Communication method and communication apparatus

Abstract

A method for allocating an artificial intelligence (AI) task, and a communication apparatus. The method comprises: a terminal sends first information to a network device, the first information being used for indicating a computing power state of the terminal or a terminal module; and furthermore, the terminal receives second information from the network device, the second information being used for instructing the terminal to participate in an AI task supported by the computing power state. By using the method, the terminal can cooperatively participate in execution of the AI task, so that the execution efficiency of the AI task can be improved. In addition, the terminal reports the computing power state thereof, so that the network device can instruct the terminal to participate in the AI task matching the computing power state of the terminal, the allocation of the AI task is thus more reasonable, and the execution efficiency of the AI task can be further improved.

Description

Communication method and communication device

[0001] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office of China on January 18, 2024, with application number 202410073885.1 and invention name “A communication method and communication device”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The embodiments of the present application relate to the field of communications, and more specifically, to a method and a communication device for allocating artificial intelligence tasks. Background Art

[0003] Artificial intelligence (AI) is the application of computers or machines to perform tasks that typically require human intelligence, such as learning, problem solving, decision making, and natural language processing. AI tasks include, but are not limited to, tasks in areas such as machine learning, natural language processing, and computer vision. With the rapid development of AI technology, the computational complexity of AI tasks has also increased, leading to a surge in the demand for device computing power, which has severely constrained AI applications.

[0004] Faced with huge computing volume and computing power requirements, how to improve the execution efficiency of AI tasks is crucial to the development of AI. Summary of the Invention

[0005] This application provides a communication method that can improve the execution efficiency of AI tasks by reasonably allocating AI tasks.

[0006] In a first aspect, a communication method is provided. This method can be applied to a terminal, such as a terminal or a communication module within the terminal, or a circuit or chip within the terminal responsible for communication functions (such as a modem chip, also known as a baseband chip, or a system-on-chip (SoC) chip or system-in-package (SIP) chip containing a modem core). The following describes this method using a terminal as an example.

[0007] In this method, the terminal sends first information to the network device, where the first information is used to indicate the computing power status of the terminal or the terminal module; further, the terminal receives second information from the network device, where the second information is used to instruct the terminal to participate in the AI ​​task supported by the computing power status.

[0008] By adopting the above method, terminals can collaboratively participate in the execution of AI tasks, which can improve the execution efficiency of AI tasks.

[0009] On the other hand, the terminal reports its computing power status, so that the network device can instruct the terminal to participate in AI tasks that match its computing power status, thereby making the allocation of AI tasks more reasonable and further improving the execution efficiency of AI tasks.

[0010] In one possible design, the computing power status includes at least one of the following: computing power accuracy, computing speed, power, memory status, and the number of AI model parameters that can be calculated.

[0011] Based on the above scheme, this application can further refine the computing power status and describe it in a variety of different ways, so as to more accurately indicate the computing power status of the terminal or terminal module, and further improve the accuracy of AI task allocation.

[0012] In one possible design, the AI ​​task includes at least one of the following: AI-based data transmission, AI model parameter training, and AI model training data collection.

[0013] Based on the above solution, the AI ​​tasks can be further refined in this application so that the terminal can participate in AI tasks that are more suitable for itself, so that the AI ​​tasks can be allocated more accurately.

[0014] In combination with the first aspect, in some implementations of the first aspect, the method further includes: the terminal receives third information from the network device, and the third information is used to request the terminal to report the computing power status.

[0015] In this way, AI tasks can be allocated more reasonably and accurately, allowing terminals to better participate in the execution of AI tasks and improve efficiency.

[0016] In combination with the first aspect, in certain implementations of the first aspect, the method further includes: the terminal sending fourth information to the network device, where the fourth information is used to indicate whether the terminal participates in the AI ​​task.

[0017] In this way, the terminal can participate in AI tasks more reasonably, thereby maximizing the utilization of the terminal's computing resources.

[0018] In one possible design, the network device is a core network element or an access network device.

[0019] In a second aspect, a communication method is provided, which can be applied to the network side, such as an access network device on the network side, a module in the access network device (such as a circuit, a chip or a chip system), or a logical node, a logical module or software that can implement all or part of the functions of the access network device. For another example, a core network element on the network side, a module in the core network element (such as a circuit, a chip or a chip system), or a logical node, a logical module or software that can implement all or part of the functions of the core network element. The following is an example of the method being applied to a network device, which can be a core network element or an access network device.

[0020] In this method, a network device receives first information from a terminal, where the first information is used to indicate the computing power status of the terminal or a terminal module; further, the network device sends second information to the terminal, where the second information is used to instruct the terminal to participate in an AI task supported by the computing power status.

[0021] By adopting the above method, terminals can collaboratively participate in the execution of AI tasks, which can improve the execution efficiency of AI tasks.

[0022] On the other hand, the terminal reports its computing power status, so that the network device can instruct the terminal to participate in AI tasks that match its computing power status, thereby making the allocation of AI tasks more reasonable and further improving the execution efficiency of AI tasks.

[0023] In one possible design, the computing power status includes at least one of the following: computing power accuracy, computing speed, power, memory status, and the number of AI model parameters that can be calculated.

[0024] Based on the above scheme, this application can further refine the computing power status and describe it in a variety of different ways, so as to more accurately indicate the computing power status of the terminal or terminal module, and further improve the accuracy of AI task allocation.

[0025] In one possible design, the AI ​​task includes at least one of the following: AI-based data transmission, AI model parameter training, and AI model training data collection.

[0026] Based on the above solution, the AI ​​tasks can be further refined in this application, so that the AI ​​tasks can be allocated more accurately, allowing the terminal to participate in AI tasks that are more suitable for itself.

[0027] In combination with the second aspect, in certain implementations of the second aspect, the method further includes: the network device sends third information to the terminal, and the third information is used to request the terminal to report the computing power status.

[0028] In this way, AI tasks can be allocated more reasonably and accurately, allowing terminals to better participate in the execution of AI tasks and improve efficiency.

[0029] In combination with the second aspect, in certain implementations of the second aspect, the method further includes: the network device sends fifth information to the server, where the fifth information is used to indicate the AI ​​task.

[0030] In combination with the second aspect, in certain implementations of the second aspect, the method further includes: the network device receives fourth information from the terminal, where the fourth information is used to indicate whether the terminal participates in the AI ​​task.

[0031] In this way, the terminal can participate in AI tasks more reasonably, thereby maximizing the utilization of the terminal's computing resources.

[0032] In combination with the second aspect, in certain implementations of the second aspect, when the fourth information indicates that the terminal participates in the AI ​​task, the method further includes: the network device sends fifth information to the server, where the fifth information is used to indicate the AI ​​task.

[0033] In a third aspect, the present application provides a communication device, which has the function of implementing the above-mentioned first aspect. For example, the communication device includes a module or unit or means corresponding to performing the operations involved in the above-mentioned first aspect. The module or unit or means can be implemented through software, or through hardware, or through a combination of software and hardware.

[0034] In a fourth aspect, the present application provides a communication device, which has the function of implementing the above-mentioned second aspect. For example, the communication device includes a module or unit or means corresponding to the operation involved in the above-mentioned second aspect. The module or unit or means can be implemented by software, or by hardware, or by a combination of software and hardware.

[0035] In a fifth aspect, the present application provides a communication device comprising an interface circuit and one or more processors. The one or more processors are coupled to a memory. The memory is used to store part or all of the necessary computer programs or instructions for implementing the functions involved in the first aspect above. The one or more processors can execute the computer program or instructions. When the computer program or instructions are executed, the communication device implements the method in any possible design or implementation of the first aspect above. The interface circuit is used to implement the communication function within the communication device and / or the communication function of the communication device with other devices or components.

[0036] In one possible design, the processor is configured to communicate with other devices or components through the interface circuit.

[0037] In one possible design, the communication device may also include the memory.

[0038] The communication device may be a terminal, or a communication module in a terminal, or a chip in the terminal responsible for communication functions such as a modem chip (also known as a baseband chip) or a SoC or SIP chip including a modem module.

[0039] In a sixth aspect, the present application provides a communication device comprising an interface circuit and one or more processors. The one or more processors are coupled to a memory. The memory is used to store part or all of the necessary computer programs or instructions for implementing the functions involved in the second aspect above. The one or more processors can execute the computer program or instructions. When the computer program or instructions are executed, the communication device implements the method in any possible design or implementation of the second aspect above. The interface circuit is used to implement the communication function within the communication device and / or the communication function of the communication device with other devices or components.

[0040] In one possible design, the processor is configured to communicate with other devices or components through the interface circuit.

[0041] In one possible design, the communication device may also include the memory.

[0042] The above-mentioned communication device can be an access network device, or a module (such as a circuit, chip, or chip system) in the access network device, or a logical node, logical module, or software that can implement all or part of the functions of the access network device. The above-mentioned communication device can also be a core network element, or a module (such as a circuit, chip, or chip system) in the core network element, or a logical node, logical module, or software that can implement all or part of the functions of the core network element.

[0043] In a seventh aspect, the present application provides a communication system, which may include the communication device of the third aspect and the fourth aspect.

[0044] In an eighth aspect, the present application provides a computer-readable storage medium, which stores computer-readable instructions. When a computer reads and executes the computer-readable instructions, the computer executes the method in any possible design of the first to second aspects above.

[0045] In a ninth aspect, the present application provides a computer program product, which, when read and executed by a computer, enables the computer to execute the method in any possible design of the first to second aspects above.

[0046] It should be understood that the beneficial effects of the third to ninth aspects mentioned above can be referred to the first to second aspects and any possible implementation methods thereof, and will not be elaborated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] FIG1 is a schematic diagram of a communication system applicable to an embodiment of the present application.

[0048] 2 to 4 are schematic diagrams of the architecture of the communication system provided in the embodiments of the present application.

[0049] FIG5 is a schematic flowchart of a communication method provided by the present application.

[0050] FIG6 shows a possible exemplary block diagram of a communication device involved in an embodiment of the present application.

[0051] FIG7 is a schematic structural diagram of a terminal 1000 provided in an embodiment of the present application. DETAILED DESCRIPTION

[0052] The technical solution in this application will be described below with reference to the accompanying drawings.

[0053] FIG1 is a schematic diagram of a communication system applicable to an embodiment of the present application.

[0054] As shown in Figure 1 , the communications system 10 includes a radio access network (RAN) 100 and a core network (CN) 200. The RAN 100 includes at least one RAN node (e.g., 110a and 110b in Figure 1 , collectively referred to as 110) and at least one terminal (e.g., 120a-120j in Figure 1 , collectively referred to as 120). The RAN 100 may also include other RAN nodes, such as wireless relay equipment and / or wireless backhaul equipment (not shown in Figure 1 ). The terminal 120 is wirelessly connected to the RAN node 110. The RAN node 110 is wirelessly or wiredly connected to the core network 200. The core network equipment in the core network 200 and the RAN node 110 in the RAN 100 may be separate physical devices, or they may be a single physical device that integrates core network logical functions and radio access network logical functions.

[0055] The RAN 100 may be a cellular system related to the Third Generation Partnership Project (3GPP), such as a fourth generation (4G) mobile communication system, a fifth generation (5G) mobile communication system, or a future-oriented evolution system (e.g., a sixth generation (6G) mobile communication system). The RAN 100 may also be an open access network (O-RAN or ORAN), a cloud radio access network (CRAN), or a wireless fidelity (WiFi) system. The RAN 100 may also be a communication system that integrates two or more of the above systems.

[0056] RAN node 110, sometimes also referred to as access network equipment, RAN entity, or access node, constitutes part of the communication system and facilitates wireless access for terminals. Multiple RAN nodes 110 in the 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, network element 120i in Figure 1 can be a helicopter or drone, which can be configured as a mobile base station. For terminal 120j accessing RAN 100 via 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, network elements 110a and 110b in Figure 1 can be understood as communication devices with base station functionality, and network elements 120a-120j can be understood as communication devices with terminal functionality.

[0057] In one possible scenario, a RAN node may be a base station, an evolved NodeB (eNodeB), an access point (AP), a transmission reception point (TRP), a next generation NodeB (gNB), a next generation base station in a sixth generation (6G) mobile communication system, a base station in a future mobile communication system, or an access node in a WiFi system. A RAN node may be a macro base station (such as 110a in FIG1 ), a micro base station or an indoor station (such as 110b in FIG1 ), a relay node or a donor node, or a wireless controller in a CRAN scenario. Optionally, a RAN node may also be a server, a wearable device, a vehicle or an onboard device. For example, an access network device in vehicle to everything (V2X) technology may be a road side unit (RSU). All or part of the functions of the RAN node in this application may also be implemented by software functions running on hardware, or by virtualized functions instantiated on a platform (such as a cloud platform). The RAN node may also be provided with a communication module, circuit, or chip that performs the corresponding communication functions. The RAN node may also be configured with program instructions for performing the corresponding communication functions and corresponding program instructions. The RAN node in this application may also be a logical node, logical module, or software that can implement all or part of the RAN node functions.

[0058] In another possible scenario, multiple RAN nodes collaborate to assist the terminal in achieving wireless access, and different RAN nodes respectively implement part of the functions of the base station. For example, the RAN node can be a centralized unit (CU), a distributed unit (DU), a CU-control plane (CP), a CU-user plane (UP), or a radio unit (RU). The CU and DU can be set separately, or they can be included in the same network element, such as a baseband unit (BBU). The RU can be included in a radio frequency device or radio frequency unit, such as a remote radio unit (RRU), an active antenna unit (AAU), or a remote radio head (RRH).

[0059] In different systems, CU (or CU-CP and CU-UP), DU or RU may also have different names, but those skilled in the art can understand their meanings. For example, in the ORAN system, CU may also be called O-CU (Open CU), DU may also be called O-DU, CU-CP may also be called O-CU-CP, CU-UP may also be called O-CU-UP, and RU may also be called O-RU. For the convenience of description, this application uses CU, CU-CP, CU-UP, DU and RU as examples for description. Any unit of CU (or CU-CP, CU-UP), DU and RU in this application can be implemented by a software module, a hardware module, or a combination of a software module and a hardware module.

[0060] Terminal 120 can be a device or module that accesses the aforementioned communication system and has corresponding communication functions. A terminal can also be referred to as a terminal device, user equipment (UE), mobile station, mobile terminal, etc. Terminals can be widely used in various scenarios, such as device-to-device (D2D), vehicle-to-everything (V2X) communication, machine-type communication (MTC), the 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. A terminal can be a mobile phone, tablet computer, computer with wireless transceiver functions, wearable device, vehicle, drone, helicopter, airplane, ship, robot, robotic arm, smart home appliance, transport vehicle with wireless communication functions, communication module, etc. The embodiments of this application do not limit the device form of the terminal. The terminal is typically provided with a communication module, circuit, or chip that performs the corresponding communication functions. The terminal is also configured with program instructions for performing the corresponding communication functions.

[0061] It is understood that Figure 1 is only an example and does not limit the scope of protection of this application. The communication method provided in the embodiment of this application may also involve network elements not shown in Figure 1. Of course, the communication method provided in the embodiment of this application may also include only some of the network elements shown in Figure 1.

[0062] FIG2 is a schematic diagram of the architecture of a communication system provided in an embodiment of the present application.

[0063] As shown in Figure 2, the communication system may include a server, a data network (DN), a core network, access network equipment, and terminals. The core network includes network openness elements, application elements, policy control elements, session management elements, access management elements, and user plane elements. The communication system shown in Figure 2 can also be referred to as a server-network-terminal architecture. The following describes each component involved in this communication system.

[0064] (1) For an introduction to access network devices and terminals, please refer to the above. Terminals can include head-mounted extended reality (XR) glasses, video players, holographic projectors, mobile phones, computers, robots, and other devices.

[0065] (2) Data network DN: provides, for example, operator services, Internet access, or third-party services.

[0066] (3) Server: implements video source encoding, rendering, etc.

[0067] (4) Core Network: This refers to the equipment in the core network (CN) that provides service support for terminals. The core network is responsible for completing three major functions: registration, connection, and session management. Currently, some examples of core network equipment include: application network elements, network open network elements, policy control network elements, session management network elements, access management network elements, and user plane network elements. The following is a detailed description of these network elements in the core network.

[0068] Application network element: In the 5G communication system, the application network element can be an application function (AF) network element, which represents the application function of a third party or operator. It is the interface for the 5G network to obtain external application data and is mainly used to convey the requirements of the application side to the network side.

[0069] Network open network element: In the long term evolution (LTE) communication system, the network open network element may be a service capability exposure function (SCEF) network element. In the 5G communication system, the network open network element may be a network element function (NEF) network element, which is mainly used to expose the services and capabilities of the 3GPP network function to the AF, and also allows the AF to provide information to the 3GPP network function.

[0070] Session management network element: It is mainly used for session management, terminal Internet protocol (IP) address allocation and management, selection of endpoints for manageable user plane functions, policy control and charging function interfaces, and downlink data notification. In LTE communication systems, the session management network element can be a serving gateway control plane (SGW-C) or a packet data network gateway control plane (PGW-C), or a network element that is a combination of SGW-C and PGW-C. In 5G communication systems, the session management network element can be a session management function (SMF) network element, which completes terminal IP address allocation, UPF selection, and billing and QoS policy control.

[0071] Access management network element: It is mainly used for mobility management and access management, and can be used to implement other functions of the mobility management entity (MME) in addition to session management, such as lawful interception and access authorization / authentication. In the LTE communication system, the access management network element can be an MME network element. In the 5G communication system, the access management network element can be an access and mobility management function (AMF), which mainly performs functions such as mobility management and access authentication / authorization. In addition, it is also responsible for transmitting user policies between the terminal and the policy control function (PCF) network element.

[0072] Policy control network element: includes user subscription data management function, policy control function, charging policy control function, quality of service (QoS) control, etc., a unified policy framework for guiding network behavior, and providing policy rule information for control plane function network elements (such as AMF, SMF network elements, etc.). In the LTE communication system, the policy control network element can be a policy control and charging function (PCRF). In the 5G communication system, the policy control network element can be a PCF network element. In the 5G communication system, the application network element can be a network slice selection function (NSSF) network element.

[0073] User plane network element: Serves as the interface with the data network, performing functions such as user plane data forwarding, session / flow-level billing and statistics, and bandwidth limiting. This includes packet routing and forwarding, as well as quality of service (QoS) processing for user plane data. In LTE communication systems, this user plane network element can be the serving gateway user plane (SGW-U), the packet data network gateway user plane (PGW-U), or a combination of the SGW-U and PGW-U. In 5G communication systems, this user plane network element can be the user plane function (UPF) network element.

[0074] As shown in Figure 2, in the core network, the application network element and the network open network element are connected via the N33 interface, the application network element and the policy control network element are connected via the N5 interface, the policy control network element and the session management network element are connected via the N7 interface, the session management network element and the access management network element are connected via the N11 interface, the session management network element and the user plane network element are connected via the N4 interface, and the user plane network element and the data network are connected via the N6 interface. In the communication system shown in Figure 2, the data network may include a server, the data network or the server is connected to the user plane network element via the N6 interface, the user plane network element is connected to the access network device via the N3 interface, and the access network device is connected to the terminal via the Uu interface.

[0075] In future communication systems, such as 6G communication systems, the above-mentioned network elements or devices may still use their names in 4G or 5G communication systems, or may have other names, and this is not limited in the embodiments of the present application. The functions of the above-mentioned network elements or devices may be completed by an independent network element or by several network elements. In actual deployment, the network elements in the core network may be deployed on the same or different physical devices. For example, as a possible deployment, AMF and SMF may be deployed on the same physical device. For another example, the network elements of the 5G core network may be deployed on the same physical device as the network elements of the 4G core network. This is not limited in the embodiments of the present application.

[0076] In addition, the above interface names are only examples and are not limited in this application.

[0077] FIG3 is a schematic diagram of the architecture of another communication system provided in an embodiment of the present application.

[0078] As shown in Figure 3, the communication system includes Terminal #1, Access Network Device #1, User Plane Network Element, Access Network Device #2, and Terminal #2. This communication system can also be referred to as a terminal-to-terminal communication network. For example, in the Tactile Internet, Terminal #1 serves as the interface between the tactile user in the primary domain and the artificial system, while Terminal #2 serves as a remote-controlled robot or remote operator in the controlled domain. The primary domain receives audio / video feedback signals from the controlled domain. The primary and controlled domains are connected via a bidirectional communication link on the network domain, aided by various command and feedback signals, thus forming a global control loop. The communication system shown in Figure 3 can also be referred to as a terminal-network-terminal architecture.

[0079] FIG4 is a schematic diagram of the architecture of another communication system provided in an embodiment of the present application.

[0080] As shown in Figure 4, the communication system includes a server, a fixed network, a WiFi router (or a WiFi access point; or a set-top box), and a terminal. The cloud server transmits large amounts of media data (e.g., XR data) or standard video data to the terminal via the fixed network and WiFi router. The communication system shown in Figure 4 can also be referred to as a WiFi architecture.

[0081] It should be understood that the architecture of the communication system shown in Figures 1 to 4 above is only an example, and the network architecture applicable to the embodiments of the present application is not limited to this. Any network architecture that can realize the functions of the above-mentioned network elements is applicable to the embodiments of the present application.

[0082] Artificial intelligence (AI) is the application of computers or machines to perform tasks that typically require human intelligence, such as learning, problem solving, decision making, and natural language processing. AI tasks include, but are not limited to, tasks in areas such as machine learning, natural language processing, and computer vision.

[0083] The size of AI tasks can be reflected in AI models. In recent years, AI models such as the chat generative pre-trained transformer (ChatGPT) have played a positive role in promoting generative AI with their outstanding natural language and multimodal understanding capabilities. However, these AI models, with their large number of parameters and training data, have led to a surge in demand for computing power. In other words, the computational complexity of AI tasks is increasing, and the computing power required is also increasing, which seriously restricts the application and development of AI.

[0084] With the continuous development of science and technology, terminals have also acquired a certain level of computing power and can handle certain AI calculations. Therefore, different nodes in the communication system, such as terminals, can also participate in the execution of AI tasks, improving the efficiency of AI task execution.

[0085] When different nodes in a communication system participate in the execution of AI tasks, how to reasonably allocate AI tasks will affect the execution efficiency of AI tasks.

[0086] In view of this, the present application provides a communication method that can improve the execution efficiency of AI tasks by reasonably allocating AI tasks.

[0087] The communication method and device provided by the present application are further described below in conjunction with the accompanying drawings. It can be understood that the present application uses network devices, terminals and servers as examples of the execution subjects of the interactive diagram, but the present application does not limit the execution subjects of the interactive diagram. For example, the method executed by the network device in the present application can also be implemented by a module in the network device (such as a circuit, chip or chip system, etc.), or a logical node, logic module or software that can implement all or part of the network function; the method executed by the terminal in the present application can also be implemented by a communication module in the terminal or a circuit or chip in the terminal responsible for the communication function (such as a modem chip (also known as a baseband chip), or a SoC chip containing a modem core, or a SIP chip); the method executed by the server in the present application can also be implemented by a module in the server (such as a circuit, chip or chip system, etc.), or a logical node, logic module or software that can implement all or part of the server.

[0088] Figure 5 is a schematic flow chart of a communication method provided by the present application. As shown in Figure 5, the method 500 may include the following steps.

[0089] S510: The terminal sends first information to the network device, and correspondingly, the network device receives the first information.

[0090] Among them, the first information is used to indicate the computing power status of the terminal or terminal module, and the first information can also be called reporting information.

[0091] The first information may indicate the computing power status of the terminal or the computing power status of a terminal module in the terminal. The terminal module may be a communication module in the terminal or a circuit or chip in the terminal responsible for communication functions, wherein the chip may be a modem chip (also known as a baseband chip), a SoC chip containing a modem core, or a SIP chip.

[0092] Computing power refers to the amount of data a computer or other computing device can process or the number of computing tasks it can complete within a certain period of time. Computing power is often used to describe the performance of a computer or other computing device. It is an important indicator of the processing power of a computing device. Computing power can be measured in various ways, such as computing speed, computing energy consumption, computing accuracy, parallelism, etc. In this application, computing power status includes at least one of the following: computing power accuracy, computing speed, power consumption, memory status, and the number of AI model parameters that can be calculated.

[0093] It should be understood that computing power status can be divided into basic computing power state (BCS) and real-time computing power state (RCS). Basic computing power state reflects the inherent computing power level of the terminal or terminal module, such as computing power accuracy and calculation speed. Real-time computing power state reflects the computing power level that changes continuously based on the terminal's usage status, such as battery level, memory status, and the number of AI model parameters that can be calculated. The following is a brief description of these computing power states.

[0094] (1) Computing power precision (precision) can also be called the number of digits of precision or calculation accuracy. It refers to the highest number of digits of calculation accuracy that a terminal or terminal module can support and is the inherent computing power level of the terminal or terminal module. Computing power precision can include integer (INT), half-precision, single-precision, double-precision, etc. Among them, integer can be divided into 8-bit integer (INT 8), 4-bit integer (INT 4), 2-bit integer (INT 2), etc. Half-precision refers to 16-bit floating point number (Float 16), single-precision refers to 32-bit floating point number (Float 32), and double-precision refers to 64-bit floating point number (double 64).

[0095] As an example, the computing power precision can be represented as a 1-bit, 2-bit, or 3-bit field. For example, if the field is 2 bits, the mapping relationship between its value and computing power precision is shown in Table 1.

[0096] Table 1

[0097] It should be understood that the mapping relationship in Table 1 is only an example, and the computing power precision can also be indicated by more or fewer bits. For example, the number of bits can be increased to represent the computing power precision of INT4 and INT2 types.

[0098] (2) Computing speed, which refers to the level of computing speed supported by a terminal or terminal module. This level can be a maximum, average, or minimum value. For example, computing speed refers to the maximum computing speed supported by a terminal or terminal module. In this case, computing speed can also be called computing-bound.

[0099] For example, the unit of computing speed may be floating-point operations per second (TFLOPS), tera operations per second (TOPS), instructions per second (IPS), or transactions per second (TPS), or other units.

[0100] For reference, the computing speed of some mobile terminals can reach up to 15TOPs, the computing speed of some notebooks with Float16 precision can reach 2TFLOP, and the computing speed of some graphics cards can reach 256TFLOPS or 460TFLOPS.

[0101] As an example, the calculation speed can be represented as a 1-bit, 2-bit, or 3-bit field. For example, the field is 2 bits, and the mapping relationship between its value and the calculation speed is shown in Table 2.

[0102] Table 2

[0103] It should be understood that the mapping relationship in Table 2 is only an example, and the computing power accuracy can also be indicated by more or fewer bits, or by other units.

[0104] (3) Power reflects the energy consumption of the terminal. Power can be expressed as a percentage of remaining power or a percentage of used power.

[0105] As an example, the power level can be represented as a 1-bit, 2-bit, or 3-bit field. For example, the field is 2 bits, and the mapping relationship between its value and power level is shown in Table 3.

[0106] Table 3

[0107] It should be understood that the ratios in Table 3 may represent the ratios of remaining power. The mapping relationship in Table 3 is merely an example, and the power level may also be indicated using more or fewer bits, or in other ways.

[0108] (4) Memory status can also be called memory condition, which refers to the usage of the storage unit in the terminal. It can be represented by the occupancy rate of the storage unit or the remaining rate of the storage unit.

[0109] In the present application, the storage unit can be implemented by a memory. For the description of the memory, reference can be made to the description in the subsequent device embodiments of the present application.

[0110] As an example, the memory status can be represented as a 1-bit, 2-bit, or 3-bit field. For example, the field is 2 bits, and the mapping relationship between its value and the memory status is shown in Table 4.

[0111] Table 4

[0112] It should be understood that the ratio in Table 4 can represent the memory occupancy rate. The mapping relationship in Table 4 is only an example, and the memory status can also be indicated by more or fewer bits, or in other ways.

[0113] (5) The number of AI model parameters that can be calculated reflects the scale of AI model parameters that can be inferred and calculated by the terminal or terminal module. Model parameters may include weight parameters, bias parameters, normalization coefficients, activation parameters, etc. The number of AI model parameters can also be referred to as the number of neural network model parameters. The number of AI model parameters that can be calculated can also be referred to as the computing power level.

[0114] Among them, the number of AI model parameters that the terminal or terminal module can calculate is related to the real-time status of the terminal. The terminal can determine the number of AI model parameters it can calculate based on real-time status such as power level and memory status.

[0115] As an example, the unit of the number of AI model parameters can be million (M) or billion (B). According to the number of AI model parameters, AI models can be divided into shallow models, small models, and large models.

[0116] It should be understood that the above classification method is only an example. There is no fixed standard for the classification of AI models. They can be divided based on the number of AI model parameters that the terminal can calculate as a reference value.

[0117] Among them, the terminal can indicate to the network device the number of AI model parameters it can calculate in the following two ways.

[0118] Method 1: The terminal directly indicates the number of AI model parameters it can calculate.

[0119] As an example, the number of AI model parameters that a terminal or terminal module can calculate can be represented as a 1-4 bit field. For example, the field is 2 bits, and its value and the number of AI model parameters have the following mapping relationship, as shown in Table 5.

[0120] Table 5

[0121] It should be understood that the mapping relationship in Table 5 is only an example, and the number of AI model parameters can also be indicated by more or fewer bits.

[0122] Method 2: The network device indicates the number of AI model parameters to the terminal, and the terminal indicates whether it can calculate the AI ​​model parameters of that order by providing feedback of yes or no.

[0123] As an example, a network device can use a 1- to 4-bit field to indicate the number of AI model parameters to be calculated. For example, this field is 2 bits, and its value and the number of AI model parameters have the mapping relationship shown in Table 5. A terminal can use a 1-bit field to provide feedback on whether it can calculate AI model parameters of a certain order of magnitude. The value of this field and the number of AI model parameters that the terminal or terminal module can calculate have the mapping relationship shown in Table 6.

[0124] Table 6

[0125] It should be understood that the mapping relationship in Table 6 is only an example. The terminal may not provide feedback, which means that the terminal does not participate in the calculation of the AI ​​model parameters.

[0126] S520: The network device sends second information to the terminal, and correspondingly, the terminal receives the second information.

[0127] The second information is used to instruct the terminal to participate in the AI ​​task supported by the computing power state. The second information can also be called task indication information.

[0128] In this application, the AI ​​task supported by the computing power state can be understood as: the computing power state supports the execution of the AI ​​task, or the AI ​​task that matches the computing power state, or the AI ​​task that can be executed by the computing power state, that is, the AI ​​task requires this level of computing power state to be executed.

[0129] In other words, the network device may determine the second information based on the first information.

[0130] Among them, AI tasks include but are not limited to tasks in the fields of machine learning, natural language processing, computer vision, etc. These tasks include classification, regression, clustering, sequence generation, reinforcement learning, etc. To achieve the above tasks, processes such as data collection, model training, model reasoning, and model testing are required. In this application, AI tasks include at least one of the following: AI-based data transmission, AI model parameter training, and AI model training data collection. The following is a brief description of these AI tasks.

[0131] (1) AI-based data transmission, also known as neural network-based transmission. AI-based model transmission is a method of data transmission that relies on the feature extraction and recovery of the AI ​​network, or in other words, on the feature encoding and decoding process of the AI ​​network. AI-based data transmission can be understood as the process of AI model inference.

[0132] Specifically, traditional video coding methods rely on complex manually designed algorithms, which make it difficult to effectively utilize the complex correlations between pixel blocks within and between video frames. Neural video coding (NVC) is a video coding method based on neural networks. NVC uses a neural network model to learn the characteristics and compression methods of video coding. It first preprocesses and extracts features from the video sequence, and then uses the neural network to learn the representation of these features and perform lossy or lossless compression. Compared with traditional manually designed coding schemes, NVC has powerful nonlinear coding capabilities, can effectively extract video features, and improve video compression capabilities. AI-based data transmission refers to first encoding the data to be transmitted based on NVC, and then transmitting the encoded data.

[0133] (2) AI model parameter training refers to adjusting model parameters using known data to generate a model that can solve a specific problem. The goal of training is to maximize the accuracy of the model's predictions or classifications. The training process can be understood as a continuous iterative process. AI model parameter training can be understood as AI model training or neural network model training.

[0134] (3) AI model training data collection: refers to the collection of data needed for AI model parameter training. Training data is also called perception data.

[0135] It should be understood that computing power and AI are closely related, as AI generally requires a large amount of computing power for training and reasoning. In this application, the network device can determine the corresponding AI task based on the computing power status reported by the terminal, so that the terminal can participate in the AI ​​task that matches its computing power status.

[0136] Specifically, when the computing power of the terminal is at a high level, it can perform a certain degree of computational reasoning and can implement AI-based encoding and decoding. At this time, the network device can instruct the terminal to participate in AI-based data transmission. When the computing power of the terminal reaches a level that can participate in model parameter training, the network device can instruct the terminal to participate in AI model parameter training. When the network device has a need to collect data and the channel transmission status is good, if the network device determines that the terminal has sufficient power based on the computing power status, the network device can instruct the terminal to participate in the collection of training data.

[0137] As an example, when the computing power accuracy is INT8, the computing speed is 100FLOPS, the power is 90%, the memory status is 40%, and the number of AI model parameters that can be calculated is <10M, the AI ​​task can be training data collection or model inference.

[0138] As another example, when the computing power accuracy is Float32, the computing speed is 30FLOPS, the power is 90%, the memory status is 40%, and the number of AI model parameters that can be calculated is <10M, the AI ​​task can be training data collection, AI-based data transmission, or AI model parameter training.

[0139] It should be understood that the network device may instruct the terminal to participate in one or more AI tasks. For example, the network device may instruct the terminal to participate in AI model parameter training and training data collection.

[0140] Optionally, the AI ​​tasks that the network device instructs the terminal to participate in may also include AI model reasoning, AI model testing, etc.

[0141] In addition to instructing terminals to participate in AI tasks, network devices can also instruct terminals to participate in non-AI tasks. For example, they can instruct terminals to perform regular transmissions, not to participate in training, or not to collect training data. Regular transmission means encoding the data to be transmitted based on traditional video coding methods and then transmitting the encoded data, or in other words, transmitting content according to existing transmission protocols.

[0142] The second information may be multiple information elements. For example, if AI tasks are divided into three categories, the second information may be three information elements, each of which is 1 bit. Each information element corresponds to an AI task and is used to indicate whether the terminal participates in the AI ​​task. Specifically, as shown in Table 7.

[0143] Table 7

[0144] Based on the above solution, terminals can collaboratively participate in the execution of AI tasks, which can improve the execution efficiency of AI tasks.

[0145] On the other hand, the terminal can report its computing power status, so that the network device can instruct the terminal to participate in AI tasks supported by the computing power status, thereby making the allocation of AI tasks more reasonable and further improving the execution efficiency of AI tasks.

[0146] Furthermore, AI models tend to be deployed jointly on the cloud and the terminal, allowing the terminal to collaboratively participate in the execution of AI tasks, which can achieve a more reasonable deployment of AI models.

[0147] Optionally, the method 500 further includes: S501, the network device sends third information to the terminal, and correspondingly, the terminal receives the third information.

[0148] The third information is used to request the terminal to report the computing power status. The third information can also be called request information.

[0149] Specifically, the network device can determine whether the terminal needs to participate in the AI ​​task. When necessary, it requests the terminal to report its computing power status through the third information, so as to determine the AI ​​task that matches the computing power status.

[0150] In this way, AI tasks can be allocated more reasonably and accurately, allowing terminals to better participate in the execution of AI tasks and improve efficiency.

[0151] Exemplarily, the third information may be 1 bit, and its values ​​0 and 1 are respectively used to indicate whether the terminal needs to report computing power information.

[0152] Optionally, as an implementation, in S510, if the terminal feeds back the number of AI model parameters it can calculate using the second method described above, the network device may indicate the number of AI model parameters to the terminal via third information. For example, the third information may be 2 bits, which indicate the number of AI model parameters to be calculated by the network device (see Table 5 for the mapping relationship). These 2 bits also instruct the terminal to report computing power information.

[0153] Optionally, the method 500 further includes: S530, the terminal sends fourth information to the network device, and correspondingly, the network device receives the fourth information.

[0154] The fourth information is used to indicate whether the terminal participates in the AI ​​task. The fourth information can also be called response information.

[0155] Specifically, the terminal can determine whether to participate in the AI ​​task instructed by the network device based on its current computing power status, and instruct the network device through the fourth information.

[0156] It should be understood that after the terminal reports the computing power status, the terminal's computing power status may change. Therefore, when the terminal receives the second information, if the terminal's current computing power status cannot perform the AI ​​task indicated by the second information, the terminal can indicate to the network device through the fourth information that it will not participate in the AI ​​task. If the terminal's current computing power status can still perform the AI ​​task indicated by the second information, the terminal can indicate to the network device through the fourth information that it will participate in the AI ​​task.

[0157] In this way, the terminal can participate in AI tasks more reasonably, thereby maximizing the utilization of the terminal's computing resources.

[0158] Exemplarily, when the second information includes 3 information elements, the fourth information may also be 3 bits, each bit corresponding to an AI task, indicating whether the terminal participates in the AI ​​task.

[0159] Optionally, S530 may not be executed, that is, the terminal receives the instruction of the network device by default and participates in the AI ​​task determined by the network device.

[0160] In this way, resources can be saved and overhead can be reduced.

[0161] Optionally, the method 500 includes: S540, the network device sends fifth information to the server, and accordingly, the application server receives the fifth information.

[0162] The fifth information is used to indicate the AI ​​task and can also be called notification information.

[0163] Specifically, the network device can notify the server terminal of the AI ​​task in which it will participate, so that the server can schedule and allocate AI tasks for different users.

[0164] In this application, the server may refer to an application server (AS).

[0165] Specifically, the implementation of S530 and S540 includes two cases:

[0166] Case 1: S530 is not executed, but S540 is executed. Specifically, after S520, the terminal will participate in the AI ​​task according to the instruction of the second information, without feedback on whether to participate in the AI ​​task (i.e., S530 is not executed). At this time, the network device will notify the server of the AI ​​task in which the terminal participates (i.e., S540 is executed).

[0167] Case 2: S530 is executed, and if the fourth information indicates that the terminal participates in the AI ​​task, S540 is executed. Specifically, after S520, the terminal needs to feedback whether it participates in the AI ​​task (i.e., execute S530). Based on the feedback from the terminal, the network device will notify the server of the AI ​​task in which the terminal participates (i.e., execute S540) only when the terminal participates in the AI ​​task. If the terminal feedbacks that it does not participate in the AI ​​task indicated by the network device, the network device will not notify the server of the AI ​​task (i.e., S540 is not executed).

[0168] As an implementation manner, the network device is an access network device.

[0169] In this implementation, the first information can be carried in uplink control information (UCI), user assistant information (UAI) in radio resource control (RRC) signaling, or media access control layer control element (MAC CE). Similarly, the fourth information can also be carried in UCI, UAI or MAC CE.

[0170] In this implementation, the second information may be carried in downlink control information (DCI), RRC signaling, or MAC CE. Similarly, the third information may be carried in DCI, RRC signaling, or MAC CE.

[0171] It should be understood that in this implementation, the access network device can communicate with the server through the core network element.

[0172] As another implementation manner, the network device is a core network element.

[0173] For example, the core network element is an access management network element, and the first information may be carried in non-access stratum (NAS) signaling. Similarly, the second information, the third information, and the fourth information may also be carried in NAS signaling.

[0174] For example, the core network element is a newly added network element, for example, it can be called a computing network element, which is used to execute AI tasks, and it can also allocate part of the AI ​​tasks to the terminal according to the computing power status of the terminal.

[0175] It should be understood that in this implementation, the core network element can communicate with the terminal through the access network device.

[0176] It should be understood that in the various embodiments of the present application, unless otherwise specified or there is a logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced to each other, and the technical features in different embodiments can be combined to form new embodiments according to their internal logical relationships.

[0177] It should also be understood that in some of the above embodiments, the devices in the existing network architecture are mainly used as examples for illustrative description (such as network devices, terminal devices, etc.), and it should be understood that the embodiments of the present application are not limited to the specific form of the devices. For example, devices that can achieve the same functions in the future are applicable to the embodiments of the present application.

[0178] It is understandable that in the above-mentioned various method embodiments, the methods and operations implemented by devices (such as network devices, terminal devices) can also be implemented by components of the devices (such as chips or circuits).

[0179] In this application, "sending information" can be understood as one device sending information to another device, or as one logic module within a device sending information to another logic module. For example, "a network device sending information" can be understood as the network device sending information to another device (such as a terminal), or as logic module 1 within the network device sending information to logic module 2 within the network device.

[0180] In this application, "receiving information" can be understood as one device receiving information from another device, or it can also be understood as a logic module within a device receiving information from another logic module. For example, "a network device receiving information" can be understood as the network device receiving information from another device (such as a terminal), or it can be understood as logic module 1 in the network device receiving information from logic module 2 in the network device.

[0181] In addition, in this application, "sending information to... (access network device)" can be understood as the destination end of the information being the access network device. This can include sending information directly or indirectly to the access network device. "Receiving information from... (access network device)" can be understood as the source end of the information being the access network device, which can include receiving information directly or indirectly from the access network device. The information may undergo necessary processing between the source end and the destination end of the information transmission, such as format changes, etc., but the destination end can understand the valid information from the source end. Similar expressions in this application can be understood similarly and will not be repeated here.

[0182] The communication method provided by the embodiment of the present application is described in detail above with reference to Figures 1 to 5. The communication device provided by the embodiment of the present application is described in detail below with reference to Figures 6 to 7.

[0183] FIG6 shows a possible exemplary block diagram of a communication device involved in an embodiment of the present application. As shown in FIG6 , a communication device 900 may include modules or units corresponding to the above-described method embodiments. In one possible design, the communication device 900 includes an interface unit 903. Optionally, the communication device 900 may also include a processing unit 902 and a storage unit 901 for storing device program code and / or data. The interface unit 903 may also be referred to as a communication interface, a transceiver unit, or a communication unit.

[0184] The communication device 900 may be the terminal-side device in the above-mentioned embodiment, for example, a terminal or a communication module in the terminal, or a circuit or chip in the terminal responsible for the communication function.

[0185] For example, in one embodiment, the interface unit 903 is used to: send first information to the network device, where the first information is used to indicate the computing power status of the terminal or terminal module; the interface unit 903 is also used to: receive second information from the network device, where the second information is used to indicate that the terminal participates in an AI task supported by the computing power status.

[0186] In one possible design, the computing power status includes at least one of the following: computing power accuracy, computing speed, power, memory status, and the number of AI model parameters that can be calculated.

[0187] In one possible design, the AI ​​task includes at least one of the following: AI-based data transmission, AI model parameter training, and AI model training data collection.

[0188] In one possible design, the interface unit 903 is also used to: receive third information from the network device, and the third information is used to request the terminal to report the computing power status.

[0189] In one possible design, the interface unit 903 is further used to: send fourth information to the network device, where the fourth information is used to indicate whether the terminal participates in the AI ​​task.

[0190] In one possible design, the network device is a core network element or an access network device.

[0191] In one possible design, when the communication device 900 is a terminal or a communication module in a terminal, the functions of the processing unit 902 may be implemented by one or more processors. Specifically, the processor may include a modem chip, or a system-on-chip (SoC) chip or SIP chip containing a modem core. The functions of the communication unit 903 may be implemented by a transceiver circuit.

[0192] In one possible design, when the communication device 900 is a circuit or chip responsible for communication functions in a terminal, such as a modem chip or a system-on-chip (SoC) chip or SIP chip containing a modem core, the functions of the processing unit 902 can be implemented by a circuit system including one or more processors or processor cores in the aforementioned chip. The functions of the communication unit 903 can be implemented by an interface circuit or data transceiver circuit on the aforementioned chip.

[0193] It should be understood that the communication device 900 may also include an AI chip. Specifically, a chip that can run an AI algorithm can be called an AI chip, or a chip that has been specially designed for acceleration of an AI algorithm can be called an AI chip. An AI chip may also be called an AI accelerator or computing card, which is used to process computing tasks in AI applications, while other non-AI computing tasks may still be handled by the central processing unit (CPU). AI chips may include graphics processing units (GPUs), field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), artificial intelligence processors (AI processors), neural processing units (NPUs), and the like.

[0194] The communication device 900 may be a network-side device in the above-mentioned embodiments, for example, an access network device, or a module (such as a circuit, chip, or chip system) in the access network device, or a logical node or logic module that can implement all or part of the functions of the access network device. Another example is a core network element, or a module (such as a circuit, chip, or chip system) in the core network element, or a logical node or logic module that can implement all or part of the functions of the core network element.

[0195] For example, in one embodiment, the interface unit 903 is used to: receive first information from the terminal, where the first information is used to indicate the computing power status of the terminal or the terminal module; and the interface unit 903 is also used to: send second information to the terminal, where the second information is used to instruct the terminal to participate in an AI task supported by the computing power status.

[0196] In one possible design, the computing power status includes at least one of the following: computing power accuracy, computing speed, power, memory status, and the number of AI model parameters that can be calculated.

[0197] In one possible design, the AI ​​task includes at least one of the following: AI-based data transmission, AI model parameter training, and AI model training data collection.

[0198] In one possible design, the interface unit 903 is further used to: send third information to the terminal, and the third information is used to request the terminal to report the computing power status.

[0199] In one possible design, the interface unit 903 is further used to: send fifth information to the server, where the fifth information is used to indicate the AI ​​task.

[0200] In one possible design, the interface unit 903 is further used to: receive fourth information from the terminal, where the fourth information is used to indicate whether the terminal participates in the AI ​​task.

[0201] In one possible design, when the fourth information indicates that the terminal participates in the AI ​​task, the interface unit 903 is further used to: send fifth information to the server, where the fifth information is used to indicate the AI ​​task.

[0202] In one possible design, when the communication device 900 is a network device or a communication module in a network device, the functions of the processing unit 902 can be implemented by one or more processors. Specifically, the processor can include a chip. The functions of the communication unit 903 can be implemented by a transceiver circuit.

[0203] It is understandable that the division of units in the above-mentioned device is merely a division of logical functions, and one function may correspond to one functional unit, or two or more functions may be integrated into one functional unit. In actual implementation, all or part of the units may be integrated into one physical entity, or distributed across different physical entities. In addition, the above-mentioned functional units may be implemented in the form of hardware, software, or a combination of hardware and software. Whether a function is executed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel may use different methods to implement the described functions for specific applications, but such implementation should not be considered to be beyond the scope of this application.

[0204] In one example, the functional unit in any of the above devices can be one or more integrated circuits configured to implement the above methods, such as: one or more ASICs, or one or more CPUs, one or more microprocessors (MPUs), one or more microcontrollers (MCUs), one or more digital signal processors (DSPs), or one or more FPGAs, or a combination of at least two of these integrated circuit forms.

[0205] In an example, the storage unit 901 may include a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory and / or a register.

[0206] Figure 7 is a schematic diagram of the structure of a terminal 1000 provided in an embodiment of the present application. Terminal 1000 may correspond to the terminals shown in Figures 1-4 and is configured to implement the operations of the terminals in the above embodiments. As shown in Figure 7(a), terminal 1000 includes one or more antennas 1010, a radio frequency processing system 1020, and a processor system 1030.

[0207] In the downlink or sidelink direction, the RF processing system 1020 receives RF signals through the antenna 1010 and sends the processed signals to the processor system 1030 for further processing. In the uplink or sidelink direction, the processor system 1030 processes the terminal side information and sends it to the RF processing system 1020. The RF processing system 1020 processes the signal and sends it through the antenna 1010.

[0208] In one example, the RF processing system 1020, serving as the terminal's external communication interface, may include an RF front end (RFFE) 1021 and an RF transceiver 1022. The RFFE 1021 primarily performs one or more of the following processing steps: shaping, passband selection, or gain control on RF signals received by the antenna or to be transmitted by the antenna. It may include one or more components such as an RF switch, a duplexer, a filter, a power amplifier, an antenna tuner, and a low-noise amplifier. The RFFE 1021 may be a circuit system composed of multiple discrete components or integrated into one or more chips. The RF transceiver 1022 processes the RF signals received by the RFFE into baseband / IF signals for further processing by the processor system 1030, and processes the baseband / IF signals provided by the processor system 1030 into RF signals for transmission to the RFFE 1021. The baseband / IF signals transmitted between the RF transceiver 1022 and the processor system 1030 may be either digital or analog. The RF transceiver 1022 may be implemented by one or more chips, which are often referred to as radio frequency integrated circuits (RFICs).

[0209] In one example, the processor system 1030 may include one or more processors for processing signals and executing one or more communication protocols. Optionally, the processor system 1030 may also include a memory 1036. In one example, the one or more processors include at least one baseband processor 1031 (also known as a modem processor). The memory 1036 is used to store data and / or computer program instructions. Optionally, the processor system 1030 may also include one or more application processors 1032 for processing the terminal operating system and application layer. Optionally, the processor system 1030 may also include one or more of a voice subsystem 1033, a multimedia subsystem 1034, or an interface circuit 1035. The voice subsystem 1033 is used to process voice signals, the multimedia subsystem 1034 is used to handle multimedia-related operations such as video encoding and decoding, image processing, etc., and the interface circuit 1035 is used to communicate with other terminal components, such as the display 1040, input device 1050, and memory 1060. The aforementioned components in the processor system 1030 may communicate with each other via a bus or communication interface circuit.

[0210] In one example, the processor system 1030 can be packaged into a processor chip, such as a SoC chip or a SIP chip. In another example, the processor system 1030 can be a system consisting of multiple chips, for example, the baseband processor 1031 can be packaged into a single chip, or packaged into a single chip with part or all of the circuits of the radio frequency processing system.

[0211] In one example, the memory 1036 may be an on-chip memory, that is, located on the chip of the processor system 1030. In one example, the memory 1060 may be an off-chip memory, that is, located outside the chip of the processor system 1030.

[0212] In one example, as shown in (b) of Figure 7, the baseband processor 1031 in the terminal 1000 provided in an embodiment of the present application may include: one or more processor cores 10311 and an interface circuit 10314. The one or more processor cores 10311 are used to process signals and execute one or more communication protocols. Optionally, the baseband processor 1031 may also include a memory 10312, which is used to store at least part of the corresponding computer program instructions and / or data. In one example, the one or more processor cores 10311 implement the relevant operations in the above-mentioned method embodiment (such as generating first information, which is used to indicate the computing power status of the terminal or terminal module) by executing the computer program instructions stored in the memory 10312. In the present disclosure, the memory 10312 is used to store corresponding computer program instructions and / or data. This may refer to the memory 10312 being used to store all corresponding computer program instructions and / or data for execution by the processor core 10311, or it may refer to the memory 10312 being used to store a portion of the corresponding computer program instructions and / or data, including the computer program instructions and / or data currently required to be executed by the processor core 10311. The memory 10312 may store different portions of computer program instructions and / or data multiple times for execution by the processor core 10311 to implement the relevant operations in the above-mentioned method embodiments. The interface circuit 10314 serves as a communication interface for communicating with other components, such as transmitting signals with the RF processing system 1020, communicating with other subsystems and related components of the processor system 1030 via a bus, such as transmitting data control signals with the application processor 1032, and transmitting data or computer program instructions with the memory 1036 or the memory 1060. Optionally, in order to reduce the load of the processor core, a baseband signal processing circuit 10313 may be provided to implement at least part of the baseband signal processing, including one or more of signal demodulation, modulation, encoding or decoding.

[0213] In one example, the communication device provided in the present application may be a terminal 1000 , a communication module including a processor system 1030 and a radio frequency system 1020 , a processor system 1030 , or a baseband processor 1031 .

[0214] The above-mentioned processors, processor systems, application processors, baseband processors, processor circuits or processor cores can be collectively referred to as processors, which may include one or more combinations of CPU, DSP, MPU, MCU, GPU, FPGA, ASIC, AI processor or NPU.

[0215] The aforementioned memory may include one or more of the following storage media: random access memory (RAM), static RAM (SRAM), dynamic RAM (DRAM), phase-change memory (PCM), resistive RAM (ReRAM), magnetoresistive RAM (MRAM), ferroelectric RAM (FRAM), cache, register, read-only memory (ROM), flash memory, erasable programmable ROM (EPROM), hard disk, etc. In one example, computer program instructions for executing the aforementioned embodiments may be stored in a non-volatile memory, such as at least a portion of the aforementioned memory 1060 (e.g., one or more of ROM, flash memory, EPROM, or hard disk). When the terminal is running, the corresponding computer program instructions can be partially or completely loaded into a memory with a faster transmission speed to the processor, such as at least a part of the above-mentioned memory 1036 and / or memory 10312 (such as one or more of RAM, SRAM, DRAM, PCM, RERAM, MRAM, FRAM, cache, or register), for execution by the processor to implement the steps in the above-mentioned method embodiments.

[0216] In one example, the RF transceiver 1022 and the RF front end 1021 may also be packaged in one chip. In one example, the RF transceiver 1022, the RF front end 1021 and the baseband processor 1031 may also be packaged in one chip.

[0217] An embodiment of the present application further provides a computer-readable storage medium on which computer instructions for implementing the methods executed by a communication device (such as a terminal or a network device) in the above-mentioned method embodiments are stored.

[0218] An embodiment of the present application also provides a computer program product, comprising instructions, which, when executed by a computer, implement the methods performed by a communication device (such as a terminal or a network device) in the above-mentioned method embodiments.

[0219] An embodiment of the present application also provides a communication system, which includes one or more of the terminals and network devices in the above embodiments.

[0220] The explanation of the relevant contents and beneficial effects of any of the above-mentioned devices can be referred to the corresponding method embodiments provided above, which will not be repeated here.

[0221] In each of the above embodiments, “optionally, the method further includes…” can be understood as these steps may be executed in full, none, or only part of them, which is not limited in this application.

[0222] In the embodiments of this application, words such as "exemplary" and "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described in this application as "exemplary" should not be construed as preferred or advantageous over other embodiments or designs. Rather, the use of the word "exemplary" is intended to present concepts in a concrete way.

[0223] It should be understood that references to "embodiments" throughout this specification mean that a particular feature, structure, or characteristic associated with the embodiment is included in at least one embodiment of the present application. Therefore, various embodiments throughout this specification do not necessarily refer to the same embodiment. Furthermore, these particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0224] It should be understood that in the various embodiments of the present application, the size of the sequence number of each process does not mean the order of execution, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present application. The names of all nodes and messages in this application are merely names set by this application for the convenience of description. The names in the actual network may be different. It should not be understood that this application limits the names of various nodes and messages. On the contrary, any name with the same or similar function as the node or message used in this application is regarded as the method or equivalent replacement of this application, and is within the scope of protection of this application.

[0225] It should also be understood that in the present application, "when...", "if...", "in the case of..." and "if" all mean that the network element will make corresponding processing under certain objective circumstances. It does not limit the time, nor does it require the network element to have a judgment action when it is implemented, nor does it mean that there are other limitations. In addition, in the present application, the description of the above-mentioned "when...", "if...", "in the case of..." and "if" conditions can be understood as necessary conditions, and there is no limitation on whether the condition is a sufficient condition or whether it is a necessary and sufficient condition. For example, "in the case of A, execute B" can be understood as "if at least A is satisfied, execute B."

[0226] In addition, in each embodiment of the present application, "B corresponding to A" means that B is associated with A and B can be determined based on A. However, it should be understood that determining B based on A does not mean determining B based solely on A, but B can also be determined based on A and / or other information.

[0227] The terms "system" and "network" in the embodiments of the present application can be used interchangeably. "At least one" refers to one or more, and "plurality" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can represent: the existence of A alone, the existence of A and B at the same time, and the existence of B alone, where A and B can be singular or plural. The character " / " generally indicates that the associated objects before and after are in an "or" relationship. "At least one of the following" or similar expressions refers 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, and "at least one of A, B and C" can also be understood to include A, B, C, AB, AC, BC or ABC. And, unless otherwise specified, the ordinal numbers such as "first" and "second" mentioned in the embodiments of the present application are used to distinguish multiple objects and are not used to limit the order, timing, priority or importance of multiple objects.

[0228] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, optical storage, etc.) that contain computer-usable program code.

[0229] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the present application. It should be understood that each flow and / or box in the flow chart and / or block diagram, as well as the combination of the flow chart and / or box in the flow chart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for implementing the functions specified in one or more flow charts and / or one or more boxes in the block diagram.

[0230] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction device that implements the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0231] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0232] Obviously, those skilled in the art may make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include these modifications and variations.

Claims

1. A communication method, characterized in that, The method is applied to the terminal side and includes: Sending first information to a network device, where the first information is used to indicate the computing power status of the terminal or a terminal module; Receiving second information from the network device, where the second information is used to indicate that the terminal participates in an artificial intelligence (AI) task supported by the computing power status.

2. The method according to claim 1, characterized in that, The computing power status includes at least one of the following: Computing power precision, computing speed, power, memory status, the number of AI model parameters that can be calculated.

3. The method according to claim 1 or 2, characterized in that, The AI task includes at least one of the following: AI-based data transmission, AI model parameter training, collection of training data for the AI model.

4. The method according to any one of claims 1 to 3, characterized in that, The method further includes: Receiving third information from the network device, where the third information is used to request the terminal to report the computing power status.

5. The method according to any one of claims 1 to 4, characterized in that, The method further includes: Sending fourth information to the network device, where the fourth information is used to indicate whether the terminal participates in the AI task.

6. The method according to any one of claims 1 to 5, characterized in that The network device is a core network element or an access network device.

7. A communication method, characterized in that, Includes: Receiving first information from a terminal, where the first information is used to indicate the computing power status of the terminal or a terminal module; Sending second information to the terminal, where the second information is used to indicate that the terminal participates in an AI task supported by the computing power status.

8. The method according to claim 7, characterized in that, The computing power status includes at least one of the following: Computing power precision, computing speed, power, memory status, the number of AI model parameters that can be calculated.

9. The method according to claim 7 or 8, characterized in that The AI task includes at least one of the following: AI-based data transmission, AI model parameter training, collection of training data for the AI model.

10. The method according to any one of claims 7 to 9, characterized in that, The method further includes: Sending third information to the terminal, where the third information is used to request the terminal to report the computing power status.

11. The method according to any one of claims 7 to 10, characterized in that, The method further includes: Sending fifth information to a server, where the fifth information is used to indicate the AI task.

12. The method according to any one of claims 7 to 10, characterized in that The method further includes: Receiving fourth information from the terminal, where the fourth information is used to indicate whether the terminal participates in the AI task.

13. The method according to claim 12, wherein In the case where the fourth information indicates that the terminal participates in the AI task, the method further includes: Sending fifth information to a server, where the fifth information is used to indicate the AI task.

14. A communication device, characterized in that, Includes: An interface unit for sending first information to a network device, where the first information is used to indicate the computing power status of the terminal or a terminal module; The interface unit is further configured to: receive second information from the network device, where the second information is used to indicate that the terminal participates in an AI task supported by the computing power status.

15. The device according to claim 14, characterized in that, The computing power status includes at least one of the following: Computing power precision, computing speed, power, memory status, the number of AI model parameters that can be calculated.

16. The device according to claim 14 or 15, characterized in that, The AI task includes at least one of the following: AI-based data transmission, AI model parameter training, collection of training data for the AI model.

17. The device according to any one of claims 14 to 16, characterized in that, The interface unit is further configured to: Receive third information from the network device, where the third information is used to request the terminal to report the computing power status.

18. The device according to any one of claims 14 to 17, characterized in that The interface unit is further configured to: Send fourth information to the network device, where the fourth information is used to indicate whether the terminal participates in the AI task.

19. The device according to any one of claims 14 to 18, characterized in that, The network device is a core network element or an access network device.

20. A communication device, characterized in that, Includes: An interface unit for receiving first information from a terminal, the first information being used to indicate the computing power status of the terminal or a terminal module; The interface unit is further configured to: send second information to the terminal, the second information being used to indicate that the terminal participates in an AI task supported by the computing power status.

21. The device according to claim 20, wherein The computing power status includes at least one of the following: Computing power accuracy, computing speed, power, memory status, the number of AI model parameters that can be calculated.

22. The device according to claim 20 or 21, characterized in that, The AI task includes at least one of the following: AI-based data transmission, AI model parameter training, collection of training data for an AI model.

23. The device according to any one of claims 20 to 22, characterized in that, The interface unit is further configured to: Send third information to the terminal, the third information being used to request the terminal to report the computing power status.

24. The device according to any one of claims 20 to 23, characterized in that, The interface unit is further configured to: Send fifth information to a server, the fifth information being used to indicate the AI task.

25. The device according to any one of claims 20 to 23, characterized in that, The interface unit is further configured to: Receive fourth information from the terminal, the fourth information being used to indicate whether the terminal participates in the AI task.

26. The device according to claim 25, characterized in that, In the case where the fourth information indicates that the terminal participates in the AI task, the interface unit is further configured to: Send fifth information to a server, the fifth information being used to indicate the AI task.

27. A communication device, characterized in that, Comprising one or more processors, the one or more processors being configured to cause the device to execute the method according to any one of claims 1 to 6 by executing computer programs or instructions stored in a memory, or by means of logic circuits.

28. A communication device, characterized in that, Comprising one or more processors, the one or more processors being configured to cause the device to execute the method according to any one of claims 7 to 13 by executing computer programs or instructions stored in a memory, or by means of logic circuits.

29. A computer-readable storage medium, characterized in that, A computer-readable storage medium stores computer programs or instructions, and when the computer programs or the instructions are run, the method according to any one of claims 1 to 6 is executed, or the method according to any one of claims 7 to 13 is executed.

30. A computer program product, characterized in that, Containing instructions, and when the instructions are run, the method according to any one of claims 1 to 6 is executed, or the method according to any one of claims 7 to 13 is executed.

Images