Communication method, apparatus, computer readable storage medium and program product

Abstract

Embodiments of the present disclosure provide a communication method, apparatus, system, computer readable storage medium and computer program product. In the communication method, a first device generates category information of a first instruction, the category information being used to indicate a data amount of first data corresponding to the first instruction and / or an arrival time of the first data. The first device transmits the category information. Based on receiving the category information, a second device performs prediction on first data related information corresponding to the first instruction. In this way, the second device can obtain the category information of the uplink / downlink instruction generated at the first device, so that the network can perceive the corresponding downlink / uplink service demand, dynamically adjust the air interface resource allocation strategy, and improve the service quality of data transmission.

Description

Technical Field

[0001] This disclosure relates to the field of communications, and more specifically to a communication method, apparatus, computer-readable storage medium, and computer program product. Background Technology

[0002] In wireless communication systems, network-side data transmission typically employs a best-effort transmission guarantee mechanism, meaning that data packets are transmitted as quickly as possible upon arrival, and discarded if transmission is impossible. However, in certain communication scenarios (e.g., for video data communication, when the source uses variable bit rate (VBR) encoding), data packet size can fluctuate drastically. On one hand, when the data volume increases, due to limited air interface resources and the need to serve multiple users simultaneously, drastic changes in data packet size may prevent the limited air interface resources from providing reliable service to multiple users at the same time, thus reducing the resource utilization of the communication system. On the other hand, when the data volume decreases, the previously allocated air interface resources may be wasted, also reducing the resource utilization of the communication system. In summary, regardless of whether the data volume increases or decreases, drastic changes in data packet size can lead to a significant reduction in the resource utilization of the communication system. Summary of the Invention

[0003] The embodiments of this disclosure provide a communication method, apparatus, system, computer-readable storage medium, and computer program product. The technical solution improves system resource utilization by reporting data volume-related information corresponding to user operation instructions, enabling the network side to dynamically optimize and schedule air interface resources based on this information.

[0004] Firstly, embodiments of this application provide a communication method that can be applied to a terminal side, such as a terminal or a communication module and / or computing module within the terminal, or circuits or chips in the terminal responsible for communication functions (such as a modem chip, also known as a baseband chip, or a system-on-chip (SoC) chip containing a modem core, or a system-in-package (SIP) chip), or circuits or chips in the terminal responsible for communication and / or computing functions (such as a graphics processing unit (GPU), a neural processing unit (NPU), an artificial intelligence (AI) processor, or an application-specific integrated circuit (ASIC)), or logic nodes, logic modules, or software capable of implementing all or part of the terminal's functions. Taking the application of this method to a terminal as an example, in this method, the terminal generates category information for a first instruction, which is used to indicate the amount of data and / or the arrival time of the first data corresponding to the first instruction. In some implementations, the aforementioned "instruction" can be implicit, meaning that network-side elements (e.g., radio access network (RAN) nodes such as base stations, evolved NodeBs (eNodeBs or eNBs), next-generation NodeBs (eNodeBs or gNBs), etc.; or core network elements such as user plane functions (UPFs), network data analytics functions (NWDAFs), session management functions (SMFs), or other network elements) can determine the data volume and / or arrival time of the first data based on this category information. The terminal transmits the aforementioned category information. For example, this category information can be encapsulated in Packet Data Convergence Protocol (PDCP) packets or Radio Link Control (RLC) packets. Specifically, this category information can be encapsulated in the header portion of PDCP or RLC packets, or it can be encapsulated in the payload portion of PDCP or RLC packets.In other implementations, this category information can also be sent via the media access control (MAC) control element (MAC CE). Using this method, the terminal sends category information from generated uplink commands (e.g., the first command mentioned above), enabling the network side to perceive corresponding downlink service demands and dynamically adjust air interface resource allocation strategies. For example, for high data volumes or bursty services, RAN nodes can reserve frequency / time domain resources in advance, activate pre-scheduling mechanisms, or enable multi-carrier functionality in advance, thereby helping to reduce transmission delays caused by traditional passive responses.

[0005] In some implementations, this type of information can also be sent via dedicated tunnels, dedicated bearers, or dedicated quality of service (QoS) streams. For example, this type of information can be sent via dedicated tunnels, dedicated bearers, or dedicated QoS streams between core network elements and terminals. It can also be sent via dedicated tunnels, dedicated bearers, or dedicated QoS streams between RAN nodes and terminals. This approach reduces resource contention and interference in signaling transmission, lowers latency and packet loss, and improves the stability of information transmission under high load. Furthermore, it provides multiple transmission paths between core network elements / RAN nodes and terminals, allowing for flexible configuration as needed, improving network scalability and adaptability, and meeting the transmission requirements of various scenarios.

[0006] In some implementations, the aforementioned category information may include a first index. In these implementations, the first index may correspond to the data volume of the first data and / or the arrival time of the first data. In this way, by utilizing lightweight indexes (such as the first index mentioned above), the network side can save signaling overhead while achieving fast matching of pre-configured resources.

[0007] In some implementations, a first association exists between the first instruction and the information of that category. This first association can be pre-configured (or aligned) on both the terminal and the network side. Specifically, in some implementations, the terminal can receive first configuration information indicating the first association. In other implementations, the terminal can send second configuration information indicating the first association. For example, the terminal can determine the first association based on an AI model. In this case, the sent second configuration information can also be used to indicate the AI ​​model. In this way, the terminal associates instructions with service characteristics (e.g., data volume / latency requirements) through a local AI model or a network-aligned association (such as the first association), providing a basis for the network side to predict data volume, enabling more accurate data volume predictions, thereby matching more appropriate resource allocation and improving resource utilization.

[0008] In some implementations, the aforementioned category information may be the same as the aforementioned first instruction. The first instruction itself can indicate the data volume and / or arrival time of the aforementioned first data. In this case, the RAN node / core network element can determine the data volume and / or arrival time of the first data based on the received first instruction. In this way, by sending uplink instructions (e.g., the aforementioned first instruction), the terminal enables the network side to perceive the corresponding downlink service requirements and dynamically adjust the air interface resource allocation strategy.

[0009] Furthermore, the method in the first aspect can also be applied to the server side, such as to AI modules within a server, components within a server (e.g., processors, SoC chips, or dedicated modules), or logical processing units implemented with software or virtualization functions. Taking the application of this method to a server as an example, the server receives task request information from a terminal, such as model inference requests or data preprocessing instructions; based on this task request information, it generates category information for a first instruction (e.g., a downlink service instruction). The server sends this category information to the network side (e.g., RAN nodes, such as eNBs, gNBs, etc.; or core network elements, such as UPFs, NWDAFs, SMFs, or other network elements). In some implementations, this category information can also be sent via dedicated tunnels, dedicated bearers, or QoS flows. For example, this category information can be sent via dedicated tunnels, dedicated bearers, or dedicated QoS flows between core network elements and the server. This category information can also be sent via dedicated tunnels, dedicated bearers, or dedicated QoS flows between RAN nodes and the server. This approach reduces resource contention and interference in signaling transmission, lowers latency and packet loss, and improves the stability of information transmission under high load. It also allows for flexible configuration of transmission paths between core network elements / RAN nodes and servers, enhancing network scalability and adaptability to meet diverse transmission needs. Other specific details (such as signaling transmission format and association alignment mechanisms) can be found in the aforementioned description of the terminal-side implementation and will not be repeated here. Using this method, by obtaining the category information (e.g., index, data volume, arrival time) of downlink commands generated by the server, the network side can perceive the corresponding uplink service requirements, dynamically adjust air interface resource allocation strategies, and reduce transmission latency.

[0010] Secondly, this method can be applied to the network side, such as RAN nodes, modules within RAN nodes (e.g., circuits, chips, or chip systems), or logical nodes, logical modules, or software that can implement all or part of the RAN node's functions, or circuits or chips (e.g., GPUs, AI processors, NPUs, or ASICs) within RAN nodes responsible for communication and / or computing functions. Taking the application of this method to RAN nodes as an example, in this method, the RAN node receives category information of the first instruction from the terminal side or server side. This category information is used to indicate the data volume and / or arrival time of the first data corresponding to the first instruction. In some implementations, the aforementioned "indication" can be implicit, meaning that the RAN node can determine the data volume and / or arrival time of the first data based on this category information. For example, the RAN node can obtain this category information by parsing PDCP / RLC packets (specifically, the header or payload portion of the PDCP / RLC packet) or MAC CE. Based on this category information, the RAN node performs prediction of information related to the first data corresponding to the first instruction. Using this method, when the RAN node supports service prediction, it can perceive the corresponding downlink / uplink service demand and dynamically adjust its air interface resource allocation strategy by receiving category information (such as index, data volume, and arrival time) from uplink / downlink commands (e.g., the first command mentioned above) from terminals and / or servers. For example, for high data volume or bursty services, the RAN node can reserve frequency / time domain resources in advance, activate pre-scheduling mechanisms, or enable multi-carriers in advance, thereby helping to reduce the transmission delay caused by traditional passive response.

[0011] In some implementations, this type of information can also be received via dedicated tunnels, dedicated bearers, or dedicated QoS streams. For example, this type of information can be received via dedicated tunnels, dedicated bearers, or dedicated QoS streams between RAN nodes and terminals / servers. This approach reduces resource contention and interference in signaling transmission, lowers latency and packet loss, and improves the stability of information transmission under high load. Furthermore, it provides multiple transmission paths between RAN nodes and terminals / servers, allowing for flexible configuration as needed, improving network scalability and adaptability, and meeting the transmission requirements of various scenarios.

[0012] In some implementations, the aforementioned category information may include a first index. In these implementations, the first index may correspond to the data volume of the first data and / or the arrival time of the first data. In this way, by utilizing lightweight indexes (such as the first index mentioned above), the network side can save signaling overhead while achieving fast matching of pre-configured resources.

[0013] In some implementations, a first association exists between the first instruction and the information of that category. This first association can be pre-configured (or aligned) on both the terminal and the network side. Specifically, in some implementations, the RAN node can send first configuration information to the terminal, which indicates the first association. In other implementations, the RAN node can receive second configuration information from the terminal, which indicates the first association. In some implementations, the second configuration information can also indicate the AI ​​model used to determine the first association. In this way, the RAN node associates instructions with service characteristics (e.g., data volume / latency requirements) through a local AI model or an association aligned with the terminal (such as the first association), providing a basis for the RAN node to predict data volume, enabling more accurate data volume predictions, thereby matching more appropriate resource allocation and improving resource utilization.

[0014] In some implementations, the aforementioned category information may be the same as the aforementioned first instruction. The first instruction itself can indicate the data volume and / or arrival time of the aforementioned first data. In this case, the RAN node can determine the data volume and / or arrival time of the first data based on the received first instruction. In this way, when the RAN node supports service prediction, by receiving uplink / downlink instructions (e.g., the aforementioned first instruction) from terminals and / or servers, the RAN node can perceive the corresponding downlink / uplink service demand and dynamically adjust the air interface resource allocation strategy.

[0015] Furthermore, the second approach can also be applied to core network elements (e.g., UPF, NWDAF, SMF, and potentially new network elements in future communication systems), or components within the device (e.g., processors, chips, or chip systems), or logical modules or software capable of implementing all or part of the device's functions. Taking the application of this method to a core network element as an example, the core network element receives the aforementioned category information from the RAN node. Specifically, the core network element parses the General Packet Radio Service (GPRS) Tunneling Protocol-User Plane (GTP-U) data packets (specifically, the header or payload portion of the GTP-U data packets) received from the RAN node to obtain the category information of the first instruction. Based on this category information, the core network element performs a prediction of the first data-related information corresponding to the first instruction and sends the predicted result (e.g., via GTP-U data packets) to the RAN node. Using this method, when core network elements support service prediction, they can perceive corresponding downlink / uplink service demands by receiving category information (e.g., index, data volume, arrival time, etc.) from uplink / downlink commands (e.g., the first command mentioned above) from terminals and / or servers. This provides strategies for dynamically adjusting air interface resource allocation at the RAN node. For example, for high data volume or bursty services, the RAN node can reserve frequency / time domain resources in advance, activate pre-scheduling mechanisms, or enable multi-carriers in advance, thereby helping to reduce transmission delays caused by traditional passive responses.

[0016] In some implementations, this type of information can be received via dedicated tunnels, dedicated bearers, or dedicated QoS streams. For example, this type of information can be received via dedicated tunnels, dedicated bearers, or dedicated QoS streams between core network elements and terminals / servers. This approach reduces resource contention and interference in signaling transmission, lowers latency and packet loss, and improves the stability of information transmission under high load. Furthermore, it provides multiple transmission paths between core network elements and terminals / servers, allowing for flexible configuration as needed, improving network scalability and adaptability, and meeting the transmission requirements of various scenarios. Other specific details (such as association alignment mechanisms) can be found in the aforementioned description of the RAN node-side implementation, and will not be repeated here.

[0017] Thirdly, this method can be applied to the network side, such as RAN nodes, modules within RAN nodes (e.g., circuits, chips, or chip systems), or logical nodes, logical modules, or software that can implement all or part of the RAN node's functions, or circuits or chips (e.g., GPUs, AI processors, NPUs, or ASICs) within RAN nodes responsible for communication and / or computing functions. Taking the application of this method to RAN nodes as an example, in this method, the RAN node receives the aforementioned category information from the terminal side or server side of the first instruction and sends this category information to core network elements (e.g., UPF, NWDAF, SMF, or other network elements). Specifically, the RAN node can obtain this category information by parsing PDCP / RLC data packets (specifically, the header or payload of the PDCP / RLC data packet) or MAC CE from the terminal side, encapsulates this category information in a GTP-U data packet, and sends it to the core network element. Specifically, this category information can be encapsulated in the header or payload of a GTP-U data packet and sent to the core network element. In this way, when the core network element supports service prediction, the RAN node can send the instruction classification information from the terminal or server to the core network element through the above signaling transmission mechanism, so that the core network element can perform service prediction.

[0018] Furthermore, the RAN node also receives prediction results related to the first data corresponding to the first instruction from the core network elements. These prediction results can be obtained, for example, by parsing GTP-U data packets received from the core network elements. In this way, by utilizing the received prediction results, the RAN node can dynamically optimize resource scheduling, thereby improving system resource utilization.

[0019] Fourthly, this application provides a communication device that has the functions of the first aspect described above. For example, the communication device includes modules, units, or means that perform the operations involved in the first aspect. These modules, units, or means can be implemented by software, hardware, or a combination of software and hardware.

[0020] Fifthly, this application provides a communication device that has the functions of the second aspect above. For example, the communication device includes a module, unit, or means for performing the operations involved in the second aspect above. The module, unit, or means can be implemented by software, hardware, or a combination of software and hardware.

[0021] Sixthly, this application provides a communication device that has the functions of the third aspect above. For example, the communication device includes a module, unit, or means for performing the operations involved in the third aspect above. The module, unit, or means can be implemented by software, hardware, or a combination of software and hardware.

[0022] In a seventh aspect, this application provides a communication device including an interface circuit and one or more processors. The one or more processors are coupled to a memory. The memory stores part or all of the necessary computer program or instructions for implementing the functions described in the first aspect. The one or more processors are executable to carry out the computer program or instructions, causing the communication device to implement the methods in any possible design or implementation of the first aspect. The interface circuit is used to implement the communication functions within the communication device and / or the communication functions between the communication device and other devices or components.

[0023] In one possible design, the processor is used to communicate with other devices or components through the interface circuit.

[0024] In one possible design, the communication device may also include the memory.

[0025] The aforementioned communication device may be a terminal, or a communication and / or computing module within a terminal, or a chip within a terminal responsible for communication functions such as a modem chip (also known as a baseband chip) or a SoC or SIP chip containing a modem module, or a circuit or chip within a terminal responsible for communication and / or computing functions (such as a GPU, AI processor, NPU, or ASIC), or a logical node or logical module capable of implementing all or part of the terminal's functions. In some implementations, the aforementioned communication device may be an AI module in a server, a component in a server (e.g., a processor, SoC chip, or dedicated module), or a logical processing unit implemented with software or virtualization functions.

[0026] Eighthly, this application provides a communication device including an interface circuit and one or more processors. The one or more processors are coupled to a memory. The memory stores part or all of the necessary computer program or instructions for implementing the functions described in the second aspect above. The one or more processors are executable to carry out the computer program or instructions, causing the communication device to implement the methods in any possible design or implementation of the second aspect above. The interface circuit is used to implement the communication functions within the communication device and / or the communication functions between the communication device and other devices or components.

[0027] In one possible design, the processor is used to communicate with other devices or components through the interface circuit.

[0028] In one possible design, the communication device may also include the memory.

[0029] The aforementioned communication device may be a RAN node, or a module within a RAN node (e.g., a circuit, chip, or chip system), or a circuit or chip within a RAN node responsible for communication and / or computing functions (e.g., a GPU, AI processor, NPU, or ASIC), or a logical node or logical module capable of implementing all or part of the RAN node's functions. In some implementations, the aforementioned communication device may be a core network element (e.g., UPF, NWDAF, SMF, or other various network elements), or a component within the device (e.g., a processor, chip, or chip system), or it may be a logical module or software capable of implementing all or part of the device's functions.

[0030] Ninthly, this application provides a communication device including an interface circuit and one or more processors. The one or more processors are coupled to a memory. The memory stores part or all of the computer program or instructions necessary to implement the functions described in the second aspect above. The one or more processors are executable to carry out the computer program or instructions, causing the communication device to implement the methods in any possible design or implementation of the second aspect above. The interface circuit is used to implement the communication functions within the communication device and / or the communication functions between the communication device and other devices or components.

[0031] In one possible design, the processor is used to communicate with other devices or components through the interface circuit.

[0032] In one possible design, the communication device may also include the memory.

[0033] The aforementioned communication device may be a RAN node, or a module (e.g., a circuit, chip, or chip system) within a RAN node, or a circuit or chip (e.g., a GPU, AI processor, NPU, or ASIC) within a RAN node responsible for communication and / or computing functions, or a logical node or logical module capable of implementing all or part of the functions of a RAN node.

[0034] In a tenth aspect, this application provides a communication system comprising a terminal or server for performing the first aspect, a RAN node for performing the second or third aspect, and a core network element for performing the second aspect.

[0035] Eleventhly, this application provides a computer-readable storage medium storing computer-readable instructions, which, when read and executed by a computer, cause the computer to perform any of the possible designs in the first to third aspects described above.

[0036] In a twelfth aspect, this application provides a computer program product that, when read and executed by a computer, causes the computer to perform any of the possible designs in the first to third aspects described above. Attached Figure Description

[0037] Figure 1A A schematic diagram of a communication system according to some embodiments of the present disclosure is shown.

[0038] Figure 1B A schematic diagram of the deployment of an AI module in a communication system is shown.

[0039] Figure 1C This is a schematic diagram of a possible application framework in a communication system.

[0040] Figure 2 and Figure 3 A schematic diagram of the communication flow of some embodiments of this disclosure is shown.

[0041] Figure 4 A possible exemplary block diagram of the communication device involved in the embodiments of this application is shown.

[0042] Figure 5 A schematic diagram of the structure of a terminal provided in an embodiment of this application is shown. Detailed Implementation

[0043] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that embodiments of this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0044] Figure 1A A schematic diagram of a communication system according to some embodiments of this disclosure is shown. For example... Figure 1A As shown, the communication system 10 includes a radio access network (RAN) 100, a core network (CN) 200, and an open cloud (O-cloud) platform 300. RAN 100 includes at least one RAN node (e.g., Figure 1A110a and 110b, collectively referred to as RAN node 110) and at least one terminal (such as Figure 1A 120a-120j in RAN 100 are collectively referred to as Terminal 120. RAN 100 may also include other RAN nodes, such as wireless relay equipment and / or wireless backhaul equipment. Figure 1A (Not shown in the image). Terminal 120 is wirelessly connected to RAN node 110. RAN node 110 is wirelessly or wired connected to core network 200. The core network elements in core network 200 and RAN node 110 in RAN 100 can be different physical devices, or they can be the same physical device integrating core network logical functions and radio access network logical functions. Core network 200 can include multiple core network elements 201, such as user plane function (UPF), network data analytics function (NWDAF), session management function (SMF), and new network elements that may appear in future communication systems. In addition, RAN 100 and core network 200 can also be connected to O-cloud 300 wirelessly or wiredly. O-cloud 300 can include multiple servers 301 for different functions, such as servers for AI inference and / or training.

[0045] RAN 100 can be a cellular system related to the 3rd Generation Partnership Project (3GPP), such as 4G, 5G mobile communication systems, or future-oriented evolution systems. RAN 100 can also be an open RAN (O-RAN or ORAN), a cloud RAN (CRAN), a virtualized RAN (vRAN), an artificial intelligence radio access network (AI RAN), or a wireless fidelity (WiFi) system. RAN 100 can also be a communication system that integrates two or more of the above systems.

[0046] RAN node 110, sometimes also referred to as RAN node, RAN entity, or access node, constitutes part of the communication system and assists terminals in achieving wireless access. Multiple RAN nodes 110 in communication system 10 can be of the same type or different types. In some scenarios, the roles of RAN node 110 and terminal 120 are relative, for example... Figure 1A Network element 120i can be a helicopter or a drone, and it can be configured as a mobile base station. For terminals 120j that access RAN 100 through network element 120i, network element 120i is a base station; however, for base station 110a, network element 120i is a terminal. RAN node 110 and terminal 120 are sometimes referred to as communication devices, for example... Figure 1A Network elements 110a and 110b can be understood as communication devices with base station functions, while network elements 120a-120j can be understood as communication devices with terminal functions.

[0047] In one possible scenario, the RAN node can be a base station, eNB, gNB, access point (AP), transmission reception point (TRP), a base station in a future mobile communication system, or an access node in a WiFi system, etc. Figure 1A 110a), micro base stations or indoor stations (such as Figure 1A The RAN node can be a relay node or donor node (as described in section 110b), or a wireless controller in a CRAN scenario. Optionally, the RAN node can also be a server, wearable device, vehicle, or in-vehicle equipment. For example, in vehicle-to-everything (V2X) technology, the RAN node can be a roadside unit (RSU). All or part of the functions of the RAN node in this application can also be implemented through software functions running on hardware, or through virtualization functions instantiated on a platform (e.g., a cloud platform). The RAN node can also be equipped with communication modules, circuits, or chips that perform corresponding communication functions. The RAN node can also be configured with program instructions for performing corresponding communication functions and corresponding program instructions. The RAN node in this application can also be a logical node, logical module, or software that can implement all or part of the access node functions, or a circuit or chip (such as a GPU, AI processor, NPU, or ASIC) responsible for communication and / or computing functions in the access node.

[0048] In another possible scenario, multiple RAN nodes collaborate to assist terminals in achieving wireless access, with different RAN nodes each implementing some of the base station's functions. For example, RAN nodes can be central units (CUs), distributed units (DUs), CU-control plane (CPs), CU-user plane (UPs), or radio units (RUs), etc. CUs and DUs can be set up separately or included in the same network element, such as a baseband unit (BBU). RUs can be included in radio frequency equipment or radio frequency units, such as remote radio units (RRUs), active antenna units (AAUs), or remote radio heads (RRHs). Furthermore, RAN nodes can also be computing units, providing computing power for tasks (such as model inference and / or model training), and can also be used to implement one or more of the following: task partitioning, scheduling, and orchestration. The functionality of a computing unit can be implemented by a separate module independent of other units (e.g., CU, DU, RU), or by one or more other units (e.g., one or more of CU, DU, RU).

[0049] In different systems, CU (or CU-CP and CU-UP), DU, computing unit, or RU may have different names, but those skilled in the art will understand their meaning. For example, in an ORAN system, CU can also be called O-CU (open CU), DU can also be called O-DU, CU-CP can also be called O-CU-CP, CU-UP can also be called O-CU-UP, and RU can also be called O-RU. For ease of description, this application uses CU, CU-CP, CU-UP, DU, computing unit, and RU as examples. Any of the units among CU (or CU-CP, CU-UP), DU, computing unit, and RU in this application can be implemented through software modules, hardware modules, or a combination of software modules and hardware modules.

[0050] A terminal can be a device or module that accesses the aforementioned communication system and has corresponding communication functions. A terminal can also be called a terminal device, user equipment (UE), mobile station, mobile terminal, etc. Terminals can be widely used in various scenarios, such as device-to-device (D2D), V2X communication, machine-type communication (MTC), Internet of Things (IoT), virtual reality, augmented reality, industrial control, autonomous driving, telemedicine, smart grids, smart furniture, smart offices, smart wearables, smart transportation, smart cities, etc. Terminals can be mobile phones, tablets, computers with wireless transceiver capabilities, wearable devices, vehicles, drones, helicopters, airplanes, ships, robots, robotic arms, smart home devices, transportation vehicles with wireless communication capabilities, communication modules, etc. The embodiments of this application do not limit the device form of the terminal. Terminals typically contain communication modules, circuits, or chips that perform corresponding communication functions. Furthermore, they can also contain modules, circuits, or chips (such as GPUs, AI processors, NPUs, or ASICs) that perform corresponding communication and / or computing functions. The terminal can also be configured with program instructions for performing corresponding communication and / or computing functions.

[0051] To support AI technology in wireless networks, AI nodes may also be introduced into the network.

[0052] AI nodes can be deployed in one or more of the following locations within the communication system: access network nodes (RAN nodes), terminal devices, or core network elements. Alternatively, AI nodes can be deployed independently, for example, in a location other than any of the aforementioned devices, such as in the host or cloud server of an over-the-top (OTT) system. AI nodes can communicate with other devices in the communication system, which can be one or more of the following: network devices, terminal devices, or core network elements.

[0053] It is understood that this application does not limit the number of AI nodes. For example, when there are multiple AI nodes, these nodes can be divided based on function, such as different AI nodes being responsible for different functions.

[0054] It can also be understood that AI nodes can be independent devices, or they can be integrated into the same device to achieve different functions. Alternatively, they can be network elements in hardware devices, software functions running on dedicated hardware, or virtualization functions instantiated on a platform (e.g., a cloud platform). This application does not limit the specific form of the aforementioned AI nodes.

[0055] AI nodes can be AI network elements or AI modules.

[0056] Figure 1B A schematic diagram (13) illustrates the deployment of an AI module in a communication system. For example... Figure 1B As shown, network elements in the communication system are connected via interfaces (e.g., NG, Xn) or air interfaces. These network element nodes include, for example, core network element 130, access network node (RAN node) 135, terminal 140, OAM 145, or cloud servers (such as OTT (Over-The-Top) servers). Figure 1B One or more AI modules are provided in one or more devices (not shown in the image). (For clarity,) Figure 1B (Only one is shown in the image). The aforementioned access network node can be a single RAN node or can include multiple RAN nodes, for example, including CU135-1 and DU 135-2. CU 135-1 and / or DU 135-2 can also be equipped with one or more AI modules. Optionally, the CU can also be split into CU-CP and CU-UP. One or more AI modules are configured in CU-CP and / or CU-UP.

[0057] AI modules are used to implement corresponding AI functions. AI modules deployed in different network elements can be the same or different. The models of AI modules can achieve different functions depending on the parameter configurations. The models of AI modules can be configured based on one or more of the following parameters: structural parameters (e.g., at least one of the following: number of neural network layers, neural network width, inter-layer connections, neuron weights, neuron activation function, or biases in the activation function), input parameters (e.g., the type and / or dimension of the input parameters), or output parameters (e.g., the type and / or dimension of the output parameters). The biases in the activation function can also be referred to as the biases of the neural network.

[0058] In one example, the neural network mentioned above could be a deep neural network (DNN), a convolutional neural network (CNN), a recurrent neural network (RNN), or a generative adversarial network (GAN).

[0059] Deep Neural Networks (DNNs) are artificial neural network architectures with multiple layers of nonlinear transformation units stacked in a hierarchical structure to form deep computational models. Compared to shallow neural networks, deep neural networks have more hidden layers, allowing the network model to capture more complex data structures and higher-level abstract features.

[0060] A CNN is a deep neural network with a convolutional structure. A CNN contains a feature extractor consisting of convolutional layers and subsampling layers. This feature extractor can be viewed as a filter, and the convolution process can be seen as performing convolution between a trainable filter and an input image or a convolutional feature map.

[0061] RNN is a type of recursive neural network that takes sequence data as input, recursively moves along the direction of sequence evolution, and connects all nodes (recurrent units) in a chain-like manner.

[0062] GAN is a deep learning model. It consists of a generator and a discriminator, and is trained through adversarial learning. Its purpose is to estimate the potential distribution of data samples and generate new data samples.

[0063] An AI module can have one or more models. A model can infer an output, which includes one or more parameters. The learning, training, or inference processes of different models can be deployed on different nodes or devices, or they can be deployed on the same node or device.

[0064] Figure 1C Schematic diagram 15 shows a possible application framework in a communication system. For example... Figure 1C As shown, the communication system includes a RAN intelligent controller (RIC). For example, an RIC can be an AI module used to implement AI-related functions. RICs include near-real-time RIC 165 (near-RT RIC) and non-real-time RIC 160 (non-RT RIC). Non-real-time RICs primarily process non-real-time information, such as data that is not sensitive to latency, with latency in the order of seconds. Real-time RICs primarily process near-real-time information, such as data that is relatively sensitive to latency, with latency in the order of tens of milliseconds.

[0065] Near real-time RICs are used for model training and inference. For example, they are used to train AI models and then use those models for inference. The near real-time RIC 165 can obtain network-side and / or terminal-side information from RAN nodes 150 (e.g., CU 151, CU-CP 153, CU-UP 155, DU 157, compute nodes, and / or RU 159) and / or terminals 170. This information can be used as training data or inference data. The 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, the near real-time RIC delivers inference results to a DU, which then forwards them to an RU.

[0066] Non-real-time RICs are also used for model training and inference. For example, they are used to train AI models and then use those models for inference. The non-real-time RIC 160 can obtain network-side and / or terminal-side information from RAN nodes 150 (e.g., CU 151, CU-CP 153, CU-UP 155, DU 157, compute nodes, and / or RU 159) and / or terminals 170. This information can be used as training data or inference data, and the inference results can be delivered to RAN nodes and / or terminals. Inference results can be exchanged between CUs and DUs, and / or between DUs and RUs; for example, the non-real-time RIC delivers the inference results to the DU, which then forwards them to the RU.

[0067] The near real-time RIC 165 and the non-real-time RIC 160 can also be configured as separate network elements. The near real-time RIC 165 and the non-real-time RIC 160 can also be part of other devices. For example, the near real-time RIC 165 can be configured in RAN node 150 (e.g., CU, DU, compute node), while the non-real-time RIC 160 can be configured in OAM, cloud servers, core network elements, or other network devices.

[0068] In this application, "sending information" can be understood as one device sending information to another device, or it can also be understood as one logical module within a device sending information to another logical module. For example, "RAN node sending information" can be understood as the RAN node sending information to another device (e.g., a terminal), or it can be understood as logical module 1 in the RAN node sending information to logical module 2 in the RAN node.

[0069] In this application, "receiving information" can be understood as one device receiving information from another device, or it can also be understood as a logical module within a device receiving information from another logical module. For example, "RAN node receiving information" can be understood as the RAN node receiving information from another device (e.g., a terminal), or it can be understood as logical module 1 in the RAN node receiving information from logical module 2 in the RAN node.

[0070] In this application, phrases such as "sending information to... (e.g., a terminal)" or related illustrations in the accompanying drawings can be understood as indicating that the destination of the information is a terminal. This can include sending information directly or indirectly to a terminal. Similarly, phrases such as "receiving information from... (e.g., a terminal)," "receiving information from... (e.g., a terminal)," or "receiving information sent by (e.g., a terminal)," or related illustrations in the accompanying drawings, can be understood as indicating that the source of the information is a terminal. This can include receiving information directly or indirectly from a terminal. Information may undergo necessary processing between the source and destination, such as format changes, but the destination can understand the valid information from the source. Similar expressions in this application can be interpreted similarly and will not be elaborated further here.

[0071] With the development of 5G communication technology, data transmission latency has been significantly reduced and transmission capacity has been greatly improved. 5G communication systems are gradually penetrating into multimedia service fields with extremely high requirements for real-time performance and data capacity, such as video transmission, cloud gaming (CG), and extended reality (XR, which includes virtual reality (VR) and augmented reality (AR)).

[0072] Cloud virtual reality (VR) and cloud augmented reality (AR) technologies, by integrating cloud computing and cloud rendering concepts and leveraging a high-speed and stable network environment, encode and compress display and audio content generated in the cloud before transmitting it to the user device (UE). This enables the migration of VR / AR service content and rendering processes to the cloud, thereby reducing the burden on the terminal side and improving its portability and flexibility. In specific communication scenarios, VR / AR terminals can access the network through base stations or access points to obtain service content from the cloud.

[0073] As VR / AR technology evolves, cloud VR / AR services are placing increasingly stringent demands on network bandwidth and latency, posing greater challenges to communication systems. For example, cloud gaming and cloud VR deploy content in the cloud, with data interaction primarily consisting of downlink audio / video streams and uplink control streams. For downlink audio / video streams, higher resolution and higher bitrate result in a better user experience, but also require higher bandwidth. Uplink control streams are more sensitive to latency and jitter. For instance, in cloud gaming scenarios, rapid and continuous transmission of control commands is required; therefore, the network must ensure low latency and low jitter for these commands. In contrast, cloud VR services have more diverse network requirements. For example, to provide high resolution, bandwidth and bitrate requirements may be higher, while latency requirements may be relatively less stringent, but high stability and reliability must be maintained.

[0074] In terms of video encoding, cloud gaming and cloud VR can employ two encoding methods: VBR (Video Bit Rate) and Constant Bit Rate (CBR). Under CBR encoding, the video file bitrate remains constant throughout the entire file transmission process, making it suitable for applications requiring high data stream stability, such as video conferencing or real-time streaming media. Its advantages lie in high transmission stability and ease of network bandwidth control and management; however, its disadvantages include the potential for image quality degradation and lower efficiency when dealing with scenes of varying complexity due to the fixed video bitrate.

[0075] In contrast, VBR encoding can dynamically adjust the bitrate based on the complexity of the scene, allocating more bitrate to complex scenes to maintain video quality and less bitrate to simple scenes. Its advantages are higher efficiency and better video quality; however, its disadvantages include potential network instability due to bitrate fluctuations, and a more complex encoding and decoding process.

[0076] For cloud gaming, given users' high demands for image quality, VBR encoding is typically used. Since image changes are closely related to user input, changes in frame size are also correlated to some extent with user actions. For example, when a user presses a specific button in a cloud game to trigger a skill release, the game plays a corresponding animation. In this case, the downlink data packet size can change drastically. However, because network-side data transmission usually employs a best-effort transmission guarantee mechanism—meaning data packets are transmitted as quickly as possible upon arrival, and discarded if transmission is impossible—the air interface may not be able to provide transmission guarantees, leading to transmission failures.

[0077] Furthermore, in certain scenarios, end users can leverage cloud-based large-scale models to complete tasks. One approach is a purely visual one. The user first submits a task request, which the cloud then breaks down into multiple sub-tasks, prompting the user to upload screenshots of the current screen. The cloud-based large-scale model analyzes these screenshots to determine the next operational instructions.

[0078] The process of cloud-based big data model-assisted task execution typically includes the following steps: First, in the user task request stage, the user can input a task request in natural language through the mobile interface, for example, "Find me a pair of black size 42 sneakers on the XX e-commerce APP and place an order for them." This request is then transmitted to the cloud for task breakdown. In this stage, the cloud-based big data model uses natural language processing capabilities to identify keywords (such as "XX e-commerce APP," "black size 42 sneakers," "place an order for them," etc.) and understand the user's intent and operation sequence, thereby breaking down a complex task into multiple sub-tasks. Subsequently, the cloud-based big data model sends the broken-down sub-tasks to the mobile device in sequence. After completing the sub-tasks, the mobile device uses the screenshot function to capture image data of the currently displayed content on the screen and uploads it to the cloud via the network. The cloud-based big data model uses image recognition capabilities to analyze the screenshot and accurately identify elements (such as the layout of the APP interface, button positions, text information, etc.), and combines the sub-tasks and analysis results to infer the next operation instruction (such as "click the search box"). Next, the cloud sends the instruction to the mobile device. After receiving the instruction, the mobile device simulates the user's operation, takes a screenshot again after performing the action, and uploads it. The cloud analyzes and infers based on the screenshot and issues a new instruction. This process is repeated until the entire task is completed.

[0079] However, in the above scenarios, the amount of screen data uploaded by the terminal varies by orders of magnitude depending on the task execution stage (such as the initial interface versus complex form pages) and the user's actions (such as text input versus image display). Furthermore, cloud inference latency also dynamically changes due to factors such as model load fluctuations and network bandwidth variations. Consequently, the size and time of user-uploaded images are not fixed but exhibit dynamic characteristics. This dual dynamism of data throughput and processing latency increases the complexity of system design and places higher demands on the network-side data transmission scheduling mechanism. An adaptive transmission system with real-time perception and dynamic resource allocation capabilities is required to maintain stable service quality in changing network environments.

[0080] Based on the foregoing analysis and discussion, this disclosure proposes a communication method, such as a method for predicting burst data size. In some embodiments, by utilizing the inherent correlation between uplink and downlink data in interactive services, the network side can perceive changes in the service and provide predictive data packet (service frame) information to the radio interface. Based on this, the network side can perceive the fluctuations in service data packets and thus execute more accurate and efficient resource scheduling strategies, providing stable and reliable transmission guarantees for various services with fluctuating data packet sizes.

[0081] The method and apparatus for predicting the size of bursty data proposed in this disclosure will be further described below with reference to the accompanying drawings. It is understood that this application uses RAN nodes, core network elements, terminals, and servers as examples of the execution entities in the interactive illustration, but this application does not limit the execution entities in the interactive illustration. For example, the method executed by the RAN node in this application can also be implemented by modules (e.g., circuits, chips, or chip systems) in the RAN node, or by logical nodes, logical modules, or software that can implement all or part of the functions of the RAN node, or by circuits or chips (e.g., GPUs, AI processors, NPUs, or ASICs) in the RAN node responsible for communication and / or computing functions. Similarly, the method executed by the terminal in this application can also be implemented by communication and / or computing modules in the terminal, or by circuits or chips (e.g., modem chips, or SoC chips / SIP chips containing modem cores, or GPUs / NPUs / AI processors / ASICs) in the terminal responsible for communication and / or computing functions, or by logical nodes, logical modules, or software that can implement all or part of the terminal functions. The methods executed by core network elements in this application can also be implemented by components within the device (e.g., processors, chips, or chip systems), or by logical modules or software capable of implementing all or part of the device's functions. Similarly, the methods executed by a server in this application can be implemented by hardware components within the server (e.g., processors, SoC chips, or dedicated modules), or by logical processing units implemented in software or virtualization. The process executed by a single executing entity can also be divided into multiple executing entities, which can be logically and / or physically separated. For example, the process executed by a RAN node can be divided into execution by at least one of CU, DU, RU, etc.

[0082] Figure 2 A schematic diagram of the communication flow of some embodiments of this disclosure is shown. For example... Figure 2 As shown, process 200 involves a first device 203, a second device 205, and a third device 207. The first device 203 can be as follows: Figure 1A The terminal 120 shown (e.g., Figure 1AThe second device 205 can be, for example, terminals 120a to 120j, or server 301 (e.g., a server for AI inference and / or training); Figure 1A The core network element 201 shown is (e.g., UPF, NWDAF, SMF, or other network elements); the third device 207 can be, for example, Figure 1A The RAN node 110 shown (e.g., Figure 1A Terminals 110a and 110b in the middle).

[0083] like Figure 2 As shown, in process 200, at point 210, the first device 203 can generate category information for a first instruction. This category information can, for example, indicate the amount of data and / or the arrival time of the first data corresponding to the first instruction. In some implementations, the category information can also be the first instruction itself, in which case the amount of data and / or the arrival time of the first data can be indicated by the first instruction itself. The "indication" can be an implicit indication, that is, the network side can determine the amount of data and / or the arrival time of the first data based on the category information. For example, in a cloud gaming scenario, the first instruction can refer to various game instructions (such as gamepad buttons, touch operations, etc.) captured by the user input on the terminal side. Optionally, the first device 203 is as follows: Figure 1A In the case of server 301 shown, before step 210, the first device 203 can receive task request information from the user device, such as model inference requests and data preprocessing instructions sent by the user to the cloud server in a cloud-based large model-assisted task execution scenario. In this scenario, the first instruction can be, for example, various operation instructions (such as "open XX e-commerce APP", "click the search box", etc.) generated by the cloud server based on the task request information on the user side. The execution of different instructions may trigger the transmission of different amounts of data, causing fluctuations in frame size or delays in frame arrival time. Therefore, there can be a first correlation between the first instruction and the category information. For example, the terminal or server can classify these user instructions into multiple categories according to the degree of data fluctuation. Taking the cloud gaming scenario as an example, they can be exemplarily divided into: drastic change category, such as scene switching, special effect triggering, etc.; moderate change category, such as character movement, view adjustment, etc.; and stable category, such as menu operation, parameter fine-tuning, etc. Different categories correspond to different category information, which are used to indicate the size range of frame data generated by the execution of the instruction, or the level range of frame data arrival time. Table 1 below shows an example of the association between operation instructions and category information.

[0084] Table 1 shows the relationship between operation instructions and category information (taking user instructions in a cloud gaming scenario as an example).

[0085]

[0086] In some embodiments, the first association can be pre-configured (or aligned) at the first device 203 and the second device 205. Specifically, in some implementations, the first device 203 can receive first configuration information from the second device 205, which indicates the first association. For example, core network elements (such as UPF, NWDAF, SMF, etc.) can obtain the associations in Table 1 above offline and send them to the terminal. In other implementations, the first device 203 can send second configuration information to the second device 205, which indicates the first association. For example, the terminal can determine the associations in Table 1 above based on an AI model and send the associations to the core network elements (such as UPF, NWDAF, SMF, etc.). Optionally, the terminal can also directly send the AI ​​model to the core network elements, so that the core network elements can know the corresponding relationships in Table 1 above.

[0087] In some embodiments, the category information described above may include a first index. In these implementations, the first index may correspond to the amount of first data and / or the arrival time of the first data. For example, in Table 1 above, user instructions may also be associated with an index used to indicate the category information described above, as shown in Table 2 below:

[0088] Table 2 shows the relationship between operation commands and indexes (taking user commands in a cloud gaming scenario as an example).

[0089]

[0090] In this way, the terminal obtains the association between user commands and category information (such as the first association mentioned above) through local AI models or alignment with the network, so that the commands are associated with business characteristics (e.g., data volume / latency requirements), providing a basis for the network side to predict data volume, and can obtain more accurate data volume prediction, thereby matching more appropriate resource allocation and improving resource utilization. At the same time, by using lightweight indexes (such as the first index mentioned above), it helps the network side to save transmission overhead while achieving rapid matching of pre-configured resources.

[0091] At point 220, the first device 203 sends the aforementioned category information to the third device 207. For example, this category information can be encapsulated within a PDCP / RLC data packet. Specifically, the category information can be encapsulated within the header portion of a PDCP or RLC data packet, or it can be encapsulated within the payload portion of a PDCP or RLC data packet. In other implementations, the category information can also be sent via a MAC CE. The third device 207 can obtain the category information by parsing a PDCP / RLC data packet (e.g., its header or payload portion) or by parsing a MAC CE.

[0092] At position 230, the third device 207 sends the aforementioned category information to the second device 205. Specifically, the third device 207 may encapsulate the aforementioned category information in a GTP-U data packet and send it to the second device 205. Specifically, the category information may be encapsulated in the header or payload of the GTP-U data packet and sent to the second device 205. The second device 205 can obtain the aforementioned category information by parsing the received GTP-U data packet information.

[0093] Furthermore, in some implementations, this category information can also be sent via a dedicated tunnel, a dedicated bearer, or a dedicated QoS stream. Specifically, this category information can be sent via a dedicated tunnel, a dedicated bearer, or a dedicated QoS stream between the first device 203 and the second device 205. Specifically, a dedicated channel can be defined, for example, between the terminal 120 (or server 301) and the core network element 201 (such as UPF, NWDAF, SMF, etc.). Depending on the specific implementation, this channel can be configured with one or more of the following: specific QoS parameters (such as 5QI, GFBR, etc.), an independent QoS Flow Identifier (QFI), and a Dedicated Tunnel Endpoint Identifier (TEID). In this mechanism, the terminal 120 (or server 301) and the core network element 201 act as channel endpoints, responsible for processing such as encoding and decoding of instruction information; the RAN node 110 (e.g., eNB, gNB, etc.) identifies the bearer type based on, for example, the QFI, without needing to parse the specific details of the content transmitted by the logical bearer, which helps to achieve efficient and reliable transmission of instruction category information.

[0094] At point 240, based on the received category information, the second device 205 performs a prediction of the first data-related information corresponding to the first instruction. For example, a core network element may trigger the prediction based on the category information (e.g., the first index) parsed from the GTP-U data packet. Optionally, the second device 205 may also combine information from historical data (e.g., the size and interval of the past N frames) to perform the prediction.

[0095] In the design of the prediction mechanism, both the prediction window and the prediction size can have a certain degree of flexibility. The prediction window can be configured according to actual needs, for example, set to N=5, which predicts the size of the next 5 frames. At the same time, the prediction size can also be configured according to different application scenarios and requirements. For example, three size ranges can be preset: 0-1Mbits, 1-2Mbits, and >2Mbits, so as to classify, predict, and process frames of different sizes.

[0096] In addition to information about the data size, this prediction mechanism can also indicate the time it takes for data (e.g., the first data mentioned above) to arrive at the RAN node. The principle is that when the system receives an instruction from the terminal, the time required for the cloud to process that instruction is relatively fixed. Based on this characteristic, the specific time it takes for the downlink data to arrive at the RAN node can be calculated by determining the total time from receiving the uplink instruction to its completion, and then to the downlink data transmission to the RAN node. This function provides more accurate support for latency management and resource scheduling in communication networks.

[0097] At point 250, the second device 205 sends a prediction result of the first data-related information corresponding to the first instruction to the third device 207. For example, the core network element can encapsulate the predicted information for a single frame / multiple frames in a GTP-U data packet and send it to the RAN node. Specifically, this information can be encapsulated in the header or payload of a GTP-U data packet and sent to the second device 205. The prediction result may include, for example, predicted values ​​for information such as the size of the frame data and the arrival time of the data, and optionally, a confidence interval (e.g., 80%) for the predicted values.

[0098] It is worth noting that in the embodiment described in process 200, the second device 205 (i.e., the core network element) supports service prediction based on instruction category information. When the first device 203 is as follows... Figure 1A The terminal 120 shown (e.g., Figure 1A When terminals 120a to 120j are connected, the core network elements, based on uplink instructions (e.g., instructions from the terminals) and combined with AI models, perform downlink service prediction and send the prediction information to the RAN nodes. This enables the RAN nodes to perceive future service volume and orchestrate air interface resources, providing reliable air interface transmission for suddenly changing services, thereby providing satisfactory transmission services to more users. When the first device 203 is as follows... Figure 1AWhen the server 301 shown (e.g., a server used for AI inference and / or training) is in use, the core network elements, based on downlink instructions (e.g., instructions from the server) and combined with the AI ​​model, perform uplink service prediction, enabling RAN nodes to sense future service volume, orchestrate air interface resources, and provide reliable air interface transmission for services that change suddenly.

[0099] Figure 3 A schematic diagram of the communication flow of some embodiments of this disclosure is shown. For example... Figure 3 As shown, process 300 involves a first device 303 and a second device 305. The first device 303 can be as follows: Figure 1A The terminal 120 shown (e.g., Figure 1A The second device 305 can be, for example, terminals 120a to 120j, or server 301 (e.g., a server for AI inference and / or training); Figure 1A The RAN node 110 shown (e.g., Figure 1A Terminals 110a and 110b in the middle).

[0100] like Figure 3 As shown, in process 300, at point 310, the first device 303 can generate category information for the first instruction. Optionally, the first device 303 is as follows: Figure 1A In the case of server 301 shown, before step 310, the first device 303 can receive task request information from the user device, such as model inference requests and data preprocessing instructions sent by the user to the cloud server in a cloud-based large model-assisted task execution scenario. A first association relationship may exist between the first instruction and the category information. A description of the above instructions, category information, and the association relationship between instructions and category information can be found in [reference needed]. Figure 2 The relevant descriptions in the document will not be repeated here.

[0101] At point 320, the first device 303 sends the aforementioned category information to the second device 305. For example, this category information can be encapsulated within a PDCP / RLC data packet. Specifically, the category information can be encapsulated within the header of a PDCP or RLC data packet, or it can be encapsulated within the payload of a PDCP or RLC data packet. In other implementations, the category information can also be sent via a MAC CE. The second device 305 can obtain the category information by parsing a PDCP / RLC data packet (e.g., its header or payload) or a MAC CE. Furthermore, in some implementations, the category information can also be sent via a dedicated tunnel, a dedicated bearer, or a dedicated QoS stream. Specifically, the category information can be sent via a dedicated tunnel, a dedicated bearer, or a dedicated QoS stream between the first device 303 and the second device 305.

[0102] At point 330, based on the received category information, the second device 305 performs a prediction of the first data-related information corresponding to the first instruction. A description of the specific prediction process and method can be found in [link to relevant documentation]. Figure 2 The relevant descriptions in the document will not be repeated here.

[0103] It is worth noting that, compared to process 200, process 300 differs in that, in the embodiment described in process 300, the second device 305 (i.e., the RAN node) supports service prediction based on instruction category information. When the first device 303 is as follows... Figure 1A The terminal 120 shown (e.g., Figure 1A When terminals 120a to 120j are connected, the RAN node, based on uplink instructions (e.g., instructions from the terminals), combines an AI model to predict downlink traffic. Based on the predicted information, it senses future traffic volume and orchestrates air interface resources to provide reliable air interface transmission for unexpectedly changing services, thereby providing satisfactory video transmission services to more users. When the first device 303 is as follows... Figure 1A When the server 301 shown is used (e.g., a server used for AI inference and / or training), the RAN node performs uplink service prediction based on downlink instructions (e.g., instructions from the server) and the AI ​​model, and senses future service volume based on the predicted information, and makes air interface resource orchestration in advance to provide reliable air interface transmission for services that change suddenly.

[0104] Figure 4 A possible exemplary block diagram of the communication device involved in an embodiment of this application is shown. For example... Figure 4As shown, the communication device 400 may include modules or units for implementing the methods described in the embodiments above. In one possible design, the communication device 400 includes a processing unit 402 and a communication unit 403. Optionally, the communication device 400 may further include a storage unit 401 for storing device program code and / or data.

[0105] The communication device 400 can be the above-mentioned Figure 2 or Figure 3 The first device in the embodiments, for example, Figure 1A The terminal 120 or server 301 shown, or the communication module in the terminal 120 or server 301, or the circuit or chip in the terminal 120 or server 301 responsible for communication functions.

[0106] For example, in one embodiment, the processing unit 402 is configured to: generate category information of a first instruction, wherein the category information is used to indicate the amount of data of the first data corresponding to the first instruction and / or the arrival time of the first data.

[0107] In one possible design, the communication unit 403 is used to: send the aforementioned type of information.

[0108] In one possible design, there is a first association between the first instruction and the category information.

[0109] In one possible design, the communication unit 403 is further configured to: receive first configuration information, the first configuration information being used to indicate a first association relationship.

[0110] In one possible design, the communication unit 403 is also used to: send second configuration information, which is used to indicate the first association relationship.

[0111] In one possible design, the processing unit 402 is further configured to: determine a first association based on an artificial intelligence (AI) model, and the second configuration information is further configured to instruct the AI ​​model.

[0112] In one possible design, the category information includes a first index, which corresponds to the amount of data in the first data and / or the arrival time of the first data.

[0113] In one possible design, this category of information is transmitted via at least one of a dedicated tunnel, a dedicated bearer, or a dedicated QoS stream.

[0114] In one possible design, when the communication device 400 is a terminal 120 or server 301, or a communication module within terminal 120 or server 301, the function of the processing unit 402 can be implemented by one or more processors. Specifically, the processor may include a modem chip, or a system-on-a-chip (SoC) chip or a SIP chip containing a modem core. The function of the communication unit 403 can be implemented by a transceiver circuit.

[0115] In one possible design, when the communication device 400 is a circuit or chip responsible for communication functions in the terminal 120 or server 301, such as a modem chip or a system-on-a-chip (SoC) or SIP chip containing a modem core, the function of the processing unit 402 can be implemented by a circuit system in the aforementioned chip that includes one or more processors or processor cores. The function of the communication unit 403 can be implemented by interface circuits or data transceiver circuits on the aforementioned chip.

[0116] In one possible design, when the communication device 400 is a terminal 120 or server 301, or a communication and / or computing module within terminal 120 or server 301, the functionality of the processing unit 402 can be implemented by one or more processors. Specifically, the processor may include a GPU, or a system-on-a-chip (SoC) or SIP chip containing a GPU. Alternatively, the processor may include an AI processor, or a SoC or SIP chip containing an AI processor. Alternatively, the processor may include an ASIC, or a SoC or SIP chip containing an ASIC. Alternatively, the processor may include an NPU, or a SoC or SIP chip containing an NPU. The functionality of the communication unit 403 can be implemented by transceiver circuitry.

[0117] In one possible design, when the communication device 400 is a circuit or chip in the terminal 120 or server 301 responsible for communication and / or computing functions, such as a GPU or a system-on-a-chip (SoC) or SIP chip containing a GPU, an AI processor or a SoC or SIP chip containing an AI processor, an NPU or a SoC or SIP chip containing an NPU, or an ASIC or a SoC or SIP chip containing an ASIC, the function of the processing unit 402 can be implemented by a circuit system in the aforementioned chip that includes one or more processors or processor cores. The function of the communication unit 403 can be implemented by interface circuits or data transceiver circuits on the aforementioned chip.

[0118] The communication device 400 can be the above-mentioned Figure 2 or Figure 3 The second device in the embodiments, for example, Figure 1AThe core network element 201 or RAN node 110 shown, or the communication module in the core network element 201 or RAN node 110, or the circuit or chip in the core network element 201 or RAN node 110 responsible for communication functions.

[0119] For example, in one embodiment, the communication unit 403 is configured to: receive category information of a first instruction, wherein the category information is used to indicate the amount of data of the first data corresponding to the first instruction and / or the arrival time of the first data.

[0120] In one possible design, the processing unit 402 is used to: perform a prediction of the first data-related information corresponding to the first instruction based on the category information.

[0121] In one possible design, there is a first association between the first instruction and the category information.

[0122] In one possible design, the communication unit 403 is also used to: send first configuration information, the first configuration information being used to indicate a first association relationship.

[0123] In one possible design, the communication unit 403 is also used to: receive second configuration information, which is used to indicate the first association relationship.

[0124] In one possible design, the category information includes a first index, which corresponds to the amount of data in the first data and / or the arrival time of the first data.

[0125] In one possible design, this category of information is transmitted via at least one of a dedicated tunnel, a dedicated bearer, or a dedicated QoS stream.

[0126] In one possible design, when the communication device 400 is a core network element 201 or RAN node 110, or a communication module within the core network element 201 or RAN node 110, the function of the processing unit 402 can be implemented by one or more processors. Specifically, the processor may include a modem chip, or a system-on-a-chip (SoC) chip or a SIP chip containing a modem core. The function of the communication unit 403 can be implemented by a transceiver circuit.

[0127] In one possible design, when the communication device 400 is a circuit or chip responsible for communication functions in the core network element 201 or RAN node 110, such as a modem chip or a system-on-a-chip (SoC) or SIP chip containing a modem core, the function of the processing unit 402 can be implemented by a circuit system in the aforementioned chip that includes one or more processors or processor cores. The function of the communication unit 403 can be implemented by the interface circuitry or data transceiver circuitry on the aforementioned chip.

[0128] In one possible design, when the communication device 400 is a core network element 201 or RAN node 110, or a communication and / or computing module within the core network element 201 or RAN node 110, the function of the processing unit 402 can be implemented by one or more processors. Specifically, the processor may include a GPU, or a system-on-a-chip (SoC) or SIP chip containing a GPU. Alternatively, the processor may include an AI processor, or a SoC or SIP chip containing an AI processor. Alternatively, the processor may include an ASIC, or a SoC or SIP chip containing an ASIC. Alternatively, the processor may include an NPU, or a SoC or SIP chip containing an NPU. The function of the communication unit 403 can be implemented by transceiver circuitry.

[0129] In one possible design, when the communication device 400 is a circuit or chip in the core network element 201 or RAN node 110 responsible for communication and / or computing functions, such as a GPU or a system-on-a-chip (SoC) or SIP chip containing a GPU, an AI processor or a SoC or SIP chip containing an AI processor, an NPU or a SoC or SIP chip containing an NPU, or an ASIC or a SoC or SIP chip containing an ASIC, the function of the processing unit 402 can be implemented by a circuit system in the aforementioned chip that includes one or more processors or processor cores. The function of the communication unit 403 can be implemented by interface circuits or data transceiver circuits on the aforementioned chip.

[0130] The communication device 400 can be the above-mentioned Figure 3 The second device in the embodiments, for example, Figure 1A The RAN node 110 shown, or the communication module in the RAN node 110, or the circuit or chip in the RAN node 110 responsible for communication functions.

[0131] For example, in one embodiment, the communication unit 403 is used to: receive category information of a first instruction from the first device.

[0132] In one possible design, the communication unit 403 is also used to: send category information of the first instruction to the second device.

[0133] In one possible design, when the communication device 400 is RAN node 110 or a communication module within RAN node 110, the function of the processing unit 402 can be implemented by one or more processors. Specifically, the processor may include a modem chip, or a system-on-a-chip (SoC) chip or SIP chip containing a modem core. The function of the communication unit 403 can be implemented by transceiver circuitry.

[0134] In one possible design, when the communication device 400 is a circuit or chip responsible for communication functions in the RAN node 110, such as a modem chip or a system-on-a-chip (SoC) or SIP chip containing a modem core, the function of the processing unit 402 can be implemented by a circuit system in the aforementioned chip that includes one or more processors or processor cores. The function of the communication unit 403 can be implemented by the interface circuitry or data transceiver circuitry on the aforementioned chip.

[0135] In one possible design, when the communication device 400 is RAN node 110, or a communication and / or computing module within RAN node 110, the functionality of the processing unit 402 can be implemented by one or more processors. Specifically, the processor may include a GPU, or a system-on-a-chip (SoC) or SIP chip containing a GPU. Alternatively, the processor may include an AI processor, or a SoC or SIP chip containing an AI processor. Alternatively, the processor may include an ASIC, or a SoC or SIP chip containing an ASIC. Alternatively, the processor may include an NPU, or a SoC or SIP chip containing an NPU. The functionality of the communication unit 403 can be implemented by transceiver circuitry.

[0136] In one possible design, when the communication device 400 is a circuit or chip in the RAN node 110 responsible for communication and / or computing functions, such as a GPU or a system-on-a-chip (SoC) or SIP chip containing a GPU, an AI processor or a SoC or SIP chip containing an AI processor, an NPU or a SoC or SIP chip containing an NPU, or an ASIC or a SoC or SIP chip containing an ASIC, the function of the processing unit 402 can be implemented by a circuit system in the aforementioned chip that includes one or more processors or processor cores. The function of the communication unit 403 can be implemented by interface circuits or data transceiver circuits on the aforementioned chip.

[0137] It is understood that the division of units in the above-described device is merely a logical functional division. One function can correspond to one functional unit, or two or more functions can be integrated into one functional unit. In actual implementation, all or some units can be integrated onto a single physical entity, or distributed across different physical entities. Furthermore, the aforementioned functional units can be implemented in hardware, software, or a combination of both. Whether a function is executed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for specific applications, but such implementations should not be considered beyond the scope of this application.

[0138] In one example, the functional unit in any of the above devices may be one or more integrated circuits configured to implement the above methods, such as: one or more 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.

[0139] In one example, storage unit 401 may include random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory and / or registers, etc.

[0140] Figure 5 This illustration shows a structural diagram of a terminal 500 provided in an embodiment of this application. The terminal 500 can correspond to... Figure 1A The terminal shown is used to implement the operations of the terminal in the above embodiments. Figure 5 As shown, the terminal includes: one or more antennas 510, a radio frequency processing system 520, and a processor system 530.

[0141] In the downlink or sidelink direction, the RF processing system 520 receives RF signals through the antenna 510 and sends the RF-processed signals to the processor system 530 for further processing. In the uplink or sidelink direction, the processor system 530 processes the terminal-side information and sends it to the RF processing system 520, which then processes the signal and transmits it through the antenna 510.

[0142] In one example, the radio frequency (RF) processing system 520 serves as the communication interface for external communication of the terminal and may include an RF front end (RFFE) 521 and an RF transceiver 522. The RFFE 521 is primarily used for one or more processing operations, such as shaping, passband selection, or gain adjustment, on the RF signals received by the antenna or those to be transmitted through the antenna. It may include one or more components such as RF switches, duplexers, filters, power amplifiers, antenna tuners, and low-noise amplifiers. The RFFE 521 can be a circuit system composed of multiple discrete devices or integrated into one or more chips. The RF transceiver 522 processes the RF signals received by the RFFE into baseband / IF signals for further processing by the processor system 530, and processes the baseband / IF signals provided by the processor system 530 into RF signals for transmission to the RFFE 521. The baseband / IF signals transmitted between the RF transceiver 522 and the processor system 530 can be digital or analog signals. The radio frequency transceiver 522 can be implemented by one or more chips, which are commonly referred to as radio frequency chips (RFICs).

[0143] In one example, processor system 530 may include one or more processors for processing signals and executing one or more communication protocols. Optionally, processor system 530 may also include memory 536. In one example, the one or more processors include at least one baseband processor 531 (also known as a modem processor). Memory 536 is used to store data and / or computer program instructions. Optionally, processor system 530 may also include one or more application processors 532 for implementing processing of the terminal operating system and application layer. Application processor 532 may include, for example, a GPU, NPU, AI processor, or ASIC. Optionally, processor system 530 may also include one or more of a voice subsystem 533, a multimedia subsystem 534, or an interface circuit 535. The voice subsystem 533 is used to process voice signals, the multimedia subsystem 534 is used to handle multimedia-related operations, such as video encoding / decoding, image processing, etc., and the interface circuit 535 is used to implement communication with other terminal components, such as a display 540, an input device 550, memory 560, etc. The above-mentioned components in processor system 530 can communicate with each other via a bus or communication interface circuit.

[0144] In one example, the processor system 530 can be packaged as a single processor chip, such as a SoC chip or a SIP chip. In another example, the processor system 530 can be a system of multiple chips, for example, the baseband processor 531 can be packaged as a single chip, or packaged with part or all of the circuitry of the radio frequency processing system into a single chip.

[0145] In one example, memory 536 can be on-chip memory, i.e., located on the processor system 530 chip. In another example, memory 560 can be off-chip memory, i.e. located outside the processor system 530 chip.

[0146] In one example, the baseband processor 531 may include one or more processor cores 5311 and interface circuitry 5314. The one or more processor cores 5311 are used to process signals and execute one or more communication protocols. Optionally, the baseband processor 531 may also include a memory 5312 for storing at least a portion of the corresponding computer program instructions and / or data. In one example, the one or more processor cores 5311 execute the computer program instructions stored in the memory 5312 to implement the relevant operations in the above method embodiments (e.g., generating category information of the first instruction described above). In this disclosure, memory 5312 is used to store corresponding computer program instructions and / or data. This can mean that memory 5312 stores all corresponding computer program instructions and / or data for execution by processor core 5311; or it can mean that memory 5312 stores a portion of corresponding computer program instructions and / or data, including the computer program instructions and / or data currently required to be executed by processor core 5311. Memory 5312 can store different portions of computer program instructions and / or data multiple times for execution by processor core 5311 to implement the relevant operations in the above method embodiments. Interface circuit 5314 serves as a communication interface for communication with other components, such as transmitting signals with radio frequency processing system 520, communicating with other subsystems and related components of processor system 530 via bus, such as transmitting data control signals with application processor 532, and transmitting data or computer program instructions with memory 536 or memory 560. Optionally, in order to reduce the load on the processor core, a baseband signal processing circuit 5313 can be set up to perform at least some baseband signal processing work, including one or more of signal demodulation, modulation, encoding or decoding.

[0147] In one example, the communication device provided in this application may be a terminal 500, a communication module including a processor system 530 and a radio frequency system 520, or a baseband processor 531.

[0148] The processor, processor system, application processor, baseband processor, processor circuit or processor core mentioned above can be collectively referred to as a processor. The processor may include one or more of the following: central processing unit (CPU), digital signal processor (DSP), microprocessor unit (MPU), microcontroller unit (MCU), GPU, field programmable gate array (FPGA), ASIC, AI processor or NPU.

[0149] The aforementioned memory may include one or more of the following storage media: random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), phase-change memory (PCM), resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), cache, register, read-only memory (ROM), flash memory, erasable programmable read-only memory (EPROM), hard disk, etc. In one example, computer program instructions for executing the above embodiments may be stored on non-volatile memory, such as at least a portion of the aforementioned memory 560 (e.g., one or more of ROM, flash memory, EPROM, or hard disk). When the terminal is running, the corresponding computer program instructions may be partially or wholly loaded onto a memory with a faster transfer speed than the processor, such as at least a portion of memory 536 and / or memory 5312 (e.g., one or more of RAM, SRAM, DRAM, PCM, RERAM, MRAM, FRAM, cache, or register), for the processor to execute in order to implement the steps in the above method embodiments.

[0150] In one example, the RF transceiver 522 and the RF front-end 521 can also be packaged in a single chip. In another example, the RF transceiver 522, the RF front-end 521, and the baseband processor 531 can also be packaged in a single chip.

[0151] The terms "system" and "network" in this application embodiment are used interchangeably. "At least one" refers to one or more, and "multiple" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, "at least one of A, B, or C" includes A, B, C, AB, AC, BC, or ABC; "at least one of A, B, and C" can also be understood as including A, B, C, AB, AC, BC, or ABC. Furthermore, unless otherwise specified, the ordinal numbers such as "first" and "second" mentioned in this application embodiment are used to distinguish multiple objects and are not used to limit the order, sequence, priority, or importance of multiple objects.

[0152] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, etc.) containing computer-usable program code.

[0153] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in one or more blocks of the flowchart illustrations and / or one or more blocks of the block diagrams.

[0154] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means that implement the functions specified in one or more flowcharts and / or one or more block diagrams.

[0155] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, such that the instructions, which execute on the computer or other programmable apparatus, provide steps for implementing the functions specified in one or more flowcharts and / or one or more block diagrams.

Claims

1. A communication method, characterized in that, include: Generate category information for a first instruction, wherein the category information is used to indicate the amount of data of the first data corresponding to the first instruction and / or the arrival time of the first data; as well as Send the category information.

2. The method according to claim 1, characterized in that, There is a first association between the first instruction and the category information.

3. The method according to claim 1 or 2, characterized in that, Also includes: Receive first configuration information, which is used to indicate the first association relationship.

4. The method according to claim 1 or 2, characterized in that, Also includes: Send second configuration information, which is used to indicate the first association relationship.

5. The method according to claim 4, characterized in that, Also includes: The first association is determined based on an artificial intelligence (AI) model, and the second configuration information is also used to instruct the AI ​​model.

6. The method according to any one of claims 1 to 5, characterized in that, The category information includes a first index, which corresponds to the amount of data in the first data and / or the arrival time of the first data.

7. The method according to any one of claims 1 to 6, characterized in that, The category information is transmitted via at least one of a dedicated tunnel, a dedicated bearer, or a dedicated Quality of Service (QoS) stream.

8. A communication device, characterized in that, include: Units for performing the method according to any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions that, when executed, cause the method according to any one of claims 1 to 7 to be performed.

10. A computer program product, characterized in that, Includes instructions for causing the method according to any one of claims 1 to 7 to be implemented.

Images