CN106372775A - Assessment method and system of comprehensive value of power grid client - Google Patents
Assessment method and system of comprehensive value of power grid client Download PDFInfo
- Publication number
- CN106372775A CN106372775A CN201610696848.1A CN201610696848A CN106372775A CN 106372775 A CN106372775 A CN 106372775A CN 201610696848 A CN201610696848 A CN 201610696848A CN 106372775 A CN106372775 A CN 106372775A
- Authority
- CN
- China
- Prior art keywords
- indexes
- index
- electricity
- level
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000012417 linear regression Methods 0.000 claims abstract description 24
- 238000012216 screening Methods 0.000 claims abstract description 10
- 230000005611 electricity Effects 0.000 claims description 115
- 238000011156 evaluation Methods 0.000 claims description 64
- 230000008901 benefit Effects 0.000 claims description 43
- 238000005259 measurement Methods 0.000 claims description 38
- 230000008859 change Effects 0.000 claims description 24
- 238000011084 recovery Methods 0.000 claims description 20
- 238000004458 analytical method Methods 0.000 claims description 17
- 230000001419 dependent effect Effects 0.000 claims description 8
- 238000007726 management method Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000013278 delphi method Methods 0.000 claims description 6
- 238000007689 inspection Methods 0.000 claims description 6
- 230000003993 interaction Effects 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 230000003449 preventive effect Effects 0.000 claims description 6
- 238000013077 scoring method Methods 0.000 claims description 6
- 230000035945 sensitivity Effects 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 6
- 239000000654 additive Substances 0.000 claims description 4
- 230000000996 additive effect Effects 0.000 claims description 4
- 238000013461 design Methods 0.000 claims description 4
- 238000011161 development Methods 0.000 claims description 4
- 238000005265 energy consumption Methods 0.000 claims description 3
- 230000010354 integration Effects 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 239000002131 composite material Substances 0.000 claims 6
- 230000002411 adverse Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012847 principal component analysis method Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000011524 similarity measure Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Theoretical Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides an assessment method and system of the comprehensive value of a power grid client. The method comprises the following steps of: dividing power grid client indexes to obtain first-class indexes, second-level indexes and third-level indexes; screening related true and effective fields from a database, and determining n basic indexes in the three-level indexes; adopting a hierarchical clustering method and a Pareto law to carry out level judgment on the n basic indexes; on the basis of a Delphi expert grading method, obtaining a collection index consultation score graph and a client total score; and according to a multiple linear regression method, analyzing and determining a basic index weight. The power grid client indexes are divided, the hierarchical clustering method and the Pareto law are adopted to carry out level judgment on the n basic indexes, the Delphi expert grading method is combined to obtain the collection index consultation score graph and the client total score, the basic index weight is analyzed and determined according to the multiple linear regression method, the comprehensive value of the power grid client is assessed from multiple aspects in an omnibearing way, and a power enterprise is effectively assisted in appointing a personalized power utilization strategy to clients.
Description
Technical Field
The invention relates to the technical field of power grid customer analysis, in particular to a power grid customer comprehensive value evaluation method and system.
Background
In recent years, the 2002 State Council formally issues a power system reform scheme, and the market-oriented reform of the power industry in China formally pulls up curtains. The traditional vertical integrated monopoly business pattern is broken, and the main supply bodies are thoroughly separated. The scientific and objective power grid operation state index system is researched and established, and the method has important significance for promoting the scientific development of the power grid and improving the power grid management level.
An integrated Power grid Operation intelligent System (OSS) and a Power System Operation Cockpit module (POC) provided by a southern Power grid are important applications of a Power grid Operation state index System, and the purpose is to deeply analyze Power grid Operation characteristics, truly reflect the Power grid Operation state and further improve the Operation and control capability of operators on the Power grid. The number of indexes of the running state of the power grid is large, and how to establish a reasonable index system and distribute the weight of related indexes is an important problem which always troubles researchers.
Disclosure of Invention
The invention aims to provide a comprehensive value evaluation method and system for power grid customers, which can evaluate the comprehensive value of the power grid customers in an all-around and multi-angle manner.
In order to solve the technical problem, an embodiment of the present invention provides a power grid customer comprehensive value evaluation method, where the power grid customer comprehensive value evaluation method includes:
dividing the client indexes of the power grid to obtain a first-level index, a second-level index and a third-level index, wherein the first-level index, the second-level index and the third-level index comprise a current value and a potential value, the current value comprises income contribution, stability, social benefit and operation benefit, the potential value comprises loyalty, exhibition prospect, credit and policy guidance, and the income contribution, the stability, the social benefit and the operation benefit are the second-level indexes;
screening relevant real effective fields from a database for matching, and determining n basic indexes in the three-level indexes;
judging the grade of the n basic indexes by adopting a hierarchical clustering method and a Parlotto rule;
combining with a Delphi method expert evaluation method to obtain a collection index inquiry score table and a customer total score;
and analyzing and determining the weight of the basic index according to a multiple linear regression method.
Preferably, the income contribution includes the metrics of the electricity purchasing quantity, the regional contribution rate of the electricity fee, the ratio contribution degree of the enterprise electricity purchasing quantity, the average price of the enterprise electricity, the execution electricity price standard, the ratio of the occupied regional capacity and the like; the stability comprises the measurement of indexes such as low-ebb electricity consumption rate, high-ebb electricity consumption rate, capacity change electricity consumption condition, capacity change period, electricity purchasing quantity increase rate, electricity purchasing quantity increase quantity and the like; the social benefits comprise whether the power consumption is high or not, whether the power consumption is a strong electricity requirement enterprise such as military medical treatment and the like, the load importance degree, the voltage level, the client scale, the power supply access condition, whether a thousand-level high-voltage client participates in the power protection task measurement or not; the operation benefits comprise the balance of power restoration, the number of times of meter faults, the load type of a client, whether double multi-source clients exist or not, the level of high-risk important clients, the power utilization change condition, the capacity change frequency and the inspection period; loyalty includes data completion, whether the client is a three-party client, accumulated electricity charge recovery rate, electricity charge recovery rate of the current period, electricity charge recovery punctuality, electricity charge recovery rate, electricity charge repayment capability, payment duration, price sensitivity, client interaction behavior and electricity consumption duration measurement; the development prospect comprises the amount of the electricity charge increase, the rate of the electricity charge increase, the influence degree of enterprises, the business scene degree, the advantages of the located industries, the management level of the enterprises and the measurement of the life cycle of the enterprises; the credit degree comprises historical arrearage amount, accumulated arrearage frequency ratio, average arrearage frequency, electric charge repayment guarantee level, arrearage power failure condition, pre-charged electric charge condition, metering fault information, preventive test information, potential safety hazard information, illegal electricity utilization condition, meter reading illegal frequency and meter fault frequency measurement; policy guidance includes whether to place policy restrictions, whether to place policy encouragement measures;
the electricity purchasing quantity, the regional contribution rate of the electricity fee, the contribution rate of the enterprise electricity purchasing quantity ratio, the average price of the enterprise electricity, the execution electricity price standard, the index measurement such as the ratio of the occupied regional capacity, the low-ebb electricity consumption rate, the peak electricity consumption rate, the electricity consumption condition of the capacitance change, the capacitance change period, the electricity purchasing quantity growth rate, the electricity purchasing quantity growth quantity, whether the electricity purchasing quantity is high energy consumption, whether the electricity purchasing quantity is a high-intensity electricity requiring enterprise such as military medical treatment, the load importance degree, the voltage grade, the client scale, the power supply access condition, whether the thousands of high-voltage clients participate in the electricity protection task measurement, the electricity recovery, the counter fault frequency, the client load type, whether the two multi-source clients exist, the high-risk important client grade, the electricity consumption condition of the change, the capacity change frequency, the inspection period measurement, the data completion degree, whether the three-party clients exist, the accumulated electricity fee recovery rate, The system comprises an electric charge recovery rate, an electric charge paying capacity, a payment duration, a price sensitivity, a customer interaction behavior, an electric charge duration measurement, an electric charge increase amount, an electric charge increase rate, an enterprise influence degree, an industry scene degree, an industry advantage, an enterprise management level, an enterprise life cycle measurement, a historical arrearage amount, an accumulated arrearage frequency ratio, an average arrearage frequency, an electric charge paying guarantee level, an arrearage power failure condition, a pre-paid electric charge condition, metering fault information, preventive test information, potential safety hazard information, a violation electric power consumption condition, a violation meter reading rule frequency, a meter fault frequency measurement, whether to be listed in policy restriction or not, and whether to be listed in policy encouragement measurement is a three-level index.
Preferably, the screening of the relevant real effective fields from the database for matching and the determination of n basic indexes in the three-level indexes include:
corresponding the determined three-level indexes to database fields;
deleting indexes with vacant fields and data errors from the index library, and complementing the indexes with average number when some indexes are not applicable in time period;
and updating the three-level indexes corresponding to the database fields into n basic indexes.
Preferably, the method for evaluating the grades of the n basic indexes by using the hierarchical clustering method and the pareto rule includes:
normalizing and preprocessing the power data;
determining a k value range, and calculating a profile coefficient of the k value;
and extracting a clustering analysis result corresponding to the k value, and determining a threshold value and a score value of the classification grade according to numerical values of different clusters.
Preferably, the obtaining of the collected index solicitation score table and the customer total score by combining with a delphi expert scoring method includes:
designing a value analysis object inquiry opinion list by taking n basic indexes as factors influencing the bond;
integrating the scores of the indexes evaluated by the experts by an additive evaluation type Delphi expert evaluation method, and feeding back the statistical result to the experts;
and combining anonymous consultation and opinion feedback according to the scores and the total object scores of all the indexes corrected by the experts to obtain the final scores and the total scores of the indexes and obtain an index consultation score table.
Preferably, the analyzing and determining the basic index weight according to the multiple linear regression method includes:
and taking the scores corresponding to the evaluation grades of the n basic indexes as independent variables, collecting the total client scores in the index query score table as dependent variables, and determining the weight of each basic index by using a matlab or R language tool to perform a multiple linear regression method.
The invention also provides a power grid customer comprehensive value evaluation system, which comprises:
the client index dividing module is used for dividing the client indexes of the power grid to obtain a first-level index, a second-level index and a third-level index, wherein the first-level index, the second-level index and the third-level index comprise a current value and a potential value, the current value comprises income contribution, stability, social benefits and operation benefits, the potential value comprises loyalty, exhibition prospect, credit and policy guidance, the income contribution, the stability, the social benefits and the operation benefits are the second-level indexes, and the income contribution, the stability, the social benefits and the operation benefits are the second-level indexes;
the database matching module is used for screening relevant real effective fields from the database for matching and determining n basic indexes in the three-level indexes;
the grade judging module is used for judging the grade of the n basic indexes by adopting a hierarchical clustering method and a Parlotto rule;
the scoring module is used for obtaining a collection index inquiry score table and a customer total score by combining a Delphi method expert scoring method;
and the weight determining module is used for analyzing and determining the weight of the basic index according to the multiple linear regression method.
Preferably, the grade judging module includes:
the normalization unit is used for normalizing and preprocessing the power data;
the coefficient calculation unit is used for determining a k value range and calculating a profile coefficient of a k value;
and the grade threshold unit is used for extracting the clustering analysis result corresponding to the k value and determining the grade threshold and the grade according to the numerical values of different clusters.
Preferably, the scoring module comprises:
an opinion table design unit, which is used for designing a value analysis object to inquire an opinion table by taking n basic indexes as factors influencing the bond;
the score integration unit is used for integrating scores of the indexes evaluated by the experts by an addition evaluation type Delphi expert evaluation method and feeding back the statistical result to the experts;
and the score determining unit is used for combining anonymous consultation and opinion feedback according to the scores of all the indexes corrected by the experts and the total object score to obtain the final score and the total score of the indexes and obtain an index consultation score table.
Preferably, the weight determination module includes:
and the weight determining unit is used for collecting the total customer division dependent variable in the index query score table by taking the scores corresponding to the evaluation grades of the n basic indexes as independent variables, and performing multiple linear regression by using a matlab or R language tool to determine the weight of each basic index.
The technical scheme of the invention has the following beneficial effects:
in the scheme, the indexes of the power grid customers are divided, the indexes of n basic indexes are judged according to a hierarchical clustering method and a pareto rule, a collected index inquiry score table and a customer total score are obtained by combining a Delphi expert evaluation method, the weight of the basic indexes is analyzed and determined according to a principal component analysis method, the comprehensive value of the power grid customers is evaluated in an all-dimensional and multi-angle manner, and the power grid customers are effectively assisted to designate individual power utilization strategies to the customers by power enterprises.
Drawings
FIG. 1 is a flow chart of the steps of a comprehensive value evaluation method for a power grid customer according to an embodiment of the invention;
fig. 2 is a connection block diagram of a power grid customer comprehensive value evaluation system structure according to an embodiment of the present invention.
Detailed Description
In order to make the technical problems, technical solutions and advantages of the present invention more apparent, the following detailed description is given with reference to the accompanying drawings and specific embodiments.
As shown in fig. 1, a method for evaluating a comprehensive value of a power grid customer according to an embodiment of the present invention includes:
step 101: dividing the client indexes of the power grid to obtain a first-level index, a second-level index and a third-level index, wherein the first-level index, the second-level index and the third-level index comprise a current value and a potential value, the current value comprises income contribution, stability, social benefit and operation benefit, the potential value comprises loyalty, exhibition prospect, credit and policy guidance, and the income contribution, the stability, the social benefit and the operation benefit are the second-level indexes;
after the index items of the three-level indexes are designed, different time dimensions can be set according to the characteristics of different indexes. Such as enterprise electricity consumption, meter reading violation frequency, electricity purchasing increment and other quantitative indexes, the method mainly considers the total measurement of the indexes, properly considers the partial measurements of different time periods, and calculates the indexes in year/season/month respectively; multiplying power related indexes such as the electricity purchasing increase rate, the electricity charge recovery rate in the period, the peak power consumption rate and the like pay more attention to periodicity, the time dimension needs to be subdivided, and the indexes are calculated mainly in weeks/months/seasons. The design not only considers the different time dimensions of different indexes, but also enriches the polymorphism of the indexes, so that the index system is more objective and reasonable, and the later grade division and weight analysis are more well-documented.
Step 102: screening relevant real effective fields from a database for matching, and determining n basic indexes in the three-level indexes;
step 103: judging the grade of the n basic indexes by adopting a hierarchical clustering method and a Parlotto rule;
step 104: combining with a Delphi method expert evaluation method to obtain a collection index inquiry score table and a customer total score;
step 105: and analyzing and determining the weight of the basic index according to a multiple linear regression method.
Preferably, the income contribution includes the metrics of the electricity purchasing quantity, the regional contribution rate of the electricity fee, the ratio contribution degree of the enterprise electricity purchasing quantity, the average price of the enterprise electricity, the execution electricity price standard, the ratio of the occupied regional capacity and the like; the stability comprises the measurement of indexes such as low-ebb electricity consumption rate, high-ebb electricity consumption rate, capacity change electricity consumption condition, capacity change period, electricity purchasing quantity increase rate, electricity purchasing quantity increase quantity and the like; the social benefits comprise whether the power consumption is high or not, whether the power consumption is a strong electricity requirement enterprise such as military medical treatment and the like, the load importance degree, the voltage level, the client scale, the power supply access condition, whether a thousand-level high-voltage client participates in the power protection task measurement or not; the operation benefits comprise the balance of power restoration, the number of times of meter faults, the load type of a client, whether double multi-source clients exist or not, the level of high-risk important clients, the power utilization change condition, the capacity change frequency and the inspection period; loyalty includes data completion, whether the client is a three-party client, accumulated electricity charge recovery rate, electricity charge recovery rate of the current period, electricity charge recovery punctuality, electricity charge recovery rate, electricity charge repayment capability, payment duration, price sensitivity, client interaction behavior and electricity consumption duration measurement; the development prospect comprises the amount of the electricity charge increase, the rate of the electricity charge increase, the influence degree of enterprises, the business scene degree, the advantages of the located industries, the management level of the enterprises and the measurement of the life cycle of the enterprises; the credit degree comprises historical arrearage amount, accumulated arrearage frequency ratio, average arrearage frequency, electric charge repayment guarantee level, arrearage power failure condition, pre-charged electric charge condition, metering fault information, preventive test information, potential safety hazard information, illegal electricity utilization condition, meter reading illegal frequency and meter fault frequency measurement; policy guidance includes whether to place policy restrictions, whether to place policy encouragement measures;
the electricity purchasing quantity, the regional contribution rate of the electricity fee, the contribution rate of the purchased electricity quantity of the enterprise, the average price of the electricity consumed by the enterprise, the execution electricity price standard, the index measurement such as the ratio of the occupied regional capacity, the low-ebb electricity consumption rate, the peak electricity consumption rate, the electricity consumption condition of the capacitance change, the capacitance change period, the electricity purchasing quantity growth rate, the electricity purchasing quantity growth quantity and the like, whether the electricity purchasing quantity is high energy consumption or not, whether the electricity purchasing quantity is a strong electricity requiring enterprise such as military medical treatment or not, the load importance degree, the voltage level, the client scale, the power supply access condition, whether the thousands of high-voltage clients or not, whether the electricity purchasing quantity participates in the electricity protection task measurement, the electricity recovery, the counter fault times, the client load type, whether the double multi-source clients are high-risk important client levels or not, the electricity consumption condition of the change, the capacity change frequency, the inspection period measurement, the data completion degree, the system comprises an electric charge recovery rate, an electric charge paying capacity, a payment duration, a price sensitivity, a customer interaction behavior, an electric charge duration measurement, an electric charge increase amount, an electric charge increase rate, an enterprise influence degree, an industry scene degree, an industry advantage, an enterprise management level, an enterprise life cycle measurement, a historical arrearage amount, an accumulated arrearage frequency ratio, an average arrearage frequency, an electric charge paying guarantee level, an arrearage power failure condition, a pre-paid electric charge condition, metering fault information, preventive test information, potential safety hazard information, a violation electric power consumption condition, a violation meter reading rule frequency, a meter fault frequency measurement, whether to be listed in policy restriction or not, and whether to be listed in policy encouragement measurement is a three-level index.
Preferably, the screening of the relevant real effective fields from the database for matching and the determination of n basic indexes in the three-level indexes include:
corresponding the determined three-level indexes to database fields;
deleting indexes with vacant fields and data errors from the index library, and complementing the indexes with average number when some indexes are not applicable in time period;
and updating the three-level indexes corresponding to the database fields into n basic indexes.
Preferably, the method for evaluating the grades of the n basic indexes by using the hierarchical clustering method and the pareto rule includes:
normalizing and preprocessing the power data;
determining a k value range, and calculating a profile coefficient of the k value;
and extracting a clustering analysis result corresponding to the k value, and determining a threshold value and a score value of the classification grade according to the numerical values of different clusters, as shown in the following table.
| Value of K | Score value for each level |
| 3 | 33、66、100 |
| 4 | 25、50、75、100 |
| 5 | 20、40、60、80、100 |
| 6 | 16、32、48、60、72、84、100 |
| 7 | 14、28、43、57、71、86、100 |
| 8 | 12、25、47、50、62、75、87、100 |
| 9 | 11、22、33、44、55、66、77、88、100 |
| 10 | 10、20、30、40、50、60、70、80、90、100 |
The K value is generally selected to be 3 to 10, and then clustering calculation is performed on K values of 3,4, …, and 10, and the contour coefficient of the K value is calculated. The larger the value of k in the range, the better, the larger the value of k, the more cohesive the clustered clusters. And considering the twenty-eight law, business knowledge and contour coefficients for quantifiable indexes such as electric quantity, capacity and the like, and selecting a k value with the contour coefficient more than 0.5.
Specifically, the euclidean distance:
the k-means algorithm is a very widely applied clustering algorithm, is a typical target function clustering method based on a prototype, and obtains an adjustment rule of iterative operation by using a method of solving an extreme value by a function. The K-means algorithm takes Euclidean distance as a similarity measure. The basic flow of the k-means algorithm is as follows: randomly selecting k objects in the data set as initial centers of the possible classes; for the rest objects, assigning them to the most similar class according to their distance from the center of each class; for each class, calculating a new mean value as a new center for the class using the objects assigned to the class; after all objects are reassigned, iterations are repeated until the assignment stabilizes.
1) Randomly selecting k objects from D as initial class centers;
2)repeat
(1) assigning each object to the "most similar" class according to the distance from the center of each class;
(2) recalculating the average value of each cluster as a new class center;
3) the util is not changed any more
The time complexity of the k-means algorithm is O (nkl), where n is the number of data, k is the number of clusters, and l is the number of iterations required for the algorithm to converge. Typically, k < < n, and l < < n. The algorithm is therefore relatively scalable and efficient for processing large data sets.
K value is selected and determined by the contour coefficient and the actual index business requirement
Suppose we have clustered the data to be classified by a certain algorithm. It is common to divide the data to be classified into K clusters, for example using K-means. For each vector in the cluster. Their contour coefficients are calculated separately.
For one of the points i:
calculate a (i) average (distance of i vector to other points in all clusters it belongs to)
Calculate b (i) min (average distance of i vector to all points not in its own cluster)
Then the i vector contour coefficients are:
it can be seen that the value of the profile factor is between [ -1,1], and that approaching 1 means that both the cohesion and the separation are relatively good.
And averaging the contour coefficients of all the points to obtain the total contour coefficient of the clustering result.
In actual operation, the K value with larger contour coefficient is selected.
In the embodiment, the threshold value of the index can be updated regularly according to the time lapse, and the renewability and diversity are ensured.
Preferably, the obtaining of the collected index solicitation score table and the customer total score by combining with a delphi expert scoring method includes:
designing a value analysis object inquiry opinion list by taking n basic indexes as factors influencing the bond;
integrating the scores of the indexes evaluated by the experts by an additive evaluation type Delphi expert evaluation method, and feeding back the statistical result to the experts;
and combining anonymous consultation and opinion feedback according to the scores and the total object scores of all the indexes corrected by the experts to obtain the final scores and the total scores of the indexes and obtain an index consultation score table.
The method comprises the steps of firstly selecting a plurality of evaluation items according to the specific requirements of an evaluation object, and then making an evaluation standard according to the evaluation items. The method comprises the steps of inquiring opinions of related experts in an anonymous mode, carrying out statistics, processing, analysis and induction on the opinions of the experts, objectively integrating most of expert experiences and subjective judgment, carrying out reasonable estimation on a large number of factors which are difficult to quantitatively analyze by adopting a technical method, and analyzing the value and the realizable degree of the creditor value after multiple rounds of opinion inquiry, feedback and adjustment. The operation steps are as follows:
selecting an expert:
determining factors influencing the creditor value, designing a value analysis object to inquire an opinion table:
thirdly, providing the background data of the debt rights for the expert, and inquiring the opinion of the expert in an anonymous way:
fourthly, analyzing and summarizing the expert opinions, and feeding back the statistical result to the expert:
the expert corrects own opinions according to the feedback result:
and sixthly, forming a final analysis conclusion through multiple rounds of anonymous inquiry and opinion feedback.
The expert score calculation method comprises the following steps:
(ii) additive evaluation type
The scores obtained by evaluating the index items are added and summed up, and the evaluation result is expressed in terms of total score. This method is used for the simple relationship between indexes. The formula is as follows:
wherein, W is the total score of the evaluation object; wiThe score value of the ith index is obtained; n is the number of index items. The method has two modes, namely a continuous addition evaluation method and a point counting addition evaluation method.
② evaluation type of continuous product
And (4) multiplying the scores of the various projects together, and expressing the performance result according to the product size. This method is very sensitive and it is very sensitive,
the indexes of the evaluated object are particularly closely related, and the score of one item affects the total result of other items, namely
The method has the characteristic that the whole is negated when a certain index is unqualified.
The formula is as follows:
wherein W is the total score of the evaluation object, WiThe score of the item is i, and the number of the index items is n.
(iii) evaluation type of multiplication of numbers
Dividing the evaluation indexes of the evaluation objects into a plurality of groups, firstly calculating the sum of the grading values of each group, and then multiplying the grading values of each group together to obtain the total grade. The determination is made in consideration of the difference in the degree of closeness of relationship between the factors and the difference in the manner of mutual influence.
The formula is as follows:
wherein W isijIs the ith group of jth index value in the evaluation object, m is the group number of the evaluation object, and n is the number of index items contained in the i group
Weighted evaluation type
And giving different weights to each index item in the evaluation object according to the importance degree of the evaluation index, namely, distinguishing the importance degree of each factor.
Wherein W is the total score of the evaluation objects, WiScore of i index item as evaluation object, AiIs the weight of the index item i. And 1)
Preferably, the analyzing and determining the basic index weight according to the multiple linear regression method includes:
and taking the scores corresponding to the evaluation grades of the n basic indexes as independent variables, collecting the total client scores in the index query score table as dependent variables, and determining the weight of each basic index by using a matlab or R language tool to perform a multiple linear regression method.
Where, for unary linear regression, the data is modeled with a straight line. Linear regression is the simplest form of regression. Bivariate regression treats one random variable Y (called the response variable) as a linear function of another random variable X (called the predictor variable). Namely:
Y＝α+βx
wherein the variance of Y is a constant; α and β are regression coefficients, representing the truncation of the line on the Y-axis and the slope of the line, respectively. These coefficients can be solved with a least squares method, which minimizes the error between the actual data and the estimate of the line. Given s samples or data points in the form of (x1, y1), (x2, y2),., (xs, ys), the regression coefficients α and β can be calculated using the following equation:
wherein,is the average of x1, x 2.., xs, and y is the average of y1, y 2.., ys. Linear regression often gives a good approximation compared to other complex regression methods.
For multiple linear regression, multiple linear regression is a generalization of simple linear regression, which refers to the regression of multiple dependent variables to multiple independent variables. The most common of these is the case of multiple independent variables, limited to one dependent variable, also called multiple regression. The general form of multiple regression is as follows:
Y＝a+b1X1+b2X2+b3X3+...+bkXk
a represents the intercept, b1,b2,b3,...,bkAre regression coefficients.
In the method, the model of the multivariate regression and index system is abnormally matched with x1, x2, xs which can be regarded as index scores of various basic index variables; y is the comprehensive total score given by the expert; b1,b2,b3,...,bkIs the weight of each index we need to obtain, b1,b2,b3,...,bkPossibly negative, indicating that this index adversely affects the evaluation score of the customer; a is set as the initial factor of the index system.
In the method, the multivariate linear regression is matched with the model abnormity of the index system. x1, x 2.., xs may be considered herein as index scores of the basic index variables; y is the comprehensive total score given by the expert; b1,b2,b3,...,bkIs the weight of each index we need to obtain, b1,b2,b3,...,bkPossibly negative, indicating that this index adversely affects the evaluation score of the customer; a is set as the initial factor of the index system.
In the embodiment, the different-level data of the third-level n basic indexes are used as independent variables, so that the calculation complexity is reduced, the hardware requirement is reduced, the clustering result is reasonably used, and the method is more objective and efficient.
As shown in fig. 2, a power grid customer integrated value evaluation system according to an embodiment of the present invention includes:
the client index dividing module 201 is configured to divide the power grid client indexes to obtain a first-level index, a second-level index and a third-level index, where the first-level index, the second-level index and the third-level index include a current value and a potential value, the current value includes revenue contribution, stability, social benefit and operation benefit, the potential value includes loyalty, exhibition prospect, credit and policy guidance, the revenue contribution, stability, social benefit and operation benefit are the second-level indexes, and the revenue contribution, stability, social benefit and operation benefit are the second-level indexes;
the database matching module 202 is used for screening relevant real effective fields from the database for matching and determining n basic indexes in the three-level indexes;
the grade judging module 203 is used for judging the grade of the n basic indexes by adopting a hierarchical clustering method and a Parlotto rule;
the scoring module 204 is used for obtaining a collection index inquiry score table and a customer total score by combining a Delphi method expert scoring method;
and the weight determining module 205 is used for analyzing and determining the weight of the basic index according to a multiple linear regression method.
Preferably, the grade judging module includes:
the normalization unit is used for normalizing and preprocessing the power data;
the coefficient calculation unit is used for determining a k value range and calculating a profile coefficient of a k value;
and the grade threshold unit is used for extracting the clustering analysis result corresponding to the k value and determining the grade threshold and the grade according to the numerical values of different clusters.
Preferably, the scoring module comprises:
an opinion table design unit, which is used for designing a value analysis object to inquire an opinion table by taking n basic indexes as factors influencing the bond;
the score integration unit is used for integrating scores of the indexes evaluated by the experts by an addition evaluation type Delphi expert evaluation method and feeding back the statistical result to the experts;
and the score determining unit is used for combining anonymous consultation and opinion feedback according to the scores of all the indexes corrected by the experts and the total object score to obtain the final score and the total score of the indexes and obtain an index consultation score table.
Preferably, the weight determination module includes:
and the weight determining unit is used for collecting the total customer division dependent variable in the index query score table by taking the scores corresponding to the evaluation grades of the n basic indexes as independent variables, and performing multiple linear regression by using a matlab or R language tool to determine the weight of each basic index.
The method adopted by the power grid customer comprehensive value evaluation system of the embodiment of the invention is a power grid customer comprehensive value evaluation method, so that the characteristics of the power grid customer comprehensive value evaluation system are the same as those of the power grid customer comprehensive value evaluation method, and are not described again.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (10)
1. A comprehensive value evaluation method for a power grid customer is characterized by comprising the following steps:
dividing the client indexes of the power grid to obtain a first-level index, a second-level index and a third-level index, wherein the first-level index, the second-level index and the third-level index comprise a current value and a potential value, the current value comprises income contribution, stability, social benefit and operation benefit, the potential value comprises loyalty, exhibition prospect, credit and policy guidance, and the income contribution, the stability, the social benefit and the operation benefit are the second-level indexes;
screening relevant real effective fields from a database for matching, and determining n basic indexes in the three-level indexes;
judging the grade of the n basic indexes by adopting a hierarchical clustering method and a Parlotto rule;
combining with a Delphi method expert evaluation method to obtain a collection index inquiry score table and a customer total score;
and analyzing and determining the weight of the basic index according to a multiple linear regression method.
2. The power grid customer comprehensive value evaluation method according to claim 1, wherein the income contribution comprises index measures such as the amount of electricity purchased, the regional contribution rate of the electricity fee, the ratio contribution degree of the amount of electricity purchased by an enterprise, the average price of the electricity used by the enterprise, the execution electricity price standard and the ratio of the occupied regional capacity; the stability comprises the measurement of indexes such as low-ebb electricity consumption rate, high-ebb electricity consumption rate, capacity change electricity consumption condition, capacity change period, electricity purchasing quantity increase rate, electricity purchasing quantity increase quantity and the like; the social benefits comprise whether the power consumption is high or not, whether the power consumption is a strong electricity requirement enterprise such as military medical treatment and the like, the load importance degree, the voltage level, the client scale, the power supply access condition, whether a thousand-level high-voltage client participates in the power protection task measurement or not; the operation benefits comprise the balance of power restoration, the number of times of meter faults, the load type of a client, whether double multi-source clients exist or not, the level of high-risk important clients, the power utilization change condition, the capacity change frequency and the inspection period; loyalty includes data completion, whether the client is a three-party client, accumulated electricity charge recovery rate, electricity charge recovery rate of the current period, electricity charge recovery punctuality, electricity charge recovery rate, electricity charge repayment capability, payment duration, price sensitivity, client interaction behavior and electricity consumption duration measurement; the development prospect comprises the amount of the electricity charge increase, the rate of the electricity charge increase, the influence degree of enterprises, the business scene degree, the advantages of the located industries, the management level of the enterprises and the measurement of the life cycle of the enterprises; the credit degree comprises historical arrearage amount, accumulated arrearage frequency ratio, average arrearage frequency, electric charge repayment guarantee level, arrearage power failure condition, pre-charged electric charge condition, metering fault information, preventive test information, potential safety hazard information, illegal electricity utilization condition, meter reading illegal frequency and meter fault frequency measurement; policy guidance includes whether to place policy restrictions, whether to place policy encouragement measures;
the electricity purchasing quantity, the regional contribution rate of the electricity fee, the contribution rate of the purchased electricity quantity of the enterprise, the average price of the electricity consumed by the enterprise, the execution electricity price standard, the index measurement such as the ratio of the occupied regional capacity, the low-ebb electricity consumption rate, the peak electricity consumption rate, the electricity consumption condition of the capacitance change, the capacitance change period, the electricity purchasing quantity growth rate, the electricity purchasing quantity growth quantity and the like, whether the electricity purchasing quantity is high energy consumption or not, whether the electricity purchasing quantity is a strong electricity requiring enterprise such as military medical treatment or not, the load importance degree, the voltage level, the client scale, the power supply access condition, whether the thousands of high-voltage clients or not, whether the electricity purchasing quantity participates in the electricity protection task measurement, the electricity recovery, the counter fault times, the client load type, whether the double multi-source clients are high-risk important client levels or not, the electricity consumption condition of the change, the capacity change frequency, the inspection period measurement, the data completion degree, the system comprises an electric charge recovery rate, an electric charge paying capacity, a payment duration, a price sensitivity, a customer interaction behavior, an electric charge duration measurement, an electric charge increase amount, an electric charge increase rate, an enterprise influence degree, an industry scene degree, an industry advantage, an enterprise management level, an enterprise life cycle measurement, a historical arrearage amount, an accumulated arrearage frequency ratio, an average arrearage frequency, an electric charge paying guarantee level, an arrearage power failure condition, a pre-paid electric charge condition, metering fault information, preventive test information, potential safety hazard information, a violation electric power consumption condition, a violation meter reading rule frequency, a meter fault frequency measurement, whether to be listed in policy restriction or not, and whether to be listed in policy encouragement measurement is a three-level index.
3. The method for evaluating the comprehensive value of the power grid customer as claimed in claim 1 or 2, wherein the step of screening relevant real effective fields from the database for matching and determining n basic indexes in the three-level indexes comprises the following steps:
corresponding the determined three-level indexes to database fields;
deleting indexes with vacant fields and data errors from the index library, and complementing the indexes with average number when some indexes are not applicable in time period;
and updating the three-level indexes corresponding to the database fields into n basic indexes.
4. The method for evaluating the comprehensive value of the power grid customer according to claim 1 or 2, wherein the step of judging the grades of the n basic indexes by adopting a hierarchical clustering method and a pareto rule comprises the following steps:
normalizing and preprocessing the power data;
determining a k value range, and calculating a profile coefficient of the k value;
and extracting a clustering analysis result corresponding to the k value, and determining a threshold value and a score value of the classification grade according to numerical values of different clusters.
5. The method for evaluating the comprehensive value of the grid customer as claimed in claim 4, wherein the step of obtaining the collected index solicitation score and the customer total score by combining with a Delphi expert scoring method comprises the following steps:
designing a value analysis object inquiry opinion list by taking n basic indexes as factors influencing the bond;
integrating the scores of the indexes evaluated by the experts by an additive evaluation type Delphi expert evaluation method, and feeding back the statistical result to the experts;
and combining anonymous consultation and opinion feedback according to the scores and the total object scores of all the indexes corrected by the experts to obtain the final scores and the total scores of the indexes and obtain an index consultation score table.
6. The grid customer composite value assessment method according to claim 5, wherein said analytically determining the base index weight according to a multiple linear regression method comprises:
and taking the scores corresponding to the evaluation grades of the n basic indexes as independent variables, collecting the total customer scores in the index query score table as dependent variables, and determining the weight of each basic index by using a multi-element linear regression method by using a mat ab or R language tool.
7. A grid customer composite value evaluation system, characterized in that, the grid customer composite value evaluation system includes:
the client index dividing module is used for dividing the client indexes of the power grid to obtain a first-level index, a second-level index and a third-level index, wherein the first-level index, the second-level index and the third-level index comprise a current value and a potential value, the current value comprises income contribution, stability, social benefits and operation benefits, the potential value comprises loyalty, exhibition prospect, credit and policy guidance, the income contribution, the stability, the social benefits and the operation benefits are the second-level indexes, and the income contribution, the stability, the social benefits and the operation benefits are the second-level indexes;
the database matching module is used for screening relevant real effective fields from the database for matching and determining n basic indexes in the three-level indexes;
the grade judging module is used for judging the grade of the n basic indexes by adopting a hierarchical clustering method and a Parlotto rule;
the scoring module is used for obtaining a collection index inquiry score table and a customer total score by combining a Delphi method expert scoring method;
and the weight determining module is used for analyzing and determining the weight of the basic index according to the multiple linear regression method.
8. The grid customer composite value evaluation system according to claim 7, wherein the level evaluation module comprises:
the normalization unit is used for normalizing and preprocessing the power data;
the coefficient calculation unit is used for determining a k value range and calculating a profile coefficient of a k value;
and the grade threshold unit is used for extracting the clustering analysis result corresponding to the k value and determining the grade threshold and the grade according to the numerical values of different clusters.
9. The grid customer composite value assessment system according to claim 8, wherein said scoring module comprises:
an opinion table design unit, which is used for designing a value analysis object to inquire an opinion table by taking n basic indexes as factors influencing the bond;
the score integration unit is used for integrating scores of the indexes evaluated by the experts by an addition evaluation type Delphi expert evaluation method and feeding back the statistical result to the experts;
and the score determining unit is used for combining anonymous consultation and opinion feedback according to the scores of all the indexes and the total object scores corrected by the experts to obtain the final index score and the total object score so as to obtain an index consultation score table.
10. The grid customer composite value evaluation system of claim 9, wherein the weight determination module comprises:
and the weight determining unit is used for collecting the customer total score in the index query score table as a dependent variable by taking the scores corresponding to the n basic index judgment grades as independent variables, and performing multi-element linear regression by using a mat l ab or an R language tool to determine the weight of each basic index.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610696848.1A CN106372775A (en) | 2016-08-19 | 2016-08-19 | Assessment method and system of comprehensive value of power grid client |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610696848.1A CN106372775A (en) | 2016-08-19 | 2016-08-19 | Assessment method and system of comprehensive value of power grid client |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106372775A true CN106372775A (en) | 2017-02-01 |
Family
ID=57878583
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610696848.1A Pending CN106372775A (en) | 2016-08-19 | 2016-08-19 | Assessment method and system of comprehensive value of power grid client |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106372775A (en) |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107133734A (en) * | 2017-04-28 | 2017-09-05 | 浙江极赢信息技术有限公司 | A kind of Channel Quality evaluation method and system |
| CN107180392A (en) * | 2017-05-18 | 2017-09-19 | 北京科技大学 | A kind of electric power enterprise tariff recovery digital simulation method |
| CN107292518A (en) * | 2017-06-21 | 2017-10-24 | 中国农业科学院农田灌溉研究所 | Topsoil index acquisition methods and device |
| CN107729651A (en) * | 2017-10-17 | 2018-02-23 | 黄河水利委员会黄河水利科学研究院 | Domatic rill developmental morphology characteristic synthetic quantization method based on various dimensions |
| CN108021739A (en) * | 2017-11-22 | 2018-05-11 | 中国北方发动机研究所(天津) | A kind of high-power military diesel machine Real-Time Model parameter Impact analysis method |
| CN108074108A (en) * | 2017-11-02 | 2018-05-25 | 平安科技（深圳）有限公司 | A kind of display methods and its terminal of net recommendation |
| CN108446834A (en) * | 2018-03-02 | 2018-08-24 | 国网湖北省电力公司 | A kind of residential electricity consumption boot policy Potentials method based on fuzzy evaluation |
| CN108931755A (en) * | 2018-06-11 | 2018-12-04 | 宁波三星智能电气有限公司 | A kind of electric energy meter power grid quality determining method |
| CN109508855A (en) * | 2018-09-27 | 2019-03-22 | 国网福建省电力有限公司信息通信分公司 | A kind of sales service compliance discriminatory analysis method based on big data processing |
| CN110163706A (en) * | 2018-02-13 | 2019-08-23 | 北京京东尚科信息技术有限公司 | Method and apparatus for generating information |
| CN110197313A (en) * | 2018-02-27 | 2019-09-03 | 顺丰科技有限公司 | Employee's evaluation method and device, equipment and storage medium |
| CN110288395A (en) * | 2019-06-20 | 2019-09-27 | 卓尔智联(武汉)研究院有限公司 | Outdoor advertising position Valuation Method, electronic equipment and storage medium |
| CN110858343A (en) * | 2018-08-23 | 2020-03-03 | 国信优易数据有限公司 | Data asset value evaluation system and method |
| CN111709327A (en) * | 2020-05-29 | 2020-09-25 | 中国人民财产保险股份有限公司 | Fuzzy matching method and device based on OCR recognition |
| CN112100246A (en) * | 2020-09-22 | 2020-12-18 | 国网辽宁省电力有限公司电力科学研究院 | Customer electricity value mining method based on multi-dimensional graph code label |
| CN112102003A (en) * | 2020-09-18 | 2020-12-18 | 国网辽宁省电力有限公司电力科学研究院 | Big data platform-based electricity customer core resource management system and method |
| CN113298398A (en) * | 2021-05-31 | 2021-08-24 | 中国建设银行股份有限公司 | Client viscosity evaluation method and device, readable medium and equipment |
| CN113407827A (en) * | 2021-06-11 | 2021-09-17 | 广州三七极创网络科技有限公司 | Information recommendation method, device, equipment and medium based on user value classification |
| CN113591018A (en) * | 2021-07-30 | 2021-11-02 | 中国联合网络通信集团有限公司 | Communication client classification management method, system, electronic device and storage medium |
| CN113780861A (en) * | 2021-09-18 | 2021-12-10 | 深圳供电局有限公司 | Component index evaluation method and system based on user daily electric quantity adjustment value |
-
2016
- 2016-08-19 CN CN201610696848.1A patent/CN106372775A/en active Pending
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107133734A (en) * | 2017-04-28 | 2017-09-05 | 浙江极赢信息技术有限公司 | A kind of Channel Quality evaluation method and system |
| CN107180392A (en) * | 2017-05-18 | 2017-09-19 | 北京科技大学 | A kind of electric power enterprise tariff recovery digital simulation method |
| CN107292518A (en) * | 2017-06-21 | 2017-10-24 | 中国农业科学院农田灌溉研究所 | Topsoil index acquisition methods and device |
| CN107729651A (en) * | 2017-10-17 | 2018-02-23 | 黄河水利委员会黄河水利科学研究院 | Domatic rill developmental morphology characteristic synthetic quantization method based on various dimensions |
| CN108074108A (en) * | 2017-11-02 | 2018-05-25 | 平安科技（深圳）有限公司 | A kind of display methods and its terminal of net recommendation |
| CN108074108B (en) * | 2017-11-02 | 2021-02-09 | 平安科技（深圳）有限公司 | Method and terminal for displaying net recommendation value |
| CN108021739A (en) * | 2017-11-22 | 2018-05-11 | 中国北方发动机研究所(天津) | A kind of high-power military diesel machine Real-Time Model parameter Impact analysis method |
| CN110163706B (en) * | 2018-02-13 | 2024-04-19 | 北京京东尚科信息技术有限公司 | Method and device for generating information |
| CN110163706A (en) * | 2018-02-13 | 2019-08-23 | 北京京东尚科信息技术有限公司 | Method and apparatus for generating information |
| CN110197313A (en) * | 2018-02-27 | 2019-09-03 | 顺丰科技有限公司 | Employee's evaluation method and device, equipment and storage medium |
| CN108446834A (en) * | 2018-03-02 | 2018-08-24 | 国网湖北省电力公司 | A kind of residential electricity consumption boot policy Potentials method based on fuzzy evaluation |
| CN108931755A (en) * | 2018-06-11 | 2018-12-04 | 宁波三星智能电气有限公司 | A kind of electric energy meter power grid quality determining method |
| CN110858343A (en) * | 2018-08-23 | 2020-03-03 | 国信优易数据有限公司 | Data asset value evaluation system and method |
| CN109508855A (en) * | 2018-09-27 | 2019-03-22 | 国网福建省电力有限公司信息通信分公司 | A kind of sales service compliance discriminatory analysis method based on big data processing |
| CN110288395A (en) * | 2019-06-20 | 2019-09-27 | 卓尔智联(武汉)研究院有限公司 | Outdoor advertising position Valuation Method, electronic equipment and storage medium |
| CN111709327A (en) * | 2020-05-29 | 2020-09-25 | 中国人民财产保险股份有限公司 | Fuzzy matching method and device based on OCR recognition |
| CN111709327B (en) * | 2020-05-29 | 2023-06-27 | 中国人民财产保险股份有限公司 | Fuzzy matching method and device based on OCR (optical character recognition) |
| CN112102003A (en) * | 2020-09-18 | 2020-12-18 | 国网辽宁省电力有限公司电力科学研究院 | Big data platform-based electricity customer core resource management system and method |
| CN112102003B (en) * | 2020-09-18 | 2024-08-09 | 国网辽宁省电力有限公司电力科学研究院 | System and method for managing core resources of electricity utilization client based on big data platform |
| CN112100246A (en) * | 2020-09-22 | 2020-12-18 | 国网辽宁省电力有限公司电力科学研究院 | Customer electricity value mining method based on multi-dimensional graph code label |
| CN113298398A (en) * | 2021-05-31 | 2021-08-24 | 中国建设银行股份有限公司 | Client viscosity evaluation method and device, readable medium and equipment |
| CN113407827A (en) * | 2021-06-11 | 2021-09-17 | 广州三七极创网络科技有限公司 | Information recommendation method, device, equipment and medium based on user value classification |
| CN113591018A (en) * | 2021-07-30 | 2021-11-02 | 中国联合网络通信集团有限公司 | Communication client classification management method, system, electronic device and storage medium |
| CN113780861A (en) * | 2021-09-18 | 2021-12-10 | 深圳供电局有限公司 | Component index evaluation method and system based on user daily electric quantity adjustment value |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106372775A (en) | Assessment method and system of comprehensive value of power grid client | |
| CN110135612B (en) | Method for monitoring capacity of material supply Shang Sheng and early warning abnormality based on electricity consumption analysis | |
| CN109063945B (en) | Value evaluation system-based 360-degree customer portrait construction method for electricity selling company | |
| Li et al. | A MIDAS modelling framework for Chinese inflation index forecast incorporating Google search data | |
| CN103632203A (en) | Distribution network power supply area division method based on comprehensive evaluation | |
| CN105160416A (en) | Transformer area reasonable line loss prediction method based on principal component analysis and neural network | |
| CN109872061A (en) | Power grid infrastructure improvement and promotion decision-making method | |
| CN101398919A (en) | Electric power requirement analytic system for utilizing mode analysis and method thereof | |
| CN106709818A (en) | Power consumption enterprise credit risk evaluation method | |
| Boogen et al. | Demand-side management by electric utilities in Switzerland: Analyzing its impact on residential electricity demand | |
| CN106447198A (en) | Power consumption checking method based on business expanding installation data | |
| CN111815060A (en) | Short-term load prediction method and device for power utilization area | |
| CN104182835A (en) | Three-dimensional material goods classification model based on entire life-cycle management and type determination method | |
| CN106447075A (en) | Industrial electricity demand prediction method and system | |
| CN108805331A (en) | A kind of electricity demand forecasting method | |
| CN115905319B (en) | Automatic identification method and system for abnormal electricity fees of massive users | |
| CN106600146A (en) | Electricity fee collection risk evaluation method and apparatus | |
| CN112308305A (en) | Multi-model synthesis-based electricity sales amount prediction method | |
| CN111798333A (en) | Energy utilization evaluation and electricity utilization safety analysis method and system | |
| CN115239502A (en) | Analyst simulation method, analyst simulation system, electronic device and storage medium | |
| CN114219225A (en) | Power grid investment benefit evaluation system and evaluation method based on multi-source data | |
| CN113450004A (en) | Power credit report generation method and device, electronic equipment and readable storage medium | |
| CN113570250A (en) | Full life cycle multi-target comprehensive evaluation method for transformer temperature measuring device | |
| Zhang et al. | Two-stage characteristic recognition of demand side resource for load aggregator based on bias-SVD matrix factorization and Bayesian inference | |
| Belhaiza et al. | A Neural Network Forecasting Approach for the Smart Grid Demand Response Management Problem |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170201 |