QoS flow includes the computation latency budget and the transmission latency budget as an example. The server can notify the first core network element (such as the AF network element) of the computation latency budget and the transmission latency budget. The first core network element can notify the second core network element (such as the SMF network element) of the computation latency budget and the transmission latency budget, and the second core network element configures the computation latency budget and the transmission latency budget to the access network device. Alternatively, the second core network element can also determine the computation latency budget and the transmission latency budget in other ways, and then configure the computation latency budget and the transmission latency budget to the access network device, and the embodiments of the present application are not limited.

[0147] For example, the delay budget information corresponding to the first QoS flow is the sum of the computation delay budget and the transmission delay budget. The server can notify the sum of the computation delay budget and the transmission delay budget to the first core network element (e.g., the AF network element). The first core network element can notify the sum of the computation delay budget and the transmission delay budget to the second core network element (e.g., the SMF network element), and the second core network element configures the sum of the computation delay budget and the transmission delay budget to the access network device. Alternatively, the second core network element can determine the sum of the computation delay budget and the transmission delay budget in other manners, and then configures the sum of the computation delay budget and the transmission delay budget to the access network device, which is not limited in the embodiments of the present application.

[0148] In another possible embodiment, the delay budget information corresponding to the first QoS flow can be predefined by a protocol, that is, the QoS configuration of the first QoS flow can be predefined by the protocol.

[0149] In a possible embodiment, before the terminal sends the first video data to the access network device through the first QoS flow, the terminal can obtain video data of a second resolution, and the second resolution is higher than the first resolution; and the terminal sends the first video data to the access network device through the first QoS flow based on the video data of the second resolution. For example, the terminal can convert the video data of the second resolution into the first video data, and then sends the first video data to the access network device through the first QoS flow. Optionally, the specific implementation manner of converting the video data of the second resolution into the first video data can be that the terminal can perform downsampling processing on the video data of the second resolution to obtain the first video data. That is, after collecting the video data of a high resolution, the terminal can convert the video data of the high resolution into video data of a low resolution, and then sends the video data of the low resolution to the access network device through the first QoS flow, so that the access network device converts the video data of the low resolution into the video data of the high resolution and then sends the video data of the high resolution to the server.

[0150] In a possible embodiment, the access network device can further send indication information to the terminal, and the indication information is used to indicate the terminal to upload the video data of the first resolution. Correspondingly, the terminal can receive the indication information. After receiving the indication information, the terminal sends the first video data to the access network device through the first QoS flow based on the indication information. That is, the access network device can select a resolution, and then notifies the terminal of the selected resolution, so that the terminal can upload the video data of the resolution in the future. Based on the possible embodiment, the access network device can flexibly indicate the terminal to upload the resolution of the video data, which is beneficial to improve the transmission performance of the video data.

[0151] In a possible embodiment, the access network device can send the indication information to the terminal based on one or more of the following information: channel state information, computing power information of the access network device, or time delay budget information corresponding to the first QoS flow. Based on this possible embodiment, the access network device can more reasonably instruct the terminal to upload the resolution of the video data, and the transmission performance of the video data can be improved.

[0152] The channel state information can be channel state information between the terminal and the access network device. For example, the channel state information can include, but is not limited to, one or more of the following: information for indicating channel quality, SINR, size of reference signal received power, or subcarrier spacing, and the like.

[0153] The computing power information of the access network device is used to indicate the computing capability of the access network device, for example, the unit of computing power can be TFLOPS (floating point operations per second), IPS (instructions per second), or TPS (transactions per second), and the like. In the case where the computing capability of the access network device is certain, the computing time delay of the access network device for converting different low-resolution video data into a certain high-resolution video data is different. For example, as shown in Table 2 below. When the computing power of the access network device is 60 TFLOPS, the access network device needs 4.7 ms to convert 270P video data into 1080P video data. The access network device needs 4 ms to convert 360P video data into 1080P video data. The access network device needs 1.5 ms to convert 720P video data into 1080P video data.

[0154] Table 2

[0155] For example, based on the channel state information, the access network device instructs the terminal to indicate the resolution. When the channel state is poor, the access network device can instruct the terminal to indicate a lower resolution, which can reduce the amount of data to be transmitted over the air as much as possible to reduce the air interface transmission time delay of the video data; when the channel state is good, the access network device can instruct the terminal to indicate a higher resolution, which can save the overhead of computing resources.

[0156] For another example, based on the computing power information of the access network device, the access network device instructs the terminal to indicate the resolution. When the computing power resources of the access network device are sufficient, the access network device can instruct the terminal to indicate a lower resolution, which can reduce the amount of data to be transmitted over the air as much as possible to reduce the air interface transmission time delay of the video data; when the computing power resources of the access network device are insufficient, the access network device can instruct the terminal to indicate a higher resolution, which can save the overhead of computing resources.

[0157] For example, the resolution can be indicated to the terminal based on channel state information and computing power information of the access network device. When the channel state is poor and the computing power resource of the access network device is sufficient, the access network device can indicate a lower resolution to the terminal, so as to reduce the amount of data to be transmitted over the air interface as much as possible, thereby reducing the air interface transmission delay of the video data; when the channel state is good or the computing power resource of the access network device is insufficient, the access network device can indicate a higher resolution to the terminal, so as to save the overhead of computing resources.

[0158] For example, the resolution can be indicated to the terminal based on channel state information, computing power information of the access network device, and delay budget information corresponding to the first QoS flow. Assuming that the computing delay budget corresponding to the first QoS flow is 4 ms. The access network device determines that it needs 4.7 ms to convert 270P video data into 1080P video data, 4 ms to convert 360P video data into 1080P video data, and 1.5 ms to convert 720P video data into 1080P video data based on the computing power level. Therefore, the access network device can select one resolution from 360P and 720P to meet the computing delay budget. The access network device can further select one resolution from 360P and 720P in combination with the channel state information. For example, if the channel state is poor, the access network device can select 360P and notify the terminal. If the channel state is good, the access network device can select 720P and notify the terminal.

[0159] In another possible embodiment, the first resolution can also be a preset value smaller than the second resolution.

[0160] Optionally, V1 is less than V2. V1 is equal to the size of the video data of the first resolution divided by the transmission delay budget, that is, V1 can be understood as the equivalent transmission rate when the resolution is the first resolution. V2 is equal to the size of the video data of the second resolution divided by the sum of the transmission delay budget and the computing delay budget, that is, V2 can be understood as the equivalent transmission rate when the resolution is the second resolution. By making V1 less than V2, the demand for uplink transmission rate is reduced, which is beneficial to terminals with low uplink transmission rate to meet the demand for uplink transmission rate.

[0161] 502. The access network device converts the first video data into second video data, the resolution of the second video data being a second resolution, the second resolution being higher than the first resolution.

[0162] In the embodiments of the present application, the access network device can use super-resolution technology to convert the first video data into the second video data, that is, the access network device can convert low-resolution video data into high-resolution video data. For the introduction of super-resolution technology, please refer to the description under the 5th point in the term introduction in the foregoing, which will not be described here.

[0163] 503、The access network device sends the second video data to the server. Accordingly, the server can receive the second video data.

[0164] In the embodiments of the present application, after the access network device converts the first video data into the second video data, the access network device sends the second video data to the server. Optionally, before the access network device sends the second video data to the server, the access network device can also compress or encode the second video data, and then send the compressed or encoded second video data to the server.

[0165] In a possible embodiment, the specific implementation of the access network device converting the first video data into the second video data is that the access network device converts the first video data into the second video data based on the neural network model.

[0166] In a possible embodiment, the terminal can also send training video data to the access network device. Accordingly, the access network device can receive the training video data, and the resolution of the training video data is the second resolution; the access network device trains the neural network model based on the training video data. The training video data can be an image block or a video frame, and the embodiments of the present application are not limited thereto.

[0167] For example, the access network device can take the video data with the first resolution as the input of the neural network model, take the training video data as the target output of the neural network, take the two as the training set of the neural network, take the peak signal to noise ratio (PSNR) as the loss function, and perform neural network training.

[0168] That is, the terminal can not only send the low-resolution video data to the access network device, but also send the high-resolution video data to the access network device, so that the access network device can optimize the neural network model based on the high-resolution video data, which is conducive to improving the performance of the neural network model.

[0169] In a possible embodiment, the QoS of the first video data and the training video data is different. That is, the first video data and the training video data are sent to the access network device through different QoS flows, that is, the first video data and the training video data are carried by different QoS flows. The first video data needs to follow the constraints of the computation latency budget and the transmission latency budget, while the training video data only needs to follow the transmission latency budget specified by the traditional method. Based on this possible embodiment, it is conducive to meeting the QoS requirements of video data with different purposes.

[0170] For example, as shown in FIG. 6, the terminal sends low-resolution video data 1 to the access network device through a QoS flow 1. After receiving the video data 1, the access network device inputs the video data 1 into the neural network model, and outputs high-resolution video data 2 from the neural network model. The access network device sends the video data 2 to the server. The terminal also sends high-resolution image blocks (i.e., high-definition image blocks) to the access network device through a QoS flow 2. After receiving the high-resolution image blocks, the access network device trains the neural network model based on the high-resolution image blocks to optimize the parameters of the neural network model, so that the neural network model can better restore high-resolution video data.

[0171] It can be seen that, based on the method described in FIG. 5, the terminal can upload low-resolution video data, and the access network device converts the low-resolution video data into high-resolution video data and sends the high-resolution video data to the server. By making the terminal upload low-resolution video data, the amount of data that needs to be transmitted over the air interface can be reduced as much as possible to reduce the air interface transmission delay of the video data. Therefore, based on the method described in FIG. 5, the terminal can upload video data in time.

[0172] Please refer to FIG. 7, which is a flowchart of another data transmission method provided by an embodiment of the present application. In the method, the steps are as follows:

[0173] 701. The terminal sends first video data to the access network device through a first QoS flow. Correspondingly, the access network device can receive the first video data. The resolution of the first video data is a first resolution, and there is a first correspondence between the transmission delay budget of the first video data and the first resolution.

[0174] In the embodiment of the present application, the video data can be a video frame. Alternatively, a video frame can be divided into multiple image blocks, and the video data can be an image block. Optionally, the video data can be video data of an XR service, or the video data can be video data of other services, which are not limited in the embodiment of the present application. In the embodiment of the present application, the video can be replaced by image, that is, the scheme provided by the embodiment of the present application can be used not only for transmitting and processing video data, but also for transmitting and processing images.

[0175] In the embodiment of the present application, the transmission delay budget of the first video data can be the transmission delay budget of the first video data between the terminal and the UPF network element. For example, the transmission delay budget of the first video data can be the upper limit of the transmission delay of the first video data between the terminal and the UPF network element.

[0176] In an embodiment of the present application, the first video data has a first corresponding relationship between a transmission delay budget and a first resolution. Since the terminal no longer directly uploads high-resolution video data, but uploads low-resolution video data, the access network device sends the low-resolution video data to the server, and the server converts the low-resolution video data into high-resolution video data. Therefore, there is a calculation delay on the server side for converting low-resolution video data into high-resolution video data. In the case of a certain calculation capability of the server, the calculation delay of the server for converting different low-resolution video data into high-resolution video data is different. For example, as shown in Table 5 above. When the server's computing power is 60TFLOPS, the server needs 4.7ms to convert 270P video data into 1080P video data. The server needs 4ms to convert 360P video data into 1080P video data. The server needs 1.5ms to convert 720P video data into 1080P video data. Since the total delay of the server obtaining high-resolution video data is fixed, the higher the resolution of the video data, the smaller the calculation delay of the server, and the more sufficient the transmission delay budget left for the video data; on the contrary, the lower the resolution of the video data, the greater the calculation delay of the server, and the less the transmission delay budget left for the video data. For example, assuming that the terminal directly uploads video data with a resolution of 1080P, the transmission delay budget is 10ms; if the terminal uploads video data with a resolution of 270P, since the server has a calculation delay of 4.7ms for converting 270P video data into 1080P video data, the actual transmission delay budget for 270P video data is 10ms-4.7ms=5.3ms. Therefore, the transmission delay budget of the video data is related to the resolution of the video data, and different resolutions of the video data can correspond to different transmission delay budgets.

[0177] In a possible embodiment, the access network device can also receive configuration information from a core network element (such as an SMF network element), and the configuration information is used to configure the first corresponding relationship. Based on this possible embodiment, the corresponding relationship between the resolution and the transmission delay budget can be more flexibly configured.

[0178] Optionally, the configuration information is configuration information of the first QoS flow, which is beneficial to guarantee the end-to-end delay requirement of the first QoS flow. That is, the first QoS flow has the first corresponding relationship, and the first corresponding relationship is a corresponding relationship for the first QoS flow. The transmission delay budget of the first video data can be understood as the transmission delay budget corresponding to the first QoS flow.

[0179] The QoS configuration corresponding to the first QoS flow comprises a 5QI of the first QoS flow. Optionally, the 5G QoS characteristics indexed by the 5QI of the first QoS flow comprise a correspondence between a transmission delay budget and a resolution of the first QoS flow. Optionally, the transmission delay budget can be referred to as PDB or TDB or other names, which are not limited in the embodiments of the present application.

[0180] For example, the 5G QoS characteristics indexed by the 5QI of the first QoS flow can be as shown in Table 3. If the resolution of the video data is resolution 1, the transmission delay budget of the video data is T1; if the resolution of the video data is resolution 2, the transmission delay budget of the video data is T2; if the resolution of the video data is resolution 3, the transmission delay budget of the video data is T3. The greater the resolution, the greater the corresponding transmission delay budget. The 5G QoS characteristics indexed by the 5QI of the first QoS flow can also include other contents, such as resource type, priority, etc., which are not limited in the embodiments of the present application.

[0181] Table 3

[0182] In a possible embodiment, the first correspondence is determined based on a second correspondence, and the second correspondence is a correspondence between a first calculation delay and a first resolution, and the first calculation delay is a processing delay of the server for converting video data of the first resolution into video data of a second resolution, and the second resolution is higher than the first resolution. Based on this possible embodiment, the first correspondence can be more accurately determined.

[0183] For example, it is assumed that the transmission delay budget of the terminal directly uploading video data of a resolution of 1080P is 10ms; if the terminal uploads video data of a resolution of 270P, since there is a calculation delay of 4.7ms for the server to convert the video data of 270P into video data of 1080P, the actual transmission delay budget of the video data of 270P is 10ms-4.7ms=5.3ms.

[0184] Optionally, the server can send the second correspondence to the first core network device (such as an AF network element). The first core network device can send the second correspondence to the second core network element (such as an SMF network element). The second core network element determines the first correspondence based on the second correspondence. The second core network element configures the first correspondence to the access network device.

[0185] Alternatively, the server can send the second correspondence to the first core network device (such as an AF network element). The first core network device can determine the first correspondence based on the second correspondence and send the first correspondence to the second core network element (such as an SMF network element). The second core network element configures the first correspondence to the access network device.

[0186] Alternatively, the server can determine the first correspondence relationship based on the second correspondence relationship, and then send the first correspondence relationship to the first core network device, and then the first core network device sends the first correspondence relationship to the second core network device (such as the SMF network element). The second core network element configures the first correspondence relationship to the access network device.

[0187] In a possible embodiment, before the terminal sends the first video data to the access network device through the first QoS flow, the terminal can obtain video data of a second resolution, the second resolution being higher than the first resolution; and the terminal sends the first video data to the access network device through the first QoS flow based on the video data of the second resolution. For example, the terminal can convert the video data of the second resolution into the first video data, and then send the first video data to the access network device through the first QoS flow. Optionally, the specific implementation manner in which the terminal converts the video data of the second resolution into the first video data can be that the terminal can perform downsampling processing on the video data of the second resolution to obtain the first video data. That is, after the terminal collects the video data of a high resolution, the terminal can convert the video data of the high resolution into video data of a low resolution, and then send the video data of the low resolution to the access network device through the first QoS flow, so that the access network device converts the video data of the low resolution into the video data of the high resolution and then sends the video data of the high resolution to the server.

[0188] In a possible embodiment, the access network device can also send indication information to the terminal, the indication information being used to instruct the terminal to upload the video data of the first resolution. Correspondingly, the terminal can receive the indication information. After receiving the indication information, the terminal sends the first video data to the access network device through the first QoS flow based on the indication information. That is, the access network device can select a resolution, and then notify the terminal of the selected resolution, so that the terminal can subsequently upload the video data of the resolution. Based on this possible embodiment, the access network device can flexibly instruct the terminal to upload the resolution of the video data, which is beneficial to improving the transmission performance of the video data.

[0189] In a possible embodiment, the access network device can send the indication information to the terminal based on one or more of the following information: channel state information or a transmission delay budget corresponding to the first QoS flow. Based on this possible design, the access network device can more reasonably instruct the terminal to upload the resolution of the video data, which is beneficial to improving the transmission performance of the video data.

[0190] The channel state information can be the channel state information between the terminal and the access network device. For example, the channel state information can include but is not limited to one or more of the following: information used to indicate the channel quality, the SINR, the size of the reference signal received power, or the subcarrier spacing, etc.

[0191] For example, taking the resolution of the transmission delay budget corresponding to the first QoS flow as an example. The access network device can divide the size of the video data by the transmission delay budget corresponding to the resolution of the video data for different resolutions, to obtain the equivalent transmission rate of the video data. The access network device selects the resolution corresponding to the lowest equivalent transmission rate and indicates it to the terminal, which is conducive to reducing the demand for uplink transmission rate and is conducive to enabling the terminal with low uplink transmission rate to meet the demand for uplink transmission rate. For example, the access network device divides the size of the video data 1 of resolution 1 by the transmission delay budget corresponding to resolution 1, to obtain the equivalent transmission rate 1 of the video data 1. The access network device divides the size of the video data 2 of resolution 2 by the transmission delay budget corresponding to resolution 2, to obtain the equivalent transmission rate 2 of the video data 2. The access network device divides the size of the video data 3 of resolution 3 by the transmission delay budget corresponding to resolution 3, to obtain the equivalent transmission rate 3 of the video data 3. If the equivalent transmission rate 1 is the minimum value in the equivalent transmission rate 1 to the equivalent transmission rate 3, the access network device selects resolution 1 and indicates resolution 1 to the terminal.

[0192] For example, taking the resolution of the transmission delay budget corresponding to the first QoS flow as an example. The access network device can divide the size of the video data by the transmission delay budget corresponding to the resolution of the video data for different resolutions, to obtain the equivalent transmission rate of the video data. The access network device selects the resolution corresponding to the lowest equivalent transmission rate and indicates it to the terminal, which is conducive to reducing the demand for uplink transmission rate and is conducive to enabling the terminal with low uplink transmission rate to meet the demand for uplink transmission rate. For example, the access network device divides the size of the video data 1 of resolution 1 by the transmission delay budget corresponding to resolution 1, to obtain the equivalent transmission rate 1 of the video data 1. The access network device divides the size of the video data 2 of resolution 2 by the transmission delay budget corresponding to resolution 2, to obtain the equivalent transmission rate 2 of the video data 2. The access network device divides the size of the video data 3 of resolution 3 by the transmission delay budget corresponding to resolution 3, to obtain the equivalent transmission rate 3 of the video data 3. If the equivalent transmission rate 1 is the minimum value in the equivalent transmission rate 1 to the equivalent transmission rate 3, the access network device selects resolution 1 and indicates resolution 1 to the terminal.

[0193] For example, the resolution is indicated to the terminal based on the channel state information and the transmission delay budget corresponding to the first QoS flow. In order to guarantee the reliability of transmission, the time caused by air interface error retransmission can be considered. Different subcarrier spacings will result in different retransmission times. For example, it is assumed that the transmission delay budget is 7 ms. When the subcarrier spacing is 30 kHz, the retransmission time of the video data is 2 ms, and the time left for the new transmission of the video data is 5 ms. When the subcarrier spacing is 15 kHz, the retransmission time of the video data is 3 ms, and the time left for the new transmission of the video data is 4 ms. Assuming that the terminal transmits the video data by using the subcarrier spacing of 30 kHz, the access network device divides the size of the video data 1 of the resolution 1 by (the transmission delay budget corresponding to the resolution 1 minus 2 ms) to obtain the equivalent transmission rate 1 of the video data 1. The access network device divides the size of the video data 2 of the resolution 2 by (the transmission delay budget corresponding to the resolution 2 minus 2 ms) to obtain the equivalent transmission rate 2 of the video data 2. The access network device divides the size of the video data 3 of the resolution 3 by (the transmission delay budget corresponding to the resolution 3 minus 2 ms) to obtain the equivalent transmission rate 3 of the video data 3. If the equivalent transmission rate 1 is the minimum value in the equivalent transmission rate 1 to the equivalent transmission rate 3, the access network device selects the resolution 1 and indicates the resolution 1 to the terminal.

[0194] In another possible embodiment, the first resolution can also be a preset value smaller than the second resolution.

[0195] Optionally, V1 is less than V2. V1 is equal to the size of the video data of the first resolution divided by the transmission delay budget corresponding to the first resolution, that is, V1 can be understood as the equivalent transmission rate when the resolution is the first resolution. V2 is equal to the size of the video data of the second resolution divided by (the transmission delay budget corresponding to the first resolution plus the calculation delay corresponding to the first resolution), that is, V2 can be understood as the equivalent transmission rate when the resolution is the second resolution. By making V1 less than V2, the requirement of the uplink transmission rate is reduced, which is beneficial to the terminal with a low uplink transmission rate to meet the requirement of the uplink transmission rate.

[0196] 702. The access network device sends the first video data to the server. Accordingly, the server can receive the first video data.

[0197] 703. The server converts the first video data into second video data. The resolution of the second video data is the second resolution.

[0198] In the embodiment of the application, the server can convert the first video data into the second video data by using the super-resolution technology, that is, the server can convert the video data with a low resolution into the video data with a high resolution. The super-resolution technology is described in the description of the 5th point in the term introduction, which is not described herein again.

[0199] In a possible implementation, the server converts the first video data into the second video data in the following manner: the server converts the first video data into the second video data based on the neural network model.

[0200] In a possible implementation, the terminal can further send training video data to the access network device. Accordingly, the access network device can receive the training video data, the resolution of the training video data being the second resolution; and the access network device sends the training video data to the server. After receiving the training video data, the server trains the neural network model based on the training video data. The training video data can be an image block or a video frame, which is not limited in the embodiments of the present application.

[0201] That is, the terminal can not only send low-resolution video data to the access network device, but also send high-resolution video data to the server through the access network device, so that the server can optimize the neural network model based on the high-resolution video data, which is conducive to improving the performance of the neural network model.

[0202] In a possible implementation, the QoS of the first video data is different from that of the training video data. That is, the first video data and the training video data are sent to the access network device through different QoS flows, i.e., the first video data and the training video data are carried by different QoS flows. The first video data needs to comply with the constraints of the computation latency budget and the transmission latency budget, while the training video data only needs to comply with the transmission latency budget specified by the conventional method.

[0203] For example, as shown in FIG. 8, the terminal sends low-resolution video data 1 to the access network device through a QoS flow 1. After receiving the video data 1, the access network device sends the video data 1 to the server. After receiving the video data 1, the server inputs the video data 1 into the neural network model, and outputs high-resolution video data 2 from the neural network model. The terminal further sends high-resolution image blocks (i.e., high-definition image blocks) to the access network device through a QoS flow 2. After receiving the high-resolution image blocks, the access network device sends the high-resolution image blocks to the server. After receiving the high-resolution image blocks, the server trains the neural network model based on the high-resolution image blocks, so as to optimize the parameters of the neural network model, and make the neural network model better restore high-resolution video data.

[0204] It can be seen that, based on the method described in FIG. 7, the terminal can upload low-resolution video data, the low-resolution video data is sent to the server by the access network device, and the low-resolution video data is converted into high-resolution video data by the server. By making the terminal upload low-resolution video data, the amount of data that needs to be transmitted over the air interface can be reduced as much as possible to reduce the air interface transmission delay of the video data. Therefore, based on the method described in FIG. 7, the terminal can upload video data in time.

[0205] It is worth mentioning that, in a logical case, the content in the embodiment corresponding to FIG. 5 can also be freely combined with the content in the embodiment corresponding to FIG. 7.

[0206] FIG. 9 is a possible exemplary block diagram of a communication apparatus involved in an embodiment of the present application. As shown in FIG. 9, the communication apparatus 900 can include modules or units for implementing the above-mentioned method embodiments. In a possible design, the communication apparatus 900 includes a processing unit 902 and a communication unit 903. Optionally, the communication apparatus 900 can further include a storage unit 901 for storing apparatus program code and / or data.

[0207] The communication apparatus 900 can be a terminal-side apparatus in the above-mentioned embodiments, for example, a terminal or a communication module in the terminal, or a circuit or chip responsible for communication functions in the terminal.

[0208] For example, in an embodiment, the communication unit 903 is configured to receive indication information from the access network device, the indication information being used to indicate uploading of first-resolution video data; the processing unit 902 is configured to obtain second-resolution video data; and the communication unit 903 is further configured to send, to the access network device, first video data based on the second-resolution video data, the resolution of the first video data being the first resolution, and the second resolution being higher than the first resolution.

[0209] In a possible design, the communication unit 903 is further configured to send, to the access network device, training video data, the resolution of the training video data being the second resolution, and the training video data being used for training of a neural network model, the neural network model being used for conversion of the first video data into the second-resolution video data.

[0210] In a possible design, the QoS of the first video data and the training video data is different.

[0211] In a possible design, when the communication apparatus 900 is a terminal or a communication module in a terminal, the function of the processing unit 902 can be implemented by one or more processors. Specifically, the processor can include a modem chip, or a system on chip (SoC) chip or a SIP chip including a modem core. The function of the communication unit 903 can be implemented by a transceiver circuit.

[0212] In a possible design, when the communication apparatus 900 is a circuit or chip responsible for communication functions in a terminal, such as a modem chip or a system on chip (SoC) chip or a SIP chip including a modem core, the function of the processing unit 902 can be implemented by circuitry including one or more processors or processor cores in the chip. The function of the communication unit 903 can be implemented by an interface circuit or a data transceiver circuit on the chip.

[0213] In a possible design, when the communication apparatus 900 is a terminal or a processing module in a terminal, the function of the processing unit 902 can be implemented by one or more processors. Specifically, the processor can include a GPU, or a system on chip (SoC) chip or a SIP chip including a GPU. The function of the communication unit 903 can be implemented by a transceiver circuit.

[0214] In a possible design, when the communication apparatus 900 is a circuit or chip responsible for processing functions in a terminal, such as a GPU or a system on chip (SoC) chip or a SIP chip including a GPU, the function of the processing unit 902 can be implemented by circuitry including one or more processors or processor cores in the chip. The function of the communication unit 903 can be implemented by an interface circuit or a data transceiver circuit on the chip.

[0215] The communication apparatus 900 can be a network side device in the embodiments, for example, an access network device or a communication module in an access network device, or a circuit or chip responsible for communication functions in an access network device.

[0216] For example, in an embodiment, the communication unit 903 is configured to receive first video data from a terminal through a first quality of service (QoS) flow, the resolution of the first video data being a first resolution; the latency budget information corresponding to the first QoS flow is related to at least a calculation latency budget, and the calculation latency budget is a processing latency budget for converting low-resolution video data into high-resolution video data; the processing unit 902 is configured to convert the first video data into second video data, the resolution of the second video data being a second resolution, and the second resolution being higher than the first resolution; and the communication unit 903 is further configured to send the second video data to a server.

[0217] In a possible design, the communication unit 903 is further configured to send, to the terminal, indication information, where the indication information is used to instruct the terminal to upload the video data of the first resolution.

[0218] In a possible design, the sending of the indication information to the terminal comprises: sending the indication information to the terminal based on one or more of the following information: channel state information, computing power information of the access network device, or time delay budget information corresponding to the first QoS flow.

[0219] In a possible design, the conversion of the first video data into the second video data comprises: converting the first video data into the second video data based on a neural network model.

[0220] The communication unit 903 is further configured to receive, from the terminal, training video data, where the training video data is of a second resolution; and the processing unit 902 is further configured to train the neural network model based on the training video data.

[0221] In a possible design, the QoS of the first video data and the training video data is different.

[0222] For another example, in another embodiment, the communication unit 903 is configured to receive, from the terminal, first video data through a first quality of service (QoS) flow, where the first video data is of a first resolution, and there is a first correspondence relationship between a transmission time delay budget of the first video data and the first resolution; and the communication unit 903 is further configured to send, to the server, the first video data.

[0223] In a possible design, the communication unit 903 is further configured to receive, from a core network element, configuration information, where the configuration information is used to configure the first correspondence relationship.

[0224] In a possible design, the configuration information is configuration information of the first QoS flow.

[0225] In a possible design, the first correspondence relationship is determined based on a second correspondence relationship, where the second correspondence relationship is a correspondence relationship between a first computing time delay and the first resolution, and the first computing time delay is a processing time delay of the server for converting video data of the first resolution into video data of a second resolution, and the second resolution is higher than the first resolution.

[0226] In a possible design, the communication unit 903 is further configured to send, to the terminal, indication information, where the indication information is used to instruct the terminal to upload the video data of the first resolution.

[0227] In a possible design, the sending of the indication information to the terminal comprises: sending the indication information to the terminal based on one or more of the following information: channel state information or a transmission time delay budget corresponding to the first QoS flow.

[0228] In a possible design, the communication unit 903 is further configured to receive training video data from the terminal, the training video data being at a second resolution; and the communication unit 903 is further configured to send the training video data to the server, the second resolution being higher than the first resolution, the training video data being used for training of a neural network model, the neural network model being used for conversion of the first video data to video data at the second resolution.

[0229] In a possible design, the QoS of the first video data and the training video data is different.

[0230] In a possible design, when the communication apparatus 900 is an access network device or a communication module in an access network device, the function of the processing unit 902 can be implemented by one or more processors. Specifically, the processor can include a modem chip, or a system on chip (SoC) chip or a SIP chip that includes a modem core. The function of the communication unit 903 can be implemented by a transceiver circuit.

[0231] In a possible design, when the communication apparatus 900 is a circuit or chip responsible for communication functions in an access network device, such as a modem chip or a system on chip (SoC) chip or a SIP chip that includes a modem core, the function of the processing unit 902 can be implemented by circuitry including one or more processors or processor cores in the chip. The function of the communication unit 903 can be implemented by an interface circuit or a data transceiver circuit on the chip.

[0232] In a possible design, when the communication apparatus 900 is an access network device or a processing module in an access network device, the function of the processing unit 902 can be implemented by one or more processors. Specifically, the processor can include a GPU, or a system on chip (SoC) chip or a SIP chip that includes a GPU. The function of the communication unit 903 can be implemented by a transceiver circuit.

[0233] In a possible design, when the communication apparatus 900 is a circuit or chip responsible for processing functions in an access network device, such as a GPU or a system on chip (SoC) chip or a SIP chip that includes a GPU, the function of the processing unit 902 can be implemented by circuitry including one or more processors or processor cores in the chip. The function of the communication unit 903 can be implemented by an interface circuit or a data transceiver circuit on the chip.

[0234] It can be understood that the division of units in the above apparatus is only a logical function division, one function can correspond to one functional unit, or two or more functions can be integrated into one functional unit. In actual implementation, all or part of the units can be integrated into one physical entity, or can be distributed in different physical entities. In addition, the above functional units can be realized in the form of hardware, or in the form of software, or in the form of hardware combined with software. Whether a certain function is executed in the form of hardware or software depends on the specific application and design constraints of the technical scheme. Professional technicians can use different methods to implement the described functions for specific applications, but such implementation should not be considered beyond the scope of the present application.

[0235] In one example, the functional units in any of the above apparatuses can 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.

[0236] In one example, the storage unit 901 can include random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, and / or registers, etc.

[0237] Referring to FIG. 10, FIG. 10 is a structural schematic diagram of a terminal 1000 provided by an embodiment of the present application, which can correspond to the terminal shown in FIG. 5 or FIG. 7, and is used to implement the operation of the terminal in the above embodiments. As shown in FIG. 10, the terminal includes one or more antennas 1010, a radio frequency processing system 1020, and a processor system 1030.

[0238] In the downlink or sidelink direction, the radio frequency processing system 1020 receives radio frequency signals through the antenna 1010, and sends the signals after radio frequency processing to the processor system 1030 for further processing. In the uplink or sidelink direction, the processor system 1030 performs signal processing on the information at the terminal side, and sends it to the radio frequency processing system 1020, which performs radio frequency processing on the signal and transmits it through the antenna 1010.

[0239] In one example, the radio frequency processing system 1020, which serves as a communication interface for the terminal to communicate with the outside, can include a radio frequency front end 1021 (RFFE) and a radio frequency transceiver 1022. The RFFE 1021 is mainly used for one or more of shaping, passband selection, or gain processing of RF signals received by an antenna or to be transmitted through an antenna, and can include one or more of radio frequency switches, duplexers, filters, power amplifiers, antenna tuning, and low-noise amplifiers. The RFFE 1021 can be circuitry composed of a plurality of discrete devices, or can be integrated and packaged in one or more chips. The radio frequency transceiver 1022 is used to process RF signals received by the RFFE into baseband / intermediate frequency signals for further processing by the processor system 1030, and to process baseband / intermediate frequency signals provided by the processor system 1030 into RF signals for transmission to the RFFE 1021. The baseband / intermediate frequency signals transmitted between the radio frequency transceiver 1022 and the processor system 1030 can be digital signals or analog signals. The radio frequency transceiver 1022 can be implemented by one or more chips, which are commonly referred to as radio frequency chips (RFIC).

[0240] In one example, the processor system 1030 can include one or more processors for processing signals and executing one or more communication protocols. Optionally, the processor system 1030 can also include a memory 1036. In one example, the one or more processors include at least one baseband processor 1031 (also referred to as a modem processor). The memory 1036 is used to store data and / or computer program instructions. Optionally, the processor system 1030 can also include one or more application processors 1032 for implementing processing of the terminal operating system and the application layer. The application processor 1032 can include a GPU, for example. Optionally, the processor system 1030 can also include one or more of a voice subsystem 1033, a multimedia subsystem 1034, or an interface circuit 1035. The voice subsystem 1033 is used to process voice signals, the multimedia subsystem 1034 is used to process multimedia-related operations such as video encoding and decoding, image processing, etc., and the interface circuit 1035 is used to implement communication with other terminal components such as a display 1040, an input device 1050, a memory 1060, etc. The above-mentioned components in the processor system 1030 can communicate with each other through a bus or a communication interface circuit.

[0241] In one example, the processor system 1030 can be packaged as one processor chip, such as a SoC chip or a SIP chip. In one example, the processor system 1030 can be a system composed of multiple chips, for example, the baseband processor 1031 can be packaged as a separate chip, or packaged as a chip with part or all of the circuitry of the radio frequency processing system.

[0242] In one example, the memory 1036 can be an on-chip memory, i.e., located on the chip of the processor system 1030. In one example, the memory 1060 can be an off-chip memory, i.e., located off the chip of the processor system 1030.

[0243] In one example, the baseband processor 1031 can include one or more processor cores 10311 and interface circuitry 10314. The one or more processor cores 10311 are configured to process signals and perform one or more communication protocols. Optionally, the baseband processor 1031 can further include a memory 10312 configured to store at least part of corresponding computer program instructions and / or data. In one example, the one or more processor cores 10311 implement the relevant operations in the above method embodiments (such as the method embodiments described in FIG. 5 or FIG. 7) by executing the computer program instructions stored in the memory 10312. In this disclosure, the memory 10312 configured to store corresponding computer program instructions and / or data can mean that the memory 10312 is configured to store all corresponding computer program instructions and / or data for execution by the processor core 10311; or can mean that the memory 10312 is configured to store part of corresponding computer program instructions and / or data, which includes computer program instructions and / or data currently needed for execution by the processor core 10311, and the memory 10312 can store different parts of computer program instructions and / or data for execution by the processor core 10311 multiple times to implement the relevant operations in the above method embodiments. The interface circuitry 10314 serves as a communication interface to enable communication with other components, such as transmitting signals with the radio frequency processing system 1020, communicating with other subsystems and related components of the processor system 1030 through a bus, such as transmitting data control signals with the application processor 1032, and transmitting data or computer program instructions with the memory 1036 or the memory 1060. Optionally, to reduce the load of the processor core, a baseband signal processing circuit 10313 can be further provided to implement at least part of the processing of baseband signals, including one or more of demodulation, modulation, encoding or decoding of signals.

[0244] In one example, the communication apparatus provided in the present application can be the terminal 1000, the communication module including the processor system 1030 and the radio frequency processing system 1020, the processor system 1030, or the baseband processor 1031.

[0245] The processor, processor system, application processor, baseband processor, processor circuit, or processor core can be collectively referred to as a processor, which can include one or a combination of a central processing unit (CPU), a digital signal processor (DSP), a microprocessor unit (MPU), a microcontroller unit (MCU), a graphics processing unit (GPU), a field programmable gate array (FPGA), an artificial intelligence processor (AI processor), or a neural processing unit (NPU).

[0246] The above-mentioned memory can include one or more of the following storage media: random access memory (RAM), static RAM (SRAM), dynamic RAM (DRAM), phase-change memory (PCM), resistive RAM (ReRAM), magnetoresistive RAM (MRAM), ferroelectric RAM (FRAM), cache, register, read-only memory (ROM), flash memory, erasable programmable ROM (EPROM), hard disk, etc. In one example, the computer program instructions for implementing the above-embodiments can be stored on a non-volatile memory, such as at least part of the above-mentioned memory 1060 (e.g., one or more of ROM, flash memory, EPROM, or hard disk). During terminal operation, the corresponding computer program instructions can be loaded in whole or in part into a memory with faster transmission speed to the processor, such as at least part of the above-mentioned memory 1036 and / or memory 10312 (e.g., one or more of RAM, SRAM, DRAM, PCM, RERAM, MRAM, FRAM, cache, or register), for execution by the processor to implement the steps in the above-mentioned method embodiments.

[0247] In one example, the radio frequency transceiver 1022 and the radio frequency front end 1021 can also be packaged in one chip. In one example, the radio frequency transceiver 1022, the radio frequency front end 1021, and the baseband processor 1031 can also be packaged in one chip.

[0248] The terms "system" and "network" can be used interchangeably in the embodiments of the present application. Those skilled in the art understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, optical storage, etc.) containing computer-usable program code.

[0249] The computer program instructions can 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 the flowchart block or blocks.

[0250] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart block or blocks.

[0251] These computer program instructions can 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 the flowchart block or blocks.

[0252] Obviously, numerous modifications and variations of the present application are possible in light of the above teachings. It is therefore to be understood that within the scope of the claims and their equivalents, the application can be practiced otherwise than as specifically described.

Claims

1. A data transmission method, characterized by, The method comprises: The terminal sends first video data to an access network device through a first quality of service (QoS) flow, the access network device receives the first video data, and a resolution of the first video data is a first resolution; time delay budget information corresponding to the first QoS flow is related to at least a calculation time delay budget, and the calculation time delay budget is a processing time delay budget for converting low-resolution video data into high-resolution video data; The access network device converts the first video data into second video data, and a resolution of the second video data is a second resolution higher than the first resolution; The access network device sends the second video data to a server.

2. The method of claim 1, wherein, The method further comprises: The access network device sends indication information to the terminal, and the terminal receives the indication information, and the indication information is used to instruct the terminal to upload video data of the first resolution.

3. The method of claim 2, wherein, The access network device sends the indication information to the terminal, comprising: The access network device sends the indication information to the terminal based on one or more of the following information: channel state information, computing power information of the access network device, or time delay budget information corresponding to the first QoS flow.

4. The method according to any one of claims 1 to 3, characterized in that, The access network device converts the first video data into second video data, comprising: The access network device converts the first video data into the second video data based on a neural network model; The method further comprises: The terminal sends training video data to the access network device, and the access network device receives the training video data, and a resolution of the training video data is the second resolution; The access network device trains the neural network model based on the training video data.

5. The method of claim 4, wherein, QoS of the first video data and the training video data is different.

6. A data transmission method, characterized by, The method comprises: Receiving indication information from an access network device, and the indication information is used to instruct to upload video data of a first resolution; Obtaining video data of a second resolution; Sending first video data to the access network device based on the video data of the second resolution, and a resolution of the first video data is the first resolution, and the second resolution is higher than the first resolution.

7. The method of claim 6, wherein, The method further comprises: Sending training video data to the access network device, and a resolution of the training video data is the second resolution, and the training video data is used for training of a neural network model, and the neural network model is used for conversion of the first video data into video data of the second resolution.

8. The method of claim 7, wherein, QoS of the first video data and the training video data is different.

9. A data transmission method, characterized by, The method comprises: The terminal sends first video data to an access network device through a first quality of service (QoS) flow, the access network device receives the first video data, and a resolution of the first video data is a first resolution, and a transmission time delay budget of the first video data has a first corresponding relationship with the first resolution; The access network device sends the first video data to a server.

10. The method of claim 9, wherein, The method further comprises: The access network device receives configuration information from a core network element, the configuration information being used to configure the first correspondence.

11. The method of claim 10, wherein, The configuration information is configuration information of the first QoS flow.

12. The method according to any one of claims 9 to 11, characterized in that, The first correspondence is determined based on a second correspondence, the second correspondence being a correspondence between a first calculation delay and the first resolution, the first calculation delay being a processing delay of the server in converting video data of the first resolution into video data of a second resolution, the second resolution being higher than the first resolution.

13. The method according to any one of claims 9 to 12, characterized in that, The method further comprises: The access network device sends indication information to the terminal, and the terminal receives the indication information, the indication information being used to instruct the terminal to upload video data of the first resolution.

14. The method of claim 13, wherein, The access network device sends indication information to the terminal, and the terminal receives the indication information, the indication information being used to instruct the terminal to upload video data of the first resolution. The access network device sends indication information to the terminal based on one or more of the following information: channel state information or a transmission delay budget corresponding to the first QoS flow.

15. The method according to any one of claims 9 to 14, characterized in that, The method further comprises: The terminal sends training video data to the access network device, and the access network device receives the training video data, the resolution of the training video data being a second resolution; The access network device sends the training video data to the server, the second resolution being higher than the first resolution, the training video data being used for training of a neural network model, the neural network model being used for conversion of the first video data into video data of the second resolution.

16. The method of claim 15, wherein, The QoS of the first video data and the training video data is different.

17. A communications device, characterized by The apparatus comprises means for performing the method of any one of claims 6-8.

18. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer executable instructions, which, when invoked, cause the method of any one of claims 6-8 to be performed.

19. A computer program product, characterised in that, The computer program product comprises computer program code, which, when run, causes the method of any one of claims 6-8 to be performed.

20. A communications device, characterized by The apparatus comprises interface circuitry for enabling communication within the apparatus and / or between the apparatus and other apparatuses or components, and one or more processors coupled with a memory, the memory storing computer programs or instructions that, when executed by the one or more processors, cause the method of any one of claims 6-8 to be implemented.

Images