CN111784379A

CN111784379A - Estimation method and device for additional payment electric charge and screening method and device for abnormal cases

Info

Publication number: CN111784379A
Application number: CN202010424910.8A
Authority: CN
Inventors: 万泉; 陈雁; 刘俊玲; 袁葆; 欧阳红; 张文; 姜涛; 刘俊恺; 白琳; 闫富荣
Original assignee: State Grid Corp of China SGCC; State Grid Information and Telecommunication Co Ltd; Beijing China Power Information Technology Co Ltd
Current assignee: State Grid Corp of China SGCC; State Grid Information and Telecommunication Co Ltd; Beijing China Power Information Technology Co Ltd
Priority date: 2020-05-19
Filing date: 2020-05-19
Publication date: 2020-10-16
Anticipated expiration: 2040-05-19
Also published as: CN111784379B

Abstract

The application provides an estimation method and device for the additional payment electric charge and a screening method and device for abnormal cases. The problem that when the confirmed electricity stealing user is calculated, if the electricity fee to be paid is directly calculated in the conventional electricity fee calculation mode, the calculated electricity fee to be paid is not accurate enough, and the phenomenon that the electricity fee to be paid is too much or too little is often caused is solved.

Description

Estimation method and device for additional payment electric charge and screening method and device for abnormal cases

Technical Field

The application relates to the technical field of electric power systems, in particular to an estimation method and device for electric charge tracing and a screening method and device for abnormal cases.

Background

With the continuous increase of regional economy, the living standard of residents is continuously improved, and the electricity stealing phenomenon is more serious while the power demand is increased. The electricity stealing methods are various, so that the electricity stealing troubleshooting work is more difficult. Aiming at the confirmed electricity stealing users, how to accurately and reasonably calculate the electricity fee to be paid after the electricity stealing is a big problem in the field of electricity stealing prevention.

At present, when calculating the recollection fee of the confirmed electricity stealing users, the conventional recollection fee calculation mode is mainly calculated according to an electric power method and supply and utilization business rules, and the calculation mode has a very serious problem. Because the types of the electricity stealing users are different and the electricity stealing methods of the electricity stealing users are different, if the current calculation mode of the additional payment of the electricity fee is directly used for calculating the electricity fee to be additionally paid, the calculated additional payment fee is easy to be inaccurate, and the phenomenon of excessive or insufficient additional payment of the electricity fee often exists. This results in inaccurate treatment of electricity stealing prevention work and loss of the relevant power supply unit.

Disclosure of Invention

In view of the above, the present application provides an estimation method and apparatus for paying electric charge after tracking, and a screening method and apparatus for abnormal cases, so as to solve the problem that when calculating the electric charge after tracking of a confirmed electricity stealing user, if the electric charge to be paid is calculated directly by using the existing calculation method for paying electric charge after tracking, the calculated electric charge after tracking is not accurate enough, and the electric charge after tracking is too much or too little.

In order to achieve the above purpose, the present application provides the following technical solutions:

the application discloses in a first aspect a method for estimating an electric charge of pursuing payment, comprising:

aiming at a user who steals electricity, acquiring electricity utilization characteristic data of the user; the electricity utilization characteristic data comprise electricity consumption of the user, line loss of a transformer area and time for opening an electricity meter cover by the user;

obtaining the electricity stealing time interval of the user according to the electricity utilization characteristic data;

identifying an electricity stealing method of the user, and obtaining the average electricity stealing capacity of the user according to the electricity stealing method of the user;

calculating the electricity stealing time interval and the average electricity stealing capacity to obtain the electricity stealing capacity of the user in the electricity stealing time interval;

and calculating the additional payment electric charge corresponding to the electric larceny quantity of the user in the electric larceny time interval according to a preset electric charge calculation method.

Optionally, in the method, obtaining the electricity stealing time interval of the user according to the electricity utilization characteristic data includes:

inquiring the electricity utilization characteristic data to obtain an electricity utilization data sequence from the latest meter cover opening time of the user to the electricity stealing check time; the electricity consumption data sequence comprises a line loss electricity quantity sequence of a transformer area of each day from the latest meter opening and covering time of the user to electricity stealing check time and an electricity consumption quantity sequence of the user;

searching a time interval meeting the conditions that the line loss of the distribution room is suddenly increased and the number of times of the sudden decrease of the power consumption of the user is higher than a preset threshold value within a preset time period from the power consumption data sequence, and taking the time interval as a first suspected power stealing time interval;

screening to obtain a time interval from electricity stealing check time to meter cover opening time which is the latest time from the electricity stealing check time of the user from the time when the user opens the meter cover;

performing sliding window type scanning in a time interval from the electricity stealing check time to the meter opening time which is the latest time from the electricity stealing check time by the user to obtain a time interval in which the pearson correlation between the line loss data of all the distribution areas and the electricity consumption of the user is higher than a preset threshold value, and taking the time interval as a second suspected electricity stealing time interval;

and combining the first suspected electricity stealing time and the second suspected electricity stealing time to obtain an electricity stealing time interval of the user.

Optionally, in the method, the obtaining the average electricity stealing capacity data of the user according to the electricity stealing method of the user includes:

if the electricity stealing method of the user is equal ratio electricity stealing, judging the proportion of electricity stealing according to an electricity stealing instrument of the user;

calculating the power consumption data of the user according to the proportion to obtain average electricity stealing data of the user;

if the electricity stealing method of the user is bypassing electricity stealing, acquiring an electricity stealing application mode of the user;

and inquiring the average power consumption corresponding to the electricity stealing application mode to obtain the average electricity stealing quantity data of the user.

The second aspect of the present application discloses a method for screening abnormal cases, which includes:

analyzing the data of each electricity stealing case sample aiming at the electricity stealing case sample which finishes the electricity fee tracing service to obtain the sample characteristic data of each electricity stealing case sample; the sample characteristic data comprises electricity stealing methods, electricity utilization properties, electricity consumption, line loss electricity, average electricity stealing electricity data, a ratio of live line current to zero line current, interval time from occurrence of a power failure event to occurrence of a power-on event and interval time from occurrence of a meter opening event to occurrence of a meter closing event of each sample case;

dividing the electricity stealing case samples by utilizing a fuzzy clustering algorithm according to the sample characteristic data to form one or more electricity stealing category clustering results;

obtaining the standard additional payment electric charge of each electric larceny category according to the clustering result;

screening the electricity fee tracing service abnormal cases by utilizing the electricity fee tracing of the electricity stealing case samples of the same electricity stealing category and the standard electricity fee tracing; wherein the electric charge of the additional payment of the electric larceny case sample is calculated by the method according to any one of the first aspect of the application.

Optionally, in the method, the step of screening the abnormal cases of the electricity fee recollecting service by using the electricity fee recollecting and the standard electricity fee recollecting of the electricity stealing case samples of the same electricity stealing category includes:

respectively differentiating the recollected electric charge of each electric larceny case sample of the same electric larceny category with the standard recollected electric charge of the same electric larceny category to obtain a result value;

and if the result value is larger than a preset threshold value, the electricity stealing case sample corresponding to the result value belongs to the electricity fee service exception case.

Optionally, in the method, the additional payment electric charge of the electric larceny case sample of the same electric larceny category and the standard additional payment electric charge are utilized to screen out the additional payment electric charge service abnormal case, which includes

Inputting the standard additional payment electric charge of each electricity stealing category and the sample characteristic data of each electricity stealing case sample into a classifier;

dividing the electricity stealing case sample into a training set and a testing set;

training a classifier by using the electricity stealing case samples in the training set, and if the difference value between the electric charge chased by the electricity stealing case samples of the same electricity stealing category in the training set and the standard electric charge chased by the same electricity stealing category is larger than the threshold value, setting the electricity stealing case samples as abnormal cases of electricity charge chased business;

and inputting the electricity stealing case samples with the concentrated test into the classifier for classification processing, and screening the abnormal cases of the electricity fee tracing service.

Optionally, the method further includes:

and evaluating the electric charge tracing service work by using the screened abnormal case data of the electric charge tracing service.

The third aspect of the present application discloses an estimation device of electric charge of pursuing payment, including:

the acquisition unit is used for acquiring the electricity utilization characteristic data of a user who steals electricity; the electricity utilization characteristic data comprise electricity consumption of the user, line loss of a transformer area and time for opening an electricity meter cover by the user;

the first processing unit is used for obtaining the electricity stealing time interval of the user according to the electricity utilization characteristic data;

the second processing unit is used for identifying the electricity stealing method of the user and obtaining the average electricity stealing capacity of the user according to the electricity stealing method of the user;

the first calculation unit is used for calculating the electricity stealing time interval and the average electricity stealing capacity to obtain the electricity stealing capacity of the user in the electricity stealing time interval;

and the second calculating unit is used for calculating the additional payment electric charge corresponding to the electric larceny quantity of the user in the electric larceny time interval according to a preset electric charge calculating method.

Optionally, in the above apparatus, the first processing unit includes:

the first inquiry subunit is used for inquiring the electricity utilization characteristic data to obtain an electricity utilization data sequence from the latest meter opening time of the user to the electricity stealing check time; the electricity consumption data sequence comprises a line loss electricity quantity sequence of a transformer area of each day from the latest meter opening and covering time of the user to electricity stealing check time and an electricity consumption quantity sequence of the user;

the first searching subunit is configured to search, from the electricity consumption data sequence, a time interval satisfying a condition that, within a preset time period, the number of times that the line loss of the distribution room increases suddenly and the electricity consumption of the user decreases suddenly at the same time is higher than a preset threshold value, and use the time interval as a first suspected electricity stealing time interval;

the second searching subunit is used for screening and obtaining a time interval from the electricity stealing check time to the meter cover opening time which is the latest time from the electricity stealing check time of the user from the time when the user opens the meter cover;

the scanning subunit is used for performing sliding window type scanning in a time interval from the electricity stealing check time to the meter opening cover time which is the latest time away from the electricity stealing check time by the user to obtain a time interval in which the pearson correlation between the line loss data of all the distribution areas and the electricity consumption of the user is higher than a preset threshold value, and the time interval is used as a second suspected electricity stealing time interval;

and the merging subunit is used for merging the first suspected electricity stealing time and the second suspected electricity stealing time to obtain an electricity stealing time interval of the user.

Optionally, in the above apparatus, the second processing unit includes:

the judging subunit is used for judging the proportion of electricity stealing according to the electricity stealing instrument of the user if the electricity stealing method of the user is equal proportion electricity stealing;

the calculating subunit is used for calculating the power consumption data of the user according to the proportion to obtain the average electricity stealing capacity data of the user;

the obtaining subunit is used for obtaining the electricity stealing application mode of the user if the electricity stealing method of the user is bypassing electricity stealing;

and the second inquiry subunit is used for inquiring the average power consumption corresponding to the electricity stealing application mode to obtain the average electricity stealing quantity data of the user.

The fourth aspect of the present application discloses a screening device for abnormal cases, which includes:

the analysis unit is used for analyzing the data of each electricity stealing case sample aiming at the electricity stealing case sample which finishes the electricity fee tracing service to obtain the sample characteristic data of each electricity stealing case sample; the sample characteristic data comprises electricity stealing methods, electricity utilization properties, electricity consumption, line loss electricity, average electricity stealing electricity data, a ratio of live line current to zero line current, interval time from occurrence of a power failure event to occurrence of a power-on event and interval time from occurrence of a meter opening event to occurrence of a meter closing event of each sample case;

the dividing unit is used for dividing the electricity stealing case samples by utilizing a fuzzy clustering algorithm according to the sample characteristic data to form one or more clustering results of electricity stealing categories;

the acquisition unit is used for acquiring the standard additional payment electric charge of each electric larceny category according to the clustering result;

the screening unit is used for screening the electricity fee tracing service abnormal cases by utilizing the electricity fee tracing of the electricity stealing case samples of the same electricity stealing category and the standard electricity fee tracing; wherein the electric charge of the additional payment of the electric larceny case sample is calculated by the method according to any one of the first aspect of the application.

Optionally, in the foregoing apparatus, the screening unit includes:

the calculation subunit is used for respectively subtracting the electric charge paid by the electricity stealing case sample of the same electricity stealing category from the standard electric charge paid by the electricity stealing case sample of the same electricity stealing category to obtain a result value;

and the judging subunit is used for judging that the electricity stealing case sample corresponding to the result value belongs to the electricity fee service abnormal case if the result value is greater than a preset threshold value.

Optionally, in the foregoing apparatus, the screening unit includes:

the input subunit is used for inputting the standard surcharge electric charge of each electricity stealing category and the sample characteristic data of each electricity stealing case sample into the classifier;

the dividing subunit is used for dividing the electricity stealing case sample into a training set and a test set;

the training subunit is used for training the classifier by using the electricity stealing case samples in the training set, and if the difference value between the recollected electricity fee of the electricity stealing case sample of the same electricity stealing category in the training set and the standard recollected electricity fee of the same electricity stealing category is greater than the threshold value, setting the electricity stealing case sample as a recollected electricity fee service abnormal case;

and the screening subunit is used for inputting the electricity stealing case samples in the test set into the classifier for classification processing, and screening the abnormal cases of the electricity fee tracing service.

Optionally, the above apparatus further includes:

and the evaluation unit is used for evaluating the electric charge tracing service work by utilizing the screened abnormal case data of the electric charge tracing service.

According to the technical scheme, the method for estimating the electric charge chasing provided by the application aims at the user who steals electricity, and obtains the electricity utilization characteristic data of the user. The electricity utilization characteristic data comprises electricity consumption of a user, line loss of a platform area and time for opening an electricity meter cover by the user. And then obtaining the electricity stealing time interval of the user according to the electricity utilization characteristic data. And identifying the electricity stealing method of the user, and obtaining the average electricity stealing capacity of the user according to the electricity stealing method of the user. And calculating the electricity stealing time interval and the average electricity stealing quantity to obtain the electricity stealing quantity of the user in the electricity stealing time interval. And finally, calculating the additional payment electric charge corresponding to the electric larceny quantity of the user in the electric larceny time interval according to a preset electric charge calculation method. Therefore, the method can be used for solving the problems that when the payment following of the confirmed electricity stealing users is calculated, if the electric charge to be paid is directly calculated by the conventional calculation method of the payment following electric charge, the calculated payment following charge is not accurate enough, and the phenomenon of excessive or insufficient payment following electric charge often exists.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.

Fig. 1 is a flowchart of an estimation method of an electric charge reimbursement disclosed in an embodiment of the present application;

FIG. 2 is a flowchart of one implementation of step S102 disclosed in another embodiment of the present application;

FIG. 3 is a flowchart of a method for screening abnormal cases according to another embodiment of the present disclosure;

FIG. 4 is a flowchart of one implementation of step S304 disclosed in another embodiment of the present application;

FIG. 5 is a schematic diagram of a prior art linear support vector machine;

fig. 6 is a schematic diagram of an electricity fee tracking and estimating device according to another embodiment of the present disclosure;

fig. 7 is a schematic diagram of a screening apparatus for abnormal cases according to another embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

In this application, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.

Moreover, in this document, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions.

It can be known from the background art that, when calculating the recollection fee of the confirmed electricity stealing users, the existing calculation method of the recollection fee is mainly calculated according to the power law and the business rules of supplying and using electricity, and the calculation method has a very serious problem. Because the types of the electricity stealing users are different and the electricity stealing methods of the electricity stealing users are different, if the current calculation mode of the additional payment of the electricity fee is directly used for calculating the electricity fee to be additionally paid, the calculated additional payment fee is easy to be inaccurate, and the phenomenon of excessive or insufficient additional payment of the electricity fee often exists. This results in inaccurate treatment of electricity stealing prevention work and loss of the relevant power supply unit.

In view of this, an embodiment of the present application provides a method for adjusting a server load, as shown in fig. 1, specifically including:

s101, acquiring power utilization characteristic data of a user aiming at the user who steals power; the electricity utilization characteristic data comprises electricity consumption of a user, line loss of a platform area and time for opening an electricity meter cover by the user.

It should be noted that, for those users who have determined that there is an electricity stealing behavior, the electricity using characteristic data of the user is obtained, where the electricity stealing behavior refers to that the electricity consumer steals the electric energy with the purpose of reducing the electric energy metering and the electric charge payment. And the electricity utilization characteristic data comprises the electricity consumption of the user, the line loss of the platform area and the time when the user opens the meter cover. The active power loss and the electric energy loss generated in the transmission and distribution process of the power grid are collectively called line loss, which is called line loss for short. The line loss types can be classified into statistical line loss, theoretical line loss and management line loss, wherein the line loss electric quantity of the distribution room refers to statistical line loss, namely actual line loss, and is a difference value between the power supply quantity and the electricity selling quantity calculated according to the electric energy meter index.

And S102, obtaining the electricity stealing time interval of the user according to the electricity utilization characteristic data.

The electricity consumption characteristic data such as the electricity consumption of the user, the line loss of the platform area, the time for opening the meter cover of the user and the like are utilized to analyze the data which accord with the electricity stealing characteristics of the user, so that the electricity stealing time interval of the user is obtained.

Optionally, in another embodiment of the present application, an implementation manner of step S102, as shown in fig. 2, specifically includes:

s201, inquiring power utilization characteristic data to obtain a power utilization data sequence from the latest meter cover opening time of a user to the electricity stealing check time; the electricity consumption data sequence comprises a line loss electricity quantity sequence of a transformer area of each day from the last meter opening time of a user to the electricity stealing check time and an electricity consumption quantity sequence of the user.

It should be noted that, the electricity consumption characteristic data such as the electricity consumption of the user, the line loss of the platform area, and the time when the user opens the electricity meter cover are queried to obtain the electricity consumption data sequence from the time when the user opens the electricity meter cover last time to the time when the electricity stealing check is performed. The electricity consumption data sequence comprises a line loss electricity quantity sequence of a transformer area of each day from the last meter opening time of a user to the electricity stealing check time and an electricity consumption quantity sequence of the user. For example, if the electricity stealing subscriber a in the transformer area a has the latest uncapping time of 1 month and 1 day of 2020 and the electricity stealing survey time of 3 months and 1 day of 2020, the line loss power sequence Y (Y) of the transformer area a from 1 month and 1 day of 2020 to 1 month and 3 days of 2020 is extracted (Y)₁,y₂…y_n) And daily electric quantity sequence X (X) of user A₁,x₂…x_n)。

S202, searching a time interval meeting the conditions that the line loss quantity of the transformer area suddenly increases and the power consumption quantity of the user suddenly decreases simultaneously within a preset time period and the frequency is higher than a preset threshold value from the power consumption data sequence, and taking the time interval as a first suspected power stealing time interval.

The sudden increase of the line loss generally indicates that the electrical load of the user in the station area is generally suddenly increased or caused by electricity stealing behavior, and if the line loss is suddenly increased and the electrical load of the user is suddenly decreased, abnormal behavior may exist. Therefore, from the electricity data sequence, a time interval satisfying the condition that the number of times of the station line loss sudden increase and the user electricity consumption sudden decrease occurring simultaneously in a certain time period is higher than a threshold value is found out and is used as a first suspected electricity stealing time interval. For example, in a time interval of 30 days from 2/1/2020 to 3/1/2020, where the station line loss suddenly increases and the number of times of simultaneous occurrence of sudden decreases in the power consumption of the user is higher than 5 times, the time interval from 2/1/2020 to 3/1/2020 is defined as the first suspected electricity stealing time interval.

S203, screening the time interval from the electricity stealing check time to the meter cover opening time which is the latest time from the electricity stealing check time of the user from the time when the user opens the meter cover.

The time when the user opens the electric meter cover is obtained from the electricity utilization characteristic data of the user, and then the time interval from the electricity stealing check time to the cover opening time which is the latest time from the electricity stealing check time of the user is screened and obtained from the time when the user opens the electric meter cover.

S204, performing sliding window type scanning in a time interval from the electricity stealing check time to the meter opening time which is the latest time from the electricity stealing check time by the user to obtain a time interval in which the Pearson correlation coefficient of the line loss data of all the transformer areas and the electricity consumption of the user is higher than a preset threshold value, and taking the time interval as a second suspected electricity stealing time interval.

It should be noted that a Pearson correlation coefficient (Pearson correlation coefficient) is a linear correlation coefficient, which is a statistic for reflecting the linear correlation degree of two variables, and is also called as a "simple correlation coefficient", "Pearson product moment correlation coefficient" or "linear correlation coefficient", and is generally denoted by r, where n is a sample quantity, and is an observed value and a mean value of two variables, respectively. r describes the degree of linear correlation between two variables. The value of r is between-1 and +1, if r >0, the two variables are positively correlated, namely the larger the value of one variable is, the larger the value of the other variable is; if r <0, it indicates that the two variables are negatively correlated, i.e., the larger the value of one variable, the smaller the value of the other variable. If r is 0, it indicates that there is not a linear correlation between the two variables, but there may be other ways of correlation, such as a curve. The correlation between the line loss data of the transformer area and the power consumption of the user can be obtained by utilizing the calculation of the Pearson correlation coefficient, and when the correlation between the daily power consumption of a single user and the daily line loss of the transformer area is high, the power consumption behavior of the single user is similar to the line loss change of the transformer area, so that the power stealing behavior is likely to exist.

Therefore, the sliding window type scanning is carried out in the time interval from the electricity stealing check time to the meter opening time which is the latest time from the electricity stealing check time by the user, 15 days are set as the window, 7 days are set as the step length, and the cyclic scanning is carried out. And obtaining a time interval in which the Pearson correlation coefficient of the line loss data of all the distribution areas and the power consumption of the user is higher than a threshold value, wherein the threshold value can be set to be 0.85 and is used as a second suspected electricity stealing time interval. For example, in a time interval of 1/3/1/2020, if the pearson correlation coefficient between the line loss data of the distribution room and the power consumption of the user in two time intervals of 1/2020 to 1/15/2020 and 2/14/2020 to 2/28/2020 is higher than 0.85, both of the two time intervals are regarded as the second suspected power stealing time interval.

S205, the first suspected electricity stealing time and the second suspected electricity stealing time are combined to obtain an electricity stealing time interval of the user.

In addition, according to the above example, the first pseudo electricity stealing time interval is from 1/2/2020 to 1/3/2020, and the second pseudo electricity stealing time interval is from 1/2020 to 15/1/2020 and from 14/2/2020 to 28/2/2020. And combining the first suspected electricity stealing time and the second suspected electricity stealing time to obtain two time intervals of 1 month and 1 day of 2020 to 1 month and 15 days of 2020 and 2 months and 1 day of 2020 to 3 months and 1 day of 2020, so that the two time intervals are the electricity stealing time intervals of the user.

S103, identifying the electricity stealing method of the user, and obtaining the average electricity stealing capacity of the user according to the electricity stealing method of the user.

It should be noted that, the staff identifies the electricity stealing methods of the electricity stealing users according to experience, and performs data analysis according to different electricity stealing methods of the electricity stealing users to obtain the average electricity stealing amount of the users.

Optionally, in another embodiment of the present application, an implementation manner of obtaining the average electricity stealing capacity of the user according to the electricity stealing method of the user in step S103 may include:

if the electricity stealing method of the user is equal ratio electricity stealing, the proportion of electricity stealing is judged according to the electricity stealing instrument of the user.

And calculating the electricity consumption data of the user according to the proportion to obtain the average electricity stealing quantity data of the user.

And if the electricity stealing method of the user is bypassing electricity stealing, acquiring the electricity stealing application mode of the user.

It should be noted that, if the electricity stealing method of the user is equal ratio electricity stealing, the actual electricity consumption is generally multiple times of the electricity consumption of the meter, so the electricity stealing proportion can be determined according to the property of the electricity stealing instrument, and the electricity consumption data of the user is calculated according to the proportion to obtain the average electricity stealing data of the user. If the electricity is stolen by winding, the electricity stealing user usually goes over metering devices such as an electricity meter and the like to steal electricity, and the actual electricity consumption is difficult to judge through the electricity metering amount of the meter, so that the average electricity consumption corresponding to the high-power machine used for breeding or production by the user can be inquired according to the electricity stealing application mode of the user, such as part of users used for breeding or production of the high-power machine, and the average electricity stealing amount data of the user is obtained.

And S104, calculating the electricity stealing time interval and the average electricity stealing quantity to obtain the electricity stealing quantity of the user in the electricity stealing time interval.

It should be noted that after the electricity stealing time interval and the average electricity stealing amount of the electricity stealing user are obtained, the total electricity stealing amount of the user in the electricity stealing time interval can be obtained by multiplying the average electricity stealing amount of the user by the electricity stealing time.

And S105, calculating the additional payment electric charge corresponding to the electric larceny quantity of the user in the electric larceny time interval according to a preset electric charge calculation method.

It should be noted that after the total electricity stealing electric quantity of the user in the electricity stealing time interval is obtained, the electric charge paid after the total electricity stealing electric quantity of the user in the electricity stealing time interval is calculated according to the electric charge calculation method of each power supply unit.

In the method for estimating the electric fee paid by the following charge, the electricity utilization characteristic data of the user is acquired for the user who steals electricity. The electricity utilization characteristic data comprises electricity consumption of a user, line loss of a platform area and time for opening an electricity meter cover by the user. And then obtaining the electricity stealing time interval of the user according to the electricity utilization characteristic data. And identifying the electricity stealing method of the user, and obtaining the average electricity stealing capacity of the user according to the electricity stealing method of the user. And calculating the electricity stealing time interval and the average electricity stealing quantity to obtain the electricity stealing quantity of the user in the electricity stealing time interval. And finally, calculating the additional payment electric charge corresponding to the electric larceny quantity of the user in the electric larceny time interval according to a preset electric charge calculation method. Therefore, the method can be used for solving the problems that when the payment following of the confirmed electricity stealing users is calculated, if the electric charge to be paid is directly calculated by the conventional calculation method of the payment following electric charge, the calculated payment following charge is not accurate enough, and the phenomenon of excessive or insufficient payment following electric charge often exists.

In another embodiment of the present application, a method for screening an abnormal case is further disclosed, which is shown in fig. 3, and specifically includes:

s301, aiming at the electricity stealing case samples which finish the electricity fee tracing service, analyzing the data of each electricity stealing case sample to obtain the sample characteristic data of each electricity stealing case sample; the sample characteristic data comprises electricity stealing methods, electricity using properties, electricity consumption, line loss electricity, average electricity stealing electricity data, a ratio of live line current to zero line current, interval time from power failure events to power-on events and interval time from meter opening events to meter closing events of each sample case.

It should be noted that, for the electricity stealing case samples that have completed the electric fee tracing service, the data of each electricity stealing case sample is analyzed, and the sample characteristic data of each electricity stealing case sample is extracted. The sample characteristic data comprises electricity stealing methods, electricity using properties, electricity consumption, line loss electricity, average electricity stealing electricity data, a ratio of live line current to zero line current, interval time from power failure events to power-on events and interval time from meter opening events to meter closing events of each sample case.

And S302, dividing the electricity stealing case samples by utilizing a fuzzy clustering algorithm according to the sample characteristic data to form one or more electricity stealing category clustering results.

It should be noted that the fuzzy C-means algorithm is a clustering algorithm based on partitioning, and the idea is to maximize the similarity between objects partitioned into the same cluster, and minimize the similarity between different clusters. The fuzzy C-means algorithm is an improvement of a common C-means algorithm, the common C-means algorithm is hard for data division, and the fuzzy C-means algorithm is a flexible fuzzy division. Assume that the sample set is X ═ X₁，x₂，…，x_nC is the number of classes, m (j ═ 1, 2, …, C) is the center of each cluster, u is the number of classes_j(x_i) If the ith sample is a membership function corresponding to the jth class, the clustering loss function based on the membership function can be written as:

b is a weighting index, also called a smoothing factor, and controls the sharing degree of the mode among fuzzy classes; let J_fTo m_jAnd u_j(x_i) The minimum value of the formula (1) is obtained with the partial derivative of (2) being 0. From equation (1) we can obtain:

and (3) solving the formula (2) and the formula (3) by adopting an iterative method until a convergence condition is met to obtain an optimal solution.

In a plurality of fuzzy clustering algorithms, the fuzzy C-means algorithm is most widely and successfully applied, and the membership degree of each sample point to all class centers is obtained by optimizing a target function, so that the class of the sample points is determined to achieve the purpose of automatically classifying sample data. The specific implementation of the algorithm can refer to the prior art, and is not described in detail here.

Therefore, after the sample characteristic data of each electricity stealing case sample is obtained, the electricity stealing case samples are divided by using a fuzzy C-means algorithm, and different category clusters are distinguished according to the membership degree to form a clustering result of one or more electricity stealing categories.

And S303, obtaining the standard additional payment electric charge of each electric larceny category according to the clustering result.

It should be noted that after the clustering result of one or more electricity stealing categories is formed, the standard recollecting electricity fee of each electricity stealing category is obtained according to the characteristics of the clustering center of each electricity stealing category, and the clustering center generally refers to the average recollecting electricity fee of all case samples in the electricity stealing category.

S304, screening the electricity fee tracing service abnormal cases by utilizing the electricity fee tracing and the standard electricity fee tracing of the electricity stealing case samples of the same electricity stealing category; the additional payment electric charge of the electricity stealing case sample is calculated by the estimation method of the additional payment electric charge.

It should be noted that after the standard recollecting electric charges of each electric larceny category are obtained, the actual recollecting electric charges of the electric larceny case samples belonging to the same electric larceny category are compared with the standard recollecting electric charges of the category, if the difference between the actual recollecting electric charges of a certain electric larceny case sample and the standard recollecting electric charges of the electric larceny category exceeds a standard value, the electric larceny case is an abnormal case, and therefore an abnormal case of the recollecting electric charges service is screened out. The actual recollection electric charge of the electricity stealing case sample is obtained by calculating by using an estimation method such as the recollection electric charge.

Optionally, in another embodiment of the present application, an implementation manner of step S304 specifically includes:

and (4) respectively subtracting the recollected electric charge of each electric larceny case sample of the same electric larceny category from the standard recollected electric charge of the same electric larceny category to obtain a result value.

And if the result value is larger than the preset threshold value, the electricity stealing case sample corresponding to the result value belongs to the electricity fee tracing service abnormal case.

It should be noted that after the standard recollecting electric charge of each electricity stealing category is obtained, the difference between the actual recollecting electric charge of each electricity stealing case sample belonging to the same electricity stealing category and the standard recollecting electric charge of the category is calculated. If the difference value between the actual recollecting electric charge of a certain electric larceny case sample and the standard recollecting electric charge of the electric larceny category is larger than a threshold value, the threshold value is generally set to be thirty percent of the standard recollecting electric charge of the corresponding electric larceny category, and the electric larceny case sample belongs to the abnormal case of the recollecting electric charge service.

Optionally, in another embodiment of the present application, as shown in fig. 4, an implementation manner of step S304 specifically includes:

s401, standard additional payment electric charge of each electric larceny category and sample characteristic data of each electric larceny case sample are input into a classifier.

It should be noted that, in the present embodiment, the standard recollecting electric charge of each electricity stealing category and the sample feature data of each electricity stealing case sample are input into a Support Vector Machine (SVM) classifier as a feature vector to perform data analysis and processing.

It should be noted that the support vector machine method is generally used for classification, and is a classification method with strong universality. The essence of classification is to take a vector as input and assign a type label to this vector. For sample space S { (x)₁,y₁),(x₂,y₂),…(x_n,y_n) X denotes sample characteristics, y isAnd (4) sample labeling. In most classification scenarios, types are mutually exclusive, so only one type is assigned to each sample. The input vector space is divided by decision regions, which are determined by decision boundaries or decision planes. As shown in fig. 5, the regular triangles and squares represent two different classes of samples, the blue squares and gray triangles on the straight line are referred to as support vectors, and D is referred to as decision plane.

The SVM classifier may be referred to as a linear classifier or a non-linear classifier. It is defined to find the model with the largest geometrical spacing on the two-dimensional space of fig. 5. The essence of the method is to solve the problem of convex quadratic programming. The ultimate goal of linear SVMs is to maximize the separation of distances to solve for the hyperplane (in two dimensions, decision D), and is the only hyperplane present. The linear separable SVM generally adopts an optimal convex quadratic problem to obtain an optimal solution, i.e., a maximum interval method. The target function of the linear separable SVM meets the Lagrangian function solving condition, and the linear separable SVM can be extended to the nonlinear classification SVM by introducing the Lagrangian function, namely, the kernel function is introduced.

The above is an ideal case that training samples can be divided, but in practice, there is always noise or outlier in the samples. In order to eliminate the influence of noise point interference, a relaxation variable is introduced into the objective formula of the SVM, the objective function is converted into soft interval maximization, and the obtained vector machine is called a linear SVM. When the linear model fails to solve the classification problem, a non-linear model, such as an elliptic curve, may be used for classification. However, the nonlinear model is very difficult to solve, so the nonlinear model is generally converted into a linear model by a conversion method.

And S402, dividing the power stealing case sample into a training set and a testing set.

It should be noted that, from all the power stealing case samples, part of the samples are randomly selected as a training set for training the support vector machine classifier. And classifying and processing all the electricity stealing case samples as a test set.

And S403, training the classifier by using the electricity stealing case samples in the training set, and if the difference value between the electric charge chased by the electricity stealing case samples of the same electricity stealing category in the training set and the standard electric charge chased by the electricity stealing category is larger than a threshold value, setting the electricity stealing case samples as abnormal cases of the electric charge chased business.

It should be noted that, the classifier is trained by using the electricity stealing case samples in the training set, the threshold value for screening the abnormal cases is thirty percent of the standard recollecting electricity fee of the electricity stealing category, and if the difference value between the actual recollecting electricity fee of the electricity stealing case samples in the same electricity stealing category in the training set and the standard recollecting electricity fee of the same electricity stealing category is greater than the threshold value, the electricity stealing case samples are set as the abnormal cases of the recollecting electricity fee service.

S404, inputting the electricity stealing case samples in the test set into a classifier for classification processing, and screening the abnormal cases of the electricity fee tracing service.

It should be noted that after the classifier is trained by using the electricity stealing case samples in the training set, the support vector machine classifier can realize the function of classification processing, and at this time, the case samples in the training set can be input into the support vector machine classifier for classification processing, so as to directly screen out the abnormal cases of the electricity fee tracing service.

In the method for screening the abnormal cases provided by this embodiment, the data of each electricity stealing case sample is analyzed according to the electricity stealing case sample for which the electricity fee tracing service is completed, so as to obtain the sample characteristic data of each electricity stealing case sample. And then, dividing the electricity stealing case samples by using a fuzzy clustering algorithm according to the sample characteristic data to form a clustering result of one or more electricity stealing categories. And obtaining the standard additional payment electric charge of each electric larceny category according to the clustering result. Screening the electricity fee tracing service abnormal cases by utilizing the electricity fee tracing and the standard electricity fee tracing of the electricity stealing case samples of the same electricity stealing category; the additional payment electric charge of the electricity stealing case sample is calculated by the estimation method of the additional payment electric charge. Therefore, the data calculated by the method for estimating the additional payment electric charge can be checked, and the accuracy is improved.

Optionally, in another embodiment of the present application, the method for screening an abnormal case may further include:

It should be noted that, by using the screened abnormal case data of the electricity fee recollection service, the deviation between the reasonable recollection electric quantity of different typical categories is calculated according to the field work order of each field processing personnel, as shown in table 1,

TABLE 1

The generated form data is used for evaluating the unit or individual recollection electricity charge business work, for example, the deviation between the recollection electricity charge of the electricity stealing user case and the standard recollection electricity charge of the corresponding electricity stealing category is high in common occurrence of part of business personnel, which shows that the recollection electricity charge business work has problems, the business personnel or the unit needs to be investigated to find the reason, and the business personnel or the unit can be trained correspondingly if necessary.

Another embodiment of the present application further provides an estimation device for paying electric charge, as shown in fig. 6, specifically including:

the acquiring unit 601 is used for acquiring power utilization characteristic data of a user aiming at the user who steals power; the electricity utilization characteristic data comprises electricity consumption of a user, line loss of a platform area and time for opening an electricity meter cover by the user.

The first processing unit 602 is configured to obtain a power stealing time interval of the user according to the power utilization characteristic data.

The second processing unit 603 is configured to identify a power stealing method of the user, and obtain an average power stealing amount of the user according to the power stealing method of the user.

The first calculating unit 604 is configured to calculate the electricity stealing time interval and the average electricity stealing amount to obtain the electricity stealing amount of the user in the electricity stealing time interval.

The second calculating unit 605 is configured to calculate an electricity fee paid in the electricity stealing time interval according to a preset electricity fee calculating method.

In the estimation apparatus for paying electric charge for an additional fee according to this embodiment, the obtaining unit 601 obtains the electricity characteristic data of the user for the user who has an electricity stealing behavior. The electricity utilization characteristic data comprises electricity consumption of a user, line loss of a platform area and time for opening an electricity meter cover by the user. Then the first processing unit 602 obtains the electricity stealing time interval of the user according to the electricity utilization characteristic data. The second processing unit 603 identifies the electricity stealing method of the user, and obtains the average electricity stealing capacity of the user according to the electricity stealing method of the user. The first calculating unit 604 calculates the electricity stealing time interval and the average electricity stealing capacity to obtain the electricity stealing capacity of the user in the electricity stealing time interval. Finally, the second calculating unit 605 calculates the additional payment electric charge corresponding to the electric larceny quantity of the user in the electric larceny time interval according to the preset electric charge calculating method. Therefore, the method can be used for solving the problems that when the payment following of the confirmed electricity stealing users is calculated, if the electric charge to be paid is directly calculated by the conventional calculation method of the payment following electric charge, the calculated payment following charge is not accurate enough, and the phenomenon of excessive or insufficient payment following electric charge often exists.

In this embodiment, for specific execution processes of the obtaining unit 601, the first processing unit 602, the second processing unit 603, the first calculating unit 604, and the second calculating unit 605, reference may be made to the contents of the method embodiment corresponding to fig. 1, and details are not described here.

Optionally, in another embodiment of the present invention, an implementation manner of the first processing unit 602 includes:

the first inquiry subunit is used for inquiring the electricity utilization characteristic data to obtain an electricity utilization data sequence from the latest meter cover opening time of a user to the electricity stealing check time; the electricity consumption data sequence comprises a line loss electricity quantity sequence of a transformer area of each day from the last meter opening time of a user to the electricity stealing check time and an electricity consumption quantity sequence of the user.

And the first searching subunit is used for searching a time interval meeting the conditions that the line loss quantity of the transformer area suddenly increases and the power consumption quantity of the user suddenly decreases simultaneously within a preset time period from the power consumption data sequence, and the time interval is higher than a preset threshold value and is used as a first suspected power stealing time interval.

And the second searching subunit is used for screening and obtaining a time interval from the electricity stealing check time to the meter cover opening time which is the latest time from the electricity stealing check time of the user from the time when the user opens the meter cover.

And the scanning subunit is used for performing sliding window type scanning in a time interval from the electricity stealing check time to the meter opening cover time which is the latest time away from the electricity stealing check time of the user to obtain a time interval in which the Pearson correlation between the line loss data of all the distribution areas and the electricity consumption of the user is higher than a preset threshold value, and the time interval is used as a second suspected electricity stealing time interval.

In this embodiment, the specific execution processes of the first querying subunit, the first searching subunit, the second searching subunit, the scanning subunit and the merging subunit may refer to the contents of the method embodiment corresponding to fig. 2, and are not described herein again.

Optionally, in another embodiment of the present invention, an implementation manner of the second processing unit 603 includes:

and the judging subunit is used for judging the proportion of electricity stealing according to the electricity stealing instrument of the user if the electricity stealing method of the user is equal proportion electricity stealing.

And the calculating subunit is used for calculating the power consumption data of the user according to the proportion to obtain the average electricity stealing quantity data of the user.

And the obtaining subunit is used for obtaining the electricity stealing application mode of the user if the electricity stealing method of the user is bypassing electricity stealing.

In this embodiment, for the specific execution processes of the determining subunit, the calculating subunit, the obtaining subunit, and the second querying subunit, reference may be made to the contents of the above method embodiments, and details are not described here.

Another embodiment of the present application further provides a device for screening abnormal cases, as shown in fig. 7, specifically including:

the analysis unit 701 is used for analyzing the data of each electricity stealing case sample to obtain the sample characteristic data of each electricity stealing case sample aiming at the electricity stealing case sample which completes the electricity fee tracing service; the sample characteristic data comprises electricity stealing methods, electricity using properties, electricity consumption, line loss electricity, average electricity stealing electricity data, a ratio of live line current to zero line current, interval time from power failure events to power-on events and interval time from meter opening events to meter closing events of each sample case.

The dividing unit 702 is configured to divide the electricity stealing case samples by using a fuzzy clustering algorithm according to the sample feature data to form a clustering result of one or more electricity stealing categories.

The obtaining unit 703 is configured to obtain the standard additional payment electric charge for each electric larceny category according to the clustering result.

The screening unit 704 is used for screening the electricity fee tracing service abnormal cases by utilizing the electricity fee tracing and standard electricity fee tracing of the electricity stealing case samples of the same electricity stealing category; the additional payment electric charge of the electricity stealing case sample is calculated by any one of the above estimation methods of the additional payment electric charge.

In the screening apparatus for abnormal cases provided in this embodiment, the analyzing unit 701 analyzes data of each electricity stealing case sample for the electricity stealing case sample that has completed the electricity fee tracing service, so as to obtain sample characteristic data of each electricity stealing case sample. Then, the dividing unit 702 divides the electricity stealing case samples by using a fuzzy clustering algorithm according to the sample characteristic data to form a clustering result of one or more electricity stealing categories. The obtaining unit 703 obtains the standard recollection electricity fee of each electricity stealing category according to the clustering result. The screening unit 704 screens out the electricity fee tracing service abnormal cases by utilizing the electricity fee tracing and standard electricity fee tracing of the electricity stealing case samples of the same electricity stealing category; the additional payment electric charge of the electricity stealing case sample is calculated by the estimation method of the additional payment electric charge. Therefore, the data calculated by the method for estimating the additional payment electric charge can be checked, and the accuracy is improved.

In this embodiment, for the specific implementation processes of the analysis unit 701, the dividing unit 702, the obtaining unit 703 and the screening unit 704, reference may be made to the contents of the method embodiment corresponding to fig. 3, and details are not described here.

Optionally, in another embodiment of the present invention, an implementation manner of the screening unit 704 specifically includes:

and the calculating subunit is used for respectively differentiating the recollected electric charge of each electricity stealing case sample of the same electricity stealing category with the standard recollected electric charge of the same electricity stealing category to obtain a first result value.

And the judging subunit is used for judging that the electricity stealing case sample corresponding to the first result value belongs to the electricity fee service exception case if the first result value is greater than the preset threshold value.

In this embodiment, the specific execution processes of the calculating subunit and the determining subunit can refer to the contents of the above method embodiments, which are not described herein again.

and the input subunit is used for inputting the standard surcharge electric charge of each electricity stealing category and the sample characteristic data of each stolen electric case sample into the classifier.

And the dividing subunit is used for dividing the electricity stealing case sample into a training set and a testing set.

And the training subunit is used for training the classifier by using the electricity stealing case samples in the training set, and if the difference value between the electric charge chased by the electricity stealing case samples of the same electricity stealing category in the training set and the standard electric charge chased by the same electricity stealing category is larger than a threshold value, setting the electricity stealing case samples as the abnormal cases of the electric charge chased service.

In this embodiment, the specific execution processes of the input subunit, the dividing subunit, the training subunit, and the screening subunit may refer to the content of the embodiment of the method corresponding to fig. 4, and are not described herein again.

Optionally, in another embodiment of the present invention, the screening apparatus for abnormal cases may further include:

In this embodiment, the specific execution process of the evaluation unit may refer to the content of the above method embodiment, which is not described herein again.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, the system or system embodiments are substantially similar to the method embodiments and therefore are described in a relatively simple manner, and reference may be made to some of the descriptions of the method embodiments for related points. The above-described system and system embodiments are only illustrative, wherein the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.

Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An estimation method of an electric charge recollecting fee is characterized by comprising the following steps:

2. The method of claim 1, wherein obtaining the electricity stealing time interval of the user according to the electricity utilization characteristic data comprises:

3. The method of claim 1, wherein the obtaining of the average electricity stealing capacity data of the user according to the electricity stealing method of the user comprises:

4. A method for screening abnormal cases is characterized by comprising the following steps:

screening the electricity fee tracing service abnormal cases by utilizing the electricity fee tracing of the electricity stealing case samples of the same electricity stealing category and the standard electricity fee tracing; wherein the recollection electric charge of the electricity stealing case sample is calculated by the method of any one of claims 1 to 3.

5. The method according to claim 4, wherein the screening of the abnormal cases of the electricity fee service by using the electricity fee recollection of the electricity-stealing case samples of the same electricity-stealing category and the standard electricity fee recollection comprises:

6. The method according to claim 4, wherein the electricity charge overtaking service abnormal case is screened out by utilizing the electricity charge overtaking of the electricity-stealing case sample of the same electricity-stealing category and the standard electricity charge overtaking

7. The method of claim 4, further comprising:

8. An estimation device of an electric charge fee of pursuit, characterized by comprising:

9. The apparatus of claim 8, wherein the first processing unit comprises:

10. An abnormal case screening device, comprising:

the screening unit is used for screening the electricity fee tracing service abnormal cases by utilizing the electricity fee tracing of the electricity stealing case samples of the same electricity stealing category and the standard electricity fee tracing; wherein the recollection electric charge of the electricity stealing case sample is calculated by the method of any one of claims 1 to 3.