An evolutionary optimization method and system for e-government performance evaluation management

Through the calculation of the initial population and fitness function value of chromosome formalized random vectors and combined with the cross-operation of variants, the assessment and scoring order of the e-government performance appraisal management system is optimized, which solves the problems of low efficiency and insufficient intelligence in the existing system, and realizes efficient intelligence assessment management.

CN113487142BActive Publication Date: 2024-11-12SUQIAN YUANTONG INTELLIGENT TECH CO LTD +3
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202110660964.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-06-15
Publication Date
2024-11-12
Estimated Expiration
2041-06-15

AI Technical Summary

Technical Problem

The existing e-government performance appraisal management system is difficult to efficiently push assessment tasks and optimize the assessment scoring order, resulting in low efficiency, insufficient intelligence and poor user experience.

Method used

The initial population of chromosome formalized random vectors, the calculation of fitness function value, the cross-operation of chromosome vector sorting and variation are used to generate chromosome vectors that meet the optimization goals through iterative optimization, and the scoring order of the assessment indicators is optimized.

Benefits of technology

It realizes efficient and intelligent operation of e-government performance appraisal management, and targeted assessment tasks are pushed and optimized according to the scoring conditions and priorities in different situations.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113487142B_ABST
    Figure CN113487142B_ABST
Patent Text Reader

Abstract

The invention discloses an evolutionary optimization method for e-government performance assessment management, including: constructing an initial population of chromosome formalized random vectors of e-government performance assessment indicators; calculating a fitness function value according to the scoring completion status, importance weight and special priority setting value of the e-government performance assessment indicators; sorting the chromosome vectors of the e-government performance assessment indicators according to the fitness function value, and judging whether the optimal chromosome vector meets the optimization target; if the optimal chromosome vector meets the optimization target, the algorithm is terminated; otherwise, generating a new chromosome vector through a mutation operation of the chromosome vector and a crossover operation between two chromosome vectors, adding the new chromosome vector to the current population, calculating the fitness function value of the new chromosome vector, sorting all chromosome vectors of the current population according to the fitness function value, and eliminating the last chromosome vector; then judging whether the optimal chromosome vector meets the optimization target, if the optimal chromosome vector meets the optimization target, the algorithm is terminated; otherwise, performing iterative evolutionary optimization again through the mutation operation and crossover operation until the optimal chromosome vector meets the optimization target. The method can promote the efficiency improvement and intelligence of e-government performance assessment management.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of e-government management, and in particular to an evolutionary optimization method and system for e-government performance evaluation management. Background Art

[0002] Since e-government performance appraisal management is highly professional, policy-changing, unknown, and time-space-constrained, the labor cost of on-site management is high and there are many uncertain factors. Therefore, the efficient delivery of appraisal tasks and optimization of the order of appraisal scores in e-government performance appraisal management have always been difficult.

[0003] Most traditional e-government services are unable to efficiently push assessment tasks and optimize the order of assessment scores in e-government performance appraisal management. They are non-bionic conventional programming methods, and their intelligence, calculation schemes and scoring time all need to be optimized. They cannot imitate the intelligent computing and evolutionary optimization capabilities of biological genetic systems, thus resulting in lower e-government efficiency, lack of intelligence and poor user experience in the weak links of complex and changeable e-government performance appraisal management services. Summary of the invention

[0004] (I) Purpose of the invention

[0005] The purpose of the present invention is to provide an evolutionary optimization method and system for e-government performance appraisal management to solve the problem that existing e-government software is difficult to efficiently push appraisal tasks and optimize the appraisal scoring order service.

[0006] (II) Technical solution

[0007] To solve the above problems, the first aspect of the present invention provides an evolutionary optimization method for e-government performance appraisal management, including: constructing an initial population of chromosome-formalized random vectors of e-government performance appraisal indicators; calculating a fitness function value according to the scoring completion status, importance weight and special priority setting value of the e-government performance appraisal indicators; sorting the chromosome vectors of the e-government performance appraisal indicators according to the fitness function value, and judging whether the optimal chromosome vector meets the optimization goal; if the optimal chromosome vector meets the optimization goal, the algorithm is terminated; otherwise, a new chromosome vector is generated through a mutation operation of the chromosome vector and a crossover operation between two chromosome vectors, the new chromosome vector is added to the current population, the fitness function value of the new chromosome vector is calculated, and all chromosome vectors of the current population are sorted according to the fitness function value, and the last chromosome vector is eliminated; then judging whether the optimal chromosome vector meets the optimization goal, if the optimal chromosome vector meets the optimization goal, the algorithm is terminated; otherwise, iterative evolutionary optimization is performed again through the mutation operation and crossover operation until the optimal chromosome vector meets the optimization goal.

[0008] Furthermore, the steps for constructing the chromosome-formalized random vector initial population of e-government performance appraisal indicators include: entering the name of the e-government performance appraisal indicator; entering the value range of the e-government performance appraisal indicator; entering the importance weight of the e-government performance appraisal indicator; entering the scoring standard of the e-government performance appraisal indicator; entering the special priority setting value of the scoring order of the e-government performance appraisal indicator; entering the random initial priority sorting number of the e-government performance appraisal indicator; and entering the scoring completion progress value of the e-government performance appraisal indicator.

[0009] Furthermore, the step of calculating the fitness function value according to the scoring completion status, importance weight and special priority setting value of the e-government performance appraisal indicators includes: the priority setting of the e-government performance appraisal indicators that have completed scoring is lower than the priority setting of the e-government performance appraisal indicators that have not completed scoring, the e-government performance appraisal indicators that have completed scoring are sorted according to their initial serial numbers, and the fitness function values ​​are set; the greater the importance weight of the e-government performance appraisal indicators that have not completed scoring, the higher the priority setting and the greater the fitness function value; and the fitness function value is calculated according to the special priority setting value when other conditions are the same.

[0010] Furthermore, the chromosome vectors of the e-government performance evaluation indicators are sorted according to the fitness function value to determine whether the optimal chromosome vector meets the optimization target; if the optimal chromosome vector meets the optimization target, the algorithm is terminated; otherwise, a new chromosome vector is generated through a mutation operation of the chromosome vector and a crossover operation between two chromosome vectors, the new chromosome vector is added to the current population, the fitness function value of the new chromosome vector is calculated, all chromosome vectors of the current population are sorted according to the fitness function value, and the chromosome vector at the bottom is eliminated; then determine whether the optimal chromosome vector meets the optimization target, if the optimal chromosome vector meets the optimization target, the algorithm is terminated; otherwise, iterative evolutionary optimization is performed again through the mutation operation and crossover operation until the optimal chromosome vector meets the optimization target.

[0011] According to another aspect of the present invention, an evolutionary optimization system for e-government performance appraisal management is provided, including: a chromosome-formalized random vector initial population construction module for e-government performance appraisal indicators, which is used to construct the chromosome-formalized random vector initial population for e-government performance appraisal indicators; a fitness function value calculation module, which is used to calculate the fitness function value according to the scoring completion status, importance weight and special priority setting value of the e-government performance appraisal indicators; a chromosome vector sorting and optimization target judgment module, which is used to sort the chromosome vectors of the e-government performance appraisal indicators according to the fitness function value, and judge whether the optimal chromosome vector meets the optimization target; a chromosome vector mutation and crossover operation module, which is used to generate a new chromosome vector through a mutation operation of the chromosome vector and a crossover operation between two of the chromosome vectors, the new chromosome vector is added to the current population, the fitness function value of the new chromosome vector is calculated, all chromosome vectors of the current population are sorted according to the fitness function value, and the chromosome vector at the last position is eliminated.

[0012] Furthermore, the chromosome-formalized random vector initial population construction module of the e-government performance appraisal indicators includes: a name input unit for the e-government performance appraisal indicators, which is used to input the names of the e-government performance appraisal indicators; a value range input unit for the e-government performance appraisal indicators, which is used to input the value range of the e-government performance appraisal indicators; an importance weight input unit for the e-government performance appraisal indicators, which is used to input the importance weight of the e-government performance appraisal indicators; a scoring standard input unit for the e-government performance appraisal indicators, which is used to input the scoring standard of the e-government performance appraisal indicators; a special priority setting value input unit for the scoring order of the e-government performance appraisal indicators, which is used to input the special priority setting value for the scoring order of the e-government performance appraisal indicators; a random initial ranking number input unit for the priority of the e-government performance appraisal indicators, which is used to input the random initial ranking number of the priority of the e-government performance appraisal indicators; and an e-government performance appraisal indicator scoring completion progress value input unit, which is used to input the scoring completion progress value of the e-government performance appraisal indicators.

[0013] Furthermore, the fitness function value calculation module includes: a fitness function value setting unit for indicators that have completed scoring, which is used to set fitness function values ​​for indicators that have completed scoring, the priority setting of the e-government performance appraisal indicators that have completed scoring is lower than the priority setting of the e-government performance appraisal indicators that have not completed scoring, and the e-government performance appraisal indicators that have completed scoring are sorted according to their initial serial numbers; a fitness function value setting unit for unscored indicators, which is used to set fitness function values ​​for unscored indicators, the greater the importance weight of the unscored e-government performance appraisal indicators, the higher the priority setting, and the greater the fitness function value; a special priority setting unit, which is used to set the fitness function value according to the special priority setting value when other conditions are equal.

[0014] Furthermore, it also includes the chromosome vector mutation and crossover operation module, which is used to sort the chromosome vectors of the e-government performance evaluation indicators according to the fitness function value, and determine whether the optimal chromosome vector meets the optimization goal; if the optimal chromosome vector meets the optimization goal, the algorithm is terminated; otherwise, a new chromosome vector is generated through the mutation operation of the chromosome vector and the crossover operation between two of the chromosome vectors, and the new chromosome vector is added to the current population, and the fitness function value of the new chromosome vector is calculated. All chromosome vectors of the current population are sorted according to the fitness function value, and the chromosome vector at the last position is eliminated; then determine whether the optimal chromosome vector meets the optimization goal, if the optimal chromosome vector meets the optimization goal, the algorithm is terminated; otherwise, iterative evolutionary optimization is performed again through the mutation operation and crossover operation until the optimal chromosome vector meets the optimization goal.

[0015] (III) Beneficial effects

[0016] The above technical solution of the present invention has the following beneficial technical effects:

[0017] This method and system can be used to perform evolutionary optimization on complex situations involving intelligence and optimization in e-government performance appraisal management, and set up targeted appraisal task push, intelligent management and optimization according to the scoring conditions and priorities of different situations, thus ensuring the efficient and intelligent operation of e-government performance appraisal management. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a flow chart of the evolutionary optimization method for e-government performance evaluation management in the first embodiment of the present invention;

[0019] Figure 2 It is a schematic diagram of the structure of an evolutionary optimization system for e-government performance evaluation management in an optional implementation mode of the present invention;

[0020] Figure 3 It is a flow chart of an evolutionary optimization algorithm for e-government performance appraisal management in an optional implementation mode of the present invention. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical scheme and advantages of the present invention clearer, the present invention is further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings. It should be understood that these descriptions are only exemplary and are not intended to limit the scope of the present invention. In addition, in the following description, the description of well-known structures and technologies is omitted to avoid unnecessary confusion of the concept of the present invention.

[0022] Obviously, the described embodiments are only some embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] In addition, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0024] like Figure 1 As shown, in the first aspect of the embodiment of the invention, an evolutionary optimization method for e-government performance appraisal management is provided, including: constructing an initial population of chromosome-formalized random vectors of e-government performance appraisal indicators; calculating fitness function values ​​according to the scoring completion status, importance weights and special priority setting values ​​of the e-government performance appraisal indicators; sorting the chromosome vectors of the e-government performance appraisal indicators according to the fitness function values, and judging whether the optimal chromosome vector meets the optimization goal; if the optimal chromosome vector meets the optimization goal, the algorithm is terminated; otherwise, a new chromosome vector is generated through a mutation operation of the chromosome vector and a crossover operation between two of the chromosome vectors, the new chromosome vector is added to the current population, the fitness function value of the new chromosome vector is calculated, all chromosome vectors of the current population are sorted according to the fitness function value, and the last chromosome vector is eliminated; then judging whether the optimal chromosome vector meets the optimization goal, if the optimal chromosome vector meets the optimization goal, the algorithm is terminated; otherwise, iterative evolutionary optimization is performed again through the mutation operation and crossover operation until the optimal chromosome vector meets the optimization goal.

[0025] The above-mentioned embodiment method can carry out evolutionary optimization of e-government performance appraisal management to address the problem that existing e-government software has difficulty in efficiently pushing appraisal tasks and optimizing appraisal scoring order services, and can set up targeted appraisal task push, intelligent management and optimization according to the scoring conditions and priorities in different situations, thereby ensuring the efficient and intelligent operation of e-government performance appraisal management.

[0026] Optionally, the steps for constructing the initial population of chromosome-formalized random vectors of e-government performance appraisal indicators include: entering the name of the e-government performance appraisal indicator; entering the value range of the e-government performance appraisal indicator; entering the importance weight of the e-government performance appraisal indicator; entering the scoring standard of the e-government performance appraisal indicator; entering the special priority setting value of the scoring order of the e-government performance appraisal indicator; entering the random initial priority sorting number of the e-government performance appraisal indicator; and entering the scoring completion progress value of the e-government performance appraisal indicator.

[0027] Optionally, the step of calculating the fitness function value according to the scoring completion status, importance weight and special priority setting value of the e-government performance appraisal indicators includes: setting the priority of the e-government performance appraisal indicators that have completed scoring to be lower than the priority of the e-government performance appraisal indicators that have not completed scoring; the e-government performance appraisal indicators that have completed scoring are sorted according to their initial serial numbers, and the fitness function values ​​are set; the greater the importance weight of the e-government performance appraisal indicators that have not completed scoring, the higher the priority setting and the greater the fitness function value; and calculating the fitness function value according to the special priority setting value when other conditions are the same.

[0028] Optionally, the chromosome vectors of the e-government performance evaluation indicators are sorted according to the fitness function value to determine whether the optimal chromosome vector meets the optimization goal; if the optimal chromosome vector meets the optimization goal, the algorithm is terminated; otherwise, a new chromosome vector is generated through a mutation operation of the chromosome vector and a crossover operation between two chromosome vectors, the new chromosome vector is added to the current population, the fitness function value of the new chromosome vector is calculated, all chromosome vectors of the current population are sorted according to the fitness function value, and the last chromosome vector is eliminated; then determine whether the optimal chromosome vector meets the optimization goal, if the optimal chromosome vector meets the optimization goal, the algorithm is terminated; otherwise, iterative evolutionary optimization is performed again through the mutation operation and crossover operation until the optimal chromosome vector meets the optimization goal.

[0029] In another aspect of the embodiments of the present invention, an evolutionary optimization system for e-government performance appraisal management is provided, including: a chromosome-formalized random vector initial population construction module for e-government performance appraisal indicators, which is used to construct the chromosome-formalized random vector initial population for e-government performance appraisal indicators; a fitness function value calculation module, which is used to calculate the fitness function value according to the scoring completion status, importance weight and special priority setting value of the e-government performance appraisal indicators; a chromosome vector sorting and optimization target judgment module, which is used to sort the chromosome vectors of the e-government performance appraisal indicators according to the fitness function value, and judge whether the optimal chromosome vector meets the optimization target; a chromosome vector mutation and crossover operation module, which is used to generate a new chromosome vector through a mutation operation of the chromosome vector and a crossover operation between two of the chromosome vectors, the new chromosome vector is added to the current population, the fitness function value of the new chromosome vector is calculated, all chromosome vectors of the current population are sorted according to the fitness function value, and the chromosome vector at the last position is eliminated.

[0030] Optionally, the chromosome-formalized random vector initial population construction module of the e-government performance appraisal indicators includes: a name input unit for the e-government performance appraisal indicators, used to input the names of the e-government performance appraisal indicators; a value range input unit for the e-government performance appraisal indicators, used to input the value range of the e-government performance appraisal indicators; an importance weight input unit for the e-government performance appraisal indicators, used to input the importance weight of the e-government performance appraisal indicators; a scoring standard input unit for the e-government performance appraisal indicators, used to input the scoring standard for the e-government performance appraisal indicators; a special priority setting value input unit for the scoring order of the e-government performance appraisal indicators, used to input the special priority setting value for the scoring order of the e-government performance appraisal indicators; a random initial ranking number input unit for the priority of the e-government performance appraisal indicators, used to input the random initial ranking number of the priority of the e-government performance appraisal indicators; and an e-government performance appraisal indicator scoring completion progress value input unit, used to input the scoring completion progress value of the e-government performance appraisal indicators.

[0031] Optionally, the fitness function value calculation module includes: a fitness function value setting unit for indicators that have completed scoring, which is used to set fitness function values ​​for indicators that have completed scoring, the priority setting of the e-government performance appraisal indicators that have completed scoring is lower than the priority setting of the e-government performance appraisal indicators that have not completed scoring, and the e-government performance appraisal indicators that have completed scoring are sorted according to their initial serial numbers; a fitness function value setting unit for unscored indicators, which is used to set fitness function values ​​for unscored indicators, the greater the importance weight of the unscored e-government performance appraisal indicators, the higher the priority setting, and the greater the fitness function value; a special priority setting unit, which is used to set the fitness function value according to the special priority setting value when other conditions are equal.

[0032] Optionally, it also includes the chromosome vector mutation and crossover operation module, which is used to sort the chromosome vectors of the e-government performance evaluation indicators according to the fitness function value, and determine whether the optimal chromosome vector meets the optimization goal; if the optimal chromosome vector meets the optimization goal, the algorithm is terminated; otherwise, a new chromosome vector is generated through the mutation operation of the chromosome vector and the crossover operation between two chromosome vectors, the new chromosome vector is added to the current population, the fitness function value of the new chromosome vector is calculated, and all chromosome vectors of the current population are sorted according to the fitness function value, and the last chromosome vector is eliminated; then determine whether the optimal chromosome vector meets the optimization goal, if the optimal chromosome vector meets the optimization goal, the algorithm is terminated; otherwise, iterative evolutionary optimization is performed again through the mutation operation and crossover operation until the optimal chromosome vector meets the optimization goal.

[0033] In an optional embodiment, a self-designed evolutionary optimization algorithm for e-government performance appraisal management is provided. This embodiment constructs an evolutionary optimization system for e-government performance appraisal management according to the following steps.

[0034] 1. Construct an evolutionary optimization system for e-government performance evaluation management

[0035] The evolutionary optimization system of e-government performance appraisal management is composed of a chromosome formalized random vector initial population construction module of e-government performance appraisal indicators, a fitness function value calculation module, a chromosome vector sorting and optimization target judgment module, and a chromosome vector mutation crossover operation module. The fitness function value calculation module, the chromosome vector sorting and optimization target judgment module, and the chromosome vector mutation crossover operation module are the evolutionary computing centers of the evolutionary optimization system of e-government performance appraisal management. Figure 2The evolutionary optimization algorithm of e-government performance evaluation management is the core optimization algorithm of the evolutionary optimization system of e-government performance evaluation management, which mainly includes the following steps: random population initialization; fitness function value calculation; optimization selection operation; mutation operation; crossover operation and iterative judgment and calculation operation, such as Figure 3 shown.

[0036] 2. Construct a randomly initialized population

[0037] When constructing an evolutionary optimization system for e-government performance appraisal management, first construct the necessary chromosome-formalized random vector initial population construction module for the e-government performance appraisal indicators, including an e-government performance test indicator name input unit, an e-government performance appraisal indicator value range input unit, an e-government performance appraisal indicator importance weight input unit, an e-government performance appraisal indicator scoring standard input unit, an e-government performance appraisal indicator scoring order special priority setting value input unit, an e-government performance appraisal indicator priority random initial sorting number input unit and an e-government performance appraisal indicator scoring completion progress value input unit.

[0038] The name input unit of the e-government performance examination indicator is used to enter the name of the e-government performance evaluation indicator.

[0039] The value range input unit of the e-government performance evaluation index is used to input the value range of the e-government performance evaluation index.

[0040] The importance weight input unit of the e-government performance appraisal indicator is used to input the importance weight of the e-government performance appraisal indicator.

[0041] The scoring standard input unit for e-government performance appraisal indicators is used to input the scoring standard for e-government performance appraisal indicators.

[0042] The special priority setting value input unit for the scoring order of e-government performance appraisal indicators is used to input the special priority setting values ​​for the scoring order of e-government performance appraisal indicators.

[0043] The priority random initial ranking number input unit of the e-government performance evaluation indicators is used to input the priority random initial ranking number of the e-government performance evaluation indicators.

[0044] The scoring completion progress value input unit of the e-government performance appraisal indicator is used to input the scoring completion progress value of the e-government performance appraisal indicator.

[0045] 3. Constructing an optimization selection operator

[0046] According to the fitness function values ​​of the chromosome vector individuals in the population, the individuals with the largest fitness function value are selected as the optimal individuals, which are also the e-government performance evaluation indicators with the highest scoring priority. The individuals with the worst fitness function values ​​are eliminated at the end to complete the optimization selection operation of the population. The priority setting of the e-government performance evaluation indicators that have completed scoring is lower than the priority setting of the e-government performance evaluation indicators that have not completed scoring. The e-government performance evaluation indicators that have completed scoring are sorted according to the initial serial numbers of the indicators, and the fitness function values ​​are set. The greater the importance weight of the e-government performance evaluation indicators that have not completed scoring, the higher its priority setting and the greater its fitness function value. The fitness function value is calculated according to the special priority setting value when other conditions are the same.

[0047] 4. Construct mutation operator

[0048] A chromosome vector individual is randomly selected from the population, and the priority sorting number of the chromosome vector individual is randomly mutated to generate a new chromosome vector individual, thus completing the mutation operation of the population.

[0049] 5. Constructing the crossover operator

[0050] Two chromosome vector individuals are randomly selected from the population, and the priority sorting numbers of the two chromosome vector individuals are exchanged to generate two new chromosome vector individuals, thus completing the crossover operation of the population.

[0051] The above is just an example. The evolutionary optimization process of e-government performance evaluation management in the example is as follows: Figure 1 The evolutionary optimization system of e-government performance evaluation management adopted in this example can be extended to other e-government systems to achieve intelligent management and optimization of e-government systems.

[0052] The present invention aims to protect an evolutionary optimization method for e-government performance appraisal management, including: constructing an initial population of chromosome-formalized random vectors of e-government performance appraisal indicators; calculating a fitness function value according to the scoring completion status, importance weights and special priority setting values ​​of the e-government performance appraisal indicators; sorting the chromosome vectors of the e-government performance appraisal indicators according to the fitness function values, and judging whether the optimal chromosome vector meets the optimization goal; if the optimal chromosome vector meets the optimization goal, terminating the algorithm; otherwise, generating a new chromosome vector through a mutation operation of the chromosome vector and a crossover operation between two chromosome vectors, adding the new chromosome vector to the current population, calculating the fitness function value of the new chromosome vector, sorting all chromosome vectors of the current population according to the fitness function value, and eliminating the chromosome vector at the bottom; then judging whether the optimal chromosome vector meets the optimization goal, if the optimal chromosome vector meets the optimization goal, terminating the algorithm; otherwise, performing iterative evolutionary optimization through the mutation operation and crossover operation again until the optimal chromosome vector meets the optimization goal.

[0053] It should be understood that the above specific embodiments of the present invention are only used to illustrate or explain the principles of the present invention, and do not constitute a limitation of the present invention. Therefore, any modifications, equivalent substitutions, improvements, etc. made without departing from the spirit and scope of the present invention should be included in the protection scope of the present invention. In addition, the appended claims of the present invention are intended to cover all changes and modifications that fall within the scope and boundaries of the appended claims, or the equivalent forms of such scope and boundaries.

Claims

1. An evolutionary optimization method for e-government performance appraisal management, It is characterized in that include: Constructing the initial population of random vectors in the chromosome formalization of e-government performance evaluation indicators; The fitness function value is calculated according to the scoring completion status, importance weight and special priority setting value of the e-government performance evaluation indicators. The step includes: the priority setting of the e-government performance evaluation indicators that have completed scoring is lower than the priority setting of the e-government performance evaluation indicators that have not completed scoring, the e-government performance evaluation indicators that have completed scoring are sorted according to the initial sequence numbers of the indicators, and the fitness function value is set; the greater the importance weight of the e-government performance evaluation indicators that have not completed scoring, the higher the priority setting and the greater the fitness function value; and the fitness function value is calculated according to the special priority setting value when other conditions are the same; Sort the chromosome vectors of the e-government performance evaluation indicators according to the fitness function value, and determine whether the optimal chromosome vector meets the optimization goal; If the optimal chromosome vector meets the optimization goal, the algorithm ends; Otherwise, a new chromosome vector is generated by a mutation operation of the chromosome vector and a crossover operation between two chromosome vectors, the new chromosome vector is added to the current population, the fitness function value of the new chromosome vector is calculated, all chromosome vectors of the current population are sorted according to the fitness function value, and the chromosome vector at the bottom is eliminated; Then determine whether the optimal chromosome vector meets the optimization goal. If the optimal chromosome vector meets the optimization goal, end the algorithm; Otherwise, the iterative evolutionary optimization is performed again through the mutation operation and the crossover operation until the optimal chromosome vector meets the optimization goal.

2. According to claim 1, the evolutionary optimization method for e-government performance evaluation management, It is characterized in that The steps of constructing the chromosome formalized random vector initial population of the e-government performance evaluation index include: Enter the name of the e-government performance evaluation indicator; Enter the value range of e-government performance evaluation indicators; Enter the importance weights of e-government performance evaluation indicators; Enter the scoring criteria for e-government performance evaluation indicators; Enter the special priority setting values ​​for the scoring order of e-government performance evaluation indicators; Enter the random initial ranking number of the priority of the e-government performance evaluation indicators; and Enter the scoring completion progress value of the e-government performance evaluation indicators.

3. An evolutionary optimization system for e-government performance assessment management, It is characterized in that include: A chromosome-formalized random vector initial population construction module for e-government performance evaluation indicators, which is used to construct a chromosome-formalized random vector initial population for e-government performance evaluation indicators; A fitness function value calculation module, used to calculate the fitness function value according to the scoring completion status, importance weight and special priority setting value of the e-government performance evaluation indicator; The fitness function value calculation module includes: a fitness function value setting unit for the indicators that have been scored, which is used to set the fitness function value for the indicators that have been scored, the priority setting of the e-government performance assessment indicators that have been scored is lower than the priority setting of the e-government performance assessment indicators that have not been scored, and the e-government performance assessment indicators that have been scored are sorted according to the initial sequence numbers of the indicators; a fitness function value setting unit for the indicators that have not been scored, which is used to set the fitness function value for the indicators that have not been scored, the greater the importance weight of the e-government performance assessment indicators that have not been scored, the higher the priority setting, and the greater the fitness function value; A special priority setting unit, used to set the fitness function value according to the special priority setting value when other conditions are equal; A chromosome vector sorting and optimization target judgment module is used to sort the chromosome vectors of the e-government performance evaluation indicators according to the fitness function value and judge whether the optimal chromosome vector meets the optimization target; The chromosome vector mutation and crossover operation module is used to generate a new chromosome vector through the mutation operation of the chromosome vector and the crossover operation between the two chromosome vectors, the new chromosome vector is added to the current population, the fitness function value of the new chromosome vector is calculated, all the chromosome vectors of the current population are sorted according to the fitness function value, and the chromosome vector at the bottom is eliminated; the chromosome vector mutation and crossover operation module is used to sort the chromosome vectors of the e-government performance evaluation indicators according to the fitness function value, and judge whether the optimal chromosome vector meets the optimization target; if the optimal chromosome vector meets the optimization target, the algorithm is terminated; otherwise, a new chromosome vector is generated through the mutation operation of the chromosome vector and the crossover operation between the two chromosome vectors, the new chromosome vector is added to the current population, the fitness function value of the new chromosome vector is calculated, all the chromosome vectors of the current population are sorted according to the fitness function value, and the chromosome vector at the bottom is eliminated; then it is judged whether the optimal chromosome vector meets the optimization target, if the optimal chromosome vector meets the optimization target, the algorithm is terminated; otherwise, iterative evolutionary optimization is performed again through the mutation operation and crossover operation until the optimal chromosome vector meets the optimization target.

4. The evolutionary optimization system for e-government performance evaluation management according to claim 3, It is characterized in that The chromosome formalized random vector initial population construction module of the e-government performance evaluation index includes: The name input unit of the e-government performance test indicator is used to input the name of the e-government performance assessment indicator; The value range input unit of the e-government performance evaluation index is used to input the value range of the e-government performance evaluation index; The importance weight input unit of the e-government performance evaluation index is used to input the importance weight of the e-government performance evaluation index; The scoring standard input unit of the e-government performance appraisal indicator is used to input the scoring standard of the e-government performance appraisal indicator; The special priority setting value input unit of the scoring order of the e-government performance appraisal indicators is used to input the special priority setting value of the scoring order of the e-government performance appraisal indicators; The priority random initial ranking number input unit of the e-government performance evaluation index is used to input the priority random initial ranking number of the e-government performance evaluation index; and The scoring completion progress value input unit of the e-government performance appraisal indicator is used to input the scoring completion progress value of the e-government performance appraisal indicator.