CN116433402A - Analysis processing device, method and storage medium for automatic sales of user electricity fees - Google Patents
Analysis processing device, method and storage medium for automatic sales of user electricity fees Download PDFInfo
- Publication number
- CN116433402A CN116433402A CN202310422532.3A CN202310422532A CN116433402A CN 116433402 A CN116433402 A CN 116433402A CN 202310422532 A CN202310422532 A CN 202310422532A CN 116433402 A CN116433402 A CN 116433402A
- Authority
- CN
- China
- Prior art keywords
- user
- charge data
- electricity charge
- data
- user electricity
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000005611 electricity Effects 0.000 title claims abstract description 213
- 238000004458 analytical method Methods 0.000 title claims abstract description 65
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000012545 processing Methods 0.000 title claims abstract description 14
- 230000002159 abnormal effect Effects 0.000 claims abstract description 59
- 238000001514 detection method Methods 0.000 claims abstract description 31
- 230000005856 abnormality Effects 0.000 claims abstract description 15
- 238000013450 outlier detection Methods 0.000 claims description 70
- 238000012300 Sequence Analysis Methods 0.000 claims description 61
- 238000012937 correction Methods 0.000 claims description 33
- 238000003672 processing method Methods 0.000 claims description 10
- 238000012731 temporal analysis Methods 0.000 claims description 10
- 238000000700 time series analysis Methods 0.000 claims description 10
- 230000008859 change Effects 0.000 claims description 6
- 238000007405 data analysis Methods 0.000 claims description 6
- 230000009191 jumping Effects 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 238000013480 data collection Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000010219 correlation analysis Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 241001123248 Arma Species 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/12—Accounting
- G06Q40/125—Finance or payroll
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The invention discloses an analysis processing device, a method and a storage medium for automatic billing of user electric charges, wherein the method comprises the following steps that 1, a system acquires first user electric charge data, wherein the first user electric charge data comprises user electric quantity, electric charge unit price and time for acquiring the user electric charge data; step 2, inputting the first user electricity charge data into an abnormality detection model, and judging whether the first user electricity charge data is abnormal or not; step 3, the first user electricity charge data with abnormality is adjusted to second user electricity charge data, the first user electricity charge data and the second user electricity charge data are input into a judging model, and the reasonable degree of the second user electricity charge data is judged; and 4, calculating the electricity fee to be deducted by the user of the first user electricity fee data and the third user electricity fee data, and billing the electricity fee to be deducted by the user. The invention can quickly find out the abnormal data, and sell the normal electricity fee data, thereby improving the efficiency of automatic electricity fee sales of users.
Description
Technical Field
The invention relates to the technical field of electric charge management of an electric power system, in particular to an analysis processing device, an analysis processing method and a storage medium for automatic sales of electric charges of users.
Background
At present, along with the economic development of each region, the matched power grid construction is also followed, the existing automatic electric charge billing process of the user generally includes the steps of deducting money from a designated corresponding payment account according to the electric charge of the electric charge bill after receiving the electric charge bill, recording the time information of the electric charge fund after the deduction result file and the electric charge bill information are approved correctly, and conducting electric charge billing. However, the default electric bill of the automatic billing process is correct, and the abnormal electric bill has no distinguishing capability, so that if the abnormal electric bill is billed, the loss of an electric company or a user can be caused, the use experience of the user is affected, and meanwhile, the wrong billing process also needs to be checked and corrected manually, thereby wasting time and labor.
Disclosure of Invention
The invention aims to overcome the defect that whether an electric charge bill cannot be correctly distinguished in the automatic electric charge bill selling process of a user in the prior art, and the abnormal electric charge bill can possibly cause loss of an electric company or a user and influence the use experience of the user.
The invention aims at realizing the following technical scheme:
the analysis processing method for the automatic sales of the electric charge of the user comprises the following steps:
step 1, a system acquires first user electricity charge data, wherein the first user electricity charge data comprises user electric quantity, electricity charge unit price and time for acquiring the user electricity charge data;
step 2, inputting the first user electricity charge data into an abnormality detection model, judging whether the first user electricity charge data is abnormal, if so, jumping to step 3, and if not, jumping to step 4;
step 3, the first user electricity charge data with abnormality is adjusted to second user electricity charge data, the first user electricity charge data and the second user electricity charge data are input into a judging model, the reasonable degree of the second user electricity charge data is judged, and if the reasonable degree of the second user electricity charge data exceeds a set first threshold value, the second user electricity charge data is adjusted to third user electricity charge data;
and 4, calculating the electricity charge to be deducted of the user of the first user electricity charge data and the third user electricity charge data, selling the electricity charge to be deducted of the user, and generating an abnormality report for reminding related operators of the second user electricity charge data.
Preferably, the anomaly detection model is a time series analysis model, and the step 2 of inputting the first user electricity charge data into the anomaly detection model, and the judging whether the first user electricity charge data is abnormal specifically includes:
inputting the first user electricity charge data into a time sequence analysis model, acquiring historical data of a user corresponding to the first user electricity charge data by the time sequence analysis model, judging the change period and the change trend of the user electricity quantity according to the historical data of the user, predicting the future user electricity quantity, comparing the user electricity quantity of the first user electricity charge data with the future user electricity quantity matched in time, and judging that the first user electricity charge data is abnormal if the user electricity charge data exceeds a set second threshold;
or the anomaly detection model is an outlier detection model, and the step 2 is to input the first user electricity charge data into the anomaly detection model, and the step of judging whether the first user electricity charge data is abnormal specifically comprises the following steps:
and inputting the first user electric charge data into an outlier detection model, acquiring historical data of a user corresponding to the first user electric charge data by the outlier detection model, calculating the user average electric quantity of the historical data, setting a tolerance value on the user electric quantity and a tolerance value under the user electric quantity by the outlier detection model according to the user average electric quantity, and judging that the first user electric charge data is abnormal if the user electric quantity of the first user electric charge data exceeds the tolerance value on the user electric quantity or does not exceed the tolerance value under the user electric quantity.
Preferably, in the step 3, the judging the reasonable degree of the second user electricity fee data specifically includes: if the anomaly detection model is a time sequence analysis model, judging that the model is an outlier detection model, calculating the deviation degree of the user electric quantity of the second user electric charge data from the normal user electric quantity range in the time sequence analysis model result, and then calculating the deviation degree of the user electric quantity of the second user electric charge data from the normal user electric quantity range in the outlier detection model, wherein the reasonable degree of the second user electric charge data is as follows:
R＝α·E Tsam +β·E Odm
wherein R is the reasonable degree of the electric charge data, E Tsam For the deviation degree from the normal user electric quantity range in the time sequence analysis model result, E Odm And alpha is a correction coefficient of the importance of the time sequence analysis model, and beta is a correction coefficient of the importance of the outlier detection model.
Preferably, in the step 3, the judging the reasonable degree of the second user electricity fee data specifically includes: if the anomaly detection model is an outlier detection model, the judgment model is a time sequence analysis model, the deviation degree of the user electric quantity of the second user electric charge data from the normal user electric quantity range in the outlier detection model result is calculated, then the deviation degree of the user electric quantity of the second user electric charge data from the normal user electric quantity range in the time sequence analysis model is calculated, and then the reasonable degree of the second user electric charge data is as follows:
R＝α·E Odm +β·E Tsam
wherein R is the reasonable degree of the electric charge data, E Tsam For the deviation degree from the normal user electric quantity range in the time sequence analysis model result, E Odm And alpha is a correction coefficient of the importance of the outlier detection model, and beta is a correction coefficient of the importance of the time sequence analysis model.
Preferably, the correction coefficient of the importance of the time series analysis model and the correction coefficient of the importance of the outlier detection model are dynamically updated through a training model, specifically:
acquiring analysis results of a time sequence analysis model, wherein the analysis results comprise first normal user electricity charge data and first abnormal user electricity charge data with correct analysis results, and second normal user electricity charge data and second abnormal user electricity charge data with incorrect analysis results;
acquiring analysis results of the outlier detection model, wherein the analysis results comprise first normal user electricity charge data and first abnormal user electricity charge data with correct analysis results, and second normal user electricity charge data and second abnormal user electricity charge data with incorrect analysis results;
if the second normal user electricity charge data with the wrong analysis result in the time sequence analysis model is the first abnormal user electricity charge data with the correct analysis result in the outlier detection model, the correction coefficient of the importance of the time sequence analysis model is reduced by M1, and if the second abnormal user electricity charge data with the wrong analysis result in the time sequence analysis model is the first normal user electricity charge data with the correct analysis result in the outlier detection model, the correction coefficient of the importance of the time sequence analysis model is reduced by N1, M1 and N1 are all proportional coefficients, and M1 is larger than N1;
if the second normal user electricity charge data with the incorrect analysis result in the outlier detection model is the first abnormal user electricity charge data with the correct analysis result in the time sequence analysis model, the correction coefficient of the importance of the outlier detection model is reduced by M2, and if the second abnormal user electricity charge data with the incorrect analysis result in the outlier detection model is the first normal user electricity charge data with the correct analysis result in the time sequence analysis model, the correction coefficient of the importance of the outlier detection model is reduced by N2, M2 and N2 are all proportional coefficients, and M2 is larger than N2.
Preferably, the analysis processing method for automatic sales of the electricity fee of the user also updates the history data of the electric quantity range of the normal user, specifically:
in the time sequence analysis model, a fitting curve is constructed by taking time for acquiring user electricity charge data as an abscissa and a user electricity quantity value as an ordinate, a reasonable range is set to be S (1+/-r), S is a value of the fitting curve, r is a corrected percentage coefficient, for a certain user electricity quantity value exceeding the reasonable range, a value of the fitting curve corresponding to the user electricity quantity value is acquired, a tangential slope of the fitting curve at the time point is calculated, if the absolute value of the tangential slope of the fitting curve at the time point does not exceed 120% of the maximum value in the tangential slope absolute values of all other remaining time points, the user electricity quantity value is reserved, r value is increased, and if the absolute value of the tangential slope of the fitting curve at the time point exceeds 120% of the maximum value in the tangential slope absolute values of all other remaining time points, the user electricity quantity value is deleted, the fitting curve is reconstructed, and r value is unchanged.
Preferably, the analysis processing method for automatic sales of the electricity fee of the user also updates the passing history data of the electricity quantity range of the normal user, specifically:
in the outlier detection model, setting a power consumption range as [ a, b ], setting a user power value exceeding an initial power consumption range as a to-be-determined user power value, searching other user power values within a time range set after the to-be-determined user power value, and if the difference between the value of at least two user power values in the other user power values and the to-be-determined user power value is within the set range, redefining the value corresponding to the to-be-determined user power value as the upper limit or the lower limit of the power consumption range, and if the difference between the value of at most one user power value in the other user power values and the to-be-determined user power value is within the set range, keeping the power consumption range unchanged.
An analysis processing device for automatic sales of electric charges of users, comprising:
the data collection module is used for acquiring the first user electricity charge data and sending the first user electricity charge data to the data analysis module; the data analysis module is used for analyzing the first user electricity charge data and finding out abnormal data;
the data judging module is used for judging the abnormal data and recovering part of the abnormal data into normal data according to the judgment; and the deduction Fei Xiaozhang module is used for acquiring the electricity fee data of the normal user and carrying out deduction and billing.
The storage medium is stored with a computer program which is used for realizing the analysis processing method of the automatic sales of the electric charge of the user when being executed by the processor.
The beneficial effects of the invention are as follows: according to the invention, the user electricity charge data is detected through the anomaly detection model, so that the anomaly data can be quickly found out, the normal electricity charge data is subjected to sales, and an anomaly report is generated for the anomaly electricity charge data to remind related operators, so that the efficiency of automatic sales of the user electricity charge is improved, and the influence on the user experience caused by sales of wrong user electricity charge is prevented;
the invention has better discrimination capability for the abnormal electric charge data, and can further screen the electric charge data which is initially detected as abnormal, find out the normal electric charge data therein, and further improve the accuracy of the abnormal electric charge data; according to the method, the anomaly detection model is dynamically updated, and the anomaly detection model is trained through the data, so that the effectiveness of the anomaly detection model is further improved.
According to the invention, the correlation analysis is skillfully carried out on the time sequence analysis model and the outlier detection model, the interaction improves the performance of the opposite model, and the combined action of the time sequence analysis model and the outlier detection model further improves the detection accuracy of abnormal electricity charge data.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of the present invention.
Detailed Description
The invention is further described below with reference to the drawings and examples.
Examples:
the analysis processing method for the automatic sales of the electric charge of the user, as shown in fig. 1, comprises the following steps:
step 1, a system acquires first user electricity charge data, wherein the first user electricity charge data comprises user electric quantity, electricity charge unit price and time for acquiring the user electricity charge data;
step 2, inputting the first user electricity charge data into an abnormality detection model, judging whether the first user electricity charge data is abnormal, if so, jumping to step 3, and if not, jumping to step 4;
step 3, the first user electricity charge data with abnormality is adjusted to second user electricity charge data, the first user electricity charge data and the second user electricity charge data are input into a judging model, the reasonable degree of the second user electricity charge data is judged, and if the reasonable degree of the second user electricity charge data exceeds a set first threshold value, the second user electricity charge data is adjusted to third user electricity charge data;
and 4, calculating the electricity charge to be deducted of the user of the first user electricity charge data and the third user electricity charge data, selling the electricity charge to be deducted of the user, and generating an abnormality report for reminding related operators of the second user electricity charge data.
The anomaly detection model is a time sequence analysis model, the step 2 is to input the first user electricity charge data into the anomaly detection model, and the judgment whether the first user electricity charge data is abnormal specifically:
inputting the first user electricity charge data into a time sequence analysis model, acquiring historical data of a user corresponding to the first user electricity charge data by the time sequence analysis model, judging the change period and the change trend of the user electricity quantity according to the historical data of the user, predicting the future user electricity quantity, comparing the user electricity quantity of the first user electricity charge data with the future user electricity quantity matched in time, and judging that the first user electricity charge data is abnormal if the user electricity charge data exceeds a set second threshold;
or the anomaly detection model is an outlier detection model, and the step 2 is to input the first user electricity charge data into the anomaly detection model, and the step of judging whether the first user electricity charge data is abnormal specifically comprises the following steps:
and inputting the first user electric charge data into an outlier detection model, acquiring historical data of a user corresponding to the first user electric charge data by the outlier detection model, calculating the user average electric quantity of the historical data, setting a tolerance value on the user electric quantity and a tolerance value under the user electric quantity by the outlier detection model according to the user average electric quantity, and judging that the first user electric charge data is abnormal if the user electric quantity of the first user electric charge data exceeds the tolerance value on the user electric quantity or does not exceed the tolerance value under the user electric quantity.
Time series analysis is a theory and method for establishing a mathematical model through curve fitting and parameter estimation according to time series data obtained by system observation. Typically using curve fitting and parameter estimation methods such as nonlinear least squares. In this embodiment, the time series analysis model may be an ARMA model.
Outlier detection is the process of finding objects whose behavior is different from that of the intended object, which is called outliers or anomalies. In this embodiment, a conventional outlier detection method or a DBScan cluster is used as the outlier detection method, where DBScan is a clustering algorithm that groups data. It can also be used as a density-based anomaly detection method, whether it is single-dimensional or multi-dimensional.
In the present embodiment, it is obvious that if the abnormality detection model is a time-series analysis model, the judgment model is an outlier detection model, and conversely, if the abnormality detection model is an outlier detection model, the judgment model is a time-series analysis model. The user electricity charge data, namely the coincidence time sequence analysis model is judged through the prediction of the historical data on the current data, and the load outlier detection is judged on the current data, so that the correlation analysis is skillfully carried out on the time sequence analysis model and the outlier detection model, the performance of the opposite model is improved through interaction, and the detection accuracy of the abnormal electricity charge data is further improved through the combined action of the time sequence analysis model and the outlier detection model.
In the step 3, the judging of the reasonable degree of the second user electricity fee data specifically includes:
if the anomaly detection model is a time sequence analysis model, judging that the model is an outlier detection model, calculating the deviation degree of the user electric quantity of the second user electric charge data from the normal user electric quantity range in the time sequence analysis model result, and then calculating the deviation degree of the user electric quantity of the second user electric charge data from the normal user electric quantity range in the outlier detection model, wherein the reasonable degree of the second user electric charge data is as follows:
R＝α·E Tsam +β·E Odm
wherein R is the reasonable degree of the electric charge data, E Tsam For the deviation degree from the normal user electric quantity range in the time sequence analysis model result, E Odm And alpha is a correction coefficient of the importance of the time sequence analysis model, and beta is a correction coefficient of the importance of the outlier detection model.
In the step 3, the judging of the reasonable degree of the second user electricity fee data specifically includes:
if the anomaly detection model is an outlier detection model, the judgment model is a time sequence analysis model, the deviation degree of the user electric quantity of the second user electric charge data from the normal user electric quantity range in the outlier detection model result is calculated, then the deviation degree of the user electric quantity of the second user electric charge data from the normal user electric quantity range in the time sequence analysis model is calculated, and then the reasonable degree of the second user electric charge data is as follows:
R＝α·E Odm +β·E Tsam
wherein R is the reasonable degree of the electric charge data, E Tsam For the deviation degree from the normal user electric quantity range in the time sequence analysis model result, E Odm And alpha is a correction coefficient of the importance of the outlier detection model, and beta is a correction coefficient of the importance of the time sequence analysis model.
Because the user electricity quantity may deviate from the average value or the previous electricity quantity to a certain extent in the actual use process, the abnormality of the user electricity charge data is caused, and the abnormality is not necessarily the recording error of the user electricity charge data but the fluctuation range of the normal user electricity quantity, so that the reasonable degree of the second user electricity charge data is considered in the embodiment, the reasonable user electricity charge data is still judged to be the normal electricity charge data, and then the electricity charge deduction is carried out. In this embodiment, the deviation from the normal user power range in the outlier detection model is calculated by a specific difference value of the user power or by a euclidean distance from the clustering center after clustering.
The correction coefficient of the importance of the time sequence analysis model and the correction coefficient of the importance of the outlier detection model are dynamically updated through a training model, and specifically:
acquiring analysis results of a time sequence analysis model, wherein the analysis results comprise first normal user electricity charge data and first abnormal user electricity charge data with correct analysis results, and second normal user electricity charge data and second abnormal user electricity charge data with incorrect analysis results;
acquiring analysis results of the outlier detection model, wherein the analysis results comprise first normal user electricity charge data and first abnormal user electricity charge data with correct analysis results, and second normal user electricity charge data and second abnormal user electricity charge data with incorrect analysis results;
if the second normal user electricity charge data with the wrong analysis result in the time sequence analysis model is the first abnormal user electricity charge data with the correct analysis result in the outlier detection model, the correction coefficient of the importance of the time sequence analysis model is reduced by M1, and if the second abnormal user electricity charge data with the wrong analysis result in the time sequence analysis model is the first normal user electricity charge data with the correct analysis result in the outlier detection model, the correction coefficient of the importance of the time sequence analysis model is reduced by N1, M1 and N1 are all proportional coefficients, and M1 is larger than N1;
if the second normal user electricity charge data with the incorrect analysis result in the outlier detection model is the first abnormal user electricity charge data with the correct analysis result in the time sequence analysis model, the correction coefficient of the importance of the outlier detection model is reduced by M2, and if the second abnormal user electricity charge data with the incorrect analysis result in the outlier detection model is the first normal user electricity charge data with the correct analysis result in the time sequence analysis model, the correction coefficient of the importance of the outlier detection model is reduced by N2, M2 and N2 are all proportional coefficients, and M2 is larger than N2.
In this embodiment, the correction coefficients of the importance of the time series analysis model and the importance of the outlier detection model are dynamically updated, and the correction coefficients can be flexibly adjusted by taking the two models as references, so that when training is performed, whether the time series analysis model and the outlier detection model are normal or not can be judged by the determined abnormal user electricity fee data, and when a model with wrong judgment occurs, the correction coefficients can be reduced, and the effectiveness of the final reasonable degree is ensured.
The analysis processing method for the automatic sales of the user electric charge also updates the normal user electric quantity range through historical data, and specifically comprises the following steps:
in the time sequence analysis model, a fitting curve is constructed by taking time for acquiring user electricity charge data as an abscissa and a user electricity quantity value as an ordinate, a reasonable range is set to be S (1+/-r), S is a value of the fitting curve, r is a corrected percentage coefficient, for a certain user electricity quantity value exceeding the reasonable range, a value of the fitting curve corresponding to the user electricity quantity value is acquired, a tangential slope of the fitting curve at the time point is calculated, if the absolute value of the tangential slope of the fitting curve at the time point does not exceed 120% of the maximum value in the tangential slope absolute values of all other remaining time points, the user electricity quantity value is reserved, r value is increased, and if the absolute value of the tangential slope of the fitting curve at the time point exceeds 120% of the maximum value in the tangential slope absolute values of all other remaining time points, the user electricity quantity value is deleted, the fitting curve is reconstructed, and r value is unchanged.
The analysis processing method for the automatic sales of the user electric charge also updates the history data of the normal user electric quantity range, specifically:
in the outlier detection model, setting a power consumption range as [ a, b ], setting a user power value exceeding an initial power consumption range as a to-be-determined user power value, searching other user power values within a time range set after the to-be-determined user power value, and if the difference between the value of at least two user power values in the other user power values and the to-be-determined user power value is within the set range, redefining the value corresponding to the to-be-determined user power value as the upper limit or the lower limit of the power consumption range, and if the difference between the value of at most one user power value in the other user power values and the to-be-determined user power value is within the set range, keeping the power consumption range unchanged.
An analysis processing device for automatic sales of electric charges of users, comprising:
the data collection module is used for acquiring the first user electricity charge data and sending the first user electricity charge data to the data analysis module; the data analysis module is used for analyzing the first user electricity charge data and finding out abnormal data;
the data judging module is used for judging the abnormal data and recovering part of the abnormal data into normal data according to the judgment; and the deduction Fei Xiaozhang module is used for acquiring the electricity fee data of the normal user and carrying out deduction and billing.
The storage medium is stored with a computer program which is used for realizing the analysis processing method of the automatic sales of the electric charge of the user when being executed by the processor.
The storage medium may be a computer storage medium or a communication medium. Communication media includes any medium that facilitates transfer of a computer program from one place to another. Computer storage media can be any available media that can be accessed by a general purpose or special purpose computer. For example, a storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. In the alternative, the storage medium may be integral to the processor. The processor and the storage medium may reside in an application specific integrated circuit (Application Specific Integrated Circuits, ASIC for short). In addition, the ASIC may reside in a user device. The processor and the storage medium may reside as discrete components in a communication device. The storage medium may be read-only memory (ROM), random-access memory (RAM), CD-ROMs, magnetic tape, floppy disk, optical data storage device, etc.
The present invention also provides a program product comprising execution instructions stored in a storage medium. The at least one processor of the device may read the execution instructions from the storage medium, the execution instructions being executed by the at least one processor to cause the device to implement the methods provided by the various embodiments described above.
It should be understood that the processor may be a central processing unit (english: central Processing Unit, abbreviated as CPU), or other general purpose processor, digital signal processor (english: digital Signal Processor, abbreviated as DSP), application specific integrated circuit (english: application Specific Integrated Circuit, abbreviated as ASIC), etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present invention may be embodied directly in a hardware processor for execution, or in a combination of hardware and software modules in a processor for execution.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the 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 scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention.
In addition to the above embodiments, the present invention may have other embodiments; all technical schemes formed by equivalent substitution or equivalent transformation fall within the protection scope of the invention.
Claims (9)
1. The analysis processing method for the automatic sales of the electric charge of the user is characterized by comprising the following steps:
step 1, a system acquires first user electricity charge data, wherein the first user electricity charge data comprises user electric quantity, electricity charge unit price and time for acquiring the user electricity charge data;
step 2, inputting the first user electricity charge data into an abnormality detection model, judging whether the first user electricity charge data is abnormal, if so, jumping to step 3, and if not, jumping to step 4;
step 3, the first user electricity charge data with abnormality is adjusted to second user electricity charge data, the first user electricity charge data and the second user electricity charge data are input into a judging model, the reasonable degree of the second user electricity charge data is judged, and if the reasonable degree of the second user electricity charge data exceeds a set first threshold value, the second user electricity charge data is adjusted to third user electricity charge data;
and 4, calculating the electricity charge to be deducted of the user of the first user electricity charge data and the third user electricity charge data, selling the electricity charge to be deducted of the user, and generating an abnormality report for reminding related operators of the second user electricity charge data.
2. The method for automatically billing the user electric charge according to claim 1, wherein the anomaly detection model is a time series analysis model, and the step 2 is to input the first user electric charge data into the anomaly detection model, and the determining whether the first user electric charge data is abnormal specifically comprises:
inputting the first user electricity charge data into a time sequence analysis model, acquiring historical data of a user corresponding to the first user electricity charge data by the time sequence analysis model, judging the change period and the change trend of the user electricity quantity according to the historical data of the user, predicting the future user electricity quantity, comparing the user electricity quantity of the first user electricity charge data with the future user electricity quantity matched in time, and judging that the first user electricity charge data is abnormal if the user electricity charge data exceeds a set second threshold;
or the anomaly detection model is an outlier detection model, and the step 2 is to input the first user electricity charge data into the anomaly detection model, and the step of judging whether the first user electricity charge data is abnormal specifically comprises the following steps:
and inputting the first user electric charge data into an outlier detection model, acquiring historical data of a user corresponding to the first user electric charge data by the outlier detection model, calculating the user average electric quantity of the historical data, setting a tolerance value on the user electric quantity and a tolerance value under the user electric quantity by the outlier detection model according to the user average electric quantity, and judging that the first user electric charge data is abnormal if the user electric quantity of the first user electric charge data exceeds the tolerance value on the user electric quantity or does not exceed the tolerance value under the user electric quantity.
3. The method for analyzing and processing the automatic sales of the electric charges of the users according to claim 2, wherein in the step 3, the judging of the reasonable degree of the second electric charge data of the users is specifically:
if the anomaly detection model is a time sequence analysis model, judging that the model is an outlier detection model, calculating the deviation degree of the user electric quantity of the second user electric charge data from the normal user electric quantity range in the time sequence analysis model result, and then calculating the deviation degree of the user electric quantity of the second user electric charge data from the normal user electric quantity range in the outlier detection model, wherein the reasonable degree of the second user electric charge data is as follows:
R＝α·E Tsam +β·E Odm
wherein R is the reasonable degree of the electric charge data, E Tsam For the deviation degree from the normal user electric quantity range in the time sequence analysis model result, E Odm And alpha is a correction coefficient of the importance of the time sequence analysis model, and beta is a correction coefficient of the importance of the outlier detection model.
4. The method for analyzing and processing the automatic sales of the electric charges of the users according to claim 2, wherein in the step 3, the judging of the reasonable degree of the second electric charge data of the users is specifically:
if the anomaly detection model is an outlier detection model, the judgment model is a time sequence analysis model, the deviation degree of the user electric quantity of the second user electric charge data from the normal user electric quantity range in the outlier detection model result is calculated, then the deviation degree of the user electric quantity of the second user electric charge data from the normal user electric quantity range in the time sequence analysis model is calculated, and then the reasonable degree of the second user electric charge data is as follows:
R＝α·E Odm +β·E Tsam
wherein R is the reasonable degree of the electric charge data, E Tsam For the deviation degree from the normal user electric quantity range in the time sequence analysis model result, E Odm And alpha is a correction coefficient of the importance of the outlier detection model, and beta is a correction coefficient of the importance of the time sequence analysis model.
5. The method for analyzing and processing the automatic sales of the electric charges of the users according to claim 3 or 4, wherein the correction coefficient of the importance of the time series analysis model and the correction coefficient of the importance of the outlier detection model are dynamically updated through a training model, specifically:
acquiring analysis results of a time sequence analysis model, wherein the analysis results comprise first normal user electricity charge data and first abnormal user electricity charge data with correct analysis results, and second normal user electricity charge data and second abnormal user electricity charge data with incorrect analysis results;
acquiring analysis results of the outlier detection model, wherein the analysis results comprise first normal user electricity charge data and first abnormal user electricity charge data with correct analysis results, and second normal user electricity charge data and second abnormal user electricity charge data with incorrect analysis results;
if the second normal user electricity charge data with the wrong analysis result in the time sequence analysis model is the first abnormal user electricity charge data with the correct analysis result in the outlier detection model, the correction coefficient of the importance of the time sequence analysis model is reduced by M1, and if the second abnormal user electricity charge data with the wrong analysis result in the time sequence analysis model is the first normal user electricity charge data with the correct analysis result in the outlier detection model, the correction coefficient of the importance of the time sequence analysis model is reduced by N1, M1 and N1 are all proportional coefficients, and M1 is larger than N1;
if the second normal user electricity charge data with the incorrect analysis result in the outlier detection model is the first abnormal user electricity charge data with the correct analysis result in the time sequence analysis model, the correction coefficient of the importance of the outlier detection model is reduced by M2, and if the second abnormal user electricity charge data with the incorrect analysis result in the outlier detection model is the first normal user electricity charge data with the correct analysis result in the time sequence analysis model, the correction coefficient of the importance of the outlier detection model is reduced by N2, M2 and N2 are all proportional coefficients, and M2 is larger than N2.
6. The method for analyzing and processing automatic sales of electric charges of users according to claim 3 or 4, wherein the history data of the normal electric quantity range is updated, specifically:
in the time sequence analysis model, a fitting curve is constructed by taking time for acquiring user electricity charge data as an abscissa and a user electricity quantity value as an ordinate, a reasonable range is set to be S (1+/-r), S is a value of the fitting curve, r is a corrected percentage coefficient, for a certain user electricity quantity value exceeding the reasonable range, a value of the fitting curve corresponding to the user electricity quantity value is acquired, a tangential slope of the fitting curve at the time point is calculated, if the absolute value of the tangential slope of the fitting curve at the time point does not exceed 120% of the maximum value in the tangential slope absolute values of all other remaining time points, the user electricity quantity value is reserved, r value is increased, and if the absolute value of the tangential slope of the fitting curve at the time point exceeds 120% of the maximum value in the tangential slope absolute values of all other remaining time points, the user electricity quantity value is deleted, the fitting curve is reconstructed, and r value is unchanged.
7. The method for analyzing and processing automatic sales of electric charges of users according to claim 3 or 4, wherein the history data of the passing of the normal electric quantity range of the users is updated, specifically:
in the outlier detection model, setting a power consumption range as [ a, b ], setting a user power value exceeding an initial power consumption range as a to-be-determined user power value, searching other user power values within a time range set after the to-be-determined user power value, and if the difference between the value of at least two user power values in the other user power values and the to-be-determined user power value is within the set range, redefining the value corresponding to the to-be-determined user power value as the upper limit or the lower limit of the power consumption range, and if the difference between the value of at most one user power value in the other user power values and the to-be-determined user power value is within the set range, keeping the power consumption range unchanged.
8. The analysis processing device of automatic sales of user's charges of electricity, characterized by includes:
the data collection module is used for acquiring the first user electricity charge data and sending the first user electricity charge data to the data analysis module;
the data analysis module is used for analyzing the first user electricity charge data and finding out abnormal data;
the data judging module is used for judging the abnormal data and recovering part of the abnormal data into normal data according to the judgment;
and the deduction Fei Xiaozhang module is used for acquiring the electricity fee data of the normal user and carrying out deduction and billing.
9. A storage medium having stored therein a computer program for implementing the method of any one of claims 1 to 7 when executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310422532.3A CN116433402B (en) | 2023-04-11 | 2023-04-11 | Analysis processing device, method and storage medium for automatic sales of user electricity fees |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310422532.3A CN116433402B (en) | 2023-04-11 | 2023-04-11 | Analysis processing device, method and storage medium for automatic sales of user electricity fees |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116433402A true CN116433402A (en) | 2023-07-14 |
| CN116433402B CN116433402B (en) | 2024-03-08 |
Family
ID=87094142
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310422532.3A Active CN116433402B (en) | 2023-04-11 | 2023-04-11 | Analysis processing device, method and storage medium for automatic sales of user electricity fees |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116433402B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140358838A1 (en) * | 2013-06-04 | 2014-12-04 | International Business Machines Corporation | Detecting electricity theft via meter tampering using statistical methods |
| CN105630885A (en) * | 2015-12-18 | 2016-06-01 | 国网福建省电力有限公司泉州供电公司 | Abnormal power consumption detection method and system |
| US20180330250A1 (en) * | 2017-05-09 | 2018-11-15 | Nec Laboratories America, Inc. | Energy management system with intelligent anomaly detection and prediction |
| CN113723861A (en) * | 2021-09-13 | 2021-11-30 | 南方电网数字电网研究院有限公司 | Abnormal electricity consumption behavior detection method and device, computer equipment and storage medium |
| CN114328625A (en) * | 2021-12-29 | 2022-04-12 | 深圳供电局有限公司 | Electric charge data rescreening method and system |
| CN115905319A (en) * | 2022-11-16 | 2023-04-04 | 国网山东省电力公司营销服务中心(计量中心) | Automatic identification method and system for abnormal electricity charges of massive users |
-
2023
- 2023-04-11 CN CN202310422532.3A patent/CN116433402B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140358838A1 (en) * | 2013-06-04 | 2014-12-04 | International Business Machines Corporation | Detecting electricity theft via meter tampering using statistical methods |
| CN105630885A (en) * | 2015-12-18 | 2016-06-01 | 国网福建省电力有限公司泉州供电公司 | Abnormal power consumption detection method and system |
| US20180330250A1 (en) * | 2017-05-09 | 2018-11-15 | Nec Laboratories America, Inc. | Energy management system with intelligent anomaly detection and prediction |
| CN113723861A (en) * | 2021-09-13 | 2021-11-30 | 南方电网数字电网研究院有限公司 | Abnormal electricity consumption behavior detection method and device, computer equipment and storage medium |
| CN114328625A (en) * | 2021-12-29 | 2022-04-12 | 深圳供电局有限公司 | Electric charge data rescreening method and system |
| CN115905319A (en) * | 2022-11-16 | 2023-04-04 | 国网山东省电力公司营销服务中心(计量中心) | Automatic identification method and system for abnormal electricity charges of massive users |
Non-Patent Citations (2)
| Title |
|---|
| 王新娜;郝宁;郑爽;郭晨晨;: "基于水平迁移侦测的异常用电在线分析方法", 电气自动化, no. 06, 30 November 2016 (2016-11-30), pages 108 * |
| 王新娜;郝宁;郑爽;郭晨晨;: "基于水平迁移侦测的异常用电在线分析方法", 电气自动化, no. 06, pages 108 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116433402B (en) | 2024-03-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109034244B (en) | Line loss abnormity diagnosis method and device based on electric quantity curve characteristic model | |
| CN104811344A (en) | Network dynamic service monitoring method and apparatus | |
| CN109583729B (en) | Data processing method and device for platform online model | |
| CN113723861A (en) | Abnormal electricity consumption behavior detection method and device, computer equipment and storage medium | |
| CN114662602A (en) | Outlier detection method and device, electronic equipment and storage medium | |
| CN116433402B (en) | Analysis processing device, method and storage medium for automatic sales of user electricity fees | |
| CN112565422B (en) | Method, system and storage medium for identifying fault data of power internet of things | |
| CN116434425B (en) | Electricity charge data acquisition method, acquisition equipment and storage medium | |
| CN111681094B (en) | Method and device for monitoring resource policy abnormality and electronic equipment | |
| CN116258484B (en) | Method, device, terminal equipment and medium for generating predictive operation and maintenance scheme of equipment | |
| CN114721326B (en) | Marketing inspection information processing method and device based on deep learning algorithm | |
| CN116452242A (en) | Game profit prediction method, device and equipment based on fitting regression | |
| CN116228225A (en) | Matching method and system for automatic matching wallet by online recharging | |
| CN114037285A (en) | Distribution network automation application success analysis method and related system | |
| CN115130577A (en) | Method and device for identifying fraudulent number and electronic equipment | |
| CN111835281B (en) | Solar charging fault detection method and device and readable storage medium | |
| CN113743532B (en) | Abnormality detection method, abnormality detection device, abnormality detection apparatus, and computer storage medium | |
| CN116843489B (en) | Engineering financial accounting method and system based on multi-system linkage | |
| CN114648025B (en) | Power grid data processing method and system based on multi-dimensional evolution diagram in power field | |
| CN110880101A (en) | Data processing method, device, server and storage medium thereof | |
| US20030074308A1 (en) | System and method for optimizing collection from skip accounts | |
| CN117076894B (en) | Supply chain risk overall process monitoring prevention and control management method and management system | |
| CN116861101B (en) | Data processing method and device for social matching | |
| CN116777305A (en) | Power data quality improving method and device, electronic equipment and storage medium | |
| KR20240012048A (en) | Apparatus and method for estimating outage damage cost, computer program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |