Power marketing evaluation method based on big data information analysis
The power marketing evaluation method based on big data information analysis solves the problem of subjective influence in multi-object and multi-indicator evaluation, realizes objective and accurate power marketing evaluation, and improves the accuracy and comprehensiveness of evaluation results.
Patent Information
- Application Number
- CN202511148135.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-08-16
- Publication Date
- 2025-11-21
AI Technical Summary
Existing electricity marketing evaluation methods lack multi-object and multi-indicator evaluation, are easily influenced by subjective reference materials, and result in low evaluation accuracy.
Using big data information analysis methods, electricity marketing satisfaction data from multiple power supply bureaus in the power grid system are obtained, preprocessed, and an evaluation matrix is constructed. The initial evaluation entropy value and allocation weight are calculated, as well as the first and second business weight values. Combined with reward and penalty scores, the overall evaluation value is finally generated for objective evaluation.
It achieves comprehensive and accurate evaluation of multiple objects and indicators, reduces subjective influence, improves the objectivity and accuracy of evaluation results, avoids zero results that occur in traditional scoring, and improves the accuracy of business evaluation.
Smart Images
Figure CN120996880A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of power marketing, and particularly relates to a power marketing evaluation method based on big data information analysis. BACKGROUND
[0002] The application of big data technology makes power marketing more accurate and efficient. By analyzing customer behavior data, power enterprises can reveal electricity usage habits and demand trends, laying the foundation for personalized marketing. At the same time, real-time monitoring systems can timely discover market changes, which is conducive to adjusting marketing strategies to better meet changing demands. The existing evaluation methods for power marketing data generally include expert subjective weighting method, analytic hierarchy process and fuzzy hierarchy method. These methods lack multi-objective and multi-index evaluation when evaluating power marketing, and lack objective evaluation reference materials. The evaluation results are easily affected by subjective evaluation reference materials, resulting in low accuracy of the evaluation results. SUMMARY
[0003] In view of the deficiencies of the prior art, the present application provides a power marketing evaluation method based on big data information analysis, which solves the technical problems of lack of multi-objective and multi-index evaluation in the prior art, and low evaluation accuracy affected by subjective reference materials, and achieves the purpose of more comprehensive and accurate evaluation through multi-objective and multi-index evaluation, and improves the accuracy of the evaluation results by using objective evaluation methods.
[0004] To solve the above technical problems, the present application provides the following technical scheme: a power marketing evaluation method based on big data information analysis, the method comprising the following steps: S1, obtaining satisfaction data of power marketing of multiple power supply stations in a power grid system, and preprocessing the satisfaction data to obtain a preprocessed data set ; S2, constructing an evaluation matrix according to the preprocessed data set , calculating the planning value of the data in the evaluation matrix and generating a planning matrix ; ; S3, calculating initial evaluation entropy and matching weight , and obtaining a first evaluation value ; S4, collecting business data in the power marketing data of the multiple power supply stations, and calculating a first industry weight value of a single enterprise ; S5, calculating an average score value and a second industry weight value , and according to the first industry weight value and the second industry weight value Calculate the second evaluation value ; S6. Calculate the reward score and penalty points And based on the first evaluation value Second evaluation value Reward points and penalty points Calculate the overall evaluation value ; S7. Calculate the evaluation threshold based on historical electricity marketing data. Based on evaluation threshold An overall evaluation of the electricity marketing situation is conducted to obtain evaluation results, which are then sent to the power grid system.
[0005] Preferably, in step S1, the specific implementation steps are as follows: S11, The satisfaction data includes customer power quality. Line loss management score Average power outage time and customer satisfaction The customer's power quality will be respectively Line loss management score Average power outage time and customer satisfaction Sort by size to obtain the customer power quality sequence. Line loss management scoring sequence Average power outage time series Customer satisfaction sequence ,in, Indicates the first Electricity quality for each customer Indicates the first Individual line loss management score, Indicates the first Average power outage time, Indicates the first Customer satisfaction; S12, Customer power quality Line loss management score Average power outage time and customer satisfaction Divide the data into multiple data groups based on the same time period. , ,in, They represent The order value; S13. Calculate the power quality for each customer. With customer satisfaction Line loss management score With customer satisfaction and average power outage time With customer satisfaction order difference and The calculation formula is: in, and They represent the first , , Each order difference; S14. Calculate the order difference respectively. and Correlation value and The calculation formula is: in, , and Representing the order difference and Quantity; S15. Based on the correlation value and Power quality for customers Line loss management score and average power outage time Irrelevant data is removed from the data. like If so, the data is relevant and will be retained; like If the data is not relevant, it should be removed. S16. The retained satisfactory data set is used as a preprocessing dataset. .
[0006] Preferably, in step S2, the specific implementation steps are as follows: S21. Based on the preprocessed dataset Data to construct an evaluation matrix The expression is: in, Represents preprocessed datasets The Middle The first object Data corresponding to each evaluation value; S22, in the evaluation matrix Selecting a data from the same object Calculate data Planning value The calculation formula is: in, Indicates the first One planning value, This represents the minimum value of data within the same object. This represents the maximum value of data within the same object. S23, Preprocess the dataset The planned value of each data point Calculate and construct the planning matrix. The expression is: in, Represents the first in the planning matrix The first object One planned value.
[0007] Preferably, in step S3, the specific implementation steps are as follows: S31, Calculate the programming matrix The probability value represents the data of the same object. The calculation formula is: in, Representing the first of the same object The probability value of each data point; S32, Based on probability values Calculate the initial entropy value of data for the same object. The calculation formula is: in, Representing the first of the same object The initial entropy value of each data point. Represents probability value The quantity, based on the evaluation matrix available Initial entropy value ; S33. Based on the initial entropy value Calculate the proportion weight The calculation formula is: wherein, represents the th proportion weight; S34, according to the proportion weight , the first evaluation value is calculated , and the calculation formula is: wherein, represents the first evaluation value.
[0008] Preferably, in step S4, the specific implementation steps are as follows: S41, the collected service data is divided into the number of power supply stations the score value of the th service of the power supply station , the total number of services is calculated , and the calculation formula is: wherein, represents the number of power supply stations, the number of services of the power supply station; S42, the average number of services is calculated , and the calculation formula is: wherein, represents the th average number of services; S43, one power supply station is randomly selected from the number of services and the score value of each service of the power supply station are obtained; S44, according to the number of services and the average number of services , the first weight value is calculated , and the calculation formula is: wherein, represents the first weight value of the th power supply station; S45, according to the first weight value , the first industry weight value is calculated , and the calculation formula is: wherein, the score value of the th service.
[0009] Preferably, in step S5, the specific implementation steps are as follows: S51, calculating the second weight value according to the service amount and the average service amount S52, calculating the average score value , the calculation formula is: wherein, represents the second weight value of the total service of the mth power supply bureau; S52, calculating the average score value , the calculation formula is: wherein, represents the mth average score value; S53, calculating the second weight value according to the second weight value , the calculation formula is: wherein, represents the second weight value; S54, calculating the second evaluation value , the calculation formula is: wherein, the mth assigned weight.
[0010] Preferably, in step S6, the following steps are specifically implemented: S61, obtaining the reward points of each service of the plurality of power supply bureaus , calculating the reward point value , the calculation formula is: wherein, represents the number of services obtaining the reward points, represents the reward points of the mth service; S62, obtaining the penalty points of each service of the plurality of power supply bureaus , calculating the penalty point value , the calculation formula is: wherein, the penalty points of the mth service; S63, calculating the overall evaluation value according to the reward point value and the penalty point value .
[0011] Preferably, the overall evaluation value The calculation formula is: Wherein, And Respectively represent the weight coefficient of the overall evaluation value .
[0012] Preferably, in step S7, the specific implementation steps are as follows: S71, obtain the overall evaluation value of each year in the historical data , calculate the average evaluation value , and the calculation formula is: Wherein, Indicates the number of years of the overall evaluation value of each year , and Indicates the first Overall evaluation value; S72, calculate the fluctuation difference value of the overall evaluation value , and the calculation formula is: Wherein, Indicates the number of groups of the first Overall evaluation value And the average evaluation value . S73, calculate the evaluation threshold , and the calculation formula is: Wherein, The first Fluctuation difference value; S74, overall evaluation of the power marketing situation of the power grid according to the evaluation threshold . If , the power marketing is not ideal, and an ideal evaluation result is generated. If , the power marketing is ideal, and an ideal evaluation result is generated.
[0013] Through the above technical scheme, the present application provides a power marketing evaluation method based on big data information analysis, which has at least the following beneficial effects: 1、The application carries out evaluation by using initial evaluation entropy value calculation, and carries out evaluation of multiple objects and multiple indexes by means of establishment of the first evaluation value, can accurately judge the dispersion degree of indexes through the initial evaluation entropy value, has strong resolution capacity and contains information quantity, can increase the accuracy of the evaluation method, and the method avoids the influence of subjective reference data, the evaluation result is very objective, and the influence of subjective evaluation data is reduced.
[0014] 2、The application calculates the first industry right value and the second industry right value, and evaluates the business data through the second evaluation value, avoids the deduction of business evaluation in the traditional scoring, causes the result of the business score to be zero, makes the evaluation more accurate, avoids the evaluation to be zero through the method, and greatly improves the accuracy of business evaluation.
[0015] 3、The application can more comprehensively select data of customer satisfaction related aspects through preprocessing of the satisfaction data, retain data with greater relevance, provide more accurate data selection for subsequent evaluation, improve the accuracy of subsequent evaluation, and eliminate irrelevant data, reduce the interference of irrelevant data, and improve the evaluation efficiency of the evaluation method. BRIEF DESCRIPTION OF DRAWINGS
[0016] The drawings described herein are used to provide further understanding of the present application, constitute a part of the present application, the illustrative embodiments of the present application and the description thereof are used to explain the present application, and do not constitute improper limitation on the present application. In the drawings: Figure 1 A flowchart of the power marketing evaluation method according to big data information analysis of the application. DETAILED DESCRIPTION
[0017] In order to make the above-mentioned purposes, characteristics and advantages of the present application more obvious and easy to understand, the present application will be further described in detail below in combination with the drawings and specific embodiments. The realization process of how to apply technical means to solve technical problems and achieve technical effects of the present application can be fully understood and implemented.
[0018] Due to the lack of evaluation of multiple objects and multiple indexes in the prior art, the evaluation accuracy is low and is easily affected by subjective reference data, please refer to Figure 1 The embodiment provides a power marketing evaluation method according to big data information analysis, which can more comprehensively and accurately evaluate multiple objects and multiple indexes, and improves the accuracy of the evaluation result by using an objective evaluation method, and is effectively applied in the project of "Retail transaction marketing management mode research suitable for Yunnan market", and the method comprises the following steps: S1, obtaining satisfaction data of power marketing of multiple power supply bureaus in a power grid system, and preprocessing the satisfaction data to obtain a preprocessing data set ;In this step, the satisfaction data needs to be preprocessed, which mainly includes the data values related to the customer's satisfaction with the power grid. In step S1, the specific implementation steps are as follows: S11, the satisfaction data includes customer power quality , line loss management score , average outage time and customer satisfaction , respectively, the customer power quality , line loss management score , average outage time and customer satisfaction are sorted according to size, and the customer power quality sequence , line loss management score sequence , average outage time sequence , customer satisfaction sequence , wherein represents the customer power quality of the th customer, the th line loss management score , the th average outage time , and the th customer satisfaction ; In addition to customer satisfaction , the satisfaction data also includes data such as electricity recovery rate and outage recovery efficiency. In this step, customer satisfaction is calculated, and in practice, objective data related to electricity recovery rate and outage recovery efficiency are also needed for more comprehensive and multi-objective calculation.
[0019] S12, the customer power quality , line loss management score , average outage time and customer satisfaction are divided into multiple same time period data groups according to time, wherein respectively represent the order value of ; Each time corresponds to multiple evaluation indicators of the same object, so that the evaluation can accurately evaluate the same object. Therefore, in order to facilitate the subsequent steps, preprocessing in this way is more conducive to subsequent steps, and in the analysis, a single indicator value can be sorted, which is more conducive to the selection of indicators.
[0020] S13, respectively calculate customer power quality and customer satisfaction , line loss management score with customer satisfaction and average outage time with customer satisfaction order difference value and , the calculation formula is: wherein, and respectively represent the first , , order difference value; S14, respectively calculate the correlation values of order difference values and , the calculation formula is: wherein, , and respectively represent the number of order difference values and ; according to the order value, the correlation values and can be calculated. The correlation of each evaluation index can be obtained, the interference data can be quickly removed in a large amount of satisfaction data, and the evaluation efficiency of the evaluation method is improved.
[0021] S15, according to the correlation values and , irrelevant data is removed; if , it has correlation and is retained; if , it has no correlation and is removed; S16, the retained satisfaction data set is collected as a pretreatment data set . The retained pretreatment data set should include customer satisfaction Other evaluation data, such as electricity bill collection rate and power outage restoration efficiency, can improve the accuracy of subsequent calculation steps. By preprocessing the satisfaction data, we can more comprehensively filter data related to customer satisfaction, retain more relevant data, provide more accurate data selection for subsequent evaluation steps, improve the accuracy of subsequent evaluation steps, and remove irrelevant data to reduce interference from irrelevant data and improve the evaluation efficiency of the evaluation method.
[0022] S2, Based on the preprocessed dataset Constructing an evaluation matrix Calculate the evaluation matrix The planned values of the data And generate the planning matrix For preprocessed datasets The construction of objects and evaluation indicators, and the establishment of a matrix, will help in the subsequent calculation of evaluation values. In step S2, the specific implementation steps are as follows: S21. Based on the preprocessed dataset Data to construct an evaluation matrix The expression is: in, Represents preprocessed datasets The Middle The first object The data corresponding to each evaluation value; the preprocessed dataset Classify by object and evaluation value, for example, multiple evaluation values for a certain row corresponding to a certain evaluation object A.
[0023] S22, in the evaluation matrix Selecting a data from the same object Calculate data Planning value The calculation formula is: in, Indicates the first One planning value, This represents the minimum value of data within the same object. This represents the maximum value of data within the same object; multiple evaluation values for each object require planning value calculation, which facilitates the subsequent calculation of the first evaluation value.
[0024] S23, Preprocess the dataset The planned value of each data point Calculate and construct the planning matrix. The expression is: in, Represents the first in the planning matrix The first object Each planning value is obtained by processing the preprocessed dataset. Processing each piece of data individually can improve data processing efficiency, reduce algorithmic bias, and enhance data interpretability.
[0025] S3. Calculate the initial evaluation entropy value. and proportion weight And obtain the first evaluation value. ; By analyzing the planning matrix The calculation of the data further calculates the first evaluation value. In step S3, the specific implementation steps are as follows: S31, Calculate the programming matrix The value represents the probability of data for the same object. The calculation formula is: in, Representing the first of the same object The probability value of each data point; S32, Based on probability values Calculate the initial entropy value of data for the same object. The calculation formula is: in, Representing the first of the same object The initial entropy value of each data point. Represents probability value The quantity, based on the evaluation matrix available Initial entropy value ; S33, Based on the initial entropy value Calculate the proportion weight The calculation formula is: in, Indicates the first Each ratio weight; this step involves initial evaluation of the entropy value. Calculate the weighting ratio based on the number of evaluation values. S34. According to the proportions and weights Calculate the first evaluation value The calculation formula is: in, represents the first evaluation value, and the matching weight is calculated Calculate the evaluation matrix The value of each data is calculated and accumulated, so that the evaluation is calculated by using the initial evaluation entropy value, and the evaluation method for evaluating multiple objects and multiple indicators by establishing the first evaluation value accurately judges the dispersion degree of the indicators, has strong resolution capability and contains information quantity, which can increase the accuracy of the evaluation method. And this method avoids the influence of subjective reference data, the evaluation result is very objective, and the influence of subjective evaluation data is reduced.
[0026] S4, collect business data in power marketing data of multiple power supply bureaus, and calculate the first industry right value of a single enterprise ; In the power grid system, there are multiple power supply bureaus in the power marketing data, real-time changes are recorded and stored in real time, and the business is evaluated through the business data of these marketing data. In step S4, the specific implementation steps are as follows: S41, divide the collected business data into business score values of a power supply bureau , calculate the total number of businesses , and the calculation formula is: Wherein, represents the number of power supply bureaus, the number of businesses of a power supply bureau; S42, calculate the average number of businesses , and the calculation formula is: Wherein, represents the th average number of businesses; The amount of business of each power supply bureau will have a certain gap, so the average value of the amount of business is calculated, which is beneficial to the calculation of the subsequent steps.
[0027] S43, select one power supply bureau from power supply bureaus arbitrarily, obtain the amount of business and the score value of each business of the power supply bureau; S44, according to the amount of business and the average number of businesses , calculate the first weight value , and the calculation formula is: Wherein, the first weight value of the th power supply bureau; The first weight value Able to reflect the first industry's equity value The weight.
[0028] S45, Based on the first weight value Calculate the first ownership value The calculation formula is: in, No. The score of each business, the weight of the first business. This can be understood as the evaluation result of a single enterprise's business volume. For example, if the evaluation is to be calculated for a specific power supply bureau, then the first business volume value would be used. The method calculates the first and second business weight values and evaluates the business data using the second evaluation value. This avoids the deduction of business evaluation points in traditional scoring, which could result in a zero business score and make the evaluation less accurate. This method can avoid the situation where the evaluation is zero, thus greatly improving the accuracy of business evaluation.
[0029] S5. Calculate the average score. Secondary industry weight And according to the first property value Secondary industry weight Calculate the second evaluation value Second property rights The evaluation mainly focuses on all power business data in the power grid system. In step S5, the specific implementation steps are as follows: S51, Based on business volume and average number of business Calculate the second weight value The calculation formula is: in, express The second weighting value of all business operations of a power supply bureau; S52. Calculate the average score. The calculation formula is: in, Indicates the first The average score is calculated at this position; summing all the scores at this position is beneficial for subsequent second-order weighting. The calculation.
[0030] S53, According to the second weight value Calculate the second ownership value The calculation formula is: in, Indicates the second-hand weight value; S54. Calculate the second evaluation value. The calculation formula is: in, No. The method assigns weights, calculates the first and second business weights, and evaluates the business data using the second evaluation value. This avoids the deduction of points in the business evaluation in traditional scoring, which could result in a zero business score and make the evaluation less accurate. This method can avoid the situation where the evaluation is zero, thus greatly improving the accuracy of the business evaluation.
[0031] S6. Calculate the reward score and penalty points And based on the first evaluation value Second evaluation value Reward points and penalty points Calculate the overall evaluation value The evaluation of electricity marketing also involves rewards and penalties, which accounts for a certain proportion of most evaluations. This invention also incorporates reward and penalty evaluations to make the evaluation method more comprehensive. In step S6, the specific implementation steps are as follows: S61. Obtain reward points for each service from multiple power supply bureaus. Calculate the reward score The calculation formula is: in, This indicates the number of businesses that received reward points. Indicates the first Reward points for each business segment; S62. Obtain the penalty score for each service from multiple power supply bureaus. Calculate the penalty score The calculation formula is: in, No. Penalty points for each business segment; S63. Based on reward points and penalty points Calculate the overall evaluation value The calculation formula is: in, and These represent the overall evaluation values. Weighting coefficients, weighting coefficients and The weighting coefficients can be obtained using the Analytic Hierarchy Process (AHP), a common method for obtaining weighting coefficients. In this step, only the AHP is needed to obtain the weighting coefficients, without any additional steps, which will not be elaborated here. By weighting multiple evaluation values, a comprehensive evaluation of the electricity marketing situation can be achieved, providing a more complete assessment. At the same time, by using the calculation of the first and second business weights and evaluating the business data through the second evaluation value, the deduction of business evaluation points in traditional scoring methods can be avoided, which could result in a business score of zero, making the evaluation less accurate. This method can avoid the situation of a zero evaluation, significantly improving the accuracy of business evaluation.
[0032] S7. Calculate the evaluation threshold based on historical electricity marketing data. Based on evaluation threshold An overall evaluation of the electricity marketing situation is conducted to obtain the evaluation results, which are then sent to the power grid system. The specific implementation steps in step S7 are as follows: S71. Obtain the overall evaluation value for each year from historical data. Calculate the average evaluation value The calculation formula is: in, This represents the overall evaluation value for each year. The number of years, Indicates the first One overall evaluation value; S72. Calculate the overall evaluation value Fluctuation difference The calculation formula is: in, Indicates the first Overall evaluation value and average rating The number of groups; S73, Calculate the evaluation threshold The calculation formula is: in, No. One fluctuation difference; S74. Based on the evaluation threshold To conduct an overall evaluation of the power grid's electricity marketing situation; like If the electricity marketing is unsatisfactory, an unsatisfactory evaluation result will be generated. If , the power marketing ideal, the ideal evaluation results, by using the initial evaluation entropy value calculation for evaluation, with the establishment of the first evaluation value of multi-objective multi-index evaluation evaluation method, through the initial evaluation entropy value accurately judge the dispersion degree of index, strong resolution ability contains information, can increase the accuracy of the evaluation method, and this method avoids the influence of subjective reference data, the evaluation result is very objective, reduces the influence of subjective evaluation data, through the calculation of the first industry right value and the second industry right value, and through the second evaluation value of business data evaluation, avoid the traditional score of business evaluation of deduction, cause the result of business score is zero, make the evaluation can not be more accurate, through this method can avoid the evaluation for zero, make the accuracy of business evaluation greatly improved.
[0033] Those skilled in the art can understand that all or part of the steps of the above-mentioned embodiment methods can be completed by programs instructing relevant hardware, therefore, the present application can adopt a completely hardware embodiment, a completely software embodiment or an embodiment combining software and hardware aspects. Moreover, the present application can adopt a computer program product in the form of being implemented on one or more computer usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) containing computer usable program codes.
[0034] The above embodiments are described in detail, and the principles and embodiments of the present application are described by applying specific examples. The above examples are only used to help understand the method and core idea of the present application; at the same time, for those skilled in the art, according to the idea of the present application, the specific embodiments and application scope will be changed, and the above description should not be understood as a limitation of the present application.
Claims
1. A method for evaluating electricity marketing based on big data information analysis, characterized in that, The method includes the following steps: S1. Obtain satisfaction data on electricity marketing from multiple power supply bureaus in the power grid system, and preprocess the satisfaction data to obtain a preprocessed dataset. ; S2, Based on the preprocessed dataset Constructing an evaluation matrix Calculate the evaluation matrix The planned values of the data And generate the planning matrix ; S3. Calculate the initial evaluation entropy value. and proportion weight And obtain the first evaluation value. ; S4. Collect business data from the electricity marketing data of multiple power supply bureaus and calculate the first business weight value of a single enterprise. ; S5. Calculate the average score. Secondary industry weight And according to the first property value Secondary industry weight Calculate the second evaluation value ; S6. Calculate the reward score and penalty points And based on the first evaluation value Second evaluation value Reward points and penalty points Calculate the overall evaluation value ; S7. Calculate the evaluation threshold based on historical electricity marketing data. Based on evaluation threshold An overall evaluation of the electricity marketing situation is conducted to obtain evaluation results, which are then sent to the power grid system.
2. The electricity marketing evaluation method according to claim 1, characterized in that, In step S1, the specific implementation steps are as follows: S11, The satisfaction data includes customer power quality. Line loss management score Average power outage time and customer satisfaction The customer's power quality will be respectively Line loss management score Average power outage time and customer satisfaction Sort the customers' power quality from smallest to largest to obtain a sequence. Line loss management scoring sequence Average power outage time series Customer satisfaction sequence ,in, Indicates the first Electricity quality for each customer Indicates the first Individual line loss management score, Indicates the first Average power outage time, Indicates the first Customer satisfaction; S12, Customer power quality Line loss management score Average power outage time and customer satisfaction Divide the data into multiple data groups based on the same time period. , ,in, They represent The order value; S13. Calculate the power quality for each customer. With customer satisfaction Line loss management score With customer satisfaction and average power outage time With customer satisfaction order difference and The calculation formula is: in, and They represent the first , , Each order difference; S14. Calculate the order difference respectively. and Correlation value and The calculation formula is: in, , and Representing the order difference and Quantity; S15. Based on the correlation value and Remove irrelevant data; like If so, the data is relevant and will be retained; like If the data is not relevant, it should be removed. S16. The retained satisfactory data set is used as a preprocessing dataset. .
3. The electricity marketing evaluation method according to claim 1, characterized in that, In step S2, the specific implementation steps are as follows: S21. Based on the preprocessed dataset Constructing an evaluation matrix The expression is: in, Represents preprocessed datasets The Middle The first object Data corresponding to each evaluation value; S22, in the evaluation matrix Selecting a data from the same object Calculate data Planning value The calculation formula is: in, Indicates the first One planning value, Representing the same object The Middle One data point, Representing the same object The minimum value of the data. Representing the same object The maximum value of the data in the middle; S23, Calculate the preprocessed dataset The planned value of each data point And construct a planning matrix The expression is: in, Represents the first in the planning matrix The first object One planned value.
4. The electricity marketing evaluation method according to claim 1, characterized in that, In step S3, the specific implementation steps are as follows: S31, Calculate the programming matrix The probability value represents the data of the same object. The calculation formula is: in, Representing the first of the same object The probability value of each data point; S32, Based on probability values Calculate the initial entropy value of data for the same object. The calculation formula is: in, Representing the first of the same object The initial entropy value of each data point. Represents probability value The quantity, based on the evaluation matrix available Initial entropy value ; S33. Based on the initial entropy value Calculate the proportion weight The calculation formula is: in, Indicates the first Each proportion and weight; S34. According to the proportions and weights Calculate the first evaluation value The calculation formula is: in, Represents preprocessed datasets The Middle The first object The data corresponding to each evaluation value.
5. The electricity marketing evaluation method according to claim 1, characterized in that, In step S4, the specific implementation steps are as follows: S41. Divide the collected business data into... A power supply bureau The rating of each business Calculate the total number of business transactions The calculation formula is: in, Indicates the number of power supply bureaus. Indicates the first The number of services provided by each power supply bureau; S42. Calculate the average number of business transactions. The calculation formula is: in, Indicates the first Average number of business transactions; S43, in Choose any one of the power supply bureaus. To obtain the business volume of the power supply bureau And the score of each business ; S44. Based on business volume and average number of business Calculate the first weight value The calculation formula is: in, Indicates the first The first weight value for each power supply bureau; S45, Based on the first weight value Calculate the first ownership value The calculation formula is: in, Indicates the first The score for each business.
6. The electricity marketing evaluation method according to claim 1, characterized in that, In step S5, the specific implementation steps are as follows: S51, Based on business volume and average number of business Calculate the second weight value The calculation formula is: in, express The second weighting value of all business operations of a power supply bureau; S52. Calculate the average score. The calculation formula is: in, Indicates the first Average rating value; S53, According to the second weight value Calculate the second ownership value The calculation formula is: in, Indicates the second-hand weight value; S54. Calculate the second evaluation value. The calculation formula is: in, Indicates the first Each assigned weight.
7. The electricity marketing evaluation method according to claim 1, characterized in that, In step S6, the specific implementation steps are as follows: S61. Obtain reward points for each service from multiple power supply bureaus. Calculate the reward score The calculation formula is: in, This indicates the number of businesses that received reward points. Indicates the first Reward points for each business segment; S62. Obtain the penalty score for each service from multiple power supply bureaus. Calculate the penalty score The calculation formula is: in, Indicates the first Penalty points for each business segment; S63. Based on reward points and penalty points Calculate the overall evaluation value .
8. The electricity marketing evaluation method according to claim 7, characterized in that, The overall evaluation value The calculation formula is: in, and These represent the overall evaluation values. The weighting coefficients.
9. The electricity marketing evaluation method according to claim 1, characterized in that, In step S7, the specific implementation steps are as follows: S71. Obtain the overall evaluation value for each year from historical data. Calculate the average evaluation value The calculation formula is: in, This represents the overall evaluation value for each year. The number of years, Indicates the first One overall evaluation value; S72. Calculate the overall evaluation value Fluctuation difference The calculation formula is: in, Indicates the first Overall evaluation value and average rating The number of groups; S73, Calculate the evaluation threshold The calculation formula is: in, Indicates the first One fluctuation difference; S74. Based on the evaluation threshold To conduct an overall evaluation of the power grid's electricity marketing situation; like If the electricity marketing is unsatisfactory, an unsatisfactory evaluation result will be generated. like If the electricity marketing is ideal, then an ideal evaluation result will be generated.