Method and apparatus for distributing computing power tasks

Abstract

The application discloses a computing power task distribution method and device, and belongs to the technical field of computers, to solve the problem of unreasonable computing power task distribution in related technologies. The method comprises the following steps: determining the demand weights corresponding to different computing power requirements of a computing power task according to the computing power requirements of the computing power task to be distributed to computing power equipment; for each computing power equipment, determining the recommended coefficients of the computing power equipment under different computing power characteristics according to real-time resource occupation information of the computing power equipment and computing power test results for different computing power characteristics; determining the computing power recommended value of each computing power equipment for the computing power task according to the recommended coefficients of the computing power equipment under different computing power characteristics and the demand weights corresponding to different computing power requirements of the computing power task; and distributing the computing power task to a target computing power equipment in the computing power equipment based on the computing power recommended value for processing. The technical scheme realizes more reasonable and accurate distribution of the computing power task.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of computer, and particularly relates to a computing power task allocation method and device. BACKGROUND

[0002] With the development of Internet of Things, industrial automation, intelligent transportation, smart home, virtual reality and other fields, the amount of data is growing, and the demand for data processing and analysis is also increasing. Although the traditional cloud computing center can provide powerful computing power, the delay of data transmission and processing is large, which cannot meet the application scenarios with high real-time requirements. Migrating computing power to the edge side can solve this problem. In this scenario, computing power is deployed at the network edge and directly connected to terminal devices, which can quickly process and analyze data, reducing the delay and cost of data transmission. At the same time, since data is processed locally, the security and privacy protection of data are also increased. However, how to allocate computing power tasks to each computing power device deployed on the edge side becomes a technical problem to be solved in the field.

[0003] In the related art, each computing power device is generally allocated computing power tasks in a balanced manner according to its real-time state. The real-time state of each computing power device is obtained by comprehensively analyzing its computing power occupation condition and its own specification parameters. However, for different computing power tasks, the demand direction is different, so if the same allocation method is used, the demand characteristics of different tasks cannot be met, and the computing power resources of each computing power device cannot be maximized. SUMMARY

[0004] The embodiments of the present application provide a computing power task allocation method and device, which can solve the problem of unreasonable allocation of computing power tasks in the related art.

[0005] In a first aspect, embodiments of this application provide a method for allocating computing power tasks, comprising: determining the demand weights corresponding to different computing power demands of the computing power tasks to be allocated to computing power devices, based on the computing power demands of each computing power task to be allocated to computing power devices; the different computing power demands include data processing demand, image processing demand, and resource demand of the task; the demand weights include data processing computing characteristic weights, image processing computing characteristic weights, and transmission and storage characteristic weights; for each computing power device, determining a recommendation coefficient for the computing power device under different computing power characteristics based on the real-time resource occupancy information of the computing power device and the computing power test results for different computing power characteristics; the computing power characteristics include data processing computing characteristics, image processing computing characteristics, and transmission and storage characteristics; determining a recommended computing power value for each computing power device for the computing power task based on the recommended coefficient of the computing power device under different computing power characteristics and the demand weights corresponding to the different computing power demands of the computing power tasks; and allocating the computing power tasks to target computing power devices among the computing power devices for processing based on the recommended computing power values.

[0006] Secondly, embodiments of this application provide a computing power task allocation device, comprising: a first determining module, configured to determine the demand weights corresponding to different computing power demands of the computing power tasks to be allocated to computing power devices, based on the computing power demands of the computing power tasks to be allocated to computing power devices; the different computing power demands include data processing demand, image processing demand, and resource demand of the task; the demand weights include data processing computing characteristic weights, image processing computing characteristic weights, and transmission and storage characteristic weights; a second determining module, configured to determine, for each computing power device, a recommendation coefficient of the computing power device under different computing power characteristics based on the real-time resource occupancy information of the computing power device and the computing power test results for different computing power characteristics; the computing power characteristics include data processing computing characteristics, image processing computing characteristics, and transmission and storage characteristics; a third determining module, configured to determine the recommended computing power value of each computing power device for the computing power task based on the recommended coefficient of the computing power device under the different computing power characteristics and the demand weights corresponding to the different computing power demands of the computing power tasks; and a computing power task allocation module, configured to allocate the computing power tasks to target computing power devices among the computing power devices for processing based on the recommended computing power values.

[0007] Thirdly, embodiments of this application provide an electronic device including a processor; and a memory arranged to store computer-executable instructions configured to be executed by the processor to implement the steps of the computing task allocation method as described in the first aspect.

[0008] Fourthly, embodiments of this application provide a computer-readable storage medium for storing computer-executable instructions, which, when executed by a processor, implement the steps of the computing power task allocation method as described in the first aspect.

[0009] Fifthly, embodiments of this application provide a computer program product, the computer program product including a computer program, which, when executed by a processor, implements the steps of the computing power task allocation method as described in the first aspect.

[0010] In a sixth aspect, embodiments of this application provide a chip, the chip including a processor and a communication interface, the communication interface being coupled to the processor, the processor being used to run executable instructions to implement the steps of the computing power task allocation method as described in the first aspect.

[0011] By employing the technical solution of this application embodiment, during the allocation of computing power tasks, the demand weights corresponding to different computing power requirements of the computing power tasks to be allocated to computing power devices can be determined according to the computing power requirements of each computing power task. Different computing power requirements include data processing requirements, image processing requirements, and the amount of resources required by the task. Demand weights include data processing computing characteristic weights, image processing computing characteristic weights, and transmission and storage characteristic weights. Furthermore, for each computing power device, a recommendation coefficient for the computing power device under different computing power characteristics is determined based on the real-time resource occupancy information of the computing power device and the computing power test results for different computing power characteristics. Computing power characteristics include data processing computing characteristics, image processing computing characteristics, and transmission and storage characteristics. Therefore, based on the recommendation coefficients of the computing power devices under different computing power characteristics and the demand weights corresponding to different computing power requirements of the computing power tasks, a recommended computing power value for each computing power device for the computing power task is determined, and based on the recommended computing power value, the computing power task is allocated to the target computing power device among the various computing power devices for processing. Since demand weights reflect the emphasis of a computing task on the computing power requirements of each device, and recommendation coefficients reflect the computing power resources of a computing device under different computing power characteristics (for example, if a computing device has a large amount of remaining computing power resources under a certain computing power characteristic, then the recommendation coefficient of that computing power device under that characteristic will be higher), this technical solution determines the target computing power devices among all computing power devices by calculating the demand weights of computing power tasks and the recommendation coefficients of computing power devices. It fully considers the impact of the computing power requirements of computing power tasks and the computing power resources of computing power devices on the selection of computing power devices. Compared with the method of evenly allocating computing power tasks to each computing power device in related technologies, this not only enables the target computing power devices to better meet the computing power requirements of computing power tasks, achieving a more reasonable and accurate allocation of computing power tasks, but also improves the full utilization of the computing power resources of each computing power device. Attached Figure Description

[0012] Figure 1 This is a schematic block diagram of a computing power task allocation system provided in an embodiment of this application;

[0013] Figure 2 This is a flowchart illustrating a method for allocating computing power tasks according to an embodiment of this application;

[0014] Figure 3 This is a flowchart illustrating a method for allocating computing power tasks according to another embodiment of this application;

[0015] Figure 4 This is a schematic diagram of the structure of a computing power task allocation device provided in an embodiment of this application;

[0016] Figure 5 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0017] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0018] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0019] The method and apparatus for allocating computing power tasks provided in this application will be described in detail below with reference to the accompanying drawings, through specific embodiments and application scenarios.

[0020] Figure 1 This is a schematic block diagram of a computing power task allocation system provided in an embodiment of this application, such as... Figure 1 As shown, the computing power task allocation system includes a task analysis unit 110, a computing power equipment monitoring unit 120, and an operation and maintenance management center 130. The task analysis unit 110 and the computing power equipment monitoring unit 120 are communicatively connected to the operation and maintenance management center 130.

[0021] In this embodiment, the task analysis unit 110 is used to determine the demand weights corresponding to the different computing power requirements of the computing power tasks to be allocated to the computing power devices, and send the demand weights to the operation and maintenance management center 130. Different computing power requirements include data processing requirements, image processing requirements, and the amount of resources required by the task. The demand weights include data processing computing characteristic weights, image processing computing characteristic weights, and transmission and storage characteristic weights.

[0022] The computing power equipment monitoring unit 120 is used to determine the recommendation coefficient of each computing power equipment under different computing power characteristics based on the real-time resource usage information of the computing power equipment and the computing power test results for different computing power characteristics, and then send the recommendation coefficient to the operation and maintenance management center 130. The computing power characteristics include data processing computing characteristics, image processing computing characteristics, and transmission and storage characteristics.

[0023] The operation and maintenance management center 130 is used to determine the recommended computing power value for each computing power device for a computing power task based on the recommendation coefficient of the computing power device under different computing power characteristics and the demand weight corresponding to the different computing power requirements of the computing power task. Based on the recommended computing power value, the computing power task is allocated to the target computing power device in each computing power device for processing.

[0024] The following details the method for allocating computing power tasks in the allocation system applied to this computing power task. Figure 2 This application illustrates an embodiment of a method for allocating computing power tasks. This method can be executed by an electronic device, which may include a server and / or a terminal device, such as a vehicle-mounted terminal or a mobile terminal. In other words, the method can be executed by software or hardware installed on the electronic device, and includes the following steps:

[0025] Step 202: Determine the demand weights corresponding to the different computing power demands of the computing power tasks to be allocated to the computing power devices.

[0026] The number of computing devices is multiple. Optionally, the computing devices can be distributed computing devices deployed at the edge. Different computing power requirements include data processing requirements, image processing requirements, and resource requirements for the task. Demand weights include weights for data processing computing characteristics, image processing computing characteristics, and transmission and storage characteristics. In this embodiment, the demand weights can reflect the emphasis of the computing task on each computing power requirement, that is, which aspect of computing power the computing task needs more.

[0027] Optionally, the data processing requirement can be used to characterize information such as the computing power model required for data processing, the expected completion time of data processing, and the computing power required for data processing. Similarly, the image processing requirement can be used to characterize information such as the computing power model required for image processing, the expected completion time of image processing, and the computing power required for image processing. The resource requirement for a task can be used to characterize information such as the computing power model required for a computing task, the expected completion time of a computing task, and the total computing power required for a computing task.

[0028] Step 204: For each computing power device, determine the recommendation coefficient of the computing power device under different computing power characteristics based on the real-time resource usage information of the computing power device and the computing power test results for different computing power characteristics.

[0029] The computing power characteristics include data processing computing characteristics, image processing computing characteristics, and transmission and storage characteristics. In this embodiment, the recommendation coefficient can reflect the computing power resource status of the computing power device under different computing power characteristics. For example, if the computing power device has a lot of remaining computing power resources under a certain computing power characteristic, then the recommendation coefficient of the computing power device under that computing power characteristic will be higher.

[0030] Step 206: Determine the recommended computing power value for each computing power device for the computing power task based on the recommendation coefficient of the computing power device under different computing power characteristics and the demand weight corresponding to the different computing power requirements of the computing power task.

[0031] Step 208: Based on the recommended computing power value, the computing power tasks are allocated to the target computing power devices in each computing power device for processing.

[0032] By employing the technical solution of this application embodiment, during the allocation of computing power tasks, the demand weights corresponding to different computing power requirements of the computing power tasks to be allocated to computing power devices can be determined according to the computing power requirements of each computing power task. Different computing power requirements include data processing requirements, image processing requirements, and the amount of resources required by the task. Demand weights include data processing computing characteristic weights, image processing computing characteristic weights, and transmission and storage characteristic weights. Furthermore, for each computing power device, a recommendation coefficient for the computing power device under different computing power characteristics is determined based on the real-time resource occupancy information of the computing power device and the computing power test results for different computing power characteristics. Computing power characteristics include data processing computing characteristics, image processing computing characteristics, and transmission and storage characteristics. Therefore, based on the recommendation coefficients of the computing power devices under different computing power characteristics and the demand weights corresponding to different computing power requirements of the computing power tasks, a recommended computing power value for each computing power device for the computing power task is determined, and based on the recommended computing power value, the computing power task is allocated to the target computing power device among the various computing power devices for processing. Since demand weights reflect the emphasis of a computing task on the computing power requirements of each device, and recommendation coefficients reflect the computing power resources of computing devices under different computing power characteristics, this technical solution calculates the demand weights of computing tasks and the recommendation coefficients of computing devices to determine the target computing devices among all computing devices. This fully considers the impact of the computing power requirements of the computing tasks and the computing power resources of the devices on the selection of computing devices. Compared to the method of evenly allocating computing power tasks to each computing device in related technologies, this approach not only enables the target computing devices to better meet the computing power requirements of the computing tasks, achieving a more reasonable and accurate allocation of computing power tasks, but also improves the full utilization of the computing power resources of each computing device.

[0033] In one implementation, the demand weights corresponding to the different computing power demands of the computing power tasks to be allocated to the computing power devices are determined according to their respective computing power demands (i.e., step 202), which can be executed as follows: Steps A1-A2:

[0034] Step A1: For each computing power requirement of the computing power task, determine the required value corresponding to the computing power requirement based on the computing power requirement, as well as the standard value, standard function, and weight adjustment coefficient corresponding to the computing power requirement.

[0035] Step A2: Calculate the ratio of the demand value to the total demand value to obtain the demand weight corresponding to the computing power demand.

[0036] The total demand value is determined based on the demand value of each computing power requirement.

[0037] In this embodiment, by determining the demand weights corresponding to different computing power requirements of computing power tasks, since the demand weights can reflect the emphasis of computing power tasks on each computing power requirement, a data basis is provided for the reasonable allocation of computing power tasks.

[0038] In one implementation, step A1 can be specifically executed as follows: steps A11-A13:

[0039] Step A11: For the data processing requirement of the computing power task, calculate the ratio between the data processing requirement and the function value of the standard function corresponding to the data processing requirement, and then calculate the product of this ratio and the first weight adjustment coefficient corresponding to the data processing requirement. Calculate the ratio between the data processing requirement and the standard value corresponding to the data processing requirement, and then calculate the product of this ratio and the second weight adjustment coefficient corresponding to the data processing requirement. Sum these two products to obtain the required value corresponding to the data processing requirement.

[0040] The function value of the standard function corresponding to the data processing demand is obtained by taking the value of the resource quantity required for the task from the standard function corresponding to the data processing demand.

[0041] Optionally, the demand value corresponding to the data processing requirement can be represented by the following expression (1):

[0042] (1)

[0043] in, To meet the data processing requirements, The amount of resources required for the task. The standard function corresponding to the data processing requirements. The standard value corresponding to the data processing demand. x1 This is the first weight adjustment coefficient corresponding to the data processing demand. x2 This is the second weighting adjustment coefficient corresponding to the data processing demand.

[0044] Step A12: For the graphics processing requirement of the computing power task, calculate the ratio between the graphics processing requirement and the function value of the standard function corresponding to the graphics processing requirement, and then calculate the product of this ratio and the first weight adjustment coefficient corresponding to the graphics processing requirement. Calculate the ratio between the graphics processing requirement and the standard value corresponding to the graphics processing requirement, and then calculate the product of this ratio and the second weight adjustment coefficient corresponding to the graphics processing requirement. Sum these two products to obtain the requirement value corresponding to the graphics processing requirement.

[0045] The function value of the standard function corresponding to the graphics processing demand is obtained by taking the value of the resource quantity required for the task from the standard function corresponding to the graphics processing demand.

[0046] Optionally, the demand value corresponding to the graphics processing demand can be represented by the following expression (2):

[0047] (2)

[0048] in, For graphics processing requirements, The standard function corresponding to the graphics processing requirements. This represents the standard value corresponding to the graphics processing requirements. y1 This is the first weight adjustment coefficient corresponding to the graphics processing demand. y2 This is the second weighting adjustment coefficient corresponding to the graphics processing demand.

[0049] Step A13: For the resource requirement of the computing power task, calculate the ratio between the resource requirement of the task and the standard value corresponding to the resource requirement of the task, and calculate the product of this ratio and the weight adjustment coefficient corresponding to the resource requirement of the task.

[0050] Optionally, the required resource quantity for a task can be represented by the following expression (3):

[0051] (3)

[0052] in, This represents the standard value corresponding to the amount of resources required for the task. The weight adjustment coefficient corresponding to the amount of resources required for the task.

[0053] In one implementation, the sum of expressions (1) to (3) above can be calculated to obtain the total demand value corresponding to all computing power requirements of the computing power task. Then, based on the ratio of the demand value of each computing power requirement to the total demand value, the demand weight corresponding to each computing power requirement can be obtained. Specifically, this includes the demand weight for data processing requirements. Demand weight for image processing requirements The required weight of resources for the task .

[0054] Among them, the demand weight of data processing requirements The calculation process is shown in formula (4), which is the demand weight of image processing requirements. The calculation process is shown in formula (5), which is the weight of the required resources for the task. The calculation process is shown in formula (6).

[0055] (4)

[0056] (5)

[0057] (6)

[0058] In one implementation, for each computing power device, based on the real-time resource occupancy information of the computing power device and the computing power test results for different computing power characteristics, the recommendation coefficient of the computing power device under different computing power characteristics is determined (i.e., step 204), which can be executed as follows: Steps B1-B3:

[0059] Step B1: For each computing power device, determine the real-time operating status value of the computing power device for different computing power characteristics based on the real-time resource occupancy information and device parameters of the computing power device.

[0060] The equipment parameters may include one or more of the following: rated storage capacity, rated power load, rated load of cooling equipment, rated computing capacity and storage impact coefficient corresponding to different computing power characteristics.

[0061] Step B2: Based on the computing power test results of the computing power equipment for different computing power characteristics, determine the operational evaluation value of the computing power equipment for different computing power characteristics.

[0062] Step B3: Based on the real-time operating status values ​​and operating evaluation values ​​of the computing power equipment for different computing power characteristics, determine the recommendation coefficient of the computing power equipment under different computing power characteristics. The recommendation coefficient is negatively correlated with the real-time operating status value and positively correlated with the operating evaluation value.

[0063] In this embodiment, based on the real-time resource occupancy information and equipment parameters of the computing power device, the real-time operating status value of the computing power device for different computing power characteristics is determined. This allows for the assessment of the computing power occupancy corresponding to different computing power characteristics within the computing power device. Furthermore, based on the computing power test results, the operating evaluation value of the computing power device for different computing power characteristics is determined. This allows for the assessment of the computing power execution capability of the computing power device for different computing power characteristics. By comprehensively considering the computing power occupancy and computing power execution capability, a recommendation coefficient for the computing power device under different computing power characteristics is obtained. This recommendation coefficient reflects the computing power resource situation of the computing power device under different computing power characteristics, providing a data foundation for the rational allocation of computing power tasks.

[0064] In one implementation, real-time resource usage information includes data computation usage, transmission and storage usage, power load usage, and cooling equipment load usage. Equipment parameters include rated storage capacity, rated power load, and rated cooling equipment load.

[0065] In this embodiment, based on the real-time resource occupancy information and device parameters of the computing power device, the real-time operating status value of the computing power device for different computing power characteristics is determined (i.e., step B1), which can be executed as follows: steps C1-C6:

[0066] Step C1: Determine the first constituent factor of the real-time operating status value based on the first ratio between the power load occupancy and the rated power load, the second ratio between the refrigeration equipment load occupancy and the rated refrigeration equipment load, and a preset logic function.

[0067] Optionally, the preset logic function can be ,when When it exceeds the preset rated value, ;otherwise, In determining the first constituent factor of the real-time operating state value, the sum of the first ratio and the second ratio can be used as a variable of the preset logic function. Therefore, the first constituent factor can be characterized by the following expression (7):

[0068] (7)

[0069] in, This refers to the amount of electricity load. For rated electrical load, This refers to the load occupancy of the refrigeration equipment. This refers to the rated load of the refrigeration equipment. In this embodiment, the preset rated value can be 2, meaning the power load occupancy is the same as the rated power load, and the refrigeration equipment load occupancy is the same as the rated load of the refrigeration equipment. If the load exceeds the preset rated value, it indicates that the power load and / or cooling equipment load exceeds their corresponding rated load. In this case, the computing equipment is operating under overload. Therefore, the computing equipment cannot provide computing power for the tasks to be allocated, and analyzing the real-time operating status value of the computing equipment is meaningless. The value is 0. And... If the load is less than the preset rated value, it indicates that the power load and / or cooling equipment load have not exceeded their corresponding rated load. In this case, the computing device can provide computing power for the computing tasks to be allocated. The value is 1.

[0070] Step C2: Obtain the rated computing power and data computing storage impact coefficient of the computing device under the data processing computing characteristics.

[0071] Optionally, the rated computing capacity and the data computing storage impact coefficient can be the equipment parameters of the computing power equipment.

[0072] Step C3: Calculate the first difference between the rated computing load and the data computing usage, and the second difference between the average rated computing load of all computing devices and the average data computing usage of all computing devices.

[0073] The average rated computing load is determined based on the rated computing load of each computing device, and the average data computing usage is determined based on the data computing usage of each computing device.

[0074] Step C4: Based on the data calculation occupancy, the first difference, the second difference, and the preset exponential function, determine the second constituent factor of the real-time operating status value of the computing power device under the data processing and computing characteristics.

[0075] Optionally, the preset exponential function can be based on the natural constant. e The exponent of this function is a base-based exponential function, and the exponent of this function is composed of the data computation occupancy, the first difference, and the second difference. Specifically, the ratio between the data computation occupancy and the first difference and the second difference can be calculated respectively, and then the product of these two ratios can be calculated. The square root of this product is taken as the exponent of the function. Thus, the second constituent factor can be characterized by the following expression (8):

[0076] (8)

[0077] in, Calculate the usage of the data. Calculate the average data usage for all computing devices. Calculate the rated computational load for the data. Calculate the average rated computing load for all computing devices.

[0078] Step C5: Based on the transmission and storage occupancy, the average rated storage capacity of all computing devices, and the data calculation storage impact coefficient, determine the third constituent factor of the real-time operating status value of the computing devices under the data processing and computing characteristics.

[0079] The average rated storage capacity is determined based on the rated storage capacity of each computing device.

[0080] Optionally, the ratio between the transmission storage occupancy and the average rated storage capacity of all computing devices can be calculated, and then the data storage impact coefficient can be calculated as a product of this ratio to obtain the third constituent factor. Thus, the third constituent factor can be characterized by the following expression (9):

[0081] (9)

[0082] in, Calculate the storage impact coefficient for the data. for t Data usage for data transmission at a given time point. This represents the average rated storage capacity of all computing devices.

[0083] Step C6: Calculate the product of the first constituent factor, the second constituent factor, and the third constituent factor to obtain the real-time operating status value of the computing power device under the data processing and computing characteristics.

[0084] In this embodiment, the real-time operating status value of the computing device under the data processing and computing characteristics can be obtained by calculating the product of the above expressions (7) to (9). . The calculation process is shown in formula (10).

[0085] (10)

[0086] In one implementation, real-time resource usage information may include image processing usage. In this embodiment, based on the real-time resource usage information and device parameters of the computing power device, the real-time operating status value of the computing power device for different computing power characteristics is determined (i.e., step B1), which can be executed as follows: steps D1-D5:

[0087] Step D1: Obtain the rated computational load and image processing storage impact coefficient of the computing power device under the image processing computational characteristics.

[0088] Optionally, the image processing rated computational load and the image processing storage impact coefficient can be equipment parameters of the computing power device.

[0089] Step D2: Calculate the third difference between the rated computational load of image processing and the image processing usage, and the fourth difference between the average rated computational load of all computing devices and the average image processing usage of all computing devices.

[0090] The average rated computational load for image processing is determined based on the rated computational load for each computing device, and the average image processing usage is determined based on the image processing usage of each computing device.

[0091] Step D3: Based on the image processing occupancy, the third difference, the fourth difference, and the preset exponential function, determine the fourth constituent factor of the real-time operating status value of the computing power device under the image processing computing characteristics.

[0092] Optionally, the preset exponential function can be based on the natural constant. e The exponent of this function is composed of image processing occupancy, the third difference, and the fourth difference. Specifically, the ratio between image processing occupancy and the third and fourth differences can be calculated separately, and then the product of these two ratios can be calculated. The square root of this product is taken as the exponent of the function. Thus, the fourth constituent factor can be characterized by the following expression (11):

[0093] (11)

[0094] in, Image processing usage This represents the average image processing usage across all computing devices. For image processing, the rated computational load, This represents the average rated computational load for image processing across all computing devices.

[0095] Step D4: Based on the transmission and storage occupancy, the average rated storage capacity of all computing devices, and the image processing storage influence coefficient, determine the fifth component of the real-time operating status value of the computing devices under the image processing computing characteristics.

[0096] Optionally, the ratio between the transmission storage occupancy and the average rated storage capacity of all computing devices can be calculated, and then the image processing storage influence coefficient can be multiplied by this ratio to obtain the fifth constituent factor. Thus, the fifth constituent factor can be characterized by the following expression (12):

[0097] (12)

[0098] in, Store the influence coefficients for image processing.

[0099] Step D5: Calculate the product of the first constituent factor, the fourth constituent factor, and the fifth constituent factor to obtain the real-time operating status value of the computing power device under the image processing computing characteristics.

[0100] In this embodiment, the real-time operating status value of the computing device under the image processing computing characteristics can be obtained by calculating the product of the above expressions (7), (11) and (12). . The calculation process is shown in formula (13).

[0101] (13)

[0102] In one implementation, based on the real-time resource occupancy information and equipment parameters of the computing power device, the real-time operating status value of the computing power device for different computing power characteristics is determined (i.e., step B1), which can be executed as follows: Steps E1-E2:

[0103] Step E1: Based on the transmission and storage occupancy and the average rated storage capacity of all computing devices, determine the sixth component factor of the real-time operating status value of the computing devices under the transmission and storage characteristics.

[0104] In this embodiment, the sixth constituent factor can be characterized by the following expression (14):

[0105] (14)

[0106] Step E2: Calculate the product of the first constituent factor and the sixth constituent factor to obtain the real-time operating status value of the computing power device under the transmission and storage characteristics.

[0107] In this embodiment, the real-time operating status value of the computing device under the transmission and storage characteristics can be obtained by calculating the product of the above expressions (7) and (14). . The calculation process is shown in formula (15).

[0108] (15)

[0109] In one implementation, before determining the operational evaluation value of the computing power device for different computing power characteristics (i.e., step B2) based on the computing power test results of the computing power device for different computing power characteristics, the data processing computing characteristics, image processing computing characteristics, and transmission and storage characteristics of the computing power device can be tested by a preset number of test computing power tasks to obtain the computing power test results of the computing power device for different computing power characteristics.

[0110] The computing power test results may include data processing scores, image processing scores, and transmission and storage scores. In this embodiment, the computing power device can be made to process multiple test computing power tasks. Based on the processing performance of the computing power device on the multiple test computing power tasks (such as processing speed, model used, processing time, etc.), the computing power test results of the computing power device under different computing power characteristics can be comprehensively analyzed.

[0111] Optionally, the data processing score can be composed of factors such as data processing speed score, model score used, and processing time score in a preset proportion. The image processing score can be composed of factors such as image processing speed score, model score used, and processing time score in a preset proportion. The transmission and storage score can be composed of factors such as transmission and storage speed score, model score used, and processing time score in a preset proportion. The process of obtaining each score based on the test computing power task is not elaborated in detail in this embodiment. In practical applications, the corresponding score can be determined based on the actual processing situation within a given range by setting processing situation ranges for each score.

[0112] In one implementation, the evaluation value of the computing power device for different computing power characteristics is determined based on the computing power test results of the computing power device for different computing power characteristics (i.e., step B2). This can be performed as follows: the normalized value of the data processing score of each test computing power task is calculated by using a first preset function, and the average data processing score of all test computing power tasks is determined based on the normalized value of the data processing score of each test computing power task. The average data processing score is then determined as the evaluation value of the computing power device under the data processing computing characteristics.

[0113] In this embodiment, the performance evaluation value of the computing device under the data processing and computing characteristics The calculation process is shown in formula (16).

[0114] (16)

[0115] in, To test the number of computing power tasks, ∈[1, ]. For the first The data processing score for a type of computing power test task. For the first The normalization function for the data processing score of the test computing power task is the first preset function mentioned above.

[0116] Therefore, based on the real-time operating status values ​​of computing devices under data processing and computing characteristics and operational evaluation values This allows us to obtain the recommendation coefficient for the computing power device under the data processing and computing characteristics. , .

[0117] In one implementation, the evaluation value of the computing power device for different computing power characteristics is determined based on the computing power test results of the computing power device for different computing power characteristics (i.e., step B2). This can be performed as follows: the normalized value of the image processing score of each test computing power task is calculated by the second preset function, and the average image processing score of all test computing power tasks is determined based on the normalized value of the image processing score of each test computing power task. The average image processing score is then determined as the evaluation value of the computing power device under the image processing computing characteristics.

[0118] In this embodiment, the performance evaluation value of the computing device under image processing computing characteristics The calculation process is shown in formula (17).

[0119] (17)

[0120] in, To test the number of computing power tasks, ∈[1, ]. For the first Image processing scores for a test computing power task. For the first The normalization function for the image processing score of the test computing power task is the second preset function mentioned above.

[0121] Therefore, based on the real-time operating status values ​​of the computing power device under the image processing computing characteristics... and operational evaluation values This allows us to obtain the recommendation coefficient for the computing power of the device under the image processing computing characteristics. , .

[0122] In one implementation, the evaluation value of the computing power device for different computing power characteristics is determined based on the computing power test results of the computing power device for different computing power characteristics (i.e., step B2). This can be performed as follows: the normalized value of the transmission and storage score of each test computing power task is calculated by a third preset function, and the average transmission and storage score of all test computing power tasks is determined based on the normalized value of the transmission and storage score of each test computing power task. The average transmission and storage score is then determined as the evaluation value of the computing power device under the transmission and storage characteristics.

[0123] In this embodiment, the performance evaluation value of the computing device under transmission and storage characteristics The calculation process is shown in formula (18).

[0124] (18)

[0125] in, To test the number of computing power tasks, ∈[1, ]. For the first The transmission and storage score of a type of computing power test task. For the first The normalization function for the transmission and storage score of the test computing power task is the third preset function mentioned above.

[0126] Therefore, based on the real-time operating status values ​​of computing devices under transmission and storage characteristics and operational evaluation values This allows us to obtain the recommendation coefficient for the computing power device under the transmission and storage characteristics. ,

[0127] .

[0128] In one implementation, based on the recommendation coefficients of computing devices under different computing power characteristics and the demand weights corresponding to different computing power requirements of computing tasks, the recommended computing power value for each computing device for a computing task is determined (i.e., step 206). This can be performed as follows: calculate the first product between the demand weight corresponding to the data processing demand and the recommendation coefficient corresponding to the data processing computing characteristics; calculate the second product between the demand weight corresponding to the image processing demand and the recommendation coefficient corresponding to the image processing computing characteristics; and calculate the third product between the demand weight corresponding to the resource quantity required by the task and the recommendation coefficient corresponding to the transmission and storage characteristics. The sum of the first, second, and third products is then calculated to obtain the recommended computing power value for the computing device for the computing task.

[0129] Optionally, the first k Recommended computing power value for individual computing devices The calculation process is shown in formula (19).

[0130] (19)

[0131] in, For the first k The demand weight corresponding to the data processing demand of each computing device. For the first k The recommendation coefficient corresponding to the data processing and computing characteristics of each computing device. For the first k The demand weight corresponding to the image processing demand of each computing device. For the first k Recommendation coefficients corresponding to the image processing computing characteristics of each computing device. For the first k The resource requirements of a computing device for a task, and their corresponding demand weights. For the first k The recommendation coefficient corresponding to the transmission and storage characteristics of each computing device.

[0132] In one implementation, before allocating computing tasks to target computing devices in each computing device for processing based on the computing power recommendation value (i.e., step 208), target computing devices that meet preset conditions can be determined from each computing device based on the computing power recommendation value.

[0133] Optionally, the preset condition can be one of the following: highest recommended computing power value, lowest recommended computing power value, second highest recommended computing power value, second lowest recommended computing power value, etc.

[0134] In this embodiment, after obtaining the recommended computing power value for each computing power device for a computing power task, the computing power devices can be sorted according to the recommended computing power value, thereby determining the target computing power device among the computing power devices based on preset conditions.

[0135] Figure 3 This is a flowchart illustrating a method for allocating computing power tasks according to another embodiment of this application. This method can be executed by an electronic device, which may include a server and / or a terminal device, such as a vehicle-mounted terminal or a mobile phone terminal. In other words, the method can be executed by software or hardware installed on the electronic device, and the method includes the following steps:

[0136] Step 301: Determine the demand weights corresponding to the different computing power demands of the computing power tasks to be allocated to the computing power devices.

[0137] The different computing power requirements include data processing requirements, image processing requirements, and resource requirements for the tasks. The requirement weights include weights for data processing computational characteristics, image processing computational characteristics, and transmission and storage characteristics.

[0138] Specifically, for each computing power requirement of a computing power task, the required value can be determined based on the computing power requirement, its corresponding standard value, standard function, and weight adjustment coefficient. The ratio of this required value to the total required value is then calculated to obtain the required weight for each computing power requirement. The total required value is determined based on the required value for each computing power requirement.

[0139] Step 302: For each computing power device, determine the real-time operating status value of the computing power device for different computing power characteristics based on the real-time resource occupancy information and device parameters of the computing power device.

[0140] The equipment parameters include one or more of the following: rated storage capacity, rated power load, rated cooling equipment load, rated computing capacity and storage impact coefficient corresponding to different computing power characteristics. Computing power characteristics include data processing computing characteristics, image processing computing characteristics, and transmission and storage characteristics.

[0141] Step 303: Based on the computing power test results of the computing power equipment for different computing power characteristics, determine the operation evaluation value of the computing power equipment for different computing power characteristics.

[0142] This involves testing the data processing, image processing, and transmission / storage characteristics of a computing device using a preset number of computing power tasks. The results will be used to obtain computing power test scores for different computing power characteristics. These scores can include data processing scores, image processing scores, and transmission / storage scores.

[0143] Step 304: Determine the recommendation coefficient of the computing power equipment under different computing power characteristics based on the real-time operating status value and operating evaluation value of the computing power equipment for different computing power characteristics.

[0144] Among them, the recommendation coefficient is negatively correlated with the real-time operating status value, and positively correlated with the operating evaluation value.

[0145] Step 305: Based on the recommendation coefficient of the computing power device under different computing power characteristics and the demand weight corresponding to the different computing power requirements of the computing power task, determine the recommended computing power value of each computing power device for the computing power task.

[0146] Step 306: Based on the recommended computing power value, the computing power tasks are allocated to the target computing power devices in each computing power device for processing.

[0147] The specific processes of steps 301 to 306 above have been described in detail in the above embodiments, and will not be repeated here.

[0148] By employing the technical solution of this application embodiment, during the allocation of computing power tasks, the demand weights corresponding to different computing power requirements of the computing power tasks to be allocated to computing power devices can be determined according to the computing power requirements of each computing power task. Different computing power requirements include data processing requirements, image processing requirements, and the amount of resources required by the task. Demand weights include data processing computing characteristic weights, image processing computing characteristic weights, and transmission and storage characteristic weights. Furthermore, for each computing power device, a recommendation coefficient for the computing power device under different computing power characteristics is determined based on the real-time resource occupancy information of the computing power device and the computing power test results for different computing power characteristics. Computing power characteristics include data processing computing characteristics, image processing computing characteristics, and transmission and storage characteristics. Therefore, based on the recommendation coefficients of the computing power devices under different computing power characteristics and the demand weights corresponding to different computing power requirements of the computing power tasks, a recommended computing power value for each computing power device for the computing power task is determined, and based on the recommended computing power value, the computing power task is allocated to the target computing power device among the various computing power devices for processing. Since demand weights reflect the emphasis of a computing task on the computing power requirements of each device, and recommendation coefficients reflect the computing power resources of computing devices under different computing power characteristics, this technical solution calculates the demand weights of computing tasks and the recommendation coefficients of computing devices to determine the target computing devices among all computing devices. This fully considers the impact of the computing power requirements of the computing tasks and the computing power resources of the devices on the selection of computing devices. Compared to the method of evenly allocating computing power tasks to each computing device in related technologies, this approach not only enables the target computing devices to better meet the computing power requirements of the computing tasks, achieving a more reasonable and accurate allocation of computing power tasks, but also improves the full utilization of the computing power resources of each computing device.

[0149] It should be noted that the computing power task allocation method provided in this application embodiment can be executed by a computing power task allocation device or a control module in the computing power task allocation device for executing the computing power task allocation method. This application embodiment uses the execution of the computing power task allocation method by a computing power task allocation device as an example to illustrate the computing power task allocation device provided in this application embodiment.

[0150] Figure 4 This is a schematic diagram of the structure of a computing task allocation device provided in an embodiment of this application. Figure 4 As shown, the computing power task allocation device includes: a first determining module 410, a second determining module 420, a third determining module 430, and a computing power task allocation module 440.

[0151] The first determining module 410 is used to determine the demand weights corresponding to different computing power requirements of computing power tasks based on the computing power requirements of the computing power tasks to be allocated to computing power devices; different computing power requirements include data processing demand, image processing demand, and resource requirements of the task; demand weights include data processing computing characteristic weights, image processing computing characteristic weights, and transmission and storage characteristic weights; the second determining module 420 is used to determine the recommendation coefficient of each computing power device under different computing power characteristics based on the real-time resource occupancy information of the computing power device and the computing power test results for different computing power characteristics; computing power characteristics include data processing computing characteristics, image processing computing characteristics, and transmission and storage characteristics; the third determining module 430 is used to determine the recommended computing power value for each computing power device for the computing power task based on the recommended coefficient of the computing power device under different computing power characteristics and the demand weights corresponding to the different computing power requirements of the computing power task; the computing power task allocation module 440 is used to allocate the computing power task to the target computing power device among the computing power devices for processing based on the recommended computing power value.

[0152] In one implementation, the second determining module 420 includes: a first determining unit, configured to determine, for each computing power device, a real-time operating status value for different computing power characteristics based on the real-time resource occupancy information and device parameters of the computing power device; a second determining unit, configured to determine an operating evaluation value for different computing power characteristics based on the computing power test results of the computing power device for different computing power characteristics; and a third determining unit, configured to determine a recommendation coefficient for the computing power device under different computing power characteristics based on the real-time operating status value and the operating evaluation value of the computing power device for different computing power characteristics; wherein the recommendation coefficient is negatively correlated with the real-time operating status value and positively correlated with the operating evaluation value.

[0153] In one implementation, real-time resource usage information includes data computation usage, transmission and storage usage, power load usage, and cooling equipment load usage; equipment parameters include rated storage capacity, rated power load, and rated cooling equipment load.

[0154] The first determining unit is specifically used for: determining the first constituent factor of the real-time operating status value based on the first ratio between the power load occupancy and the rated power load, the second ratio between the cooling equipment load occupancy and the rated cooling equipment load, and a preset logic function; obtaining the rated data computing load and data computing storage influence coefficient of the computing power equipment under the data processing computing characteristics; calculating the first difference between the rated data computing load and the data computing occupancy, and the second difference between the average rated data computing load of all computing power equipment and the average data computing occupancy of all computing power equipment; the average rated data computing load is determined based on the rated data computing load of each computing power equipment. The average computational occupancy is determined based on the data computational occupancy of each computing device. A second component of the real-time operating status value of the computing device under data processing computational characteristics is determined based on the data computational occupancy, the first difference, the second difference, and a preset exponential function. A third component of the real-time operating status value of the computing device under data processing computational characteristics is determined based on the transmission and storage occupancy, the average rated storage capacity of all computing devices, and the data computation and storage influence coefficient. The average rated storage capacity is determined based on the rated storage capacity of each computing device. The product of the first, second, and third components is calculated to obtain the real-time operating status value of the computing device under data processing computational characteristics.

[0155] In one implementation, real-time resource usage information also includes image processing usage.

[0156] The first determining unit is specifically used for: obtaining the rated image processing computation and image processing storage influence coefficient of the computing power device under the image processing computing characteristics; calculating the third difference between the rated image processing computation and the image processing usage, and the fourth difference between the average rated image processing computation and the average image processing usage of all computing power devices; the average rated image processing computation is determined based on the rated image processing computation of each computing power device, and the average image processing usage is determined based on the image processing usage of each computing power device; determining the fourth constituent factor of the real-time operating status value of the computing power device under the image processing computing characteristics based on the image processing usage, the third difference, the fourth difference, and a preset exponential function; determining the fifth constituent factor of the real-time operating status value of the computing power device under the image processing computing characteristics based on the transmission storage usage, the average rated storage of all computing power devices, and the image processing storage influence coefficient; and calculating the product of the first constituent factor, the fourth constituent factor, and the fifth constituent factor to obtain the real-time operating status value of the computing power device under the image processing computing characteristics.

[0157] In one implementation, the first determining unit is specifically used to: determine the sixth constituent factor of the real-time operating status value of the computing power device under the transmission and storage characteristics based on the transmission and storage occupancy and the average rated storage capacity of all computing power devices; and calculate the product of the first constituent factor and the sixth constituent factor to obtain the real-time operating status value of the computing power device under the transmission and storage characteristics.

[0158] In one implementation, the second determining module 420 further includes: a testing unit, used to test the data processing computing characteristics, image processing computing characteristics, and transmission and storage characteristics of the computing power device respectively through a preset number of test computing power tasks before determining the operating evaluation value of the computing power device for different computing power characteristics based on the computing power test results of the computing power device for different computing power characteristics, so as to obtain the computing power test results of the computing power device for different computing power characteristics; the computing power test results include data processing score, image processing score, and transmission and storage score.

[0159] In one implementation, the second determining unit is specifically used to: calculate the normalized value of the data processing score of each test computing power task using a first preset function; determine the average data processing score of all test computing power tasks based on the normalized value of the data processing score of each test computing power task; and determine the average data processing score as the operating evaluation value of the computing power device under the data processing computing characteristics.

[0160] In one implementation, the second determining unit is specifically used to: calculate the normalized value of the image processing score of each test computing power task using a second preset function; determine the average image processing score of all test computing power tasks based on the normalized value of the image processing score of each test computing power task; and determine the average image processing score as the operating evaluation value of the computing power device under the image processing computing characteristics.

[0161] In one implementation, the second determining unit is specifically used to: calculate the normalized value of the transmission and storage score of each test computing power task using a third preset function; determine the average transmission and storage score of all test computing power tasks based on the normalized value of the transmission and storage score of each test computing power task; and determine the average transmission and storage score as the operating evaluation value of the computing power device under the transmission and storage characteristics.

[0162] In one implementation, the first determining module 410 includes: a fourth determining unit, used to determine the demand value corresponding to each computing power demand for each computing power task, based on the computing power demand, the standard value, the standard function, and the weight adjustment coefficient corresponding to the computing power demand; a calculation unit, used to calculate the ratio of the demand value to the total demand value to obtain the demand weight corresponding to the computing power demand; the total demand value is determined based on the demand value of each computing power demand.

[0163] By employing the technical solution of this application embodiment, during the allocation of computing power tasks, the demand weights corresponding to different computing power requirements of the computing power tasks to be allocated to computing power devices can be determined according to the computing power requirements of each computing power task. Different computing power requirements include data processing requirements, image processing requirements, and the amount of resources required by the task. Demand weights include data processing computing characteristic weights, image processing computing characteristic weights, and transmission and storage characteristic weights. Furthermore, for each computing power device, a recommendation coefficient for the computing power device under different computing power characteristics is determined based on the real-time resource occupancy information of the computing power device and the computing power test results for different computing power characteristics. Computing power characteristics include data processing computing characteristics, image processing computing characteristics, and transmission and storage characteristics. Therefore, based on the recommendation coefficients of the computing power devices under different computing power characteristics and the demand weights corresponding to different computing power requirements of the computing power tasks, a recommended computing power value for each computing power device for the computing power task is determined, and based on the recommended computing power value, the computing power task is allocated to the target computing power device among the various computing power devices for processing. Since demand weights reflect the emphasis of a computing task on the computing power requirements of each device, and recommendation coefficients reflect the computing power resources of computing devices under different computing power characteristics, this technical solution calculates the demand weights of computing tasks and the recommendation coefficients of computing devices to determine the target computing devices among all computing devices. This fully considers the impact of the computing power requirements of the computing tasks and the computing power resources of the devices on the selection of computing devices. Compared to the method of evenly allocating computing power tasks to each computing device in related technologies, this approach not only enables the target computing devices to better meet the computing power requirements of the computing tasks, achieving a more reasonable and accurate allocation of computing power tasks, but also improves the full utilization of the computing power resources of each computing device.

[0164] The computing power task allocation device in this application embodiment can be a device, or a component, integrated circuit, or chip in a terminal. The device can be a mobile electronic device or a non-mobile electronic device. For example, mobile electronic devices can be mobile phones, tablets, laptops, PDAs, in-vehicle electronic devices, wearable devices, ultra-mobile personal computers (UMPCs), netbooks, or personal digital assistants (PDAs), etc., while non-mobile electronic devices can be servers, network attached storage (NAS), personal computers (PCs), televisions (TVs), ATMs, or self-service machines, etc. This application embodiment does not impose specific limitations.

[0165] The computing power task allocation device in this application embodiment can be a device with an operating system. This operating system can be Android, iOS, or other possible operating systems; this application embodiment does not specifically limit it.

[0166] The computing power task allocation device provided in this application embodiment can achieve Figures 2-3 The various processes implemented in the method embodiments are not described in detail here to avoid repetition.

[0167] Based on the same technical concept, embodiments of this application also provide an electronic device for performing the above-described method for allocating computing power tasks. Figure 5 This is a schematic diagram of the structure of an electronic device to implement various embodiments of this application. The electronic device can vary significantly due to differences in configuration or performance, and may include a processor 510, a communications interface 520, a memory 530, and a communication bus 540. The processor 510, communications interface 520, and memory 530 communicate with each other via the communication bus 540. The processor 510 can call a computer program stored in the memory 530 and executable on the processor 510 to perform the following steps:

[0168] Based on the computing power requirements of the computing power tasks to be allocated to computing power devices, the demand weights corresponding to the different computing power requirements of the computing power tasks are determined. These different computing power requirements include data processing requirements, image processing requirements, and the amount of resources required by the task. The demand weights include weights for data processing computing characteristics, image processing computing characteristics, and transmission and storage characteristics. For each computing power device, based on the real-time resource occupancy information of the computing power device and the computing power test results for different computing power characteristics, a recommendation coefficient for the computing power device under different computing power characteristics is determined. These computing power characteristics include data processing computing characteristics, image processing computing characteristics, and transmission and storage characteristics. Based on the recommendation coefficients of the computing power device under different computing power characteristics and the demand weights corresponding to the different computing power requirements of the computing power tasks, a recommended computing power value for each computing power device for the computing power task is determined. Based on the recommended computing power value, the computing power tasks are allocated to the target computing power devices within each computing power device for processing.

[0169] By employing the technical solution of this application embodiment, during the allocation of computing power tasks, the demand weights corresponding to different computing power requirements of the computing power tasks to be allocated to computing power devices can be determined according to the computing power requirements of each computing power task. Different computing power requirements include data processing requirements, image processing requirements, and the amount of resources required by the task. Demand weights include data processing computing characteristic weights, image processing computing characteristic weights, and transmission and storage characteristic weights. Furthermore, for each computing power device, a recommendation coefficient for the computing power device under different computing power characteristics is determined based on the real-time resource occupancy information of the computing power device and the computing power test results for different computing power characteristics. Computing power characteristics include data processing computing characteristics, image processing computing characteristics, and transmission and storage characteristics. Therefore, based on the recommendation coefficients of the computing power devices under different computing power characteristics and the demand weights corresponding to different computing power requirements of the computing power tasks, a recommended computing power value for each computing power device for the computing power task is determined, and based on the recommended computing power value, the computing power task is allocated to the target computing power device among the various computing power devices for processing. Since demand weights reflect the emphasis of a computing task on the computing power requirements of each device, and recommendation coefficients reflect the computing power resources of computing devices under different computing power characteristics, this technical solution calculates the demand weights of computing tasks and the recommendation coefficients of computing devices to determine the target computing devices among all computing devices. This fully considers the impact of the computing power requirements of the computing tasks and the computing power resources of the devices on the selection of computing devices. Compared to the method of evenly allocating computing power tasks to each computing device in related technologies, this approach not only enables the target computing devices to better meet the computing power requirements of the computing tasks, achieving a more reasonable and accurate allocation of computing power tasks, but also improves the full utilization of the computing power resources of each computing device.

[0170] The specific execution steps can be found in the various steps of the above-described embodiment of the computing power task allocation method, and can achieve the same technical effect. To avoid repetition, they will not be repeated here.

[0171] It should be noted that the electronic devices in the embodiments of this application include: servers, terminals, or other devices besides terminals.

[0172] The above electronic device structure does not constitute a limitation on the electronic device. An electronic device may include more or fewer components than illustrated, or combine certain components, or arrange them differently. For example, an input unit may include a Graphics Processing Unit (GPU) and a microphone, and a display unit may use a liquid crystal display (LCD), organic light-emitting diode (OLED), or other similar display panels. User input units include at least one of a touch panel and other input devices. A touch panel is also called a touchscreen. Other input devices may include, but are not limited to, physical keyboards, function keys (such as volume control buttons, power buttons, etc.), trackballs, mice, and joysticks, which will not be elaborated further here.

[0173] Memory can be used to store software programs and various data. Memory can primarily include a first storage area for storing programs or instructions and a second storage area for storing data. The first storage area can store the operating system, application programs or instructions required for at least one function (such as sound playback, image playback, etc.). Furthermore, memory can include volatile memory or non-volatile memory, or both. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (Synchlink DRAM, SLDRAM), and direct memory bus RAM (DRRAM).

[0174] The processor may include one or more processing units; optionally, the processor integrates an application processor and a modem processor, wherein the application processor mainly handles operations related to the operating system, user interface, and applications, while the modem processor mainly handles wireless communication signals, such as a baseband processor. It is understood that the aforementioned modem processor may also not be integrated into the processor.

[0175] This application also provides a computer-readable storage medium for storing computer-executable instructions. When these computer-executable instructions are executed by a processor, they implement the various processes of the above-described method for allocating computing power tasks and achieve the same technical effects. To avoid repetition, these will not be described again here.

[0176] The processor mentioned above is the processor in the electronic device described in the above embodiments. The computer-readable storage medium may be a computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0177] This application also provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the various processes of the above-described method for allocating computing power tasks and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0178] This application embodiment also provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement the various processes of the above-described computing power task allocation method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0179] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0180] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0181] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0182] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. A method for allocating computing power tasks, characterized in that, include: Based on the computing power requirements of each computing power task to be allocated to the computing power device, determine the demand weights corresponding to the different computing power requirements of the computing power task. The different computing power requirements include data processing requirements, image processing requirements, and resource requirements for tasks. The demand weights include data processing computational characteristic weights, image processing computational characteristic weights, and transmission and storage characteristic weights. For each computing device, a recommendation coefficient is determined based on the real-time resource usage information and computing power test results for different computing power characteristics. The computing power characteristics include data processing computing characteristics, image processing computing characteristics, and transmission and storage characteristics. The real-time resource usage information includes data computing usage, transmission and storage usage, power load usage, cooling equipment load usage, and image processing usage. The computing power test results for different computing power characteristics are obtained by testing the data processing computing characteristics, image processing computing characteristics, and transmission and storage characteristics of the computing device through a preset number of test computing power tasks. The computing power test results include data processing score, image processing score, and transmission and storage score. Based on the recommendation coefficient of the computing power device under different computing power characteristics and the demand weight corresponding to the different computing power requirements of the computing power task, the recommended computing power value of each computing power device for the computing power task is determined. Based on the recommended computing power value, the computing power tasks are allocated to the target computing power devices among the computing power devices for processing.

2. The method according to claim 1, characterized in that, For each computing power device, based on the real-time resource usage information of the computing power device and the computing power test results for different computing power characteristics, a recommendation coefficient for the computing power device under the different computing power characteristics is determined, including: For each computing power device, the real-time operating status value of the computing power device for the different computing power characteristics is determined based on the real-time resource occupancy information and device parameters of the computing power device; Based on the computing power test results of the computing power equipment for different computing power characteristics, determine the operation evaluation value of the computing power equipment for the different computing power characteristics; Based on the real-time operating status value and the operating evaluation value of the computing power device for different computing power characteristics, the recommendation coefficient of the computing power device under the different computing power characteristics is determined; wherein, the recommendation coefficient is negatively correlated with the real-time operating status value and positively correlated with the operating evaluation value.

3. The method according to claim 2, characterized in that, The real-time resource usage information includes data computing usage, transmission and storage usage, power load usage, and cooling equipment load usage; the equipment parameters include rated storage capacity, rated power load, and rated cooling equipment load. The step of determining the real-time operating status value of the computing power device for different computing power characteristics based on the real-time resource occupancy information and device parameters of the computing power device includes: The first constituent factor of the real-time operating status value is determined based on the first ratio between the power load occupancy and the rated power load, the second ratio between the refrigeration equipment load occupancy and the rated load of the refrigeration equipment, and a preset logic function. Obtain the rated computational load and data computation storage impact coefficient of the computing power device under the data processing and computing characteristics; Calculate a first difference between the rated computing load of the data computing and the data computing usage, and a second difference between the average rated computing load of all computing devices and the average data computing usage of all computing devices; the average rated computing load is determined based on the rated computing load of each computing device, and the average data computing usage is determined based on the data computing usage of each computing device. Based on the data calculation of occupancy, the first difference, the second difference, and a preset exponential function, a second constituent factor is determined for the real-time operating status value of the computing power device under the data processing and computing characteristics. The third component of the real-time operating status value of the computing power device under the data processing and computing characteristics is determined based on the transmission and storage occupancy, the average rated storage capacity of all computing power devices, and the data calculation and storage influence coefficient; the average rated storage capacity is determined based on the rated storage capacity of each computing power device. The product of the first constituent factor, the second constituent factor, and the third constituent factor is calculated to obtain the real-time operating status value of the computing power device under the data processing and computing characteristics.

4. The method according to claim 3, characterized in that, The real-time resource usage information also includes image processing usage; The step of determining the real-time operating status value of the computing power device for different computing power characteristics based on the real-time resource occupancy information and device parameters of the computing power device includes: Obtain the rated computational load and image processing storage impact coefficient of the computing power device under the image processing computational characteristics; Calculate the third difference between the rated image processing workload and the image processing usage, and the fourth difference between the average rated image processing workload of all computing devices and the average image processing usage of all computing devices; the average rated image processing workload is determined based on the rated image processing workload of each computing device, and the average image processing usage is determined based on the image processing usage of each computing device. Based on the image processing occupancy, the third difference, the fourth difference, and the preset exponential function, determine the fourth constituent factor of the real-time operating status value of the computing power device under the image processing computing characteristics; Based on the transmission and storage occupancy, the average rated storage capacity of all computing devices, and the image processing storage influence coefficient, the fifth constituent factor of the real-time operating status value of the computing device under the image processing computing characteristics is determined. The product of the first constituent factor, the fourth constituent factor, and the fifth constituent factor is calculated to obtain the real-time operating status value of the computing power device under the image processing computing characteristics.

5. The method according to claim 3, characterized in that, The step of determining the real-time operating status value of the computing power device for different computing power characteristics based on the real-time resource occupancy information and device parameters of the computing power device includes: Based on the transmission and storage occupancy and the average rated storage capacity of all computing devices, determine the sixth component factor of the real-time operating status value of the computing device under the transmission and storage characteristics. The product of the first constituent factor and the sixth constituent factor is calculated to obtain the real-time operating status value of the computing power device under the transmission and storage characteristics.

6. The method according to claim 2, characterized in that, The step of determining the operational evaluation value of the computing power device for different computing power characteristics based on the computing power test results of the computing power device for different computing power characteristics includes: The normalized value of the data processing score for each test computing power task is calculated using the first preset function. Based on the normalized value of the data processing score of each test computing power task, determine the mean data processing score of all test computing power tasks; The average data processing score is determined as the performance evaluation value of the computing power device under the data processing and computing characteristics.

7. The method according to claim 2, characterized in that, The step of determining the operational evaluation value of the computing power device for different computing power characteristics based on the computing power test results of the computing power device for different computing power characteristics includes: The normalized value of the image processing score for each test computing power task is calculated using the second preset function. The mean image processing score of all test computing power tasks is determined based on the normalized value of the image processing score of each test computing power task. The average image processing score is determined as the performance evaluation value of the computing power device under the image processing computing characteristics.

8. The method according to claim 2, characterized in that, The step of determining the operational evaluation value of the computing power device for different computing power characteristics based on the computing power test results of the computing power device for different computing power characteristics includes: The normalized value of the transmission and storage score for each test computing power task is calculated using the third preset function. The mean transmission and storage score of all test computing power tasks is determined based on the normalized value of the transmission and storage score of each test computing power task. The average transmission and storage score is determined as the performance evaluation value of the computing power device under the transmission and storage characteristics.

9. The method according to claim 1, characterized in that, The step of determining the demand weights corresponding to the different computing power demands of the computing power tasks to be allocated to the computing power devices includes: For each computing power requirement of the computing power task, the requirement value corresponding to the computing power requirement is determined based on the computing power requirement, the standard value, the standard function and the weight adjustment coefficient corresponding to the computing power requirement; The ratio of the demand value to the total demand value is calculated to obtain the demand weight corresponding to the computing power demand; the total demand value is determined based on the demand value of each computing power demand.

10. A computing power task allocation device, characterized in that, include: The first determining module is used to determine the demand weights corresponding to the different computing power demands of the computing power tasks to be allocated to the computing power devices, based on the computing power demands of each computing power task. The different computing power requirements include data processing requirements, image processing requirements, and resource requirements for tasks. The demand weights include data processing computational characteristic weights, image processing computational characteristic weights, and transmission and storage characteristic weights. The second determining module is used to determine, for each computing power device, a recommendation coefficient for the computing power device under different computing power characteristics based on the real-time resource usage information of the computing power device and the computing power test results for different computing power characteristics; the computing power characteristics include data processing computing characteristics, image processing computing characteristics, and transmission and storage characteristics; the real-time resource usage information includes data computing usage, transmission and storage usage, power load usage, cooling equipment load usage, and image processing usage; the computing power test results for different computing power characteristics are obtained by testing the data processing computing characteristics, image processing computing characteristics, and transmission and storage characteristics of the computing power device through a preset number of test computing power tasks; the computing power test results include data processing score, image processing score, and transmission and storage score. The third determining module is used to determine the recommended computing power value for each computing power device for the computing power task based on the recommendation coefficient of the computing power device under the different computing power characteristics and the demand weight corresponding to the different computing power requirements of the computing power task. The computing power task allocation module is used to allocate the computing power tasks to the target computing power devices among the computing power devices for processing based on the computing power recommendation value.

11. An electronic device, characterized in that, include: processor; as well as A memory configured to store computer-executable instructions configured to be executed by the processor to implement the computing task allocation method as described in any one of claims 1-9.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store computer-executable instructions, which, when executed by a processor, implement the computing power task allocation method as described in any one of claims 1-9.

13. A computer program product, characterized in that, It includes a computer program that, when executed by a processor, implements the method for allocating computing power tasks as described in any one of claims 1-9.

Images