Artificial intelligence priority notification method and related apparatus

Abstract

An artificial intelligence priority notification method and a related apparatus. The method comprises: a terminal generating first information, the first information being used to indicate a processing priority of a data unit, wherein the processing priority is used to allocate processing resources to the data unit, and the data unit is used for AI inference and / or training tasks; and, the terminal sending the first information. Hence, in this method, the terminal or a server can mark a processing priority of a data unit for an AI task, so that a network side can allocate processing resources on the basis of the processing priority, thereby improving the utilization of processing resources of the network and alleviating the problem of computing power shortage.

Description

Artificial intelligence priority notification method and related apparatus

[0001] The present application claims priority to the Chinese patent application No. 202410602027.1, filed on May 14, 2024, with the State Intellectual Property Office of China, and entitled "Artificial intelligence priority notification method and related apparatus", the whole content of which is incorporated herein by reference. TECHNICAL FIELD

[0002] The present application relates to the field of communication technology, in particular to an artificial intelligence priority notification method and related apparatus in a communication system. BACKGROUND

[0003] With the rise of large-scale artificial intelligence generated content (AIGC) applications, the massive growth of user traffic brings severe computing power challenges to central servers. Wireless networks are naturally close to terminals, and distributed learning based on wireless transmission has outstanding value in terms of sensing data acquisition, auxiliary training, and auxiliary reasoning. Considering the growing trend of wireless network computing resources in the future, the computing power and real-time computing resource status of wireless networks can fully support the computing power of massive terminal users and the central server.

[0004] With the continuous development of terminal devices, the terminal itself also has certain computing power and can bear certain neural network computing. For example, the application server can split the deep neural network (DNN) model computing task, perform front-end preprocessing and computing by the terminal, upload complex computing to the cloud application server for computing and processing, or perform computing on the part with lower level and lower computing power requirement by the terminal, and perform processing on the part with higher level and higher computing power requirement by uploading to the cloud server. Compared with the traditional way of directly uploading and processing the original image quantity by the network, the above-mentioned way of splitting the DNN model computing task, such as extracting image information by the terminal and uploading the extracted intermediate feature information to the network, reduces the amount of data uploaded.

[0005] Therefore, for the way of splitting the computing task, how the network provides computing power support to the terminal and the server to alleviate the computing power shortage problem is a problem to be solved. SUMMARY

[0006] The present application provides an artificial intelligence priority notification method and related apparatus, which can improve the utilization rate of network processing resources and alleviate the computing power shortage problem.

[0007] In a first aspect, the present application provides an artificial intelligence priority notification method. The method is applied to a terminal side, for example, a terminal or a communication module / processing module in the terminal, or a circuit or chip responsible for communication function in the terminal (such as a modem chip, also known as a baseband chip, or a system on chip (SoC) chip or a system in package (SIP) chip containing a modem core), or a circuit or chip responsible for processing function in the terminal (such as a graphics processing unit (GPU)). The method is also applied to a server side, for example, a server or a communication module / processing module in the server, or a circuit or chip responsible for communication function in the server (such as a modem chip, also known as a baseband chip, or a system on chip (SoC) chip or a system in package (SIP) chip containing a modem core), or a circuit or chip responsible for processing function in the server (such as a graphics processing unit (GPU)).

[0008] In the method, the terminal generates first information, the first information is used to indicate a processing priority of a data unit, the processing priority is used for allocation of a processing resource of the data unit; the data unit is used for an inference task and / or a training task of artificial intelligence (AI); and the terminal sends the first information. It can be seen that in the method, the terminal or the server can mark the processing priority of the data unit of the AI task, so that the network side can allocate the processing resource such as a communication resource and / or a computing resource according to the processing priority, thereby improving the utilization rate of the processing resource of the network and relieving the problem of tight computing power.

[0009] Optionally, the inference task refers to adjusting the input of the AI model to obtain the desired output without modifying the AI model. The training task refers to adjusting the input of the AI model and the parameters or weights of the AI model to improve the effect of the model.

[0010] In an optional implementation, the first information is carried in uplink control information, medium access control-control element, or radio resource control signaling. It can be seen that in this implementation, the first information is transmitted through control information or signaling, which can improve the reliability of the transmission of the processing priority.

[0011] In another optional implementation, the first information is carried in a data packet, such as a packet header of the data packet, where the data packet is used to carry a data unit. It can be seen that, in this implementation, the first information is transmitted by using the data packet, and the data unit and the processing priority are transmitted in the form of the data packet, which can improve the real-time performance and flexibility of setting the processing priority.

[0012] In an optional implementation, the first information is further used to indicate a quantity of data units corresponding to the processing priority. In this way, the corresponding processing priority can be marked for each of the data units, so that the network side can allocate processing resources to the data units based on the processing priority corresponding to the data units.

[0013] In another optional implementation, the terminal further generates and sends second information, where the second information is used to indicate the quantity of data units, and the processing priority of the data units is indicated by the first information corresponding to the data units. In this way, for N data units, N first information can be generated and sent, in one-to-one correspondence with the N data units; or for N data units, M first information can be generated and sent, where there is a one-to-many correspondence between the N data units and the M first information, and data units with the same processing priority correspond to the same first information.

[0014] In an optional implementation, the second information is carried in uplink control information, medium access control-control element, or radio resource control signaling. It can be seen that, in this implementation, the second information is transmitted by using the control information or the signaling, which can improve the reliability of transmitting the quantity of data units. The first information and the second information can be carried in the same information or the same signaling and sent together, or the first information and the second information can be carried in different information or signaling and sent separately.

[0015] In another optional implementation, the second information is carried in a data packet, such as a packet header of the data packet. In this way, the first information and the second information are both sent in the form of the data packet, which can improve the flexibility of setting the processing priority and the timeliness of information transmission.

[0016] In an optional real-time manner, the terminal further receives fourth information; accordingly, the terminal generates the first information, including: the terminal generates the first information based on the fourth information. That is, the fourth information is used to inform the terminal or the server to generate the first information. It can be seen that in this embodiment, the network side informs the terminal to generate the first information, that is, to set the processing priority of the data unit, thereby facilitating the network side to allocate processing resources to the data unit based on the processing priority.

[0017] In a second aspect, the present application also provides an artificial intelligence priority notification method, which is applied to an access network device on the network side, a module (such as a circuit, a chip or a chip system, etc.) in the access network device, or a logical node, a logical module or software capable of realizing all or part of the functions of the access network device; for example, the method can be applied to a core network element on the network side, such as a user plane function network element, a module (such as a circuit, a chip or a chip system, etc.) in the user plane function network element, or a logical node, a logical module or software capable of realizing all or part of the functions of the user plane function network element. Taking the method applied to the access network device as an example, the access network device receives first information, the first information being used to indicate the processing priority of a data unit; the data unit is used for an inference task and / or a training task of artificial intelligence (AI); and the access network device allocates processing resources to the data unit according to the processing priority indicated by the first information, that is, allocates corresponding processing resources to the data unit.

[0018] It can be seen that in the method, the access network device detects the processing priority of the data unit of the AI task, and allocates processing resources such as communication resources and / or computing resources to the data unit according to the processing priority, thereby improving the utilization rate of the processing resources and relieving the problem of tight computing power.

[0019] In an optional embodiment, the first information is also used to indicate the number of data units corresponding to the processing priority. In this way, the terminal or the server marks a plurality of data units with corresponding processing priorities respectively, and the access network device can allocate processing resources to the data units based on the processing priorities corresponding to the data units.

[0020] In another optional embodiment, the access network device further receives second information, the second information being used to indicate the number of data units, and the processing priority of the data unit being indicated by the first information corresponding to the data unit. In this way, for N data units, N first information corresponds to the N data units one by one; or for N data units, there is a many-to-one correspondence between N data units and M first information, wherein data units with the same processing priority correspond to the same first information.

[0021] The sending manner of the first information and the second information can be referred to the related content described in the first aspect, which will not be described in detail here.

[0022] In an optional implementation, the access network device further receives third information, the third information being used to request the network side to detect the processing priority. In this way, the access network device such as a base station or the core network device such as a user plane function network element can detect the processing priority of the data unit, so as to allocate the processing resource to the data unit according to the processing priority.

[0023] In an optional real-time manner, the access network device further sends fourth information; the fourth information is used to notify the terminal or the server to generate the first information. In this way, the access network device can receive the processing priority of the data unit, so as to allocate the processing resource to the data unit according to the processing priority.

[0024] In an optional implementation, if the processing resource allocated by the access network device to the data unit does not meet the preset condition, the method further includes: the access network device sends a GTP-U protocol data unit to the core network network element, the GTP-U protocol data unit including the data unit of the AI task carried by the GTP-U protocol data unit and the processing priority of the data unit. The GTP-U is the abbreviation of general packet radio service tunneling protocol-user plane, and the GTP-U protocol is a user data transmission protocol used in a general packet radio service (GPRS) network, which is a protocol for establishing a tunnel in a user plane. It can be seen that, in this implementation, the core network can also assist the access network device to complete the processing of the AI task, improve the utilization rate of the processing resource, and alleviate the problem of tight computing power of the access network device.

[0025] In another optional implementation, the method is applied to a core network network element, and if the processing resource allocated by the core network network element to the data unit does not meet the preset condition, the method further includes: the core network network element sends the data unit of the AI task and the processing priority of the data unit to the access network device. It can be seen that, in this implementation, the access network device can also assist the core network network element to complete the processing of the AI task, improve the utilization rate of the processing resource, and alleviate the problem of tight computing power of the core network network element.

[0026] The further elaboration and beneficial effects of the optional implementation in the second aspect can be referred to the related content described in the first aspect, and will not be described in detail here.

[0027] In the third aspect, the present application provides a communication device, which has the function of realizing the first aspect, for example, the communication device includes a module or unit or means corresponding to the operation of the first aspect, which can be realized by software, or by hardware, or by a combination of software and hardware.

[0028] In a fourth aspect, the present application provides a communication apparatus, which has the function of the second aspect, e.g., the communication apparatus includes modules or units or means corresponding to the operations of the second aspect, which can be implemented by software or by hardware or by a combination of software and hardware.

[0029] In a fifth 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 first aspect. The one or more processors can execute the computer programs or instructions, which, when executed, cause the communication apparatus to implement the method of any possible design or implementation manner of the first aspect. The interface circuit is used to implement the communication function within the communication apparatus and / or the communication function of the communication apparatus with other apparatuses or components.

[0030] In a possible design, the processor is configured to communicate with other apparatuses or components via the interface circuit.

[0031] In a possible design, the communication apparatus can further include the memory.

[0032] The communication apparatus can be a terminal, a communication / processing module in the terminal, 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 the terminal, or a circuit or chip responsible for processing function (e.g., a GPU) in the terminal. The communication apparatus can be a server, a communication / processing module in the server, 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 the server, or a circuit or chip responsible for processing function (e.g., a GPU) in the server.

[0033] In a sixth 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. The one or more processors can execute the computer programs or instructions, which, when executed, cause the communication apparatus to implement the method of any possible design or implementation manner of the second aspect. The interface circuit is used to implement the communication function within the communication apparatus and / or the communication function of the communication apparatus with other apparatuses or components.

[0034] In a possible design, the processor is configured to communicate with other apparatuses or components via the interface circuit.

[0035] In a possible design, the communication apparatus further includes the memory.

[0036] The communication apparatus described above can be a network-side device, a communication / processing module in the network-side device, a chip responsible for communication function in the network-side device (such as a modem chip, also referred to as a baseband chip), or an SoC or SIP chip including a modem module, or a circuit or chip (such as a GPU) responsible for processing function in the network-side device. Optionally, the network-side device can be an access network device or a core network device.

[0037] In a seventh aspect, the present application provides a communication system, including a first communication apparatus and a second communication apparatus; the first communication apparatus is configured to perform the method in the first aspect or any possible implementation manner of the first aspect, and the second communication apparatus is configured to perform the method in the second aspect or any possible implementation manner of the second aspect.

[0038] In an eighth 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 is caused to perform the method in any possible design of the first aspect to the second aspect.

[0039] In a ninth aspect, the present application provides a computer program product, when a computer reads and executes the computer program product, the computer is caused to perform the method in any possible design of the first aspect to the second aspect. BRIEF DESCRIPTION OF DRAWINGS

[0040] FIG. 1 is a simplified schematic diagram of a communication system;

[0041] FIG. 2 is a schematic diagram of a possible application framework in the communication system;

[0042] FIG. 3 is a schematic diagram of another possible application framework in the communication system;

[0043] FIG. 4 to FIG. 6 are schematic diagrams of architecture scenarios to which the present application can be applied;

[0044] FIG. 7 is a schematic diagram of a communication method provided by an embodiment of the present application;

[0045] FIG. 8 to FIG. 10 are schematic diagrams of communication methods provided by embodiments of the present application;

[0046] FIG. 11 is a schematic diagram of a structure of a communication apparatus provided by an embodiment of the present application;

[0047] FIG. 12 is a schematic diagram of a structure of a terminal provided by an embodiment of the present application. DETAILED DESCRIPTION

[0048] The present application can be applied to various communication systems, including but not limited to: a long term evolution (LTE) system, a 4th generation (4G) system, a 5th generation (5G) system such as new radio access technology (NR), a network integrating multiple systems, an Internet of Things system, a vehicle-to-everything system, an open radio access network (O-RAN) system, and a future communication system, etc.

[0049] Referring to FIG. 1, FIG. 1 is a simplified schematic diagram of a communication system. As shown in FIG. 1, the communication system includes a radio access network (RAN) 100 and a core network (CN) 200. The RAN 100 includes at least one RAN node (e.g., 110a and 110b in FIG. 1, collectively referred to as RAN nodes 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. The terminal 120 is connected to the RAN node 110 in a wireless manner. The RAN node 110 is connected to the core network 200 in a wireless or wired manner. The core network device in the core network 200 and the RAN node 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 radio access network.

[0050] The RAN 100 can be a 3rd generation partnership project (3GPP) related cellular system, e.g., an LTE system, a 4G or 5G mobile communication system, or a future-oriented communication system. The RAN 100 can also be an open RAN (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 integrating two or more of the above systems.

[0051] The RAN node 110, which can also be referred to as an access network device, a RAN entity, or an access node, etc., forms part of the communication system, and is configured to facilitate the wireless access by the terminals. The RAN nodes 110 in the communication system can be of the same type or can be 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 Figure 1 can be a helicopter or a drone, which can be configured to move as a mobile base station, and for a terminal 120j accessing the RAN 100 via 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 devices, e.g., the network elements 110a and 110b in Figure 1 can be understood as communication devices with base station functionalities, and the network elements 120a-120j can be understood as communication devices with terminal functionalities.

[0052] In a possible scenario, the RAN node can be a base station, an evolved NodeB (eNodeB), an access point (AP), a transmission reception point (TRP), a next generation NodeB (gNB), a base station in a future mobile communication system, or an access node in a WiFi system, etc. The RAN node 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. Optionally, the RAN node can also be a server, a wearable device, a vehicle or a vehicle-mounted device, etc. For example, the access network device in vehicle to everything (V2X) technology can be a road side unit (RSU). All or part of the functions of the RAN node in this application can also be implemented by software functions running on hardware, or by virtualized functions instantiated on a platform (e.g., a cloud platform). The RAN node can also be provided with a communication module, circuit or chip for performing corresponding communication functions, and program instructions for performing corresponding communication functions. The RAN node in this application can also be a logic node, a logic module or software that can implement all or part of the functions of the RAN node.

[0053] In another possible scenario, a terminal is assisted by multiple RAN nodes to implement wireless access, and different RAN nodes respectively implement part of functions of a base station. For example, a RAN node 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 also be included in the same network element, for example, in a baseband unit (BBU). The RU can be included in a radio frequency device or a radio frequency unit, for example, included in a remote radio unit (RRU), an active antenna processing unit (AAU), or a remote radio head (RRH).

[0054] 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 an ORAN system, the CU can also be referred to as an O-CU (open CU), the DU can also be referred to as an O-DU, the CU-CP can also be referred to as an O-CU-CP, the CU-UP can also be referred to as an O-CU-UP, and the RU can also be referred to as an 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.

[0055] A terminal can be a device or module with corresponding communication functions and can access the above communication system. The terminal can also be referred to as a terminal device, user equipment (UE), mobile station, mobile terminal, etc. The terminal can be widely used in various scenarios, such as device-to-device (D2D), vehicle to everything (V2X) communication, machine-type communication (MTC), internet of things (IOT), virtual reality, augmented reality, industrial control, autonomous driving, remote medical treatment, smart power grid, smart furniture, smart office, smart wear, smart transportation, smart city, etc. The terminal can be a mobile phone, tablet computer, computer with wireless transceiver function, wearable device, vehicle, unmanned aerial vehicle, helicopter, airplane, ship, robot, mechanical arm, smart home device, transport vehicle with wireless communication function, communication module, etc. 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 performing corresponding communication functions. The terminal is also configured with program instructions for performing corresponding communication functions.

[0056] In order to support AI technology in a wireless network, an AI node can also be introduced in the network.

[0057] The AI node can be deployed in one or more of the following positions in the communication system: access network node (RAN node), terminal device, or core network device, etc., or the AI node can also be deployed separately, for example, in a position other than any of the above devices, such as a host or cloud server of an over the top (OTT) system. The AI node can communicate with other devices in the communication system, which can be one or more of the following: network device, terminal device, or core network element, etc.

[0058] 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, such as different AI nodes responsible for different functions.

[0059] It can also be understood that the AI node can be a separate device, can be integrated into the same device to implement different functions, or can be a network element in a hardware device, or 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 above AI node.

[0060] The AI node can be an AI network element or an AI module.

[0061] FIG. 2 is a schematic diagram of a possible application framework in a communication system. As shown in FIG. 2, 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. 2 for clarity) are deployed in one or more of the network element nodes, such as a core network device, an access network node, a terminal, or one or more devices in operations administration and maintenance (OAM). The access network node can be a standalone RAN node or can include multiple RAN nodes, such as 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.

[0062] The AI module is used to implement a corresponding AI function. The 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 structural parameter (such as 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 (such as a type of input parameter and / or a dimension of the input parameter), or an output parameter (such as 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.

[0063] 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).

[0064] 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.

[0065] A CNN is a deep neural network with a convolutional structure. A CNN includes a feature extractor composed of convolutional layers and subsampling layers. The feature extractor can be viewed as a filter, and the convolution process can be viewed as using a trainable filter to convolve with an input image or a convolutional feature map.

[0066] An RNN is a type of recursive neural network that takes sequence data as input, performs recursion in the direction of the sequence evolution, and connects all nodes (recurrent units) in a chain.

[0067] A GAN is a type of deep learning model. It is composed of a generator and a discriminator, and is trained through adversarial learning. The goal is to estimate the underlying distribution of data samples and generate new data samples.

[0068] An AI module can have one or more models. A model can infer an output, which includes a parameter or multiple 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.

[0069] FIG. 3 is a schematic diagram of another possible application framework in a communication system. As shown in FIG. 3, the communication system includes a radio access network intelligent controller (RIC). For example, the RIC can be the AI module 117, 118 shown in FIG. 2, and is configured 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-RT RIC mainly processes non-real-time information, such as data that is not sensitive to latency, which can be on the order of seconds. The near-RT RIC mainly processes near-real-time information, such as data that is relatively sensitive to latency, which can be on the order of tens of milliseconds.

[0070] Near real-time RIC is used for model training and inference. For example, it is used for training an AI model, and inference with the AI model. Near real-time RIC can obtain network side and / or terminal side information from RAN nodes (e.g., CU, CU-CP, CU-UP, DU, and / or RU) and / or terminals. The information can be used as training data or inference data. Near real-time RIC can deliver inference results to RAN nodes and / or terminals. Inference results can be exchanged between CUs and DUs, and / or between DUs and RUs. For example, near real-time RIC delivers inference results to a DU, which sends them to RUs.

[0071] Non-real-time RIC is also used for model training and inference. For example, it is used for training an AI model, and inference with the AI model. Non-real-time RIC can obtain network side and / or terminal side information from RAN nodes (e.g., CU, CU-CP, CU-UP, DU, and / or RU) and / or terminals. The information can be used as training data or inference data, and inference results can be delivered to RAN nodes and / or terminals. Inference results can be exchanged between CUs and DUs, and / or between DUs and RUs. For example, non-real-time RIC delivers inference results to a DU, which sends them to RUs.

[0072] Near real-time RIC and non-real-time RIC can also be separately configured as a network element. Near real-time RIC and non-real-time RIC can also be part of other devices. For example, near real-time RIC can be configured in a RAN node (e.g., CU, DU), and non-real-time RIC can be configured in an OAM, a cloud server, a core network device, or other network devices.

[0073] In this application, “sending information” can be understood as a device sending information to another device, or a logical module in a device sending information to another logical module in the device. For example, “terminal sending information” can be understood as a terminal sending information to another device (e.g., an access network device), or a logical module 1 in the terminal sending information to a logical module 2 in the terminal.

[0074] In this application, “receiving information” can be understood as a device receiving information from another device, or a logical module in a device receiving information from another logical module in the device. For example, “access network device receiving information” can be understood as an access network device receiving information from another device (e.g., a terminal), or a logical module 1 in the access network device receiving information from a logical module 2 in the access network device.

[0075] In this application, "sending information to (for example, an access network device)" or related illustrations in the drawings can be understood as the destination of the information is the access network device. It can include direct or indirect sending information to the access network device. "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 the source of the information is the terminal, which can include direct or indirect receiving information from the terminal. The information between the source and the destination of the information sending may be necessary processing, such as format change, etc., but the destination can understand the effective information from the source. Similar expressions in this application can be similarly understood, and will not be repeated here.

[0076] The application provides a communication method, which can be applied to the architecture scenarios shown in FIGS. 4-6 in addition to the communication system described above, but is not limited to them. FIG. 4 shows a server-network-terminal architecture scenario, which can be used in a video transmission scenario or an AI service scenario, and the AI service scenario can be a distributed network training, distributed model inference, etc. The network includes a data network (DN) (such as a fixed network), a core network and an access network (AN) of a mobile communication system such as LTE and 5G. The terminal can be various forms of terminals described above, such as a head-mounted extended reality (XR) glasses, a video player, a holographic projector, a mobile phone, a computer, a robot, etc. Here, the details are not described again. The DN is used to provide, for example, operator services, Internet access or third-party services, which includes a server, and the server side is used to realize video source encoding, rendering, etc.

[0077] The core network is used to complete three major functions of registration, connection and session management, as shown in FIG. 4, and mainly includes network exposure function (NEF) network element, policy control function (PCF) network element, application function (AF) network element, access and mobility management function (AMF) network element, session management function module (SMF) network element, user plane function (UPF) network element and the like. Among them, the NEF network element exposes the services and capabilities of the 3GPP network function to the AF network element, and at the same time can also allow the AF network element to provide information to the 3GPP network function, the corresponding interface between the NEF network element and the AF network element is N33 interface; the PCF network element performs policy management of charging policy and QoS policy; the AF network element mainly transmits the demand of the application side to the network side; the AMF network element mainly performs mobility management, access authentication / authorization and the like, in addition, it is also responsible for transmitting user policy between the terminal and the PCF network element; N1 interface is the signaling interface between the terminal and the AMF network element, since the terminal cannot directly interact with the core network, it needs to pass through the RAN to transmit NAS (non-access layer) information; N2 interface is the signaling interface for the AMF network element to request the RAN to allocate resources for the protocol data unit (PDU) session and the like; the SMF network element is used to complete the session management functions of terminal internet protocol (IP) address allocation, UPF selection, charging and quality of service (QoS) policy control and the like; the UPF network element is the interface with the DN, and completes the functions of user plane data forwarding, charging statistics based on session / stream level and bandwidth limitation and the like; N3 interface is the interface between the RAN node and the UPF network element, and is mainly used to transmit the uplink and downlink user plane data between the RAN node and the UPF network element.

[0078] Fig. 5 shows a terminal-network-terminal architecture scenario, which can be used in the tactile internet, in which one terminal is a master domain tactile user and the other terminal is a controlled domain user, such as a remote control robot or a remote operator; the network is as described in Fig. 5, and details are not repeated here. The master domain tactile user receives audio / video feedback signals from the controlled domain user, and the master domain tactile user and the controlled domain user are connected through a two-way communication link on the network with the help of various commands and feedback signals, thereby forming a global control loop. Fig. 6 shows a WiFi architecture scenario, in which a cloud server transmits XR media data or ordinary video to a terminal (such as an XR device) through a fixed network, as well as a WiFi router, a WiFi access point (AP) or a set-top box. The WiFi router, WiFi AP) can transmit information between the terminal through a WiFi link.

[0079] With the rise of large-scale AIGC applications, the massive growth of user business brings severe computing power challenges to central servers. Wireless networks are naturally close to terminals, and distributed learning based on wireless transmission has outstanding value in terms of perception data acquisition, auxiliary training, and auxiliary reasoning. According to relevant estimates, the total computing power of the current base station exceeds 2.2 ETOPS. Considering the growing trend of future wireless network computing power resources, the computing power capabilities, real-time computing power resource states, and other processing resources of the wireless network can fully support the computing power of a large number of terminal users and the central server. ETOPS is the abbreviation of exatera operations per second, which is a unit of measuring computing performance; TOPS is the abbreviation of tera operations per second, which represents the number of floating-point operations that can be performed per second, ETOPS = 10 18 TOPS.

[0080] In distributed computing, different levels of tasks (such as high and low levels of tasks) are divided into multiple computing sub-tasks, which are completed by the same or different computing nodes. The completion time of the task depends on the time when the last computing sub-task is completed. Taking the DNN model computing task as an example, with the continuous development of terminal devices, the terminal itself also has a certain computing capability and can bear a certain neural network calculation. The application server can segment the deep neural network (DNN) model computing task, perform front-end preprocessing and calculation on the terminal, upload the complex calculation part to the cloud application server for calculation and processing, or perform calculation on the part with lower level and lower algorithm requirement by the terminal, and perform processing on the part with higher level and higher algorithm requirement by uploading to the cloud server. Compared with the traditional network directly uploading and processing the original image quantity, the above-mentioned method of segmenting the DNN model computing task, such as extracting image information by the terminal and uploading the extracted intermediate feature information to the network, reduces the amount of data uploaded.

[0081] Therefore, for the method of segmenting the computing task, how the network provides algorithm support to the terminal and the server to alleviate the algorithm tension problem is a problem to be solved.

[0082] The communication method provided in the present application provides an AI priority notification method and related device. The processing priority of the data unit of the AI task is set by the terminal or the server, and the network side allocates processing resources to the data unit according to the processing priority of the data unit, which can improve the utilization rate of the processing resources of the network and alleviate the algorithm tension problem of the terminal or the server.

[0083] For ease of understanding, some concepts related to the present application are introduced. In the present application, the data unit is used for an artificial intelligence (AI) inference task and / or a training task. The inference task refers to adjusting the input of the AI model to obtain the desired output without modifying the AI model. The training task refers to adjusting the input of the AI model and the parameters or weights of the AI model to improve the effect of the model. Optionally, the processing priority can include but is not limited to a calculation priority and / or a transmission priority. The processing priority is used for the allocation of processing resources of the data unit.

[0084] The embodiments of the present application are described below with reference to the accompanying drawings.

[0085] The communication method and related devices are further described below with reference to the drawings. It can be understood that the access network device and the terminal are taken as an example to illustrate the execution subject of the interaction in the present application, but the present application is not limited to the execution subject of the interaction. For example, 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 logical node, a logical module or software capable of implementing all or part of the functions of the access network device; the method performed by the terminal in the present application can also be implemented by a communication / processing module in the terminal 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 core network element in the present application, such as the method performed by the UPF element, can also be implemented by a communication / processing module in the UPF element 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 UPF element.

[0086] FIG. 7 is a flow diagram of a communication method according to an embodiment of the present application. The communication method shown in FIG. 7 takes the architecture scenario shown in FIG. 4 as an example, and the network is taken as an example of the structure of the access network device-core network. In the communication method, the terminal sets the processing priority of the data unit, and the access network device mainly allocates processing resources to the data unit according to the processing priority. Specifically, the communication method includes but is not limited to the following steps:

[0087] S101. The terminal generates first information, and the first information is used to indicate the processing priority of the data unit.

[0088] S102. The terminal sends the first information to the access network device, and correspondingly, the access network device receives the first information.

[0089] In an optional embodiment, the first information is carried in uplink control information (UCI), medium access control-control element (MAC-CE) or radio resource control (RRC) signaling. It can be seen that this embodiment can improve the reliability of the transmission of the processing priority by transmitting the first information through control information or signaling.

[0090] In another alternative implementation, the first information is carried in a data packet, such as a header of the data packet, and the data packet is used to carry the data unit. It can be seen that, in this implementation, the first information is transmitted by the data packet, and thus the data unit and the processing priority are transmitted in the form of the data packet, which can improve the real-time performance and flexibility of setting the processing priority.

[0091] S103. The access network device allocates the processing resource to the data unit according to the processing priority indicated by the first information.

[0092] Optionally, the terminal and the access network device can define the processing priority of the data unit, and indicate the corresponding processing priority by setting the value of the first information. For example, the correspondence between the value of the first information and the processing priority is shown in Table 1, and the processing priority 0 to the processing priority 3 is indicated by 2 bits. If the value of the first information is 00, it indicates that the processing priority indicated by the first information is 0; if the value of the first information is 01, it indicates that the processing priority indicated by the first information is 1; if the value of the first information is 10, it indicates that the processing priority indicated by the first information is 2; and if the value of the first information is 11, it indicates that the processing priority indicated by the first information is 3.

[0093] Table 1: Correspondence between the value of the first information and the processing priority

[0094] In an alternative implementation, the first information is also used to indicate the number of data units corresponding to the processing priority. In this way, the corresponding processing priority can be marked for multiple data units, so that the network side allocates the processing resource to the data unit based on the processing priority corresponding to the data unit. For example, but not limited to, the terminal and the access network device agree that the first part of the bits in the first information is used to indicate the number of data units, and the second part of the bits in the first information is used to indicate the processing priority corresponding to the number of data units. The correspondence between the second part of the bits and the processing priority can be referred to Table 1, which is not described in detail here. For example, the correspondence between the value of the first part of the bits of the first information and the number of data units is shown in Table 2, and the number of data units 1 to 4 is indicated by 2 bits, i.e., the first part of the bits is 2 bits. If the value of the first part of the bits is 00, it indicates that the number of data units corresponding to the processing priority indicated by the second part of the bits is 1; if the value of the first part of the bits is 01, it indicates that the number of data units corresponding to the processing priority indicated by the second part of the bits is 2; if the value of the first part of the bits is 10, it indicates that the number of data units corresponding to the processing priority indicated by the second part of the bits is 3; and if the value of the first part of the bits is 11, it indicates that the number of data units corresponding to the processing priority indicated by the second part of the bits is 4.

[0095] Table 2: Correspondence between the value of the first part of the bits of the first information and the number of data units

[0096] In another optional implementation, the terminal further generates and sends second information, the second information being used to indicate the number of data units, the processing priority of the data units being indicated by the first information corresponding to the data units. In this way, for N data units, N first information can be generated and sent, in one-to-one correspondence with the N data units; or for N data units, M first information can be generated and sent, the N data units and the M first information being in a many-to-one correspondence, wherein the data units with the same processing priority correspond to the same first information. Optionally, the correspondence between the value of the first information and the processing priority can be seen from Table 1, and the value of the second information is equivalent to the first part of bits in the above implementation, i.e., the second information uses 2 bits to represent the number 1 to the number 4 of data units. It should be noted that in this implementation, the number of data units indicated by the second information is the number of data units, one data unit corresponds to one first information, and therefore the number of data units indicated by the second information is equal to the number of first information. For example, assuming that the second information sent by the terminal to the access network device is 10 and the first information is 000110, the access network device receives the first information and the second information and determines that the number of data units of the AI task transmitted is 3, wherein the processing priority of the first data unit is 0, the processing priority of the second data unit is 1, and the processing priority of the third data unit is 2.

[0097] In an optional implementation, the second information can also be carried in the UCI, the MAC-CE or the RRC signaling. It can be seen that this implementation can improve the reliability of the transmission of the number of data units by transmitting the second information through the control information or the signaling.

[0098] The first information and the second information can be carried in the same information or the same signaling and sent together, or the first information and the second information can be carried in different information or signaling and sent separately.

[0099] In another optional implementation, the second information is carried in a data packet, such as the header of the data packet, and the data packet is used to carry the data units of the AI. In this way, the first information and the second information are both sent in the form of data packets, which can improve the flexibility of setting the processing priority and the timeliness of information transmission.

[0100] In an optional implementation, as shown in FIG. 7, the terminal further sends third information to the access network device, the third information being used to request the access network device to detect the processing priority. It can be seen that in this implementation, the terminal can inform the access network device to detect the processing priority through the third information, avoiding the processing load caused by the default continuous detection of the access network device.

[0101] Optionally, the access network device is a base station, and the third information is carried in UCI, MAC-CE or RRC signaling to notify the base station to detect the processing priority, for example, the third information occupies 1 bit.

[0102] In another optional implementation, the third information is sent by an SMF network element to an AMF network element, and the AMF network element notifies the access network device to detect the processing priority. It can be seen that these implementations can avoid the access network device or the core network to continuously monitor whether the data unit is marked with the processing priority, thereby reducing the detection load of the access network device or the core network element.

[0103] In another optional implementation, as shown in FIG. 7, the access network device sends fourth information to the terminal, and the fourth information is used to notify the terminal to generate the first information, so that the terminal generates the first information for indicating the processing priority of the data unit according to the fourth information. It can be seen that in this implementation, the access network device notifies the terminal to generate the first information, that is, to set the processing priority of the data unit, thereby facilitating the access network device to allocate processing resources for the data unit based on the processing priority.

[0104] Optionally, the access network device is a base station, and the fourth information is carried in downlink control information (DCI), MAC-CE or RRC signaling to notify the terminal to generate the first information, that is, to mark the processing priority of the data unit.

[0105] In an optional embodiment, the access network device allocates processing resources for the data unit according to the processing priority indicated by the first information. If the processing resources of the access network device satisfy the required processing resources of the data unit, the access network device allocates the processing resources for the data unit, processes the data unit using the processing resources to obtain a processing result, and returns the processing result to the terminal. If the processing resources of the access network device do not satisfy the required processing resources of the data unit, the access network device sends the data unit and the processing priority of the data unit to the core network, for example, a GTP-U protocol data unit including the data unit and the processing priority of the data unit. Wherein, GTP-U is the abbreviation of general packet radio service tunneling protocol-user plane, and GTP-U protocol is a user data transmission protocol used in GPRS network, which is a protocol for establishing a tunnel in user plane. The core network element assists the access network device or the core network element to process the data unit according to the processing priority to obtain a processing result. Optionally, the core network element also returns the processing result to the terminal. It can be seen that this embodiment can also assist the access network device to complete the processing of the AI task by the core network, improve the utilization rate of the processing resources, and alleviate the problem of tight computing power of the access network device.

[0106] In another embodiment, the operation of allocating processing resources for the data unit mainly by the access network device according to the processing priority in the embodiment described in FIG. 7 is performed by the core network element. For example, in this embodiment, after the access network device determines the processing priority of the data unit, the access network device can send information indicating the processing priority to the UPF network element, and the UPF network element allocates processing resources for the data unit according to the processing priority. This embodiment schedules the processing resources by the core network, which can realize the full utilization of the processing resources of the network and improve the AI service satisfaction of the terminal side.

[0107] In another embodiment, in an optional embodiment, the terminal sends third information to the access network device (such as a base station) before step S101 described in FIG. 7, and the third information is used to request the access network device to monitor the processing priority. In another optional embodiment, the access network device (such as a base station) sends fourth information to the terminal before step S101 described in FIG. 7, and the fourth information is used to notify the terminal to generate the first information, that is, to notify the terminal to mark the processing priority for the data unit. This embodiment can enable the access network device or the core network to allocate processing resources for the data unit according to the processing priority, and improve the utilization rate of the processing resources of the network side.

[0108] In yet another embodiment, the operations performed by the terminal in the embodiment described in FIG. 7 are performed by the server, and the operations performed by the access network device are performed by the UPF network element. That is, in this embodiment, the server sets the processing priority, and the core network schedules processing resources for the data unit according to the processing priority, thereby relieving the server's computing power shortage and improving the network's computing power service capability.

[0109] The embodiments of the present application are further described below in combination with a communication system architecture.

[0110] FIG. 8 is a schematic diagram of another communication method provided by an embodiment of the present application. The embodiment described in FIG. 8 is to transmit instructions to the user plane through the control plane, such as to notify the network side to detect the processing priority. As shown in FIG. 8, the information corresponding to the dashed line indicates that the network element transmits information through the control plane, and the information corresponding to the solid line indicates that the network element transmits information through the user plane. In addition, this embodiment is described by taking an example in which the core network includes a UPF network element, a NEF network element, a PCF network element, an AMF network element, an SMF network element, and an AF network element. Among them, the terminal and the AMF network element can interact through the N1 interface, and the interaction between other network function network elements is similar. For example, the access network device and the AMF network element can interact through the N2 interface, the N3 interface supports the selective activation / deactivation of the user plane connection, so the access network device and the UPF network element can interact through the N3 interface; the SMF network element and the UPF network element interact through the N4 interface, and the UPF network element and the DN (such as an enterprise application server (EAS)) interact through the N6 interface. All NFs in the control plane can interact through a service interface. For example, the NEF network element and other network function network elements can interact through the service interface Nnef. The PCF network element and other network function network elements can interact through the service interface Npcf. The AF network element and other network function network elements can interact through the service interface Naf. The AMF network element and other network function network elements can interact through the service interface Namf. The SMF network element and other network function network elements can interact through the service interface Nsmf.

[0111] The communication method can include but is not limited to the following steps:

[0112] S201. The terminal sends information for notifying the core network element to detect the processing priority to the AMF network element.

[0113] Alternatively, the information sent in step S201 can also be used to inform the core network element to start the processing priority mode, wherein the processing priority mode is a mode in which the core network element detects the processing priority of the data unit. If step S201 is not performed, the core network element can continuously detect the mark of the processing priority of the data unit.

[0114] S202. The SMF network element sends information to the access network device through the AMF network element to inform the access network device to detect the processing priority.

[0115] In step S201, the core network element that informs the core network element to detect the processing priority can be an SMF network element.

[0116] Alternatively, the information sent in step S202 can also be used to inform the access network device to start the processing priority mode, wherein the processing priority mode is a mode in which the access network device detects the processing priority of the data unit. If step S202 is not performed, the access network device can continuously detect the mark of the processing priority of the data unit.

[0117] S203. The terminal sends information to the access network device to indicate the processing priority of the data unit.

[0118] This embodiment is described by taking the information sent in step S203 as an example, which is carried in a data packet. Step S203 can include: the terminal sends a data packet to the access network device, the data packet carries the data unit of the inference task and / or the training task of the AI, and the packet header of the data packet further includes information indicating the processing priority of the data unit. Alternatively, the terminal marks the processing priority in the packet header of the upper layer such as the application layer or the transport layer, such as adding information indicating the processing priority in the packet header of the IP data packet, or marking the priority in the packet header of one picture frame, one video frame, or one input data slice of an AI task.

[0119] The processing priority carried in different data packets can be different. For example, there is a sequence of data units of AI tasks (i.e., inference tasks and / or training tasks of AI) and the processing priorities of data units (such as input data) of different AI tasks are different, the data packet header of the data unit of the AI task is marked with the processing priority, for example, the data unit is a video frame, the third video frame has a higher processing priority than the second video frame, and in combination with the processing priority shown in Table 1, the data packet header of the third video frame is marked with a high processing priority (such as 00), and the processing priority marked in the data packet header of the second video frame can be set to 11, so that the access network device will preferentially execute the AI task corresponding to the third video frame when receiving the AI task execution sequence corresponding to the second and third video frames.

[0120] In another optional implementation, the data packet includes a plurality of data units of AI tasks, as shown in the embodiment of FIG. 7, the information sent by the terminal in S103 is also used to indicate the number of data units corresponding to the processing priority, or the terminal sends information for indicating the number of data units to the access network device in addition to sending information for indicating the processing priority. Optionally, the number of data units can also be referred to as the number of data units or data frames of AI tasks. Optionally, if the terminal does not indicate the number of data units in the data packet or other information, it can be defaulted that all data units of AI tasks of the terminal belong to the same processing priority. Optionally, the information for indicating the processing priority in the data packet header can be a processing priority field, and the information for indicating the number of data units in the data packet can be an AI task data unit number field.

[0121] S204. The access network device determines the processing priority of the data unit and allocates processing resources to the data unit according to the processing priority.

[0122] For example, the access network device detects the information of the processing priority carried in the header of the data packet carrying the data unit of the AI task, and then determines the processing priority of the data unit.

[0123] Optionally, if the processing resources of the access network device are sufficient, the access network device can return the processing result to the terminal after completing the AI task using the data unit; if the processing resources of the access network device are insufficient, the method further includes: the access network device sends the processing priority of the data unit and the data unit to the core network element through the GTP-U header in the PDU set; the core network element can assist the access network device to complete the AI task, or the core network element independently completes the AI task, and then returns the processing result to the terminal.

[0124] It can be seen that in the communication method, the terminal can mark the processing priority of the data unit of the AI task in a data packet or other messages (such as UCI, MAC-CE or RRC signaling). Optionally, the terminal can also send information to the core network element or the access network device to inform the detection of the processing priority. Optionally, the access network device or the core network element can independently or cooperatively process the data unit of the AI task according to the determined processing priority, to realize the arrangement of the overall computing resource and / or transmission resource of the network.

[0125] FIG. 9 is a schematic diagram of another communication method provided by an embodiment of the present application. The communication system architecture example shown in FIG. 9 is the same as that shown in FIG. 8, and the architecture of the communication system will not be described in detail here. In the communication method described in FIG. 9, steps S301 to S302 are the same as steps S201 to S202 in the communication method described in FIG. 8, and will not be described in detail here. Optionally, in the communication method described in FIG. 9, after the SMF network element detects the processing priority of the data unit of the AI task through the AMF network element, the method further includes:

[0126] S303. The SMF network element sends information for informing the UPF network element to detect the processing priority to the UPF network element.

[0127] In addition, in the communication method described in FIG. 9, step S304 is the same as step S203 in FIG. 8, and will not be described in detail here.

[0128] The difference between the communication method described in FIG. 9 and the communication method described in FIG. 8 is that in the communication method described in FIG. 9, the access network device does not need to determine whether the processing resource is sufficient, and after the access network device determines the processing priority of the data unit, the access network device also sends the processing priority of the data unit to the UPF network element, so in FIG. 9, S305. The access network device sends the processing priority of the data unit to the UPF network element. For example, the access network device sends the processing priority of the data unit to the UPF network element through the GTP-U header in the PDU set; or the access network device sends the processing priority to the UPF network element through other messages.

[0129] The communication method described in FIG. 9 further includes the following steps:

[0130] S306. The UPF network element determines the processing priority of the data unit, allocates processing resources to the data unit according to the processing priority, and returns the processing result to the terminal after completing the processing.

[0131] The UPF network element determines the processing priority of the data unit according to the received data packet or information.

[0132] That is, the difference between the communication method described in FIG. 9 and the communication method described in FIG. 8 is that the communication method described in FIG. 9 is scheduling of processing resources by a core network element, such as a UPF network element, based on processing priorities for data units. Thus, full utilization of the processing resources of the network can be achieved, and the AI service satisfaction of the terminal can be improved.

[0133] FIG. 10 is a schematic diagram of another communication method provided by an embodiment of the present application. In the communication system shown in FIG. 10, the core network is exemplified by a NEF network element, a PCF network element, a SMF network element, an AMF network element, and a UPF network element. In the communication method described in FIG. 10, the processing priority of a data unit is marked by a server and sent to an access network device and a core network for allocation of processing resources. The communication method can include, but is not limited to, the following steps:

[0134] S401. The server sends information for informing the UPF network element to detect the processing priority to the UPF network element through N4;

[0135] The step S401 is optional. If the server does not send the information to the UPF network element, the UPF network element can continuously detect the processing priority of the data unit of the AI task. In another optional embodiment, in step S401, the server sends information for informing the UPF network element to detect the processing priority to the UPF network element through N2. As shown in FIG. 10, the server first sends the information to the access network device through N2, and then the access network device sends the information to the UPF network element.

[0136] S402. The server sends information for indicating the processing priority of the data unit to the UPF network element.

[0137] This embodiment is exemplified by the information sent in step S402 being carried in a data packet. Similar to the step S203 described in FIG. 8, the difference is that in this embodiment, the step S402 can include: the server sends a data packet to the UPF network element, the data packet carries the data unit of the inference task and / or the training task of the AI, and the packet header of the data packet further includes information for indicating the processing priority of the data unit. Optionally, the server marks the processing priority in the packet header of the upper layer data packet, such as the real-time transport protocol (RTP) or secure real-time transport protocol (SRTP) data packet.

[0138] S403. The UPF network element determines the processing priority of the data unit, allocates processing resources to the data unit according to the processing priority, and returns the processing result to the server after the processing is completed.

[0139] Optionally, if the processing resources of the UPF network element are sufficient, step S403 is performed; if the processing resources of the UPF network element are insufficient, step S404 is performed.

[0140] S404. The UPF network element sends the processing priority of the data unit and the data unit to the access network device.

[0141] Correspondingly, the access network device returns the processing result to the UPF network element after determining the processing priority of the data unit. The UPF network element returns the processing result to the server.

[0142] It can be seen that the communication method described in FIG. 10 is different from the above-mentioned embodiments in that the server sets the processing priority of the data unit, and the core network allocates processing resources to the data unit according to the processing priority, so as to realize full utilization of the processing resources of the network, alleviate the problem of shortage of processing resources of the server, and improve the resource service capability of the network.

[0143] FIG. 11 shows a possible exemplary block diagram of a communication device involved in the embodiments of the present application. As shown in FIG. 11, the communication device can include modules or units for implementing the corresponding modules or units of the above-mentioned method embodiments. In one possible design, the communication device includes a processing unit 501 and a communication unit 502. Optionally, the communication device can further include a storage unit 503 for storing device program code and / or data.

[0144] The communication device can be a terminal-side device in the above-mentioned embodiments, for example, a terminal or a communication module in the terminal, or a circuit or chip responsible for the communication function in the terminal.

[0145] For example, in one embodiment, the processing unit 501 is configured to generate first information, the first information being used to indicate a processing priority of a data unit, the processing priority being used for allocation of processing resources of the data unit, and the data unit being used for an inference task and / or a training task of artificial intelligence (AI); and the communication unit 502 is configured to send the first information.

[0146] In one possible design, the first information is further used to indicate a quantity of data units corresponding to the processing priority.

[0147] In one possible design, the first information is carried in a data packet, and the data packet is used to carry the data unit.

[0148] In a possible design, the communication unit 502 is further configured to send third information, where the third information is used to request the network side to detect the processing priority.

[0149] In a possible design, the communication unit 502 is further configured to receive fourth information. Correspondingly, the processing unit 501 is configured to generate the first information by generating the first information based on the fourth information.

[0150] In a possible design, when the communication apparatus is a terminal or a communication module in a terminal, the function of the processing unit 501 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 502 can be implemented by a transceiver circuit.

[0151] In a possible design, when the communication apparatus 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 501 can be implemented by a circuit system including one or more processors or processor cores in the chip. The function of the communication unit 502 can be implemented by an interface circuit or a data transceiver circuit on the chip.

[0152] In a possible design, when the communication apparatus is a terminal or a processing module in a terminal, the function of the processing unit 501 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 502 can be implemented by a transceiver circuit.

[0153] In a possible design, when the communication apparatus 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 501 can be implemented by a circuit system including one or more processors or processor cores in the chip. The function of the communication unit 502 can be implemented by an interface circuit or a data transceiver circuit on the chip.

[0154] The communication apparatus can be a network side apparatus in the embodiments, such as a core network element (e.g., a UPF network element) or an access network device.

[0155] For example, in an embodiment, the communication apparatus can be an access network device in the embodiments.

[0156] The communication unit 502 is configured to receive and detect a processing priority of a data unit of an AI task.

[0157] The processing unit 501 is further configured to allocate the processing resource to the data unit according to the processing priority.

[0158] In a possible design, the first information is further used for indicating a quantity of data units corresponding to the processing priority.

[0159] In a possible design, the communication unit 502 is further configured to receive second information, where the second information is used for indicating the quantity of data units, and the processing priority of the data unit is indicated by the first information corresponding to the data unit.

[0160] In a possible design, the communication unit 502 is further configured to receive third information, where the third information is used for requesting the network side to detect the processing priority.

[0161] In a possible design, the communication unit 502 is further configured to further send fourth information, where the fourth information is used for notifying the terminal or the server to generate the first information.

[0162] In a possible design, if the processing resource allocated to the data unit does not meet a preset condition, the communication unit 502 is further configured to send, to a core network network element, a GTP-U protocol data unit, where the GTP-U protocol data unit includes the data unit of the AI task carried by the GTP-U protocol data unit and the processing priority of the data unit.

[0163] It can be understood that the division of the units in the apparatus described above is a logical function division, one function unit can be used for one function, or two or more functions can be integrated into one function unit. In actual implementation, all or part of the units can be integrated into one physical entity, or can be distributed on different physical entities. In addition, the function units described above can be implemented in the form of hardware, or in the form of software, or in the form of combination of hardware and software. Whether a certain function is implemented in the form of hardware or software depends on the specific application and design constraints of the technical solution. 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.

[0164] 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, for example: 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.

[0165] In one example, the storage unit 503 can include random access memory, flash memory, read only memory, programmable read only memory, electrically erasable programmable memory, and / or registers, etc.

[0166] FIG. 12 is a structure diagram of a terminal according to an embodiment of the present application, which can correspond to the terminal shown in FIGS. 1 to 10, and is used to implement the operation of the terminal in the above embodiments. As shown in FIG. 12, the terminal includes one or more antennas 610, a radio frequency processing system 620, and a processor system 630.

[0167] In the downlink or sidelink direction, the radio frequency processing system 620 receives radio frequency signals through the antenna 610, and sends the signals after radio frequency processing to the processor system 630 for further processing. In the uplink or sidelink direction, the processor system 630 performs signal processing on the information at the terminal side, and sends the signal to the radio frequency processing system 620, which performs radio frequency processing on the signal and transmits it through the antenna 610.

[0168] In one example, the radio frequency processing system 620, which serves as a communication interface for the terminal to communicate with the outside, can include a radio frequency front end 621 (RFFE) and a radio frequency transceiver 622. The RFFE 621 is mainly used for one or more of shaping, passband selection, or gain processing of radio frequency (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 621 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 622 is used to process RF signals received by the RFFE 621 into baseband / intermediate frequency signals for further processing by the processor system 630, and to process baseband / intermediate frequency signals provided by the processor system 630 into RF signals for transmission to the RFFE 621. The baseband / intermediate frequency signals transmitted between the radio frequency transceiver 622 and the processor system 630 can be digital signals or analog signals. The radio frequency transceiver 622 can be implemented by one or more chips, which are commonly referred to as radio frequency integrated circuits (RFICs).

[0169] In one example, the processor system 630 can include one or more processors for processing signals and executing one or more communication protocols. Optionally, the processor system 630 can further include a memory 636. In one example, the one or more processors include at least one baseband processor 631 (also referred to as a modem processor). The memory 636 is used to store data and / or computer program instructions. Optionally, the processor system 630 can further include one or more application processors 632 for implementing processing of the terminal operating system and the application layer. The application processor 632 can include a GPU, for example. Optionally, the processor system 630 can further include one or more of a voice subsystem 633, a multimedia subsystem 634, or an interface circuit 635. The voice subsystem 633 is used to process voice signals, the multimedia subsystem 634 is used to process multimedia-related operations such as video encoding and decoding, image processing, etc., and the interface circuit 635 is used to implement communication with other terminal components such as the display 640, the input device 650, the memory 660, etc. The above-mentioned components in the processor system 630 can communicate with each other through a bus or a communication interface circuit.

[0170] In one example, the processor system 630 can be packaged as one processor chip, such as a SoC chip or a SIP chip. In one example, the processor system 630 can be a system composed of multiple chips, for example, the baseband processor 631 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.

[0171] In one example, the memory 636 can be an on-chip memory, i.e., located on the chip of the processor system 630. In one example, the memory 660 can be an off-chip memory, i.e., located off the chip of the processor system 630.

[0172] In one example, the baseband processor 631 can include one or more processor cores 6311 and interface circuitry 6314. The one or more processor cores 6311 are configured to process signals and perform one or more communication protocols. Optionally, the baseband processor 631 can further include a memory 6312 configured to store at least part of corresponding computer program instructions and / or data. In one example, the one or more processor cores 6311 implement the relevant operations (such as generating and sending the first information) in the above method embodiments by executing the computer program instructions stored in the memory 6312. In this application, the memory 6312 configured to store corresponding computer program instructions and / or data can mean that the memory 6312 is configured to store all corresponding computer program instructions and / or data for execution by the processor core 6311; or can mean that the memory 6312 is configured to store part of corresponding computer program instructions and / or data, which includes computer program instructions and / or data currently required for execution by the processor core 6311, and the memory 6312 can store different parts of computer program instructions and / or data for execution by the processor core 6311 multiple times to implement the relevant operations in the above method embodiments. The interface circuitry 6314 serves as a communication interface to enable communication with other components, such as transmitting signals with the radio frequency processing system 620, communicating with other subsystems and related components of the processor system 630 through a bus, such as transmitting data control signals with the application processor 632, and transmitting data or computer program instructions with the memory 636 or the memory 660. Optionally, to reduce the load of the processor core, the baseband signal processing circuitry 6313 can be provided to implement at least part of the processing of the baseband signals, including one or more of demodulation, modulation, encoding or decoding of the signals.

[0173] 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).

[0174] The above-mentioned memory can include one or more of the following storage media: random access memory (RAM), static RAM (SRAM), dynamic random access memory (DRAM), phase-change memory (PCM), resistive random access memory (RERAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), cache, register, read-only memory (ROM), flash memory, erasable programmable read-only memory (EPROM), hard disk, etc. In one example, 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 660 (e.g., one or more of ROM, flash memory, EPROM, or hard disk). During terminal operation, the corresponding computer program instructions can be partially or entirely loaded onto a memory with faster transmission speed than the processor, such as at least part of the above-mentioned memory 636 and / or memory 6312 (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.

[0175] In one example, the radio frequency transceiver 622 and the radio frequency front end 621 can also be packaged in one chip. In one example, the radio frequency transceiver 622, the radio frequency front end 621, and the baseband processor 631 can also be packaged in one chip.

[0176] The terms "system" and "network" in the embodiments of the present application can be used interchangeably. "At least one" means one or more, and "multiple" means two or more. The "and / or" describes the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B, which can represent the cases of A alone, A and B together, and B alone, where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects before and after it. "At least one of the following" or similar expressions means any combination of these items, including any combination of single or multiple items. For example, "at least one of A, B, or C" includes A, B, C, AB, AC, BC, or ABC, and "at least one of A, B, and C" can also be understood to include A, B, C, AB, AC, BC, or ABC. In addition, unless otherwise specified, the ordinal numbers "first", "second", etc. mentioned in the embodiments of the present application are used to distinguish a plurality of objects, and are not used to limit the order, time sequence, priority or importance of the plurality of objects.

[0177] Those skilled in the art should 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 an entirely hardware embodiment, an entirely 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.

[0178] The present application is described with reference to flowcharts and / or block diagrams according to the methods, devices (systems), and computer program products of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing apparatus produce the means for implementing the functions specified in one or more flows in the flowcharts and / or one or more blocks in the block diagrams.

[0179] These computer program instructions can also be stored in a computer-readable storage medium that can direct the computer or other programmable data processing apparatus to work in a specific manner, so that the instructions stored in the computer-readable storage medium produce a product including instruction means, which implements the functions specified in one or more flows in the flowcharts and / or one or more blocks in the block diagrams.

[0180] These computer program instructions can also be loaded into a computer or other programmable data processing devices, so that a series of operational steps are performed on the computer or other programmable devices to generate computer-implemented processes, so that the instructions executed on the computer or other programmable devices provide steps for implementing the functions specified in one or more flows in the flowchart and / or one or more blocks in the block diagram.

[0181] Obviously, various modifications and changes can be made to the present application by those skilled in the art without departing from the scope of the present application. Thus, it is intended that the present application embrace all such modifications and changes and, accordingly, the application is not to be limited by the above-described one or more embodiments.

Claims

1. A communication method characterized by comprising: The method comprises: generating first information, the first information being used to indicate a processing priority of a data unit, the processing priority being used for allocation of a processing resource of the data unit; the data unit being used for an inference task and / or a training task of artificial intelligence (AI); sending the first information.

2. The method of claim 1, wherein the first information is further used to indicate a quantity of the data units corresponding to the processing priority.

3. The method of claim 1 or 2, wherein the first information is carried in a data packet, the data packet being used to carry the data unit.

4. The method according to any one of claims 1 to 3, characterized in that, The method further comprises: sending third information, the third information being used to request detection of the processing priority by a network side.

5. The method according to any one of claims 1 to 4, characterized in that, The method further comprises: receiving fourth information; The generating of the first information comprises: generating the first information based on the fourth information.

6. A communication device, characterized by comprise: a processing unit configured to generate first information, the first information being used to indicate a processing priority of a data unit, the processing priority being used for allocation of a processing resource of the data unit; the data unit being used for an inference task and / or a training task of artificial intelligence (AI); a communication unit configured to send the first information.

7. The apparatus of claim 6, wherein the first information is further used to indicate a quantity of the data units corresponding to the processing priority.

8. The apparatus of claim 6 or 7, wherein the first information is carried in a data packet, the data packet comprising the data unit.

9. The apparatus of any one of claims 6 to 8, wherein the communication unit is further configured to send third information, the third information being used to request detection of the processing priority by a network side.

10. The apparatus of any one of claims 6 to 9, wherein the communication unit is further configured to receive fourth information; the processing unit generates the first information by: generating the first information based on the fourth information.

11. A communications device, characterized by comprise one or more processors coupled with one or more memories, the one or more memories being configured to store instructions that, when executed by the processors, cause the apparatus to implement the method of any one of claims 1 to 5.

12. 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 1 to 5 to be performed.

13. A computer program product, characterised in that, The computer program product comprises computer program code, which, when executed, causes the method of any one of claims 1 to 5 to be performed.

14. A communications device, characterized by comprise units for performing the method of any one of claims 1 to 5.

Images