Computing power resource management method and device, storage medium and program product

Abstract

Provided are a computing power resource management method and apparatus, a storage medium and a program product, the method comprising: after establishing a link between a terminal and a computing power node, managing the computing power resource of the computing power node occupied by the terminal, that is, controlling the duration of the terminal occupying the computing power node to be within a certain duration, so that the computing power resource management efficiency is improved. The situation that the computing power resource is occupied by the terminal but is vacant for a long time can be reduced, so that the utilization rate of the computing power resource of the computing power node can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of communication, and particularly relates to a management method and device of computing power resources, a storage medium and a program product. BACKGROUND

[0002] In wireless communication, the computing task of a terminal can be offloaded to a network, and a device (such as a base station, a router, or a gateway device, etc.) in the network is used to execute the computing task, and the computing result is returned to the terminal. The device used to execute the computing task can be referred to as a computing power node. Exemplarily, the terminal initiates a computing power request when a computing service is started, and then establishes a link with a suitable computing power node (at this time, computing data has not been generated). The terminal can send the computing data to the computing power node when the computing data is generated. Taking photographing as an example, a user opens a mobile phone to take a photo. At this time, the service of photo cloud rendering is started, but the user has not clicked the shooting button, and the computing data has not been generated.

[0003] As can be seen from the above process, the computing power resources of the computing power node are allocated to the terminal after the terminal sends the computing power request, and the computing power resources are occupied by the terminal. Therefore, the computing power resources cannot be allocated to other users. However, the computing data has not been generated. If the computing data is not generated, the computing power resources are always empty, which is easy to cause resource waste. SUMMARY

[0004] The present application provides a management method, device, storage medium and program product of computing power resources to improve the utilization rate of computing power resources.

[0005] In a first aspect, the present application provides a management method of computing power resources. The method can be executed by a communication device. The communication device can be a computing power node, a component (such as a chip, a chip system, etc.) configured in the computing power node, or a logic module or software capable of realizing all or part of the functions of the computing power node. The present application does not make any limitation on this. The management method of computing power resources can include the following steps.

[0006] The computing power node establishes a link with the terminal. In a case where the computing power node does not receive data from the terminal within a first time length, the computing power resources are released. The computing power resources are resources used to execute the computing task from the terminal.

[0007] Releasing computing resources can be understood as the computing node ceasing to serve the terminal. Optionally, computing resources can be resources allocated to the terminal for executing computing tasks from the terminal. In this embodiment, computing resources can be at least one of hardware or software resources capable of executing computing tasks. Optionally, computing resources can include, but are not limited to, hardware resources such as a central processing unit (CPU), a graphics processing unit (GPU), a neural processing unit (NPU), and memory.

[0008] In this embodiment of the application, the computing power node manages the release of computing power resources. If no computing task is received from the terminal within the first time period after the terminal establishes a connection, the computing power resources allocated to the terminal are released so that the computing power resources can be used for computing tasks of other terminals, thereby improving the utilization rate of computing power resources.

[0009] In one possible implementation, the first duration can be predefined. Since the first duration can be predefined in the computing node, after establishing a connection with the terminal device, the computing node can look up the predefined first duration and start timing. In this way, the computing node can know the duration of the timing based on its stored first duration, thereby improving the convenience of starting timing from the first duration.

[0010] In another possible implementation, the first duration may be indicated by a computing power control network element. For example, a computing power node receives a first message from a computing power control network element that indicates the first duration, and the computing power control network element manages at least one computing power node.

[0011] In this embodiment, the first message may carry the first duration. Upon receiving the first message, the computing node can parse it to obtain the first duration. This allows the computing node to obtain the first duration promptly, facilitating the timely release of computing resources. Optionally, the first message may also carry identification information corresponding to the first duration. The computing node is configured with a mapping relationship between the identification information and the corresponding duration. After parsing the first message to obtain the identification information corresponding to the first duration, the computing node can find the first duration through the mapping relationship and the identification information. Since the first message carries identification information corresponding to the first duration, and the data size occupied by the identification information can be smaller than the data size occupied by the first duration, this reduces the transmission resources required to indicate the first duration, thus reducing the signaling overhead.

[0012] In one possible implementation, if the computing node does not receive data from the terminal within a first time period, it releases computing resources, including:

[0013] If a computing node does not receive data from a terminal within the first time period, it releases computing resources and dismantles the link with the terminal.

[0014] In this embodiment of the application, if no data is received from the terminal device within a first time period, the computing resources can be released and the link with the terminal can be terminated, thereby releasing the transmission resources between the computing node and the terminal.

[0015] In one possible implementation, if the computing node does not receive data from the terminal within a first time period, it releases computing resources, including:

[0016] If the computing power node does not receive data from the terminal within a first time period, it sends a second message to the computing power control network element, the second message being used to request the release of computing power resources; and if the computing power node receives a third message from the computing power control network element, it releases the computing power resources, the third message being used to instruct the release of computing power resources.

[0017] In this embodiment, the computing power node first requests the computing power control network element to release computing power resources, and then releases the computing power resources after receiving a message from the computing power control network element instructing the release of computing power resources. This is beneficial for the computing power control network element to manage the computing power nodes of the computing power nodes in the network.

[0018] In one possible implementation, the computing node sends a fourth message to the terminal, which is used to notify the terminal that the computing resources have been released.

[0019] In this embodiment of the application, by notifying that the computing resources have been released, the terminal can be informed in a timely manner that the computing resources have been released. In this way, the terminal will no longer initiate subsequent computing tasks to the computing node, reducing the invalid transmission of computing tasks. Furthermore, after the terminal is informed that the computing resources have been released, it can also request new computing resources in a timely manner, which is beneficial to the continuity of terminal computing task execution and improves user experience.

[0020] In one possible implementation, the method for managing computing resources also includes:

[0021] The computing node starts a timer, and the timer corresponds to the first duration.

[0022] Accordingly, if a computing node does not receive data from a terminal within the first time period, it releases computing resources, including:

[0023] If a computing node does not receive data from the terminal after the timer expires, it releases its computing resources.

[0024] The data from the terminal can be data to be computed, which can be understood as the input for the computing node to perform the computation. Additionally, the data from the terminal can also be heartbeat messages, signaling, etc., without restriction.

[0025] In this embodiment, the timer can be maintained locally on the computing node, which allows computing resources to be released in a timely manner.

[0026] In one possible implementation, the method for managing computing resources also includes:

[0027] Before the timer expires, receive data from the terminal and restart the timer.

[0028] In this embodiment, restarting the timer after receiving data from the terminal reduces the efficiency of re-managing the release of computing resources. Furthermore, the terminal can continue to use computing resources, reducing the time required to request new computing resources, thereby improving the user experience.

[0029] Secondly, this application provides another method for managing computing resources. This method can be executed by a communication device, which can be a terminal, a component configured in the terminal (such as a chip, chip system, etc.), or a logic module or software capable of implementing all or part of the terminal's functions. This application does not limit the specific implementation of this method. The method may include:

[0030] The terminal establishes a connection with the computing node, which provides computing resources to the terminal. The terminal receives a fourth message, which notifies the terminal that the computing resources have been released. Computing resources are resources used to execute computing tasks from the terminal, and they are released if no data is received from the terminal within a first time period.

[0031] In this embodiment of the application, the computing resources are released when no data is received from the terminal within a first time period. This allows the computing resources occupied by the terminal to be released in a timely manner, which is conducive to improving the utilization rate of computing resources.

[0032] In one possible implementation, the fourth message originates from the computing power node, meaning that the terminal can be notified that computing resources have been released via the computing power node. Alternatively, the fourth message originates from the computing power control network element, which manages at least one computing power node, including the computing power node; that is, the terminal can be notified that computing resources have been released via the computing power control network element.

[0033] Thirdly, this application provides another method for managing computing resources. This method can be executed by a communication device, which can be a computing power control network element, a component (such as a chip, chip system, etc.) configured in the computing power control network element, or a logic module or software capable of implementing all or part of the functions of the computing power control network element. This application does not limit this aspect. The method may include:

[0034] The computing power control network element receives a second message from the computing power node, which requests the release of computing resources, which are resources used to execute computing tasks from the terminal. The computing power control network element then sends a third message to the computing power node, which instructs the release of computing resources.

[0035] In this embodiment of the application, after receiving the second message from the computing node, the computing power control network element can send a third message to the computing node, thereby instructing the computing node to release computing resources. This allows the computing resources to be released to improve the utilization rate of computing resources and facilitates the computing power control network element in managing the computing resources of computing nodes in the network.

[0036] In one possible implementation, the method further includes:

[0037] A fourth message is sent to the terminal to notify the terminal that computing resources have been released.

[0038] In one possible implementation, the method further includes:

[0039] Send the first message to the computing node. The first message is used to indicate the first duration.

[0040] Fourthly, this application provides another method for managing computing resources. This method can be executed by a communication device, which can be a terminal, a component configured in the terminal (such as a chip, chip system, etc.), or a logic module or software capable of implementing all or part of the terminal's functions. This application does not limit the specific implementation of this method. The method may include:

[0041] The terminal sends a fifth message, which requests computing resources. This fifth message carries one or more of the following: the start time of the computing resource usage, the end time of the computing resource usage, or a second duration, where the second duration is the requested duration of computing resource usage. The terminal receives a sixth message, which includes a response message to the fifth message.

[0042] In this embodiment, the terminal can request the required computing resources and the duration of their usage according to its needs, and can flexibly adjust the computing resources allocated to the terminal and the duration of their usage. Furthermore, the terminal can receive a response message from a fifth message, indicating the actual allocated computing resources and usage duration, etc., which facilitates the management and control of the computing resources of the computing nodes.

[0043] In another possible implementation, the method may also include:

[0044] If the terminal has a remaining duration greater than or equal to the third duration, it sends a seventh message. This seventh message requests a change in computing power requirements. The third duration is less than or equal to the actual available duration of the computing power resources allocated to the terminal, and the remaining duration is the actual available duration of the computing power resources allocated to the terminal.

[0045] In this embodiment of the application, by restricting the terminal from requesting changes to computing power requirements within a certain period of time, the terminal device is given time to determine how to change the computing power requirements, so that the requests to change computing power requirements can be accurately allocated.

[0046] In one possible implementation, the seventh message carries one or more of the following: a first computing power type, a first computing power size, a first computation result feedback time, a first end time, or a fourth duration, where the fourth duration is the requested duration for continued use of computing power resources.

[0047] In this embodiment of the application, the terminal can select the computing power requirement it needs to change, which improves the flexibility of changing computing power requirements.

[0048] In one possible implementation, the method for managing computing resources also includes:

[0049] The terminal receives a ninth message, which carries one or more of the following: a second computing power type, a second computing power size, a second calculation result feedback time, a second end time, or a fifth duration, where the fifth duration is the duration of continued use of computing power resources allocated to the terminal.

[0050] In this embodiment of the application, the parameters requested by the terminal when changing the computing power request may be different from the new parameters actually allocated to the terminal. This is beneficial for changing the computing power requirements of the terminal for the entire network and improving the overall resource utilization of the network.

[0051] In one possible implementation, the sixth message also indicates a third duration, or the third duration is predefined.

[0052] In one possible implementation, after the terminal receives the sixth message, the method further includes:

[0053] The terminal starts a timer to determine whether the computing resources allocated to the terminal have expired; if the timer expires, the terminal releases the computing resources allocated to it.

[0054] In one possible implementation, the method may further include:

[0055] The duration of the terminal update timer is the sum of the remaining duration and the fifth duration. The remaining duration is the difference between the actual available duration of the computing resources allocated to the terminal and the duration of the computing resources already occupied by the terminal. The fifth duration is the duration of the computing resources allocated to the terminal for continued use.

[0056] In one possible implementation, the method for managing the computing resources may further include:

[0057] The second duration is determined based on the application to which the computing task belongs and the first correspondence. The first correspondence is used to indicate the computing power requirements corresponding to the computing tasks of various applications and each application in the various applications. The computing power requirements include one or more of the following: usage duration, computing power type, computing power size, or computing result feedback time.

[0058] In this embodiment of the application, the second duration is determined by calculating the application to which the task belongs and the first correspondence, which can improve the efficiency of finding the second duration. This is beneficial for the terminal to use the computing power resources of the computing power node in a timely manner.

[0059] It should be understood that the application to which the computing task belongs is one identifier for the computing task; that is, the second duration can also be determined by other identifiers.

[0060] In one possible implementation, the method for managing this computing resource also includes:

[0061] If the terminal has more than 0 remaining available time for computing resources and the computing task has stopped, a tenth message is sent to request the release of computing resources.

[0062] In this embodiment of the application, although the usage time of computing resources has not yet been reached, the computing task stops. In this way, the computing resources can be released by sending the tenth message, which is beneficial to improving the utilization rate of computing resources.

[0063] In one possible implementation, when the remaining available time of the terminal's computing resources is greater than 0 and the computing task stops, a tenth message is sent, including:

[0064] If the computing task stops before the timer expires, a tenth message is sent. The timer is used to determine whether the computing resources allocated to the terminal have expired.

[0065] In this embodiment of the application, a timer can be used to determine whether the time for releasing computing resources has been reached, which is beneficial for timely release of computing resources.

[0066] Fifthly, this application provides another method for managing computing resources. This method can be executed by a communication device, which can be a computing power control network element, a component (such as a chip, chip system, etc.) configured in the computing power control network element, or a logic module or software capable of implementing all or part of the functions of the computing power control network element. This application does not limit this aspect. The method may include:

[0067] The computing power control network element receives a fifth message from the terminal, which requests computing power resources. This fifth message carries one or more of the following: the start time of computing power resource usage, the end time of computing power resource usage, or a second duration, where the second duration is the duration of computing power resource usage requested by the terminal. The computing power control network element then sends a sixth message to the terminal, which includes a response message to the fifth message.

[0068] In one possible implementation, the computing power control network element receives a seventh message, which is used to request a change in computing power requirements.

[0069] In another possible implementation, the seventh message carries one or more of the following: a first computing power type, a first computing power size, a first computation result feedback time, a first end time, or a fourth duration, where the fourth duration is the requested duration for continued use of computing power resources.

[0070] In one possible implementation, the computing power control network element sends a ninth message to the terminal, which carries one or more of the following: a second computing power type, a second computing power size, a second calculation result feedback time, a second end time, or a fifth duration, where the fifth duration is the duration of continued use of computing power resources allocated to the terminal.

[0071] In one possible implementation, the sixth message also indicates a third duration, which is less than or equal to the actual available duration of the computing resources allocated to the terminal.

[0072] In one possible implementation, the method for managing computing resources also includes:

[0073] The computing power control network element receives the tenth message from the terminal, which is used to request the release of computing power resources.

[0074] In one possible implementation, the method for managing computing resources also includes:

[0075] When the remaining time is 0 and no seventh message has been received from the terminal, the computing power control network element sends an eighth message. The eighth message is used to indicate the release of computing power resources. The remaining time is the difference between the actual available time of the computing power resources allocated to the terminal and the time that the terminal has occupied the computing power resources.

[0076] In this embodiment of the application, if the remaining time is 0 and no seventh message is received from the terminal, an eighth message is sent, thereby releasing computing resources immediately.

[0077] Sixthly, embodiments of this application also provide a communication device, which includes a module for implementing the method in any of the possible implementations of the first, second, third, fourth, or fifth aspects.

[0078] In a seventh aspect, embodiments of this application also provide another communication device, including a processor and a memory, wherein,

[0079] The memory stores a computer program; the processor invokes the computer program to cause the device to implement the methods in any of the possible implementations of the first, second, third, fourth, or fifth aspects. Optionally, the device further includes a memory. Optionally, the device further includes a communication interface, to which the processor is coupled.

[0080] The processor may include input circuitry, output circuitry, and processing circuitry. The processing circuitry receives signals through the input circuitry and transmits signals through the output circuitry, causing the processor to execute the method in any of the possible implementations of the first, second, third, fourth, or fifth aspects.

[0081] A processor can be implemented in hardware or software. When implemented in hardware, the processor can be a logic circuit, an integrated circuit, etc. When implemented in software, the processor can be a general-purpose processor that reads software code stored in memory. This memory can be integrated into the processor or located outside the processor and exist independently.

[0082] In specific implementation, the processor can be a chip, the input circuit can be an input pin, the output circuit can be an output pin, and the processing circuit can be a transistor, gate circuit, flip-flop, and various logic circuits. The input signal received by the input circuit can be received and input by, for example, but not limited to, a receiver, and the signal output by the output circuit can be output to, for example, but not limited to, a transmitter and transmitted by the transmitter. Furthermore, the input circuit and the output circuit can be the same circuit, which is used as the input circuit and the output circuit at different times. This application does not limit the specific implementation of the processor and various circuits.

[0083] Optionally, there may be one or more processors and one or more memories.

[0084] Alternatively, the memory can be integrated with the processor, or the memory can be set up separately from the processor.

[0085] In specific implementation, the memory can be a non-transitory memory, such as read-only memory (ROM), which can be integrated with the processor on the same chip or set on different chips. The embodiments of this application do not limit the type of memory or the way the memory and processor are set.

[0086] It should be understood that the relevant data interaction process, such as sending indication information, can be the process of outputting indication information from the processor, and receiving capability information can be the process of the processor receiving input capability information. Specifically, the processed output data can be output to the transmitter, and the input data received by the processor can come from the receiver. Here, the transmitter and receiver can be collectively referred to as a transceiver.

[0087] Eighthly, embodiments of this application also provide a computer-readable storage medium storing a computer program or instructions that, when executed by a computer, implement the method in any of the possible implementations of the first, second, third, fourth, or fifth aspects.

[0088] In a ninth aspect, embodiments of this application also provide a computer program product, which includes instructions that, when executed by a computer, implement the method in any of the possible implementations of the first, second, third, fourth, or fifth aspects. Attached Figure Description

[0089] Figure 1 A schematic diagram of a system architecture provided for an embodiment of this application;

[0090] Figure 2 A flowchart illustrating a method for managing computing resources provided in an embodiment of this application;

[0091] Figure 3 A flowchart illustrating another method for managing computing resources provided in this application embodiment;

[0092] Figure 4 A flowchart illustrating another method for managing computing resources provided in this application embodiment;

[0093] Figure 5 A flowchart illustrating another method for managing computing resources provided in this application embodiment;

[0094] Figure 6 A flowchart illustrating another method for managing computing resources provided in this application embodiment;

[0095] Figure 7 A flowchart illustrating another method for managing computing resources provided in this application embodiment;

[0096] Figure 8 A flowchart illustrating another method for managing computing resources provided in this application embodiment;

[0097] Figure 9 A flowchart illustrating another method for managing computing resources provided in this application embodiment;

[0098] Figure 10 A flowchart illustrating another method for managing computing resources provided in this application embodiment;

[0099] Figure 11 A flowchart illustrating another method for managing computing resources provided in this application embodiment;

[0100] Figure 12 A flowchart illustrating another method for managing computing resources provided in this application embodiment;

[0101] Figure 13 This is a schematic diagram of the structure of a communication device provided in an embodiment of this application;

[0102] Figure 14 This is a schematic diagram of another communication device provided in an embodiment of this application. Detailed Implementation

[0103] It should be understood that the steps in different embodiments and between different embodiments can be arranged and combined, and are not limited to the description of the embodiments below. Furthermore, although arrows indicate various operation steps in the flowcharts of the embodiments of this application, the order of implementation of these steps is not limited to the order indicated by the arrows. Unless explicitly stated herein, in some implementation scenarios of the embodiments of this application, the implementation steps in each flowchart can be executed in other orders as needed. In addition, some or all of the steps in each flowchart may include multiple sub-steps or multiple stages based on the actual implementation scenario. Some or all of these sub-steps or stages can be executed at the same time, and each sub-step or stage can also be executed at different times. In scenarios where the execution times are different, the execution order of these sub-steps or stages can be flexibly configured according to needs, and the embodiments of this application do not limit this.

[0104] The technical solutions in this application will now be described with reference to the accompanying drawings.

[0105] The technical solutions of this application can be applied to various communication systems, such as: Long Term Evolution (LTE) system, LTE Frequency Division Duplex (FDD) system, LTE Time Division Duplex (TDD) system, Universal Mobile Telecommunication System (UMTS), 5th Generation (5G) system, or New Radio (NR) or other evolved communication systems such as future communication networks.

[0106] The terminal equipment in this application embodiment can also be referred to as: user equipment (UE), mobile station (MS), mobile terminal (MT), access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, electronic device, user terminal, terminal, wireless communication equipment, user agent, or user device, etc.

[0107] Terminal devices can be devices that provide voice / data connectivity to users, such as handheld devices with wireless connectivity, in-vehicle devices, etc. Currently, examples of terminals include: mobile phones, tablets, laptops, PDAs, mobile internet devices (MIDs), wearable devices, virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals in industrial control, wireless terminals in self-driving vehicles, wireless terminals in remote medical surgery, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, wireless terminals in smart homes, cellular phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), handheld devices with wireless communication capabilities, computing devices or other processing devices connected to wireless modems, in-vehicle devices, wearable devices, terminal devices in 5G networks, or future public land mobile communication networks. Terminal devices in a network (PLMN), etc., are not limited to this in the embodiments of this application.

[0108] By way of example and not limitation, in this embodiment, the terminal device can also be a wearable device. Wearable devices, also known as wearable smart devices, are a general term for devices that utilize wearable technology to intelligently design and develop everyday wearables, such as glasses, gloves, watches, clothing, and shoes. Wearable devices are portable devices that are worn directly on the body or integrated into the user's clothing or accessories. Wearable devices are not merely hardware devices, but also achieve powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include those that are feature-rich, large in size, and can achieve complete or partial functions without relying on a smartphone, such as smartwatches or smart glasses, as well as those that focus on a specific type of application function and require the use of other devices such as smartphones, such as various smart bracelets and smart jewelry for vital sign monitoring.

[0109] Furthermore, in this application embodiment, the terminal device can also be a terminal device in an Internet of Things (IoT) system. IoT is an important component of future information technology development, and its main technical feature is connecting objects to networks through communication technology, thereby realizing an intelligent network of human-machine interconnection and object-to-object interconnection. The terminal device in this application can also be an on-board unit, on-board module, on-board component, on-board chip, or on-board unit built into a vehicle as one or more components or units. The vehicle can implement the methods of this application through the built-in on-board unit, on-board module, on-board component, on-board chip, or on-board unit. Therefore, the embodiments of this application can be applied to vehicle networking, such as vehicle-to-everything (V2X), long-term evolution-vehicle (LTE-V) communication technology, and vehicle-to-vehicle (V2V) communication.

[0110] In addition, the access network device in this application embodiment can also be called a wireless access network device, which can be a transmission reception point (TRP), an evolved NodeB (eNB or eNodeB) in an LTE system, a home base station (e.g., home evolved NodeB or home Node B, HNB), a base band unit (BBU), a wireless controller in a cloud radio access network (CRAN) scenario, or the access network device can be a relay station, access point, vehicle-mounted equipment, wearable device, or access network device in a 5G network or an access network device in a future evolved PLMN network, etc. It can be an access point (AP) in a WLAN, a gNB in ​​a new radio (NR) system, a satellite base station in a satellite communication system, etc. The embodiments of this application are not limited.

[0111] The access network equipment in this embodiment may include centralized unit (CU) nodes, distributed unit (DU) nodes, or access network equipment including CU nodes and DU nodes, or access network equipment including control plane CU nodes (CU-CP nodes), user plane CU nodes (CU-UP nodes), and DU nodes. Access network equipment including CU nodes and DU nodes can separate the protocol layers of the access network equipment, with some protocol layer functions centrally controlled by the CU, and the remaining part or all protocol layer functions distributed in the DU, which is centrally controlled by the CU. As one implementation, the CU deployment protocol stack includes a radio resource control (RRC) layer, a packet data convergence protocol (PDCP) layer, and a service data adaptation protocol (SDAP) layer. The DU deployment protocol stack includes a radio link control (RLC) layer, a media access control (MAC) layer, and a physical layer (PHY). Thus, the CU has RRC, PDCP, and SDAP processing capabilities. The DU has RLC, MAC, and PHY processing capabilities. The above functional division is merely an example and does not constitute a limitation on the CU and DU. That is, there can be other ways to divide functions between the CU and DU, which will not be elaborated upon in this embodiment. The functions of the CU can be implemented by a single entity or by different entities. For example, the functions of the CU can be further divided, such as separating the control plane (CP) and user plane (UP), i.e., the CU control plane (CU-CP) and the CU user plane (CU-UP). For example, CU-CP and CU-UP can be implemented by different functional entities, and CU-CP and CU-UP can be coupled with the DU to jointly complete the functions of the access network device. In one possible approach, CU-CP is responsible for control plane functions, mainly including RRC and PDCP-C, where PDCP-C is mainly responsible for encryption / decryption, integrity protection, and data transmission of control plane data. CU-UP is responsible for user plane functions (UPF), mainly including SDAP and PDCP-U, where SDAP is mainly responsible for processing data from the core network device and mapping data flows to bearers. PDCP-U is primarily responsible for data plane encryption and decryption, integrity protection, header compression, sequence number maintenance, and data transmission. CU-CP and CU-UP are connected via an E1 interface.CU-CP represents the access network device connecting to the core network device through the interface between the core network device and the access network device. It connects to the DU via F1-C (control plane). CU-UP connects to the DU via F1-U (user plane). Additionally, another possible implementation is that PDCP-C is also located in CU-UP, but this application does not limit this implementation.

[0112] In this application embodiment, the core network equipment refers to the equipment in the core network (CN) that provides service support for terminal equipment. Currently, the aforementioned core network equipment can be: access and mobility management function (AMF) entities, session management function (SMF) entities, user plane function entities, etc., which are not listed here. Among them, the aforementioned AMF entity can be responsible for the access management and mobility management of terminal equipment; the aforementioned SMF entity can be responsible for session management, such as user session establishment; the aforementioned UPF entity can be a user plane function entity, mainly responsible for connecting to external networks. It should be noted that in this application, entities can also be referred to as network elements or functional entities. For example, an AMF entity can also be referred to as an AMF network element or an AMF functional entity, and an SMF entity can also be referred to as an SMF network element or an SMF functional entity, etc., and this application does not limit this.

[0113] To make the objectives and technical solutions of this application clearer and more intuitive, the embodiments of this application will be described in detail below with reference to the accompanying drawings and examples, illustrating the communication method and communication device. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit the scope of this application.

[0114] Before introducing the methods and apparatus provided in the embodiments of this application, the following points should be made first.

[0115] First, in the embodiments shown below, the terms and English abbreviations, such as computing power control network element or computing power node, are merely exemplary examples given for ease of description and should not constitute any limitation on this application. This application does not preclude the possibility of defining other terms that can achieve the same or similar functions in existing or future agreements.

[0116] Second, in the embodiments shown below, the first, second, and various numerical designations are merely distinctions for ease of description and are not intended to limit the scope of the embodiments of this application.

[0117] Third, "at least one" means one or more, while "more than one" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, and c can mean: a, or b, or c, or a and b, or a and c, or b and c, or a, b, and c, where a, b, and c can be single or multiple.

[0118] Please see Figure 1 , Figure 1 This is a schematic diagram of a system architecture provided for an embodiment of this application. Figure 1 The system shown may include, but is not limited to, computing power control network element 101, computing power node 102, and terminal 103.

[0119] The computing power control network element 101 manages the computing power nodes 102. Optionally, the computing power control network element 101 can obtain information about each computing power node 102 in the entire network. The information about the computing power node 102 may include, but is not limited to, the location information, computing power type information, and computing power information of the computing power node 102. The location information indicates the location of the computing power node 102. The computing power type information indicates the hardware type of the computing power node 102, such as a central processing unit (CPU), graphics processing unit (GPU), neural processing unit (NPU), and memory. The memory may include, but is not limited to, at least one of random access memory (RAM) or read-only memory (ROM). The computing power information indicates the computing power of the computing power node 102; computing power can also be referred to as computing power resources. Computing power can refer to the computing capability of a device. Methods for measuring computing power may include, but are not limited to, at least one of the following: million instructions per second (MIPS), dhrystonemillion instructions executed per second, operations per second (OPS), floating-point operations per second (FLOPS), or hashes per second (Hash / s). Optionally, the computing power control network element 101 may be a network element added to the computing power network.

[0120] It should be noted that the computing power in this embodiment of the application can be the total computing power of computing node 102, the computing power currently being used by computing node 102, or the remaining computing power of computing node 102, etc., and is not limited here.

[0121] In this embodiment of the application, the computing power control network element 101 may be a logical function network element, deployed in one or more physical nodes (e.g., nodes or devices in the access network or core network).

[0122] The computing node 102 possesses data processing capabilities and is used to process one or more computing tasks or computing data. In this embodiment, the computing node 102 is used to undertake at least part of the data processing required by the terminal 103. Optionally, the computing node 102 may include, but is not limited to, nodes or devices in the network capable of data processing, such as nodes or devices with data capabilities in the access network, bearer network, or core network (e.g., base stations, routers, or gateway devices). The computing node 102 may also include a server, which is not limited herein. For each computing node 102, the computing node 102 can provide one or more services. For example, a computing node 102 can provide at least one of server 1 or service 2. For example, service 1 may be, for example, an image processing service, and service 2 may be, for example, a network status analysis service, which is not limited herein.

[0123] In one possible implementation, computing node 102 includes a server, server 1 providing service 1 and server 2 providing service 2. For example, terminal 103 can be connected to a wireless access network, which is connected to user plane gateway 105 via a bearer network. The bearer network is used for data transmission and may include one or more routing devices 104. User plane gateway 105 can connect to the server via the Internet. Thus, when terminal 103 needs to offload its computing tasks to the network, that is, when it needs to execute computing tasks through computing node 102 in the network, it can sequentially transmit data related to the computing task to the server via the wireless access network device, the bearer network, user plane gateway 105, and the Internet. After the server processes the computing task, it sequentially transmits the processed data (also called the computing result or result data) to terminal 103 via the Internet, user plane gateway 105, the bearer network, and the wireless access network device.

[0124] It should be understood that the above data transmission path is merely an example. The actual transmission path depends on the system architecture and connection relationships, and is not limited here.

[0125] In this application's embodiments, the scenarios for offloading computing power include, but are not limited to, extended reality (XR) and autonomous driving scenarios. For example, with the development of extended reality and autonomous driving in such scenarios, more and more computing power is needed to provide higher-quality services.

[0126] However, terminals 103 (such as glasses, helmets, and vehicles) cannot provide such high computing power. Therefore, one possible implementation is to offload the computing tasks of terminal 103 to the network. Taking cloud gaming as an example, some or all of the game's computing tasks are performed by the game server, and the computing results are then sent back to terminal 103. However, placing the computing power on the server results in significant transmission latency between terminal 103 and the server due to the long distance. For example, if terminal 103 uploads a raw image to the server, it will take a long time to receive the rendered image from the server, resulting in a poor user experience due to the large latency.

[0127] Therefore, in one possible implementation, computing nodes 102 (such as base stations, routers, gateways, etc.) are distributed throughout the network. A suitable computing node 102 can be selected from the nearest node in the network to provide services to users, thereby reducing latency.

[0128] In related technologies, since computing power nodes 102 are scattered throughout the network, for a computing task, terminal 103 can initiate a computing power request to find a suitable computing power node 102, and then know where the data to be computed needs to be sent. Then, computing power node 102 releases the computing power resources occupied by terminal 103 only after receiving a computing power release message from terminal 103. Otherwise, that is, before receiving the computing power release message, some or all of the computing power resources of computing power node 102 are occupied by the services of terminal 103.

[0129] In one possible scenario, the computing service of terminal 103 is initiated, but a computing power request is triggered before the data to be computed is actually generated (for example, a user opens their phone to take a picture, and the photo cloud rendering service is started, but the user has not yet clicked the shutter button, so the data to be computed has not yet been generated). The advantage of this is that when the data to be computed is actually generated, it can be immediately sent to the pre-selected computing power node 102 for computation, without having to temporarily find a computing power node 102, thus saving time. When the network allocates a suitable computing power node 102 to the computing power request of terminal 103, some or all of the computing power resources on that computing power node 102 are occupied by the service of terminal 103. Optionally, if a computing power node 102 can only be occupied by one terminal 103, then some or all of the computing power resources of the computing power node 102 can be allocated to terminal 103. Optionally, if a computing power node 102 can be occupied by at least two terminals 103, then a portion of the computing power resources of the computing power node 102 can be allocated to each of the at least two terminals 103. Optionally, if a computing node 102 can only be occupied by one service of the terminal 103, then some or all of the computing resources of the computing node 102 can be allocated to that service. Optionally, if a computing node 102 can be occupied by at least two services of the terminal 103, then a portion of the computing resources of the computing node 102 can be allocated to each of the at least two services.

[0130] However, the computing power request is triggered before the actual computational data is generated, and the computing power resources allocated upon triggering the request are then occupied and cannot be allocated to other services or terminal 103. Whether the computational data will be generated subsequently (e.g., terminal 103 opens the camera app but then locks the screen without actually clicking the shutter button), or when the computational data will be generated, is uncertain. This means that the computing power resources occupied by terminal 103 may remain idle, leading to various situations where the computing power resources of computing node 102 are wasted. Examples of situations leading to wasted computing power resources include, but are not limited to, the following:

[0131] Scenario 1: Terminal 103 can exhaust or ineffectively occupy the network's computing resources by sending a few computing power request messages without sending any computing data.

[0132] Scenario 2: Terminal 103 may experience signal weakness due to entering an underground parking garage or other reasons. The computing power release message that terminal 103 needs to send to computing power node 102 may fail to be sent successfully, and terminal 103 may even lose network access altogether, requiring it to re-search for a network and re-register. Furthermore, the re-searched network may not be the same as the previous one, making it difficult for terminal 103 to send the computing power release message to computing power node 102 in the previous network. Since computing power node 102 does not receive the message from terminal 103, it will not release the computing power resources occupied by terminal 103, resulting in wasted computing power resources on computing power node 102.

[0133] In view of this, embodiments of this application propose a method, apparatus, storage medium, and program product for managing computing resources, which can release the computing resources occupied by computing nodes in a timely manner, reduce the situation where resources are occupied but left idle for a long time, thereby improving the utilization rate of computing resources and reducing the waste of computing resources.

[0134] In one possible implementation, the timing of releasing computing resources can be managed. For example, after a terminal device requests computing resources, if the terminal does not send data to the computing node for a long time, the computing node can be triggered to release the computing resources occupied by the terminal.

[0135] The following is an exemplary description of the solution of the embodiments of this application, with reference to the flowchart.

[0136] Please see Figure 2 , Figure 2 This is a flowchart illustrating a method for managing computing resources according to an embodiment of this application. This embodiment manages computing resources through computing nodes. If a terminal requests computing resources but fails to send data for an extended period, the computing node automatically releases the computing power. The method in this embodiment may include:

[0137] S201. Establish a link between the terminal and the computing power node.

[0138] In this embodiment, a link is established between the terminal and the computing node, allowing data and messages to be transmitted between them. For example, the terminal can send computational data to the computing node via this link, and the computing node, after processing the computational data and obtaining the result data, returns the result data to the terminal via the same link. Taking an image processing task as an example, the terminal can send the image data it needs to display to the computing node via this link. Then, the computing node renders the image data based on the image data, obtaining the rendered image data, and then sends the rendered image data back to the computing node via the same link. For instance, the link between the terminal and the computing node can be described as follows:Figure 1 The following is an example illustration of the link. It should be understood that the link between the terminal and the computing node is related to factors such as the location of the terminal, the location of the computing node, and the network architecture, but no specific limitations are made here. It should also be understood that computing tasks can be voice processing tasks, in which case the terminal can transmit voice data to the computing node.

[0139] In one possible implementation, the terminal sends a computing power request to the computing power control network element. This request is used to request the allocation of computing power nodes. The computing power request carries at least one of the terminal's location information or the computing power resources required by the terminal. The computing power control network element can then allocate a suitable computing power node to the terminal based on the information carried in the request. For example, it can allocate the computing power node closest to the terminal, or allocate a node that meets the terminal's computing power requirements, or allocate the closest computing power node while meeting the terminal's requirements, or select the computing power node with the largest computing power resource or the computing power resource closest to the terminal's requirements from among multiple computing power nodes close to the terminal. This is not limited in scope. The terminal can then link with the computing power node allocated to it by the computing power control network element. This method of allocating suitable computing power resources to the terminal improves the effective utilization of the overall network's computing power resources. Optionally, the computing power request may also carry the terminal's device identification information. The computing power control network element can then allocate a computing power node to be linked with the terminal from among the computing power nodes associated with the terminal based on the device identification information carried in the computing power request.

[0140] In another possible implementation, the terminal can broadcast a computing power request. This request can be used to establish a link with a computing power node. If the computing power node receiving the request is not currently in use, it returns a response message to the terminal. The terminal can then select one of the computing power nodes that returned the response message to establish a link. This improves the efficiency of establishing a link between the terminal and the computing power node. Optionally, when establishing a link with a computing power node, the terminal can also notify the computing power control network element of the linked computing power node, or a computing power node can notify the computing power control network element of the linked terminal when establishing a link with the terminal. In this way, the computing power control network element can know the link relationship between the terminal and the computing power node.

[0141] In another possible implementation, the terminal broadcasts a computing power request, and then the computing power node forwards the computing power request to the computing power control network element, which then allocates a suitable computing power node to the terminal.

[0142] It should be understood that the above-described link between the terminal and the computing node is only an example, and this embodiment does not impose specific restrictions on how the link between the terminal and the computing node is established.

[0143] S202, Computing power control network element indicates the duration of computing power node failure.

[0144] Among them, the failure duration can be used to determine whether it is time to release the computing resources of the computing node.

[0145] In one possible implementation, the failure duration can be predefined. Optionally, the predefined failure duration can be consistent for all computing power nodes. In this case, the computing power control network element can indicate the predefined failure duration for that computing power node. For example, if the predefined failure duration is duration T1, the computing power control network element indicates the failure duration T = T1 for the computing power node. This allows the computing power control network element to promptly indicate the failure duration of the computing power node, which facilitates timely management of the computing power node and further reduces the waste of computing power resources. Alternatively, a certain amount of time can be added to or subtracted from the predefined failure duration T1 to determine the indicated failure duration T. In another possible implementation, corresponding coefficients can be configured based on the information carried in the computing power request reported by the terminal. For example, if the computing power request carries information 1, the corresponding duration coefficient is K1; if the computing power request carries information 2, the corresponding duration coefficient is K2. Then, the product of the predefined failure duration T1 and the duration coefficient is used as the indicated failure duration T for the computing power node. For example, if a terminal that has established a link with a computing power node reports a computing power request carrying information 1, then the computing power control network element indicates that the failure duration T of the computing power node is equal to the default failure duration T1 * duration coefficient K1. This allows for different failure durations to be indicated for computing power nodes based on different situations, which helps improve the accuracy of computing power resource release timing and enhances user experience.

[0146] It should be noted that the information carried in the computing power request can also include the terminal's movement speed, which can then determine the duration coefficient. In one possible implementation, the greater the terminal's movement speed, the greater the likelihood that the terminal is moving away from the computing power node, and thus the greater the possibility that a new computing power node needs to be allocated to the terminal. Therefore, a greater terminal movement speed corresponds to a smaller duration coefficient, allowing for faster release of computing power resources. In other words, a smaller terminal movement speed corresponds to a larger duration coefficient, allowing for slower release of computing power resources. Optionally, a speed threshold can be configured. If the movement speed is higher than the speed threshold, the duration coefficient is K1; if the movement speed is lower than or equal to the speed threshold, the duration coefficient is K2, where K1 > K2.

[0147] S203, Computing node start timer.

[0148] In this embodiment, the purpose of starting the timer includes: determining when to release the computing power resources of the computing power node, which can also be understood as determining whether the terminal's occupation of the computing power resources of the computing power node has timed out; in other words, determining whether the terminal's occupation of the computing power resources is within a suitable occupation time. Optionally, the duration of the computing power node starting the inactive timer is T2, i.e., inactive timer = T2. Here, T2 can be understood as the management duration of the timer. Optionally, the management duration T2 of the timer is related to the failure duration T indicated by the computing power control network element. In one possible implementation, the management duration T2 of the timer = the indicated failure duration T of the computing power node. In this way, the management of computing power resource occupation can start in a timely manner. In another possible implementation, the failure duration T indicated by the computing power control network element = the predefined failure duration T1. Then, the management duration T2 of the timer can be configured with a corresponding coefficient according to the information carried by the computing power request reported by the terminal, and then the product of the failure duration T indicated by the computing power control network element and the coefficient is used as the management duration of the timer. For example, if the computing power request reported by the terminal that has established a link with the computing power node carries information 1, then the management duration T2 of the timer = the failure duration T indicated by the computing power control network element * duration coefficient K1. In this way, different management durations can be indicated to the computing power node according to different situations, which helps to improve the accuracy of the timing of computing power resource release and improve the user experience.

[0149] It should be noted that the computing power request reported by the terminal can be sent to the computing power node or to the computing power control network element. If the terminal sends the computing power request to the computing power control network element, the computing power control network element can forward the computing power request to the computing power node, or send the information carried in the computing power request to determine the management duration to the computing power node. The computing power node can then determine the coefficients through the request or information forwarded by the computing power control network element.

[0150] It should be understood that after determining the management duration T2 of the timer, the timer can start counting down. The countdown can start from 0 and gradually increase. When the timer reaches the management duration T2, it can be considered that the timer has timed out, indicating that the terminal has exceeded its computing resource usage limit. Alternatively, the timer can start counting down from the management duration T2 and gradually decrease. When the timer reaches 0, it can also be considered that the timer has timed out, indicating that the terminal has exceeded its computing resource usage limit. In another possible implementation, the start time of the countdown can be unrestricted; as long as the time difference between the last time and the start time reaches the management duration T2, it can be determined whether the computing resource usage has timed out.

[0151] It should be noted that the timing of the timer's start can be as follows: it can begin after receiving the failure duration indicated by the computing power control network element; it can begin after determining the management duration; it can begin some time after receiving the failure duration; it can begin some time after determining the management duration; it can begin after the computing power node establishes a connection with the terminal; or it can begin some time after establishing a connection with the terminal. There are no restrictions on this. The interval can be predefined or indicated by the computing power control network element.

[0152] S204. The terminal sends data to the computing node.

[0153] In this embodiment, the data sent by the terminal to the computing node may include, but is not limited to, computational data or heartbeat data. The heartbeat data indicates that the terminal is alive, or it can be understood as indicating that the terminal maintains a normal connection with the computing node.

[0154] S205, Computing node restart timer.

[0155] In this embodiment, if the computing node receives data from the terminal before the timer expires (i.e., before the timer expires), the timer is restarted. This allows for a fresh start in determining whether the terminal's use of the computing node's computing resources has timed out. It should be noted that the timer's starting point after restarting can be referenced in S203, and will not be repeated here. For example, the computing node restarts with inactivetimer = T.

[0156] It should be noted that the management duration of the timer after restarting can be the same as or different from the management duration of the timer when it was first started. If the management duration of the timer after restarting is different from the management duration of the timer when it was first started, it can be greater or less than the management duration of the timer when it was first started. This allows for flexible adjustment of the management duration after restarting the timer, thereby improving the flexibility of releasing computing resources.

[0157] S206. The computing node determines whether the timer has timed out.

[0158] The timer timeout status can be referred to in S203, and is not limited here. In this embodiment, since the timer will be restarted if data is received from the terminal before the timer expires, if the timer expires, it means that no data was received from the terminal before the timer expired, indicating that the terminal has been consuming computing resources for too long without any data. In this case, the computing resources occupied by the terminal can be released. For example, the terminal determines whether the inactive timer has expired.

[0159] Therefore, in this embodiment, if the computing node determines that the timer has expired, S207 is executed. If the computing node determines that the timer has not expired, the timer continues to count down.

[0160] S207. The computing node sends a computing resource release message to the computing control network element.

[0161] Among them, the computing power resource release message can be used to request the release of the computing power resources of the computing power node occupied by the terminal, or to instruct the release of the computing power resources of the computing power node occupied by the terminal.

[0162] In this embodiment, the computing power node sends a computing power resource release message to the computing power control network element when the timer expires and no data is received from the terminal. In other words, when the timer expires, the computing power node informs the computing power control network element to release the corresponding computing power resources. After receiving the computing power resource release message, the computing power control network element can execute at least one of S208 or S209.

[0163] S208, the link between the computing power control network element trigger terminal and the computing power node is dismantled.

[0164] In this embodiment, the computing power control network element informs the terminal of computing power release and triggers the terminal to dismantle the link with the computing power node. After the computing power control network element informs the terminal of computing power release, the terminal no longer occupies the computing power resource, meaning the computing power resource can be released. Then, the terminal can dismantle the link with the computing power node. Optionally, the terminal can immediately dismantle the link with the computing power node after receiving the notification of computing power release, thereby releasing the link resource between the computing power node and the terminal. Alternatively, the link with the computing power node can be dismantled after a certain period of time. Before dismantling the link, the terminal can request to use the computing power resource of the computing power node from the computing power control network element or the computing power node. In this way, when the terminal requests to use the computing power resource of the computing power node again, it does not need to re-establish the link, which can improve the efficiency of the terminal continuing to use the computing power resource of the computing power node.

[0165] S209, The link between the computing power control network element triggering the dismantling of the computing power node and the terminal.

[0166] In this embodiment, the computing power control network element responds to the computing power node's computing power resource release message and triggers the computing power node to dismantle the link with the terminal. After the computing power control network element responds to the computing power node's computing power resource release message, the computing power resources occupied by the terminal can be released. Then, the computing power node can dismantle the link with the terminal. Optionally, the computing power node can immediately dismantle the link with the terminal after receiving the computing power control network element's response to the computing power resource release message, or it can dismantle the link with the terminal after a certain period of time; no limitation is imposed here.

[0167] It should be understood that S208 and S209 can be executed either one or separately, which can improve the success rate of releasing computing resources and the success rate of dismantling the link between computing nodes and terminals.

[0168] In S207-S209, the computing power nodes send computing power resource release messages to the computing power control network element to inform the computing power nodes and / or terminals to release computing power resources. In this way, the computing power control network element can know which computing power nodes have released computing power resources, and then the computing power control network element can redistribute the released computing power resources to other terminals, which can improve the overall utilization rate of the network's computing power resources.

[0169] Another possible implementation is to release computing resources and dismantle links through S210.

[0170] In another possible implementation, S209 may not be necessary. That is, the computing resource release message is used to notify or inform the computing node that its computing resources need to be released. Then, the computing node can release the computing resources directly without waiting for a response message to the computing resource release message, which can improve the timeliness of computing resource release.

[0171] S210, the link between the dismantling of computing nodes and the terminal.

[0172] In this embodiment, the computing power node informs the terminal of the release of computing power and disconnects the link between the computing power node and the terminal. The computing power node informs the terminal of the release of computing resources, simultaneously releasing the computing resources occupied by the terminal, and disconnects the link between the computing power node and the terminal. This improves the timeliness of computing resource release. The disconnection of the link can be referred to in the description of S208, and will not be repeated here.

[0173] Optionally, while informing the computing power control network element to release computing power resources, the computing power node can also generate a data or control message. This data or control message can be sent to the terminal through the connection between the computing power node and the terminal to inform the terminal to release computing power and dismantle the link between itself and the terminal. In another possible implementation, the computing power node can notify the terminal to release computing power resources, thereby triggering the terminal to dismantle the link between itself and the computing power node.

[0174] In this embodiment of the application, by establishing a link between the terminal and the computing power node, the computing power node begins to manage the release of computing power resources. If data is received from the terminal before the timer expires, the timer is restarted. If no data is received from the terminal after the timer expires, the computing power resources are released and the link is terminated. In this way, the situation where the computing power resources of the computing power node are controlled for a long time can be reduced, thereby improving the utilization rate of computing power resources.

[0175] In another possible implementation, S202 may not be necessary. In this case, when determining the management duration, the computing node can use the default failure duration as the management duration, or determine the management duration by multiplying the default failure duration with the coefficient. This part can be referred to in the relevant descriptions of S202 and S203, and will not be elaborated here.

[0176] In other words, after a computing node is instructed to provide services to a terminal, it can start a timer. This timer can either decrement from a value (e.g., the management duration) until it reaches 0, or it can increment from 0 until a certain threshold (e.g., the management duration). The timer's duration or expiration threshold can be predefined or configured by the computing power control network element. This allows for the timely release of managed computing resources, which helps improve the utilization rate of computing resources.

[0177] In another possible implementation, in S205, the release of computing resources can also be managed by using the operating system's timed tasks or delay functions of the computing node to implement the timed function, without any restrictions.

[0178] exist Figure 2 In the illustrated embodiment, the timing of releasing computing resources is managed through computing power nodes. In another possible implementation, the timing of releasing computing resources can also be managed by a computing power control network element. The following description uses an embodiment where the computing power control network element manages the timing of computing resources.

[0179] Please see Figure 3 , Figure 3This is a flowchart illustrating another method for managing computing resources provided in an embodiment of this application. In this embodiment, management can be achieved through a computing power control network element. If a terminal requests computing power resources but fails to send data to the computing power node for an extended period, the computing power control network element instructs the computing power node or the terminal to automatically release the computing power. The method in this embodiment may include:

[0180] S301. Establish a link between the terminal and the computing power node.

[0181] S301 can be referred to the explanation of S201, and will not be repeated here.

[0182] S302, Start-up timer for computing power control network element.

[0183] The management duration of the timer can be referred to in the description of S203, and will not be repeated here.

[0184] S303, The terminal sends data to the computing power node.

[0185] S303 can be referred to the explanation of S204, and will not be repeated here.

[0186] S304. The computing power node informs the computing power control network element that the computing power node has received data from the terminal.

[0187] In this embodiment of the application, the computing power node can notify the computing power control network element that it has received data from the terminal through a message, data or message.

[0188] S305, Computing power control network element restart timer.

[0189] In this embodiment, if the computing node informs that it has received data from the terminal, it indicates that the computing resources of the computing node have not been idle for a long time, and the timer can be restarted. S305 can be referred to in the description of S205, and will not be repeated here.

[0190] S306, the computing power control network element determines whether the timer has timed out.

[0191] For S306, please refer to the explanation of S206, which will not be repeated here.

[0192] S307, the link between the computing power control network element trigger terminal and the computing power node is dismantled.

[0193] S308, the link between the computing power control network element triggering the dismantling of computing power nodes and the terminal.

[0194] For S307-S308, please refer to the explanation of S208-S209, and it will not be repeated here.

[0195] In this embodiment, by establishing a link between the terminal and the computing power node, the computing power control network element begins to manage the release of computing power resources. If it is known that the computing power node has received data from the terminal before the timer expires, the timer is restarted. If there is still no notification from the computing power node that it has received data from the terminal after the timer expires, the computing power resources are released and the link is terminated. In this way, the situation where the computing power resources of the computing power node are controlled for a long time can be reduced, thereby improving the utilization rate of computing power resources.

[0196] In another possible implementation, S304 can be replaced by: when the terminal sends data to the computing power node, it also informs the computing power node that it has sent data through a message, data or message. In this way, the computing power control network element can also restart the timer, thereby triggering the computing power control network element to restart the timer in a timely manner, reducing the situation where the computing power control network element still instructs to release computing power resources when the terminal has already sent data to the computing power node.

[0197] In another possible implementation, the computing power control network element can also inform the terminal to release computing power and trigger the terminal to dismantle the link between the terminal and the computing power node.

[0198] exist Figure 2 and Figure 3 In the example, the network includes a computing power control network element, computing power nodes, and terminals. In some cases, the computing power control network element may not be necessary, for example, when a terminal requests a connection from a computing power node, or when the capabilities of the computing power control network element are integrated into the computing power node. In other words, the computing power control network element and the computing power node are the same node or device.

[0199] Please see Figure 4 , Figure 4 This is a flowchart illustrating another method for managing computing resources provided in an embodiment of this application. Figure 4 The methods shown may include:

[0200] S401. Establish a link between the terminal and the computing node.

[0201] S401 can be referred to the explanation of S201, and will not be repeated here.

[0202] S402, Computing node start timer.

[0203] S402 can be referred to in the explanation of S203, and will not be repeated here. When determining the management duration, the computing node can use the default failure duration as the management duration, or determine the management duration by multiplying the default failure duration by a coefficient. This part can be referred to in the relevant descriptions of S202 and S203, and will not be repeated here.

[0204] S403, The terminal sends data to the computing node.

[0205] S403 can be referred to the explanation of S204, and will not be repeated here.

[0206] S404, Computing node restart timer.

[0207] S404 can be referred to the explanation of S205, and will not be repeated here.

[0208] S405, the computing node determines whether the timer has timed out.

[0209] S405 can be referred to the explanation in S206, and will not be repeated here.

[0210] S406, the link between the dismantling of computing nodes and the terminal.

[0211] S406 can be referred to the explanation in S210, and will not be repeated here.

[0212] In this embodiment of the application, by establishing a link between the terminal and the computing power node, the computing power node begins to manage the release of computing power resources. If data is received from the terminal before the timer expires, the timer is restarted. If no data is received from the terminal after the timer expires, the computing power resources are released and the link is terminated. In this way, the situation where the computing power resources of the computing power node are controlled for a long time can be reduced, thereby improving the utilization rate of computing power resources.

[0213] In another possible implementation, the management of computing resource release can also be performed on the terminal. That is, the terminal starts a timer, the management duration of which can be predefined or indicated by the computing power control network element. The terminal restarts the timer every time it sends data to the computing power node. Then, if the timer expires, the terminal can directly release the computing power resources and dismantle the link with the computing power node, or request the computing power control network element to release the computing power. The computing power control network element can then inform the terminal and / or the computing power node to release the computing power and dismantle the link between the terminal and the computing power node.

[0214] In another possible implementation, at least two of the terminal, computing node, and computing control network element can jointly manage the release of computing resources, thereby improving the accuracy of computing resource release. It should be noted that, in this embodiment, computing resources can be released when any one of the terminal, computing node, or computing control network element times out and requires release; alternatively, computing resources can only be released when at least two of the terminal, computing node, or computing control network element times out and require release.

[0215] It should be understood that if at least two of the terminal, computing node, and computing control network element jointly manage the release of computing resources, then the terminal, computing node, and computing control network element can use the same or different timers for management. If the terminal, computing node, and computing control network element use different timers for management, then each of the terminal, computing node, and computing control network element can maintain its own local timer.

[0216] The above embodiments provide an exemplary description of the management of computing resource release. The following embodiments, based on the above embodiments, provide an exemplary description of how a terminal instructs itself on the duration of computing resource usage when requesting computing power. Compared to the above embodiments, the following embodiments facilitate more refined management of computing resource usage because the terminal instructs itself on the duration of computing resource usage. Furthermore, the terminal can also request changes to its computing power requirements to improve the flexibility of its computing resource usage.

[0217] Please see Figure 5 , Figure 5 This is a flowchart illustrating another method for managing computing resources provided in an embodiment of this application. Figure 5 The methods shown may include:

[0218] S501. The terminal sends a computing power request to the computing power control network element. The computing power request carries the computing power type 1, computing power requirement 1, computing result feedback time 1, and computing power resource usage duration 1.

[0219] The computing power request is used to request computing power to be allocated to the terminal. The computing power type 1 can indicate the type of computing power, such as requesting a central processing unit, graphics processing unit, or neural network processor. In this embodiment, computing power type 1 can be the type of computing power the terminal expects to be allocated. The computing power requirement can indicate the computing power needed by the terminal; the computing power requirement can also be simply referred to as computing power. The computation result feedback time 1 can indicate the interval between when the terminal expects to send computation data and when it receives the result data. In other words, the computation result feedback time 1 indicates that the interval between when the terminal expects to send computation data and when it expects to receive the result data is less than the computation result feedback time 1, meaning that after sending computation data, the terminal expects to receive the result data within the computation result feedback time 1. The computing power resource usage duration can be the time the terminal requests to use computing power resources; that is, it indicates how long the computing power resources need to be used. Optionally, the computing power resource usage duration can be, for example, the continuous duration or the cumulative duration of the terminal occupying the computing power resources.

[0220] In this embodiment of the application, when a terminal requests the allocation of computing power resources, it can carry the information related to the computing power it needs in the computing power request. In this way, the terminal can obtain computing power resources that match its needs, thereby improving the accuracy of computing power resource matching.

[0221] In another possible implementation, the computing power request may carry some parameters from computing power type, computing power requirement 1, computation result feedback time 1, or computing power resource usage duration 1. This can reduce the transmission resources required to send the computing power request. Optionally, the computing power request may carry at least parameters related to the usage time of the computing power resources, such as computing power resource usage duration 1.

[0222] S502, the computing power control network element sends a confirmation message to the terminal. The confirmation message carries computing power node information, actual allocated computing power resource usage duration 2, time threshold, computing power demand 2, computing power type 2, and calculation result feedback time 2.

[0223] The confirmation message can be a response to a computing power request. The computing power node information indicates the computing power node allocated to the terminal. Optionally, the computing power node information may include address information or identification information of the computing power node, allowing the terminal to establish a link with it. In other words, S501 and S502 can be understood as a process of establishing a link between the terminal and the computing power node. The allocated computing power resource usage duration 2 refers to the actual resource usage duration allocated to the terminal (also known as the available computing power resource duration), meaning the terminal can use the computing power node's computing power resources within this usage duration 2. Optionally, the confirmation message may also carry the allocated computation result feedback time 2. The computation result feedback time 2 in the confirmation message may be the same as or different from the computation result feedback time 1 requested in the computing power request. Optionally, the confirmation message may also carry the actual allocated computing power type 2. The computing power type 2 in the confirmation message may be the same as or different from the computing power type 1 requested in the computing power request. It should be understood that if the computing power type 2 in the confirmation message is different from the computing power type 1 requested in the computing power request, then the computing power type 2 in the confirmation message needs to be able to perform the computing tasks required by the terminal.

[0224] It should be noted that the actual computing resource usage duration 2 allocated by the computing power control network element can be the same as or different from the computing resource usage duration 1 requested by the terminal. If they are different, the computing resource usage duration 2 can be greater than or less than the computing resource usage duration 1. In this embodiment, the computing power control network element can allocate the actual computing resource usage duration 2 to the terminal according to the actual situation. In this embodiment, the computing power control network element can determine the actual allocated computing resource usage duration 2 based on the requested computing resource usage duration 1. In one possible implementation, a certain amount of time can be added to or subtracted from the computing resource usage duration 1 to obtain the computing resource usage duration 2. In another possible implementation, there can be a predefined coefficient, in which case the computing power control network element can use the product between the computing resource usage duration 1 and the predefined coefficient as the computing resource usage duration 2. For example, if a computing power request carries information 1, the corresponding duration coefficient is K3; if the request carries information 2, the corresponding duration coefficient is K4. The product of computing power resource usage duration 1 and the duration coefficient is then used as computing power resource usage duration 2. For example, if a terminal linking to a computing power node reports a computing power request carrying information 1, then the actual computing power resource usage duration 2 allocated by the computing power control network element is = computing power resource usage duration 1 * duration coefficient K3. This allows for the allocation of different computing power resource usage durations 2 based on different situations, which helps improve the accuracy of computing power resource occupancy and increase the overall utilization rate of network computing power resources.

[0225] It should be noted that the information carried in the computing power request can also include the terminal's movement speed, which can then determine the duration coefficient. In one possible implementation, the higher the terminal's movement speed, the greater the likelihood that the terminal is moving away from the computing power node, and thus the greater the possibility that a new computing power node needs to be allocated to the terminal. Therefore, a higher terminal movement speed corresponds to a smaller duration coefficient, allowing for faster release of computing power resources. In other words, a lower terminal movement speed corresponds to a larger duration coefficient, allowing for slower release of computing power resources. Optionally, a speed threshold can be configured. If the movement speed is higher than the speed threshold, the duration coefficient is K3; if the movement speed is lower than or equal to the speed threshold, the duration coefficient is K4, where K3 > K4.

[0226] The time threshold can refer to the time limit for restricting the terminal to update its computing power requirements. In other words, if the terminal needs to change its computing power requirements, it is expected that the terminal will initiate the change of computing power requirements within the time threshold. That is to say, the terminal needs to initiate the change of computing power requirements within the time threshold. It can also be understood as an instruction that if the terminal wants to renew its computing power resources, it must initiate a renewal request (also known as a computing power update message) at least this long in advance, so as to leave sufficient processing time for the network.

[0227] It should be noted that, in one possible implementation, if the terminal initiates a change in computing power demand within the specified time threshold, the computing power control network element accepts the change; if the terminal initiates a change in computing power demand outside the specified time threshold, the computing power control network element does not accept the change. The change in computing power demand may include, but is not limited to, changes to at least one of the following: computing power resource usage duration, computing power type, or computing power. In another possible implementation, the result of the terminal initiating a change in computing power demand within the specified time threshold is superior to the result of the terminal initiating a change in computing power demand outside the specified time threshold. Since the change in computing power demand includes changes to computing power and / or changes to computing power resource usage duration, the actual allocated computing power and computing power resource usage duration are higher when the change in computing power demand is initiated within the specified time threshold than when the change in computing power demand is initiated outside the specified time threshold.

[0228] For example, if a terminal requests to change to computing power 2 within the time threshold, the actual computing power allocated to the terminal is computing power 3. If the terminal requests to change to computing power 2 outside the time threshold, the actual computing power allocated to the terminal is computing power 4, where computing power 4 < computing power 3. Assuming the terminal requests to change to computing power resource usage duration 3 within the time threshold, the actual computing power resource usage duration allocated to the terminal is computing power resource usage duration 4, where computing power resource usage duration 5 < computing power resource usage duration 4.

[0229] In this embodiment, the actual allocated computing power and the duration of computing power resource usage may differ from those requested by the terminal. This allows for the allocation of computing power and the duration of computing power resource usage based on the actual situation, thereby improving the flexibility of computing power resource allocation and usage duration allocation.

[0230] It should be noted that S501 and S503 can be understood as the process of establishing a link between the terminal and the computing power node.

[0231] S503, Terminal Start Timer.

[0232] In this embodiment, the timer duration can be equal to twice the actual allocated computing resource usage time. In this application, the timer duration can be gradually reduced starting from twice the actual allocated computing resource usage time. When the current timer duration is 0, it can be considered that the timer has timed out, meaning the terminal's use of computing resources has expired. In another possible implementation, the timer duration can be less than twice the actual allocated computing resource usage time.

[0233] In summary, the terminal maintains a local timer, the initial value of which can be the available computing resources duration indicated in the network response message. When the timer value deducts to a level below a certain threshold, such as below a standard preset value (e.g., 0), or below a time threshold, and the terminal anticipates that the service may still need to continue, or when the terminal wants to modify the computing resource requirements, steps S505-S507 can be executed. If the service has stopped before the timer expires, step S509 is executed to release the computing resources in advance.

[0234] It should be noted that the timing of the terminal starting the timer can be either after the terminal receives the confirmation message or after a certain period of time after receiving the confirmation message; there is no restriction here.

[0235] S504: The terminal determines whether the remaining duration of the timer is greater than the time threshold and whether it still wants to continue using computing resources.

[0236] In this embodiment of the application, if the remaining duration of the timer is greater than the time threshold and the terminal still wants to continue using computing resources, then S505 is executed.

[0237] It should be understood that in S504, the remaining duration of the timer is less than or equal to twice the duration of computing resource usage.

[0238] In one possible implementation, if the terminal wants to continue using computing resources, but the remaining timer duration is less than or equal to the time threshold, the timer continues to run until the remaining timer duration is 0, at which point the computing resources are released. Alternatively, if the terminal wants to continue using computing resources, but the remaining timer duration is less than or equal to the time threshold, the steps in S505 can still be executed.

[0239] It should be noted that if the timer starts counting from 0, then S504 can be used by the terminal to determine whether the remaining duration of the timer is less than or equal to the time threshold and whether it still wants to continue using computing resources. If the remaining duration of the timer is less than the time threshold and the terminal still wants to continue using computing resources, it can initiate a change in computing power requirements.

[0240] S505, The terminal sends a computing power update message to the computing power control network element. The computing power update message carries the computing power demand 3 and the computing power resource usage duration 3.

[0241] The `renew` message is used to request a change in computing power requirements. It can also be called a computing power renewal message. The computing power requirement of 3 in the `renew` message can be either the terminal's expectation to change the allocated computing power to 3 or an expectation to increase the allocated computing power by 3. In other words, the computing power requirement of 3 can be a final result (also called a total amount) or an increment. The computing power resource usage duration of 3 carried in the `renew` message can be the terminal's expectation to extend the time occupied by the computing power resources by this usage duration of 3. Optionally, the computing power resource usage duration of 3 can be the final duration (also called a total amount), meaning the terminal expects to update the remaining timer duration to the computing power resource usage duration of 3; or it can be an increased duration (also called an increment), meaning the terminal expects to add this computing power resource usage duration of 3 to the current remaining time to obtain the final duration. For example, the terminal expects the remaining timer duration = current remaining time + computing power resource usage duration of 3.

[0242] In this embodiment of the application, the terminal can send a computing power update message to the computing power control network element to change the computing power request. In this way, it is not necessary to re-request computing power after release, which can improve the utilization efficiency of computing power resources.

[0243] In another possible implementation, the computing power update message can carry the computing power requirement of 3 or the computing power resource usage duration of 3, which can reduce the transmission resources required to send the computing power update message, that is, reduce the transmission resources required to update computing power resources.

[0244] S506, the computing power control network element sends a computing power update confirmation message to the terminal. The computing power update confirmation message carries the computing power requirement of 4 and the computing power resource usage duration of 4.

[0245] The `renew acknowledge` (`renew ACK`) message can be considered a response to the `computing power update` request. `computing power requirement 4` can be the actual computing power requirement allocated by the computing power control network element. The computing power requirement can be a final result or an increment; refer to the explanation of `computing power requirement 3` for details, which will not be repeated here. `computing power resource usage duration 4` can be the actual usage duration allocated by the computing power control network element. `computing power resource usage duration 4` can be a final result or an increment; refer to the explanation of `computing power resource usage duration 3` for details, which will not be repeated here.

[0246] The computing power requirement 4 and the computing power requirement 3 can be the same or different. Optionally, if the computing power requirement 4 and the computing power requirement 3 are different, the computing power requirement 3 can be greater than or less than the computing power requirement 1. This can be allocated according to the actual situation and is not restricted here.

[0247] The computing resource usage duration 4 can be the same as or different from the computing resource usage duration 3. Optionally, if the computing resource usage duration 4 is different from the computing resource usage duration 3, the computing resource usage duration 4 can be greater than or less than the computing resource usage duration 3.

[0248] In this embodiment, the actual updated computing power and computing resource usage time may differ from those requested by the terminal. This allows for updates to the computing power and usage time based on actual conditions, improving the flexibility of these updates. Optionally, the relationship between computing resource usage time 4 and computing resource usage time 3 can be analogous to the relationship between computing resource usage time 2 and computing resource usage time 1, where computing resource usage time 4 corresponds to computing resource usage time 2, and computing resource usage time 3 corresponds to computing resource usage time 1.

[0249] It should be understood that the information carried in the computing power update confirmation message corresponds to the information carried in the computing power update message. For example, if the computing power request carries a computing power requirement of 3, then the computing power update confirmation message carries a computing power requirement of 4; if the computing power request carries a usage duration of 3, then the computing power update confirmation message carries a usage duration of 4. This also reduces the transmission resources required for the computing power control network element to send the computing power update confirmation message to the terminal.

[0250] In this embodiment, the computing power update request can also be called a computing power continuation request. Furthermore, this computing power continuation request may not include any parameters, in which case the computing power control network element can issue a new request based on the terminal's initial computing power request or the initial resource allocation for the terminal (e.g., the resource allocation information carried in the confirmation message or computing power request). Alternatively, this computing power continuation request may only carry a continuation duration parameter. Optionally, this continuation request may carry parameters of the same type as those in the computing power request, used to change the computing power requirement, such as increasing the total computing power from 100 to 150; or changing the computing power type, etc. The network responds to the computing power continuation request with a computing power update confirmation message, which may carry the actual computing power allocated to the terminal.

[0251] It's important to note that while S501-S502 are similar to S505-S506, the processing flow for a request received from S501 differs from that received from S505. For example, upon receiving an S501 request, the network needs to find a computing power node for the terminal, configure link establishment parameters, and trigger the establishment of a link between the computing power node and the terminal. However, upon receiving an S505 request, the network should update the computing power demand allocation information on the already designated computing power node as much as possible. Unless the current computing power node becomes unable to continue serving the terminal due to an update in the terminal's computing power demand, the steps of S501 can be re-executed to find a new computing power node, etc. Furthermore, the network can reject a computing power demand request initiated by the terminal if it is unable to process it.

[0252] It should be noted that changes can also be made to computing power requirements such as computing power type and computation result feedback time, without limitation. For example, a computing power update message requesting a change to computing power type 3 or computation result feedback time 3, etc. Correspondingly, the computing power update confirmation message can also carry the actual allocated type 4 and computation result feedback time 4, etc.

[0253] It should be understood that the parameters carried in the computing power update confirmation message can correspond to the parameters carried in the computing power update message. For example, if the computing power update message carries the computing power type, then the computing power update confirmation message can carry the actual allocated computing power type.

[0254] S507, The terminal increases the computing resource usage time by 4 to the remaining time of the timer.

[0255] In this embodiment of the application, the computing resource usage duration 4 can be an incremental duration. For example, the remaining duration of the timer = the current remaining duration + the computing resource usage duration 4. In other words, the duration of the timer = the computing resource usage duration 4 + the remaining value. For example, Timer = computing resource usage duration 4 + the current remaining value of Timer.

[0256] In another possible implementation, the computing resource usage time 4 can be a total duration, for example, the remaining duration of the timer = computing resource usage time 4.

[0257] In this embodiment of the application, when the terminal successfully renews the loan, the terminal updates its local timer duration. This can be done by directly updating the duration information in the response message to the loan renewal request or the duration information in the loan renewal request, or by adding the duration in the response message to the loan renewal request or the duration in the loan renewal request to the current remaining value, as described in S507.

[0258] It should be noted that the terminal can be restricted to changing its computing power requirements only once, or the terminal can change its computing power requirements again. Optionally, the number of times the computing power requirements can be changed can be unlimited, which can improve the flexibility of computing power requirements. Alternatively, the number of times the computing power requirements can be changed can be limited to a certain number, which can reduce the situation where the terminal occupies the computing power node for a long time.

[0259] S508: The terminal determines whether the timer has timed out.

[0260] The method for determining whether the timer has timed out can be referred to the relevant description in S206, and will not be repeated here. In this embodiment, if the timer has timed out, that is, if the terminal determines that the timer has timed out, then step S509 is executed.

[0261] S509: The terminal sends a computing resource release message to the computing power control network element.

[0262] S509 can be referred to in the description of S207, and will not be repeated here. The difference between this embodiment and S207 is that the subject that sends the computing resource release message to the computing power control network element is different.

[0263] S510, the computing power control network element triggers the termination of the link between the terminal and the computing power node.

[0264] S510 can be referred to the description of S208, and will not be repeated here. In the embodiments of this application, how to release computing resources and dismantle the link between the computing node and the terminal can be referred to... Figure 2 The description of the embodiments is omitted here. Furthermore, the computing power control network element can also notify the computing power nodes to release computing power, thereby triggering the disconnection of the link between the computing power nodes and the terminals. Optionally, a message can be sent to the terminal or computing power node to release computing power; this message can be a response message to the computing power resource release message.

[0265] In another possible implementation, if the timer does not expire, but the business that the terminal needs to process has ended, such as the camera application being closed, the terminal can also execute step S509 to release computing resources in advance.

[0266] S511, the computing power control network element triggers the dismantling of the link between the computing power node and the terminal.

[0267] S511 can be referred to in the explanation of S209, and will not be repeated here.

[0268] In summary, this application embodiment requires the terminal to specify the duration of the computing power resource to be used when issuing a computing power request. For example, the maximum usage time for voice services is 60 seconds, and the maximum usage time for video services is 30 seconds. Therefore, when a service starts, the terminal can first estimate when the service it needs to process will end or the duration it needs to last. Subsequently, if the service ends early, the terminal can also proactively initiate a computing power release request to release it early. Similarly, if the service wants to continue, it can initiate a renewal request when the computing power resource is about to expire.

[0269] In another possible implementation, the terminal can also disconnect the link with the computing node without having to perform the steps of S509.

[0270] In this embodiment, not only can the release of computing resources be managed to improve the utilization rate of computing resources, but the terminal can also improve the flexibility and accuracy of computing resource allocation based on the requested duration of computing resource usage, that is, the requested duration of computing resource occupation.

[0271] In another possible implementation, in S501, the computing power request sent by the terminal can also carry the start time of computing power resource usage. Correspondingly, the timer can start counting at that start time, thus improving the flexibility of computing power resource usage. In another possible implementation, the end time of computing power resource usage can also be carried. The countdown time of the timer can be determined by the end time and the start time, thus controlling the release of computing power resources. In yet another possible implementation, the computing power resource usage duration 1 can be predefined. Therefore, the computing power request does not need to carry the computing power resource usage duration 1, thus reducing the transmission resources required to send the computing power request. In yet another possible implementation, the computing power request can also indicate the time during which it will not use computing power resources. Thus, by knowing the time period during which the terminal will not use computing power resources as indicated in the computing power request, the time during which the terminal needs to use computing power resources can be determined, thereby enabling the management of computing power resource release. Correspondingly, in S502, the terminal can also be indicated with the actual start time of using computing power resources and / or the actual end time of using computing power resources.

[0272] In another possible implementation, in S505, the computing power update message can carry a requested new start time and / or a requested new end time, thus also enabling the modification of the terminal's usage time of computing power resources. Specifically, the terminal can continue using the computing power node at the requested new start time; that is, between the end time of usage of computing power resources in S501 or S502 and the requested new start time, the computing power resources can be temporarily released, or they can remain available, depending on the actual situation.

[0273] In another possible implementation, in S506, the computing power update confirmation message can carry the actually allocated new start time and / or the actually allocated new end time, thus also enabling the modification of the terminal's usage time of computing power resources. The terminal can continue using the computing power node at this actually allocated new start time; that is, between the end time of using computing power resources in S501 or S502 and the actually allocated new start time, the computing power resources can be temporarily released, or they can remain available, depending on the actual situation.

[0274] In another possible implementation, the confirmation message in S502 may not carry a time threshold. This allows the terminal to request a change in computing power requirements before the timer expires. Since the confirmation message does not carry a time threshold, less transmission resources are required to send it. Furthermore, the time threshold can be predefined, meaning it can also be omitted from the confirmation message. Alternatively, the time difference between the end time and the time threshold can be predefined, allowing the time threshold to be determined by specifying the end time of computing power resource usage and the difference. This time difference can also be carried in the confirmation message. Furthermore, S502 may not be necessary, allowing the duration of the started timer to be the requested computing power resource usage duration 1. Alternatively, S502 can send a confirmation message without specifying the computing power resource usage duration 2, further reducing the transmission resources required to send the confirmation message. In another possible implementation, the time threshold can be variable, for example, by carrying a new time threshold in the computing power update confirmation message. Optionally, the new time threshold can be the same as or different from the existing time threshold. If different, the new time threshold can be less than or greater than the existing time threshold.

[0275] In another possible implementation, S504-S507 may not be necessary, meaning that they may not support the updating or renewal of computing power requirements, thus enabling the timely release of computing power resources.

[0276] In another possible implementation, in S505, the computing power update message may not carry the computing power requirement 3 and computing power resource usage duration 3, thus reducing the transmission resources required to send the computing power update message. In this case, the computing power requirement 3 or computing power resource usage duration 3 can be predefined; or modified according to the computing power requirement 1 or computing power resource usage duration 1 requested in the computing power request; or modified according to the computing power requirement 2 or computing power resource usage duration 2 in the confirmation message. In another possible implementation, the computing power control network element can also reject the computing power update. Optionally, the computing power control network element can reject it if the terminal initiates a computing power update outside the time threshold, or if the computing power resource needs to be allocated to other terminals later.

[0277] In another possible implementation, if the terminal requests to change the computing power or computing resource usage duration, the actual allocated computing power and computing resource usage duration can be predefined, that is, it is unrelated to the computing power or computing resource usage duration requested by the terminal.

[0278] In another possible implementation, the method of this application embodiment can also be applied to the server corresponding to the service or application used by the terminal. The server corresponding to the service or application and the computing power node can be different devices or the same device, without limitation. If the server corresponding to the service or application and the computing power node are different devices, the server corresponding to the service or application performs a part of the data processing related to the service or application, and the computing power node performs another part of the data processing related to the service or application.

[0279] In another possible implementation, the capabilities of the computing power control network element are integrated into the computing power node; in other words, the computing power control network element and the computing power node are the same node or device.

[0280] pass Figure 5 As shown in the illustrated embodiment, the request to release computing resources is made through the terminal. However, if the terminal is consuming network computing resources, it may not actively initiate a request to release computing resources after the timer expires, thus posing a risk of computing resources being idle for an extended period. Therefore, the following embodiments further illustrate how to reduce the long-term idleness of computing resources, building upon the previous embodiments. In the following embodiments, the release of computing resources can be managed through computing nodes or computing control network elements.

[0281] First, the management of computing resource release through computing power control network elements will be explained.

[0282] Please see Figure 6 , Figure 6This is a flowchart illustrating another method for managing computing resources provided in an embodiment of this application. Figure 6 The methods shown may include:

[0283] S601. The terminal sends a computing power request to the computing power control network element. The computing power request carries the computing power type 1, computing power requirement 1, computing result feedback time 1, and computing power resource usage duration 1.

[0284] S602, The computing power control network element sends a confirmation message to the terminal. The confirmation message carries computing power node information, actual allocated computing power resource usage duration 2, time threshold, computing power demand 2, computing power type 2, and calculation result feedback time 2.

[0285] The explanations for S601-S602 can be found in the descriptions of S501-S502, and will not be repeated here.

[0286] S603, Start-up timer for computing power control network element.

[0287] In this embodiment, the duration of the timer started by the computing power control network element can be equal to twice the actual allocated computing power resource usage time. The purpose of starting the timer by the computing power control network element includes determining when to trigger the release of computing power resources. S603 can be referred to the description of S503, and will not be repeated here. The difference between S603 and S503 includes that the objects that start the timer are different.

[0288] S604, Terminal Start Timer.

[0289] S605: The terminal determines whether the remaining duration of the timer is greater than the time threshold and whether it still wants to continue using computing resources.

[0290] S606. The terminal sends a computing power update message to the computing power control network element. The computing power update message carries the computing power demand 3 and the computing power resource usage duration 3.

[0291] S607, The computing power control network element sends a computing power update confirmation message to the terminal. The computing power update confirmation message carries the computing power requirement of 4 and the computing power resource usage duration of 4.

[0292] S608, The terminal increases the computing resource usage time by 4 to the remaining time of the timer.

[0293] For S604-S608, please refer to the descriptions of S503-S507, and they will not be repeated here.

[0294] In this embodiment, the timer on the terminal may function to determine whether the time for requesting a change in computing power requirements has been exceeded. Furthermore, if the terminal can initiate the release of computing power resources, the timer's function may also include determining whether the time for releasing computing power resources has been reached.Figure 5 In this embodiment, the timer on the terminal may function to: determine whether computing resources need to be released and whether the time for requesting a change in computing power requirements has been exceeded.

[0295] S609, The computing power control network element increases the computing power resource usage time by 4 to the remaining time of the timer.

[0296] S610, the computing power control network element determines whether the timer has timed out.

[0297] For S609-S610, please refer to the descriptions in S507-S508.

[0298] S611, the computing power control network element triggers the terminal to dismantle the link between the computing power node and the computing power node.

[0299] S612, the computing power control network element triggers the dismantling of the link between the computing power node and the terminal.

[0300] The explanations for S611-S612 can be found in S510-S511, and will not be repeated here.

[0301] In this embodiment of the application, the release of computing resources can also be managed through computing power nodes, which can reduce the risk of computing resources being idle for a long time and thereby improve the utilization rate of computing resources.

[0302] In another possible implementation, if there is no time threshold to consider, the terminal may not need a timer for timing. This would reduce the convenience of managing computing resources.

[0303] In another possible implementation, the time threshold can also be variable. For example, after the terminal requests a change in computing power requirements, the computing power control network element instructs the terminal to set a new time threshold, such as in the computing power update confirmation message.

[0304] The following section explains the management of computing resource release through computing nodes. Please refer to [link / reference]. Figure 7 , Figure 7 This is a flowchart illustrating another method for managing computing resources provided in an embodiment of this application. Figure 7 The methods shown may include:

[0305] S701. The terminal sends a computing power request to the computing power control network element. The computing power request carries the computing power type 1, computing power requirement 1, computing result feedback time 1, and computing power resource usage duration 1.

[0306] S702, the computing power control network element sends a confirmation message to the terminal. The confirmation message carries computing power node information, actual allocated computing power resource usage duration 2, time threshold, computing power demand 2, computing power type 2, and calculation result feedback time 2.

[0307] S703, The computing power control network element indicates the actual usage time of the allocated computing power resources for the computing power node is 2.

[0308] S704, Computing Node Startup Timer.

[0309] In this embodiment of the application, the duration of the timer started by the computing node is equal to twice the actual usage time of the allocated computing resources.

[0310] S705, Terminal Startup Timer.

[0311] S706: The terminal determines whether the remaining duration of the timer is greater than the time threshold and whether it still wants to continue using computing resources.

[0312] S707, The terminal sends a computing power update message to the computing power control network element. The computing power update message carries the computing power demand 3 and the computing power resource usage duration 3.

[0313] S708, the computing power control network element sends a computing power update confirmation message to the terminal. The computing power update confirmation message carries the computing power requirement of 4 and the computing power resource usage duration of 4.

[0314] S709, The terminal increases the computing resource usage time by 4 to the remaining time of the timer.

[0315] S710, the computing power control network element indicates the computing power node's usage time for the computing power resource is 4.

[0316] S711, the computing node increases the computing resource usage time by 4 to the remaining time of the timer.

[0317] S712, the computing node determines whether the timer has timed out.

[0318] S713, Send a computing resource release message to the computing power control network element.

[0319] S714, the computing power control network element triggers the terminal to dismantle the link between the computing power node and the computing power node.

[0320] S715, the link between the computing power control network element triggering the dismantling of computing power nodes and the terminal.

[0321] S716, the link between the dismantling of computing nodes and the terminal.

[0322] For S701-S716, please refer to the description of S601-S612, which will not be repeated here.

[0323] In this embodiment of the application, the release management of computing resources can also be carried out through computing power nodes, which can reduce the risk of computing resources being idle for a long time and thus improve the utilization rate of computing resources.

[0324] In another possible implementation, at least two of the computing power nodes, computing power control network elements, and terminals can manage the release of computing power resources. That is, the release of computing power resources can be triggered only after at least two managing nodes have granted permission to release them. This improves the accuracy of computing power resource management. In this embodiment, managing the release of computing power resources through one of the computing power nodes, computing power control network elements, or terminals improves the timeliness of computing power resource release.

[0325] It should be noted that for computing nodes, computing control network elements, and terminals, the timer is deployed on the node itself. That is, each computing node, computing control network element, and terminal has its own timer deployed. Alternatively, the clock of a network device can be used as the timer. In this case, the computing nodes, computing control network elements, and terminals can determine whether the timer has expired by requesting time from that device or requesting an indication of whether the timer has expired.

[0326] The following examples summarize and illustrate the above examples.

[0327] Please see Figure 8 , Figure 8 This is a flowchart illustrating another method for managing computing resources provided in an embodiment of this application. The method described in this application can be applied to computing nodes. Figure 8 The methods shown may include:

[0328] S801, establishing a connection between the computing node and the terminal.

[0329] The process of establishing a link between the computing node and the terminal can be referred to in the description of S201, and will not be repeated here.

[0330] It should be noted that the link established in the embodiments of this application may be, for example, a packet data unit session (PDU session), or a logical channel for data exchange, such as letting the terminal know the Internet Protocol (IP address) of the computing power node so that the terminal device can send data to the computing power device at any time, etc., without limitation.

[0331] S802. If the computing node does not receive data from the terminal within the first time period, it releases computing resources, which are resources used to execute computing tasks from the terminal.

[0332] The first duration can be the duration for which the computing node determines when to trigger the release of computing resources. Optionally, this first duration can be fixed or dynamically changing. Furthermore, the first duration can be restarted under certain conditions. Optionally, the first duration can be managed through a timer, such as the timer in S206.

[0333] S802 can be referred to the explanations in S206-S210, and will not be repeated here.

[0334] It should be noted that the release of computing resources can be understood as the computing nodes ceasing to provide services to the terminals.

[0335] In this embodiment of the application, the computing power node manages the release of computing power resources. If no computing task is received from the terminal within the first time period after the terminal establishes a connection, the computing power resources allocated to the terminal are released so that the computing power resources can be used for computing tasks of other terminals, thereby improving the utilization rate of computing power resources.

[0336] In one possible implementation, the first duration can be predefined. Since the first duration can be predefined in the computing node, after establishing a connection with the terminal device, the computing node can look up the predefined first duration and start timing. In this way, the computing node can know the duration of the timing based on its stored first duration, thereby improving the convenience of starting timing from the first duration.

[0337] In another possible implementation, the first duration may be indicated by a computing power control network element. For example, a computing power node receives a first message from a computing power control network element that indicates the first duration, and the computing power control network element manages at least one computing power node.

[0338] In this embodiment, the first message may carry the first duration. Upon receiving the first message, the computing node can parse it to obtain the first duration. This allows the computing node to obtain the first duration promptly, facilitating the timely release of computing resources. Optionally, the first message may also carry identification information corresponding to the first duration. The computing node is configured with a mapping relationship between the identification information and the corresponding duration. After parsing the first message to obtain the identification information corresponding to the first duration, the computing node can find the first duration through the mapping relationship and the identification information. Since the first message carries identification information corresponding to the first duration, and the data size occupied by the identification information can be smaller than the data size occupied by the first duration, the transmission resources required to indicate the first duration can be reduced.

[0339] It should be noted that the first message can be an existing message. The first duration can be indicated by using the free fields of the first message or reusing the used fields of the first message. In other words, in addition to indicating the first duration, the first message can also indicate other parameters or information. Furthermore, the message can be a newly defined message, at least for indicating the first duration, but this is not limited here.

[0340] For example, the first duration can also be called the failure duration. The first duration of the computing power node indicated by the computing power control network element can be referred to the description in S202, which will not be repeated here.

[0341] In one possible implementation, if the computing node does not receive data from the terminal within a first time period, it releases computing resources, including:

[0342] If a computing node does not receive data from a terminal within the first time period, it releases computing resources and connections.

[0343] For example, the embodiments of this application can be described with reference to S209 or S210, which will not be repeated here.

[0344] In this embodiment of the application, if no data is received from the terminal device within a first time period, the computing resources can be released and the link with the terminal can be terminated, thereby releasing the transmission resources between the computing node and the terminal.

[0345] In another possible implementation, the computing node may not release its computing resources initially. In this way, if the terminal needs to continue using the computing resources of the computing node later, it will not be necessary to rebuild the chain, which can improve the efficiency of continuing to use computing resources.

[0346] In one possible implementation, if the computing node does not receive data from the terminal within a first time period, it releases computing resources, including:

[0347] If the computing power node does not receive data from the terminal within a first time period, it sends a second message to the computing power control network element, the second message being used to request the release of computing power resources; and if the computing power node receives a third message from the computing power control network element, it releases the computing power resources, the third message being used to instruct the release of computing power resources.

[0348] For example, the second message can also be called a computing resource release message. The third message can also be called a response message, such as a response message to the computing resource release message. The embodiments of this application can be referred to in the description of S208-S209, which will not be repeated here.

[0349] In this embodiment, the computing power node first requests the computing power control network element to release computing power resources, and then releases the computing power resources after receiving a message from the computing power control network element instructing the release of computing power resources. This is beneficial for the computing power control network element to manage the computing power nodes of the computing power nodes in the network.

[0350] In another possible implementation, if the computing node does not receive data from the terminal within the first time period, it sends a second message to the computing power control network element and then releases the computing power resources, or it does not need to send a second message to the computing power control network element, which can improve the timeliness of computing power resource release.

[0351] In one possible implementation, the computing node sends a fourth message to the terminal, which is used to notify the terminal that the computing resources have been released.

[0352] The fourth message could be, for example, a data packet carrying the most recent computation result of the computing node, or a data packet carrying arbitrary data but with an indication in its header. This indication indicates the computing power of the computing node; for example, a computing power of 0 indicates that the computing resources have been released, thus instructing the terminal to release the connection. Alternatively, the computing node could instruct the terminal to release the connection by sending the same technical result twice consecutively.

[0353] For example, the embodiments of this application can be described with reference to S210, which will not be repeated here.

[0354] In this embodiment of the application, by notifying that the computing resources have been released, the terminal can be informed in a timely manner that the computing resources have been released. In this way, the terminal will no longer initiate subsequent computing tasks to the computing node, reducing the invalid transmission of computing tasks. Furthermore, after the terminal is informed that the computing resources have been released, it can also request new computing resources in a timely manner, which is beneficial to the continuity of terminal computing task execution and improves user experience.

[0355] In another possible implementation, the computing node may not want the terminal to send a fourth message. If the terminal requests the computing node to execute a computing task but does not receive the result data from the computing node within a time threshold, it can be assumed that the computing node's computing resources have been released. In this way, the transmission resources of the computing node can be reduced.

[0356] In one possible implementation, the method for managing computing resources also includes:

[0357] The computing node starts a timer, and the timer corresponds to the first duration.

[0358] Accordingly, if a computing node does not receive data from a terminal within the first time period, it releases computing resources, including:

[0359] If a computing node does not receive data from the terminal after the timer expires, it releases its computing resources.

[0360] The computing nodes can be timed using timers. It should be noted that the timer can be started after the chain is established or after receiving the first message instruction; there are no restrictions on when to start it.

[0361] For example, this embodiment can be described with reference to S206, which will not be repeated here.

[0362] In one possible implementation, the method for managing computing resources also includes:

[0363] Before the timer expires, receive data from the terminal and restart the timer.

[0364] For example, the embodiments of this application can be described with reference to S205, which will not be repeated here.

[0365] In this embodiment of the application, restarting the timer after receiving data from the terminal can reduce the efficiency of re-managing the release of computing resources.

[0366] Another possible implementation is to add a certain amount of time to the current remaining duration of the timer.

[0367] It should be noted that the management of computing power resource release can also be carried out through terminal devices or computing power control network elements, and there are no restrictions here.

[0368] Please see Figure 9 , Figure 9 This is a flowchart illustrating another method for managing computing resources provided in an embodiment of this application. The method described in this application can be applied to a terminal. Figure 9 The methods shown may include:

[0369] S901. The terminal establishes a connection with the computing power node, and the computing power node provides computing power resources to the terminal.

[0370] S902, The terminal receives a fourth message, which is used to notify the terminal that computing resources have been released. Computing resources are resources used to execute computing tasks from the terminal. The computing resources are released when no data is received from the terminal within a first time period.

[0371] S901 and S902 can be referenced. Figure 8 The description of the embodiments will not be repeated here.

[0372] In this embodiment of the application, the computing resources are released when no data is received from the terminal within a first time period. This allows the computing resources occupied by the terminal to be released in a timely manner, which is conducive to improving the utilization rate of computing resources.

[0373] In one possible implementation, the fourth message originates from the computing power node, meaning that the terminal can be notified that computing resources have been released via the computing power node. Alternatively, the fourth message originates from the computing power control network element, which manages at least one computing power node, including the computing power node; that is, the terminal can be notified that computing resources have been released via the computing power control network element.

[0374] Please see Figure 10 , Figure 10 This is a flowchart illustrating another method for managing computing resources provided in an embodiment of this application. The method described in this embodiment can be applied to computing power control network elements. For example... Figure 10 The methods shown may include:

[0375] S1001, the computing power control network element receives a second message from the computing power node. The second message is used to request the release of computing power resources, which are resources used to execute computing tasks from the terminal.

[0376] S1002, The computing power control network element sends a third message to the computing power node. The third message is used to instruct the release of computing power resources.

[0377] S1001-S1002 can be referred to Figure 8 The description of the embodiments will not be repeated here.

[0378] In this embodiment of the application, after receiving the second message from the computing node, the computing power control network element can send a third message to the computing node, thereby instructing the computing node to release computing resources. This allows the computing resources to be released to improve the utilization rate of computing resources and facilitates the computing power control network element in managing the computing resources of computing nodes in the network.

[0379] In another possible implementation, the method also includes:

[0380] A fourth message is sent to the terminal to notify the terminal that computing resources have been released.

[0381] In another possible implementation, the method also includes:

[0382] Send the first message to the computing node. The first message is used to indicate the first duration.

[0383] Please see Figure 11 , Figure 11This is a flowchart illustrating another method for managing computing resources provided in an embodiment of this application. The method described in this application can be applied to a terminal. Figure 11 The methods shown may include:

[0384] S1101. The terminal sends a fifth message, which is used to request computing resources. The fifth message carries one or more of the following: the start time of the use of computing resources, the end time of the use of computing resources, or a second duration, where the second duration is the duration of use of computing resources requested by the terminal.

[0385] The fifth message can also be called a computing power request. The time during which computing power resources are used can also be called the start time. The second duration can also be called the computing power resource usage duration 1.

[0386] For example, S1101 can be described with reference to the description of S501, which will not be repeated here.

[0387] Optionally, in the embodiments of this application, the terminal may send the fifth message to the computing power node or to the computing power control network element, and there is no limitation on this.

[0388] It should be noted that the fifth message can carry the start time of the computing resource usage, the end time of the computing resource usage, or the second duration, or it can carry the corresponding identification information for the start time of the computing resource usage, the end time of the computing resource usage, or the second duration. The start time of the computing resource usage, the end time of the computing resource usage, or the second duration can be found through the identification information.

[0389] S1102, The terminal receives the sixth message, which includes a response message to the fifth message.

[0390] The response message of the fifth message can also be called a confirmation message. For example, the response message of the fifth message in S1102 can be referred to the description in S502, and will not be repeated here. That is, the response message of the fifth message can carry computing power node information, the actual allocated computing power resource usage duration 2, and a time threshold. S1102 can be referred to the description in S502, and will not be limited here. In another possible implementation, the confirmation message can also be used to indicate agreement to use computing power resources according to the information in the computing power request, for example, using computing power resources according to the computing power resource usage duration 1.

[0391] Optionally, the terminal may receive a sixth message from a computing power node or from a computing power control network element; no restriction is imposed here.

[0392] It should be noted that the response message of the fifth message can carry computing power node information, actual allocated computing power resource usage time 2 and time threshold, or it can carry the corresponding identification information of computing power node information, actual allocated computing power resource usage time 2 and time threshold. In this case, the computing power node information, actual allocated computing power resource usage time 2 and time threshold can be found through the identification information.

[0393] In this embodiment, the terminal can request the required computing resources and the duration of their usage according to its needs, and can flexibly adjust the computing resources allocated to the terminal and the duration of their usage. Furthermore, the terminal can receive a response message from a fifth message, indicating the actual allocated computing resources and usage duration, etc., which facilitates the management and control of the computing resources of the computing nodes.

[0394] In another possible implementation, the method may also include:

[0395] If the remaining duration is greater than or equal to the third duration, the terminal sends a seventh message. The seventh message is used to request a change in computing power requirements. The third duration is less than or equal to the actual available duration of the computing power resources allocated to the terminal. The remaining duration is the difference between the actual available duration of the computing power resources allocated to the terminal and the duration of computing power resources already occupied by the terminal.

[0396] The third duration can also be called a time threshold. The seventh message can be called a computing power update message. In this embodiment, the computing power requirement may include, but is not limited to, at least one of computing power type, computing power, or computing power resource usage duration. That is, changes to the computing power requirement may include changes to at least one of computing power type, computing power, or computing power resource usage duration. The actual available duration of the computing power resources allocated to the terminal may be the usage duration 2 carried in the confirmation message.

[0397] For example, this embodiment can be described with reference to S505-S511, which will not be repeated here.

[0398] It should be noted that the third duration can be a specific duration carried in the sixth message, or it can be a duration calculated from the sixth message, such as a duration calculated from the start and end times, or a duration shorter than the duration calculated from the start and end times. Optionally, if the third duration is not associated with an explicit start time, its starting point can be calculated from when the terminal device sends the fifth message, or from when the terminal device receives the sixth message. No restrictions are imposed here. It should also be noted that the terminal can send a seventh message to the computing power node or the computing power control network element.

[0399] In this embodiment of the application, by restricting the terminal from requesting changes to computing power requirements within a certain period of time, the terminal device is given time to determine how to change the computing power requirements, so that the requests to change computing power requirements can be accurately allocated.

[0400] In one possible implementation, the seventh message carries one or more of the following: a first computing power type, a first computing power size, a first computation result feedback time, a first end time, or a fourth duration, where the fourth duration is the requested duration for continued use of computing power resources.

[0401] The first computing power type can be the requested computing power type, meaning it can be the type of computing power the terminal expects or hopes to be allocated. The first computing power size can be the requested computing power size, meaning it can be the type of computing power the terminal expects or hopes to be allocated. The first computation result feedback time can be the time the computing power node requests feedback on the computation result, meaning it can be the time the terminal expects or hopes to receive the computation result. Optionally, the computation result feedback time can be the delay between the terminal device sending the data to be computed and receiving the computation result (also called result data). This delay includes at least one of the computation time or the time the data is sent in the network. The first end time can be the time the terminal expects or hopes to end its use of computing power resources.

[0402] For example, the first computing power size can be referred to as computing power demand 2, and the fourth duration can be referred to as computing power resource usage duration 3. The first end time can be referred to as the requested new end time.

[0403] In this embodiment of the application, the terminal can select the computing power requirement it needs to change, which improves the flexibility of changing computing power requirements.

[0404] In another possible implementation, the seventh message may not carry at least one of the following: the first computing power type, the first computing power size, the first computation result feedback time, the first end time, or the fourth duration. In this case, the computing power can be allocated according to the parameters or information carried in the computing power request or confirmation message. Thus, by reducing the parameters or information carried in the seventh message, the transmission resources required to change the computing power requirement can be reduced.

[0405] In one possible implementation, the method for managing computing resources also includes:

[0406] The terminal receives a ninth message, which carries one or more of the following: a second computing power type, a second computing power size, a second calculation result feedback time, a second end time, or a fifth duration, where the fifth duration is the duration of continued use of computing power resources allocated to the terminal.

[0407] The ninth message can also be called a computing power update confirmation message. The ninth message can be considered a response to the seventh message. The response message can also be called a reply message. The second computing power type can be the actually allocated computing power type, that is, the second computing power type can be the same as or different from the first computing power type, without restriction. It should be understood that when the first and second computing power types are different, the computing power type allocated to the terminal should be able to execute the computing task requested by the terminal. The second computing power size can be the actually allocated computing power size. Optionally, the first and second computing power sizes can be the same as or different, without restriction. The second computation result feedback time can be the time when the computing power node actually feeds back the computation result. Optionally, the second computation result feedback time can be the same as or different from the first computation result feedback time. The second end time can be the time when the allocated computing power resources are used up. Optionally, the second end time can be the same as or different from the first end time. Optionally, the fifth duration and the fourth duration can be the same as or different, without restriction.

[0408] For example, this embodiment can refer to the description of S506. The second computing power size can be called computing power demand 3, the fifth duration can be called computing power resource usage duration 4, and the second end time can also be called the actual allocated new end time.

[0409] It should be noted that the terminal can receive the ninth message from the computing power node or the computing power control network element.

[0410] In this embodiment of the application, the parameters requested by the terminal when changing the computing power request may be different from the new parameters actually allocated to the terminal. This is beneficial for changing the computing power requirements of the terminal for the entire network and improving the overall resource utilization of the network.

[0411] In one possible implementation, the sixth message also indicates a third duration, or the third duration is predefined.

[0412] It should be noted that if the sixth message indicates the third duration, then the sixth message can include the third duration, in which case parsing the sixth message can yield the third duration; or the sixth message can include an identifier corresponding to the third duration, in which case parsing the sixth message allows locating the third duration using the identifier corresponding to the third duration. Optionally, the data size of the identifier corresponding to the third duration can be smaller than the data size of the third duration itself.

[0413] In one possible implementation, after the terminal receives the sixth message, the method further includes:

[0414] The terminal starts a timer to determine whether the computing resources allocated to the terminal have expired; if the timer expires, the terminal releases the computing resources allocated to it.

[0415] For example, the embodiments of this application can be referred to the descriptions in S508-S511, which will not be repeated here.

[0416] In one possible implementation, the method may further include:

[0417] The duration of the terminal update timer is the sum of the remaining duration and the fifth duration. The remaining duration is the difference between the actual available duration of the computing resources allocated to the terminal and the duration of the computing resources already occupied by the terminal. The fifth duration is the duration of the computing resources allocated to the terminal for continued use.

[0418] For example, the embodiments of this application can be described with reference to S507, which will not be repeated here.

[0419] In one possible implementation, the method for managing the computing resources may further include:

[0420] The second duration is determined based on the application to which the computing task belongs and the first correspondence. The first correspondence is used to indicate the computing power requirements corresponding to the computing tasks of various applications and each application in the various applications. The computing power requirements include one or more of the following: usage duration, computing power type, computing power size, or computing result feedback time.

[0421] Optionally, the first mapping may include a UE route selection policy (URSP), which includes a mapping between traffic descriptors and route selection descriptors. A traffic descriptor is a data structure that provides a description of traffic characteristics on any given requested connection. It contains a series of attribute information about the application (App) or data flow. Traffic descriptors may include, but are not limited to, application identification (APP ID), data network name (DNN), IP descriptor, domain descriptor, and connection capabilities description. The data network name indicates the data network to which the data traffic should access. The IP descriptor may include the source IP address, destination IP address, and IP protocol type, used to identify a specific IP data flow. The domain descriptor provides the domain name information of the data flow. Connection capabilities descriptions may include quality of service (QoS) requirements, etc.

[0422] The routing descriptor is a data structure containing routing-related parameters that guides or restricts the routing algorithm to select a route path for specific traffic. The routing descriptor includes PDU session type (PDU sessionType), session and service continuity mode (SSC mode), network slice selection assistance information, preferred access type, and computing power requirements. The PDU session type is related to characteristics such as the session's IP version and protocol support. The SSC mode defines the PDU session's lifetime and whether it can be reassigned. Network slice selection assistance information, also known as the slice identifier (S-NSSAI), contains an identifier for the slice or service type, helping the network identify and select appropriate slices to carry specific service traffic. During PDU session establishment, the UE requests a specific S-NSSAI, and the network allocates corresponding slice resources based on this request. The preferred access type refers to the access type the UE prioritizes when attempting to establish or modify a PDU session. This can be determined based on factors such as the UE's current location, network conditions, and user preferences.

[0423] For example, the terminal routing selection strategy can be as shown in Table 1:

[0424] Table 1

[0425]

[0426] It should be understood that the first correspondence can also be indicated in other ways, and no restrictions are imposed here.

[0427] It should be noted that when determining computing power requirements, such as the duration of computing power resource usage, the parameters can be found in Table 1, and are not limited to those used in the embodiments of this application. For example, the first duration can also be found in Table 1.

[0428] In one possible implementation, the method for managing this computing resource also includes:

[0429] If the terminal has more than 0 remaining available time for computing resources and the computing task has stopped, a tenth message is sent to request the release of computing resources.

[0430] Optionally, the terminal may send a tenth message to the computing power node or the computing power control network element. For example, the tenth message may also be called a computing power resource release message.

[0431] In this embodiment of the application, although the usage time of computing resources has not yet been reached, the computing task stops. In this way, the computing resources can be released by sending the tenth message, which is beneficial to improving the utilization rate of computing resources.

[0432] Another possible implementation is to release computing resources only after the usage period has elapsed, thus reducing the inefficiency caused by the need to reallocate computing resources when the terminal device restarts the computing task before the usage period expires.

[0433] In one possible implementation, when the remaining available time of the terminal's computing resources is greater than 0 and the computing task stops, a tenth message is sent, including:

[0434] If the computing task stops before the timer expires, a tenth message is sent. The timer is used to determine whether the computing resources allocated to the terminal have expired.

[0435] In this embodiment of the application, a timer can be used to determine whether the time for releasing computing resources has been reached, which is beneficial for timely release of computing resources.

[0436] Please see Figure 12 , Figure 12 This is a flowchart illustrating another method for managing computing resources provided in an embodiment of this application. The method described in this embodiment can be applied to computing power control network elements. For example... Figure 12 The methods shown may include:

[0437] S1201, the computing power control network element receives a fifth message from the terminal. The fifth message is used to request computing power resources. The fifth message carries one or more of the following: the start time of the use of computing power resources, the end time of the use of computing power resources, or a second duration, where the second duration is the duration of use of computing power resources requested by the terminal.

[0438] S1202, The computing power control network element sends a sixth message to the terminal, which includes a response message to the fifth message.

[0439] Among them, S1201 and S1202 can be in accordance with Figure 11 The description of the embodiments is omitted here.

[0440] In another possible implementation, S1202 may not be required, in which case computing resources will be allocated according to the information or parameters in the fifth message by default.

[0441] In one possible implementation, the computing power control network element receives a seventh message, which is used to request a change in computing power requirements.

[0442] Optionally, the computing power requirements of the terminal can be changed in response to the seventh message. Optionally, the computing power requirements can be reallocated to the terminal again according to the computing power requirements requested when establishing the link between the terminal and the computing power node.

[0443] In another possible implementation, the seventh message carries one or more of the following: a first computing power type, a first computing power size, a first computation result feedback time, a first end time, or a fourth duration, where the fourth duration is the requested duration for continued use of computing power resources.

[0444] Among them, the seventh message and the fifth message may have some messages or parameters that are the same, such as the fourth duration being the same as the second duration, or the first end time being the same as the end time when the computing resources are used. They may also be completely different, depending on the actual situation, and there is no restriction here.

[0445] In one possible implementation, the computing power control network element sends a ninth message to the terminal, which carries one or more of the following: a second computing power type, a second computing power size, a second calculation result feedback time, a second end time, or a fifth duration, where the fifth duration is the duration of continued use of computing power resources allocated to the terminal.

[0446] The embodiments of this application can be referred to Figure 11 The description of the embodiments is omitted here.

[0447] In one possible implementation, the sixth message also indicates a third duration, which is less than or equal to the actual available duration of the computing resources allocated to the terminal.

[0448] The embodiments of this application can be referred to Figure 11 The description of the embodiments is omitted here.

[0449] In one possible implementation, the method for managing computing resources also includes:

[0450] Receive the tenth message from the terminal. The tenth message is used to request the release of computing resources.

[0451] For example, the tenth message can also be called a computing resource release message. This embodiment can be referred to in the description of S509, which will not be repeated here.

[0452] In one possible implementation, the method for managing computing resources also includes:

[0453] When the remaining time is 0 and no seventh message has been received from the terminal, the computing power control network element sends an eighth message. The eighth message is used to indicate the release of computing power resources. The remaining time is the difference between the actual available time of the computing power resources allocated to the terminal and the time that the terminal has occupied the computing power resources.

[0454] In this embodiment, if no seventh message is received from the terminal when the remaining time is 0 (in other words, if the timer expires, which can also be understood as reaching the time to release computing resources), it indicates that the terminal does not need to change its computing power requirements, such as not needing to extend the usage time of computing resources. Therefore, an eighth message can be sent to indicate the release of computing resources. Optionally, the computing power control network element can send an eighth message to the computing power node or the terminal to trigger the release of computing resources.

[0455] For example, the description of the eighth message can be referred to that of the tenth message, and will not be repeated here.

[0456] In this embodiment of the application, if the remaining time is 0 and no seventh message is received from the terminal, an eighth message is sent, thereby releasing computing resources immediately.

[0457] Optionally, if a seventh message is received from the terminal before the timer expires, and if the seventh message indicates an extension of the computing resource usage time, the timer duration can be updated, allowing the terminal to use computing resources for a longer period of time.

[0458] It should be noted that, in the embodiments of this application, the notification, notification or instruction can be implemented through messages, data or data packets. That is to say, notification, notification or instruction can be carried out through messages, data or data packets.

[0459] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation portals are provided for users to choose to authorize or refuse.

[0460] It should also be understood that the steps of the various embodiments described above can be coupled to each other, and this application does not limit this. Furthermore, the sequence number of each process 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.

[0461] The above embodiments describe a method for managing computing resources. The following describes an example of a product related to the method.

[0462] Figure 13 A schematic diagram of a communication device provided in an embodiment of this application is shown. The communication device in this embodiment may include a first module 1301 and a second module 1302.

[0463] In one possible implementation, the communication device is used to implement the steps and processes corresponding to the terminal. For example, the first module 1301 is used to establish a link with a computing node, which provides computing resources to the terminal; the second module 1302 is used to receive a fourth message, which notifies the terminal that computing resources have been released. Computing resources are resources used to execute computing tasks from the terminal, and are released after no data has been received from the terminal within a first duration. As another example, the first module 1301 is used to send a fifth message, which requests computing resources. The fifth message carries one or more of the following: the start time of computing resource usage, the end time of computing resource usage, or a second duration, where the second duration is the duration of computing resource usage requested by the terminal; the second module 1302 is used to receive a sixth message, which includes a response message to the fifth message.

[0464] In another possible implementation, the communication device is used to implement the steps and processes corresponding to the computing power node. For example, the first module 1301 is used to establish a link with the terminal; the second module 1302 is used to release computing power resources, which are resources used to execute computing tasks from the terminal, if no data is received from the terminal within a first time period.

[0465] In another possible implementation, the communication device is used to implement the steps and processes corresponding to the computing power control network element. For example, the first module 1301 is used to receive a second message from the computing power node, the second message requesting the release of computing power resources, which are resources used to execute computing tasks from the terminal; the second module 1302 is used to send a third message to the computing power node, the third message indicating the release of computing power resources. Also for example, the first module 1301 is used to receive a fifth message from the terminal, the fifth message requesting computing power resources, the fifth message carrying one or more of the following: the start time of computing power resource usage, the end time of computing power resource usage, or a second duration, the second duration being the duration of computing power resource usage requested by the terminal; the second module 1302 is used to send a sixth message to the terminal, the sixth message including a response message to the fifth message.

[0466] It should be noted that, in this embodiment of the application, the terminal can also indicate the time when it does not need to use computing resources.

[0467] It should be understood that the methods executed by the communication module in the embodiments of this application can refer to the description of the steps of the methods executed by the terminal, computing node or computing control network element in the above embodiments, and will not be repeated here.

[0468] It should be understood that the device 1300 here is embodied in the form of a functional module. The term "module" here may refer to application-specific integrated circuits (ASICs), electronic circuits, processors (e.g., shared processors, proprietary processors, or group processors) and memories for executing one or more software or firmware programs, combined logic circuits, and / or other suitable components that support the described functions.

[0469] In the embodiments of this application, the communication device may also be a chip or a chip system, such as a system on chip (SoC).

[0470] Figure 14 A schematic diagram of another communication device is shown. This communication device includes a processor 1401, a transceiver 1402, and a memory 1403. The processor 1401, transceiver 1402, and memory 1403 communicate with each other via internal interconnection. The memory 1403 stores instructions, and the processor 1401 executes the instructions stored in the memory 1403 to control the transceiver 1402 to transmit and / or receive signals.

[0471] It should be understood that the communication device may specifically be a terminal, computing node, or computing control network element as described in the above embodiments, and may be used to execute the various steps and / or processes corresponding to the terminal, computing node, or computing control network element in the above method embodiments. Optionally, the memory 1403 may include read-only memory and random access memory, and provide instructions and data to the processor. A portion of the memory may also include non-volatile random access memory. For example, the memory may also store device type information. The processor 1401 may be used to execute instructions stored in the memory, and when the processor 1401 executes instructions stored in the memory, the processor 1401 is used to execute the various steps and / or processes of the above method embodiments. The transceiver 1402 may include a transmitter and a receiver. The transmitter may be used to implement the various steps and / or processes corresponding to the transceiver for performing a transmitting action, and the receiver may be used to implement the various steps and / or processes corresponding to the transceiver for performing a receiving action.

[0472] It should be understood that, in the embodiments of this application, the processor may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (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.

[0473] In implementation, each step of the above method can be completed by integrated logic circuits in the processor's hardware or by instructions in software. The steps of the method disclosed in the embodiments of this application can be directly manifested as execution by a hardware processor, or as a combination of hardware and software modules within the processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory, and the processor executes the instructions in the memory, combining them with its hardware to complete the steps of the above method. To avoid repetition, detailed descriptions are omitted here.

[0474] This application also provides a communication system, including a terminal, and may further include at least one of a computing power node or a computing power control network element. The methods executed by the terminal, computing power node, and computing power control network element can be referred to the description in the above embodiments, and will not be repeated here.

[0475] This application also provides a computer-readable storage medium for storing a computer program that implements the methods shown in the above-described method embodiments.

[0476] This application also provides a computer program product, which includes a computer program (also referred to as code or instructions). When the computer program is run on a computer, the computer can execute the methods shown in the above-described method embodiments.

[0477] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0478] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0479] In the 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.

[0480] 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 the embodiments of this application, depending on actual needs.

[0481] 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.

[0482] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

Claims

1. A method for managing computing power resources, characterized in that, The method comprises: establishing a link with a terminal; releasing a computing resource for performing a computing task from the terminal in a case that no data from the terminal is received within a first time duration.

2. The method of claim 1, wherein, The method further comprises: receiving a first message from a computing resource control network element, the first message being used to indicate the first time duration, the computing resource control network element being used to manage at least one computing resource node.

3. The method of claim 1, wherein, The first time duration is predefined.

4. The method of any one of claims 1 to 3, wherein, The releasing the computing resource for performing a computing task from the terminal in a case that no data from the terminal is received within a first time duration comprises: releasing the computing resource and the link in a case that no data from the terminal is received within the first time duration.

5. The method of any one of claims 1 to 4, wherein, The releasing the computing resource for performing a computing task from the terminal in a case that no data from the terminal is received within a first time duration comprises: sending a second message to a computing resource control network element in a case that no data from the terminal is received within the first time duration, the second message being used to request releasing the computing resource; releasing the computing resource in a case that a third message from the computing resource control network element is received, the third message being used to indicate releasing the computing resource.

6. The method of any one of claims 1 to 5, wherein, The method further comprises: sending a fourth message to the terminal, the fourth message being used to inform the terminal that the computing resource has been released.

7. The method of any one of claims 1 to 6, wherein, The method further comprises: starting a timer, the timer corresponding to the first time duration; The releasing the computing resource for performing a computing task from the terminal in a case that no data from the terminal is received within a first time duration comprises: releasing the computing resource in a case that no data from the terminal is received within the first time duration.

8. The method of claim 7, wherein, The method further comprises: receiving data from the terminal before the timer expires, and restarting the timer. 9.A method for managing computing resource, characterized in that, The method comprises: establishing a link with a computing resource node, the computing resource node providing a computing resource for a terminal; receiving a fourth message, the fourth message being used to inform the terminal that the computing resource has been released, the computing resource being used to perform a computing task from the terminal, the computing resource being released in a case that no data from the terminal is received within a first time duration.

10. The method of claim 9, wherein, The fourth message is from the computing resource node; or, the fourth message is from a computing resource control network element, the computing resource control network element being used to manage at least one computing resource node including the computing resource node.

11. A management method of a computing resource, characterized by, The method comprises: receiving a second message from a computing resource node, the second message being used to request releasing a computing resource, the computing resource being used to perform a computing task from a terminal; sending a third message to the computing resource node, the third message being used to indicate releasing the computing resource.

12. The method of claim 11, wherein, The method further comprises: sending a fourth message to the terminal, the fourth message being used to inform the terminal that the computing resource has been released.

13. The method according to claim 11 or 12, characterized in that, The method further comprises: sending a first message to the computing resource node, the first message being used to indicate a first time duration. 14.A method for managing computing resource, characterized in that, The method comprises: sending a fifth message, the fifth message being used for requesting a computing resource, the fifth message carrying one or more of a start time at which the computing resource is used, an end time at which the computing resource is used, or a second time length, the second time length being a time length of use of the computing resource requested by the terminal; receiving a sixth message, the sixth message including a response message of the fifth message.

15. The method of claim 14, wherein, The method further includes: in a case where a remaining time length is greater than or equal to a third time length, sending a seventh message, the third time length being less than or equal to an actual available time length of the computing resource allocated to the terminal, the remaining time length being a difference between the actual available time length of the computing resource allocated to the terminal and a time length of the computing resource occupied by the terminal.

16. The method of claim 15, wherein, The seventh message carries one or more of a first computing type, a first computing size, a first computing result feedback time, a first end time, or a fourth time length, the fourth time length being a time length of continued use of the computing resource requested.

17. The method of claim 15 or 16, wherein, The method further includes: receiving a ninth message, the ninth message carrying one or more of a second computing type, a second computing size, a second computing result feedback time, a second end time, or a fifth time length, the fifth time length being a time length of continued use of the computing resource allocated to the terminal.

18. The method of any one of claims 15 to 17, wherein, The sixth message further indicates the third time length, or the third time length is predefined.

19. The method of any one of claims 14 to 18, wherein, After the receiving of the sixth message, the method further includes: starting a timer, the timer being used for judging whether the computing resource allocated to the terminal is timed out; in a case where the timer is timed out, releasing the computing resource allocated to the terminal.

20. The method of claim 19, wherein, The method further includes: updating a time length of the timer to be a sum of a remaining time length and a fifth time length, the remaining time length being a difference between an actual available time length of the computing resource allocated to the terminal and a time length of the computing resource occupied by the terminal, the fifth time length being a time length of continued use of the computing resource allocated to the terminal.

21. The method of any one of claims 14 to 20, wherein, The method further includes: determining the second time length according to an application program to which a computing task belongs and a first correspondence relationship, the first correspondence relationship being used for indicating a plurality of application programs and a computing task corresponding to a computing resource demand of each of the plurality of application programs, the computing resource demand including one or more of a time length of use, a computing type, a computing size, or a computing result feedback time.

22. The method of any one of claims 14 to 21, wherein, The method further includes: in a case where a remaining available time length of the computing resource to the terminal is greater than 0 and a computing task is stopped, sending a tenth message, the tenth message being used for requesting to release the computing resource.

23. The method of claim 22, wherein, The sending of the tenth message in the case where the remaining available time length of the computing resource to the terminal is greater than 0 and the computing task is stopped includes: sending the tenth message in a case where a timer is timed out before and the computing task is stopped, the timer being used for judging whether the computing resource allocated to the terminal is timed out. 24.A method for managing computing resource, characterized in that, includes: receiving a fifth message from the terminal, the fifth message being used for requesting a computing resource, the fifth message carrying one or more of a start time of usage of the computing resource, an end time of usage of the computing resource, or a second time length, the second time length being a time length of usage of the computing resource requested by the terminal; sending a sixth message to the terminal, the sixth message including a response message of the fifth message.

25. The method of claim 24, wherein, The method further includes: receiving a seventh message, the seventh message being used for requesting a change of a computing requirement.

26. The method of claim 25, wherein, The seventh message carries one or more of a first computing type, a first computing size, a first computing result feedback time, a first end time, or a fourth time length, the fourth time length being a time length of continuous usage of the computing resource requested.

27. The method of claim 25 or 26, wherein, The method further includes: sending a ninth message to the terminal, the ninth message carrying one or more of a second computing type, a second computing size, a second computing result feedback time, a second end time, or a fifth time length, the fifth time length being a time length of continuous usage of the computing resource allocated to the terminal.

28. The method of any one of claims 24 to 27, wherein, The sixth message further indicates a third time length, the third time length being less than or equal to an actual available time length of the computing resource allocated to the terminal.

29. The method of any one of claims 24 to 28, wherein, The method further includes: receiving a tenth message from the terminal, the tenth message being used for requesting release of the computing resource.

30. The method of any one of claims 24 to 29, wherein, The method further includes: in a case where a remaining time length is 0 and a seventh message from the terminal is not received, sending an eighth message, the eighth message being used for indicating release of the computing resource, the remaining time length being a difference between an actual available time length of the computing resource allocated to the terminal and a time length of occupation of the computing resource by the terminal.

31. A communications device, characterized by A module for implementing the method of any one of claims 1 to 30 is included.

32. A communications device, characterized by A processor and a memory are included, wherein The memory is used to store a computer program; The processor is used to invoke the computer program, so that the apparatus implements the method of any one of claims 1 to 30.

33. A computer-readable storage medium, comprising: The storage medium has a computer program or instructions stored therein, and when the computer program or instructions are executed by a computer, the method of any one of claims 1 to 30 is implemented.

34. A computer program product, characterised in that, The computer program product includes instructions, and when the instructions are executed by a computer, the method of any one of claims 1 to 30 is implemented.

Images