Computing power multiplexing method, device and architecture

Abstract

The invention discloses a computing power reuse method, device and architecture. The method comprises the following steps: determining application computing power of terminal equipment according to a computing power application from the terminal equipment; idle computing power information is continuously updated, if the application computing power is smaller than or equal to local idle computing power, computing power is distributed from the local idle computing power to execute a computing power task in the computing power application, and the terminal equipment task is ended after the computing power task is completed; and continuously updating idle computing power information, and if the application computing power is greater than the local idle computing power, selecting a corresponding mode to end the task of the terminal equipment according to the priority and task real-time requirements of the terminal equipment. According to the invention, software and hardware decoupling is realized, the resource utilization rate is improved, cooperative work of a plurality of devices with different generations and different standards is realized, and great convenience is provided for reducing the operation and maintenance cost.

Description

Technical Field

[0001] The present invention relates to the field of Internet of Things technology, and in particular to a computing power reuse method, device and architecture. Background Art

[0002] With the rapid development of intelligent devices, especially the rapid popularization of generative artificial intelligence, the demand for computing power of devices is growing exponentially. The growth of the demand for computing power of devices far exceeds the development level of the devices themselves. Therefore, in our life scenarios, on the one hand, there is a lot of idle computing power that is not fully utilized, and on the other hand, for specific applications, the computing power is insufficient. The phenomenon of computing power fragmentation is also becoming more and more serious. In this way, computing power waste and insufficient computing power appear simultaneously in production and life practices. Summary of the invention

[0003] The embodiments of the present invention provide a computing power multiplexing method, device and architecture, which provide the computing power required by each terminal device through a central computing power device, improve the computing power utilization efficiency and the stability of computing power supply, reduce computing power waste and reduce energy consumption.

[0004] To achieve the above-mentioned purpose, a first aspect of an embodiment of the present application provides a computing power reuse method, including:

[0005] Determining the requested computing power of the terminal device according to the computing power request from the terminal device;

[0006] Continuously update the idle computing power information. If the applied computing power is less than or equal to the local idle computing power, allocate computing power from the local idle computing power to execute the computing power task in the computing power application. After the computing power task is completed, end the terminal device task;

[0007] Continuously update the idle computing power information. If the applied computing power is greater than the local idle computing power, select a corresponding method to end the terminal device task according to the priority of the terminal device and the real-time requirements of the task.

[0008] In a possible implementation manner of the first aspect, the continuously updating the idle computing power information, if the applied computing power is greater than the idle computing power, selecting a corresponding method to end the terminal device task according to the priority of the terminal device and the real-time requirement of the task, specifically includes:

[0009] Continuously update the idle computing power information. If the requested computing power is greater than the idle computing power, and the priority of the terminal device is higher than the priority of other terminal devices that are executing computing power tasks, reallocate the local computing power to execute the computing power tasks in the computing power application;

[0010] If the requested computing power is greater than the idle computing power, and the priority of the terminal device is lower than the priority of other terminal devices that are executing computing power tasks, a corresponding method is selected to end the terminal device task according to the real-time requirements of the terminal device's task.

[0011] In a possible implementation manner of the first aspect, if the applied computing power is greater than the idle computing power, and the priority of the terminal device is lower than the priority of other terminal devices that are executing computing power tasks, selecting a corresponding method to end the terminal device task according to the real-time requirement of the task of the terminal device, specifically includes:

[0012] If the requested computing power is greater than the idle computing power, and the priority of the terminal device is lower than the priority of other terminal devices that are executing computing power tasks, continuously obtain the real-time task requirements of the terminal device;

[0013] If the task of the terminal device requires waiting in real time, the idle computing power information is updated again, and the relationship between the applied computing power and the idle computing power is determined, and then a corresponding method is selected to end the task of the terminal device;

[0014] If the task of the terminal device requires real-time termination without waiting, the task of the terminal device is terminated directly;

[0015] If the task of the terminal device requires real-time submission without waiting and without needing to be terminated, apply for idle network computing power to execute the computing power task in the computing power application, and terminate the terminal device task after the computing power task is completed.

[0016] In a possible implementation manner of the first aspect, applying for idle network computing power to execute the computing power task in the computing power application specifically includes:

[0017] Apply for idle network computing power from other central computing power devices to execute the computing power tasks in the computing power application; perform load balancing among the central computing power devices.

[0018] A second aspect of an embodiment of the present application provides a computing power multiplexing device, including:

[0019] A computing power confirmation module, used to determine the requested computing power of the terminal device according to the computing power application from the terminal device;

[0020] A first computing power allocation module is used to continuously update the idle computing power information. If the applied computing power is less than or equal to the local idle computing power, computing power is allocated from the local idle computing power to execute the computing power task in the computing power application. After the computing power task is completed, the terminal device task is terminated;

[0021] The second computing power allocation module is used to continuously update the idle computing power information. If the applied computing power is greater than the local idle computing power, a corresponding method is selected to end the terminal device task according to the priority of the terminal device and the real-time requirements of the task.

[0022] In a possible implementation manner of the second aspect, the continuously updating the idle computing power information, if the applied computing power is greater than the idle computing power, selecting a corresponding method to end the terminal device task according to the priority of the terminal device and the real-time requirement of the task, specifically includes:

[0023] Continuously update the idle computing power information. If the requested computing power is greater than the idle computing power, and the priority of the terminal device is higher than the priority of other terminal devices that are executing computing power tasks, reallocate the local computing power to execute the computing power tasks in the computing power application;

[0024] If the requested computing power is greater than the idle computing power, and the priority of the terminal device is lower than the priority of other terminal devices that are executing computing power tasks, a corresponding method is selected to end the terminal device task according to the real-time requirements of the terminal device's task.

[0025] In a possible implementation manner of the second aspect, if the applied computing power is greater than the idle computing power, and the priority of the terminal device is lower than the priority of other terminal devices that are executing computing power tasks, selecting a corresponding method to end the terminal device task according to the real-time requirement of the task of the terminal device, specifically including:

[0026] If the requested computing power is greater than the idle computing power, and the priority of the terminal device is lower than the priority of other terminal devices that are executing computing power tasks, continuously obtain the real-time task requirements of the terminal device;

[0027] If the task of the terminal device requires waiting in real time, the idle computing power information is updated again, and the relationship between the applied computing power and the idle computing power is determined, and then a corresponding method is selected to end the task of the terminal device;

[0028] If the task of the terminal device requires real-time termination without waiting, the task of the terminal device is terminated directly;

[0029] If the task of the terminal device requires real-time processing and does not need to be completed, the idle computing power of the network is applied for to execute the computing power task in the computing power application, and the task of the terminal device is terminated after the computing power task is completed.

[0030] In a possible implementation manner of the second aspect, applying for idle network computing power to execute the computing power task in the computing power application specifically includes:

[0031] Apply for idle network computing power from other central computing power devices to execute the computing power tasks in the computing power application; perform load balancing among the central computing power devices.

[0032] The third aspect of an embodiment of the present application provides a computing power architecture, including multiple central computing power devices and multiple terminal device networks, each central computing power device provides computing power for all terminal devices in a terminal device network, and each terminal device is communicatively connected to the corresponding central computing power device; each central computing power device is communicatively connected to each other and executes the computing power multiplexing method as described above.

[0033] Compared with the prior art, the embodiments of the present invention provide a computing power reuse method, device and architecture, which is a centralized computing power management method uniformly scheduled by a central computing power device. The computing power comes from a central computing power controller or network computing power scheduled by a central computing power controller, such as a central computing power device in the cloud or a neighbor's home. When the terminal device is connected to the network and running, the central computing power device can also coordinate computing power from the regional network or the cloud to meet the needs of specific users. When a specific central computing power device fails or needs maintenance, the central computing power device can also use the task migration method to continue user services.

[0034] In summary, the embodiments of the present invention use dynamic scheduling and computing power reuse, so that for specific terminal devices, the computing power that can be used far exceeds that of traditional solutions, so that more complex algorithms can be deployed. At the same time, the utilization rate of computing resources is improved and resource waste is reduced; high-priority tasks can quickly obtain the required resources, shorten processing time, and improve user experience; the load balancing mechanism avoids single-point overload and enhances the overall stability and reliability of the architecture; and supports cross-network computing resource sharing, so that the architecture can better cope with sudden high-load situations while maintaining good performance. The computing power reuse method provides a flexible, efficient, and fair computing resource management strategy that is suitable for complex and changing application scenarios and helps to build a more intelligent, efficient, and sustainable computing environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is a flowchart of a computing power reuse method provided by an embodiment of the present invention;

[0036] Figure 2 It is a schematic diagram of a device for providing a regional computing power reuse structure according to an embodiment of the present invention;

[0037] Figure 3 A flowchart of computing power allocation is provided according to an embodiment of the present invention. DETAILED DESCRIPTION

[0038] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0039] See also Figure 1 An embodiment of the present invention provides a computing power reuse method, including:

[0040] S10. Determine the requested computing power of the terminal device according to the computing power request from the terminal device.

[0041] S11. Continuously update the idle computing power information. If the applied computing power is less than or equal to the local idle computing power, allocate computing power from the local idle computing power to execute the computing power task in the computing power application. After the computing power task is completed, end the terminal device task.

[0042] S12. Continuously update the idle computing power information. If the applied computing power is greater than the local idle computing power, select a corresponding method to end the terminal device task according to the priority of the terminal device and the real-time requirements of the task.

[0043] The method embodiment is applied to a central computing device. In S10, the computing power application is determined: when the terminal device initiates a computing power application, the system first evaluates and determines the computing power scale required by the terminal device. This step is the basis for resource allocation and ensures the accuracy and effectiveness of subsequent resource allocation.

[0044] In S11, the local idle computing power allocation: the central computing power device continuously monitors the local idle computing power information. If the computing power requested by the terminal device is less than or equal to the current local idle computing power, the resource allocation stage is entered. The central computing power device allocates the corresponding computing power resources from the local idle computing power to execute the computing power tasks proposed by the terminal device. This step reflects the immediate response and efficient use of resources. Once the computing power task is completed, the system immediately ends the task of the terminal device and releases the allocated computing power resources for use by other terminal devices. This is a key link in resource recycling and ensures the continuous availability of computing power resources.

[0045] S12 is the processing flow when the local computing power is exceeded: when the computing power requested by the terminal device exceeds the local idle computing power, the central computing power device needs to further evaluate the priority of the terminal device and the real-time requirements of the task. According to the priority of the terminal device and the real-time nature of the task, the system decides to take different countermeasures. For example, for high-priority or urgent tasks, the system may need to reallocate resources or even suspend lower-priority tasks to meet the needs of high-priority tasks. If the needs of high-priority tasks cannot be met locally, the central computing power device can try to call computing power from other resource pools in the network, or when resources are extremely tight, it may have to reject requests for certain low-priority tasks to maintain the overall stability of the system and service quality.

[0046] The core of this embodiment is to dynamically and intelligently manage computing resources to ensure that when resources are limited, the needs of key tasks can be met first, while maximizing resource utilization and response speed. By continuously monitoring and flexibly adjusting resource allocation strategies, the system can effectively cope with changing workloads and achieve maximum utilization and optimal allocation of computing resources.

[0047] In addition, in this embodiment, the terminal device and the central computing device are connected via broadband communication. This broadband connection can be a wired connection or a wireless connection. This can effectively reduce the overall computing power requirements. For specific devices, the computing power that can be used far exceeds the traditional solution. As a result, more complex algorithms can be deployed. A better user experience can be achieved. In this way, the user experience can be improved at the same time, and multiple goals such as reducing the total computing power requirements and reducing energy consumption can be optimized.

[0048] Compared with the prior art, the embodiment of the present invention provides a computing power reuse method, a computing power centralized management method uniformly scheduled by a central computing power device, and the computing power comes from a central computing power controller or a network computing power scheduled by a central computing power controller, such as a central computing power device in the cloud or a neighbor's home. When the terminal device is connected to the network and running, the central computing power device can also coordinate computing power from the regional network or the cloud to meet the needs of specific users. When a specific central computing power device fails or needs maintenance, the central computing power device can also use the task migration method to continue user services.

[0049] In summary, the embodiments of the present invention use dynamic scheduling and computing power reuse, so that for specific terminal devices, the computing power that can be used far exceeds that of traditional solutions, so that more complex algorithms can be deployed. At the same time, the utilization rate of computing resources is improved and resource waste is reduced; high-priority tasks can quickly obtain the required resources, shorten processing time, and improve user experience; the load balancing mechanism avoids single-point overload and enhances the overall stability and reliability of the architecture; and supports cross-network computing resource sharing, so that the architecture can better cope with sudden high-load situations while maintaining good performance. The computing power reuse method provides a flexible, efficient, and fair computing resource management strategy that is suitable for complex and changing application scenarios and helps to build a more intelligent, efficient, and sustainable computing environment.

[0050] Exemplarily, the continuously updating the idle computing power information, if the applied computing power is greater than the idle computing power, selecting a corresponding method to end the terminal device task according to the priority of the terminal device and the real-time requirement of the task, specifically includes:

[0051] Continuously update the idle computing power information. If the requested computing power is greater than the idle computing power, and the priority of the terminal device is higher than the priority of other terminal devices that are executing computing power tasks, reallocate the local computing power to execute the computing power tasks in the computing power application;

[0052] If the requested computing power is greater than the idle computing power, and the priority of the terminal device is lower than the priority of other terminal devices that are executing computing power tasks, a corresponding method is selected to end the terminal device task according to the real-time requirements of the terminal device's task.

[0053] It should be noted that the priorities of different terminal devices for calling computing power are not the same. There is more than one priority judgment standard. Some judgment standards can be modified by users, and some cannot be modified by users. For example, anti-theft terminal devices usually have the highest priority for calling computing power, and its priority cannot be modified by users. When it needs to use computing power, if there is a problem of computing power demand conflict, it has the highest priority. Washing machines and sweeping robots have lower priorities and their priorities can be modified by users. For example, users can choose to wash clothes when electricity prices are low. Sweep the floor when no one is at home. It can also be modified to wash and sweep the floor at any time.

[0054] exist Figure 2 There are electronic door locks: electronic door locks can only open the door after completing character recognition; smart lighting systems can provide lighting according to environmental conditions and application scenarios; smart display terminals can be used to complete the functions of televisions, computer terminals, etc.; electronic curtains; refrigerators; sweeping robots; washing machines; are central computing devices that can be connected to the Internet or run independently.

[0055] Among the above terminal devices, their real-time requirements (immediacy requirements) for service tasks are not the same, and their demand for computing power is also different. For example, washing machines, sweeping robots and other devices have a good tolerance for service delays. In this way, users can make reservations for laundry or sweeping services in the system in advance, and the system can choose to sweep or wash when the energy is cheapest or the system is most idle. When performing laundry or sweeping services, the computing power of the sweeping robot or washing machine is provided by the central server. This is different from the traditional structure in which the washing machine or sweeping robot uses its own computing power to control the service process. The washing machine or sweeping robot is only the executor of the specific action, and the decision-making part is completely implemented by the central server. The calculation results are sent to the actuator, such as the washing machine or sweeping robot, through broadband communication. For services such as lighting control and unlocking, the real-time requirements are very high, but the demand for computing power is very low. It can interrupt other ongoing work and give priority to it. In this way, the server can determine different service priorities and times based on different constraints, such as the lowest cost. Refer to the computing power allocation process Figure 3 When multiple services are running at the same time and the computing power is insufficient, you can use nearby computing servers by migrating tasks.

[0056] In this way, it is possible to achieve simultaneous optimization of multiple objectives such as optimal cost, minimum overall computing power requirements, best user experience and minimum energy consumption.

[0057] Exemplarily, if the applied computing power is greater than the idle computing power, and the priority of the terminal device is lower than the priority of other terminal devices that are executing computing power tasks, a corresponding method is selected to end the terminal device task according to the real-time requirements of the task of the terminal device, specifically including:

[0058] If the requested computing power is greater than the idle computing power, and the priority of the terminal device is lower than the priority of other terminal devices that are executing computing power tasks, continuously obtain the real-time task requirements of the terminal device;

[0059] If the task of the terminal device requires waiting in real time, the idle computing power information is updated again, and the relationship between the applied computing power and the idle computing power is determined, and then a corresponding method is selected to end the task of the terminal device;

[0060] If the task of the terminal device requires real-time termination without waiting, the task of the terminal device is terminated directly;

[0061] If the task of the terminal device requires real-time submission without waiting and without needing to be terminated, apply for idle network computing power to execute the computing power task in the computing power application, and terminate the terminal device task after the computing power task is completed.

[0062] Exemplarily, the application for idle network computing power to execute the computing power task in the computing power application specifically includes:

[0063] Apply for idle network computing power from other central computing power devices to execute the computing power tasks in the computing power application; perform load balancing among the central computing power devices.

[0064] When used in a network, multiple central computing devices can be load balanced. For balancing methods, refer to Figure 3 When the computing power of a certain central computing device in the system is insufficient, it can distribute part of its computing power tasks to other computing devices with idle capacity on the network. In this way, flexible balance of computing power is achieved. At the same time, further optimization can be carried out, for example, computing tasks can be distributed to computing servers with relatively low computing costs or powered by new energy.

[0065] Compared with the prior art, the embodiments of the present invention provide a computing power reuse method, device and architecture, which is a centralized computing power management method uniformly scheduled by a central computing power device. The computing power comes from a central computing power controller or network computing power scheduled by a central computing power controller, such as a central computing power device in the cloud or a neighbor's home. When the terminal device is connected to the network and running, the central computing power device can also coordinate computing power from the regional network or the cloud to meet the needs of specific users. When a specific central computing power device fails or needs maintenance, the central computing power device can also use the task migration method to continue user services.

[0066] In summary, the embodiments of the present invention use dynamic scheduling and computing power reuse, so that for specific terminal devices, the computing power that can be used far exceeds that of traditional solutions, so that more complex algorithms can be deployed. At the same time, the utilization rate of computing resources is improved and resource waste is reduced; high-priority tasks can quickly obtain the required resources, shorten processing time, and improve user experience; the load balancing mechanism avoids single-point overload and enhances the overall stability and reliability of the architecture; and supports cross-network computing resource sharing, so that the architecture can better cope with sudden high-load situations while maintaining good performance. The computing power reuse method provides a flexible, efficient, and fair computing resource management strategy that is suitable for complex and changing application scenarios and helps to build a more intelligent, efficient, and sustainable computing environment.

[0067] A computing power multiplexing device according to an embodiment of the present application includes: a computing power confirmation module, a first computing power allocation module, and a second computing power allocation module.

[0068] The computing power confirmation module is used to determine the requested computing power of the terminal device according to the computing power application from the terminal device.

[0069] The first computing power allocation module is used to continuously update the idle computing power information. If the applied computing power is less than or equal to the local idle computing power, computing power is allocated from the local idle computing power to execute the computing power task in the computing power application. After the computing power task is completed, the terminal device task is terminated.

[0070] The second computing power allocation module is used to continuously update the idle computing power information. If the applied computing power is greater than the local idle computing power, a corresponding method is selected to end the terminal device task according to the priority of the terminal device and the real-time requirements of the task.

[0071] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system described above can refer to the corresponding process in the aforementioned method embodiment and will not be described again here.

[0072] Exemplarily, the continuously updating the idle computing power information, if the applied computing power is greater than the idle computing power, selecting a corresponding method to end the terminal device task according to the priority of the terminal device and the real-time requirement of the task, specifically includes:

[0073] Continuously update the idle computing power information. If the requested computing power is greater than the idle computing power, and the priority of the terminal device is higher than the priority of other terminal devices that are executing computing power tasks, reallocate the local computing power to execute the computing power tasks in the computing power application;

[0074] If the requested computing power is greater than the idle computing power, and the priority of the terminal device is lower than the priority of other terminal devices that are executing computing power tasks, a corresponding method is selected to end the terminal device task according to the real-time requirements of the terminal device's task.

[0075] Exemplarily, if the applied computing power is greater than the idle computing power, and the priority of the terminal device is lower than the priority of other terminal devices that are executing computing power tasks, a corresponding method is selected to end the terminal device task according to the real-time requirements of the task of the terminal device, specifically including:

[0076] If the requested computing power is greater than the idle computing power, and the priority of the terminal device is lower than the priority of other terminal devices that are executing computing power tasks, continuously obtain the real-time task requirements of the terminal device;

[0077] If the task of the terminal device requires waiting in real time, the idle computing power information is updated again, and the relationship between the applied computing power and the idle computing power is determined, and then a corresponding method is selected to end the task of the terminal device;

[0078] If the task of the terminal device requires real-time termination without waiting, the task of the terminal device is terminated directly;

[0079] If the task of the terminal device requires real-time submission without waiting and without needing to be terminated, apply for idle network computing power to execute the computing power task in the computing power application, and terminate the terminal device task after the computing power task is completed.

[0080] Exemplarily, the application for idle network computing power to execute the computing power task in the computing power application specifically includes:

[0081] Apply for idle network computing power from other central computing power devices to execute the computing power tasks in the computing power application; perform load balancing among the central computing power devices.

[0082] Compared with the prior art, the embodiment of the present invention provides a computing power reuse device, a computing power centralized management method uniformly scheduled by a central computing power device, and the computing power comes from a central computing power controller or a network computing power scheduled by a central computing power controller, such as a central computing power device in the cloud or a neighbor's home. When the terminal device is connected to the network and running, the central computing power device can also coordinate computing power from the regional network or the cloud to meet the needs of specific users. When a specific central computing power device fails or needs maintenance, the central computing power device can also use the task migration method to continue user services.

[0083] In summary, the embodiments of the present invention use dynamic scheduling and computing power reuse, so that for specific terminal devices, the computing power that can be used far exceeds that of traditional solutions, so that more complex algorithms can be deployed. At the same time, the utilization rate of computing resources is improved and resource waste is reduced; high-priority tasks can quickly obtain the required resources, shorten processing time, and improve user experience; the load balancing mechanism avoids single-point overload and enhances the overall stability and reliability of the architecture; and supports cross-network computing resource sharing, so that the architecture can better cope with sudden high-load situations while maintaining good performance. The computing power reuse method provides a flexible, efficient, and fair computing resource management strategy that is suitable for complex and changing application scenarios and helps to build a more intelligent, efficient, and sustainable computing environment.

[0084] An embodiment of the present application provides a computing power architecture, including multiple central computing power devices and multiple terminal device networks, each central computing power device provides computing power for all terminal devices in a terminal device network, and each terminal device is communicatively connected to the corresponding central computing power device; each central computing power device is communicatively connected to each other and executes the computing power multiplexing method as described above.

[0085] Compared with the prior art, the embodiments of the present invention provide a computing power reuse architecture, a computing power centralized management method uniformly scheduled by a central computing power device, and the computing power comes from a central computing power controller or network computing power scheduled by a central computing power controller, such as a central computing power device in the cloud or in a neighbor's house. When the terminal device is connected to the network and running, the central computing power device can also coordinate computing power from within the regional network or the cloud to meet the needs of specific users. When a specific central computing power device fails or needs maintenance, the central computing power device can also use the task migration method to continue user services.

[0086] In summary, the embodiments of the present invention use dynamic scheduling and computing power reuse, so that for specific terminal devices, the computing power that can be used far exceeds that of traditional solutions, so that more complex algorithms can be deployed. At the same time, the utilization rate of computing resources is improved and resource waste is reduced; high-priority tasks can quickly obtain the required resources, shorten processing time, and improve user experience; the load balancing mechanism avoids single-point overload and enhances the overall stability and reliability of the architecture; and supports cross-network computing resource sharing, so that the architecture can better cope with sudden high-load situations while maintaining good performance. The computing power reuse method provides a flexible, efficient, and fair computing resource management strategy that is suitable for complex and changing application scenarios and helps to build a more intelligent, efficient, and sustainable computing environment.

[0087] An embodiment of the present application provides a computer-readable storage medium storing a computer program, which implements the above-mentioned computing power reuse method when the computer program is executed by a processor.

[0088] The computer device may be a computing device such as a smart phone, a tablet computer, a desktop computer, and a cloud server. The computer device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the figure is merely an example of a computer device and does not constitute a limitation on the computer device, and may include more or fewer components than shown in the figure, or a combination of certain components, or different components, such as input and output devices, network access devices, etc.

[0089] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0090] In some embodiments, the memory may be an internal storage unit of the computer device, such as a hard disk or memory of the computer device. In other embodiments, the memory may also be an external storage device of the computer device, such as a plug-in hard disk, a smart memory card (Smart Med ia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the computer device. Further, the memory may also include both an internal storage unit of the computer device and an external storage device. The memory is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program. The memory may also be used to temporarily store data that has been output or is to be output.

[0091] An embodiment of the present application provides a computer program product. When the computer program product is run on a computer device, the computer device implements the steps in the above-mentioned method embodiments when executing the computer device.

[0092] In several embodiments provided in the present application, it is understood that each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved.

[0093] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0094] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A computing power reuse method, characterized in that: include: Determining the requested computing power of the terminal device according to the computing power request from the terminal device; Continuously update the idle computing power information. If the applied computing power is less than or equal to the local idle computing power, allocate computing power from the local idle computing power to execute the computing power task in the computing power application. After the computing power task is completed, end the terminal device task; Continuously update the idle computing power information. If the applied computing power is greater than the local idle computing power, select a corresponding method to end the terminal device task according to the priority of the terminal device and the real-time requirements of the task.

2. The computing power reuse method according to claim 1, characterized in that: The continuously updating the idle computing power information, if the applied computing power is greater than the idle computing power, selecting a corresponding method to end the terminal device task according to the priority of the terminal device and the real-time requirement of the task, specifically includes: Continuously update the idle computing power information. If the requested computing power is greater than the idle computing power, and the priority of the terminal device is higher than the priority of other terminal devices that are executing computing power tasks, reallocate the local computing power to execute the computing power tasks in the computing power application; If the requested computing power is greater than the idle computing power, and the priority of the terminal device is lower than that of other terminal devices that are executing computing power tasks, a corresponding method is selected to end the terminal device task according to the real-time requirements of the terminal device's task.

3. The computing power reuse method according to claim 2, characterized in that: If the requested computing power is greater than the idle computing power, and the priority of the terminal device is lower than that of other terminal devices that are executing computing power tasks, a corresponding method is selected to terminate the terminal device task according to the real-time requirements of the task of the terminal device, specifically including: If the requested computing power is greater than the idle computing power, and the priority of the terminal device is lower than the priority of other terminal devices that are executing computing power tasks, continuously obtain the real-time task requirements of the terminal device; If the task of the terminal device requires waiting in real time, the idle computing power information is updated again, and the relationship between the applied computing power and the idle computing power is determined, and then a corresponding method is selected to end the task of the terminal device; If the task of the terminal device requires real-time termination without waiting, the task of the terminal device is terminated directly; If the task of the terminal device requires real-time submission without waiting and without needing to be terminated, apply for idle network computing power to execute the computing power task in the computing power application, and terminate the terminal device task after the computing power task is completed.

4. The computing power reuse method according to claim 3, characterized in that: The application for network idle computing power to execute the computing power task in the computing power application specifically includes: Apply for idle network computing power from other central computing power devices to execute the computing power tasks in the computing power application; perform load balancing among the central computing power devices.

5. The computing power reuse method according to claim 1, characterized in that: The priority of the terminal device is preset; the terminal device is a device in a local network or a device in an externally connected network.

6. A computing power multiplexing device, characterized in that: include: A computing power confirmation module, used to determine the requested computing power of the terminal device according to the computing power application from the terminal device; A first computing power allocation module is used to continuously update the idle computing power information. If the applied computing power is less than or equal to the local idle computing power, computing power is allocated from the local idle computing power to execute the computing power task in the computing power application. After the computing power task is completed, the terminal device task is terminated; The second computing power allocation module is used to continuously update the idle computing power information. If the applied computing power is greater than the local idle computing power, a corresponding method is selected to end the terminal device task according to the priority of the terminal device and the real-time requirements of the task.

7. The computing power multiplexing device according to claim 6, characterized in that: The continuously updating the idle computing power information, if the applied computing power is greater than the idle computing power, selecting a corresponding method to end the terminal device task according to the priority of the terminal device and the real-time requirement of the task, specifically includes: Continuously update the idle computing power information. If the requested computing power is greater than the idle computing power, and the priority of the terminal device is higher than the priority of other terminal devices that are executing computing power tasks, reallocate the local computing power to execute the computing power tasks in the computing power application; If the requested computing power is greater than the idle computing power, and the priority of the terminal device is lower than that of other terminal devices that are executing computing power tasks, a corresponding method is selected to end the terminal device task according to the real-time requirements of the terminal device's task.

8. The computing power multiplexing device according to claim 7, characterized in that: If the requested computing power is greater than the idle computing power, and the priority of the terminal device is lower than that of other terminal devices that are executing computing power tasks, a corresponding method is selected to terminate the terminal device task according to the real-time requirements of the task of the terminal device, specifically including: If the requested computing power is greater than the idle computing power, and the priority of the terminal device is lower than the priority of other terminal devices that are executing computing power tasks, continuously obtain the real-time task requirements of the terminal device; If the task of the terminal device requires waiting in real time, the idle computing power information is updated again, and the relationship between the applied computing power and the idle computing power is determined, and then a corresponding method is selected to end the task of the terminal device; If the task of the terminal device requires real-time termination without waiting, the task of the terminal device is terminated directly; If the task of the terminal device requires real-time submission without waiting and without needing to be terminated, apply for idle network computing power to execute the computing power task in the computing power application, and terminate the terminal device task after the computing power task is completed.

9. The computing power multiplexing device as claimed in claim 8, characterized in that: The application for network idle computing power to execute the computing power task in the computing power application specifically includes: Apply for idle network computing power from other central computing power devices to execute the computing power tasks in the computing power application; perform load balancing among the central computing power devices.

10. A computing power reuse architecture, characterized in that: It includes multiple central computing power devices and multiple terminal device networks, each central computing power device provides computing power for all terminal devices in a terminal device network, and each terminal device is communicatively connected with the corresponding central computing power device; each central computing power device is communicatively connected with each other and executes the computing power reuse method as described in claims 1 to 5.

Images