Wireless communication methods and communication devices

Abstract

Provided are wireless communication methods and communication devices. A wireless communication method comprises: a first device sending first information, wherein the first information is used for indicating computing power information of the first device. By means of the first information, other communication devices can learn the computing power information of the first device, such that the other communication devices can offload computing power tasks to the first device. Similarly, the other communication devices may also send computing power information of the communication devices, such that the first device or a second device can obtain the computing power information of the communication devices, thereby helping the first device offload computing power tasks to the other communication devices.

Description

Wireless communication methods and communication devices Technical Field

[0001] This application relates to the field of communication technology, and more specifically, to a wireless communication method and a communication device. Background Technology

[0002] Computing power has gradually become an important element in communication systems. For example, the intelligentization of various nodes in a communication system requires computing power as a foundation. In earlier communication systems (such as 5G), computing power was not discussed. Summary of the Invention

[0003] This application provides a wireless communication method and a communication device. The various aspects covered by this application are described below.

[0004] In a first aspect, a wireless communication method is provided, the method comprising: a first device transmitting first information; wherein the first information is used to indicate computing power information of the first device.

[0005] In a second aspect, a wireless communication method is provided, the method comprising: a second device receiving first information; wherein the first information is used to indicate computing power information of the first device.

[0006] Thirdly, a communication device is provided, which is a first device, comprising: a transmitting unit for transmitting first information; wherein the first information is used to indicate computing power information of the first device.

[0007] Fourthly, a wireless communication device is provided, which is a second device. The communication device includes: a receiving unit for receiving first information; wherein the first information is used to indicate computing power information of a first device.

[0008] Fifthly, a communication device is provided, including a transceiver, a memory, and a processor, wherein the memory is used to store a program, the processor is used to invoke the program in the memory, and to control the transceiver to receive or send signals so that the communication device performs some or all of the steps in the method of the first aspect.

[0009] In a sixth aspect, a communication device is provided, including a transceiver, a memory, and a processor, wherein the memory is used to store a program, the processor is used to invoke the program in the memory, and to control the transceiver to receive or transmit signals so that the communication device performs some or all of the steps in the method of the second aspect.

[0010] In a seventh aspect, a communication system is provided, which includes the communication device described above. In another possible design, the system may further include other devices that interact with the communication device as provided in the embodiments of this application.

[0011] Eighthly, a computer-readable storage medium is provided, the computer-readable storage medium storing a computer program that causes a communication device to perform some or all of the steps of the methods described in the preceding aspects.

[0012] Ninthly, embodiments of this application provide a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program operable to cause a communication device to perform some or all of the steps of the methods described in the foregoing aspects. In some implementations, the computer program product may be a software installation package.

[0013] In a tenth aspect, embodiments of this application provide a chip including a memory and a processor, the processor being able to call and run a computer program from the memory to implement some or all of the steps described in the methods of the foregoing aspects.

[0014] Through the first information, other communication devices can obtain the computing power information of the first device, thereby enabling other communication devices to offload computing tasks to the first device. Similarly, other communication devices can also send out the computing power information of the communication device, so that the first device or the second device can obtain the computing power information of the communication device, thereby facilitating the first device to offload computing tasks to other communication devices. Attached Figure Description

[0015] Figure 1 is a schematic diagram of the wireless communication system used in the embodiments of this application.

[0016] Figure 2 is a schematic diagram of a network architecture.

[0017] Figure 3 is a schematic diagram of the interface between the network data analytics function (NWDAF) and other network elements.

[0018] Figure 4 is an example diagram of a scheme for segmenting artificial intelligence (AI) / machine learning (ML) reasoning.

[0019] Figure 5 is a performance example of model segmentation.

[0020] Figure 6 is a schematic flowchart of a wireless communication method provided in an embodiment of this application.

[0021] Figure 7 is a schematic diagram of a network architecture provided in an embodiment of this application.

[0022] Figure 8A is a schematic flowchart of another wireless communication method provided in an embodiment of this application.

[0023] Figure 8B is a schematic flowchart of another wireless communication method provided in an embodiment of this application.

[0024] Figure 9 is a schematic flowchart of another wireless communication method provided in an embodiment of this application.

[0025] Figure 10 is a schematic structural diagram of a communication device 1000 provided in an embodiment of this application.

[0026] Figure 11 is a schematic structural diagram of a communication device 1100 provided in an embodiment of this application.

[0027] Figure 12 is a schematic structural diagram of a communication device provided in an embodiment of this application. Detailed Implementation

[0028] The technical solutions in this application will now be described with reference to the accompanying drawings.

[0029] Communication system

[0030] Figure 1 illustrates a wireless communication system 100 according to an embodiment of this application. The wireless communication system 100 may include communication devices. These communication devices may include a network device 110 and a terminal device 120. The network device 110 may be a device that communicates with the terminal device 120.

[0031] Figure 1 illustrates an exemplary network device and two terminals. Optionally, the wireless communication system 100 may include multiple network devices, and each network device may include other terminal devices within its coverage area. This application embodiment does not limit this.

[0032] Optionally, the wireless communication system 100 may also include other network entities such as a network controller and a mobility management entity, which is not limited in this embodiment.

[0033] It should be understood that the technical solutions of the embodiments of this application can be applied to various communication systems, such as: 5th generation (5G) systems or new radio (NR), long term evolution (LTE) systems, LTE frequency division duplex (FDD) systems, LTE time division duplex (TDD) systems, etc. The technical solutions provided in this application can also be applied to future communication systems, such as 6th generation mobile communication systems, satellite communication systems, and so on.

[0034] The terminal device in this application embodiment can also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station (MS), mobile terminal (MT), remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent, or user device. The terminal device in this application embodiment can be a device that provides voice and / or data connectivity to a user, and can be used to connect people, objects, and machines, such as a handheld device with wireless connectivity, vehicle-mounted device, etc. The terminal device in the embodiments of this application can be a mobile phone, tablet computer, laptop computer, PDA, mobile internet device (MID), wearable device, virtual reality (VR) device, augmented reality (AR) device, wireless terminal in industrial control, wireless terminal in self-driving, wireless terminal in remote medical surgery, wireless terminal in smart grid, wireless terminal in transportation safety, wireless terminal in smart city, wireless terminal in smart home, etc. Optionally, the UE can be used to act as a base station. For example, the UE can act as a scheduling entity, providing sidelink signals between UEs in vehicle-to-everything (V2X) or device-to-device (D2D) communication. For example, cellular phones and cars communicate with each other using sidelink signals. Cellular phones and smart home devices communicate without relaying communication signals through a base station.

[0035] The network device in this application embodiment can be a device for communicating with terminal devices. The network device may also include an access network device. The access network device can provide communication coverage for a specific geographical area and can communicate with the terminal device 120 located within that coverage area. The access network device can also be called a wireless access network device or a base station, etc. In this application embodiment, the access network device can refer to a radio access network (RAN) node (or device) that connects the terminal device to the wireless network. Access network equipment can broadly encompass various names listed below, or be replaced by names such as: NodeB, Evolved NodeB (eNB), Next Generation NodeB (gNB), Relay Station, Transmitting and Receiving Point (TRP), Transmitting Point (TP), Master eNB (MeNB), Secondary eNB (SeNB), Multi-Standard Radio (MSR) Node, Home Base Station, Network Controller, Access Node, Wireless Node, Access Point (AP), Transmitter Node, Transceiver Node, Baseband Unit (BBU), Remote Radio Unit (RRU), Active Antenna Unit (AAU), Remote Radio Head (RRH), Central Unit (CU), Distributed Unit (DU), Location Node, Centralized Unit-Control Plane (CU-CP), Centralized Unit-User Plane (CU-User) Base stations can be macro base stations, micro base stations, relay nodes, donor nodes, or similar entities, or combinations thereof. A base station can also refer to a communication module, modem, or chip installed within the aforementioned equipment or apparatus. A base station can also be a mobile switching center, equipment performing base station functions in D2D, V2X, and machine-to-machine (M2M) communications, network-side equipment in 6G networks, and equipment performing base station functions in future communication systems. Base stations can support networks using the same or different access technologies. The embodiments of this application do not limit the specific technologies or equipment forms used in the access network equipment.

[0036] Base stations can be fixed or mobile. For example, a helicopter or drone can be configured to act as a mobile base station, and one or more cells can move depending on the location of the mobile base station. In other examples, a helicopter or drone can be configured as a device to communicate with another base station.

[0037] Wireless communication systems involve communication equipment that can include not only access network equipment and terminal equipment, but also core network elements. Core network elements can be implemented through devices; that is, core network elements are core network devices. It can be understood that core network devices can also be a type of network device.

[0038] The core network elements in this application embodiment may include network elements that process and forward user signaling and data. For example, core network equipment may include core access and mobility management function (AMF), session management function (SMF), location management function (LMF), network slice selection function (NSSF), authentication server function (AUSF), unified data management (UDM), policy control function (PCF), user plane function (UPF), sensing function (SF), NWDAF, artificial intelligence (AI) function management entity, etc. Of course, the core network may also include other network elements, which are not listed here.

[0039] In some deployments, the network device in this application embodiment may refer to a CU or a DU, or the network device may include both a CU and a DU. The gNB may also include an AAU.

[0040] Network devices and terminal devices can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; they can also be deployed on water; and they can also be deployed in the air on airplanes, balloons, and satellites. This application does not limit the scenario in which the network devices and terminal devices are located.

[0041] It should be understood that all or part of the functions of the communication device in this application can also be implemented by software functions running on hardware, or by virtualization functions instantiated on a platform (e.g., a cloud platform).

[0042] Mobile network system architecture

[0043] Figure 2 is a schematic diagram of a network architecture. This network architecture may include terminal devices, access network (AN) elements, and core network elements.

[0044] The core network elements can be categorized into several types, including user plane function (UPF) elements, access and mobility management function (AMF) elements, session management function (SMF) elements, policy control function (PCF) elements, application function (AF) elements, data network (DN) elements, network slice selection function (NSSF) elements, authentication server function (AUSF) elements, unified data management (UDM) elements, network exposure function (NEF) elements, network repository function (NRF) elements, and network slice-specific authentication and authorization function (NSSAAF). Among these, UPF elements are primarily responsible for user data transmission. The other elements, which can be referred to as control plane function elements, are mainly responsible for authentication, authorization, registration management, session management, mobility management, and policy control to ensure reliable and stable user data transmission.

[0045] UPF network elements can be used to forward and receive data from terminals. For example, a UPF network element can receive service data from the data network and transmit it to the terminal through access network equipment; a UPF network element can also receive user data from the terminal through access network equipment and forward it to the data network. The transmission resources allocated and scheduled by the UPF network element for the terminal are managed and controlled by the SMF network element. The bearer between the terminal and the UPF network element can include: the user plane connection between the UPF network element and the access network equipment, and the establishment of a channel between the access network equipment and the terminal. The user plane connection is where a QoS flow (transmission flow) for data transmission can be established between the UPF network element and the access network equipment.

[0046] AMF network elements can be used to manage terminal access to the core network, such as terminal location updates, network registration, access control, terminal mobility management, and terminal attachment and detachment. When providing services for a terminal's session, AMF network elements can also provide control plane storage resources for that session to store session identifiers and the associated SMF network element identifiers.

[0047] SMF network elements can be used to select user plane network elements for terminals, redirect user plane network elements for terminals, assign Internet Protocol (IP) addresses to terminals, establish bearers (also known as sessions) between terminals and UPF network elements, modify and release sessions, and perform QoS control.

[0048] PCF network elements are used to provide policies to AMF and SMF network elements, such as QoS policies and slice selection policies.

[0049] AF network elements are used to interact with 3GPP core network elements to support the routing of application-affected data, access network exposure functions, and interact with PCF network elements for policy control, etc.

[0050] A Data Network (DN) can provide data services to users for networks such as IP Multimedia Service (IMS) and the Internet. A DN can contain various application servers (AS) that provide different application services, such as carrier services, Internet access, or third-party services. The AS can implement the functions of an Application Server (AF).

[0051] NSSF is used for network slice selection and supports the following functions: selecting the set of network slice instances to serve the UE; determining allowed Network Slice Selection Assistance Information (NSSAI), and, when necessary, determining the mapping to the subscribed Single-Network Slice Selection Assistance Information (S-NSSAI); determining the configured NSSAI, and, when necessary, determining the mapping to the subscribed S-NSSAI; determining the set of AMFs that may be used to query the UE, or determining a list of candidate AMFs based on configuration.

[0052] AUSF is used to receive AMF requests for terminal authentication. It requests a key from UDM and then forwards the issued key to AMF for authentication processing.

[0053] UDM includes functions such as generating and storing user subscription data and managing authentication data, and supports interaction with external third-party servers.

[0054] NEF is used for capability exposure, meaning that based on NEF, network capabilities can be exported to external networks. Untrusted external applications can access core network data through NEF to ensure network security. NEF can provide functions such as QoS capability exposure for external applications, event subscription, and AF request distribution.

[0055] The Network Request Forwarder (NRF) is used for the registration, management, and status detection of core network elements, thereby achieving automated management of core network elements. When a core network element starts up, it must register with the NRF before it can provide services. Registration information may include, for example, the type, address, and service list of the core network element.

[0056] It should be noted that in some communication systems (such as 5G systems), core network elements can also be called network functions (NFs).

[0057] In addition to the network elements in the architecture shown in Figure 2, some networks (such as 5G networks) have also added NWDAF to the core network. NWDAF can collect data from various network elements and network management systems in the core network for big data statistics, analysis, or intelligent data analysis to obtain network-side analysis or prediction data, thereby assisting various network elements in more effectively controlling terminal device access based on the data analysis results.

[0058] Specifically, the NWDAF network element can collect data from other network elements for big data analysis. To this end, an interface between the NWDAF and other network elements is defined, as shown in Figure 3. Based on this interface, the NF can request an analysis result from the NWDAF (identified by an analytics ID), and the NWDAF can send an analysis result to the NF. Some of the analysis services provided by the NWDAF are shown in Table 1.

[0059] Table 1

[0060] Quality of Service (QoS) parameters

[0061] In some communication systems, a QoS (Quality of Service) flow is the basic unit used to manage and guarantee service quality. Each QoS flow represents a specific type of data flow with clearly defined service quality requirements. QoS flows are mainly divided into guaranteed bit rate (GBR) QoS flows and non-GBR QoS flows. For GBR QoS flows, the network needs to reserve resources to guarantee bandwidth.

[0062] QoS parameters mainly include: 5G QoS identifier (5QI), allocation and retention priority (ARP), reflective QoS attribute (RQA), guaranteed flow bit rate (GFBR), maximum flow bit rate (MFBR), notification control, and aggregate maximum bit rate (AMBR). These will be explained in detail below.

[0063] 5QI can be understood as a scalar pointing to multiple QoS feature values, categorized into three types: standardized 5QI, pre-configured 5QI, and dynamically allocated 5QI. For dynamically allocated 5QI, when the core network provides QoS flow configuration to the base station, it must include not only the 5QI but also the complete set of QoS feature values ​​corresponding to that 5QI. For standardized and pre-configured 5QI, the core network only needs to provide the 5QI, and the base station can resolve the set of multiple QoS feature values ​​corresponding to it. Furthermore, for a standardized or pre-configured 5QI, the core network is also allowed to provide one or more QoS feature values ​​different from the standardized or pre-configured ones to modify the corresponding standardized or pre-configured QoS feature values. Standardized 5QI is mainly used for more common, frequently used services. Dynamically allocated 5QI is mainly used for less common services that cannot be satisfied by standardized 5QI.

[0064] ARP allocates and maintains priorities, specifically including three types of information: priority level, resource preemption capability, and whether resource preemption is allowed. It is used to determine whether the establishment, modification, and switching of QoS flows are permitted when resources are limited, and is generally used for admission control of GBR-type QoS flows. ARP is also used to preempt existing QoS flows when resources are limited; for example, a high-priority QoS flow can preempt a low-priority QoS flow.

[0065] RQA is used to indicate that QoS is applied to certain SDF-bearing QoS flows.

[0066] GFBR is used to instruct the base station to reserve sufficient resources for the bit rate of a QoS stream transmission within an average time window. MFBR limits the maximum bit rate for QoS stream transmission.

[0067] The QoS notification control instruction indicates that when the base station cannot guarantee the GFBR of the QoS flow, it should continue to try to maintain the QoS flow and notify the core network that the QoS requirement cannot be guaranteed. The NG-RAN will attempt to re-guarantee the QoS requirement and notify the SMF that the QoS requirement is re-guaranteed.

[0068] The session-AMBR controls the total bitrate of all non-GBR type QoS streams for a PDU session. The UE-AMBR controls the total bitrate of all non-GBR type QoS streams for a UE.

[0069] computing power of communication equipment

[0070] The intelligentization of nodes in a communication system requires computing power. In earlier communication systems (such as 5G), computing power was not discussed. The core network element NWDAF, as the only intelligent network element, has the ability to collect data, train models, and perform data analysis based on the models to generate analysis results. As mentioned earlier, related technologies only standardized what data NWDAF needs to collect and what analysis results it needs to output. They did not consider the computing power of NWDAF; therefore, they did not theoretically analyze the model size that NWDAF could support or the time required to return analysis results.

[0071] With technological advancements, communication systems will support a multitude of new applications, such as sensing, AI, and digital twins. This makes communication networks inherently intelligent. That is, not only does the NWDAF possess intelligent capabilities, but the entire network is inherently intelligent from the outset. Every node (such as core network elements, base stations, and terminals) can possess intelligent capabilities, thereby enabling the completion of more complex applications.

[0072] Model segmentation

[0073] In model segmentation technology, the inference process of a model can be divided, allowing the model to be executed by multiple devices. For example, a large model can be divided into multiple smaller models, each executed by a different device. For instance, model 1 can be segmented into model 1-1, model 1-2, and model 1-3. Models 1-1, 1-2, and 1-3 together can achieve the same functionality as model 1. A terminal device can execute model 1-1, network device 1 can execute model 1-2, and network device 2 can execute model 1-3. Alternatively, the model can be segmented into multiple layers, with multiple devices executing specific layers of the model. For instance, a model can include five layers; a terminal device can execute two layers, and a network device can execute the remaining three.

[0074] Model segmentation can be implemented based on task requirements and the working environment. For example, in model segmentation technology, AI / ML models can be segmented according to the current AI / ML task and working environment.

[0075] For example, a terminal device performs AI / ML operations on a specific part or executes an AI / ML model (such as a neural network) to a specific layer, and sends the generated intermediate data to a network device. This allows the network device to execute other parts of the AI / ML operation or other layers of the AI / ML model. The aim is to offload computationally intensive tasks to network-side nodes, thereby reducing the computational load on the terminal device. Furthermore, model segmentation can also keep latency-sensitive computations and computations that are required to remain on the terminal device under certain privacy protection rules, thus protecting privacy.

[0076] Figure 4 illustrates an example of a segmented AI / ML inference scheme. The terminal device performs AI / ML operations or a portion of the AI / ML model. Network AI / ML endpoint 1 and network AI / ML endpoint 2 are responsible for performing the remaining parts of the AI / ML operations or the remaining layers of the AI / ML model and feeding the inference results back to the terminal device.

[0077] It should be noted that Figure 4 uses AI / ML inference for image recognition as an example for illustration. However, model segmentation can also be applied to AI / ML inference in other types or scenarios.

[0078] It is important to note that in Figure 4, the final inference result is output by network AI / ML node 2. The inference result can also be output by other endpoints, such as network AI / ML node 1.

[0079] Model segmentation techniques can be implemented by setting segmentation points in the model or operation. Generally, the earlier the segmentation point (closer to the terminal device), the less computation the terminal device needs; the later the segmentation point (closer to the network device), the lower the required data transmission rate.

[0080] As shown in Figure 5, a potential split point (e.g., potential split point 1, potential split point 2, or potential split point 3 in Figure 5) can be set after a pooling layer with a relatively small output data volume. As shown in Figure 5, the size of the output data corresponding to potential split points 1, 2, or 3 is significantly reduced compared to the previous layers. Therefore, setting the potential split at potential split point 1, 2, or 3 can significantly reduce the required uplink data rate.

[0081] As discussed above, the relevant technologies lack a clear definition of information related to computing power. Furthermore, with technological advancements, the computing power required for business operations is enormous, and communication equipment itself may struggle to handle the large number of computational tasks. For example, terminal devices, due to their inherent limitations, find it difficult to handle a significant amount of computation. In such cases, communication equipment can offload computing tasks, for instance, by performing the model segmentation described above, placing some model inference processes on the network side. For example, the computing task can be divided into multiple models, and these models can be run on both the terminal device and at least one network device, meaning the network device assists the terminal device in performing the computing task. However, communication equipment cannot definitively know the computing power of other devices, making it difficult to perform computing task offloading.

[0082] Figure 6 is a schematic flowchart of a wireless communication method provided in an embodiment of this application. The method shown in Figure 6 can be executed by a first device and a second device. The first device can be any communication device in a communication system. For example, the first device may include: a terminal device, an access network device, a core network element, a third-party application server (e.g., an edge server), etc. The second device may include a core network element.

[0083] The method shown in Figure 6 may include step S610.

[0084] In step S610, the first device sends the first information. The second device can receive the first information.

[0085] As one possible implementation, the first device can directly send messages to the second device. That is, messages sent by the first device do not need to be forwarded through devices other than the first and second devices (e.g., a third device). For example, if the first device includes core network elements or access network elements, these core network elements or access network elements can directly send messages to the second device. Therefore, in this approach, the first information can be directly sent to the second device.

[0086] As another possible implementation, the first device can send a message intended for the second device to a third device, and the third device can forward this information to the second device (e.g., pass it through to the second device). For example, if the first device includes a terminal device, the third device can include an AMF (Application Management Function). Exemplarily, the terminal device includes a computing container in the NAS message sent to the AMF. The computing container can include computing-related information that the terminal device needs to interact with the second device. The AMF determines the appropriate second device based on the container type, calls the Ncmf service, and sends the computing container to the second device. The computing container can include the first information. Therefore, in this approach, the first information does not necessarily need to be sent directly to the second device; it can be sent via forwarding.

[0087] In this application, the first information is used to indicate the computing power information of the first device. In other words, the first information can be used to indicate information related to the computing power of the first device. The computing power can be the computing ability and / or computing resources of the device to achieve specific output results by processing data. The process by which the first device sends its computing power information can also be referred to as the registration process of the first device's computing power information.

[0088] Therefore, it can be seen that through the first information, other communication devices can obtain the computing power information of the first device, thereby enabling other communication devices to offload computing tasks to the first device. Similarly, other communication devices can also send out the computing power information of the communication device, so that the first device or the second device can obtain the computing power information of the communication device, thereby facilitating the first device to offload computing tasks to other communication devices.

[0089] Based on the first information, the second device can obtain the computing power information of the first device. Using a similar method, the second device can also obtain the computing power information of other devices. Based on the computing power information of each device, the second device can perform one or more of the following functions: managing computing power information, storing computing power information, collecting computing power information, analyzing computing power information, and formulating computing power strategies.

[0090] As one possible implementation, the computing power information of each node can be stored in a computing power profile. After receiving the computing power profile, the second device can store the profile and implement the above functions based on the computing power profiles of each node.

[0091] Based on the above scheme, the second device can uniformly manage and schedule a large amount of idle computing power in the network. It connects idle computing resource nodes together through the network and then provides computing resources to the required applications and services (i.e., achieves computing power allocation) through the network. This allows the computing power of the entire network to be allocated flexibly, rationally, and efficiently, enabling various communication devices to support more complex services and meet the huge computing power demands of individual devices. In other words, based on the second device, a flexible, efficient, and complex computing power network can be realized. Here, the computing power network can refer to a system that aggregates computing resources based on the network, uniformly manages and schedules computing power, and provides applications to users.

[0092] Optionally, the second device can be a newly defined core network element. This application does not limit the name of the newly defined network element. For example, the newly defined core network element could be called a computing management function (CMF). As one possible implementation, the CMF can interact with other network elements in a service-based architecture (SBA). The service interface for calling the CMF network element services can be Ncmf.

[0093] Figure 7 is a schematic diagram of a network architecture provided in an embodiment of this application. As shown in Figure 7, the network architecture includes a network element matrix (CMF). The descriptions of the other network elements shown in Figure 7 can be found above.

[0094] It should be noted that, except for the CMF, all other network elements in Figure 7 are optional; that is, the network architecture may or may not include the network elements shown in Figure 7. Furthermore, the network architecture may also include other network elements besides those shown in Figure 7.

[0095] Optionally, the second device can be a core network element that has been defined in relevant technologies. For example, a core network element that has been defined in relevant technologies can also have one or more of the following functions: managing computing power information, storing computing power information, collecting computing power information, analyzing computing power information, and formulating computing power strategies.

[0096] Therefore, the second device in this application can manage the computing power of the communication system and allocate computing power to specific services, thereby enabling the computing power of the entire network to be allocated flexibly, reasonably and efficiently, and thus enabling each communication device to support more and more complex services.

[0097] The following section uses the computing power information of the first device as an example to explain the computing power information that each node may report.

[0098] The computing power information of the first device may include one or more of the following: first computing power information, attribute information, second computing power information, and first time information. These will be explained below.

[0099] The first computing power information can be used to indicate the total computing power supported by the first device. Therefore, each node can send the total computing power it supports to the second device.

[0100] The total computing power supported by a device can be understood as the device's total computing power-related capabilities, i.e., its total computing capacity. Alternatively, the total computing power supported by a device can be understood as indicating the maximum computing power that the device can support. For example, the magnitude of the total computing power supported by a first device can be determined based on the hardware of the first device.

[0101] As can be seen from the content indicated by the first computing power information, this information typically does not change. Therefore, the first computing power information does not need to be reported frequently. For example, the first information sent by the first device may include the first computing power information, but subsequent first information sent may not include it.

[0102] It should be noted that in this application, the unit of measurement for computing power can be floating-point operations per second (FLOPS). Based on this, the first computing power information can be represented by XX FLOPS, where XX represents a specific numerical value.

[0103] Attribute information can be used to indicate the computing power attributes supported by the first device. Therefore, each node can send its supported computing power attributes to the second device.

[0104] As one possible implementation, computing power attributes can include: general-purpose computing power or specialized computing power. General-purpose computing power can be computing power capable of performing calculations on arbitrary data or using arbitrary models. For example, general-purpose computing power may include computing power provided by a central processing unit (CPU) and / or a graphics processing unit (GPU). Specialized computing power can be computing power that needs to perform calculations on specific data or specific models. For example, specialized computing power may include computing power provided by a field-programmable gate array (FPGA) and / or an application-specific integrated circuit (ASIC).

[0105] As another possible implementation, computing power attributes can include computing power provided by the following hardware: CPU, GPU, FPGA, or ASIC.

[0106] The second computing power information can be used to indicate the amount of computing power that the first device can provide within a first time period. In other words, each node can send the amount of computing power it can provide within a certain time period to the second device. The amount of computing power that can be provided within a certain time period can also be referred to as computing power status or available computing power capability.

[0107] The computing power that can be provided within a certain period can be understood as the actual computing power that the device can provide within that period. The actual computing power that the device can provide can change over time. For example, when the device (e.g., the first device) is not performing any computing tasks, the computing power that the device can provide can be the total computing power mentioned above. Alternatively, the device can reserve some computing power for a specific computing task, and the computing power that the device can provide can be reduced by the reserved portion. Furthermore, when the device is currently performing a computing task, the computing power that the device can provide can be reduced by the portion of computing power that is currently being used.

[0108] The first time period can include the current time; therefore, the second computing power information can be used to indicate the amount of computing power that the first device can provide at the current time. In this case, the second computing power information can also be used to indicate the current computing power capability.

[0109] The first-time information can be used to indicate the first time period. That is, each node can indicate the validity period of its reported computing power status to the second device. As mentioned above, the computing power indicated by the second computing power information is real-time and dynamic; it is valid within the first time period but may be invalid outside of it. Therefore, by indicating the first-time information, the validity period of the second computing power information can be determined, thus allowing for the reasonable use of the first device's computing power within the valid period of the second computing power information.

[0110] In some embodiments, the first time information may include one or more of the following: a timestamp, the end time of a first time period, the duration of the first time period, etc. The timestamp may be used to indicate the time when the first device acquires or sends the second computing power information. Alternatively, the timestamp may be used to indicate the time when the first device registers the computing power information. If the first time information does not include the duration of the first time period, the duration of the first time period may satisfy one or more of the following: predefined, preconfigured.

[0111] In some embodiments, the first information may further include the identifier (ID) of the first device. The identifier of the first device can distinguish the first device from other devices, so that the second device can determine which device the received computing power information belongs to.

[0112] In some embodiments, the first information can be used to update the second computing power information. The process of updating the second computing power information can also be called a registration update process. For example, if the second computing power information becomes invalid, the first device can send the first information. The first information may include the updated second computing power information and first time information.

[0113] In some embodiments, the first device may receive an update request message sent by the second device. The update request message may be used to request the first device to send first information for updating the second computing power information. That is, the update of the second computing power information can be request-based. For example, when the second device detects that the second computing power information is about to expire, it may send an update request message to the first device.

[0114] For example, the second device can set a time limit for the second computing power information. It determines whether the time limit has been exceeded based on the first time period information sent by the first device. If the time limit is exceeded, the second device considers the second computing power information previously sent by the first device to be outdated and can notify the first device to update the second computing power information.

[0115] Optionally, the update request information may include request reason information. The request reason information can be used to indicate the reason for sending the update request. This reason can be indicated by a reason value, with different original values ​​corresponding to different reasons. Reasons may include: the second computing power information is invalid, i.e., its validity period has expired.

[0116] In some embodiments, the first device may periodically send first information. In this case, the update of the second computing power information may also be periodic.

[0117] As one possible implementation, the first device can maintain a first timer. When the first timer expires, the first device needs to send first information. The first timer can also be called a computing power update timer. In some embodiments, the first device can receive timer information sent by the second device, and the timer information can be used to indicate the first timer. That is, the first timer can be configured by the second device. In some embodiments, the first timer can be predefined or preconfigured.

[0118] As described above, the first device can register its computing power information with the second device using first information. For example, the first device can send a computing power information registration request message to the second device, which may include the first information. In the initial registration process (the first device sending the first information to the second device for the first time), the first information may include, for example, the identifier of the first device, first computing power information, attribute information, second computing power information, and first time information.

[0119] Taking the second device, which includes a Computation Management Provider (CMF), as an example, the CMF can provide a first service. This first service can be used to register computing power information for the first device. For example, the first service can be represented as Ncmf_ComputationManagement_Register.

[0120] As described above, the first device can update the second computing power information to the second device using the first information, i.e., perform a registration update process. For example, the second device can send a computing power information registration update message to the first device, which may include the update request information described above. The first device can send a computing power information registration update response message to the second device, which may include the first information. In this case, the first information may include, for example, the identifier of the first device, the second computing power information, and the first time information. If the first computing power information has already been sent during the initial registration process, the first information during the registration update process may not include the first computing power information.

[0121] Taking a second device including a Computation Management Filter (CMF) as an example, the CMF can provide a second service. This second service can be used by the first device to update computing power information. For example, the second service can be represented as Ncmf_ComputationManagement_Update.

[0122] The second device can send a first response message to indicate that it has received and stored the first information. For example, the second device can send a computing power information registration request response message to the first device, which may include the first response message.

[0123] The following description refers to the embodiments shown in Figures 8A and 8B. In Figure 8A or Figure 8B, the first device is a UE, and the second device is a CMF.

[0124] The method shown in Figure 8A includes steps S811 to S816.

[0125] In step S811, the UE sends a computing power information registration request to the CMF, which includes the UE computing power configuration file. The computing power configuration file includes the UE ID, the UE's first computing power information, attribute information, second computing power information, and a timestamp.

[0126] Step S812: CMF stores the UE computing power configuration file.

[0127] In step S813, the CMF sends a computing power information registration request response to the UE, instructing the UE to complete the registration of its computing power information.

[0128] Steps S811 to S813 belong to the computing power information registration process S810.

[0129] In step S814, the CMF determines whether the UE's second computing power information has expired (i.e., whether the second computing power information has become invalid) based on the timestamp information in the stored computing power configuration file.

[0130] In step S815, the CMF sends a computing power information registration update request to the UE. The request includes the UE's computing power configuration file and an indication that the UE needs to update its computing power status. The request also includes a reason value, namely, that the UE's second computing power information needs to be updated due to expiration.

[0131] In step S816, the UE sends a computing power information registration update response to update the CMF with the UE's current available computing power and timestamp. The CMF can update the stored UE computing power configuration file based on the received computing power information registration update response.

[0132] The method shown in Figure 8B includes steps S810 and S821 to S824.

[0133] The details of step S810 are shown in Figure 8A and will not be repeated here.

[0134] In step S821, the UE performs a timeliness check, that is, checks whether the second computing power information it registered with the CMF is valid. The timeliness check can be implemented based on a computing power update timer. When the computing power update timer expires, it can be determined whether the second computing power information has expired or is about to expire.

[0135] Step S822: When the UE's computing power update timer expires, the UE actively sends a computing power information registration update request.

[0136] The computing power information registration update request carries the UE computing power configuration file, including the updated second computing power information and timestamp.

[0137] Step S823: CMF updates the stored UE computing power configuration file.

[0138] In step S824, the CMF sends a computing power information registration update response to the UE.

[0139] The above explains how the second device collects and manages computing power information. The following section explains how the second device analyzes computing power information and formulates computing power strategies.

[0140] For the first computing power task, the second device can analyze computing power information (i.e., computing power analysis) based on the computing power information registered by each node and / or information collected from other network elements. For example, the second device can analyze and calculate latency (e.g., including computation latency and processing latency) based on one or more of the computing power information of each node, as well as data, models, and connection information, and / or generate a recommended computing power configuration strategy.

[0141] The output of the second device's computing power analysis can be the second information. The input of the second device's computing power analysis can be the third information. That is to say, the second device can obtain the second information based on the third information. The third information and the second information will be explained below.

[0142] The third information may include information about one or more nodes that may participate in the first computing power task. The following explanation uses the second node among the one or more nodes that may participate in the first computing power task as an example to illustrate the third information.

[0143] It should be noted that the second node can be any node in the communication system. For example, the second node may include terminal equipment, access network equipment, core network elements, or third-party servers. Where the first device may participate in the first computing task, the second node may include the first device.

[0144] In some embodiments, the third information may indicate one or more of the following: fourth computing power information, data information, model information, and connection information. These will be described below.

[0145] The fourth computing power information is used to indicate the computing power of the second node. In other words, the fourth computing power information is used to indicate information related to the computing power of the second node. Therefore, the third information can be used to indicate the computing power information of one or more nodes that may participate in the first computing power task.

[0146] In some embodiments, the fourth computing power information includes one or more of the following: the total computing power supported by the second node; the type of total computing power; the amount of computing power that the second node can provide during a second time period; the type of computing power that the second node can provide during the second time period; and the second time period. The amount of computing power that the second node can provide during the second time period can be understood as the computing power status of the second node, and the information about the second time period included in the fourth computing power information can be used to indicate the validity period of the computing power status of the second node.

[0147] Therefore, the third information can be used to indicate one or more of the following: the total computing power supported by each node that may participate in the first computing power task, the computing power that each node that may participate in the first computing power task can provide in the second time period, and the second time period.

[0148] It should be noted that the second time period can be a period of time in the past, present, or future.

[0149] The data information is used to indicate the data processed by the second node in executing the first computing task. Based on this, the third information may include: the data that each node that may participate in the first computing task needs to process in executing the first computing task.

[0150] In some embodiments, the data information includes one or more of the following: data size information, data type information, and data format information.

[0151] Data size information can be used to indicate the size of the input data and / or the size of the output data for the second node to perform the first computing task.

[0152] It should be noted that, in this application, output data may refer to the output data generated after node processing.

[0153] Data type information is used to indicate the type of input data and / or output data for the second node to perform the first computing task. The data type may include one or more of the following: perception-related data, location-related data, and QoS-related data.

[0154] Data format information is used to indicate the format of the input data and / or output data for the second node to perform the first computing task. The data format may include one or more of the following: floating-point numbers, point cloud data, image data, strings, etc.

[0155] It should be noted that, as mentioned above, the first computing task can be split into multiple models, each executed by a different device. This offloads computing power across multiple devices, avoiding the problem of excessive computing pressure on the first device if the first computing task is executed solely by the first device. The first computing task executed by the second node can be a part of the first computing task; that is, the second node can use one of the multiple models derived from the split first computing task. Therefore, the data information can indicate the input data and / or output data information of the model used by the second node to execute the first computing task.

[0156] The model information is used to indicate the model adopted by the second node when executing the first computing task. Based on this, the third information may include: the model that each node that may participate in the first computing task needs to adopt when executing the first computing task.

[0157] The second node can execute the first computing task using one or more models. That is, the model corresponding to the first computing task can be split in multiple ways, and the second node will use different models for each different splitting method. Taking the computing task shown in Figure 5 as the first computing task as an example, if the second node is a terminal device, for potential split point 1, the terminal device uses the model before potential split point 1 (including the input layer, conv1 layer, relu1 layer, and pool1 layer); for potential split point 2, the terminal device uses the model before potential split point 2 (including the input layer, conv1 layer, relu1 layer, pool1 layer, norm1 layer, conv2 layer, relu2 layer, and pool2 layer); and for potential split point 3, the terminal device uses the model before potential split point 3 (including the input layer, conv1 layer, relu1 layer, pool1 layer, norm1 layer, conv2 layer, relu2 layer, pool2 layer, norm2 layer, conv3 layer, relu3 layer, conv4 layer, relu4 layer, conv5 layer, relu5 layer, and pool5 layer). Based on this, the model information can indicate one or more models that the second node can use to execute the first computing power task. Continuing with Figure 5 as an example, if the second node is a terminal device, the model information can indicate one or more of the following models: the model before potential split point 1, the model before potential split point 2, and the model before potential split point 3.

[0158] Therefore, model information can be used to indicate one or more model splitting methods (or combinations of one or more models used by individual nodes). In other words, the second device can collect one or more model splitting methods to provide a recommended computing power offloading strategy for the output.

[0159] In some embodiments, model information includes one or more of the following: model identification information, model type information, and model size information.

[0160] The model identification information is used to indicate the identifier of the model used by the second node to perform the first computing task.

[0161] The model type information indicates the type of model used by the second node to execute the first computing task. The model type can include DNN, RNN, etc.

[0162] Model size information is used to indicate the size of the model used by the second node to perform the first computing task. The model size can be represented by one or more of the following: the number of layers in the model, the number of nodes in the model (including the number of nodes in each layer and / or the total number of nodes), etc.

[0163] The connectivity information is used to indicate the QoS quality of one or more terminal devices. QoS quality can be represented by the QoS parameters described above. Where the first device includes terminal devices, the one or more terminal devices may include the first device. Optionally, if the one or more terminal devices belong to a first area, the connectivity information is used to indicate the QoS quality of each terminal device within the first area (hereinafter referred to as the QoS quality of the first area).

[0164] In some embodiments, the source of the aforementioned third information may include: various nodes registered to the second device, the second device, and other core network elements. Other core network elements may include, for example, one or more of the following: data management function (DMF), model management function (MMF), NWDAF, PCF, and SMF. Here, DMF is the network element that manages data, and MMF is the network element that manages models.

[0165] It should be noted that the nodes registered to the second device may include the first device; therefore, the source of the third information may also include the first device. When the source of the third information includes the first device, the third information may originate from the first information described above or the first request information described below.

[0166] It should be noted that, as mentioned above, any device in the communication network can register with the second device; therefore, the source of the third information can be any device in the communication network.

[0167] It should be noted that when the source of the third information includes the second device, the source of the third information may include the registration information of each node stored by the second device (e.g., computing power configuration file), and / or, the source of the third information may include the information obtained by the second device after processing or calculating the registration information of each node.

[0168] The following examples illustrate the possible sources of different content in the third piece of information.

[0169] For example, the sources of computing power information for each node in the third information may include one or more of the following: UE, NF, and the second device. For example, the UE or NF may provide their respective computing power information. For example, the second device may provide the computing power information required by the third information based on the stored computing power information of each registered node.

[0170] For example, the source of the model information in the third information may include: the first device and / or the MMF. Exemplarily, the source of the model information may be the model requirement information in the first request information sent by the first device. Exemplarily, the second device may send a model information request to the MMF to request model information; the MMF may send a model request response back to the second device. The model request response may include the model information.

[0171] For example, the source of the data information in the third information may include: the first device and / or the DMF. Exemplarily, the source of the model information may be the data request information in the first request information sent by the first device. Exemplarily, the second device may send a data information request to the DMF to request data information; the DMF may send a data request response back to the second device. The data request response may include the data information.

[0172] For example, the sources of connection information for each node in the third information may include one or more of the following: UE, NF, NWDAF, PCF, and SMF. For instance, the second device may interact with the NWDAF to obtain the QoS sustainability information mentioned above, and / or, obtain end-to-end data transmission latency analysis supported by the NWDAF. For instance, the second device may interact with the PCF or SMF to obtain service level and / or QoS flow level QoS information.

[0173] The following table 2 illustrates the input information (i.e., the third information) for the CMF to perform computing power information analysis when the first device includes the UE and the second device is the CMF.

[0174] Table 2

[0175] It should be noted that some content in Table 2 can be implemented independently; that is, some rows or columns in Table 2 can be deleted. Additionally, other information can be added to Table 2.

[0176] It should be noted that, in this application, the parameter marked with the symbol > indicates the next level parameter of the parameter without the > mark, and the parameter marked with the symbol >> indicates the next level parameter of the parameter marked with the > mark.

[0177] The second information can be used to indicate the computing power analysis results for participating in the first computing power task, and the computing power analysis results can be used to indicate information on one or more nodes recommended to participate in the first computing power task.

[0178] It is understandable that the one or more nodes recommended to participate in the first computing power task can be selected from the one or more nodes that may participate in the first computing power task. That is, the one or more nodes recommended to participate in the first computing power task can be a subset of the one or more nodes that may participate in the first computing power task. For example, the one or more nodes recommended to participate in the first computing power task include a first node. The first node can be the second node described above. If the second node is a first device, the first node can be the first device.

[0179] In some embodiments, the computing power analysis results include one or more of the following: third computing power information, local processing time information, communication time information, second time information, and computing power configuration recommendations.

[0180] The third computing power information is used to indicate the available computing power and / or available computing power attributes of the first node during the second time period. That is, the second information may include the available computing power and / or available computing power attributes of one or more nodes recommended to participate in the first computing power task.

[0181] The local processing time information is used to indicate the local processing time of the first node using the first model to process the first data within the second time period. In other words, the second information may include the local processing time recommended for one or more nodes participating in the first computing power task to use a certain model to process a certain type of data.

[0182] The communication time information is used to indicate the transmission time when the first node processes the first data using the first model within a second time period, and / or the transmission time when the first device transmits the data to be processed to the first node. In other words, the second information may include: the transmission time when the data obtained after one or more nodes participating in the first computing power task process certain data using a certain model is transmitted to the first device, and / or the transmission time when the first device transmits the data to one or more nodes recommended to participate in the first computing power task in order to recommend one or more nodes participating in the first computing power task to process certain data using a certain model. Here, transmission time can also be referred to as transmission latency or end-to-end processing time.

[0183] It should be noted that, as mentioned above, the recommended one or more nodes participating in the first computing power task may include the first device, that is, the first node may be the first device. In this case, there is no transmission time between the first node and the first device. Therefore, the second information does not include the communication time information corresponding to the first device.

[0184] The second time information is used to indicate the sum of the local processing time of one or more nodes recommended to participate in the first computing power task and the transmission time of one or more nodes recommended to participate in the first computing power task. For example, if the second device recommends node 1 and node 2 (node ​​1 is the first device) to participate in the first computing power task, the time indicated by the second time information is the sum of the following times: the local processing time of node 1 using model 1, the local processing time of node 2 using model 2, the transmission time of node 1 sending the data to be processed to node 2, and the transmission time of node 2 sending the processed data to node 1. The first computing power task is divided into model 1 and model 2.

[0185] The recommended computing power configuration indicates the amount of computing power recommended for one or more nodes to participate in the first computing power task. The recommended computing power of the first node can be less than or equal to the computing power that the first node can provide within the second time period. In other words, the recommended computing power configuration can be used to recommend how much of the computing power that the first node can provide within a certain time period.

[0186] The second device can send second information. For example, after completing the computing power information analysis, the second device can send the output second information to the first device. For instance, the second device can send a computing power information analysis response message including the second information to the first device. The sending of the computing power information analysis response message can be based on a request (e.g., based on the first request information described below).

[0187] It should be noted that the destination (i.e., the target recipient) of the second information may include one or more nodes recommended to participate in the first computing power task. For example, the destination of the second information may include terminal devices and / or NFs.

[0188] The following table 3 illustrates the output information (i.e., the second information) of the CMF when the first device is the UE and the second device is the CMF, based on the example of the computing power information analysis.

[0189] Table 3

[0190] It should be noted that some content in Table 3 can be implemented independently; that is, some rows in Table 3 can be deleted. Additionally, other output information can be added to Table 3.

[0191] In some embodiments, the first device may send a first request message. The first request message may be used to request the second device to perform computing power analysis on the first computing power task. The first request message may be carried in a computing power information analysis request message, that is, the computing power information analysis request message may include the first request message.

[0192] For example, when the first device needs to perform a first computing task, such as performing local large model inference, if the first device's own computing power is limited and it needs to perform model segmentation to offload computing power, the first device can send a first request message to request the second device to perform computing power analysis. Based on the results of the computing power analysis, the first device can decide how many computing tasks to offload to other devices.

[0193] The first device can add an analysis ID to the message sent to the second device. If the analysis ID is for computing power analysis, the message carries the first request information, that is, the message is used to request the second device to perform computing power analysis.

[0194] In some embodiments, the first request information includes one or more of the following: service description information, the identifier of the first device, and demand information. These will be described in detail below.

[0195] The service description information is used to indicate the service corresponding to the first computing power task. For example, if the service corresponding to the first computing power task is a local model inference service, the service description information is represented by a service ID or a task ID.

[0196] The identifier of the first device can indicate which device sent the first request information, that is, which device requested to perform computing power analysis.

[0197] The participating node information is used to identify the nodes participating in the first computing power task. The first device can indicate one or more nodes participating in the first computing power task. That is, one or more nodes that may participate in the first computing power task can be indicated by the first device through the participating node information. In this case, the second device can only select some or all of the nodes indicated by the participating node information to participate in the first computing power task.

[0198] The demand information is used to indicate the requirements for the first computing power task. In other words, the demand information is used to indicate the conditions that the analysis results of the second device's computing power analysis must meet.

[0199] In some embodiments, the requirement information may include one or more of the following: data requirement information, model requirement information, computing power requirement information, and latency requirement information. These will be described in detail below.

[0200] Data requirement information is used to indicate the input and / or output data of the first computing task. Data requirement information can indicate the input and / or output data of the overall model corresponding to the first computing task. Data requirement information may include one or more of the following: the size, type, and format of the required data.

[0201] Model requirement information indicates the model required to perform the first computing task. This information may specify the overall model for the first computing task and / or multiple models derived from splitting the overall model. Model requirement information may include one or more of the following: the identifier, type, size, etc., of the required model.

[0202] The computing power requirement information indicates the computing power needed to execute the first computing power task. The computing power requirement information may include the amount of computing power required, the effective time period, and the influence of attributes, etc.

[0203] Latency requirement information is used to indicate the latency requirements that need to be met between nodes participating in the first computing task. For example, latency requirement information can be represented by QoS information. Exemplarily, latency requirement information may include the QoS quality of one or more terminal devices, such as the QoS quality of one or more terminal devices or the QoS quality of a first area.

[0204] In some implementations, the latency requirement information may include one or more of the following: the total latency requirement for completing the first computing task, the transmission latency requirement between the nodes participating in the first computing task and the first device, and the local processing time requirement of the nodes participating in the first computing task. The total latency requirement may include the sum of the following latency requirements: the transmission latency requirement between all nodes participating in the first computing task and the first device, and the local processing time requirement of all nodes participating in the first computing task.

[0205] It is understandable that, through the interaction of the first request information and / or the second information, the second device can open up computing power information, computing power analysis results, etc. to the first device.

[0206] Taking a second device including a Computation Management Analyzer (CMF) as an example, the CMF can provide a third service. This third service can be used by the first device to request computational power analysis from the CMF. For example, the third service could be represented as Ncmf_ComputationManagement_Analytics.

[0207] The first device can allocate computing power based on the received second information. For example, the first device can directly execute the recommended computing power configuration in the second information to meet business needs. Alternatively, the first device can, based on other parameters in the computing power information analysis, independently decide how to allocate computing resources and how to offload computing tasks to meet business needs.

[0208] To facilitate understanding, the process of the second device sending information to the first device will be explained in detail below with reference to Figure 9. In Figure 9, the first device is the UE, and the second device is the CMF.

[0209] The method shown in Figure 9 may include steps S910, S920 and S930.

[0210] In step S910, the UE sends a computing power information analysis request to the CMF. The computing power information analysis request includes the following 5 parameters.

[0211] 1. Analyze ID = computing power information.

[0212] 2. UE ID.

[0213] 3. Business description information, such as local model inference business, can be represented by service ID or task ID.

[0214] 4. End-to-end latency requirements, model requirements, computing power requirements, and data requirements.

[0215] 5. Participating node ID.

[0216] Optionally, the computing power information analysis request may also include model information, data information, and computing power information provided by the UE itself. When the computing power information analysis request includes the UE's computing power information, it can be understood that the computing power analysis request includes the first type of information mentioned above.

[0217] In step S920, CMF performs computing power information analysis and generates computing power analysis results.

[0218] Before step S920, the CMF can determine whether the computing power information analysis request and the information stored in the CMF can meet the requirements of computing power analysis, that is, whether the input information (i.e., the third information) for computing power analysis can be provided by the computing power information analysis request and the information stored in the CMF. If the computing power information analysis request and the information stored in the CMF cannot provide some of the input information for computing power analysis, the second device can execute one or more of steps S912 to S917.

[0219] In step S912, if the UE did not carry model information, data information, computing power information, etc. that it could provide in step S920, the CMF sends a data information request to the DMF based on the data requirements in the computing power analysis request sent by the UE. The data information request includes service description information, UE ID, participating node ID, and data requirements.

[0220] In step S913, the DMF returns a data information request response to the CMF based on the data information of the UE and each participating node stored in its own memory. The response includes the data information of the UE and each node mentioned in the third information above.

[0221] In step S914, the CMF sends a model information request to the MMF.

[0222] In step S915, the MMF returns a model information request response. The model information request response includes the model information of the UE and each node, which was included in the third information above.

[0223] In step S916, the CMF sends a QoS information request to the NF, requesting to obtain the QoS information of the UE.

[0224] Step S917: The NF sends back QoS information. The QoS information response includes the UE's QoS information.

[0225] For example, CMF can interact with NWDAF to obtain the QoS sustainability information mentioned above, or the end-to-end data volume transmission latency analysis supported by NWDAF. As another example, CMF can interact with PCF or SMF to obtain service-level or QoS flow-level QoS information.

[0226] In addition, if the CMF wants to ensure that it can provide more timely computing power configuration, the CMF can send computing power information update requests to the relevant UEs and NFs to obtain the latest computing power information of the UEs and NFs.

[0227] In step S930, the CMF sends a computing power information analysis response to the UE.

[0228] The UE can allocate computing power based on the recommended computing power configuration in the computing power analysis response. Alternatively, it can make its own final decision on how to allocate computing resources and how to offload computing tasks based on other parameters in the computing power information analysis, thereby meeting business needs.

[0229] The method embodiments of this application have been described in detail above. The apparatus embodiments of this application are described in detail below. It should be understood that the descriptions of the method embodiments correspond to the descriptions of the apparatus embodiments. Therefore, any parts not described in detail can be referred to the foregoing method embodiments.

[0230] Figure 10 is a schematic structural diagram of a communication device 1000 provided in an embodiment of this application. The communication device 1000 is a first device. The communication device 1000 may include a transmitting unit 1010.

[0231] The sending unit 1010 is used to send first information; wherein the first information is used to indicate the computing power information of the first device.

[0232] In some embodiments, the computing power information of the first device includes one or more of the following: first computing power information, used to indicate the total computing power supported by the first device; attribute information, used to indicate the computing power attributes supported by the first device; second computing power information, used to indicate the computing power that the first device can provide within a first time period; and first time information, used to indicate the first time period.

[0233] In some embodiments, the first information is used to update the second computing power information.

[0234] In some embodiments, the communication device 1000 is further configured to: receive update request information; wherein the update information is configured to request the first device to send the first information for updating the second computing power information.

[0235] In some embodiments, the update request information includes: request reason information, which indicates the reason for sending the update request information.

[0236] In some embodiments, the first information is sent periodically.

[0237] In some embodiments, the communication device 1000 is further configured to: receive timer information; wherein the timer information is used to indicate a first timer, and when the first timer expires, the first device needs to send the first information.

[0238] In some embodiments, the communication device 1000 is further configured to: send a first request message; wherein the first request message is configured to request a second device to perform computing power analysis on a first computing power task.

[0239] In some embodiments, the first request information includes one or more of the following: service description information, used to indicate the service corresponding to the first computing power task; the identifier of the first device; participating node information, used to indicate the identifier of the node participating in the first computing power task; and demand information, used to indicate the demand for the first computing power task.

[0240] In some embodiments, the requirement information includes one or more of the following: data requirement information, used to indicate the input data and / or output data of the first computing power task; model requirement information, used to indicate the model required to execute the first computing power task; computing power requirement information, used to indicate the computing power required to execute the first computing power task; and latency requirement, used to indicate the latency information that needs to be met between nodes participating in the first computing power task.

[0241] In some embodiments, the communication device 1000 is further configured to: receive second information; wherein the second information is used to indicate the computing power analysis results of participating in the first computing power task, and the computing power analysis results are used to indicate information on one or more nodes recommended to participate in the first computing power task.

[0242] In some embodiments, the one or more nodes recommended to participate in the first computing power task include a first node, and the computing power analysis result includes one or more of the following: third computing power information, used to indicate the available computing power and / or available computing power attributes of the first node in a second time period; local processing time information, used to indicate the local processing time of the first node processing the first data using the first model in the second time period; communication time information, used to indicate the transmission time of transmitting the processed data to the first device when the first node processes the first data using the first model in the second time period; second time information, used to indicate the sum of the local processing time of the one or more nodes recommended to participate in the first computing power task and the transmission time of the one or more nodes recommended to participate in the first computing power task; and computing power configuration recommendation, used to indicate the computing power of the one or more nodes recommended to participate in the first computing power task.

[0243] In an optional embodiment, the transmitting unit 1010 may be a transceiver 1230. The communication device 1000 may also include a processor 1210 and a memory 1220, as shown in FIG12.

[0244] Figure 11 is a schematic structural diagram of a communication device 1100 provided in an embodiment of this application. The communication device 1100 is a second device. The communication device 1100 may include a receiving unit 1110.

[0245] The receiving unit 1110 is used to receive first information; wherein the first information is used to indicate the computing power information of the first device.

[0246] In some embodiments, the computing power information of the first device includes one or more of the following: first computing power information, used to indicate the total computing power supported by the first device; attribute information, used to indicate the computing power attributes supported by the first device; second computing power information, used to indicate the computing power that the first device can provide within a first time period; and first time information, used to indicate the first time period.

[0247] In some embodiments, the first information is used to update the second computing power information.

[0248] In some embodiments, the communication device 1100 is further configured to: send update request information; wherein the update information is configured to request the first device to send the first information for updating the second computing power information.

[0249] In some embodiments, the update request information includes: request reason information, which indicates the reason for sending the update request information.

[0250] In some embodiments, the first information is sent periodically.

[0251] In some embodiments, the communication device 1100 is further configured to: send timer information; wherein the timer information is used to indicate a first timer, and when the first timer expires, the first device needs to send the first information.

[0252] In some embodiments, the communication device 1100 is further configured to: receive first request information; wherein the first request information is used to request a second device to perform computing power analysis on a first computing power task.

[0253] In some embodiments, the first request information includes one or more of the following: service description information, used to indicate the service corresponding to the first computing power task; the identifier of the first device; participating node information, used to indicate the identifier of the node participating in the first computing power task; and demand information, used to indicate the demand for the first computing power task.

[0254] In some embodiments, the requirement information includes one or more of the following: data requirement information, used to indicate the input data and / or output data of the first computing power task; model requirement information, used to indicate the model required to execute the first computing power task; computing power requirement information, used to indicate the computing power required to execute the first computing power task; and latency requirement, used to indicate the latency information that needs to be met between nodes participating in the first computing power task.

[0255] In some embodiments, the communication device 1100 is further configured to: send second information; wherein the second information is used to indicate the computing power analysis results of participating in the first computing power task, and the computing power analysis results are used to indicate information on one or more nodes recommended to participate in the first computing power task.

[0256] In some embodiments, the one or more nodes recommended to participate in the first computing power task include a first node, and the computing power analysis result includes one or more of the following: third computing power information, used to indicate the available computing power and / or available computing power attributes of the first node in a second time period; local processing time information, used to indicate the local processing time of the first node processing the first data using the first model in the second time period; communication time information, used to indicate the transmission time of transmitting the processed data to the first device when the first node processes the first data using the first model in the second time period; second time information, used to indicate the sum of the local processing time of the one or more nodes recommended to participate in the first computing power task and the transmission time of the one or more nodes recommended to participate in the first computing power task; and computing power configuration recommendation, used to indicate the computing power of the one or more nodes recommended to participate in the first computing power task.

[0257] In some embodiments, the communication device 1100 is further configured to: obtain the second information based on third information; wherein the third information is used to indicate one or more of the following: fourth computing power information, used to indicate the computing power of the second node, the second node being a node that may participate in the first computing power task; data information, used to indicate the data processed by the second node in performing the first computing power task; model information, used to indicate the model adopted by the second node in performing the first computing power task; and connection information, used to indicate the QoS of one or more terminal devices.

[0258] In some embodiments, the fourth computing power information includes one or more of the following: the total computing power supported by the second node; the computing power that the second node can provide during the second time period; and the second time period.

[0259] In some embodiments, the data information includes one or more of the following: data size information, used to indicate the size of the input data and / or the size of the output data of the second node performing the first computing power task; data type information, used to indicate the type of the input data and / or the type of the output data of the second node performing the first computing power task; and data format information, used to indicate the format of the input data and / or the format of the output data of the second node performing the first computing power task.

[0260] In some embodiments, the model information includes one or more of the following: model identification information, used to indicate the identifier of the model used by the second node to execute the first computing power task; model type information, used to indicate the type of model used by the second node to execute the first computing power task; and model size information, used to indicate the size of the model used by the second node to execute the first computing power task.

[0261] In some embodiments, the one or more terminal devices belong to a first region, and the connection information is used to indicate the QoS of each terminal device in the first region.

[0262] In an optional embodiment, the receiving unit 1110 may be a transceiver 1230. The communication device 1100 may also include a processor 1210 and a memory 1220, as shown in FIG12.

[0263] Figure 12 is a schematic structural diagram of a communication apparatus according to an embodiment of this application. The dashed lines in Figure 12 indicate that the unit or module is optional. The apparatus 1200 can be used to implement the methods described in the above method embodiments. The apparatus 1200 can be a chip or a communication device. The communication device can be, for example, a terminal device or a network device.

[0264] Apparatus 1200 may include one or more processors 1210. The processor 1210 may support apparatus 1200 in implementing the methods described in the preceding method embodiments. The processor 1210 may be a general-purpose processor or a special-purpose processor. For example, the processor may be a CPU. Alternatively, the processor may be other general-purpose processors, digital signal processors (DSPs), ASICs, FPGAs, or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0265] The apparatus 1200 may further include one or more memories 1220. The memories 1220 store a program that can be executed by the processor 1210, causing the processor 1210 to perform the methods described in the preceding method embodiments. The memories 1220 may be independent of the processor 1210 or integrated within the processor 1210.

[0266] The device 1200 may also include a transceiver 1230. The processor 1210 can communicate with other devices or chips via the transceiver 1230. For example, the processor 1210 can send and receive data with other devices or chips via the transceiver 1230.

[0267] This application also provides a computer-readable storage medium for storing a program. This computer-readable storage medium can be applied to the communication device provided in this application, and the program causes a computer to execute the methods performed by the communication device in various embodiments of this application.

[0268] This application also provides a computer program product. The computer program product includes a program. The computer program product can be applied to the communication device provided in this application embodiment, and the program causes a computer to execute the methods performed by the communication device in various embodiments of this application.

[0269] This application also provides a computer program. This computer program can be applied to the communication device provided in this application, and causes the computer to execute the methods performed by the communication device in various embodiments of this application.

[0270] It should be understood that the terms "system" and "network" in this application can be used interchangeably. Furthermore, the terminology used in this application is only for explaining specific embodiments of the application and is not intended to limit the application. The terms "first," "second," "third," and "fourth," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. In addition, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion.

[0271] In the embodiments of this application, the term "instruction" can be a direct instruction, an indirect instruction, or an indication of a relationship. For example, A instructing B can mean that A directly instructs B, such as B being able to obtain information through A; it can also mean that A indirectly instructs B, such as A instructing C, so B can obtain information through C; or it can mean that there is a relationship between A and B.

[0272] In the embodiments of this application, "B corresponding to A" means that B is associated with A, and B can be determined based on A. However, it should also be understood that determining B based on A does not mean that B is determined solely based on A; B can also be determined based on A and / or other information.

[0273] In the embodiments of this application, the term "correspondence" can indicate a direct or indirect correspondence between two things, or an association between two things, or a relationship such as instruction and being instructed, configuration and being configured.

[0274] In this application embodiment, "predefined" or "preconfigured" can be implemented by pre-storing corresponding codes, tables, or other means that can be used to indicate relevant information in the device (e.g., including terminal devices and network devices). This application does not limit the specific implementation method. For example, predefined can refer to what is defined in the protocol.

[0275] In this application embodiment, the "protocol" may refer to a standard protocol in the field of communication, such as the LTE protocol, the NR protocol, and related protocols applied to future communication systems. This application does not limit this.

[0276] In the embodiments of this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0277] In the embodiments of this application, "comprising" can refer to direct inclusion or indirect inclusion. Optionally, "comprising" mentioned in the embodiments of this application can be replaced with "indicating" or "used to determine". For example, "A includes B" can be replaced with "A indicates B" or "A is used to determine B".

[0278] In the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. 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 embodiments of this application.

[0279] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0280] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0281] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0282] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can read or a data storage device such as a server or data center that integrates one or more available media. The available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., digital video discs, DVDs) or semiconductor media (e.g., solid-state disks, SSDs), etc.

[0283] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A wireless communication method, characterized in that, include: The first device sends the first message; The first information is used to indicate the computing power information of the first device.

2. The method according to claim 1, characterized in that, The computing power information of the first device includes one or more of the following: First computing power information is used to indicate the total computing power supported by the first device; Attribute information, used to indicate the computing power attributes supported by the first device; The second computing power information is used to indicate the amount of computing power that the first device can provide within the first time period. First-time information is used to indicate the first time period.

3. The method according to claim 1 or 2, characterized in that, The first information is used to update the second computing power information.

4. The method according to claim 3, characterized in that, Also includes: The first device receives the update request information; The update information is used to request the first device to send the first information for updating the second computing power information.

5. The method according to claim 4, characterized in that, The update request information includes: The request reason information indicates the reason for sending the update request information.

6. The method according to any one of claims 1-5, characterized in that, The first message is sent periodically.

7. The method according to claim 6, characterized in that, Also includes: The first device receives timer information; The timer information is used to indicate the first timer. When the first timer expires, the first device needs to send the first information.

8. The method according to any one of claims 1-7, characterized in that, Also includes: The first device sends the first request information; The first request information is used to request the second device to perform computing power analysis on the first computing power task.

9. The method according to claim 8, characterized in that, The first request information includes one or more of the following: Business description information is used to indicate the business corresponding to the first computing power task; The identifier of the first device; Participating node information, used to indicate the identifiers of the nodes participating in the first computing power task; Demand information, used to indicate the requirements for the first computing power task.

10. The method according to claim 9, characterized in that, The demand information includes one or more of the following: Data requirement information, used to indicate the input data and / or output data of the first computing power task; Model requirement information, used to indicate the model required to perform the first computing power task; Computing power requirement information is used to indicate the computing power required to execute the first computing power task; Latency requirement is used to indicate the latency that needs to be met between nodes participating in the first computing power task.

11. The method according to any one of claims 8-10, characterized in that, Also includes: The first device receives the second information; The second information is used to indicate the computing power analysis results of participating in the first computing power task, and the computing power analysis results are used to indicate information on one or more nodes recommended to participate in the first computing power task.

12. The method according to claim 11, characterized in that, The recommended one or more nodes to participate in the first computing power task include the first node, and the computing power analysis results include one or more of the following: The third computing power information is used to indicate the available computing power and / or available computing power attributes of the first node during the second time period; Local processing time information is used to indicate the local processing time of the first node using the first model to process the first data within the second time period; Communication time information is used to indicate the transmission time when the first node processes the first data using the first model during the second time period, and the processed data is transmitted to the first device. The second time information is used to indicate the sum of the local processing time of the one or more nodes recommended to participate in the first computing power task and the transmission time of the one or more nodes recommended to participate in the first computing power task; The recommended computing power configuration is used to indicate the computing power of one or more nodes recommended to participate in the first computing power task.

13. A wireless communication method, characterized in that, include: The second device receives the first information; The first information is used to indicate the computing power information of the first device.

14. The method according to claim 13, characterized in that, The computing power information of the first device includes one or more of the following: First computing power information is used to indicate the total computing power supported by the first device; Attribute information, used to indicate the computing power attributes supported by the first device; The second computing power information is used to indicate the amount of computing power that the first device can provide within the first time period. First-time information is used to indicate the first time period.

15. The method according to claim 13 or 14, characterized in that, The first information is used to update the second computing power information.

16. The method according to claim 15, characterized in that, Also includes: The second device sends an update request message; The update information is used to request the first device to send the first information for updating the second computing power information.

17. The method according to claim 16, characterized in that, The update request information includes: The request reason information indicates the reason for sending the update request information.

18. The method according to any one of claims 13-17, characterized in that, The first message is sent periodically.

19. The method according to claim 18, characterized in that, Also includes: The second device sends timer information; The timer information is used to indicate the first timer. When the first timer expires, the first device needs to send the first information.

20. The method according to any one of claims 13-19, characterized in that, Also includes: The second device receives the first request information; The first request information is used to request the second device to perform computing power analysis on the first computing power task.

21. The method according to claim 20, characterized in that, The first request information includes one or more of the following: Business description information is used to indicate the business corresponding to the first computing power task; The identifier of the first device; Participating node information, used to indicate the identifiers of the nodes participating in the first computing power task; Demand information, used to indicate the requirements for the first computing power task.

22. The method according to claim 21, characterized in that, The demand information includes one or more of the following: Data requirement information, used to indicate the input data and / or output data of the first computing power task; Model requirement information, used to indicate the model required to perform the first computing power task; Computing power requirement information is used to indicate the computing power required to execute the first computing power task; Latency requirement is used to indicate the latency that needs to be met between nodes participating in the first computing power task.

23. The method according to any one of claims 20-22, characterized in that, Also includes: The second device sends the second information; The second information is used to indicate the computing power analysis results of participating in the first computing power task, and the computing power analysis results are used to indicate information on one or more nodes recommended to participate in the first computing power task.

24. The method according to claim 23, characterized in that, The recommended one or more nodes to participate in the first computing power task include the first node, and the computing power analysis results include one or more of the following: The third computing power information is used to indicate the available computing power and / or available computing power attributes of the first node during the second time period; Local processing time information is used to indicate the local processing time of the first node using the first model to process the first data within the second time period; Communication time information is used to indicate the transmission time when the first node processes the first data using the first model during the second time period, and the processed data is transmitted to the first device. The second time information is used to indicate the sum of the local processing time of the one or more nodes recommended to participate in the first computing power task and the transmission time of the one or more nodes recommended to participate in the first computing power task; The recommended computing power configuration is used to indicate the computing power of one or more nodes recommended to participate in the first computing power task.

25. The method according to claim 23 or 24, characterized in that, Also includes: The second device obtains the second information based on the third information; The third information is used to indicate one or more of the following: The fourth computing power information is used to indicate the computing power of the second node, which is a node that may participate in the first computing power task; Data information, used to indicate the data processed by the second node in executing the first computing power task; Model information, used to indicate the model used by the second node to execute the first computing power task; Connection information used to indicate the Quality of Service (QoS) of one or more terminal devices.

26. The method according to claim 25, characterized in that, The fourth computing power information includes one or more of the following: The total computing power supported by the second node; The amount of computing power that the second node can provide during the second time period; The second time period.

27. The method according to claim 25 or 26, characterized in that, The data information includes one or more of the following: Data size information is used to indicate the size of the input data and / or the size of the output data of the second node when performing the first computing power task; Data type information, used to indicate the type of input data and / or output data of the second node when performing the first computing power task; Data format information is used to indicate the format of the input data and / or the format of the output data for the second node to perform the first computing power task.

28. The method according to any one of claims 25-27, characterized in that, The model information includes one or more of the following: Model identification information, used to indicate the identifier of the model used by the second node to execute the first computing power task; Model type information, used to indicate the type of model used by the second node to execute the first computing power task; Model size information is used to indicate the size of the model used by the second node to execute the first computing task.

29. The method according to any one of claims 25-28, characterized in that, The one or more terminal devices belong to the first area, and the connection information is used to indicate the QoS of each terminal device in the first area.

30. A communication device, characterized in that, The communication device is a first device, and the communication device includes: The sending unit is used to send the first information; The first information is used to indicate the computing power information of the first device.

31. The communication device according to claim 30, characterized in that, The computing power information of the first device includes one or more of the following: First computing power information is used to indicate the total computing power supported by the first device; Attribute information, used to indicate the computing power attributes supported by the first device; The second computing power information is used to indicate the amount of computing power that the first device can provide within the first time period. First-time information is used to indicate the first time period.

32. The communication device according to claim 30 or 31, characterized in that, The first information is used to update the second computing power information.

33. The communication device according to claim 32, characterized in that, The communication device is also used for: Receive update request information; The update information is used to request the first device to send the first information for updating the second computing power information.

34. The communication device according to claim 33, characterized in that, The update request information includes: The request reason information indicates the reason for sending the update request information.

35. The communication device according to any one of claims 30-34, characterized in that, The first message is sent periodically.

36. The communication device according to claim 35, characterized in that, The communication device is also used for: Receive timer information; The timer information is used to indicate the first timer. When the first timer expires, the first device needs to send the first information.

37. The communication device according to any one of claims 30-36, characterized in that, The communication device is also used for: Send the first request message; The first request information is used to request the second device to perform computing power analysis on the first computing power task.

38. The communication device according to claim 37, characterized in that, The first request information includes one or more of the following: Business description information is used to indicate the business corresponding to the first computing power task; The identifier of the first device; Participating node information, used to indicate the identifiers of the nodes participating in the first computing power task; Demand information, used to indicate the requirements for the first computing power task.

39. The communication device according to claim 38, characterized in that, The demand information includes one or more of the following: Data requirement information, used to indicate the input data and / or output data of the first computing power task; Model requirement information, used to indicate the model required to perform the first computing power task; Computing power requirement information is used to indicate the computing power required to execute the first computing power task; Latency requirement is used to indicate the latency that needs to be met between nodes participating in the first computing power task.

40. The communication device according to any one of claims 37-39, characterized in that, The communication device is also used for: Receive the second message; The second information is used to indicate the computing power analysis results of participating in the first computing power task, and the computing power analysis results are used to indicate information on one or more nodes recommended to participate in the first computing power task.

41. The communication device according to claim 40, characterized in that, The recommended one or more nodes to participate in the first computing power task include the first node, and the computing power analysis results include one or more of the following: The third computing power information is used to indicate the available computing power and / or available computing power attributes of the first node during the second time period; Local processing time information is used to indicate the local processing time of the first node using the first model to process the first data within the second time period; Communication time information is used to indicate the transmission time when the first node processes the first data using the first model during the second time period, and the processed data is transmitted to the first device. The second time information is used to indicate the sum of the local processing time of the one or more nodes recommended to participate in the first computing power task and the transmission time of the one or more nodes recommended to participate in the first computing power task; The recommended computing power configuration is used to indicate the computing power of one or more nodes recommended to participate in the first computing power task.

42. A wireless communication device, characterized in that, The communication device is a second device, and the communication device includes: The receiving unit is used to receive the first information; The first information is used to indicate the computing power information of the first device.

43. The communication device according to claim 42, characterized in that, The computing power information of the first device includes one or more of the following: First computing power information is used to indicate the total computing power supported by the first device; Attribute information, used to indicate the computing power attributes supported by the first device; The second computing power information is used to indicate the amount of computing power that the first device can provide within the first time period. First-time information is used to indicate the first time period.

44. The communication device according to claim 42 or 43, characterized in that, The first information is used to update the second computing power information.

45. The communication device according to claim 44, characterized in that, The communication device is also used for: Send update request information; The update information is used to request the first device to send the first information for updating the second computing power information.

46. ​​The communication device according to claim 45, characterized in that, The update request information includes: The request reason information indicates the reason for sending the update request information.

47. The communication device according to any one of claims 42-46, characterized in that, The first message is sent periodically.

48. The communication device according to claim 47, characterized in that, The communication device is also used for: Send timer information; The timer information is used to indicate the first timer. When the first timer expires, the first device needs to send the first information.

49. The communication device according to any one of claims 42-48, characterized in that, The communication device is also used for: Receive the first request information; The first request information is used to request the second device to perform computing power analysis on the first computing power task.

50. The communication device according to claim 49, characterized in that, The first request information includes one or more of the following: Business description information is used to indicate the business corresponding to the first computing power task; The identifier of the first device; Participating node information, used to indicate the identifiers of the nodes participating in the first computing power task; Demand information, used to indicate the requirements for the first computing power task.

51. The communication device according to claim 50, characterized in that, The demand information includes one or more of the following: Data requirement information, used to indicate the input data and / or output data of the first computing power task; Model requirement information, used to indicate the model required to perform the first computing power task; Computing power requirement information is used to indicate the computing power required to execute the first computing power task; Latency requirement is used to indicate the latency that needs to be met between nodes participating in the first computing power task.

52. The communication device according to any one of claims 49-51, characterized in that, The communication device is also used for: Send a second message; The second information is used to indicate the computing power analysis results of participating in the first computing power task, and the computing power analysis results are used to indicate information on one or more nodes recommended to participate in the first computing power task.

53. The communication device according to claim 52, characterized in that, The recommended one or more nodes to participate in the first computing power task include the first node, and the computing power analysis results include one or more of the following: The third computing power information is used to indicate the available computing power and / or available computing power attributes of the first node during the second time period; Local processing time information is used to indicate the local processing time of the first node using the first model to process the first data within the second time period; Communication time information is used to indicate the transmission time when the first node processes the first data using the first model during the second time period, and the processed data is transmitted to the first device. The second time information is used to indicate the sum of the local processing time of the one or more nodes recommended to participate in the first computing power task and the transmission time of the one or more nodes recommended to participate in the first computing power task; The recommended computing power configuration is used to indicate the computing power of one or more nodes recommended to participate in the first computing power task.

54. The communication device according to claim 52 or 53, characterized in that, The communication device is also used for: Based on the third information, the second information is obtained; The third information is used to indicate one or more of the following: The fourth computing power information is used to indicate the computing power of the second node, which is a node that may participate in the first computing power task; Data information, used to indicate the data processed by the second node in executing the first computing power task; Model information, used to indicate the model used by the second node to execute the first computing power task; Connection information used to indicate the Quality of Service (QoS) of one or more terminal devices.

55. The communication device according to claim 54, characterized in that, The fourth computing power information includes one or more of the following: The total computing power supported by the second node; The amount of computing power that the second node can provide during the second time period; The second time period.

56. The communication device according to claim 54 or 55, characterized in that, The data information includes one or more of the following: Data size information is used to indicate the size of the input data and / or the size of the output data of the second node when performing the first computing power task; Data type information, used to indicate the type of input data and / or output data of the second node when performing the first computing power task; Data format information is used to indicate the format of the input data and / or the format of the output data for the second node to perform the first computing power task.

57. The communication device according to any one of claims 54-56, characterized in that, The model information includes one or more of the following: Model identification information, used to indicate the identifier of the model used by the second node to execute the first computing power task; Model type information, used to indicate the type of model used by the second node to execute the first computing power task; Model size information is used to indicate the size of the model used by the second node to execute the first computing task.

58. The communication device according to any one of claims 54-57, characterized in that, The one or more terminal devices belong to the first area, and the connection information is used to indicate the QoS of each terminal device in the first area.

59. A communication device, characterized in that, The device includes a transceiver, a memory, and a processor. The memory stores a program, and the processor invokes the program in the memory and controls the transceiver to receive or transmit signals so that the communication device performs the method as described in any one of claims 1-29.

60. An apparatus, characterized in that, Includes a processor for calling a program from memory to cause the apparatus to perform the method as described in any one of claims 1-29.

61. A chip, characterized in that, Includes a processor for calling a program from memory, causing a device on which the chip is mounted to perform the method as described in any one of claims 1-29.

62. A computer-readable storage medium, characterized in that, It contains a program that causes a computer to perform the method as described in any one of claims 1-29.

63. A computer program product, characterized in that, Includes a program that causes a computer to perform the method as described in any one of claims 1-29.

64. A computer program, characterized in that, The computer program causes the computer to perform the method as described in any one of claims 1-29.

Images