Sorting method and related device for multi-objective optimization results
By dividing the optimization set and calculating the optimization index in multi-objective optimization, the problem of high complexity of multi-objective optimization is solved, efficient sorting and user needs matching are achieved, and user experience is improved.
Patent Information
- Application Number
- CN202111650397.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-12-29
- Publication Date
- 2024-11-05
- Estimated Expiration
- 2041-12-29
AI Technical Summary
In the multi-objective optimization problem, it is difficult to achieve the optimal value of multiple targets at the same time, resulting in high order complexity and low efficiency, and it is difficult for users to intuitively feel which learning result corresponds to the better overall effect.
By determining multiple target parameters of the target product, performing multiple multi-objective optimizations, dividing the optimization set according to the priority level of each target parameter, calculating the reference optimization index and comprehensive optimization index, and then sorting the multiple optimization results to reduce the sorting complexity And improve efficiency.
Converting multi-objective sorting problems into single-objective sorting problems simplifies the sorting process, improves efficiency, and sorts according to the needs and quality of actual industrial products, improving the user experience and the accuracy of sorting.
Smart Images

Figure CN114358409B_ABST
Abstract
Description
Technical Field
[0001] The present application belongs to the field of data processing, and specifically relates to a method for sorting multi-objective optimization results and a related device. Background Art
[0002] Multi-objective optimization refers to the situation where multiple objectives need to be achieved in a certain scenario. Due to the inherent conflicts between objectives, the optimization of one objective is at the expense of other objectives. In other words, the sub-objectives of the multi-objective optimization problem are contradictory. The improvement of one sub-objective may cause the performance of another or several other sub-objectives to decrease. In other words, it is impossible to achieve the optimal value of multiple sub-objectives at the same time. Therefore, it is difficult to find a unique optimal solution. Instead, coordination and compromise can only be made among them to optimize each sub-objective as much as possible. Summary of the invention
[0003] The embodiments of the present application provide a method and related device for sorting multi-objective optimization results, in order to simplify the sorting complexity of the multi-objective optimization results, improve the sorting efficiency, and meet the needs of users.
[0004] In a first aspect, an embodiment of the present application provides a method for ranking multi-objective optimization results, determining multiple target parameters of a target product to be optimized, wherein the target product is an intermediate product or a final product in an industrial production system, and the value of the target parameter is used to measure the quality of the target product;
[0005] Perform multiple multi-objective optimizations on the multiple objective parameters to obtain multiple comprehensive optimization indexes corresponding to the multiple multi-objective optimizations, and the comprehensive optimization index is used to indicate the comprehensive optimization effect of a multi-objective optimization, wherein the following steps are performed for each multi-objective optimization in the multiple multi-objective optimizations: obtain the optimization value of each objective parameter in the multiple objective parameters according to the current multi-objective optimization; determine the first priority level of each objective parameter, and the first priority level is used to indicate the degree of influence of the objective parameter on the quality of the target product; divide the multiple objective parameters according to the first priority level to obtain multiple optimization sets; determine the reference optimization index of each optimization set in the multiple optimization sets according to the optimization value, and the reference optimization index is used to indicate the local optimization effect of the multiple objective parameters included in one optimization set in the current multi-objective optimization; determine the comprehensive optimization index of the current multi-objective optimization according to the reference optimization index of each optimization set;
[0006] The results of the multiple multi-objective optimizations are sorted according to the comprehensive optimization index to obtain a first sorting result.
[0007] In a second aspect, an embodiment of the present application provides a device for sorting multi-objective optimization results, the device comprising:
[0008] A determination unit, used to determine a plurality of target parameters to be optimized for a target product, wherein the target product is an intermediate product or a final product in an industrial production system, and the values of the target parameters are used to measure the quality of the target product;
[0009] An optimization unit is used to perform multiple multi-objective optimizations on the multiple objective parameters to obtain multiple comprehensive optimization indexes corresponding to the multiple multi-objective optimizations, and the comprehensive optimization index is used to indicate the optimization effect for one multi-objective optimization, wherein the following steps are performed for each multi-objective optimization in the multiple multi-objective optimizations: obtaining an optimization value of each of the multiple objective parameters according to the current multi-objective optimization; determining a first priority level for each objective parameter, and the first priority level is used to indicate the degree of influence of the objective parameter on the quality of the target product; dividing the multiple objective parameters according to the first priority level to obtain multiple optimization sets; determining a reference optimization index for each of the multiple optimization sets according to the optimization value, and the reference optimization index is used to indicate the optimization effect for one optimization set in the current multi-objective optimization; determining the comprehensive optimization index of the current multi-objective optimization according to the reference optimization index of each optimization set;
[0010] A sorting unit is used to sort the results of the multiple multi-objective optimizations according to the comprehensive optimization index to obtain a first sorting result.
[0011] In a third aspect, an embodiment of the present application provides an electronic device, comprising a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the program includes instructions for executing the steps in the first aspect of the embodiment of the present application.
[0012] In a fourth aspect, an embodiment of the present application provides a computer storage medium, characterized in that it stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute some or all of the steps described in the first aspect of this embodiment.
[0013] In a fifth aspect, an embodiment of the present application provides a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps described in the first aspect of the embodiment of the present application. The computer program product may be a software installation package.
[0014] It can be seen that in the embodiment of the present application, multiple target parameters are first divided into multiple optimization sets according to the first priority level, and then the reference optimization index of each optimization set is determined, and then the comprehensive optimization index corresponding to a multi-objective optimization is determined according to the reference optimization index of each set, and finally the results of multiple multi-objective optimizations are sorted according to the comprehensive optimization index of each multi-objective optimization to obtain the first sorting result. In this way, by converting the multi-objective sorting problem into a single-objective sorting problem, the complexity of the multi-objective optimization sorting problem is reduced, the sorting efficiency is improved, and the sorting is performed according to the actual needs and quality of industrial products, so that users can directly determine the production parameters and other contents corresponding to a multi-objective optimization learning that can be used for actual production according to the sorting, which meets the actual needs of users and improves the user experience. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0016] Figure 1a is a system architecture diagram of an electronic device provided in an embodiment of the present application;
[0017] Figure 1b It is a structural schematic diagram of an electronic device provided in an embodiment of the present application;
[0018] Figure 2a It is a flowchart of a method for sorting multi-objective optimization results provided in an embodiment of the present application;
[0019] Figure 2b A target parameter management table provided in an embodiment of the present application;
[0020] Figure 3 It is a block diagram of the functional units of a device for sorting multi-objective optimization results provided in an embodiment of the present application;
[0021] Figure 4 It is a block diagram of the functional units of another multi-objective optimization result sorting device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0022] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only 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.
[0023] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.
[0024] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.
[0025] In current industrial production, especially for the production of chemical products, since the target product includes multiple substances, the content of each substance in the target product and the physical properties of the target product will affect the quality of the target product. Therefore, in order to obtain a target product with better quality, learning calculations can be performed through multi-objective optimization to obtain specific data for actual production. However, since it is necessary to perform optimization calculations for multiple objectives at the same time, users cannot intuitively feel which learning result corresponds to a better overall effect.
[0026] In view of the above problems, an embodiment of the present application provides a method for sorting multi-objective optimization results and a related device. The embodiment of the present application is described in detail below in conjunction with the accompanying drawings.
[0027] See also Figure 1a , Figure 1aThis is a system architecture diagram of an electronic device provided in an embodiment of the present application. As shown in the figure, the multi-objective optimization system 101 includes an electronic device 110, and the multi-objective optimization system 101 is also connected to the industrial production system 102 for communication. The multi-objective optimization system 101 can obtain industrial production data from the industrial production system 102, so that the electronic device 110 can perform multi-objective optimization on each target parameter in the target product, and then sort them according to multiple optimization results.
[0028] The structure diagram of the electronic device 110 is as follows Figure 1b As shown, the electronic device 110 includes a processor 120, a memory 130, a communication interface 140, and one or more programs 131, wherein the one or more programs 131 are stored in the memory 130 and are configured to be executed by the processor 120, and the one or more programs 131 include instructions for executing any step in the following method embodiment. In a specific implementation, the processor 120 is used to execute any step executed by the electronic device in the following method embodiment, and when performing data transmission such as sending, the communication interface 140 can be selectively called to complete the corresponding operation.
[0029] See also Figure 2a , Figure 2a 1 is a flow chart of a method for sorting multi-objective optimization results provided in an embodiment of the present application. As shown in the figure, the method for sorting multi-objective optimization results includes the following steps:
[0030] S21, determining a plurality of target parameters of a target product to be optimized, wherein the target product is an intermediate product or a final product in an industrial production system, and the values of the target parameters are used to measure the quality of the target product.
[0031] Wherein, the industrial production system can be a chemical product production system, and the intermediate product is a product generated in the process of producing the final product. For example, the target product can be 18D amine, or a product generated in the process of producing 18D amine, for example, the target product can be nitrile at this time. The target parameter is the parameter content of the target product that can be optimized according to the debugging process parameters or equipment parameters or product parameters, and the quality of the target product can be determined according to market demand or customer demand. The quality includes the quality of the product and the corresponding cost or benefit when producing the target product. The good quality of the target product means that the customer or market has a good evaluation or high demand for the target product under the parameter value. For example, when the target product is 18D amine, the corresponding target parameters that can be used to measure the quality of the target product may include: primary amine content, C18 content, nitrile content, primary amide content, secondary amide content, polyamide content, total amine value, iodine value, chromaticity, freezing point, moisture and yield, so it can be seen that the target parameter may include product parameters and functional index parameters.
[0032] S22, performing multiple multi-objective optimizations on the multiple objective parameters to obtain multiple comprehensive optimization indexes corresponding to the multiple multi-objective optimizations, wherein the comprehensive optimization indexes are used to indicate a comprehensive optimization effect of a multi-objective optimization.
[0033] Among them, by changing the process parameters, product parameters and / or equipment parameters in the production process, multi-objective optimization learning can be performed on the same target product multiple times. The process parameters include the parameter values corresponding to the production process, such as the product addition speed, etc. The equipment parameters are the parameter values corresponding to the equipment used to produce the target product. The product parameters can be the various parameters of the raw materials used for the current production, or the various parameters of the intermediate products generated by the target product. Each multi-objective optimization learning will obtain the parameter values of multiple target parameters of a round of learning. The comprehensive optimization index of a multi-objective optimization can be determined based on these multiple parameter values to determine the effect of the current multi-objective optimization.
[0034] In a specific implementation, the following steps may be performed for each multi-objective optimization in the multiple multi-objective optimizations:
[0035] S221, obtaining an optimized value of each objective parameter among the multiple objective parameters according to the current multi-objective optimization;
[0036] S222: Determine a first priority level for each target parameter, where the first priority level is used to indicate the degree of influence of the target parameter on the quality of the target product.
[0037] Among them, the priority level can be determined according to the current market demand or customer demand, that is, the first priority level can be changed according to the specific applicable scenario. The higher the level of the first priority level, the greater the impact of the target parameter on the quality of the target product. For example, when the target product is 18D amine, the first priority level can be divided into three levels. Since the enterprise is for the purpose of profit, the high priority can be considered from the perspective of company operation. Generally, the target parameters related to the company's profit and cost (material cost, efficiency time cost, etc.) are determined as high priority. Therefore, for the 12 target parameters mentioned above, the yield can be determined as a high priority. The medium priority can be the dimension of product delivery customer quality and market competitiveness. First of all, this parameter is the parameter of the main function of the product. It must meet the customer's quality standards before the customer can use it. At the same time, from the perspective of market competition, the better the parameter value of this parameter, the stronger the competitiveness and the more satisfied the customer. In the product of 18D amine, primary amine is the main component of 18D amine. The higher the primary amine content, the higher the purity of the 18D amine product, and the more satisfied the customer. Nitrile, primary amide, secondary amide and polyamide are subsidiary products. The lower the content, the higher the purity of 18D amine, the more satisfied the customers are and the better the market competitiveness is. Therefore, the seven target parameters of primary amine content, C18 content, nitrile content, primary amide content, secondary amide content, polyamide content and total amine value can be determined as medium priority. The target parameters corresponding to low priority can be non-basic functional indicators of products that are not important from the customer's perspective but must be achieved, such as product appearance and some basic physical properties. For example, since chromaticity belongs to appearance, it has a lower priority and the performance meets the standard. No matter how good the chromaticity is, it will not improve the performance of the product and there is no need to continue to pursue the best. Therefore, the four target parameters of iodine value, chromaticity, freezing point and moisture can be determined as low priority.
[0038] S223: Divide the multiple target parameters according to the first priority level to obtain multiple optimization sets.
[0039] Among them, the first priority levels of the target parameters included in each optimization set are the same, that is, the optimization set can include three, namely, a high-level optimization set including the target parameter of yield, an intermediate optimization set including 7 target parameters of primary amine content, C18 content, nitrile content, primary amide content, secondary amide content, polyamide content, and total amine value, and a low-level optimization set including 4 target parameters of iodine value, chromaticity, freezing point, and moisture.
[0040] S224, determining a reference optimization index of each optimization set in the multiple optimization sets according to the optimization value, wherein the reference optimization index is used to indicate a local optimization effect of multiple objective parameters included in one optimization set in the current multi-objective optimization;
[0041] S225, determining a comprehensive optimization index of the current multi-objective optimization according to the reference optimization index of each optimization set.
[0042] The local optimization effect refers to the optimization effect of all objective parameters included in an optimization set, and the comprehensive optimization index refers to the optimization effect of all objective parameters of a multi-objective optimization.
[0043] S23, sorting the results of the multiple multi-objective optimizations according to the comprehensive optimization index to obtain a first sorting result.
[0044] Among them, each multi-objective optimization result corresponds to a set of process parameters, equipment parameters and product parameters for multi-objective optimization learning. The result of a multi-objective optimization includes the optimized value of each target parameter after optimization, so the process parameters, equipment parameters and product parameters used in actual production can be determined based on the first sorting result. When sorting, the higher the comprehensive optimization index, the higher the corresponding ranking.
[0045] In a specific implementation, if the comprehensive optimization index is the same, the optimization sets of the same level can be sorted according to the reference optimization index. When sorting according to the reference optimization index, the reference optimization index in the optimization set with a higher first priority level is prioritized.
[0046] It can be seen that in this example, multiple objective parameters are first divided into multiple optimization sets according to the first priority level, and then the reference optimization index of each optimization set is determined, and then the comprehensive optimization index corresponding to a multi-objective optimization is determined according to the reference optimization index of each set, and finally the results of multiple multi-objective optimizations are sorted according to the comprehensive optimization index of each multi-objective optimization to obtain the first sorting result. In this way, by converting the multi-objective sorting problem into a single-objective sorting problem, the complexity of the multi-objective optimization sorting problem is reduced, the sorting efficiency is improved, and the sorting is performed according to the actual needs and quality of industrial products, so that users can directly determine the production parameters and other contents corresponding to a multi-objective optimization learning that can be used for actual production according to the sorting, thereby improving the user experience.
[0047] In a possible instance, determining a reference optimization index of each optimization set in the multiple optimization sets according to the optimization value includes: obtaining a target value of each target parameter; determining an optimization weight corresponding to each target parameter according to each optimization set; determining a basic index of each optimization set according to the target value, the optimization value, and the optimization weight; obtaining an optimization direction of each target parameter, wherein the optimization direction is used to indicate an optimization trend of the target parameter; determining an optimization success ratio of each optimization set according to the target value, the optimization direction, and the optimization value, wherein an optimization success means that the optimization value of the target parameter is within a preset range corresponding to the target parameter, wherein the preset range is determined according to the optimization value of the target parameter and the optimization direction of the target parameter; determining a reference optimization index of each optimization set according to the optimization success ratio and the basic index.
[0048] The target value may be determined based on market demand or customer demand, and may be changed in different markets or for different customers. Figure 2b As shown, Figure 2b A target parameter management table is provided in the embodiment of the present application. The target parameter is 18D amine, which includes the 12 target parameters mentioned above. It can be seen that the optimization direction, target value and first priority level (that is, Figure 2b The optimization weight of each target parameter is based on its corresponding optimization set. The basic index can be used to indicate the optimization index of each target parameter in its corresponding optimization set. The optimization direction is used to guide the multi-objective optimization to optimize in which trend, that is, the optimization direction may include three directions: looking big, looking for the right, and looking for the right. Among them, looking big means that the parameter value of the target parameter is as large as possible on the basis of the target value, looking for the right means that the closer the parameter value of the target parameter is to the target value, the better, and looking for the right means that the parameter value of the target parameter is as small as possible on the basis of the target value. Therefore, when the optimization direction is looking big, the preset range is a range greater than or equal to the target value, when the optimization direction is looking small, the preset range is a range less than or equal to the target value, and when the optimization direction is looking for the right, the preset range is the target value. It should be noted that multiple target parameters can have the same target value, or the target value of each target parameter can be different.
[0049] In a specific implementation, the optimization success ratio can be calculated by the following formula: F = M ÷ n, where M is the number of successfully optimized target parameters and n is the total number of all parameters included in the optimization set. For example, if there are two target parameters in the advanced optimization set, then n = 2, and only one of the target parameters has an optimized value within the preset range, i.e., the optimization is successful, then M = 1, and then F = 1 / 2 = 0.5. If the optimized values of both target parameters are not within the preset range, then M = 0, and F = 0 / 2 = 0.
[0050] It can be seen that in this example, the sorting problem of multiple target parameters can be simplified into the sorting problem of multiple optimization sets, reducing the difficulty of sorting. And because the reference optimization index is determined based on the basic index of each target parameter and the optimization success ratio in an optimization set during simplification, the accuracy of sorting can be guaranteed.
[0051] In a possible example, the multiple optimization sets include three, namely, a high-level optimization set, an intermediate optimization set, and a low-level optimization set, and the determining the optimization weight corresponding to each target parameter according to each optimization set includes: determining the first weight corresponding to each optimization set respectively; obtaining the second priority level of the target parameter included in the high-level optimization set, the second priority level being used to indicate the degree of attention paid by the corresponding customers of the target product to the target parameter included in the high-level optimization set; determining the optimization weight corresponding to each target parameter included in the high-level optimization set according to the second priority level and the first weight corresponding to the high-level optimization set; obtaining the product raw material type corresponding to the target product, the product raw material type being used to indicate the functional characteristics of the raw material of the target product; determining the second weight corresponding to each target parameter included in the intermediate optimization set according to the product raw material type; determining the optimization weight corresponding to each target parameter included in the intermediate optimization set according to the second weight and the first weight corresponding to the intermediate optimization set; determining the optimization weight corresponding to each target parameter in the low-level optimization set according to the number of target parameters included in the low-level optimization set and the first weight corresponding to the low-level optimization set, the optimization weight corresponding to each target parameter in the low-level optimization set being the same.
[0052] Among them, the first weight is the basic weight of each optimization set, and the first weights corresponding to optimization sets of different levels may be different. In the advanced optimization set, if the advanced optimization set includes only one target parameter, the first weight corresponding to the advanced optimization set can be determined as the optimization weight of the target parameter. If the advanced optimization set includes multiple target parameters, the second priority level can be determined according to the degree of concern of the customer to the target parameter. For example, the advanced optimization set includes two target parameters A and B. Since the influence of these two target parameters on the quality of the target product is relatively large, it is necessary to grade these two target parameters according to the specific needs of the user, that is, if customer 1 is more concerned about the content of A, then the second priority level of target parameter A is higher than target parameter B at this time. If customer 2 is more concerned about the content of B, then the second priority level of target parameter B is higher than target parameter A at this time. The functional characteristics include but are not limited to the composition index, physical index, chemical index and / or mechanical index of the raw material, and different indexes correspond to different types of product raw materials. Since the product raw materials will have an impact on the cost and time consumption in the manufacturing process during industrial production, different second weights can be determined for different types of product raw materials. For example, when the physical indicator of the raw material of the target product, that is, the physical state, is solid, the cost of producing a target parameter below a certain concentration is higher than that of the raw material whose physical indicator is liquid. Therefore, when the raw material type is different, the corresponding second weight of the target parameter is different. For example, when the physical indicator is liquid, the second weight value of the target parameter is greater than the second weight value when the physical indicator is solid. In this way, the cost and manufacturing difficulty of production can be comprehensively considered, so that the final sorting can better meet the actual production needs. For the low-level optimization set, the target parameters in the low-level optimization set can be weighted by average weighting.
[0053] It can be seen that in this example, a specific optimization weight acquisition method is determined according to optimization sets of different levels, so that the optimization weight of each target parameter is consistent with the importance of each parameter in the target product in actual production, ensuring that the final obtained ranking can meet the actual needs of users and improve the user experience.
[0054] In a possible example, determining the optimization weight corresponding to each target parameter included in the intermediate optimization set according to the second weight and the first weight corresponding to the intermediate optimization set includes: obtaining multiple historical quality evaluation tables for the target chemical product, each of the multiple historical quality evaluation tables including a product score of the target chemical product and a detection value of each target parameter; determining a variation range of the detection value of each target parameter according to the detection value of each target parameter in the multiple historical quality evaluation tables; determining a third weight according to the product score of each historical quality evaluation table and the variation range of the detection value of each target parameter; and determining the optimization weight corresponding to each target parameter included in the intermediate optimization set according to the first weight, the second weight, and the third weight.
[0055] Among them, the historical quality evaluation table can be given by the customer after scoring the values of various parameters included in the previous target products. The change range of the detection value of each target parameter can reflect the customer's attention to the target parameter. That is, if the change range of the detection value of a certain target parameter is large, while the change range of the detection value of other target parameters is small and the product scores of the target products corresponding to the two times with a large difference in the detection value of the target parameter are indeed not much different, it can be determined that the customer's attention to the target parameter is low. If the change range of the detection value of a certain target parameter is large, while the change range of the detection value of other target parameters is small and the product scores of the target products corresponding to the two times with a large difference in the detection value of the target parameter are indeed very different, it can be determined that the customer's attention to the target parameter is high. The higher the customer's attention, the greater the third weight.
[0056] In a specific implementation, determining the variation range of the detection value of each target parameter includes: determining the parameter type of the target parameter, determining the parameter threshold of each target parameter according to the parameter type, wherein each target parameter includes three parameter thresholds divided according to the size of the parameter value; determining the parameter threshold of the detection value of the target parameter in each historical quality evaluation table; determining the number of detection values of the same target parameter in the three parameter thresholds; and determining the variation range of the detection value of each target parameter according to the number of detection values in the three parameter thresholds. For example, the possible detection values 1-100 of parameter X are divided into three parameter thresholds, namely 1-30, 31-60 and 61-100, and the number of parameters of the target parameter X in the first parameter threshold is 5, the number of parameters in the second parameter threshold is 1, and the number of parameters in the third parameter threshold is 0, then it can be determined that the variation range of the target parameter X is small.
[0057] In specific implementation, determining the third weight according to the product scores of each historical quality evaluation form and the change range of the detected values of each target parameter includes: determining at least two historical quality evaluation forms in which the detected ranges of other target parameters except the target parameter for which the third weight is to be determined are less than the preset range among the multiple target parameters according to the change range of the detected values, determining the target historical quality evaluation forms corresponding to the minimum detected value and the maximum detected value of the target parameter for which the third weight is to be determined from the at least two historical quality evaluation forms, and determining the third weight according to the target historical quality evaluation form. For example, target product 18D amine includes 12 target parameters. At this time, if it is necessary to determine the third weight of the target parameter of primary amine content, at least two historical quality evaluation forms need to be determined according to the detected values included in multiple historical quality evaluation forms. The change ranges of the detected values of the other 11 target parameters in these at least two historical quality evaluation forms are small. At this time, only the two historical quality evaluation forms corresponding to the maximum detected value and the minimum detected value of the target parameter of primary amine content need to be determined from the at least two historical quality evaluation forms, and the attention degree of the target parameter of primary amine content is determined according to the corresponding product scores in these two forms, so as to determine the third weight of the target parameter of primary amine content.
[0058] It can be seen that in this example, determining the degree of attention of the target parameter to the customer according to the product scores in the historical quality evaluation form and the detected values of each target parameter can improve the accuracy during sorting and meet the actual production needs of users.
[0059] In a possible example, the basic index P0 is calculated by the following formula:
[0060]
[0061] where Yai is the optimized value of the i-th target parameter in each optimization set, Ybi is the target value of the i-th target parameter in each optimization set, Qi is the optimization weight corresponding to the i-th target parameter in each optimization set, and T is the adjustment coefficient.
[0062] where T is greater than 1, and 0 < Qi <= 1. In specific implementation, to ensure that the optimization index can more clearly reflect the effect of the optimization result, different adjustment coefficients can be determined according to the unit type corresponding to each target parameter.
[0063] It can be seen that in this example, the sorting problem of multiple target parameters can be simplified to the sorting problem of multiple optimization sets, reducing the sorting difficulty. And since the reference optimization index is determined according to the basic index of each target parameter and the optimization success ratio in an optimization set during simplification, the accuracy of sorting can be guaranteed.
[0064] In a possible instance, determining the comprehensive optimization index of the current multi-objective optimization based on the reference optimization index of each optimization set includes: determining the optimization index compliance values corresponding to the multiple optimization sets; determining the compliance status of the multiple optimization sets based on the optimization index compliance values and the reference optimization index of each optimization set; determining the calculation coefficient corresponding to the current multi-objective optimization based on the compliance status; and determining the comprehensive optimization index of the current multi-objective optimization based on the calculation coefficient and the reference optimization index of each optimization set.
[0065] Among them, when determining the comprehensive optimization index, it can be calculated by the following formula: P 综合 =N+C1×P1+C2×P2+...+C n ×P n , where N, C1, C2 and C n All are integers. N, C1, C2 and C corresponding to different compliance conditions are n The values of P1, P2, and P n are the reference optimization index values corresponding to different optimization sets. For example, there are currently three optimization sets: high-level optimization set, medium-level optimization set, and low-level optimization set. The comprehensive optimization index P 综合 =N+C1×P1+C2×P2+C3×P3. In particular, the target values corresponding to different optimization sets may be the same or different.
[0066] It can be seen that in this example, the comprehensive optimization index of each multi-objective optimization is determined according to different target-reaching conditions, which can improve the accuracy of the calculation of the comprehensive optimization index.
[0067] In a possible instance, the multiple optimization sets include three, namely, a high-level optimization set, an intermediate optimization set and a low-level optimization set, and the compliance of the multiple optimization sets includes: the high-level optimization set, the intermediate optimization set and the low-level optimization set all meet the standards; or, the high-level optimization set does not meet the standards, and the intermediate optimization set and the low-level optimization set both meet the standards; or, the intermediate optimization set meets the standards, and the high-level optimization set and the low-level optimization set both do not meet the standards; or, the low-level optimization set meets the standards, and the high-level optimization set and the intermediate optimization set do not meet the standards; or, the high-level optimization set, the intermediate optimization set and the low-level optimization set all do not meet the standards.
[0068] Among them, according to the compliance situation, the values corresponding to multiple reference optimization indices can be divided into 5 regions, namely S0, S1, S2, S3, and S4. The compliance value of the optimization index is determined to be 1. P1 is the reference optimization index corresponding to the high-level optimization set, P2 is the reference optimization index corresponding to the medium-level optimization set, and P3 is the reference optimization index corresponding to the low-level optimization set. Region S0 is defined as: P3 = 1 and P2 >= 1 and P1 >= 1. At this time, when sorting, region S0 can be divided into two sub-regions, S01 and S02. When sorting the multi-objective optimization results of this region, for S01: the larger P1 is, the higher the ranking; for S02: when P1 is equal, the larger P2 is, the higher the ranking. The sorting priority order is: S01 < S02. Region S1 is defined as: P3 = 1 and P2 >= 1 and P1 < 1. At this time, when sorting, region S1 can be divided into two sub-regions, S11 and S12. When sorting the multi-objective optimization results of this region, for S11: the larger P1 is, the higher the ranking; for S12: when P1 is equal, the larger P2 is, the higher the ranking. The sorting priority order is: S11 < S12. Region S2 is defined as: P3 < 1 and P2 >= 1 and P1 < 1. Region S2 is divided into three sub-regions, S21, S22, and S23. When sorting the multi-objective optimization results of this region, for S21: the larger P1 is, the higher the ranking; for S22: when P1 is equal, the larger P2 is, the higher the ranking; for S23: when both P1 and P2 are equal, the larger P3 is, the higher the ranking. The sorting priority order is: S21 < S22 < S23. Region S3 is defined as: P3 = 1 and P2 < 1 and P1 < 1. Then region S3 is divided into two sub-regions, S31 and S32. When sorting the multi-objective optimization results of this region, for S31: the larger P1 is, the higher the ranking; for S32: when P1 is equal, the larger P2 is, the higher the ranking. The sorting priority order is: S31 < S32. Region S4 is defined as P3 < 1 and P2 < 1 and P1 < 1. Region S4 is divided into three sub-regions, S41, S42, and S43. When sorting the multi-objective optimization results of this region, for S41: the larger P1 is, the higher the ranking; for S42: when P1 is equal, the larger P2 is, the higher the ranking; for S43: when P1 and P2 are equal, the larger P3 is, the higher the ranking. The sorting priority order is: S41 < S42 < S43.
[0069] It can be seen that in this embodiment, by determining the comprehensive optimization index of each multi-objective optimization according to different compliance situations, the accuracy of calculating the comprehensive optimization index can be improved.
[0070] Consistent with the above embodiments, please refer to Figure 3 , Figure 3This is a functional unit composition block diagram of a device for sorting multi-objective optimization results provided in an embodiment of the present application. The device 30 for sorting multi-objective optimization results includes: a determination unit 301, used to determine multiple target parameters of a target product to be optimized, wherein the target product is an intermediate product or a final product in an industrial production system, and the value of the target parameter is used to measure the quality of the target product; an optimization unit 302, used to perform multiple multi-objective optimizations on the multiple target parameters to obtain multiple comprehensive optimization indexes corresponding to the multiple multi-objective optimizations, wherein the comprehensive optimization index is used to indicate the optimization effect of a multi-objective optimization, wherein the following steps are performed for each multi-objective optimization in the multiple multi-objective optimizations: obtain the optimized value of each of the multiple target parameters according to the current multi-objective optimization; determine the A first priority level for each target parameter, the first priority level is used to indicate the degree of influence of the target parameter on the quality of the target product; the multiple target parameters are divided according to the first priority level to obtain multiple optimization sets; a reference optimization index of each optimization set in the multiple optimization sets is determined according to the optimization value, and the reference optimization index is used to indicate the optimization effect of an optimization set in the current multi-objective optimization; a comprehensive optimization index of the current multi-objective optimization is determined according to the reference optimization index of each optimization set; a sorting unit 303 is used to sort the results of the multiple multi-objective optimizations according to the comprehensive optimization index to obtain a first sorting result.
[0071] In a possible instance, in terms of determining the reference optimization index of each of the multiple optimization sets according to the optimization value, the optimization unit 302 is specifically used to: determine the reference optimization index of each of the multiple optimization sets according to the optimization value, including: obtaining the target value of each target parameter; determining the optimization weight corresponding to each target parameter according to each optimization set; determining the basic index of each optimization set according to the target value, the optimization value, and the optimization weight; obtaining the optimization direction of each target parameter, the optimization direction is used to indicate the optimization trend of the target parameter; determining the optimization success ratio of each optimization set according to the target value, the optimization direction and the optimization value, the optimization success means that the optimization value of the target parameter is within a preset range corresponding to the target parameter, and the preset range is determined according to the optimization value of the target parameter and the optimization direction of the target parameter; determining the reference optimization index of each optimization set according to the optimization success ratio and the basic index.
[0072] In a possible example, the multiple optimization sets include three, namely, a high-level optimization set, an intermediate optimization set, and a low-level optimization set. In terms of determining the optimization weight corresponding to each target parameter according to each optimization set, the optimization unit 302 is specifically used to: respectively determine the first weight corresponding to each optimization set; obtain the second priority level of the target parameter included in the high-level optimization set, the second priority level is used to indicate the degree of attention of the corresponding customers of the target product to the target parameter included in the high-level optimization set; determine the optimization weight corresponding to each target parameter included in the high-level optimization set according to the second priority level and the first weight corresponding to the high-level optimization set; obtain the product raw material type corresponding to the target product, the product raw material type is used to indicate the functional characteristics of the raw material of the target product; determine the second weight corresponding to each target parameter included in the intermediate optimization set according to the product raw material type; determine the optimization weight corresponding to each target parameter included in the intermediate optimization set according to the second weight and the first weight corresponding to the intermediate optimization set; determine the optimization weight corresponding to each target parameter in the low-level optimization set according to the number of target parameters included in the low-level optimization set and the first weight corresponding to the low-level optimization set, and the optimization weight corresponding to each target parameter in the low-level optimization set is the same.
[0073] In a possible example, in terms of determining the optimization weight corresponding to each target parameter included in the intermediate optimization set according to the second weight and the first weight corresponding to the intermediate optimization set, the optimization unit 302 is specifically used to: obtain multiple historical quality evaluation tables for the target chemical product, each of the multiple historical quality evaluation tables including a product score of the target chemical product and a detection value of each target parameter; determine a variation range of the detection value of each target parameter according to the detection value of each target parameter in the multiple historical quality evaluation tables; determine a third weight according to the product score of each historical quality evaluation table and the variation range of the detection value of each target parameter; and determine the optimization weight corresponding to each target parameter included in the intermediate optimization set according to the first weight, the second weight, and the third weight.
[0074] In a possible example, the basic index P0 is calculated by the following formula:
[0075]
[0076] Among them, Yai is the optimized value of the i-th objective parameter in each optimization set, Ybi is the target value of the i-th objective parameter in each optimization set, Qi is the optimization weight corresponding to the i-th objective parameter in each optimization set, and T is the adjustment coefficient.
[0077] In a possible instance, in terms of determining the comprehensive optimization index of the current multi-objective optimization based on the reference optimization index of each optimization set, the optimization unit 302 is specifically used to: determine the optimization index compliance values corresponding to the multiple optimization sets; determine the compliance status of the multiple optimization sets based on the optimization index compliance values and the reference optimization index of each optimization set; determine the calculation coefficient corresponding to the current multi-objective optimization based on the compliance status; determine the comprehensive optimization index of the current multi-objective optimization based on the calculation coefficient and the reference optimization index of each optimization set.
[0078] In a possible example, the multiple optimization sets include three, namely, a high-level optimization set, an intermediate optimization set and a low-level optimization set. In terms of the compliance of the multiple optimization sets, the optimization unit 302 is specifically used to: the high-level optimization set, the intermediate optimization set and the low-level optimization set all meet the standards; or, the high-level optimization set does not meet the standards, and the intermediate optimization set and the low-level optimization set both meet the standards; or, the intermediate optimization set meets the standards, and the high-level optimization set and the low-level optimization set both do not meet the standards; or, the low-level optimization set meets the standards, and the high-level optimization set and the intermediate optimization set both do not meet the standards; or, the high-level optimization set, the intermediate optimization set and the low-level optimization set all do not meet the standards.
[0079] It can be understood that since the method embodiment and the device embodiment are different presentation forms of the same technical concept, the content of the method embodiment part in this application should be synchronously adapted to the device embodiment part and will not be repeated here.
[0080] In the case of integrated units, such as Figure 4 As shown, Figure 4 This is a functional unit block diagram of another multi-objective optimization result sorting device provided in an embodiment of the present application. Figure 4 In the embodiment, the multi-objective optimization result ranking device 400 includes: a processing module 412 and a communication module 411. The processing module 412 is used to control and manage the actions of the multi-objective optimization result ranking device, for example, to execute the steps of the determination unit 301, the optimization unit 302, and the ranking unit 303, and / or to execute other processes of the technology described herein. The communication module 411 is used for the interaction between the multi-objective optimization result ranking device and other devices. Figure 4 As shown, the device for sorting multi-objective optimization results may further include a storage module 413, and the storage module 413 is used to store program codes and data of the device for sorting multi-objective optimization results.
[0081] Among them, the processing module 412 can be a processor or a controller, for example, a central processing unit (CPU), a general processor, a digital signal processor (DSP), an ASIC, an FPGA or other programmable logic device, a transistor logic device, a hardware component or any combination thereof. It can implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processor can also be a combination that implements a computing function, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like. The communication module 411 can be a transceiver, an RF circuit or a communication interface, and the like. The storage module 413 can be a memory.
[0082] Among them, all relevant contents of each scenario involved in the above method embodiment can be referred to the functional description of the corresponding functional module, and will not be repeated here. The above multi-objective optimization result sorting device 400 can execute the above Figure 2a The ranking method of the multi-objective optimization results is shown.
[0083] The above mainly introduces the scheme of the embodiment of the present application from the perspective of the execution process on the method side. It is understandable that, in order to realize the above functions, the electronic device includes a hardware structure and a software module corresponding to the execution of each function. It should be easily appreciated by those skilled in the art that, in combination with the units and algorithm steps of each example described in the embodiments provided herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present application.
[0084] The embodiment of the present application can divide the electronic device into functional units according to the above method example. For example, each functional unit can be divided according to each function, or two or more functions can be integrated into one processing unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units. It should be noted that the division of units in the embodiment of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation.
[0085] An embodiment of the present application also provides a chip, wherein the chip includes a processor for calling and running a computer program from a memory, so that a device equipped with the chip executes some or all of the steps described for the electronic device in the above method embodiment.
[0086] An embodiment of the present application also provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute part or all of the steps of any method described in the above method embodiments, and the above computer includes an electronic device.
[0087] The embodiment of the present application also provides a computer program product, the computer program product includes a non-transitory computer-readable storage medium storing a computer program, the computer program is operable to cause a computer to execute some or all of the steps of any method described in the method embodiment. The computer program product may be a software installation package, and the computer includes an electronic device.
[0088] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.
[0089] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0090] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the above-mentioned units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.
[0091] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0092] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0093] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the above-mentioned methods of each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or CD-ROM and other media that can store program codes.
[0094] A person skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, and the memory can include: a flash drive, a read-only memory (English: Read-Only Memory, abbreviated as: ROM), a random access memory (English: Random Access Memory, abbreviated as: RAM), a magnetic disk or an optical disk, etc.
[0095] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of the present application. At the same time, for general technical personnel in this field, according to the idea of the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.
[0096] Although the present invention is disclosed as above, the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions without departing from the spirit and scope of the present invention, and can make various changes and modifications, including the combination of the above-mentioned different functions and implementation steps, including software and hardware implementation methods, all of which are within the scope of protection of the present invention.
Claims
1. A ranking method for multi-objective optimization results, It is characterized in that The method comprises: Determining a plurality of target parameters of a target product to be optimized, wherein the target product is an intermediate product or a final product in an industrial production system, and the values of the target parameters are used to measure the quality of the target product; Performing multiple multi-objective optimizations on the multiple objective parameters to obtain multiple comprehensive optimization indexes corresponding to the multiple multi-objective optimizations, wherein the comprehensive optimization index is used to indicate the comprehensive optimization effect of a multi-objective optimization, wherein the following steps are performed for each multi-objective optimization in the multiple multi-objective optimizations: obtaining an optimized value of each objective parameter in the multiple objective parameters according to the current multi-objective optimization; determining a first priority level of each objective parameter, wherein the first priority level is used to indicate the degree of influence of the objective parameter on the quality of the target product; dividing the multiple objective parameters according to the first priority level to obtain multiple optimization sets; Obtain a target value for each target parameter; determine an optimization weight corresponding to each target parameter according to each optimization set; determine a basic index for each optimization set according to the target value, the optimization value, and the optimization weight; obtain an optimization direction for each target parameter, wherein the optimization direction is used to indicate an optimization trend for the target parameter; determine an optimization success ratio for each optimization set according to the target value, the optimization direction, and the optimization value, wherein an optimization success refers to that the optimization value of the target parameter is within a preset range corresponding to the target parameter, wherein the preset range is determined according to the optimization value of the target parameter and the optimization direction of the target parameter; determine a reference optimization index for each optimization set according to the optimization success ratio and the basic index, wherein the reference optimization index is used to indicate a local optimization effect for multiple target parameters included in an optimization set in the current multi-objective optimization; The basic index P 0 Calculated by the following formula: ; Wherein, Yai is the optimized value of the i-th objective parameter in each optimization set, Ybi is the target value of the i-th objective parameter in each optimization set, Qi is the optimization weight corresponding to the i-th objective parameter in each optimization set, and T is the adjustment coefficient; Determine the comprehensive optimization index of the current multi-objective optimization according to the reference optimization index of each optimization set; The results of the multiple multi-objective optimizations are sorted according to the comprehensive optimization index to obtain a first sorting result.
2. The method according to claim 1, It is characterized in that The multiple optimization sets include three, namely, a high-level optimization set, a medium-level optimization set, and a low-level optimization set. Determining the optimization weight corresponding to each target parameter according to each optimization set includes: Determine the first weight corresponding to each optimization set respectively; Acquire a second priority level of the target parameter included in the high-level optimization set, where the second priority level is used to indicate the degree of attention paid by the corresponding customer of the target product to the target parameter included in the high-level optimization set; Determine an optimization weight corresponding to each target parameter included in the advanced optimization set according to the second priority level and the first weight corresponding to the advanced optimization set; Acquire a product raw material type corresponding to the target product, where the product raw material type is used to indicate functional characteristics of the raw material of the target product; Determine a second weight corresponding to each target parameter included in the intermediate optimization set according to the product raw material type; Determine the optimization weight corresponding to each target parameter included in the intermediate optimization set according to the second weight and the first weight corresponding to the intermediate optimization set; According to the number of target parameters included in the low-level optimization set and the first weight corresponding to the low-level optimization set, the optimization weight corresponding to each target parameter in the low-level optimization set is determined, and the optimization weight corresponding to each target parameter in the low-level optimization set is the same.
3. The method according to claim 2, It is characterized in that The determining, according to the second weight and the first weight corresponding to the intermediate optimization set, the optimization weight corresponding to each objective parameter included in the intermediate optimization set comprises: Acquire a plurality of historical quality evaluation tables for the target chemical product, each of the plurality of historical quality evaluation tables including a product score of the target chemical product and a detection value of each target parameter; Determining a variation range of the detection value of each target parameter according to the detection value of each target parameter in the plurality of historical quality evaluation tables; Determine a third weight according to the product score of each historical quality evaluation table and the variation range of the detection value of each target parameter; The optimization weight corresponding to each objective parameter included in the intermediate optimization set is determined according to the first weight, the second weight and the third weight.
4. The method according to claim 1, It is characterized in that The determining the comprehensive optimization index of the current multi-objective optimization according to the reference optimization index of each optimization set includes: Determine the optimization index achievement values corresponding to the multiple optimization sets; Determining the compliance status of the multiple optimization sets according to the optimization index compliance value and the reference optimization index of each optimization set; Determine the calculation coefficient corresponding to the current multi-objective optimization according to the target achievement status; The comprehensive optimization index of the current multi-objective optimization is determined according to the calculation coefficient and the reference optimization index of each optimization set.
5. The method according to claim 4, It is characterized in that The multiple optimization sets include three, namely, a high-level optimization set, a medium-level optimization set and a low-level optimization set. The compliance status of the multiple optimization sets includes: The high-level optimization set, the intermediate optimization set and the low-level optimization set all meet the standards; or, the high-level optimization set does not meet the standards, and the intermediate optimization set and the low-level optimization set both meet the standards; or, the intermediate optimization set meets the standards, and the high-level optimization set and the low-level optimization set both do not meet the standards; or, the low-level optimization set meets the standards, and the high-level optimization set and the intermediate optimization set do not meet the standards; or, the high-level optimization set, the intermediate optimization set and the low-level optimization set all do not meet the standards.
6. A device for sorting multi-objective optimization results, It is characterized in that The device comprises: A determination unit, used to determine a plurality of target parameters to be optimized for a target product, wherein the target product is an intermediate product or a final product in an industrial production system, and the values of the target parameters are used to measure the quality of the target product; An optimization unit is used to perform multiple multi-objective optimizations on the multiple objective parameters to obtain multiple comprehensive optimization indexes corresponding to the multiple multi-objective optimizations, wherein the comprehensive optimization index is used to indicate the optimization effect of a multi-objective optimization, wherein the following steps are performed for each multi-objective optimization in the multiple multi-objective optimizations: obtaining an optimized value of each objective parameter in the multiple objective parameters according to the current multi-objective optimization; determining a first priority level of each objective parameter, wherein the first priority level is used to indicate the degree of influence of the objective parameter on the quality of the target product; and dividing the multiple objective parameters according to the first priority level to obtain multiple optimization sets; and for obtaining the target value of each target parameter; determining the optimization weight corresponding to each target parameter according to each optimization set; determining the basic index of each optimization set according to the target value, the optimization value and the optimization weight; obtaining the optimization direction of each target parameter, wherein the optimization direction is used to indicate the optimization trend of the target parameter; determining the optimization success ratio of each optimization set according to the target value, the optimization direction and the optimization value, wherein optimization success means that the optimization value of the target parameter is within the preset range corresponding to the target parameter, wherein the preset range is determined according to the optimization value of the target parameter and the optimization direction of the target parameter; determining the reference optimization index of each optimization set according to the optimization success ratio and the basic index, wherein the reference optimization index is used to indicate the optimization effect for an optimization set in the current multi-objective optimization; The basic index P 0 Calculated by the following formula: ; Wherein, Yai is the optimized value of the i-th objective parameter in each optimization set, Ybi is the target value of the i-th objective parameter in each optimization set, Qi is the optimization weight corresponding to the i-th objective parameter in each optimization set, and T is the adjustment coefficient; and for determining the comprehensive optimization index of the current multi-objective optimization according to the reference optimization index of each optimization set; A sorting unit is used to sort the results of the multiple multi-objective optimizations according to the comprehensive optimization index to obtain a first sorting result.
7. An electronic device, It is characterized in that The method comprises a processor, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the programs include instructions for executing the steps in the method according to any one of claims 1 to 5.
8. A computer-readable storage medium, It is characterized in that A computer program for electronic data exchange is stored, wherein the computer program enables a computer to execute the method according to any one of claims 1 to 5.
