CN115758076A

CN115758076A - Electricity stealing suspected user label generation method and device, electronic equipment and storage medium

Info

Publication number: CN115758076A
Application number: CN202211643982.7A
Authority: CN
Inventors: 孙胜博; 王晓甜; 杨迪; 马红明; 冀明; 吕云彤; 李梦宇; 高学哲; 李骥
Original assignee: State Grid Corp of China SGCC; Marketing Service Center of State Grid Hebei Electric Power Co Ltd
Current assignee: State Grid Corp of China SGCC; Marketing Service Center of State Grid Hebei Electric Power Co Ltd
Priority date: 2022-12-20
Filing date: 2022-12-20
Publication date: 2023-03-07

Abstract

The invention provides a method and a device for generating a label of a suspected electricity stealing user, electronic equipment and a storage medium. The method comprises the following steps: acquiring a line loss rate time sequence of the line loss rate abnormal region; performing inflection point detection based on the line loss rate time sequence to obtain an inflection point detection result; if the inflection point detection result comprises at least one inflection point, respectively determining the power consumption increment of each user corresponding to the at least one inflection point in the line loss rate abnormal area based on the at least one inflection point and the reference point corresponding to the at least one inflection point; respectively determining the electricity stealing suspicion coefficient of each user based on the increase of the electricity consumption; and identifying the electricity stealing suspected user based on the electricity stealing suspected coefficient of each user, and generating an electricity stealing suspected user label for the electricity stealing suspected user. The method and the device can accurately identify the electricity stealing suspected user and generate the electricity stealing suspected label for the electricity stealing suspected user so as to reduce the power loss in the power transmission process and reduce the probability of safety accidents.

Description

Electricity stealing suspected user label generation method and device, electronic equipment and storage medium

Technical Field

The invention relates to the technical field of electric power, in particular to a method and a device for generating a label of a suspected electricity stealing user, electronic equipment and a storage medium.

Background

Along with the higher application proportion of electric power in the energy field, the phenomenon of electricity stealing is also more frequent, thereby leading to the great electric power loss and the higher probability of safety accident occurrence in the electric power transmission process. The line loss rate refers to a proportion of power loss generated during power transmission. The higher the line loss rate during power transmission, the greater the power loss that occurs. The line loss rate may be increased due to aging or failure of the transmission circuit, or due to the existence of a power stealing phenomenon.

For electricity stealing phenomena, the suspected users of electricity stealing are difficult to accurately identify in the prior art.

Disclosure of Invention

The embodiment of the invention provides a method and a device for generating a label of a suspected electricity-stealing user, electronic equipment and a storage medium, which are used for solving the problem that the suspected electricity-stealing user is difficult to accurately identify in the prior art.

In a first aspect, an embodiment of the present invention provides a method for generating a suspected electricity-stealing user tag, including:

acquiring a line loss rate time sequence of the line loss rate abnormal region; the line loss rate time sequence represents a data sequence formed by line loss rates of all unit time periods in a target time period in sequence;

performing inflection point detection based on the line loss rate time series to obtain an inflection point detection result;

if the inflection point detection result comprises at least one inflection point, respectively determining the power consumption increment corresponding to the at least one inflection point of each user in the area with the abnormal line loss rate based on the at least one inflection point and the reference point corresponding to the at least one inflection point;

respectively determining the suspicion coefficient of electricity stealing of each user based on the electricity consumption increase amount;

and identifying the electricity stealing suspected user based on the electricity stealing suspicion coefficient of each user, and generating an electricity stealing suspicion user label for the electricity stealing suspicion user.

In a possible implementation manner, the performing inflection point detection based on the line loss rate time series to obtain an inflection point detection result includes:

determining the line loss rate increase amount and the line loss rate increase rate of every two adjacent unit time periods based on the line loss rate time series;

determining two adjacent unit time periods meeting the growth condition as an inflection point in the line loss rate time sequence and a corresponding reference point; the growth conditions include: the line loss rate increase amounts of the two current adjacent unit time periods are positioned in M bits with the maximum line loss rate increase amounts of the two adjacent unit time periods, the line loss rate increase rates of the two current adjacent unit time periods are larger than a first threshold, and M is a positive integer; the reference point corresponding to the inflection point is a previous unit period adjacent to the inflection point.

In a possible implementation manner, the determining, based on the at least one inflection point and a reference point corresponding to the at least one inflection point, a power consumption increase amount corresponding to the at least one inflection point for each user in the area with the abnormal line loss rate includes:

aiming at each user in the area with the abnormal line loss rate, respectively acquiring the power consumption of the user at each inflection point and the power consumption of the user at a reference point corresponding to each inflection point;

and subtracting the power consumption of the reference point corresponding to each inflection point from the power consumption of each inflection point to obtain the power consumption increment corresponding to each inflection point of the user.

In a possible implementation manner, the determining a suspicion coefficient of electricity stealing of each user based on the amount of increase in the electricity consumption includes:

for each user, respectively taking the ratio of the power consumption increment corresponding to each inflection point of the user to the line loss rate increment as the electricity stealing suspicion coefficient corresponding to each inflection point of the user;

and determining the electricity stealing suspicion coefficient of each user based on the electricity stealing suspicion coefficients corresponding to all inflection points of each user.

In a possible implementation manner, the determining the suspicion of electricity stealing coefficient of each user based on the suspicion of electricity stealing coefficients corresponding to all inflection points of each user includes:

and taking the absolute value of the mean value of the electricity stealing suspicion coefficients corresponding to all inflection points of each user as the electricity stealing suspicion coefficient of each user.

In one possible implementation manner, the determining, based on the line loss rate time series, a line loss rate increase amount and a line loss rate increase rate for each two adjacent unit time periods includes:

starting from the second unit time period in the line loss rate time sequence, taking each unit time period as the current unit time period, and calculating the line loss rate increase amount and the line loss rate increase rate of the current unit time period relative to the previous unit time period to obtain the line loss rate increase amount and the line loss rate increase rate of each two adjacent unit time periods;

if a target unit time segment with a missing line loss rate exists in the line loss rate time series, filling the line loss rate of the target unit time segment into a target line loss rate, where the target line loss rate is determined based on the line loss rate of a first unit time segment and the line loss rate of a second unit time segment, the first unit time segment is the unit time segment which is located before the target unit time segment and has the shortest time interval with the target unit time segment and has no missing line loss rate, and the second unit time segment is the unit time segment which is located after the target unit time segment and has the shortest time interval with the target unit time segment and has no missing line loss rate.

In a possible implementation manner, after the identifying a suspected electricity stealing user based on the suspected electricity stealing coefficient of each user and generating a suspected electricity stealing user tag for the suspected electricity stealing user, the method further includes:

calculating a correlation coefficient between the electricity consumption of the electricity stealing suspected user in each unit time period and the line loss rate of each unit time period;

if the correlation coefficient is larger than a second threshold value, determining that the electricity stealing suspected user is continuous electricity stealing;

and if the correlation coefficient is smaller than a third threshold value, determining that the electricity stealing suspected user is in discontinuous electricity stealing.

In a second aspect, an embodiment of the present invention provides an apparatus for generating a suspected electricity-stealing user tag, including:

the sequence acquisition module is used for acquiring a line loss rate time sequence of the line loss rate abnormal area; the line loss rate time sequence represents a data sequence formed by line loss rates of all unit time periods in a target time period in sequence;

the inflection point detection module is used for carrying out inflection point detection on the basis of the line loss rate time sequence to obtain an inflection point detection result;

a first determining module, configured to, if the inflection point detection result includes at least one inflection point, respectively determine, based on the at least one inflection point and a reference point corresponding to the at least one inflection point, a power consumption increase amount corresponding to the at least one inflection point for each user in the line loss rate abnormal area;

the second determination module is used for respectively determining the suspicion coefficient of electricity stealing of each user based on the electricity consumption increase amount;

and the label generation module is used for identifying the electricity stealing suspected user based on the electricity stealing suspicion coefficient of each user and generating an electricity stealing suspicion user label for the electricity stealing suspected user.

In a third aspect, an embodiment of the present invention provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the method according to the first aspect or any possible implementation manner of the first aspect when executing the computer program.

In a fourth aspect, the present invention provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the computer program implements the steps of the method according to the first aspect or any one of the possible implementation manners of the first aspect.

The embodiment of the invention provides a method, a device, electronic equipment and a storage medium for generating a label of a suspected electricity stealing user, which are implemented by acquiring a line loss rate time sequence of an abnormal line loss rate distribution area; performing inflection point detection based on the line loss rate time sequence to obtain an inflection point detection result; if the inflection point detection result comprises at least one inflection point, respectively determining the power consumption increment of each user corresponding to the at least one inflection point in the line loss rate abnormal area based on the at least one inflection point and the reference point corresponding to the at least one inflection point; respectively determining the electricity stealing suspicion coefficient of each user based on the increase of the electricity consumption; and identifying the electricity stealing suspected user based on the electricity stealing suspicion coefficient of each user, and generating an electricity stealing suspicion user label for the electricity stealing suspicion user. The electricity stealing suspicion coefficient can be calculated by determining the electricity consumption increment at each turning point in the online loss rate time sequence of the user, the electricity stealing suspicion coefficient is used for accurately identifying the electricity stealing suspicion user, and an electricity stealing suspicion label is generated for the electricity stealing suspicion user, so that the power loss in the power transmission process is reduced, and the probability of safety accidents is reduced.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required to be used in the embodiments or the prior art description will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings may be obtained according to these drawings without inventive labor.

Fig. 1 is a flowchart illustrating an implementation of a tag generation method for a suspected electricity stealing user according to an embodiment of the present invention;

FIG. 2 is a flowchart illustrating an implementation of a method for generating a label of a suspected fraudulent user according to another embodiment of the present invention;

FIG. 3 is a schematic structural diagram of a suspected electricity stealing user tag generation apparatus according to an embodiment of the present invention;

fig. 4 is a schematic diagram of an electronic device provided in an embodiment of the present invention.

Detailed Description

In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.

In an electrical power system, a platform refers to the supply range of a transformer. During power transmission, line loss inevitably occurs due to circuit resistance and the like. Normally, the line loss rate of power transmission in one station area can be maintained within a set range, if the line loss rate exceeds the set range, the line loss rate in the station area is abnormal, and if the line loss rate in the station area is abnormal, the electricity stealing phenomenon may exist.

For electricity stealing phenomena, the online loss rate abnormality of the area-wide memory can be known in the prior art, namely the electricity stealing phenomena can exist, but electricity stealing suspicion users in the area cannot be accurately identified, so that electricity stealing behaviors are frequent and forbidden frequently, and further, the power loss is large in the power transmission process and the probability of safety accidents is high. Based on the above, the invention provides a generation method of a label of a suspected electricity-stealing user, which is used for solving the problem that the suspected electricity-stealing user cannot be accurately identified in the prior art, so that the power loss in the power transmission process is reduced, and the probability of safety accidents is reduced.

To make the objects, technical solutions and advantages of the present invention more apparent, the following description will be made by way of specific embodiments with reference to the accompanying drawings.

Fig. 1 is a flowchart of an implementation of a method for generating a label of a suspected electricity-stealing user according to an embodiment of the present invention, which is detailed as follows:

step 101, a line loss rate time sequence of the abnormal line loss rate distribution room is obtained. The line loss rate time series represents a data series in which the line loss rates of the respective unit time periods within the target time period are sequentially configured.

The line loss rate abnormality means that the line loss rate is out of a set range. Under normal conditions, the line loss rate in the station area can be maintained within a set range, and if the line loss rate exceeds the set range, the station area is an abnormal station area of the line loss rate. The power stealing phenomenon may exist in the power distribution area with the abnormal line loss rate.

Illustratively, the target time period may be one month. The unit time period may be one day, and the line loss rate per unit time period is also called a daily line loss rate. Based on this, the line loss rate time series may be a time series formed by the daily line loss rate within one month.

In practical application, after the line loss rate time sequence of the line loss rate abnormal distribution room is obtained, the data of the line loss rate time sequence can be cleaned, and data smaller than or equal to zero are removed. Normally, the line loss rate in the line loss rate time series is greater than zero, and the data less than or equal to zero is abnormal data, which may be caused by system failure and other reasons in the process of obtaining the line loss rate time series. In the embodiment, the data of the line loss rate time sequence is cleaned, abnormal data are removed, and the abnormal data can be prevented from interfering the recognition result.

And 102, performing inflection point detection based on the line loss rate time sequence to obtain an inflection point detection result.

The inflection point refers to a unit time period in which the quantized value of the increase degree of the line loss rate satisfies a preset increase condition. The quantized value of the line loss rate is used for representing the increasing degree of the line loss rate.

Optionally, referring to fig. 2, step 102 may include:

and step 1021, determining the line loss rate increase amount and the line loss rate increase rate of every two adjacent unit time periods based on the line loss rate time sequence.

And starting from the second unit time period in the line loss rate time sequence, taking each unit time period as the current unit time period, and calculating the line loss rate increase quantity and the line loss rate increase rate of the current unit time period relative to the previous unit time period to obtain the line loss rate increase quantity and the line loss rate increase rate of each two adjacent unit time periods.

The line loss rate increase amount is the difference between the line loss rate of the current unit time period and the line loss rate of the previous unit time period. The line loss rate increase rate is a ratio of the line loss rate increase amount to the line loss rate of the unit time period before the two adjacent unit time periods. Illustratively, if the line loss rate of the previous unit time period is a, and the line loss rate of the current unit time period is b, the line loss rate increase amount is b-a, and the line loss rate increase rate is (b-a)/a. The line loss rate increase amount and the line loss rate increase rate belong to the increase degree quantized value of the line loss rate, and are used for representing the increase degree of the line loss rate.

Taking a unit time period as one day for example, the line loss rate time series is a line loss rate time series formed by line loss rates of

days

1, 2, 3, 4, 5 and 6, when the line loss rate increase amount and the line loss rate increase rate of every two adjacent unit time periods are calculated, starting from day 2, taking day 2 as the current unit time period, calculating the line loss rate increase amount and the line loss rate increase rate of day 2 relative to day 1, then taking day 3 as the current unit time period, calculating the line loss rate increase amount and the line loss rate increase rate of day 3 relative to day 2, and so on until day 6 is taken as the current unit time period, calculating the line loss rate increase amount and the line loss rate increase rate of day 6 relative to day 5.

Since the data of the line loss rate time sequence is cleaned after the line loss rate time sequence of the line loss rate abnormal region is obtained, and abnormal data smaller than or equal to zero are removed, in this embodiment, when the line loss rate increase amount and the line loss rate increase rate of the current unit time period relative to the previous unit time period are calculated, the line loss rate may be missing, and certainly, the loss of the line loss rate due to other reasons may also be missing, which is not listed one by one here.

And if the target unit time section with the missing line loss rate exists in the line loss rate time sequence, filling the line loss rate of the target unit time section into the target line loss rate.

The target line loss rate is determined based on the line loss rate of the first unit period and the line loss rate of the second unit period. The first unit time period is a unit time period which is located before the target unit time period, has the shortest time interval with the target unit time period and has no missing line loss rate, and the second unit time period is a unit time period which is located after the target unit time period, has the shortest time interval with the target unit time period and has no missing line loss rate.

For example, the target line loss rate may be an average of the line loss rate of the first unit time period and the line loss rate of the second unit time period. Of course, other values are also possible, such as a weighted sum of the line loss rate of the first unit period of time and the line loss rate of the second unit period of time, and so on.

In this embodiment, before calculating the line loss rate increase amount and the line loss rate increase rate, the unit time periods in which the line loss rates are missing in the line loss rate time sequence are reasonably filled, so that the line loss rate time sequence becomes a complete sequence, and the influence of the missing of the line loss rates on the calculation of the line loss rate increase amount and the line loss rate increase rate is avoided.

Step 1022, two adjacent unit time periods meeting the growth condition are determined as the inflection point in the line loss rate time series and the corresponding reference point.

The reference point corresponding to the inflection point is a unit time period for providing reference for the increase degree of the line loss rate of the inflection point, each inflection point has a corresponding reference point, and the reference point corresponding to the inflection point is a previous unit time period adjacent to the inflection point.

The growth conditions include: the line loss rate increase amounts of the two current adjacent unit time periods are located in the M bits with the maximum line loss rate increase amounts of the two current adjacent unit time periods, the line loss rate increase rates of the two current adjacent unit time periods are larger than a first threshold, and M is a positive integer.

Because the line loss rate increase amount and the line loss rate increase rate of two adjacent unit time periods can both represent the increase degree of the line loss rate, in the embodiment, when the inflection point detection is performed, the line loss rate increase amount and the line loss rate increase rate of two adjacent unit time periods are integrated, the inflection point is obtained by combining the increase condition detection, the contingency can be reduced, and the inflection point detection result is more accurate.

In practical application, all the line loss rate increase amounts of two adjacent unit time periods may be sorted first, which may be sorted in a descending order as an example, and accordingly, the condition that the line loss rate increase amount needs to be satisfied may include: the line loss rate increase amounts of two adjacent unit time periods are located in the first M bits in descending order. Of course, ascending sorting is also possible.

The value of M may be a preset default value, which may be 5 as an example, and then the condition that the line loss rate increase amount needs to be satisfied may include that the line loss rate increase amounts of two adjacent unit time periods are located in the first 5 bits in descending order. The value of M may also be calculated by a preset policy, for example, the preset policy may be a set percentage of the total number of the line loss rate increase amounts of all adjacent two unit time periods, and for example, the set percentage is 10%, for example, the total number of the line loss rate increase amounts of all adjacent two unit time periods that are sorted in a descending order is 100, and the first 10% includes the first 10 bits, that is, the condition that the line loss rate increase amount needs to satisfy may include: the line loss rate increase amounts of the adjacent two unit time periods are located in the first 10 bits in descending order.

The specific value of the first threshold may be set according to actual needs, and exemplarily, the first threshold may be 40%, that is, the condition that the line loss rate increase rate needs to be satisfied may include that the line loss rate increase rates of two adjacent unit time periods are greater than 40%.

The line loss rate of increase is bigger, and it is bigger to explain that there is the possibility of stealing electricity, and line loss rate of increase volume is bigger, also explains that there is the possibility of stealing electricity more, in this embodiment, has comprehensively considered line loss rate of increase and line loss rate of increase volume when setting up the growth condition, is favorable to detecting the great inflection point of possibility of stealing electricity to promote the accuracy of the suspicion user's of stealing electricity discernment.

And 103, if the inflection point detection result comprises at least one inflection point, respectively determining the power consumption increment corresponding to the at least one inflection point of each user in the area with the abnormal line loss rate based on the at least one inflection point and the reference point corresponding to the at least one inflection point.

Optionally, the determining, based on the at least one inflection point and the reference point corresponding to the at least one inflection point, the amount of increase in power consumption, corresponding to the at least one inflection point, of each user in the area with the abnormal line loss rate may include:

and step 1031, for each user in the abnormal area with the line loss rate, respectively obtaining the power consumption of the user at each inflection point and the power consumption of the user at a reference point corresponding to each inflection point.

In practical applications, the power consumption of the user may be lost due to errors of the statistical system, and for this reason, the lost power consumption may be filled.

And if the power consumption of the user at the inflection point is lacked, filling the power consumption of the user at the inflection point into the first target power consumption. The first target power consumption is determined based on power consumption of a third unit time period and a fourth unit time period, wherein the third unit time period is a unit time period which is located before the inflection point, has the shortest time interval with the inflection point and is not deficient in power consumption, and the fourth unit time period is a unit time period which is located after the inflection point, has the shortest time interval with the inflection point and is not deficient in power consumption.

And if the power consumption of the user at the reference point corresponding to the inflection point is lost, filling the power consumption of the user at the reference point corresponding to the inflection point into a second target power consumption, wherein the second target power consumption is determined based on the power consumption of a fifth unit time period and a sixth unit time period, the fifth unit time period is a unit time period which is located before the reference point corresponding to the inflection point, the time interval of the reference point corresponding to the inflection point is shortest, and the power consumption is not lost, and the sixth unit time period is a unit time period which is located after the reference point corresponding to the inflection point, the time interval of the reference point corresponding to the inflection point is shortest, and the power consumption is not lost.

For example, the first target power consumption amount may be an average value of the power consumption amounts of the third unit time period and the fourth unit time period, but may also be other values, such as a weighted sum value of the power consumption amount of the third unit time period and the power consumption amount of the fourth unit time period, and the like.

Similarly, the second target power consumption amount may be an average value of the power consumption amounts of the fifth unit time period and the sixth unit time period, or may be other values, such as a weighted sum value of the power consumption amount of the fifth unit time period and the power consumption amount of the sixth unit time period, and the like.

In this embodiment, if the power consumption of the user at the inflection point is lost, the filled first target power consumption is determined according to the power consumption of the unit time period, which is located before and after the inflection point where the power consumption is lost, has the shortest time interval with the inflection point and has no power consumption loss, so that the accurate power consumption increase amount of the user at the inflection point can be obtained. Similarly, if the power consumption of the user at the reference point corresponding to the inflection point is lost, the accurate power consumption increase of the user at the reference point corresponding to the inflection point can be obtained.

Optionally, if the power consumption of the user at the inflection point is lost and the inflection point is a holiday or a holiday, the power consumption of the inflection point is filled as the power consumption of a seventh unit time period, where the seventh unit time period is a unit time period located before the inflection point, the time interval between the seventh unit time period and the inflection point is shortest, the type of the seventh unit time period is the same as that of the holiday or the holiday at the inflection point, and the power consumption is not lost.

Accordingly, if the power consumption of the reference point corresponding to the inflection point is lost and the reference point corresponding to the inflection point is a holiday or a holiday, the power consumption of the reference point corresponding to the inflection point is filled as the power consumption of an eighth unit time period, the eighth unit time period is the unit time period before the reference point corresponding to the inflection point, the time interval of the reference point corresponding to the inflection point is shortest, the types of the holidays or the holidays of the reference point corresponding to the inflection point are the same, and the power consumption is not lost.

In this embodiment, holidays can include statutory holidays such as spring festival or morning festival, and holidays can include saturday or sunday. For the user, the power consumption on the holiday or the holiday may be inconsistent with other times, and the power consumption on the holiday or the holiday may be more than that on the non-holiday or the non-holiday, so that when the power consumption of the user on the holiday or the holiday is deficient, the same type of power consumption on the holiday or the holiday with the shortest time interval can be used for filling, and the power consumption of the unit time period with the deficient power consumption can be reflected more accurately.

And 1032, subtracting the power consumption of the reference point corresponding to each inflection point from the power consumption of each inflection point to obtain the power consumption increment corresponding to each inflection point of the user.

And step 104, respectively determining the suspicion coefficient of electricity stealing of each user based on the increment of the electricity consumption.

The suspected electricity stealing coefficient of the user is used for representing the possibility of electricity stealing of the user, namely the greater the suspected electricity stealing coefficient of the user is, the greater the possibility of electricity stealing of the user is, and the smaller the suspected electricity stealing coefficient of the user is, the smaller the possibility of electricity stealing of the user is.

Optionally, step 104 may include:

step 1041, regarding each user, taking the ratio of the power consumption increase amount and the line loss rate increase amount corresponding to each inflection point of the user as the suspected electricity stealing coefficient corresponding to each inflection point of the user.

If the line loss rate increase amount corresponding to the inflection point is large, and the power consumption increase amount of the user is small, the possibility of electricity stealing is high, and based on the fact that the absolute value of the ratio of the power consumption increase amount of the user at the inflection point to the line loss rate increase amount is large, the possibility that the user steals electricity is high is shown.

And 1042, determining the electricity stealing suspicion coefficient of each user based on the electricity stealing suspicion coefficients corresponding to all inflection points of each user.

Optionally, step 1042 may include: and taking the absolute value of the mean value of the electricity stealing suspicion coefficients corresponding to all inflection points of each user as the electricity stealing suspicion coefficient of each user.

In this embodiment, the suspicion coefficient of electricity stealing that the user corresponds at each inflection point is considered comprehensively, the absolute value of the mean value of the suspicion coefficient of electricity stealing that the user corresponds at each inflection point is used as the suspicion coefficient of electricity stealing of the user, and the suspicion coefficient of electricity stealing of the user is finally determined, so that the contingency can be avoided, and the suspicion coefficient of electricity stealing of the user can more accurately reflect the possibility that the user steals electricity.

And 105, identifying the electricity stealing suspected user based on the electricity stealing suspicion coefficient of each user, and generating an electricity stealing suspicion user label for the electricity stealing suspected user.

For example, it may be determined that N users with the largest suspicion coefficient of electricity stealing among all users are suspected users of electricity stealing, and a value of N is a positive integer. And generating electricity stealing suspected user labels for the N electricity stealing suspected users.

Optionally, after the suspected electricity stealing coefficient of each user is determined, standardized conversion can be performed on the suspected electricity stealing coefficient of each user, the suspected electricity stealing user is identified based on the suspected electricity stealing coefficient of each user after standardized conversion, and an suspected electricity stealing user tag is generated for the suspected electricity stealing user.

When standardized conversion is carried out, the maximum value and the minimum value of the electricity stealing suspicion coefficient can be obtained based on the electricity stealing suspicion coefficients of all users, the electricity stealing suspicion coefficients are subjected to standardized conversion by using a specific algorithm in combination with the distribution rule of the electricity stealing suspicion coefficients, and in practical application, the electricity stealing suspicion coefficients can be subjected to standardized conversion by using a log conversion algorithm. In this embodiment, through carrying out standardized conversion, the suspected coefficient of electricity stealing after the conversion can all be in the interval of settlement, for example [0,100], be convenient for the comparison between the suspected coefficient of electricity stealing to more accurate quick discernment suspected user of electricity stealing, and for suspected user of electricity stealing generate suspected user of electricity stealing label.

The bigger the suspected coefficient of stealing electricity of user, the more the possibility that the user steals electricity is, in this embodiment, the great user identification of suspected coefficient of stealing electricity is the suspected user of stealing electricity, has reduced the possibility of misidentification, has further promoted the accuracy of suspected user identification of stealing electricity.

Optionally, after the suspected electricity stealing user is identified based on the suspected electricity stealing coefficient of each user, the method further includes:

and calculating a correlation coefficient of the electricity consumption of each unit time period of the electricity stealing suspected user and the line loss rate of each unit time period.

If the correlation coefficient is larger than a second threshold value, determining that the electricity stealing suspected user is continuous electricity stealing; and if the correlation coefficient is smaller than a third threshold value, determining that the suspected electricity stealing user is in discontinuous electricity stealing.

In practical application, the correlation coefficient between the power consumption and the line loss rate can be calculated by a Dynamic Time Warping (DTW) algorithm. In the embodiment, after the correlation coefficient of the power consumption and the line loss rate of each unit time period of the user is obtained through calculation of the DTW algorithm, the correlation coefficient may be compared with a second threshold and a third threshold which are preset, where the second threshold and the third threshold are determined based on distribution of the correlation coefficient, the second threshold is greater than zero, and the third threshold is smaller than zero.

In the embodiment, the correlation coefficient of the power consumption of each unit time period of the electricity stealing suspected user and the line loss rate of each unit time period is calculated, and whether the electricity stealing type of the electricity stealing suspected user is continuous electricity stealing or discontinuous electricity stealing is determined according to the magnitude relation between the correlation coefficient and the second threshold value and the third threshold value, so that the label of the electricity stealing suspected user can be more complete, and the classification of the users is convenient to refine.

The embodiment of the invention obtains the line loss rate time sequence of the abnormal area of the line loss rate; performing inflection point detection based on the line loss rate time sequence to obtain an inflection point detection result; if the inflection point detection result comprises at least one inflection point, respectively determining the power consumption increment of each user corresponding to the at least one inflection point in the line loss rate abnormal area based on the at least one inflection point and the reference point corresponding to the at least one inflection point; respectively determining the electricity stealing suspicion coefficient of each user based on the increase of the electricity consumption; and identifying the electricity stealing suspected user based on the electricity stealing suspicion coefficient of each user, and generating an electricity stealing suspicion user label for the electricity stealing suspicion user. The electricity stealing suspicion coefficient can be calculated by determining the electricity consumption increase amount of each corner in the online loss rate time sequence of the user, the electricity stealing suspicion coefficient is used for accurately identifying the electricity stealing suspicion user, and an electricity stealing suspicion label is generated for the electricity stealing suspicion user, so that the power loss in the power transmission process is reduced, and the probability of safety accidents is reduced.

When the embodiment of the invention is used for detecting the inflection point, the line loss rate increase quantity and the line loss rate increase rate of two adjacent unit time periods are integrated, and the inflection point is obtained by combining the increase condition detection, so that the contingency can be reduced, and the inflection point detection result is more accurate. And the line loss rate increase rate and the line loss rate increase amount are comprehensively considered when the increase condition is set, so that the inflection point with high possibility of electricity stealing is favorably detected, and the accuracy of identifying the electricity stealing suspected user is improved.

If the line loss rate increase amount corresponding to the inflection point is large and the electricity consumption increase amount of the user is small, the possibility of electricity stealing is high, and based on the fact that the absolute value of the ratio of the electricity consumption increase amount of the user at the inflection point to the line loss rate increase amount is large, the possibility of electricity stealing of the user is high. In this embodiment, the ratio of the power consumption increase amount to the line loss rate increase amount is used as the suspected electricity stealing coefficient corresponding to the user at the inflection point, so that the possibility that the user steals electricity at the inflection point can be accurately reflected, the subsequent accurate identification of the suspected electricity stealing user is facilitated, and the suspected electricity stealing user tag is generated for the suspected electricity stealing user.

Furthermore, the absolute value of the mean value of the electricity stealing suspicion coefficient corresponding to each inflection point of the user is used as the electricity stealing suspicion coefficient of the user, so that the contingency can be avoided, and the possibility that the electricity stealing of the user can be reflected more accurately by the electricity stealing suspicion coefficient of the user.

In addition, the electricity stealing type of the electricity stealing suspected user is determined to be continuous electricity stealing or discontinuous electricity stealing by calculating the correlation coefficient of the electricity consumption of each unit time period of the electricity stealing suspected user and the line loss rate of each unit time period, so that the label of the electricity stealing suspected user is more complete, and the classification of the user is convenient to refine.

It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by functions and internal logic of the process, and should not limit the implementation process of the embodiments of the present invention in any way.

The following are embodiments of the apparatus of the invention, reference being made to the corresponding method embodiments described above for details which are not described in detail therein.

Fig. 3 is a schematic structural diagram of a suspected electricity stealing user tag generation apparatus provided by an embodiment of the present invention, and for convenience of description, only the relevant parts of the embodiment of the present invention are shown, which are detailed as follows:

as shown in fig. 3, the electricity stealing suspected user tag generation apparatus 3 includes: a sequence acquisition module 31, a knee detection module 32, a first determination module 33, a second determination module 34, and a tag generation module 35.

A sequence obtaining module 31, configured to obtain a line loss rate time sequence of the line loss rate abnormal region; the line loss rate time series represents a data series in which the line loss rates of the respective unit time periods within the target time period are sequentially configured.

And the inflection point detection module 32 is configured to perform inflection point detection based on the line loss rate time series to obtain an inflection point detection result.

A first determining module 33, configured to, if the inflection point detection result includes at least one inflection point, respectively determine, based on the at least one inflection point and a reference point corresponding to the at least one inflection point, a power consumption increase amount corresponding to the at least one inflection point for each user in the area with the abnormal line loss rate

A second determining module 34 for determining the suspicion coefficient of electricity stealing of each user based on the amount of increase in electricity consumption

And the tag generation module 35 is configured to identify the electricity stealing suspected user based on the electricity stealing suspicion coefficient of each user, and generate an electricity stealing suspicion user tag for the electricity stealing suspicion user.

In one possible implementation, the inflection point detecting module 32 is configured to determine the line loss rate increase amount and the line loss rate increase rate for each two adjacent unit time periods based on the line loss rate time series.

The inflection point detecting module 32 is further configured to determine two adjacent unit time periods that satisfy the growth condition as an inflection point in the line loss rate time series and a corresponding reference point. The growth conditions include: the line loss rate increase amounts of the two current adjacent unit time periods are positioned in M bits with the maximum line loss rate increase amounts of the two current adjacent unit time periods, the line loss rate increase rates of the two current adjacent unit time periods are larger than a first threshold, and M is a positive integer; the reference point corresponding to the inflection point is a previous unit period adjacent to the inflection point.

In a possible implementation manner, the first determining module 33 is configured to obtain, for each user in the area with the abnormal line loss rate, the power consumption of the user at each inflection point and the power consumption of the user at a reference point corresponding to each inflection point.

The first determining module 33 is further configured to subtract the power consumption at the reference point corresponding to each inflection point from the power consumption at each inflection point to obtain the power consumption increase amount corresponding to each inflection point of the user.

In a possible implementation manner, the second determining module 34 is configured to, for each user, respectively use a ratio of an electricity consumption increase amount corresponding to each inflection point of the user to a line loss rate increase amount as a suspicion coefficient of electricity stealing corresponding to each inflection point of the user.

The second determining module 34 is further configured to determine the suspicion of electricity stealing coefficient of each user based on the suspicion of electricity stealing coefficients corresponding to all inflection points of each user.

In a possible implementation manner, the second determining module 34 is configured to use an absolute value of a mean value of the suspicion stealing coefficients corresponding to all inflection points of each user as the suspicion stealing coefficient of each user.

In a possible implementation manner, the inflection point detecting module 32 is configured to, starting from the second unit time segment in the line loss rate time sequence, use each unit time segment as the current unit time segment, and calculate the line loss rate increase amount and the line loss rate increase rate of the current unit time segment relative to the previous unit time segment, so as to obtain the line loss rate increase amount and the line loss rate increase rate of each two adjacent unit time segments.

The inflection point detecting module 32 is further configured to, if a target unit time segment with a missing line loss rate exists in the line loss rate time series, fill the line loss rate of the target unit time segment into the target line loss rate, where the target line loss rate is determined based on the line loss rate of a first unit time segment and the line loss rate of a second unit time segment, where the first unit time segment is the unit time segment which is located before the target unit time segment and has the shortest time interval with the target unit time segment and has no missing line loss rate, and the second unit time segment is the unit time segment which is located after the target unit time segment and has the shortest time interval with the target unit time segment and has no missing line loss rate.

In a possible implementation manner, the tag generation module 35 is configured to calculate a correlation coefficient between the electricity consumption of the electricity stealing suspected user in each unit time period and the line loss rate of each unit time period.

The tag generating module 35 is further configured to determine that the suspected electricity stealing user is a continuous electricity stealing user if the correlation coefficient is greater than the second threshold.

The tag generating module 35 is further configured to determine that the suspected electricity stealing user is an intermittent electricity stealing situation if the correlation coefficient is smaller than the third threshold.

The embodiment of the invention is used for acquiring the line loss rate time sequence of the abnormal line loss rate distribution room through the sequence acquisition module 31; an inflection point detection module 32, configured to perform inflection point detection based on the line loss rate time series to obtain an inflection point detection result; the first determining module 33 is configured to, if the inflection point detection result includes at least one inflection point, respectively determine, based on the at least one inflection point and a reference point corresponding to the at least one inflection point, a power consumption increase amount corresponding to the at least one inflection point for each user in the line loss rate abnormal area; the second determining module 34 is configured to determine the suspected electricity stealing coefficient of each user based on the amount of increase in electricity consumption; and the label generation module 35 is configured to identify the suspected electricity-stealing user based on the suspected electricity-stealing coefficient of each user, and generate an electricity-stealing suspected user label for the suspected electricity-stealing user. The second determining module 34 is configured to obtain an electricity stealing suspicion coefficient through determining an electricity consumption increase amount at each corner in the online loss rate time sequence of the user, so that the tag generating module 35 accurately identifies the electricity stealing suspicion user according to the electricity stealing suspicion coefficient, and generates an electricity stealing suspicion tag for the electricity stealing suspicion user, so that power loss in a power transmission process is reduced, and a probability of occurrence of a safety accident is reduced.

When the inflection point detection module 32 performs inflection point detection, the line loss rate increase amount and the line loss rate increase rate of two adjacent unit time periods are integrated, and an inflection point is obtained by combining with increase condition detection, so that the contingency can be reduced, and an inflection point detection result is more accurate. And the line loss rate increase rate and the line loss rate increase amount are comprehensively considered when the increase condition is set, so that the inflection point with high possibility of electricity stealing is favorably detected, and the accuracy of identifying the electricity stealing suspected user is improved.

If the line loss rate increase amount corresponding to the inflection point is large and the electricity consumption increase amount of the user is small, the possibility of electricity stealing is high, and based on the fact that the absolute value of the ratio of the electricity consumption increase amount of the user at the inflection point to the line loss rate increase amount is large, the possibility of electricity stealing of the user is high. The second determining module 34 uses the ratio of the power consumption increase amount to the line loss rate increase amount as the suspected electricity stealing coefficient corresponding to the inflection point of the user, so that the possibility of electricity stealing corresponding to the inflection point of the user can be accurately reflected, the subsequent accurate identification of the suspected electricity stealing user is facilitated, and the suspected electricity stealing user tag is generated for the suspected electricity stealing user.

Further, the second determining module 34 may avoid contingency by using an absolute value of an average value of the electricity stealing suspicion coefficients corresponding to each inflection point of the user as the electricity stealing suspicion coefficient of the user, so that the electricity stealing suspicion coefficient of the user may more accurately reflect the possibility that the user steals electricity.

In addition, the tag generation module 35 determines whether the electricity stealing type of the electricity stealing suspected user is continuous electricity stealing or discontinuous electricity stealing by calculating the correlation coefficient between the electricity consumption of each unit time period of the electricity stealing suspected user and the line loss rate of each unit time period, so that the tag of the electricity stealing suspected user can be more complete, and the user classification can be conveniently refined.

Fig. 4 is a schematic diagram of an electronic device provided in an embodiment of the present invention. As shown in fig. 4, the electronic apparatus 4 of this embodiment includes: a processor 40, a memory 41 and a computer program 42 stored in said memory 41 and executable on said processor 40. The processor 40 implements the steps in the above embodiments of the suspected fraudulent use of electricity stealing tag generation method, such as steps 101 to 105 shown in fig. 1, when executing the computer program 42. Alternatively, the processor 40, when executing the computer program 42, implements the functions of the modules/units in the device embodiments described above, such as the modules 31 to 35 shown in fig. 3.

Illustratively, the computer program 42 may be partitioned into one or more modules/units that are stored in the memory 41 and executed by the processor 40 to implement the present invention. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution of the computer program 42 in the electronic device 4. For example, the computer program 42 may be divided into the modules 31 to 35 shown in fig. 3.

The electronic device 4 may be a desktop computer, a notebook, a palm computer, a cloud server, or other computing devices. The electronic device 4 may include, but is not limited to, a processor 40, a memory 41. Those skilled in the art will appreciate that fig. 4 is merely an example of an electronic device 4 and does not constitute a limitation of the electronic device 4 and may include more or fewer components than shown, or some components may be combined, or different components, e.g., the electronic device may also include input-output devices, network access devices, buses, etc.

The Processor 40 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The memory 41 may be an internal storage unit of the electronic device 4, such as a hard disk or a memory of the electronic device 4. The memory 41 may also be an external storage device of the electronic device 4, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the electronic device 4. Further, the memory 41 may also include both an internal storage unit and an external storage device of the electronic device 4. The memory 41 is used for storing the computer program and other programs and data required by the electronic device. The memory 41 may also be used to temporarily store data that has been output or is to be output.

It should be clear to those skilled in the art that, for convenience and simplicity of description, the foregoing division of the functional units and modules is only used for illustration, and in practical applications, the above function distribution may be performed by different functional units and modules as needed, that is, the internal structure of the apparatus may be divided into different functional units or modules to perform all or part of the above described functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

In the above embodiments, the description of each embodiment has its own emphasis, and reference may be made to the related description of other embodiments for parts that are not described or recited in any embodiment.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. 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.

In the embodiments provided in the present invention, it should be understood that the disclosed apparatus/electronic device and method may be implemented in other ways. For example, the above-described apparatus/electronic device embodiments are merely illustrative, and for example, the division of the modules or units is only one type of logical function division, and other division manners may exist in actual implementation, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and 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 units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

The integrated module/unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow in the method according to the above embodiments may be implemented by a computer program, which may be stored in a computer readable storage medium, and when the computer program is executed by a processor, the computer program may implement the steps of the foregoing embodiments of the method for generating a suspected fraudulent use of electricity tag. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, read-Only Memory (ROM), random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.

Claims

1. A method for generating a label of a suspected electricity stealing user is characterized by comprising the following steps:

acquiring a line loss rate time sequence of the line loss rate abnormal area; the line loss rate time sequence represents a data sequence formed by line loss rates of all unit time periods in a target time period in sequence;

and identifying the electricity stealing suspected user based on the electricity stealing suspected coefficient of each user, and generating an electricity stealing suspected user label for the electricity stealing suspected user.

2. The method for generating the label of the suspected electricity stealing user according to claim 1, wherein the performing inflection point detection based on the time series of line loss rates to obtain an inflection point detection result comprises:

determining two adjacent unit time periods meeting the growth condition as an inflection point in the line loss rate time sequence and a corresponding reference point; the growth conditions include: the line loss rate increase amount of the two current adjacent unit time periods is positioned in the M bits with the maximum line loss rate increase amount of the two current adjacent unit time periods, the line loss rate increase rates of the two current adjacent unit time periods are greater than a first threshold value, and M is a positive integer; the reference point corresponding to the inflection point is a previous unit period adjacent to the inflection point.

3. The method for generating the label of the electricity stealing suspected user according to claim 1, wherein the step of determining the power consumption increase amount of each user at the at least one inflection point in the area with the abnormal line loss rate based on the at least one inflection point and the reference point corresponding to the at least one inflection point comprises:

4. The label generation method of electricity stealing suspicion users according to claim 2 or 3, wherein the determining the suspicion coefficient of electricity stealing for each user based on the amount of increase in electricity consumption comprises:

for each user, respectively taking the ratio of the electricity consumption increment corresponding to the user at each inflection point to the line loss rate increment as the electricity stealing suspicion coefficient corresponding to the user at each inflection point;

5. The method for generating the electricity stealing suspicion user tag as claimed in claim 4, wherein the step of determining the electricity stealing suspicion coefficient of each user based on the electricity stealing suspicion coefficients corresponding to all inflection points of each user comprises:

6. The method for generating labels of suspected electricity stealing users according to claim 1, wherein the determining the line loss rate increase amount and the line loss rate increase rate of each two adjacent unit time periods based on the line loss rate time series comprises:

starting from the second unit time period in the line loss rate time sequence, respectively taking each unit time period as the current unit time period, and calculating the line loss rate increment and the line loss rate increment of the current unit time period relative to the previous unit time period to obtain the line loss rate increment and the line loss rate increment of each two adjacent unit time periods;

and if a target unit time segment with a missing line loss rate exists in the line loss rate time sequence, filling the line loss rate of the target unit time segment into a target line loss rate, wherein the target line loss rate is determined based on the line loss rate of a first unit time segment and the line loss rate of a second unit time segment, the first unit time segment is the unit time segment which is located before the target unit time segment, has the shortest time interval with the target unit time segment and has no missing line loss rate, and the second unit time segment is the unit time segment which is located after the target unit time segment, has the shortest time interval with the target unit time segment and has no missing line loss rate.

7. The method as claimed in claim 1, wherein after the step of identifying the suspected electricity-stealing user based on the suspected electricity-stealing coefficient of each user and generating the suspected electricity-stealing user tag for the suspected electricity-stealing user, the method further comprises:

if the correlation coefficient is larger than a second threshold value, determining that the suspected electricity stealing user is continuous electricity stealing;

8. A suspected electricity stealing user tag generation apparatus, comprising:

9. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the steps of the method according to any of the preceding claims 1 to 7 are implemented when the computer program is executed by the processor.

10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.