Verification method and device of algorithm optimization result and computer equipment
By obtaining the data verification value and intermediate value in the power equipment optimization process, and using the matching degree verification method to verify the optimization results of the intelligent algorithm, the problem of enclosedness of the intelligent algorithm optimization process is solved, ensuring the accuracy and global optimization of the optimization results.
Patent Information
- Application Number
- CN202510548240.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-28
- Publication Date
- 2025-08-01
AI Technical Summary
Intelligent algorithms are closed in the optimization of power equipment structure, and cannot ensure whether the optimization result is the global optimal solution, making it difficult to verify the correctness of the optimization result.
By obtaining the data check value and the optimization path intermediate value of the parameters to be optimized, the matching degree verification is performed using the data check set and the optimization path intermediate value to determine the correctness of the optimization result.
The validity verification of the optimization results of intelligent algorithms is achieved, the field of adaptation of optimization algorithms is improved, and the accuracy of optimization results is ensured.
Smart Images
Figure CN120409022A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the technical field of power equipment structure optimization, and particularly to a method, device, and computer device for verifying the optimization results of an algorithm. Background Art
[0002] In the structural optimization of power equipment, the single-parameter control variable method was often used for design in the early stage. However, with the wide application of intelligent algorithms (such as genetic algorithms, particle swarm optimization, etc.), the multi-parameter structural optimization problem has been solved more quickly and flexibly. The intelligent algorithm transforms the structural optimization problem into a mathematical optimization problem and can find the optimal parameter configuration of a given objective function.
[0003] However, the optimization process of the intelligent algorithm is closed, and it is impossible to ensure whether the result is the global optimal solution, making it difficult to guarantee the correctness of the optimization result. Summary of the Invention
[0004] Based on this, it is necessary to provide a method, device, and computer device for verifying the optimization results of an algorithm that can verify the correctness of the optimization results for the above technical problems.
[0005] In a first aspect, this application provides a method for verifying the optimization results of an algorithm. The method includes:
[0006] Determine a data verification value according to the parameter value range of the parameter to be optimized;
[0007] Obtain the intermediate value of the optimization path obtained after each round of iterative optimization of the parameter to be optimized when optimizing the parameter to be optimized through the objective function;
[0008] Verify the algorithm optimization of the parameter to be optimized according to the data verification set and the intermediate value of the optimization path, and obtain the algorithm optimization result of the parameter to be optimized.
[0009] In one embodiment, the determining a data verification value according to the parameter value range of the parameter to be optimized includes:
[0010] Select the target parameter positions from the parameter value ranges of the parameters to be optimized according to the preset verification accuracy requirements;
[0011] Use the objective function value at the target parameter position as the data verification value.
[0012] In one embodiment, when the parameter types of the parameters to be optimized are multiple, the amount of data of the data verification value is equal to the product of the number of target parameter positions in each type of parameter to be optimized.
[0013] In one embodiment, the algorithm optimization verification of the parameter to be optimized according to the data verification set and the intermediate value of the optimization path to obtain the algorithm optimization result of the parameter to be optimized includes:
[0014] Obtain the data matching degree between the data verification set and the intermediate value of the optimization path;
[0015] Perform algorithm optimization verification on the parameter to be optimized according to the data matching degree to obtain the algorithm optimization result of the parameter to be optimized. [[ID=,7]]
[0016] In one embodiment, the obtaining the data matching degree between the data verification set and the intermediate value of the optimization path includes:
[0017] Obtain the first data distribution trend corresponding to the data verification set and the second data distribution trend corresponding to the intermediate value of the optimization path;
[0018] Compare the first data distribution trend and the second data distribution trend to obtain the data matching degree between the data verification set and the intermediate value of the optimization path.
[0019] In one embodiment, the performing algorithm optimization verification on the parameter to be optimized according to the data matching degree to obtain the algorithm optimization result of the parameter to be optimized includes:
[0020] If the data matching degree is greater than the matching degree threshold, determine that the algorithm optimization result of the parameter to be optimized is correct;
[0021] If the data matching degree is not greater than the matching degree threshold, determine that the algorithm optimization result of the parameter to be optimized is incorrect.
[0022] In a second aspect, the present application also provides a verification device for algorithm optimization results. The device includes:
[0023] A first acquisition module, configured to determine a data verification value according to the parameter value range of the parameter to be optimized;
[0024] A second acquisition module, configured to obtain the intermediate value of the optimization path obtained after each round of iterative optimization of the parameter to be optimized when performing parameter optimization on the parameter to be optimized through an objective function;
[0025] A verification module, configured to perform algorithm optimization verification on the parameter to be optimized according to the data verification set and the intermediate value of the optimization path to obtain the algorithm optimization result of the parameter to be optimized.
[0026] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor. The memory stores a computer program. When the processor executes the computer program, the following steps are implemented:
[0027] Determine a data verification value according to the parameter value range of the parameter to be optimized;
[0028] Obtain the intermediate value of the optimization path obtained after each round of iterative optimization of the parameter to be optimized when optimizing the parameter to be optimized through the objective function;
[0029] Perform algorithm optimization verification on the parameter to be optimized according to the data verification set and the intermediate value of the optimization path, and obtain the algorithm optimization result of the parameter to be optimized.
[0030] In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon. When the computer program is executed by a processor, the following steps are implemented:
[0031] Determine a data verification value according to the parameter value range of the parameter to be optimized;
[0032] Obtain the intermediate value of the optimization path obtained after each round of iterative optimization of the parameter to be optimized when optimizing the parameter to be optimized through the objective function;
[0033] Perform algorithm optimization verification on the parameter to be optimized according to the data verification set and the intermediate value of the optimization path, and obtain the algorithm optimization result of the parameter to be optimized.
[0034] In a fifth aspect, the present application further provides a computer program product. The computer program product includes a computer program. When the computer program is executed by a processor, the following steps are implemented:
[0035] Determine a data verification value according to the parameter value range of the parameter to be optimized;
[0036] Obtain the intermediate value of the optimization path obtained after each round of iterative optimization of the parameter to be optimized when optimizing the parameter to be optimized through the objective function;
[0037] Perform algorithm optimization verification on the parameter to be optimized according to the data verification set and the intermediate value of the optimization path, and obtain the algorithm optimization result of the parameter to be optimized.
[0038] The verification method, device, and computer equipment for the above algorithm optimization results obtain a data check value and the intermediate value of the optimization path obtained after each round of iterative optimization of the parameter to be optimized when optimizing the parameter to be optimized through an objective function. Furthermore, the algorithm optimization verification of the parameter to be optimized is performed based on the data check set and the intermediate value of the optimization path, and the algorithm optimization result of the parameter to be optimized is obtained. According to the above content, it can be known that in the process of performing algorithm optimization verification on the parameter to be optimized in this application, the intermediate value of the optimization path obtained after each round of iterative optimization of the parameter to be optimized is obtained, realizing the algorithm optimization verification by combining the optimization path of the optimization algorithm and the final result of the optimization algorithm, making up for the deficiencies brought by the closed nature of the intelligent algorithm optimization process, realizing the effectiveness verification of the optimization algorithm, and improving the applicable fields of the optimization algorithm. BRIEF DESCRIPTION OF THE DRAWINGS
[0039] Figure 1 FIG. is an application environment diagram of a verification method for an algorithm optimization result provided by an embodiment of the present application;
[0040] Figure 2 FIG. is a flowchart of a first verification method for an algorithm optimization result provided by an embodiment of the present application;
[0041] Figure 3 FIG. is a schematic diagram of the intermediate value of the optimization path of two types of parameters to be optimized provided by an embodiment of the present application;
[0042] Figure 4 FIG. is a schematic diagram of the intermediate value of the optimization path of three types of parameters to be optimized provided by an embodiment of the present application;
[0043] Figure 5 FIG. is a flowchart of a second verification method for an algorithm optimization result provided by an embodiment of the present application;
[0044] Figure 6 FIG. is a schematic diagram of the data check value of two types of parameters to be optimized provided by an embodiment of the present application;
[0045] Figure 7 FIG. is a schematic diagram of the data check value of three types of parameters to be optimized provided by an embodiment of the present application;
[0046] Figure 8 FIG. is a flowchart of a third verification method for an algorithm optimization result provided by an embodiment of the present application;
[0047] Figure 9 FIG. is a flowchart of a fourth verification method for an algorithm optimization result provided by an embodiment of the present application;
[0048] Figure 10 FIG. is a structural block diagram of a verification device for an algorithm optimization result provided by an embodiment of the present application;
[0049] Figure 11 It is the internal structure diagram of a computer device in an embodiment. Specific implementation manners
[0050] In order to make the objectives, technical solutions and advantages of the present application more clear and understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0051] In structural optimization design, the traditional method usually adopts the method of controlling variables, that is, analyzing each parameter one by one and selecting the optimal configuration. This method is effective when the parameters are independent of each other. However, in practical applications, there are often complex mutual influence relationships between the parameters, resulting in the adjustment of the post-optimized parameters may affect the results of the pre-optimized parameters, thus making the final optimization result inaccurate.
[0052] In the structural optimization of power equipment, the single-parameter control variable method was often used for design in the early stage. However, with the wide application of intelligent algorithms (such as genetic algorithms, particle swarm optimization, etc.), the multi-parameter structural optimization problem has been solved more quickly and flexibly. The intelligent algorithm transforms the structural optimization problem into a mathematical optimization problem and can find the optimal parameter configuration of the given objective function. However, the optimization process of the intelligent algorithm is closed, it is difficult to analyze its optimization path, and it cannot ensure whether the result is the global optimal solution. Therefore, the single-parameter structural optimization analysis is still an important supplement to the intelligent algorithm optimization.
[0053] In previous studies, the single-parameter control variable method has been widely used in the structural optimization of UHV transmission lines, substations and key equipment, providing an important basis for explaining the influence of key structural parameters on the optimization effect. In recent years, intelligent algorithms have shown significant advantages in dealing with complex structural parameter optimization problems, but the reliability and global optimality of their results still need to be further verified.
[0054] The method for verifying the algorithm optimization result provided by the embodiment of the present application can be applied to, for example Figure 1In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or placed on the cloud or other network servers. By obtaining the data check value, and when optimizing the parameter to be optimized through the objective function, the intermediate value of the optimization path obtained after each round of iterative optimization of the parameter to be optimized; furthermore, according to the data check set and the intermediate value of the optimization path, the algorithm optimization verification is performed on the parameter to be optimized, and the algorithm optimization result of the parameter to be optimized is obtained. Among them, the terminal 102 can be but is not limited to various personal computers, laptop computers, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, etc. The portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be implemented by an independent server or a server cluster composed of multiple servers.
[0055] In one embodiment, as Figure 2 shown, a method for verifying the algorithm optimization result is provided. Taking the server 104 in Figure 1 as an example, the method includes the following steps:
[0056] S201, determine the data check value according to the parameter value range of the parameter to be optimized.
[0057] It should be noted that when it is necessary to determine the data check value, according to the parameter value range of the parameter to be optimized and the correlation relationship between different parameters to be optimized, the determination of the data check value for multiple types of parameters to be optimized is realized.
[0058] Specifically, when it is necessary to determine the data check value according to the parameter value range of the parameter to be optimized, multiple candidate parameter positions can be selected from the parameter value range of the parameter to be optimized, and the data check value is determined according to the objective function values corresponding to the respective candidate parameter positions.
[0059] S202, obtain the intermediate value of the optimization path obtained after each round of iterative optimization of the parameter to be optimized during the process of optimizing the parameter to be optimized through the optimization algorithm.
[0060] It should be noted that the intermediate value of the optimization path can characterize the change of the parameter to be optimized in each iteration process, realizing the visualization display of the optimization path of the optimization algorithm, and providing a judgment basis for the subsequent algorithm optimization verification of the parameter to be optimized.
[0061] Therefore, when it is necessary to obtain the intermediate value of the optimization path obtained after each round of iterative optimization of the parameter to be optimized during the parameter optimization of the parameter to be optimized by the optimization algorithm, after each step of iterative solution of the optimization algorithm, the parameter value after each step of iterative solution is read, and this parameter value is the intermediate value of the optimization path.
[0062] In an embodiment of the present application, if there are two types of parameters to be optimized, and the two types of parameters to be optimized are the parameter to be optimized R4 and the parameter to be optimized X4 respectively. Therefore, the initial parameter value of the optimization algorithm is given in advance. During the solution process of the optimization algorithm, the parameter values obtained after each step of iterative solution are plotted in the same image, and the obtained result is as Figure 3 shown, where the initial parameter value is at Figure 3 the red square in; if there are three types of parameters to be optimized, and the three types of parameters to be optimized are the parameter to be optimized X1, the parameter to be optimized Y1, and the parameter to be optimized R1 respectively. Therefore, the initial parameter value of the optimization algorithm is given in advance. During the solution process of the optimization algorithm, the parameter values obtained after each step of iterative solution are plotted in the same image, and the obtained result is as Figure 4 shown, where the initial parameter value is at Figure 4 the red square in.
[0063] S203. Perform algorithm optimization verification on the parameter to be optimized according to the data verification set and the intermediate value of the optimization path, and obtain the algorithm optimization result of the parameter to be optimized.
[0064] It should be noted that when it is necessary to perform algorithm optimization verification on the parameter to be optimized according to the data verification set and the intermediate value of the optimization path, it can be verified whether the data matching degree between the data verification set and the intermediate value of the optimization path is greater than the matching degree threshold. If it is greater, it is determined that the algorithm optimization result of the parameter to be optimized is correct; if it is not greater, it is determined that the algorithm optimization result of the parameter to be optimized is incorrect.
[0065] The above verification method of the algorithm optimization result obtains the data verification value and the intermediate value of the optimization path obtained after each round of iterative optimization of the parameter to be optimized when optimizing the parameter to be optimized by the objective function; furthermore, perform algorithm optimization verification on the parameter to be optimized according to the data verification set and the intermediate value of the optimization path, and obtain the algorithm optimization result of the parameter to be optimized. According to the above content, it can be seen that in the process of performing algorithm optimization verification on the parameter to be optimized in the present application, the intermediate value of the optimization path obtained after each round of iterative optimization of the parameter to be optimized is obtained, realizing the combination of the optimization path of the optimization algorithm and the final result of the optimization algorithm for algorithm optimization verification, obtaining the algorithm optimization result of the parameter to be optimized, making up for the deficiency brought by the closedness of the intelligent algorithm optimization process, realizing the effectiveness verification of the optimization algorithm, and improving the applicable field of the optimization algorithm.
[0066] In an embodiment, asFigure 5 As shown, when it is necessary to determine the data verification value according to the parameter value range of the parameter to be optimized, the following content may be included:
[0067] S501. Select the target parameter position from the parameter value ranges of each parameter to be optimized according to the preset verification accuracy requirement.
[0068] It should be noted that the parameter value range of the parameter to be optimized can be evenly divided to divide the parameter value range into a preset number of sub-ranges; select a certain parameter position in each sub-range as the target parameter position; among them, the higher the preset verification accuracy requirement, the more sub-ranges are obtained; the lower the preset verification accuracy requirement, the fewer sub-ranges are obtained.
[0069] Furthermore, when selecting a certain parameter position from each sub-range, the parameter selection rules that can be selected according to different situations and different requirements. For example, the middle parameter position of each sub-range can be used as the target parameter position; or the first parameter position of each sub-range can be used as the target parameter position; or the last parameter position of each sub-range can be used as the target parameter position, etc. The acquisition method of the target parameter position is not limited here.
[0070] Among them, when the parameter types of the parameters to be optimized are multiple, the data volume of the data verification value is equal to the product of the number of target parameter positions in each type of parameter to be optimized.
[0071] S502. Use the objective function value of the target parameter position as the data verification value.
[0072] In an embodiment of the present application, as Figure 6 shown, if there are two types of parameters to be optimized in total, the two types of parameters to be optimized are the parameter to be optimized R4 and the parameter to be optimized X4 respectively. The parameter value range of the parameter to be optimized R4 is 0-50 mm; the parameter value range of the parameter to be optimized X4 is 0-20 mm; the parameter value range of the parameter to be optimized R4 is evenly divided into 50 sub-ranges, and a target parameter position is respectively selected from the 50 sub-ranges to obtain 50 target parameter positions. The parameter value range of the parameter to be optimized X4 is evenly divided into 20 sub-ranges, and a target parameter position is respectively selected from the 20 sub-ranges to obtain 20 target parameter positions; at this time, the objective function values corresponding to the 50*20 target parameter positions are used as the data verification values.
[0073] In an embodiment of the present application, as Figure 7As shown, there are three types of parameters to be optimized, namely parameter X1 to be optimized, parameter Y1 to be optimized, and parameter R1 to be optimized. The value range of parameter X1 to be optimized is 80 - 140 mm; the value range of parameter Y1 to be optimized is 60 - 80 mm; the value range of parameter R1 to be optimized is 150 - 250 mm. The value ranges of the three types of parameters to be optimized are evenly divided into 20 sub-ranges, and one target parameter position is selected from each of the 20 sub-ranges corresponding to the three types of parameters to be optimized, obtaining 20 * 20 * 20 target parameter positions. The objective function values corresponding to the 20 * 20 * 20 target parameter positions are used as data verification values.
[0074] The verification method for the above algorithm optimization result realizes using the objective function value of the target parameter position as the data verification value by selecting the target parameter position from the value range of each parameter to be optimized, providing a data basis for subsequent algorithm optimization verification of the parameters to be optimized and ensuring the smooth progress of the subsequent process.
[0075] As Figure 8 shown, when it is necessary to perform algorithm optimization verification on the parameters to be optimized based on the data verification set and the intermediate value of the optimization path to obtain the algorithm optimization result of the parameters to be optimized, the following contents may be included:
[0076] S801, Obtain the data matching degree between the data verification set and the intermediate value of the optimization path.
[0077] It should be noted that when it is necessary to obtain the data matching degree between the data verification set and the intermediate value of the optimization path, the following contents may be included: Obtain the first data distribution trend corresponding to the data verification set and the second data distribution trend corresponding to the intermediate value of the optimization path; Compare the first data distribution trend and the second data distribution trend to obtain the data matching degree between the data verification set and the intermediate value of the optimization path.
[0078] Among them, the first data distribution trend is used to characterize the distribution of the data verification set in different data intervals, and the second data distribution trend is used to characterize the distribution of the intermediate value of the optimization path in different data intervals.
[0079] S802, Perform algorithm optimization verification on the parameters to be optimized according to the data matching degree to obtain the algorithm optimization result of the parameters to be optimized.
[0080] It should be noted that when it is necessary to perform algorithm optimization verification on the parameters to be optimized according to the data matching degree to obtain the algorithm optimization result of the parameters to be optimized, the following contents may be included: If the data matching degree is greater than the matching degree threshold, it is determined that the algorithm optimization result of the parameter to be optimized is correct; If the data matching degree is not greater than the matching degree threshold, it is determined that the algorithm optimization result of the parameter to be optimized is incorrect.
[0081] Among them, the value range of the matching degree threshold can be set or adjusted according to the actual situation, and the value range of the matching degree threshold is not limited herein.
[0082] The verification method of the above algorithm optimization result verifies the algorithm optimization of the parameter to be optimized through the data matching degree between the data verification set and the intermediate value of the optimization path, obtains the algorithm optimization result of the parameter to be optimized, realizes the combination of the optimization path of the optimization algorithm and the final result of the optimization algorithm for algorithm optimization verification, obtains the algorithm optimization result of the parameter to be optimized, makes up for the deficiency brought by the closedness of the intelligent algorithm optimization process, realizes the effectiveness verification of the optimization algorithm, and improves the applicable field of the optimization algorithm.
[0083] In one embodiment, as Figure 9 shown, when it is necessary to obtain the algorithm optimization result of the parameter to be optimized, the following content may be included:
[0084] S901, select the target parameter position from the parameter value range of each parameter to be optimized according to the preset verification accuracy requirement.
[0085] S902, use the objective function value at the target parameter position as the data verification value.
[0086] S903, obtain the intermediate value of the optimization path obtained after each round of iterative optimization of the parameter to be optimized during the process of optimizing the parameter to be optimized by the optimization algorithm.
[0087] S904, obtain the first data distribution trend corresponding to the data verification set and the second data distribution trend corresponding to the intermediate value of the optimization path.
[0088] S905, compare the first data distribution trend and the second data distribution trend to obtain the data matching degree between the data verification set and the intermediate value of the optimization path.
[0089] S906, if the data matching degree is greater than the matching degree threshold, determine that the algorithm optimization result of the parameter to be optimized is correct.
[0090] S907, if the data matching degree is not greater than the matching degree threshold, determine that the algorithm optimization result of the parameter to be optimized is incorrect.
[0091] The verification method for the above algorithm optimization result is to obtain the data verification value and the intermediate value of the optimization path obtained after each round of iterative optimization of the parameter to be optimized when optimizing the parameter to be optimized through the objective function. Furthermore, the algorithm optimization verification of the parameter to be optimized is performed according to the data verification set and the intermediate value of the optimization path, and the algorithm optimization result of the parameter to be optimized is obtained. According to the above content, it can be seen that in the process of performing algorithm optimization verification on the parameter to be optimized in this application, the intermediate value of the optimization path obtained after each round of iterative optimization of the parameter to be optimized is obtained, realizing the algorithm optimization verification by combining the optimization path of the optimization algorithm and the final result of the optimization algorithm, making up for the deficiency brought by the closedness of the intelligent algorithm optimization process, realizing the effectiveness verification of the optimization algorithm, and improving the applicable field of the optimization algorithm.
[0092] It should be understood that although the steps in the flowcharts involved in the above embodiments are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least a part of other steps or steps in other steps.
[0093] Based on the same inventive concept, an embodiment of the present application also provides an algorithm optimization result verification device for implementing the verification method for the algorithm optimization result involved above. The implementation solution for solving the problem provided by this device is similar to the implementation solution described in the above method. Therefore, the specific limitations in one or more embodiments of the algorithm optimization result verification device provided below can refer to the limitations on the verification method for the algorithm optimization result in the above text, and will not be repeated here.
[0094] In one embodiment, as Figure 10 shown, an algorithm optimization result verification device is provided, including: a first acquisition module 10, a second acquisition module 20, and a verification module 30, where:
[0095] The first acquisition module 10 is configured to determine the data verification value according to the parameter value range of the parameter to be optimized.
[0096] The second acquisition module 20 is configured to obtain the intermediate value of the optimization path obtained after each round of iterative optimization of the parameter to be optimized when optimizing the parameter to be optimized through the objective function.
[0097] A verification module 30 is configured to perform algorithm optimization verification on the parameter to be optimized according to the data verification set and the intermediate value of the optimization path, so as to obtain the algorithm optimization result of the parameter to be optimized.
[0098] In an embodiment of the present application, according to the preset verification accuracy requirement, a target parameter position is selected from the parameter value range of each parameter to be optimized;
[0099] The value of the objective function at the target parameter position is used as the data verification value.
[0100] In an embodiment of the present application, when the parameter types of the parameters to be optimized are multiple, the amount of data of the data verification value is equal to the product of the number of target parameter positions in each type of parameter to be optimized.
[0101] In an embodiment of the present application, the data matching degree between the data verification set and the intermediate value of the optimization path is obtained;
[0102] Algorithm optimization verification is performed on the parameter to be optimized according to the data matching degree, so as to obtain the algorithm optimization result of the parameter to be optimized.
[0103] In an embodiment of the present application, the first data distribution trend corresponding to the data verification set and the second data distribution trend corresponding to the intermediate value of the optimization path are obtained;
[0104] The first data distribution trend and the second data distribution trend are compared to obtain the data matching degree between the data verification set and the intermediate value of the optimization path.
[0105] In an embodiment of the present application, if the data matching degree is greater than the matching degree threshold, it is determined that the algorithm optimization result of the parameter to be optimized is correct;
[0106] If the data matching degree is not greater than the matching degree threshold, it is determined that the algorithm optimization result of the parameter to be optimized is incorrect.
[0107] The above verification device for the algorithm optimization result obtains the data verification value and the intermediate value of the optimization path obtained after each round of iterative optimization of the parameter to be optimized when performing parameter optimization on the parameter to be optimized through the objective function. Furthermore, algorithm optimization verification is performed on the parameter to be optimized according to the data verification set and the intermediate value of the optimization path, so as to obtain the algorithm optimization result of the parameter to be optimized. According to the above content, it can be seen that in the process of performing algorithm optimization verification on the parameter to be optimized in the present application, the intermediate value of the optimization path obtained after each round of iterative optimization of the parameter to be optimized is obtained, realizing algorithm optimization verification by combining the optimization path of the optimization algorithm and the final result of the optimization algorithm, making up for the deficiency brought by the closedness of the intelligent algorithm optimization process, realizing the effectiveness verification of the optimization algorithm, and improving the applicable field of the optimization algorithm.
[0108] Each module in the verification device for the above algorithm optimization result can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above modules can be embedded in the processor in the computer device in hardware form or independent of it, or stored in the memory in the computer device in software form, so that the processor can call and execute the operations corresponding to each of the above modules.
[0109] In one embodiment, a computer device is provided. The computer device can be a terminal, and its internal structure diagram can be as Figure 11 shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface, the display unit, and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a method for verifying the optimization result of an algorithm. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the computer device housing, or an external keyboard, touchpad, or mouse, etc.
[0110] Those skilled in the art can understand that Figure 11 the structure shown in
[0111] is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.
[0112] Determine a data verification value according to the parameter value range of the parameter to be optimized;
[0113] Obtain the intermediate value of the optimization path obtained after each round of iterative optimization of the parameter to be optimized during the process of parameter optimization of the parameter to be optimized by the optimization algorithm;
[0114] Perform algorithm optimization verification on the parameter to be optimized according to the data verification set and the intermediate value of the optimization path, and obtain the algorithm optimization result of the parameter to be optimized.
[0115] In one embodiment, when the processor executes the computer program, the following steps are further implemented:
[0116] According to the preset verification accuracy requirement, select the target parameter position from the parameter value range of each parameter to be optimized;
[0117] Use the objective function value at the target parameter position as the data verification value.
[0118] [[ID=X]]In one embodiment, when the processor executes the computer program, the following steps are further implemented:
[0119] When the parameter types of the parameters to be optimized are multiple, the amount of data of the data verification value is equal to the product of the number of target parameter positions in each type of parameter to be optimized.
[0120] In one embodiment, when the processor executes the computer program, the following steps are further implemented:
[0121] Obtain the data matching degree between the data verification set and the intermediate value of the optimization path;
[0122] Perform algorithm optimization verification on the parameter to be optimized according to the data matching degree, and obtain the algorithm optimization result of the parameter to be optimized.
[0123] In one embodiment, when the processor executes the computer program, the following steps are further implemented:
[0124] Obtain the first data distribution trend corresponding to the data verification set and the second data distribution trend corresponding to the intermediate value of the optimization path;
[0125] Compare the first data distribution trend and the second data distribution trend to obtain the data matching degree between the data verification set and the intermediate value of the optimization path.
[0126] In one embodiment, when the processor executes the computer program, the following steps are further implemented:
[0127] If the data matching degree is greater than the matching degree threshold, determine that the algorithm optimization result of the parameter to be optimized is correct;
[0128] If the data matching degree is not greater than the matching degree threshold, determine that the algorithm optimization result of the parameter to be optimized is incorrect.
[0129] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:
[0130] Determine a data verification value according to the parameter value range of the parameter to be optimized;
[0131] Obtain the intermediate value of the optimization path obtained after each round of iterative optimization of the parameter to be optimized during the process of optimizing the parameter to be optimized by an optimization algorithm;
[0132] Perform algorithm optimization verification on the parameter to be optimized according to the data verification set and the intermediate value of the optimization path, and obtain the algorithm optimization result of the parameter to be optimized.
[0133] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:
[0134] Select a target parameter position from the parameter value range of each parameter to be optimized according to the preset verification accuracy requirement;
[0135] Use the objective function value at the target parameter position as the data verification value.
[0136] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:
[0137] When the parameter types of the parameters to be optimized are multiple, the amount of data of the data verification value is equal to the product of the number of target parameter positions in each type of parameter to be optimized.
[0138] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:
[0139] Obtain the data matching degree between the data verification set and the intermediate value of the optimization path;
[0140] Perform algorithm optimization verification on the parameter to be optimized according to the data matching degree, and obtain the algorithm optimization result of the parameter to be optimized.
[0141] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:
[0142] Obtain the first data distribution trend corresponding to the data verification set and the second data distribution trend corresponding to the intermediate value of the optimization path;
[0143] Compare the first data distribution trend and the second data distribution trend to obtain the data matching degree between the data verification set and the intermediate value of the optimization path.
[0144] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:
[0145] If the data matching degree is greater than the matching degree threshold, it is determined that the algorithm optimization result of the parameter to be optimized is correct;
[0146] If the data matching degree is not greater than the matching degree threshold, it is determined that the algorithm optimization result of the parameter to be optimized is incorrect.
[0147] In one embodiment, a computer program product is provided, including a computer program which, when executed by a processor, implements the following steps:
[0148] According to the parameter value range of the parameter to be optimized, determine the data verification value;
[0149] Obtain the intermediate optimization path values obtained after each round of iterative optimization of the parameter to be optimized during the process of parameter optimization of the parameter to be optimized by the optimization algorithm;
[0150] Perform algorithm optimization verification on the parameter to be optimized according to the data verification set and the intermediate optimization path values, and obtain the algorithm optimization result of the parameter to be optimized.
[0151] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented:
[0152] According to the preset verification accuracy requirement, select the target parameter positions from the parameter value ranges of each parameter to be optimized;
[0153] Use the objective function value at the target parameter positions as the data verification value.
[0154] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented:
[0155] In the case where the parameter types of the parameters to be optimized are multiple, the amount of data of the data verification value is equal to the product of the number of target parameter positions in each type of parameter to be optimized.
[0156] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented:
[0157] Obtain the data matching degree between the data verification set and the intermediate optimization path values;
[0158] Perform algorithm optimization verification on the parameter to be optimized according to the data matching degree, and obtain the algorithm optimization result of the parameter to be optimized.
[0159] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented:
[0160] Obtain the first data distribution trend corresponding to the data verification set and the second data distribution trend corresponding to the intermediate optimization path values;
[0161] Compare the first data distribution trend with the second data distribution trend to obtain the data matching degree between the data verification set and the intermediate value of the optimization path.
[0162] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:
[0163] If the data matching degree is greater than the matching degree threshold, it is determined that the algorithm optimization result of the parameter to be optimized is correct;
[0164] If the data matching degree is not greater than the matching degree threshold, it is determined that the algorithm optimization result of the parameter to be optimized is incorrect.
[0165] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with the relevant laws, regulations, and standards of relevant countries and regions.
[0166] Those of ordinary skill in the art can understand that all or part of the processes in the above-described embodiment methods can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above various methods. Among them, any reference to a memory, database, or other medium used in the various embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memories can include read-only memory (ROM), magnetic tapes, floppy disks, flash memories, optical memories, high-density embedded non-volatile memories, resistive random access memories (ReRAM), magnetoresistive random access memories (MRAM), ferroelectric random access memories (FRAM), phase change memories (PCM), graphene memories, etc. Volatile memories can include random access memory (RAM) or external cache memories, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the various embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the various embodiments provided in the present application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.
[0167] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as within the scope described in this specification.
[0168] The above embodiments only represent several implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.
Claims
1. A method for verifying the optimization result of an algorithm, characterized in that The method includes: Determining a data verification value according to the parameter value range of the parameter to be optimized; Obtaining intermediate values of the optimization path obtained after each round of iterative optimization of the parameter to be optimized during the parameter optimization of the parameter to be optimized by an optimization algorithm; Performing algorithm optimization verification on the parameter to be optimized according to the data verification set and the intermediate value of the optimization path to obtain the algorithm optimization result of the parameter to be optimized.
2. The method according to claim 1, characterized in that The determining a data verification value according to the parameter value range of the parameter to be optimized includes: Selecting target parameter positions from the parameter value ranges of the parameters to be optimized according to a preset verification accuracy requirement; Using the objective function value at the target parameter position as the data verification value.
3. The method according to claim 2, wherein When there are multiple types of the parameters to be optimized, the amount of data of the data verification value is equal to the product of the number of target parameter positions in each type of the parameters to be optimized.
4. The method according to claim 1, wherein The performing algorithm optimization verification on the parameter to be optimized according to the data verification set and the intermediate value of the optimization path to obtain the algorithm optimization result of the parameter to be optimized includes: Obtaining the data matching degree between the data verification set and the intermediate value of the optimization path; Performing algorithm optimization verification on the parameter to be optimized according to the data matching degree to obtain the algorithm optimization result of the parameter to be optimized.
5. The method according to claim 4, characterized in that The obtaining the data matching degree between the data verification set and the intermediate value of the optimization path includes: Obtaining a first data distribution trend corresponding to the data verification set and a second data distribution trend corresponding to the intermediate value of the optimization path; Comparing the first data distribution trend and the second data distribution trend to obtain the data matching degree between the data verification set and the intermediate value of the optimization path.
6. The method according to claim 4, characterized in that The performing algorithm optimization verification on the parameter to be optimized according to the data matching degree to obtain the algorithm optimization result of the parameter to be optimized includes: If the data matching degree is greater than the matching degree threshold, determining that the algorithm optimization result of the parameter to be optimized is correct; If the data matching degree is not greater than the matching degree threshold, determining that the algorithm optimization result of the parameter to be optimized is incorrect.
7. A verification device for the optimization result of an algorithm, characterized in that The device includes: A first obtaining module, configured to determine a data verification value according to the parameter value range of the parameter to be optimized; A second obtaining module, configured to obtain intermediate values of the optimization path obtained after each round of iterative optimization of the parameter to be optimized when the parameter to be optimized is optimized by an objective function; A verification module, configured to perform algorithm optimization verification on the parameter to be optimized according to the data verification set and the intermediate value of the optimization path to obtain the algorithm optimization result of the parameter to be optimized.
8. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.
10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.