Standard implementation effect evaluation method and system based on analytic hierarchy process-entropy weight method

Abstract

The invention relates to the technical field of standard implementation effect evaluation, in particular to a standard implementation effect evaluation method and system based on an analytic hierarchy process-entropy weight method. Comprising the following steps: S1, setting a plurality of observation variables which are at least divided into three classes, and acquiring data values of the plurality of observation variables for each observation variable; s2, performing data reliability and finiteness inspection on the obtained data values of all the observation variables; s3, calculating the combined weight of each observation variable through an analytic hierarchy process and an entropy weight method according to the data value of each observation variable processed in the step S2; s4, obtaining a standard implementation effect evaluation index according to the combination weight of each observation variable; s5, setting evaluation grades including a superior grade, a good grade, a middle grade and a poor grade, and comparing the standard implementation effect evaluation index with the evaluation grades to obtain a specific grade of the standard implementation effect; and the standard implementation effect can be evaluated more accurately and clearly.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of standard implementation effect evaluation, and particularly relates to a standard implementation effect evaluation method and system based on analytic hierarchy process-entropy weight method. BACKGROUND

[0002] A standard is a common and reusable rule, guideline or property document that is agreed upon and approved by a recognized organization, which is used to obtain the best order within a certain range, and which specifies the rules, guidelines or property documents for activities and their results. In order to obtain the best order within the implementation range, enterprises will develop common and reusable rules for actual or potential problems.

[0003] A pumped storage power station is a hydropower station that uses the power at the low load valley to pump water to the upper reservoir, and then releases water to the lower reservoir to generate power at the power load peak. It can convert the excess power at the low load of the power grid into high-value power at the peak period, and is suitable for frequency and phase modulation, stabilizing the frequency and voltage of the power system, and is suitable for emergency backup, and can also improve the efficiency of thermal power stations and nuclear power stations in the system. The standardization of pumped storage power stations is more important, and the technology and requirements of each project and link are highly unified and coordinated, and through standardized and standardized management, scientific management and control of complex content can be systematically established; at the same time, the evaluation of the implementation effect of the standard is also crucial, and is closely related to how to dynamically manage and improve.

[0004] Therefore, it is urgent to provide a standard implementation effect evaluation method and system based on analytic hierarchy process-entropy weight method, which is more accurate and clear in evaluating the implementation effect of the standard compared with the prior art. SUMMARY

[0005] The present application solves the technical problems existing in the prior art, and provides a standard implementation effect evaluation method and system based on analytic hierarchy process-entropy weight method.

[0006] To achieve the above-mentioned purpose, the technical scheme adopted by the present application is as follows: The standard implementation effect evaluation method based on analytic hierarchy process-entropy weight method comprises the following steps: S1, a plurality of observation variables are set, the plurality of observation variables are divided into at least three categories, and for each observation variable, a plurality of observation variable data values are obtained; S2, data reliability and finiteness test is performed on all the observation variable data values obtained; S3, the combined weight of each observation variable is calculated by analytic hierarchy process and entropy weight method according to the data value of each observation variable processed by S2 step; S4, a standard implementation effect evaluation index is obtained according to the combined weight of each observation variable; S5, set evaluation levels, including excellent level, good level, medium level and poor level, compare the standard implementation effect evaluation index with the evaluation levels to obtain the specific level of the standard implementation effect.

[0007] Further, in the S3 step, the combination weight of each observation variable is calculated by the following formula: ; In the above formula, denotes the combination weight of the jth observation variable, denotes the first proportion, denotes the first weight of the jth observation variable, denotes the second proportion, denotes the second weight of the jth observation variable.

[0008] Further, in the S3 step, the first weight is obtained by the analytic hierarchy process, and four layers of indexes are set, including a first index layer, a second index layer, a third index layer and an observation variable layer.

[0009] Further, the standard implementation effect evaluation index is calculated by the following formula: ; In the above formula, denotes the standard implementation effect evaluation index, denotes the average value of the jth observation variable corresponding to the qth third index corresponding to the pth second index, denotes the weight value of the qth third index corresponding to the pth second index, denotes the weight value corresponding to the pth second index.

[0010] Further, the weight value of each second index and the weight value of each third index are obtained by the same method as the combination weight of the observation variable.

[0011] Further, the S2 step specifically includes the following steps: S21, perform reliability test on the data value of the observation variable, process the data value of each observation variable by the z-score standardization method, then input the standardized observation variable data value into the SPSS software, form a matrix for each observation variable, and obtain the coefficient of each matrix by the SPSS software, set a coefficient threshold, compare the coefficient of each observation variable with the coefficient threshold, and when the When the coefficient is greater than the coefficient threshold value, it indicates that the data in the observation variable matrix is qualified in terms of reliability, otherwise it is unqualified; when there is unqualified observation variable, the S1 step is performed again, and when all observation variables are qualified, the S22 step is performed; S22, validity test is performed on the data values of each observation variable, for each observation variable, a corresponding matrix is formed, KMO test, Bartlett test, AVE value test and reliability CR value test are performed.

[0012] Further, S22 specifically includes the following steps: S221, KMO test and Bartlett test are performed, the KMO value of each observation variable after KMO test is obtained, the KMO threshold value is set, the KMO value of each observation variable is compared with the KMO threshold value, when the KMO value is greater than the KMO threshold value, it indicates that the KMO test is qualified; the detection p value of each observation variable after Bartlett test is obtained, the p value threshold value is set, the detection p value of each observation variable is compared with the p value threshold value, when the detection p value is less than the p value threshold value, it indicates that the Bartlett test is qualified; when the KMO test and the Bartlett test of all observation variables are qualified, the S222 step is performed, otherwise the S1 step is performed again; S222, AVE value test is performed, the AVE value of each observation variable is obtained, the AVE value of each type of observation variable is averaged to obtain the AVE average value of the observation variable of this type; the CR value of each observation variable is obtained through the S21 step, the CR value of each type of observation variable is averaged to obtain the CR average value of the observation variable of this type; the AVE threshold value and the CR threshold value are set, the AVE average value is compared with the AVE threshold value, and at the same time the CR average value is compared with the CR threshold value; when the AVE average value of the observation variable of this type is less than the AVE threshold value, and the CR average value is greater than the CR threshold value, it indicates that the extraction degree and the combination reliability of the observation variable of this type are qualified, when the extraction degree and the combination reliability of all types of observation variables are qualified, the S3 step is performed.

[0013] Further, in the S222 step, when there is unqualified observation variable of the type, the type of unqualified observation variable is selected, the AVE value and the CR value of each observation variable in the type are compared with the AVE threshold value and the CR threshold value respectively, the unqualified observation variable in the observation variable of the type is selected, the observation variable is removed from the questionnaire in the S1 step, and then the S1 step is performed again.

[0014] Further, in the S5 step, the first evaluation value, the second evaluation value, the third evaluation value and the fourth evaluation value are set, and the first evaluation value, the second evaluation value, the third evaluation value and the fourth evaluation value increase in turn; when the standard implementation effect evaluation index is greater than 0 and less than or equal to the first evaluation value, the evaluation is poor; when the standard implementation effect evaluation index is greater than the first evaluation value and less than or equal to the second evaluation value, the evaluation is medium; when the standard implementation effect evaluation index is greater than the second evaluation value and less than or equal to the third evaluation value, the evaluation is good; when the standard implementation effect evaluation index is greater than the third evaluation value and less than or equal to the fourth evaluation value, the evaluation is excellent.

[0015] The standard implementation effect evaluation system based on the analytic hierarchy process-entropy weight method comprises a first module, a second module, a third module, a fourth module and a fifth module, the first module is used for executing the content in the S1 step, the second module is used for executing the content in the S2 step, the third module is used for executing the content in the S3 step, the fourth module is used for executing the content in the S4 step, and the fifth module is used for executing the content in the S5 step.

[0016] Compared with the prior art, the beneficial effects of the present application are: The present application combines the analytic hierarchy process and the entropy weight method, realizes a full-cycle coverage index system, constructs a three-dimensional evaluation system of technology, implementation and benefit for pumped storage power stations, has dynamic self-adaptive capability, supports real-time adjustment of weights and indexes, adapts to standard updates and changes in industry demand, and realizes more accurate and explicit evaluation of standard implementation effects. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 is a flowchart of the method of the present application. DETAILED DESCRIPTION

[0018] The technical solutions of the present application will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are not all the embodiments of the present application, and all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the protection scope of the present application. It should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal" and the like indicate the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as limiting the present application.

[0019] EMBODIMENT This embodiment takes the standard implementation effect evaluation of a pumped storage power station as an example for illustration.

[0020] As Figure 1As shown, the embodiment provides a standard implementation effect evaluation method based on analytic hierarchy process-entropy weight method, comprising the following steps: S1, obtaining a plurality of observation variable data values of the pumped storage power station, the plurality of observation variable data values being obtained by means of a questionnaire.

[0021] The observation variables include three categories, including standard technical content category, standard implementation status category and standard implementation benefit category, and each category specifically includes observation variables as shown in Table 1.

[0022] S2, data reliability and validity test is performed on the obtained observation data, specifically comprising the following steps: S21, data reliability test of observation variables is performed, each observation variable is processed by z-score standardization method, then the standardized observation variables are input into SPSS software, reliability analysis is performed, each standardized observation variable forms a matrix, the Cronbach's alpha coefficient of each matrix is obtained through SPSS software, a coefficient threshold value is set, the Cronbach's alpha coefficient of each observation variable is compared with the coefficient threshold value, when the Cronbach's alpha coefficient of the observation variable is greater than the coefficient threshold value, it indicates that the reliability of the data in the observation variable matrix is qualified, otherwise it is unqualified; when there is unqualified observation variable, S1 step is performed again, when all observation variables are qualified, S22 step is performed.

[0023] The coefficient threshold value is preferably 0.91.

[0024] S22, validity test of observation variable data is performed, KMO test, Bartlett test, AVE value test and reliability CR value test are performed on the matrix composed of each observation variable. Specifically comprising the following steps: S221, obtaining the KMO value of each observation variable after KMO test, setting a KMO threshold value, comparing the KMO value of each observation variable with the KMO threshold value, when the KMO value is greater than the KMO threshold value, it indicates that the KMO test is qualified; the KMO threshold value is preferably 0.6.

[0025] Obtaining the detection p value of each observation variable after Bartlett test, setting a p value threshold value, comparing the detection p value of each observation variable with the p value threshold value, when the detection p value is less than the p value threshold value, it indicates that the Bartlett test is qualified; the p value threshold value is preferably 0.05.

[0026] When the KMO test and Bartlett test of all observation variables are qualified, S222 step is performed, otherwise S1 step is performed again.

[0027] ​​​S222, after AVE value inspection, the AVE value of each observation variable is obtained, the AVE value of each type of observation variable is averaged to obtain the AVE average value of the observation variable of the type; after the S21 step, the CR value of each observation variable is obtained, the CR value of each type of observation variable is averaged to obtain the CR average value of the observation variable of the type; the AVE threshold value and the CR threshold value are set, the AVE average value is compared with the AVE threshold value, and at the same time, the CR average value is compared with the CR threshold value; when the AVE average value of the observation variable of the type is less than the AVE threshold value, and the CR average value is greater than the CR threshold value, it is indicated that the extraction degree of the observation variable of the type is qualified, and the combination confidence is qualified, otherwise, the unqualified observation variable of the type is selected out, the AVE value and the CR value of each observation variable in the type are compared with the AVE threshold value and the CR threshold value respectively, the unqualified observation variable in the observation variable of the type is selected out, the observation variable is eliminated from the questionnaire in the S1 step, that is, the observation variable is not considered in the subsequent, and then the S1 step is performed again; until the extraction degree and the combination confidence of all types of observation variables are qualified, the S3 step is performed.

[0028] The AVE threshold value is preferably 0.5, and the CR threshold value is preferably 0.7.

[0029] S3, the combination weight of each observation variable is calculated by the analytic hierarchy process and the entropy weight method, the combination weight of each observation variable is obtained after analysis by the first weight and the second weight, the first weight is obtained by the analytic hierarchy process, the second weight is obtained by the entropy weight method, and the combination weight is calculated by the following formula: ; In the above formula, indicates the combination weight of the jth observation variable, indicates the first proportion, indicates the first weight of the jth observation variable, indicates the second proportion, indicates the second weight of the jth observation variable.

[0030] The first proportion and the second proportion are both preferably 0.5.

[0031] The first weight is obtained through the hierarchical analysis method, and four levels of indicators are set. The first level is the first-level indicator layer, which is specifically the standard implementation effect evaluation index; the second level is the second-level indicator layer, which specifically includes the technical content layer of the standard, the implementation status layer of the standard, and the implementation benefit layer of the standard; the third level is the third-level indicator layer. The third-level indicator layer corresponding to the technical content layer of the standard specifically includes applicability, advancement, coordination, rationality and operability; the third-level indicator layer corresponding to the implementation status layer of the standard specifically includes standard promotion, standard execution, and standard reference; the third-level indicator layer corresponding to the implementation benefit layer of the standard specifically includes economic benefits, social benefits and ecological benefits. Each third-level indicator layer also corresponds to an observation variable layer, as shown in Table 1 below: Table 1

[0032] A judgment matrix is ​​set for the observed variable layer to obtain the first weight of each observed variable.

[0033] Through the entropy weight method, the second weight of the observation variable is obtained according to the matrix formed by the observation variables in each observation variable layer.

[0034] S4. Based on the combined weight of each observed variable, the standard implementation effect evaluation index is obtained, which is calculated using the following formula: ; In the above formula, represents the standard implementation effect evaluation index, It represents the average value of the jth observed variable corresponding to the qth third-level indicator corresponding to the pth second-level indicator, represents the weight value of the qth tertiary index corresponding to the pth secondary index, represents the weight value corresponding to the pth secondary index.

[0035] The weight value of each tertiary index and secondary index is obtained by the analytic hierarchy process and the entropy weight method, that is, the same as in the method in the S3 step.

[0036] S5, setting an evaluation level, comparing the standard implementation effect evaluation index with the evaluation level to obtain a standard implementation effect evaluation level, the evaluation level including an excellent level, a good level, a medium level and a poor level; setting a first evaluation value, a second evaluation value, a third evaluation value and a fourth evaluation value, the first evaluation value, the second evaluation value, the third evaluation value and the fourth evaluation value being set in increasing order; when the standard implementation effect evaluation index is greater than 0 and less than or equal to the first evaluation value, the evaluation is the poor level; when the standard implementation effect evaluation index is greater than the first evaluation value and less than or equal to the second evaluation value, the evaluation is the medium level; when the standard implementation effect evaluation index is greater than the second evaluation value and less than or equal to the third evaluation value, the evaluation is the good level; when the standard implementation effect evaluation index is greater than the third evaluation value and less than or equal to the fourth evaluation value, the evaluation is the excellent level.

[0037] The first evaluation value is preferably 6, the second evaluation value is preferably 7, the third evaluation value is preferably 9, and the fourth evaluation value is preferably 10.

[0038] The embodiment also provides a standard implementation effect evaluation system based on the analytic hierarchy process-entropy weight method, which comprises a first module, a second module, a third module, a fourth module and a fifth module, the first module is used for executing the content in the S1 step, the second module is used for executing the content in the S2 step, the third module is used for executing the content in the S3 step, the fourth module is used for executing the content in the S4 step, and the fifth module is used for executing the content in the S5 step.

[0039] The present application realizes a full-cycle covering index system by combining the analytic hierarchy process and the entropy weight method, constructs a three-dimensional evaluation system of technology, implementation and benefit according to the characteristics of pumped storage power stations, has dynamic self-adaptive capability, supports real-time adjustment of weights and indexes, adapts to standard updates and changes in industry demand, and realizes more accurate and explicit evaluation of standard implementation effect.

[0040] Finally, it should be noted that the above content is only used to illustrate the technical solutions of the present application, and is not a limitation on the protection scope of the present application. Simple modifications or equivalent replacements of the technical solutions of the present application made by those skilled in the art do not deviate from the essence and scope of the technical solutions of the present application.

Claims

1. A standard implementation effect evaluation method based on hierarchical analysis-entropy weight method is characterized by: The following steps are involved: S1. Set multiple observation variables, which are divided into at least three categories. For each observation variable, obtain data values ​​of the multiple observation variables. S2. Conduct data reliability and finiteness tests on the data values ​​of all observed variables obtained; S3. Calculate the combined weight of each observed variable using the analytic hierarchy process and entropy weight method based on the data value of each observed variable processed in step S2; S4. Obtain the standard implementation effect evaluation index based on the combined weight of each observed variable; S5. Set evaluation levels, including excellent, good, medium and poor, and compare the standard implementation effect evaluation index with the evaluation level to obtain the specific level of the standard implementation effect.

2. The method for evaluating the implementation effect of standards based on the hierarchical analysis-entropy weight method according to claim 1, characterized in that: In step S3, the combined weight of each observed variable is calculated using the following formula: ； In the above formula, represents the combined weight of the j-th observed variable, Indicates the first specific gravity, represents the first weight of the j-th observed variable, Indicates the second specific gravity, represents the second weight of the j-th observation variable.

3. The method for evaluating the implementation effect of standards based on the hierarchical analysis-entropy weight method according to claim 2, characterized in that: In step S3, the first weight is obtained through the hierarchical analysis method, and four levels of indicators are set, including the first-level indicator layer, the second-level indicator layer, the third-level indicator layer and the observation variable layer.

4. The method for evaluating the implementation effect of standards based on the hierarchical analysis-entropy weight method according to claim 3 is characterized in that: The standard implementation effect evaluation index is calculated using the following formula: ； In the above formula, represents the standard implementation effect evaluation index, It represents the average value of the jth observed variable corresponding to the qth third-level indicator corresponding to the pth second-level indicator, Indicates the weight value of the qth third-level indicator corresponding to the pth second-level indicator, Indicates the weight value corresponding to the p-th secondary indicator.

5. The method for evaluating the implementation effect of standards based on the hierarchical analysis-entropy weight method according to claim 4 is characterized in that: The method for obtaining the weight value of each secondary indicator and the weight value of the tertiary indicator is the same as the method for obtaining the combined weight of the observed variables.

6. The method for evaluating the implementation effect of standards based on the hierarchical analysis-entropy weight method according to claim 1 is characterized in that: Step S2 specifically includes the following steps: S21. Conduct a reliability test on the data values ​​of the observed variables. Use the z-score standardization method to process the data values ​​of each observed variable. Then input the standardized data values ​​of the observed variables into SPSS software. A matrix is ​​formed for each observed variable. The SPSS software is used to obtain the matrix of each matrix. Coefficient, set the coefficient threshold, and The coefficients are compared with the coefficient threshold. When the coefficient is greater than the coefficient threshold, it means that the reliability of the data in the observation variable matrix is ​​qualified, otherwise it is unqualified; when there are unqualified observation variables, step S1 is repeated, and when all observation variables are qualified, step S22 is performed; S22. Perform validity tests on the data values ​​of each observed variable. For each observed variable, form a corresponding matrix and perform KMO test, Bartlett test, AVE value test and reliability CR value test.

7. The method for evaluating the implementation effect of standards based on the hierarchical analysis-entropy weight method according to claim 6 is characterized in that: S22 specifically includes the following steps: S221, perform KMO test and Bartlett test, obtain the KMO value of each observed variable after the KMO test, set the KMO threshold, compare the KMO value of each observed variable with the KMO threshold, when the KMO value is greater than the KMO threshold, it indicates that the KMO test is qualified; obtain the detection p value of each observed variable after the Bartlett test, set the p value threshold, compare the detection p value of each observed variable with the p value threshold, when the detection p value is less than the p value threshold, it indicates that the Bartlett test is qualified; when all the observed variables pass the KMO test and Bartlett test, perform step S222, otherwise repeat step S1; S222. After the AVE value test, the AVE value of each observed variable is obtained, and the AVE values ​​of each category of observed variables are averaged to obtain the AVE average value of the observed variables of this category; after step S21, the CR value of each observed variable is obtained, and the CR values ​​of each category of observed variables are averaged to obtain the CR average value of the observed variables of this category; set the AVE threshold and CR threshold, compare the AVE average value with the AVE threshold, and compare the CR average value with the CR threshold; when the AVE average value of the observed variables of this category is less than the AVE threshold, and the CR average value is greater than the CR threshold, it indicates that the extraction degree and combined reliability of the observed variables of this category are qualified. When the extraction degrees and combined reliability of the observed variables of all categories are qualified, proceed to step S3.

8. The method for evaluating the implementation effect of standards based on the hierarchical analysis-entropy weight method according to claim 7 is characterized in that: In step S222, when there are unqualified observed variables, the class of unqualified observed variables is selected, and the AVE value and CR value of each observed variable in the class are compared with the AVE threshold and CR threshold respectively, and the unqualified observed variables in the class of observed variables are selected, and the observed variables are removed from the questionnaire in step S1, and then step S1 is repeated.

9. The method for evaluating the implementation effect of standards based on the hierarchical analysis-entropy weight method according to claim 1, characterized in that: In step S5, the first evaluation value, the second evaluation value, the third evaluation value and the fourth evaluation value are set, and the first evaluation value, the second evaluation value, the third evaluation value and the fourth evaluation value increase in sequence; when the standard implementation effect evaluation index is greater than 0 and less than or equal to the first evaluation value, the evaluation is poor; when the standard implementation effect evaluation index is greater than the first evaluation value and less than or equal to the second evaluation value, the evaluation is medium; when the standard implementation effect evaluation index is greater than the second evaluation value and less than or equal to the third evaluation value, the evaluation is good; when the standard implementation effect evaluation index is greater than the third evaluation value and less than or equal to the fourth evaluation value, the evaluation is excellent.

10. The standard implementation effect evaluation system based on hierarchical analysis-entropy weight method is characterized by: The method for evaluating the effect of standard implementation based on hierarchical analysis-entropy weight method according to any one of claims 1 to 9 is used, and includes a first module, a second module, a third module, a fourth module and a fifth module. The first module is used to execute the content in step S1, the second module is used to execute the content in step S2, the third module is used to execute the content in step S3, the fourth module is used to execute the content in step S4, and the fifth module is used to execute the content in step S5.

Images