Allocation method and device of computing power task

Abstract

The invention discloses a computing power task allocation method and device, belongs to the technical field of computers, and is used for solving the problem of unreasonable allocation of computing power tasks in related technologies. The method comprises the following steps: according to each computing power demand of a computing power task to be distributed to computing power equipment, determining demand weights respectively corresponding to different computing power demands of the computing power task; for each computing power device, according to the real-time resource occupation information of the computing power device and the computing power test results for different computing power characteristics, determining recommendation coefficients of the computing power device under different computing power characteristics; determining a computing power recommendation value of each computing power device for the computing power task according to the recommendation coefficients of the computing power devices under different computing power characteristics and demand weights respectively corresponding to different computing power demands of the computing power task; and based on the computing power recommendation value, allocating the computing power task to a target computing power device in the computing power devices for processing. According to the technical scheme, the computing power tasks are reasonably and accurately distributed.

Description

Technical Field

[0001] The present application belongs to the field of computer technology, and specifically relates to a method and device for allocating computing tasks. Background Art

[0002] With the development of the Internet of Things, industrial automation, smart transportation, smart homes, virtual reality and other fields, the amount of data continues to grow, and the demand for data processing and analysis is also increasing. Although traditional cloud computing centers can provide powerful computing power, the delay in data transmission and processing is large, and they cannot meet 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 edge of the network and directly connected to the terminal device, which can quickly process and analyze data and reduce the delay and cost of data transmission. At the same time, since the data is processed locally, the security and privacy protection of the data are also increased. However, how to allocate computing power tasks to each computing power device deployed on the edge side has become a technical problem that needs to be solved in this field.

[0003] In the related art, computing tasks are generally allocated to each computing device in a balanced manner according to the real-time status of each computing device. The real-time status of each computing device is obtained by comprehensive analysis based on its computing power usage and its own specification parameters. However, for different computing tasks, the direction of their demand is different. Therefore, if the same allocation method is used for all, the demand characteristics of different tasks cannot be met, and the computing resources of each computing device cannot be maximized. Summary of the invention

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

[0005] In a first aspect, an embodiment of the present application provides a method for allocating computing power tasks, comprising: determining, according to the computing power requirements of the computing power tasks to be allocated to the computing power devices, the demand weights corresponding to the different computing power requirements of the computing power tasks; the different computing power requirements include data processing requirements, image processing requirements and task resource requirements; the demand weights include data processing computing characteristics weights, image processing computing characteristics weights and transmission storage characteristics weights; for each of the computing power devices, determining the recommended coefficient of the computing power device under the different computing power characteristics according to 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 storage characteristics; according to the recommended coefficient of the computing power device under the different computing power characteristics and the demand weights corresponding to the different computing power requirements of the computing power tasks, determining the computing power recommended value of each computing power device for the computing power task; based on the computing power recommended value, allocating the computing power task to the target computing power device in each of the computing power devices for processing. In a second aspect, an embodiment of the present application provides a computing power task allocation device, comprising: a first determination module, for determining, according to each computing power requirement of the computing power task to be allocated to the computing power device, 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 task required resources; the demand weights include data processing computing characteristics weights, image processing computing characteristics weights and transmission storage characteristics weights; a second determination module, for determining, for each of the computing power devices, the recommended coefficient of the computing power device under the different computing power characteristics according to 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 storage characteristics; a third determination module, for determining the computing power recommended value of each computing power device for the computing power task according to the recommended coefficient of the computing power device under the different computing power characteristics and the demand weights corresponding to the different computing power requirements of the computing power task; a computing power task allocation module, for allocating the computing power task to the target computing power device in each of the computing power devices for processing based on the computing power recommendation value.

[0006] In a third aspect, an embodiment of the present application provides an electronic device comprising a processor; and a memory arranged to store computer-executable instructions, wherein the computer-executable instructions are configured to be executed by the processor, and the computer-executable instructions are executed by the processor to implement the steps of the method for allocating computing power tasks as described in the first aspect.

[0007] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, which is used to store computer-executable instructions. When the computer-executable instructions are executed by a processor, the steps of the method for allocating computing power tasks as described in the first aspect are implemented.

[0008] In a fifth aspect, an embodiment of the present application provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the method for allocating computing power tasks as described in the first aspect.

[0009] In a sixth aspect, an embodiment of the present application provides a chip, comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run executable instructions to implement the steps of the method for allocating computing power tasks as described in the first aspect.

[0010] By adopting the technical solution of the embodiment of the present application, in the process of allocating computing power tasks, the demand weights corresponding to the different computing power requirements of the computing power tasks to be allocated to the computing power equipment can be determined. Different computing power requirements include data processing requirements, image processing requirements, and task required resources. The demand weights include data processing computing characteristics weights, image processing computing characteristics weights, and transmission storage characteristics weights. And for each computing power device, according to the real-time resource occupancy information of the computing power device and the computing power test results for different computing power characteristics, the recommended coefficient of the computing power device under different computing power characteristics is determined. The computing power characteristics include data processing computing characteristics, image processing computing characteristics, and transmission storage characteristics. Thus, according to 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 tasks, the computing power recommended value of each computing power device for the computing power task is determined, and based on the computing power recommended value, the computing power task is allocated to the target computing power device in each computing power device for processing. Since the demand weight can reflect the emphasis of the computing task on each computing demand, the recommendation coefficient can reflect the computing resource situation of the computing device under different computing characteristics (for example, under a certain computing characteristic, the computing resource of the computing device is relatively large, so the recommendation coefficient of the computing device under this computing characteristic is relatively high). Therefore, this technical solution calculates the demand weight of the computing task and the recommendation coefficient of the computing device to determine the target computing device among the computing devices, and fully considers the influence of the computing demand of the computing task and the computing resources of the computing device on the selection of the computing device. Compared with the method of evenly allocating computing tasks to each computing device in the related technology, it not only enables the target computing device to better meet the computing demand of the computing task, realizes a more reasonable and accurate allocation of computing tasks, but also improves the adequacy of the computing resource utilization of each computing device. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 It is a schematic block diagram of a computing task allocation system provided in an embodiment of the present application; Figure 2 It is a flowchart of a method for allocating computing tasks provided in an embodiment of the present application; Figure 3 It is a flowchart of a method for allocating computing tasks provided by another embodiment of the present application; Figure 4 It is a structural diagram of a computing task allocation device provided in an embodiment of the present application; Figure 5 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0012] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0013] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0014] The following is a detailed description of the method and device for allocating computing tasks provided by the embodiments of the present application through specific embodiments and their application scenarios in conjunction with the accompanying drawings.

[0015] Figure 1 is a schematic block diagram of a computing task allocation system provided in an embodiment of the present application, such as Figure 1 As shown, the computing task allocation system includes a task analysis unit 110, a computing device monitoring unit 120 and an operation and maintenance management center 130. The task analysis unit 110 and the computing device monitoring unit 120 are respectively connected to the operation and maintenance management center 130 for communication.

[0016] 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 equipment, 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 task required resources. The demand weights include data processing computing characteristic weights, image processing computing characteristic weights, and transmission storage characteristic weights.

[0017] The computing power equipment monitoring unit 120 is used to determine the recommended coefficient of the computing power equipment under different computing power characteristics for each computing power equipment according to the real-time resource occupancy information of the computing power equipment and the computing power test results for different computing power characteristics, and send the recommended coefficient to the operation and maintenance management center 130. The computing power characteristics include data processing computing characteristics, image processing computing characteristics and transmission storage characteristics.

[0018] The operation and maintenance management center 130 is used to determine the recommended computing power value of each computing device for computing tasks based on the recommended coefficient of the computing device under different computing power characteristics and the demand weights corresponding to the different computing power requirements of the computing tasks, and based on the recommended computing power value, allocate the computing power tasks to the target computing power devices in each computing power device for processing.

[0019] The following describes in detail the method for allocating computing power tasks applied to the computing power task allocation system. Figure 2 A method for allocating computing tasks provided by an embodiment of the present application is shown. The method can be executed by an electronic device, and the electronic device may include: a server and / or a terminal device, wherein the terminal device may be, for example, a vehicle-mounted terminal or a mobile phone terminal. In other words, the method can be executed by software or hardware installed in the electronic device, and the method includes the following steps: Step 202: Determine the demand weights corresponding to the different computing power demands of the computing power tasks according to the computing power demands of the computing power tasks to be allocated to the computing power equipment.

[0020] Among them, the number of computing power devices is multiple. Optionally, the computing power devices can be computing power devices distributedly deployed on the edge side. Different computing power requirements include data processing requirements, image processing requirements, and task resource requirements. The demand weights include data processing computing feature weights, image processing computing feature weights, and transmission storage feature weights. In this embodiment, the demand weights can reflect the emphasis of the computing power task on each computing power requirement, that is, which aspect of computing power the computing power task requires more.

[0021] Optionally, the data processing demand can be used to characterize information such as the computing power model information required for data processing, the expected completion time of data processing, and the computing power required for data processing. The image processing demand can be used to characterize information such as the computing power model information required for image processing, the expected completion time of image processing, and the computing power required for image processing. The task required resources can be used to characterize information such as the computing power model information required for the computing power task, the expected completion time of the computing power task, and the total amount of computing power required for the computing power task.

[0022] Step 204, for each computing power device, determine the recommended coefficient of the computing power device under different computing power characteristics according to the real-time resource occupancy information of the computing power device and the computing power test results for different computing power characteristics.

[0023] The computing power characteristics include data processing computing characteristics, image processing computing characteristics, and transmission storage characteristics. In this embodiment, the recommended coefficient can reflect the computing power resource situation of the computing power device under different computing power characteristics. For example, under a certain computing power characteristic, the computing power resource of the computing power device is relatively large, so the recommended coefficient of the computing power device under the computing power characteristic is relatively high.

[0024] Step 206, determining 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 different computing power characteristics and the demand weights corresponding to the different computing power requirements of the computing power task.

[0025] Step 208, based on the recommended computing power value, the computing power task is allocated to the target computing power device among the computing power devices for processing.

[0026] By adopting the technical solution of the embodiment of the present application, in the process of allocating computing power tasks, the demand weights corresponding to the different computing power requirements of the computing power tasks to be allocated to the computing power equipment can be determined. Different computing power requirements include data processing requirements, image processing requirements, and task required resources. The demand weights include data processing computing characteristics weights, image processing computing characteristics weights, and transmission storage characteristics weights. And for each computing power device, according to the real-time resource occupancy information of the computing power device and the computing power test results for different computing power characteristics, the recommended coefficient of the computing power device under different computing power characteristics is determined. The computing power characteristics include data processing computing characteristics, image processing computing characteristics, and transmission storage characteristics. Thus, according to 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 tasks, the computing power recommended value of each computing power device for the computing power task is determined, and based on the computing power recommended value, the computing power task is allocated to the target computing power device in each computing power device for processing. Since the demand weight can reflect the emphasis of the computing task on each computing demand, the recommendation coefficient can reflect the computing resource situation of the computing equipment under different computing characteristics. Therefore, this technical solution calculates the demand weight of the computing task and the recommendation coefficient of the computing equipment to determine the target computing equipment in each computing equipment, and fully considers the influence of the computing demand of the computing task and the computing resources of the computing equipment on the selection of the computing equipment. Compared with the method of evenly allocating computing tasks to each computing equipment in the related technology, it not only enables the target computing equipment to better meet the computing demand of the computing task, realizes a more reasonable and accurate allocation of computing tasks, but also improves the adequacy of the computing resources of each computing equipment.

[0027] In one implementation, according to the computing power requirements of the computing power tasks to be allocated to the computing power device, the demand weights corresponding to the different computing power requirements of the computing power tasks are determined (i.e., step 202), which can be performed as follows: Steps A1-A2: Step A1, for each computing power requirement of the computing power task, determine the demand value corresponding to the computing power requirement according to the computing power requirement, and the standard value, standard function and weight adjustment coefficient corresponding to the computing power requirement.

[0028] 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.

[0029] Among them, the total demand value is determined based on the demand value of each computing power requirement.

[0030] In this embodiment, by determining the demand weights corresponding to the different computing power requirements of the computing power tasks, since the demand weights can reflect the emphasis of the computing power tasks on each computing power requirement, a data basis is provided for the reasonable allocation of computing power tasks.

[0031] In one implementation, step A1 may be specifically performed as the following steps A11 to A13: Step A11, for the data processing demand of the computing task, calculate the ratio between the data processing demand and the function value of the standard function corresponding to the data processing demand, and calculate the product of this ratio and the first weight adjustment coefficient corresponding to the data processing demand. Calculate the ratio between the data processing demand and the standard value corresponding to the data processing demand, and calculate the product of this ratio and the second weight adjustment coefficient corresponding to the data processing demand. Calculate the sum of these two products to obtain the demand value corresponding to the data processing demand.

[0032] The function value of the standard function corresponding to the data processing demand is obtained by taking the value of the resource required for the task by the standard function corresponding to the data processing demand.

[0033] Optionally, the demand value corresponding to the data processing demand can be represented by the following expression (1): , (1) in, The data processing demand, is the amount of resources required for the task, is the standard function corresponding to the data processing demand, is the standard value corresponding to the data processing demand, x1 is the first weight adjustment coefficient corresponding to the data processing demand, x2 is the second weight adjustment coefficient corresponding to the data processing demand.

[0034] Step A12, for the graphics processing demand of the computing task, calculate the ratio between the graphics processing demand and the function value of the standard function corresponding to the graphics processing demand, and calculate the product of this ratio and the first weight adjustment coefficient corresponding to the graphics processing demand. Calculate the ratio between the graphics processing demand and the standard value corresponding to the graphics processing demand, and calculate the product of this ratio and the second weight adjustment coefficient corresponding to the graphics processing demand. Calculate the sum of these two products to obtain the demand value corresponding to the graphics processing demand.

[0035] The function value of the standard function corresponding to the graphics processing demand is obtained by taking the value of the resource required for the task by the standard function corresponding to the graphics processing demand.

[0036] Optionally, the demand value corresponding to the graphics processing demand can be represented by the following expression (2): , (2) in, For graphics processing requirements, is the standard function corresponding to the graphics processing demand, is the standard value corresponding to the graphics processing demand, y1 is the first weight adjustment coefficient corresponding to the graphics processing demand, y2 is a second weight adjustment coefficient corresponding to the graphics processing demand.

[0037] Step A13, for the amount of resources required for the computing task, calculate the ratio between the amount of resources required for the task and the standard value corresponding to the amount of resources required for the task, and calculate the product of this ratio and the weight adjustment coefficient corresponding to the amount of resources required for the task.

[0038] Optionally, the demand value corresponding to the amount of resources required for the task can be represented by the following expression (3): , (3) in, is 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.

[0039] In one implementation, the sum of the above expressions (1) to (3) can be calculated to obtain the total demand value corresponding to all computing power requirements of the computing task, and then the demand weight corresponding to each computing power requirement can be obtained based on the ratio of the demand value of each computing power requirement to the total demand value. Specifically, the demand weight of the data processing demand , the demand weight of image processing demand and the demand weight of the amount of resources required for the task .

[0040] Among them, the demand weight of data processing demand The calculation process is shown in formula (4), and the demand weight of image processing demand is The calculation process is shown in formula (5), and the required resource weight of the task is The calculation process of is shown in formula (6).

[0041] . (4) . (5) . (6) In one implementation, for each computing device, according to the real-time resource occupancy information of the computing device and the computing test results for different computing characteristics, the recommended coefficient of the computing device under different computing characteristics (i.e., step 204) is determined, which can be performed as follows: Steps B1 to B3: Step B1, for each computing power device, determine the real-time operating status value of the computing power device for different computing power characteristics according to the real-time resource occupancy information and device parameters of the computing power device.

[0042] The equipment parameters may include one or more of the following: rated storage capacity, rated power load, rated load of refrigeration equipment, rated computing capacity corresponding to different computing power characteristics, and storage influence coefficient.

[0043] Step B2: determining the operation evaluation value of the computing power equipment for different computing power characteristics according to the computing power test results of the computing power equipment for different computing power characteristics.

[0044] Step B3, according to the real-time operation status value and operation evaluation value of the computing power equipment for different computing power characteristics, determine the recommended coefficient of the computing power equipment under different computing power characteristics. Among them, the recommended coefficient is negatively correlated with the real-time operation status value, and the recommended coefficient is positively correlated with the operation evaluation value.

[0045] In this embodiment, the real-time operating status value of the computing power device for different computing power characteristics is determined based on the real-time resource occupancy information and device parameters of the computing power device, so that the computing power occupancy corresponding to different computing power characteristics in the computing power device can be evaluated. According to the computing power test results, the operation evaluation value of the computing power device for different computing power characteristics is determined, so that the computing power execution capability of the computing power device for different computing power characteristics can be evaluated. By comprehensively considering the computing power occupancy and computing power execution capability, the recommended coefficient of the computing power device under different computing power characteristics is obtained, so that the recommended coefficient can reflect the computing power resource situation of the computing power device under different computing power characteristics, thereby providing a data basis for the reasonable allocation of computing power tasks.

[0046] In one implementation, the real-time resource occupancy information includes data computing occupancy, transmission storage occupancy, power load occupancy and refrigeration equipment load occupancy. Equipment parameters include rated storage capacity, power rated load and refrigeration equipment rated load.

[0047] In this embodiment, according to the real-time resource occupancy information and device parameters of the computing power device, the real-time operation status value of the computing power device for different computing power characteristics (ie, step B1) is determined, which can be performed as follows: steps C1 to C6: Step C1, determining a first component factor of the real-time operation status value according to a first ratio between the power load occupancy and the power rated load, a second ratio between the refrigeration equipment load occupancy and the refrigeration equipment rated load, and a preset logic function.

[0048] Optionally, the preset logic function can be ,when When it is greater than the preset rated value, ;otherwise, In the process of determining the first component factor of the real-time operating status 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 component factor can be represented by the following expression (7): , (7) in, is the power load occupancy, is the rated load of electricity, is the refrigeration equipment load occupancy, is the rated load of the refrigeration equipment. In this embodiment, the preset rated value may be 2, that is, the power load occupancy is consistent with the power rated load, and the refrigeration equipment load occupancy is consistent with the refrigeration equipment rated load. If it is greater than the preset rated value, it means that the power load occupancy and / or the refrigeration equipment load occupancy exceeds the corresponding rated load. In this case, the computing power device is overloaded. At this time, the computing power device cannot provide computing power for the computing power tasks to be allocated. Therefore, it is meaningless to analyze the real-time operating status value of the computing power device. The value is 0. If it is less than the preset rated value, it means that the power load occupancy and / or the refrigeration equipment load occupancy do not exceed their corresponding rated loads. At this time, the computing power device can provide computing power for the computing power tasks to be allocated. The value is 1.

[0049] Step C2, obtaining the data calculation rated amount and data calculation storage influence coefficient of the computing power equipment under the data processing calculation characteristics.

[0050] Optionally, the data calculation rated amount and the data calculation storage influence coefficient may be device parameters of the computing power device.

[0051] Step C3, respectively calculate the first difference between the rated amount of data calculation and the amount of data calculation occupied, and the second difference between the average of the rated amount of data calculation of all computing power devices and the average of the amount of data calculation occupied by all computing power devices.

[0052] Among them, the average value of the rated amount of data calculation is determined based on the rated amount of data calculation of each computing power device, and the average value of the data calculation occupancy is determined based on the data calculation occupancy of each computing power device.

[0053] Step C4, determining a second constituent factor of the real-time operating status value of the computing power device under the data processing calculation characteristics according to the data calculation occupancy, the first difference, the second difference and the preset exponential function.

[0054] Optionally, the preset exponential function may be a natural constant eAn exponential function with base , the exponent of which is composed of the data calculation occupancy, the first difference, and the second difference. Specifically, the ratios between the data calculation occupancy and the first difference and the second difference can be calculated respectively, and then the product of the two ratios can be calculated, and the square root of the product is used as the exponent of the function. Therefore, the second component factor can be represented by the following expression (8): , (8) in, Calculate the occupancy for the data, Calculate the average occupancy of all computing devices. Calculate the nominal amount for the data, Calculate the average rated computing capacity for the data of all computing power devices.

[0055] Step C5, determining the third constituent factor of the real-time operating status value of the computing power device under the data processing calculation characteristics according to the transmission storage occupancy, the average rated storage capacity of all computing power devices and the data calculation storage impact coefficient.

[0056] The average rated storage capacity is determined based on the rated storage capacity of each computing device.

[0057] Optionally, the ratio between the transmission storage usage and the average of the rated storage of all computing devices can be calculated, and then the product of the data computing storage impact coefficient and this ratio can be calculated to obtain the third component factor. Therefore, the third component factor can be represented by the following expression (9): , (9) in, Calculate the storage impact coefficient for the data, for t The amount of storage used for transmission at a point in time, It is the average rated storage capacity of all computing devices.

[0058] Step C6, calculate the product of the first component factor, the second component factor and the third component factor to obtain the real-time operating status value of the computing power device under the data processing calculation characteristics.

[0059] In this embodiment, the real-time operating status value of the computing power device under the data processing calculation characteristics can be obtained by calculating the product of the above expressions (7) to (9): . The calculation process of is shown in formula (10). . (10) In one implementation, the real-time resource occupancy information may include the image processing occupancy. In this embodiment, according to the real-time resource occupancy information and device parameters of the computing power device, the real-time operation status value of the computing power device for different computing power characteristics (i.e., step B1) can be determined, which can be performed as follows: step D1-step D5: Step D1, obtaining the image processing rated computing amount and the image processing storage influence coefficient of the computing power device under the image processing computing characteristics.

[0060] Optionally, the image processing rated computational effort and the image processing storage influence coefficient may be device parameters of the computing power device.

[0061] Step D2, respectively calculate the third difference between the rated image processing amount and the image processing amount occupied, and the fourth difference between the average of the rated image processing amount of all computing power devices and the average of the image processing amount occupied by all computing power devices.

[0062] Among them, the average image processing rated computing capacity is determined based on the image processing rated computing capacity of each computing power device, and the average image processing occupancy is determined based on the image processing occupancy of each computing power device.

[0063] Step D3, determining a fourth constituent factor of the real-time operating status value of the computing power device under the image processing calculation characteristics according to the image processing occupancy, the third difference, the fourth difference and the preset exponential function.

[0064] Optionally, the preset exponential function may be a natural constant e An exponential function with α as the base, the exponent of which is composed of the image processing occupancy, the third difference, and the fourth difference. Specifically, the ratios of the image processing occupancy to the third difference and the fourth difference can be calculated respectively, and then the product of the two ratios can be calculated, and the square root of the product is used as the exponent of the function. Therefore, the fourth component factor can be represented by the following expression (11): , (11) in, is the image processing usage, is the average image processing usage of all computing devices, The rated amount of image processing, It is the average image processing rated computing workload of all computing power devices.

[0065] Step D4, determining the fifth constituent factor of the real-time operating status value of the computing power device under the image processing calculation characteristics based on the transmission storage occupancy, the average rated storage capacity of all computing power devices and the image processing storage impact coefficient.

[0066] Optionally, the ratio between the transmission storage usage and the average of the rated storage of all computing devices can be calculated, and then the product of the image processing storage impact coefficient and this ratio can be calculated to obtain the fifth component factor. Therefore, the fifth component factor can be represented by the following expression (12): , (12) in, Stores influence coefficients for image processing.

[0067] Step D5, calculate the product of the first component factor, the fourth component factor and the fifth component factor to obtain the real-time operating status value of the computing power device under the image processing calculation characteristics.

[0068] In this embodiment, the real-time operating status value of the computing power device under the image processing computing characteristics can be obtained by calculating the product of the above expression (7), expression (11) and expression (12): . The calculation process of is shown in formula (13). . (13) In one implementation, according to the real-time resource occupancy information and device parameters of the computing power device, the real-time operation status value of the computing power device for different computing power characteristics (i.e., step B1) can be determined, which can be performed as follows: step E1-step E2: Step E1, determining the sixth component factor of the real-time operating status value of the computing power device under the transmission storage characteristics according to the transmission storage occupancy and the average of the rated storage capacity of all computing power devices.

[0069] In this embodiment, the sixth component factor can be represented by the following expression (14): . (14) Step E2, calculate the product of the first component factor and the sixth component factor to obtain the real-time operating status value of the computing power device under the transmission and storage characteristics.

[0070] In this embodiment, the real-time operating status value of the computing power device under the transmission storage characteristics can be obtained by calculating the product of the above expression (7) and expression (14): . The calculation process of is shown in formula (15). . (15) In one implementation, based on the computing power test results of the computing power device for different computing power characteristics, before determining the operation evaluation value of the computing power device for different computing power characteristics (i.e., step B2), a preset number of test computing power tasks can be used to test the data processing computing characteristics, image processing computing characteristics, and transmission and storage characteristics of the computing power device, respectively, to obtain the computing power test results of the computing power device for different computing power characteristics.

[0071] The computing power test results may include data processing scores, image processing scores, and transmission and storage scores. In this embodiment, the computing power test results of the computing power device under different computing power characteristics can be comprehensively analyzed by allowing the computing power device to process multiple test computing power tasks and according to the processing conditions of the computing power device for the multiple test computing power tasks (such as processing speed, model used, processing time, etc.).

[0072] Optionally, the data processing score can be composed of factors such as the data processing speed score, the model score used, and the processing time score in a preset ratio. The image processing score can be composed of factors such as the image processing speed score, the model score used, and the processing time score in a preset ratio. The transmission storage score can be composed of factors such as the transmission storage speed score, the model score used, and the processing time score in a preset ratio. The process of obtaining each score according to the test computing power task is not elaborated in detail in the embodiment of this application. In actual applications, the corresponding score can be determined based on the interval to which the actual processing situation belongs by setting the processing situation interval corresponding to each score.

[0073] In one implementation, based on the computing power test results of the computing power device for different computing power characteristics, the operation evaluation value of the computing power device for different computing power characteristics (i.e., step B2) can be determined, which can be executed as follows: using a first preset function, respectively calculating the normalized value of the data processing score of each test computing power task, thereby determining 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 determining the average data processing score as the operation evaluation value of the computing power device under the data processing computing characteristics.

[0074] In this embodiment, the operation evaluation value of the computing power equipment under the data processing calculation characteristics is The calculation process of is shown in formula (16). , (16) in, To test the number of computing tasks, ∈[1, ]. For the The data processing score of the test computing task. For the A normalized function of the test computing power task data processing score, namely the first preset function mentioned above.

[0075] Therefore, according to the real-time operating status value of the computing power equipment under the data processing calculation characteristics and operation evaluation value , we can get the recommended coefficient of the computing power equipment under the data processing calculation characteristics , .

[0076] In one implementation, based on the computing power test results of the computing power device for different computing power characteristics, the operation evaluation value of the computing power device for different computing power characteristics (i.e., step B2) can be determined, which can be executed as follows: through a second preset function, the normalized value of the image processing score of each test computing power task is calculated respectively, and then according to the normalized value of the image processing score of each test computing power task, the average image processing score of all test computing power tasks is determined, and the average image processing score is determined as the operation evaluation value of the computing power device under the image processing computing characteristics.

[0077] In this embodiment, the operation evaluation value of the computing power device under the image processing computing characteristics is The calculation process of is shown in formula (17). , (17) in, To test the number of computing tasks, ∈[1, ]. For the Image processing scores for a task that tests computing power. For the A normalization function for testing the image processing score of the computing power task, namely the second preset function mentioned above.

[0078] Therefore, according to the real-time operating status value of the computing power device under the image processing calculation characteristics and operation evaluation value , we can get the recommended coefficient of the computing power device under the image processing computing characteristics , .

[0079] In one implementation, based on the computing power test results of the computing power device for different computing power characteristics, the operation evaluation value of the computing power device for different computing power characteristics (i.e., step B2) can be determined, which can be executed as follows: through a third preset function, the normalized value of the transmission storage score of each test computing power task is calculated respectively, and then according to the normalized value of the transmission storage score of each test computing power task, the average transmission storage score of all test computing power tasks is determined, and the average transmission storage score is determined as the operation evaluation value of the computing power device under the transmission storage characteristic.

[0080] In this embodiment, the operation evaluation value of the computing power device under the transmission and storage characteristics is The calculation process of is shown in formula (18). , (18) in, To test the number of computing tasks, ∈[1, ]. For the The transfer and storage scores of the computing power test task. For the A normalized function of the transmission and storage score of a test computing power task, namely, the third preset function mentioned above.

[0081] Therefore, according to the real-time operating status value of the computing power equipment under the transmission and storage characteristics and operation evaluation value , we can get the recommended coefficient of the computing power device under the transmission and storage characteristics , .

[0082] In one implementation, the recommended computing power value of each computing power device for the computing power task is determined 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 (i.e., step 206). This can be performed as follows: calculating the first product between the demand weight corresponding to the data processing demand and the recommended coefficient corresponding to the data processing computing characteristic, calculating the second product between the demand weight corresponding to the image processing demand and the recommended coefficient corresponding to the image processing computing characteristic, and calculating the third product between the demand weight corresponding to the amount of resources required for the task and the recommended coefficient corresponding to the transmission and storage characteristics, thereby calculating the sum of the first product, the second product, and the third product to obtain the recommended computing power value of the computing power device for the computing power task.

[0083] Optionally, k Recommended computing power for each computing device The calculation process of is shown in formula (19). , (19) in, For the k The demand weight corresponding to the data processing demand of each computing device, For the k The recommended coefficient corresponding to the data processing calculation characteristics of each computing device, For the k The demand weight corresponding to the image processing demand of each computing device, For the k The recommended coefficients corresponding to the image processing calculation characteristics of the computing power device are: For the k The demand weight corresponding to the amount of resources required for the task of each computing device, For the k The recommended coefficient corresponding to the transmission and storage characteristics of each computing device.

[0084] In one implementation, before allocating the computing power task to the target computing power device among the computing power devices for processing (ie, step 208) based on the computing power recommendation value, the target computing power device that meets the preset conditions can be determined from the computing power devices based on the computing power recommendation value.

[0085] Optionally, the preset condition may be one of the highest recommended computing power value, the lowest recommended computing power value, the second highest recommended computing power value, the second lowest recommended computing power value, etc.

[0086] In this embodiment, when the recommended computing power value of each computing power device for a computing power task is obtained, the computing power devices can be sorted according to the recommended computing power value, so as to determine the target computing power device among the computing power devices based on preset conditions.

[0087] Figure 3 This is a flowchart of a method for allocating computing tasks provided by another embodiment of the present application. The method can be executed by an electronic device, and the electronic device may include: a server and / or a terminal device, wherein the terminal device may be, for example, a vehicle-mounted terminal or a mobile phone terminal. In other words, the method can be executed by software or hardware installed in the electronic device, and the method includes the following steps: Step 301, according to each computing power requirement of the 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.

[0088] Among them, different computing power requirements include data processing requirements, image processing requirements and task resource requirements. The demand weights include data processing computing feature weights, image processing computing feature weights and transmission storage feature weights.

[0089] Specifically, for each computing power requirement of the computing power task, the demand value corresponding to the computing power requirement can be determined according to the computing power requirement, the standard value corresponding to the computing power requirement, the standard function and the weight adjustment coefficient, so as to calculate the ratio of the demand value to the total demand value and obtain the demand weight corresponding to the computing power requirement. The total demand value is determined based on the demand value of each computing power requirement.

[0090] 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.

[0091] The equipment parameters include one or more of the following: rated storage capacity, rated power load, rated refrigeration equipment load, rated computing capacity and storage impact coefficient corresponding to different computing power characteristics. The computing power characteristics include data processing computing characteristics, image processing computing characteristics and transmission storage characteristics.

[0092] Step 303: Determine the operation evaluation value of the computing power device for different computing power characteristics according to the computing power test results of the computing power device for different computing power characteristics.

[0093] Among them, the data processing computing characteristics, image processing computing characteristics and transmission and storage characteristics of the computing power equipment can be tested respectively by a preset number of test computing power tasks, and the computing power test results of the computing power equipment for different computing power characteristics can be obtained. The computing power test results can include data processing scores, image processing scores and transmission and storage scores.

[0094] Step 304, determining the recommended coefficient of the computing power device under different computing power characteristics according to the real-time operating status value and operating evaluation value of the computing power device for different computing power characteristics.

[0095] Among them, the recommendation coefficient is negatively correlated with the real-time operation status value, and the recommendation coefficient is positively correlated with the operation evaluation value.

[0096] Step 305, determining the recommended computing power value of each computing power device for the computing power task according to 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.

[0097] Step 306: Based on the recommended computing power value, the computing power task is allocated to the target computing power device among the computing power devices for processing.

[0098] The specific process of the above steps 301 to 306 has been described in detail in the above embodiment and will not be repeated here.

[0099] By adopting the technical solution of the embodiment of the present application, in the process of allocating computing power tasks, the demand weights corresponding to the different computing power requirements of the computing power tasks to be allocated to the computing power equipment can be determined. Different computing power requirements include data processing requirements, image processing requirements, and task required resources. The demand weights include data processing computing characteristics weights, image processing computing characteristics weights, and transmission storage characteristics weights. And for each computing power device, according to the real-time resource occupancy information of the computing power device and the computing power test results for different computing power characteristics, the recommended coefficient of the computing power device under different computing power characteristics is determined. The computing power characteristics include data processing computing characteristics, image processing computing characteristics, and transmission storage characteristics. Thus, according to 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 tasks, the computing power recommended value of each computing power device for the computing power task is determined, and based on the computing power recommended value, the computing power task is allocated to the target computing power device in each computing power device for processing. Since the demand weight can reflect the emphasis of the computing task on each computing demand, the recommendation coefficient can reflect the computing resource situation of the computing equipment under different computing characteristics. Therefore, this technical solution calculates the demand weight of the computing task and the recommendation coefficient of the computing equipment to determine the target computing equipment in each computing equipment, and fully considers the influence of the computing demand of the computing task and the computing resources of the computing equipment on the selection of the computing equipment. Compared with the method of evenly allocating computing tasks to each computing equipment in the related technology, it not only enables the target computing equipment to better meet the computing demand of the computing task, realizes a more reasonable and accurate allocation of computing tasks, but also improves the adequacy of the computing resources of each computing equipment.

[0100] It should be noted that the computing power task allocation method provided in the embodiment of the present application 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. In the embodiment of the present application, the computing power task allocation method executed by the computing power task allocation device is taken as an example to illustrate the computing power task allocation device provided in the embodiment of the present application.

[0101] Figure 4 Schematic diagram of a computing task allocation device provided in an embodiment of the present application. Figure 4 As shown, the computing task allocation device includes: a first determination module 410, a second determination module 420, a third determination module 430 and a computing task allocation module 440.

[0102] The first determination module 410 is used to determine the demand weights corresponding to different computing power requirements of the computing power task to be allocated to the computing power device according to the computing power requirements of the computing power task to be allocated to the computing power device; different computing power requirements include data processing requirements, image processing requirements and task required resources; demand weights include data processing computing characteristics weights, image processing computing characteristics weights and transmission storage characteristics weights; the second determination module 420 is used to determine the recommended coefficient of the computing power device under different computing power characteristics for each computing power device according to 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 storage characteristics; the third determination module 430 is used 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 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 in each computing power device for processing based on the computing power recommendation value.

[0103] In one implementation, the second determination module 420 includes: a first determination unit, which is used to determine, for each computing power device, 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; a second determination unit, which is used to determine 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; a third determination unit, which is used to determine the recommended coefficient of the computing power device under different computing power characteristics based on the real-time operating status value and operating evaluation value of the computing power device for different computing power characteristics; wherein the recommended coefficient is negatively correlated with the real-time operating status value, and the recommended coefficient is positively correlated with the operating evaluation value.

[0104] In one implementation, the real-time resource occupancy information includes data computing occupancy, transmission storage occupancy, power load occupancy, and refrigeration equipment load occupancy; the equipment parameters include rated storage capacity, power rated load, and refrigeration equipment rated load; The first determination unit is specifically used to: determine the first constituent factor of the real-time operation status value according to a first ratio between the power load occupancy and the power rated load, a second ratio between the refrigeration equipment load occupancy and the refrigeration equipment rated load, and a preset logic function; obtain the data calculation rated amount and the data calculation storage influence coefficient of the computing power device under the data processing calculation characteristics; respectively calculate the first difference between the data calculation rated amount and the data calculation occupancy, and the second difference between the average of the data calculation rated amount of all computing power devices and the average of the data calculation occupancy of all computing power devices; the average of the data calculation rated amount is determined based on the data calculation rated amount of each computing power device, and the data The mean computing occupancy is determined based on the data computing occupancy of each computing power device; the second component factor of the real-time operating status value of the computing power device under the data processing computing characteristics is determined according to the data computing occupancy, the first difference, the second difference and the preset exponential function; the third component factor of the real-time operating status value of the computing power device under the data processing computing characteristics is determined according to the transmission storage occupancy, the mean rated storage capacity of all computing power devices and the data computing storage influence coefficient; the mean rated storage capacity is determined based on the rated storage capacity of each computing power device; the product of the first component factor, the second component factor and the third component factor is calculated to obtain the real-time operating status value of the computing power device under the data processing computing characteristics.

[0105] In one implementation, the real-time resource occupancy information also includes image processing occupancy; The first determination unit is specifically used to: obtain the image processing rated computing amount and the image processing storage influence coefficient of the computing power device under the image processing computing characteristics; calculate the third difference between the image processing rated computing amount and the image processing occupancy, and the fourth difference between the average of the image processing rated computing amount of all computing power devices and the average of the image processing occupancy of all computing power devices; the average of the image processing rated computing amount is determined based on the image processing rated computing amount of each computing power device, and the average of the image processing occupancy is determined based on the image processing occupancy of each computing power device; determine the fourth component factor of the real-time operating status value of the computing power device under the image processing computing characteristics according to the image processing occupancy, the third difference, the fourth difference and the preset exponential function; determine the fifth component factor of the real-time operating status value of the computing power device under the image processing computing characteristics according to the transmission storage occupancy, the average of the rated storage of all computing power devices and the image processing storage influence coefficient; calculate the product of the first component factor, the fourth component factor and the fifth component factor to obtain the real-time operating status value of the computing power device under the image processing computing characteristics.

[0106] In one implementation, the first determination unit is specifically used to: determine the sixth component factor of the real-time operating status value of the computing power device under the transmission storage characteristics based on the transmission storage occupancy and the average rated storage capacity of all computing power devices; calculate the product of the first component factor and the sixth component factor to obtain the real-time operating status value of the computing power device under the transmission storage characteristics.

[0107] In one implementation, the second determination module 420 also includes: a testing unit, which is used to test 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 before determining the operation 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 scores, image processing scores and transmission and storage scores.

[0108] In one implementation, the second determination unit is specifically used to: calculate the normalized value of the data processing score of each test computing power task through the 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 operation evaluation value of the computing power equipment under the data processing calculation characteristics.

[0109] In one implementation, the second determination unit is specifically used to: calculate the normalized value of the image processing score of each test computing power task through 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.

[0110] In one implementation, the second determination unit is specifically used to: calculate the normalized value of the transmission and storage score of each test computing power task through 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 operation evaluation value of the computing power device under the transmission and storage characteristics.

[0111] In one implementation, the first determination module 410 includes: a fourth determination unit, which is used to determine, for each computing power requirement of the computing power task, a demand value corresponding to the computing power requirement according to the computing power requirement, and the standard value, standard function and weight adjustment coefficient corresponding to the computing power requirement; a calculation unit, which is used to calculate the ratio of the demand value to the total demand value to obtain the demand weight corresponding to the computing power requirement; the total demand value is determined based on the demand value of each computing power requirement.

[0112] By adopting the technical solution of the embodiment of the present application, in the process of allocating computing power tasks, the demand weights corresponding to the different computing power requirements of the computing power tasks to be allocated to the computing power equipment can be determined. Different computing power requirements include data processing requirements, image processing requirements, and task required resources. The demand weights include data processing computing characteristics weights, image processing computing characteristics weights, and transmission storage characteristics weights. And for each computing power device, according to the real-time resource occupancy information of the computing power device and the computing power test results for different computing power characteristics, the recommended coefficient of the computing power device under different computing power characteristics is determined. The computing power characteristics include data processing computing characteristics, image processing computing characteristics, and transmission storage characteristics. Thus, according to 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 tasks, the computing power recommended value of each computing power device for the computing power task is determined, and based on the computing power recommended value, the computing power task is allocated to the target computing power device in each computing power device for processing. Since the demand weight can reflect the emphasis of the computing task on each computing demand, the recommendation coefficient can reflect the computing resource situation of the computing equipment under different computing characteristics. Therefore, this technical solution calculates the demand weight of the computing task and the recommendation coefficient of the computing equipment to determine the target computing equipment in each computing equipment, and fully considers the influence of the computing demand of the computing task and the computing resources of the computing equipment on the selection of the computing equipment. Compared with the method of evenly allocating computing tasks to each computing equipment in the related technology, it not only enables the target computing equipment to better meet the computing demand of the computing task, realizes a more reasonable and accurate allocation of computing tasks, but also improves the adequacy of the computing resources of each computing equipment.

[0113] The computing task allocation device in the embodiment of the present application 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. Exemplarily, the mobile electronic device can be a mobile phone, a tablet computer, a laptop computer, a PDA, an in-vehicle electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA), etc. The non-mobile electronic device can be a server, a network attached storage (NAS), a personal computer (PC), a television (TV), a teller machine or a self-service machine, etc., which is not specifically limited in the embodiment of the present application.

[0114] The computing task allocation device in the embodiment of the present application may be a device having an operating system. The operating system may be an Android operating system, an iOS operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present application.

[0115] The computing task allocation device provided in the embodiment of the present application can achieve Figures 2 to 3 To avoid repetition, the various processes implemented in the method embodiment are not described here.

[0116] Based on the same technical concept, an embodiment of the present application further provides an electronic device, which is used to execute the above-mentioned method for allocating computing tasks. Figure 5 A schematic diagram of the structure of an electronic device for implementing various embodiments of the present application. The electronic device may have relatively large differences due to different configurations or performances, and may include a processor 510, a communications interface 520, a memory 530, and a communication bus 540, wherein the processor 510, the communications interface 520, and the memory 530 communicate with each other through the communication bus 540. The processor 510 may call a computer program stored in the memory 530 and executable on the processor 510 to perform the following steps: According to the computing power requirements of the computing power tasks to be allocated to the computing power equipment, the demand weights corresponding to the different computing power requirements of the computing power tasks are determined; different computing power requirements include data processing requirements, image processing requirements and the amount of resources required for the task; the demand weights include data processing computing characteristics weights, image processing computing characteristics weights and transmission storage characteristics weights; for each computing power equipment, according to the real-time resource occupancy information of the computing power equipment and the computing power test results for different computing power characteristics, the recommended coefficient of the computing power equipment under different computing power characteristics is determined; the computing power characteristics include data processing computing characteristics, image processing computing characteristics and transmission storage characteristics; according to the recommended coefficient of the computing power equipment under different computing power characteristics and the demand weights corresponding to the different computing power requirements of the computing power tasks, the computing power recommended value of each computing power equipment for the computing power task is determined; based on the computing power recommended value, the computing power task is allocated to the target computing power equipment in each computing power equipment for processing.

[0117] By adopting the technical solution of the embodiment of the present application, in the process of allocating computing power tasks, the demand weights corresponding to the different computing power requirements of the computing power tasks to be allocated to the computing power equipment can be determined. Different computing power requirements include data processing requirements, image processing requirements, and task required resources. The demand weights include data processing computing characteristics weights, image processing computing characteristics weights, and transmission storage characteristics weights. And for each computing power device, according to the real-time resource occupancy information of the computing power device and the computing power test results for different computing power characteristics, the recommended coefficient of the computing power device under different computing power characteristics is determined. The computing power characteristics include data processing computing characteristics, image processing computing characteristics, and transmission storage characteristics. Thus, according to 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 tasks, the computing power recommended value of each computing power device for the computing power task is determined, and based on the computing power recommended value, the computing power task is allocated to the target computing power device in each computing power device for processing. Since the demand weight can reflect the emphasis of the computing task on each computing demand, the recommendation coefficient can reflect the computing resource situation of the computing equipment under different computing characteristics. Therefore, this technical solution calculates the demand weight of the computing task and the recommendation coefficient of the computing equipment to determine the target computing equipment in each computing equipment, and fully considers the influence of the computing demand of the computing task and the computing resources of the computing equipment on the selection of the computing equipment. Compared with the method of evenly allocating computing tasks to each computing equipment in the related technology, it not only enables the target computing equipment to better meet the computing demand of the computing task, realizes a more reasonable and accurate allocation of computing tasks, but also improves the adequacy of the computing resources of each computing equipment.

[0118] The specific execution steps can refer to the various steps of the above-mentioned computing power task allocation method implementation example, and can achieve the same technical effect. To avoid repetition, they will not be repeated here.

[0119] It should be noted that the electronic devices in the embodiments of the present application include: servers, terminals, or other devices except terminals.

[0120] The above electronic device structure does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. For example, the input unit may include a graphics processing unit (GPU) and a microphone, and the display unit may be configured with a display panel in the form of a liquid crystal display, an organic light-emitting diode, etc. The user input unit includes a touch panel and at least one of other input devices. The touch panel is also called a touch screen. Other input devices may include, but are not limited to, a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, and a joystick, which will not be repeated here.

[0121] The memory can be used to store software programs and various data. The memory may mainly include a first storage area for storing programs or instructions and a second storage area for storing data, wherein the first storage area may store an operating system, an application program or instructions required for at least one function (such as a sound playback function, an image playback function, etc.), etc. In addition, the memory may include a volatile memory or a non-volatile memory, or the memory may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. Volatile memory can be Random Access Memory (RAM), Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link Dynamic Random Access Memory (SLDRAM) and Direct Rambus RAM (DRRAM).

[0122] 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 processes operations related to the operating system, user interface, and application programs, and the modem processor mainly processes wireless communication signals, such as a baseband processor. It is understandable that the modem processor may not be integrated into the processor.

[0123] An embodiment of the present application also provides a computer-readable storage medium, which is used to store computer-executable instructions. When the computer-executable instructions are executed by a processor, the various processes of the above-mentioned computing power task allocation method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, they will not be repeated here.

[0124] The processor is the processor in the electronic device described in the above embodiment. The computer readable storage medium is, for example, a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0125] An embodiment of the present 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-mentioned embodiment of the method for allocating computing power tasks and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0126] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned computing power task allocation method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0127] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0128] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0129] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0130] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

1. A method for allocating computing tasks, characterized in that: include: Determine, according to the computing power requirements of the computing power tasks to be allocated to the computing power equipment, the demand weights corresponding to the different computing power requirements of the computing power tasks; The different computing power requirements include data processing requirements, image processing requirements and task required resources; The demand weights include data processing computing characteristic weights, image processing computing characteristic weights and transmission storage characteristic weights; For each of the computing power devices, determining a recommended coefficient of the computing power device under the different computing power characteristics according to the real-time resource occupation 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 storage characteristics; Determine a recommended computing power value of each computing power device for the computing power task according to the recommended coefficient of the computing power device under the different computing power characteristics and the demand weights corresponding to the different computing power requirements of the computing power task; Based on the computing power recommendation value, the computing power task is allocated to a target computing power device among the computing power devices for processing.

2. The method according to claim 1, characterized in that The step of determining, for each computing device, a recommended coefficient of the computing device under different computing power characteristics according to the real-time resource occupation information of the computing device and computing power test results for different computing power characteristics, includes: For each of the computing power devices, determining a real-time operating status value of the computing power device for the different computing power characteristics according to the real-time resource occupancy information and device parameters of the computing power device; Determining, according to the computing power test results of the computing power device for different computing power characteristics, an operation evaluation value of the computing power device for the different computing power characteristics; According to the real-time operating status value and the operating evaluation value of the computing power device for the different computing power characteristics, the recommended coefficient of the computing power device under the different computing power characteristics is determined; wherein the recommended coefficient is negatively correlated with the real-time operating status value, and the recommended coefficient is positively correlated with the operating evaluation value.

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

4. The method according to claim 3, characterized in that The real-time resource occupancy information also includes image processing occupancy; The determining, according to 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 the different computing power characteristics comprises: Obtaining an image processing rated computing amount and an image processing storage influence coefficient of the computing power device under image processing computing characteristics; Calculating respectively a third difference between the image processing rated computing amount and the image processing occupied amount, and a fourth difference between the average of the image processing rated computing amounts of all computing power devices and the average of the image processing occupied amounts of all computing power devices; the average of the image processing rated computing amount is determined based on the image processing rated computing amount of each computing power device, and the average of the image processing occupied amount is determined based on the image processing occupied amount of each computing power device; Determine a fourth component factor of the real-time operating status value of the computing power device under the image processing calculation characteristics according to the image processing occupancy, the third difference, the fourth difference and the preset exponential function; Determine a fifth component factor of a real-time operating status value of the computing power device under image processing calculation characteristics according to the transmission storage occupancy, the average of the rated storage capacity of all computing power devices, and the image processing storage influence coefficient; The product of the first component factor, the fourth component factor and the fifth component factor is calculated to obtain a real-time operating status value of the computing power device under the image processing calculation characteristics.

5. The method according to claim 3, characterized in that: The determining, according to 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 the different computing power characteristics comprises: Determine a sixth component factor of the real-time operating status value of the computing power device under the transmission storage characteristic according to the transmission storage occupancy and the average of the rated storage capacity of all the computing power devices; The product of the first component factor and the sixth component 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 Before determining the operation evaluation value of the computing power device for the different computing power characteristics according to the computing power test results of the computing power device for the different computing power characteristics, the method further includes: By presetting a number of test computing power tasks, the data processing computing characteristics, image processing computing characteristics and transmission and storage characteristics of the computing power device are tested respectively, and the computing power test results of the computing power device for different computing power characteristics are obtained; the computing power test results include data processing scores, image processing scores and transmission and storage scores.

7. The method according to claim 6, characterized in that The determining, according to the computing power test results of the computing power device for different computing power characteristics, the operation evaluation value of the computing power device for the different computing power characteristics, includes: Calculate the normalized value of the data processing score of each test computing task respectively through the first preset function; Determine the average value of the data processing scores of all the test computing power tasks according to the normalized value of the data processing scores of each test computing power task; The data processing score mean is determined as the operation evaluation value of the computing power device under the data processing calculation characteristics.

8. The method according to claim 6, characterized in that The determining, according to the computing power test results of the computing power device for different computing power characteristics, the operation evaluation value of the computing power device for the different computing power characteristics, includes: Calculate the normalized value of the image processing score of each test computing task respectively through the second preset function; Determine the mean value of the image processing scores of all the test computing power tasks according to the normalized value of the image processing score of each test computing power task; The image processing score mean is determined as the operation evaluation value of the computing power device under the image processing calculation characteristics.

9. The method according to claim 6, characterized in that The determining, according to the computing power test results of the computing power device for different computing power characteristics, the operation evaluation value of the computing power device for the different computing power characteristics, includes: Calculate the normalized value of the transmission and storage score of each test computing task through the third preset function; Determine the average of the transmission and storage scores of all the test computing power tasks according to the normalized value of the transmission and storage score of each test computing power task; The transmission and storage score mean is determined as the operation evaluation value of the computing power device under the transmission and storage characteristics.

10. The method according to claim 1, characterized in that The determining, according to each computing power requirement of the computing power task to be allocated to the computing power device, the demand weights corresponding to the different computing power requirements of the computing power task respectively include: For each computing power requirement of the computing power task, determine a demand value corresponding to the computing power requirement according to the computing power requirement, and a standard value, a standard function and a 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.

11. A computing task allocation device, characterized in that: include: A first determination module is used to determine the demand weights corresponding to different computing power requirements of the computing power tasks to be allocated to the computing power equipment according to the computing power requirements of the computing power tasks; The different computing power requirements include data processing requirements, image processing requirements and task required resources; The demand weights include data processing computing characteristic weights, image processing computing characteristic weights and transmission storage characteristic weights; A second determination module is used to determine, for each of the computing power devices, a recommended coefficient of the computing power device under the different computing power characteristics according to the real-time resource occupation 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 storage characteristics; A third determination module is used to determine the recommended computing power value of each computing power device for the computing power task according to the recommendation coefficient of the computing power device under the different computing power characteristics and the demand weights corresponding to the different computing power requirements of the computing power task; A computing power task allocation module is used to allocate the computing power task to a target computing power device among the computing power devices for processing based on the computing power recommendation value.

12. An electronic device, characterized in that: include: processor; as well as A memory arranged to store computer executable instructions, wherein the computer executable instructions are configured to be executed by the processor, and the computer executable instructions are executed by the processor to implement the method for allocating computing tasks as described in any one of claims 1-10.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store computer-executable instructions, and when the computer-executable instructions are executed by a processor, the method for allocating computing power tasks as described in any one of claims 1 to 10 is implemented.

14. A computer program product, characterized in that It includes a computer program, which, when executed by a processor, implements the method for allocating computing tasks as described in any one of claims 1 to 10.

Images