CN113723861A - Abnormal electricity consumption behavior detection method and device, computer equipment and storage medium - Google Patents
Abnormal electricity consumption behavior detection method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN113723861A CN113723861A CN202111069926.2A CN202111069926A CN113723861A CN 113723861 A CN113723861 A CN 113723861A CN 202111069926 A CN202111069926 A CN 202111069926A CN 113723861 A CN113723861 A CN 113723861A
- Authority
- CN
- China
- Prior art keywords
- electric quantity
- data
- evaluated
- user
- quantity data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000005611 electricity Effects 0.000 title claims abstract description 98
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 95
- 238000001514 detection method Methods 0.000 title claims abstract description 46
- 230000006399 behavior Effects 0.000 claims abstract description 70
- 238000000034 method Methods 0.000 claims abstract description 50
- 239000013598 vector Substances 0.000 claims description 85
- 230000011218 segmentation Effects 0.000 claims description 31
- 230000015654 memory Effects 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 13
- 230000005856 abnormality Effects 0.000 claims description 6
- 238000012937 correction Methods 0.000 claims description 6
- 238000011084 recovery Methods 0.000 claims description 3
- 230000008439 repair process Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 4
- 238000012800 visualization Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000013450 outlier detection Methods 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000013079 data visualisation Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 230000003068 static effect 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/80—Management or planning
- Y02P90/82—Energy audits or management systems therefor
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Theoretical Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to a method and a device for detecting abnormal electricity utilization behaviors, computer equipment and a storage medium. The method comprises the following steps: acquiring electric quantity data of a user to be evaluated; the electric quantity data comprises current data, phase angle data and electric energy data; determining an electricity utilization curve to be evaluated according to the electric energy data, and correcting a user file of a user to be evaluated when the similarity between the electricity utilization curve to be evaluated and an industry standard curve is lower than a preset similarity threshold; acquiring electric quantity data to be detected corresponding to the segmented time sequence from the electric quantity data, and determining whether an outlier exists in the electric quantity data to be detected; and determining whether the user to be evaluated has abnormal electricity utilization behavior according to the detection results of the outliers respectively detected by the plurality of segmented time sequences. By adopting the method, the abnormal electricity utilization behavior can be detected more accurately.
Description
Technical Field
The application relates to the technical field of power internet of things, in particular to a method and a device for detecting abnormal power utilization behaviors, computer equipment and a storage medium.
Background
With the rapid development of the power internet of things technology, the application of the metering automation system is more and more popular. The metering automation system is applied to the server, and monitors the power utilization condition of each user according to the collected power data by acquiring the power data of the user from the metering terminal.
In a traditional technical scheme, a corresponding power utilization curve to be evaluated is generally determined according to power data of a user to be evaluated, similarity comparison is carried out on the power utilization curve to be evaluated and an industry standard curve, and when the similarity of the power utilization curve to be evaluated and the industry standard curve is lower than a preset similarity threshold value, it is judged that the user to be evaluated has abnormal power utilization behaviors. However, the similarity between the power consumption curve to be evaluated of the user to be evaluated and the industry standard curve is low due to various reasons, and according to the current technical scheme, misjudgment on the abnormal power consumption behavior may be caused, that is, the detection of the abnormal power consumption behavior is inaccurate.
Therefore, how to improve the accuracy of detecting abnormal electricity consumption behavior is a technical problem that needs to be solved by those skilled in the art.
Disclosure of Invention
In view of the above, it is desirable to provide an abnormal electricity behavior detection method, an abnormal electricity behavior detection apparatus, a computer device, and a storage medium, which can improve the accuracy of abnormal electricity behavior detection.
A method of abnormal electricity usage behavior detection, the method comprising:
acquiring electric quantity data of a user to be evaluated; wherein the electric quantity data comprises current data, phase angle data and electric energy data;
determining an electricity utilization curve to be evaluated according to the electric energy data, and correcting a user file of the user to be evaluated when the similarity between the electricity utilization curve to be evaluated and an industry standard curve is lower than a preset similarity threshold;
acquiring electric quantity data to be detected corresponding to the segmented time sequence from the electric quantity data, and determining whether an outlier exists in the electric quantity data to be detected;
and determining whether the user to be evaluated has abnormal electricity utilization behavior according to the detection results of the outliers respectively detected by the segmented time sequences.
In one embodiment, the determining whether the user to be evaluated has an abnormal power consumption behavior according to the detection results of the outliers respectively detected by the plurality of segment time series includes:
determining the total number of abnormal time sequences according to the number of the segmented time sequences with outliers in the plurality of segmented time sequences;
when the total number of the abnormal time sequences is larger than a preset number threshold, judging that the user to be evaluated has abnormal electricity utilization behavior;
otherwise, judging that the electric quantity data of the user to be evaluated is sporadic abnormality.
In one embodiment, the process of obtaining the to-be-measured electric quantity data corresponding to the segmented time series from the electric quantity data and determining whether the to-be-measured electric quantity data has the outlier includes:
determining a segmentation time sequence through a sliding time window, and acquiring electric quantity data to be detected corresponding to the segmentation time sequence from the electric quantity data;
calculating the norm difference between the electric quantity data to be detected corresponding to the segmented time sequence and the norm difference between the adjacent segmented time sequences;
determining corresponding statistical characteristics according to the norm and the norm difference;
determining a corresponding first feature vector according to the statistical features, and reconstructing the first feature vector into a second feature vector;
and determining whether the outlier exists in the electric quantity data to be detected in the corresponding segmented time sequence according to whether the reconstruction error of the first characteristic vector and the second characteristic vector is larger than a preset error threshold.
In one embodiment, after the determining that the power data of the user to be evaluated is sporadically abnormal, the method further includes:
and performing data restoration on the detected electric quantity data corresponding to the outliers.
In one embodiment, the process of performing data recovery on the detected electric quantity data corresponding to the outlier includes:
acquiring a preset number of adjacent electric quantity data adjacent to the outlier;
and determining the average value of the adjacent electric quantity data of the preset quantity, and performing data restoration on the electric quantity data of the outliers by using the average value.
In one embodiment, the determining, according to the electric energy data, an electricity consumption curve to be evaluated, and modifying, when a similarity between the electricity consumption curve to be evaluated and an industry standard curve is lower than a preset similarity threshold, a user profile of the user to be evaluated includes:
determining the power utilization curve to be evaluated according to the electric energy data;
when the similarity between the power utilization curve to be evaluated and the industry standard curve is lower than the preset similarity threshold, performing word segmentation on the user name in the user file of the user to be evaluated, and converting according to word segmentation results to obtain target word vectors;
determining a target industry classification corresponding to the target word vector according to the similarity between the target word vector and each preset word vector and the corresponding relation between each preset word vector and each preset industry classification;
and if the industry classification in the user file is inconsistent with the target industry classification, modifying the user file according to the target industry classification.
In one embodiment, the method further comprises:
and visually displaying the repaired electric quantity data and/or the corrected user profile.
An abnormal electricity usage behavior detection apparatus, the apparatus comprising:
the acquisition module is used for acquiring the electric quantity data of the user to be evaluated; wherein the electric quantity data comprises current data, phase angle data and electric energy data;
the correction module is used for determining an electricity utilization curve to be evaluated according to the electric energy data and correcting the user file of the user to be evaluated when the similarity between the electricity utilization curve to be evaluated and the industry standard curve is lower than a preset similarity threshold;
the determining module is used for acquiring the electric quantity data to be detected corresponding to the segmented time sequence from the electric quantity data and determining whether the outliers exist in the electric quantity data to be detected;
and the judging module is used for determining whether the user to be evaluated has abnormal power utilization behavior according to the detection results of the outliers respectively detected by the plurality of segmented time sequences.
A computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
acquiring electric quantity data of a user to be evaluated; wherein the electric quantity data comprises current data, phase angle data and electric energy data;
determining an electricity utilization curve to be evaluated according to the electric energy data, and correcting a user file of the user to be evaluated when the similarity between the electricity utilization curve to be evaluated and an industry standard curve is lower than a preset similarity threshold;
acquiring electric quantity data to be detected corresponding to the segmented time sequence from the electric quantity data, and determining whether an outlier exists in the electric quantity data to be detected;
and determining whether the user to be evaluated has abnormal electricity utilization behavior according to the detection results of the outliers respectively detected by the segmented time sequences. A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:
acquiring electric quantity data of a user to be evaluated; wherein the electric quantity data comprises current data, phase angle data and electric energy data;
determining an electricity utilization curve to be evaluated according to the electric energy data, and correcting a user file of the user to be evaluated when the similarity between the electricity utilization curve to be evaluated and an industry standard curve is lower than a preset similarity threshold;
acquiring electric quantity data to be detected corresponding to the segmented time sequence from the electric quantity data, and determining whether an outlier exists in the electric quantity data to be detected;
and determining whether the user to be evaluated has abnormal electricity utilization behavior according to the detection results of the outliers respectively detected by the segmented time sequences.
According to the abnormal electricity consumption behavior detection method, the abnormal electricity consumption behavior detection device, the computer equipment and the storage medium, in the method, when the similarity between the electricity consumption curve to be evaluated and the industry standard curve is lower than a preset similarity threshold, the user file of the user to be evaluated is corrected, after misjudgment of the abnormal electricity consumption behavior of the user caused by the abnormality of the user file is eliminated, whether an outlier exists in the electricity quantity data to be detected corresponding to the segmented time sequence is further determined, so that a time point which is inconsistent with the normal electricity consumption behavior in the electricity quantity data is obtained, and whether the abnormal electricity consumption behavior exists in the user to be evaluated is determined according to detection results of the outlier respectively detected by the segmented time sequences.
Drawings
FIG. 1 is a diagram illustrating an exemplary embodiment of an application environment of a method for detecting abnormal power consumption;
FIG. 2 is a flowchart illustrating a method for detecting abnormal electricity usage according to an embodiment;
FIG. 3 is a schematic flow chart illustrating a method for detecting abnormal electricity consumption in another embodiment;
FIG. 4 is a block diagram showing the structure of an abnormal electricity consumption behavior detection apparatus according to an embodiment;
FIG. 5 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The abnormal electricity consumption behavior detection method provided by the application can be applied to the application environment shown in fig. 1. Wherein the server 102 and the metering terminal 104 communicate over a network. Specifically, the server 102 refers to a device for performing statistical analysis on electric quantity data in an electric power internet of things, and may be implemented by an independent server or a server cluster formed by a plurality of servers, or may be implemented by various personal computers, notebook computers, tablet computers, and the like, and the metering terminal 104 refers to a device for acquiring electric quantity data of each user, such as an intelligent electric meter, a load management terminal, a distribution transformer monitoring metering terminal, and the like; in practical applications, the metering terminals 104 may be arranged at a plurality of different positions to collect the power data, so as to perform statistical analysis on the power data collected by the plurality of metering terminals 104 by using the server 102.
In one embodiment, as shown in fig. 2, a method for detecting abnormal electricity consumption behavior is provided, which is described by taking the method as an example applied to the server in fig. 1, and includes the following steps:
step 202, acquiring electric quantity data of a user to be evaluated; the electric quantity data comprises current data, phase angle data and electric energy data.
Specifically, the user to be evaluated refers to a user who needs to perform abnormal electricity consumption behavior detection, and the user to be evaluated in this embodiment generally refers to a company enterprise user. The electric quantity data refers to data representing the electricity utilization condition of a user. Generally, the electric quantity data includes current data, phase data and electric energy data; wherein, the current data refers to the magnitude of the electricity utilization current; the phase is a physical quantity reflecting the state of the alternating current, and the phase data refer to the direction of the alternating current corresponding to the acquisition time; the electric energy data refers to the daily electricity consumption of the user; in other embodiments, the electric quantity data may further include other information, which is not limited in this embodiment.
In this embodiment, the electric quantity data of the user to be evaluated may be collected through the metering terminal and sent to the server, so that the server obtains the electric quantity data of the user to be evaluated; more specifically, in a specific implementation manner, the metering terminal acquires current data, phase data and electric energy data of 96 points of a user to be evaluated at intervals of 15 minutes; moreover, the metering terminal sends the electric quantity data to the server in a WIFI, operation network or NFC (near field communication) manner, which is not limited in this embodiment.
In addition, after the electric quantity data is acquired, preprocessing operation can be performed on the acquired electric quantity data, including format conversion on the electric quantity data, removal of each vacancy value in the electric quantity data, normalization processing on the electric quantity data, and the like, and then the preprocessed electric quantity data is used for processing and analyzing, so that the accuracy of detecting abnormal electric behavior can be further improved.
And 204, determining a power consumption curve to be evaluated according to the electric energy data, and correcting the user file of the user to be evaluated when the similarity between the power consumption curve to be evaluated and the industry standard curve is lower than a preset similarity threshold.
Specifically, in this step, the power consumption curve to be evaluated is determined by using the power data, that is, each power data is fitted to a corresponding curve according to the collection time sequence of each power data, and the curve can visually represent the change of the power consumption of the user to be evaluated along with the change of time.
In addition, acquiring an industry standard curve corresponding to the industry of the user to be evaluated; specifically, the standard power utilization curve is obtained by clustering power utilization curves of different industries, and each industry can be clustered to obtain one or more industry standard curves.
Calculating the similarity between the power consumption curve to be evaluated and an industry standard curve corresponding to the industry to which the power consumption curve belongs, specifically, determining the similarity between the power consumption curve to be evaluated and the industry standard curve by calculating an Euclidean distance, a cosine distance and the like, wherein the method for calculating the similarity is not limited; moreover, when the similarity of the two is calculated by calculating the Euclidean distance, the smaller the Euclidean distance is, the higher the similarity is; when the calculated similarity is lower than a preset similarity threshold, namely the Euclidean distance exceeds the preset threshold, the electric quantity data of the user to be evaluated may have a problem.
It can be understood that the user profile of the user to be evaluated may be pre-stored in the server, or may be obtained from the metering terminal when the electric quantity data is collected, which is not limited in this embodiment. The abnormal file is one of the main reasons for low similarity between the power consumption curve to be evaluated and the industry standard curve, and the abnormal file can be caused by false alarm of a user or error and omission in server statistics, so that the user file of the user to be evaluated is corrected when the similarity between the power consumption curve to be evaluated and the industry standard curve is determined to be lower than a preset similarity threshold.
And step 206, acquiring the electric quantity data to be detected corresponding to the segmented time sequence from the electric quantity data, and determining whether the electric quantity data to be detected has outliers.
Specifically, first, a segment time sequence is determined, for example, T1 to T2 are a segment time sequence, and T2 to T3 are a segment time sequence; according to the corresponding relation between the time point corresponding to each electric quantity data and the corresponding segmented time sequence, determining the electric quantity data to be detected corresponding to each segmented time sequence from the electric quantity data; and then judging whether the electric quantity data to be detected in each segmented time sequence has an outlier.
It should be noted that, in the case of ensuring that the user profile is correct, the cause of the abnormal electricity quantity data may be the existence of an outlier in the electricity quantity data, where the outlier detection is to find out a time point in the electricity quantity data that is inconsistent with the normal electricity consumption behavior. In this step, it is further determined whether an outlier exists in the to-be-measured electric quantity data corresponding to the segmented time series. Specifically, the electric quantity data to be measured in the segment time sequence may be clustered, or whether an outlier exists in the electric quantity data to be measured may be determined by calculating a reconstruction error, which is not limited in this embodiment.
And step 208, determining whether the user to be evaluated has abnormal electricity utilization behavior according to the detection results of the outliers respectively detected by the plurality of segmented time sequences.
Specifically, the abnormal electricity consumption behavior refers to an abnormal electricity consumption behavior of the user, such as an electricity stealing behavior of the user; in actual operation, acquiring a plurality of segment time sequences, and respectively determining detection results of outliers corresponding to electric quantity data to be detected in each segment time sequence, wherein the detection results comprise the existence of the outliers or the absence of the outliers; and judging whether the number of the outliers in the electric quantity data reaches the condition for determining the abnormal electricity utilization behavior according to the detection result of the outliers determined in each segmented time sequence. It should be noted that, in this embodiment, the specific number of the segment time sequences is generally set according to practical experience, and is generally two or more, which is not limited in this embodiment.
In the abnormal electricity consumption behavior detection method, when the similarity between the electricity consumption curve to be evaluated and the industry standard curve is lower than a preset similarity threshold, the user file of the user to be evaluated is corrected, after the misjudgment of the abnormal electricity consumption behavior of the user caused by the abnormal user file is eliminated, whether the outlier exists in the electricity consumption data to be evaluated corresponding to the segmented time sequence is further determined, so that the time point in the electricity consumption data, which is inconsistent with the normal electricity consumption behavior, is obtained, and whether the abnormal electricity consumption behavior exists in the user to be evaluated is determined according to the detection results of the outlier respectively detected by the segmented time sequences, so that the method can more accurately detect the abnormal electricity consumption behavior.
Fig. 3 is a flowchart of another abnormal electricity consumption behavior detection method according to an embodiment of the present invention; on the basis of the foregoing embodiment, this embodiment further describes and optimizes the technical solution, and specifically, in this embodiment, a process of determining whether the user to be evaluated has an abnormal power consumption behavior according to detection results of outliers respectively detected by a plurality of segment time sequences includes:
determining the total number of the abnormal time sequences according to the number of the segmented time sequences with outliers in the plurality of segmented time sequences;
when the total number of the abnormal time sequences is larger than a preset number threshold, judging that the abnormal power utilization behavior exists in the user to be evaluated;
otherwise, judging that the electric quantity data of the user to be evaluated is sporadic abnormality.
Specifically, in this embodiment, after determining whether each segment time sequence has an outlier, the number of segment time sequences having an outlier in the plurality of segment time sequences is counted, and the total number of abnormal time sequences is determined; in addition, a preset number threshold value is set, namely a limit value of the total number of the abnormal time sequences; comparing the total number of the abnormal time sequences with a preset number threshold, and when the total number of the abnormal time sequences is greater than the preset number threshold, indicating that an abnormal condition exists in the electric quantity data of the user to be evaluated for a long time, so that the user to be evaluated is judged to have an abnormal electricity utilization behavior; and if not, indicating that the electric quantity data of the user to be evaluated is sporadically abnormal.
It should be noted that, in actual operation, after it is determined that the user to be evaluated has the abnormal electricity consumption behavior, the abnormal electricity consumption behavior may be further recorded; for example, the detection time when the abnormal electricity consumption behavior is detected is recorded, and the abnormal segment time sequence corresponding to the abnormal electricity consumption behavior is recorded, so that data tracing can be performed on the abnormal electricity consumption behavior in the following.
Therefore, in the embodiment, whether the user to be evaluated has the abnormal electricity utilization behavior is determined by comparing the total number of the abnormal time sequences with the preset number threshold, and the judgment process is accurate and convenient.
On the basis of the foregoing embodiment, this embodiment further describes and optimizes the technical solution, specifically, a process of obtaining the electric quantity data to be measured corresponding to the segment time sequence from the electric quantity data and determining whether the outlier exists in the electric quantity data to be measured includes:
determining a segmentation time sequence through a sliding time window, and acquiring electric quantity data to be detected corresponding to the segmentation time sequence from the electric quantity data;
calculating the norm difference between the electric quantity data to be detected corresponding to the segmented time sequence and the norm of the adjacent segmented time sequence;
determining corresponding statistical characteristics according to the norm and the norm difference;
determining a corresponding first feature vector according to the statistical features, and reconstructing the first feature vector into a second feature vector;
and determining whether the outlier exists in the electric quantity data to be detected in the corresponding segmented time sequence according to whether the reconstruction errors of the first characteristic vector and the second characteristic vector are larger than a preset error threshold.
In this embodiment, the electric quantity data includes current data, phase angle data, and electric energy data, that is, the electric quantity data is a multi-dimensional time series, and therefore, an outlier detection algorithm of the multi-dimensional time series is used to determine whether an outlier exists in the electric quantity data to be detected in the segmented time series.
Specifically, firstly, setting the window size of a sliding time window, wherein the window size is the time length of a segmented time sequence; and determining the segmented time sequence through the sliding time window, and acquiring the electric quantity data to be detected corresponding to the segmented time sequence from the electric quantity data. More specifically, each sliding time window corresponds to a segment time sequence Tw＝{S1，S2，…，Si，…，SwIn which S isi＝(Ii，φi，Pi) A group of data S of electric quantity to be measured corresponding to the moment ii，IiRepresents the current data, phi, corresponding to the time point iiRepresenting phase data, P, corresponding to a point in time iiAnd representing the electric energy data corresponding to the time point i.
Then, calculating the norm difference between the electric quantity data to be measured corresponding to the segmented time sequence and the norm of the adjacent segmented time sequence; more particularly, according to
Calculating the norm of the electric quantity data to be measured in the segmented time sequence, wherein N istRepresenting the norm of the t (1 ≦ t ≦ w) th segmented time series; according to dN ═ Nt+1-NtCalculating the norm difference of adjacent segmented time series, wherein dNt(1. ltoreq. t. ltoreq.w) denotes the N-tht+1And NtThe norm difference of the two adjacent segmented time series.
Will calculateTaking the obtained norm and the norm difference as a first-order feature G of the electric quantity data to be detected of the segmented time sequence, extracting a statistical feature of the first-order feature G as a second-order feature, and obtaining a feature matrix H; the statistical characteristics include mean, maximum, minimum, standard deviation, and the like. Splicing the feature matrix H according to rows to obtain a first feature vector F, and reconstructing the first feature vector F into a second feature vector through a self-encoder
Then the first feature vector F and the second feature vector F
The reconstruction error of (2); comparing the reconstruction error with a preset error threshold; if the calculated reconstruction error is larger than a preset error threshold value, indicating that an outlier exists in the electric quantity data to be detected in the segmented time sequence; otherwise, it indicates that no outlier exists in the electric quantity data to be measured in the segmented time sequence.
It should be noted that the self-encoder is an unsupervised learning method suitable for identifying outliers, and whether the outliers exist can be judged by comparing the deviation between the original input data and the reconstructed data; the self-encoder can be particularly an LSTM (Long Short-Term Memory Network) self-encoder, the LSTM is a special convolutional Neural Network, and the self-encoder has the advantages that the Long-Term dependence problem of a common RNN (Recurrent Neural Network) can be solved, and the self-encoder is suitable for measuring a time sequence curve; the LSTM self-encoder is realized by encoding and decoding, wherein the encoding process comprises converting the first feature vector F into an intermediate vector with a fixed dimension, and the decoding process comprises converting the intermediate vector obtained by encoding into a feature vector to obtain a second feature vector
As can be seen, in the embodiment, by determining the statistical characteristics in the segment time sequence, the corresponding first feature vector is determined according to the statistical characteristics, and the first feature vector is reconstructed into the second feature vector; determining whether an outlier exists in the electric quantity data to be detected in the corresponding segmented time sequence according to whether the reconstruction errors of the first eigenvector and the second eigenvector are larger than a preset error threshold value; whether the outliers exist or not is determined according to the reconstruction error, and the method can be more accurate.
On the basis of the foregoing embodiment, the present embodiment further describes and optimizes the technical solution, and specifically, after determining that the electric quantity data of the user to be evaluated is sporadic abnormal, the method further includes:
and performing data restoration on the detected electric quantity data corresponding to the outliers.
Specifically, in this embodiment, when it is determined that the electric quantity data of the user to be evaluated is sporadic and abnormal, that is, the electric quantity data of the time point corresponding to the outlier in the electric quantity data is incorrect, the electric quantity data corresponding to the outlier is replaced by the determined electric quantity restoration value by determining a more accurate electric quantity restoration value, so that data restoration is performed on the electric quantity data of the outlier.
As a preferred embodiment, the process of performing data recovery on the electric quantity data corresponding to the detected outlier includes:
acquiring adjacent electric quantity data of a preset quantity adjacent to the outlier;
and determining the average value of the adjacent electric quantity data of the preset quantity, and performing data restoration on the electric quantity data of the outliers by using the average value.
In the present embodiment, data restoration is performed by a sample moving average method, and the moving average method is a method for predicting electric quantity data at an outlier by using a group of electric quantity data closest to the outlier, that is, an average value of adjacent electric quantity data. Specifically, the adjacent electric quantity data refers to electric quantity data at a time point close to an outlier in a time sequence, specifically, the adjacent electric quantity data may be a preset number of adjacent electric quantity data before the outlier or a preset number of adjacent electric quantity data after the outlier, or a part of data may be respectively taken before the outlier and after the outlier, and the sum of the data quantities is a preset number; after a preset number of adjacent electric quantity data adjacent to the outlier are obtained, calculating an average value of the obtained preset number of adjacent electric quantity data, taking the average value as an electric quantity restoration value, and performing data restoration on the electric quantity data of the outlier by using the average value.
In a specific implementation mode, data restoration is performed on the electric quantity data by using a moving average method, and an electric quantity restoration value is calculated by using the following calculation formula:
wherein E isrAs a power restoration value, EdThe electric quantity data of the time point corresponding to the outlier, namely the predicted actual electric quantity data corresponding to the outlier; n is the number of periods of movement; ed-1The electric quantity data is the electric quantity data of a time point before the outlier; ed-2The electric quantity data of two time points before the outlier is obtained; ed-NThe electric quantity data of N time points before the outlier is obtained; assuming that N is set to 7, that is, historical data of near 7 days is used as adjacent electric quantity data, and electric quantity data at a time point corresponding to an outlier is restored by an average value of the adjacent electric quantity data of the 7 days.
In addition, in actual operation, after the data of the electric quantity data at the outlier is repaired, a repair identifier may be further added at the outlier to identify that the electric quantity data at the time point is obtained through data repair.
Therefore, in the embodiment, the average value of the adjacent electric quantity data adjacent to the outlier is adopted to repair the electric quantity data of the outlier, so that the accuracy of the electric quantity repair value can be relatively guaranteed.
On the basis of the above embodiment, this embodiment further describes and optimizes the technical solution, specifically, a process of determining an electricity consumption curve to be evaluated according to the electric energy data, and correcting a user profile of a user to be evaluated when a similarity between the electricity consumption curve to be evaluated and an industry standard curve is lower than a preset similarity threshold includes:
determining an electricity utilization curve to be evaluated according to the electric energy data;
when the similarity between the power utilization curve to be evaluated and the industry standard curve is lower than a preset similarity threshold value, performing word segmentation on the user name in the user file of the user to be evaluated, and converting according to word segmentation results to obtain a target word vector;
determining a target industry classification corresponding to the target word vector according to the similarity between the target word vector and each preset word vector and the corresponding relation between each preset word vector and each preset industry classification;
and if the industry classification in the user file is inconsistent with the target industry classification, modifying the user file according to the target industry classification.
Pre-sorting industries to be classified to obtain a corresponding industry library; the industry library comprises preset word vectors and preset industry classifications, and the corresponding relation between the preset word vectors and the preset industry classifications is set, so that the corresponding industry classifications can be determined according to a certain word vector. In actual operation, industry classification codes corresponding to various industry classifications can be further set, namely, the corresponding relation among the word vectors, the industry classifications and the industry classification codes is set.
In the embodiment, after the power consumption curve to be evaluated is determined according to the electric energy data, the similarity between the power consumption curve to be evaluated and the industry standard curve is calculated, when the similarity is lower than a preset similarity threshold value, word segmentation and industry name extraction are performed on the user name through automatic inspection, and the steps of word segmentation, filtering, word vector generation, similarity matching and the like are automatically inspected.
More specifically, the user name in the user profile of the user to be evaluated may be segmented by using jieba segmentation, for example, the segmentation of "china telecommunication company, cloud computing, and guizhou segmentation" may result in the segmentation result being "china/telecommunication/share/limited/company/cloud computing/guizhou/segmentation"; then, filtering the word segmentation result, and removing word segmentation results which are irrelevant to industries, such as a preset region, shares, a limit and the like, wherein the filtered word segmentation result is 'telecommunication/cloud computing'; performing word vector generation on the filtered word segmentation result, converting the word segmentation result into a corresponding target word vector by adopting word2vec, and converting words in the word segmentation result into a corresponding mathematical vector; after corresponding target word vectors are obtained according to word segmentation results, the similarity between the target word vectors and each preset word vector is calculated, the preset word vectors with the highest similarity with the target word vectors are determined, the preset industry classifications corresponding to the preset word vectors are determined, the preset industry classifications are determined as target industry classifications, and the target industry classifications corresponding to the target word vectors are obtained; then comparing the target industry classification with the industry classification in the user file, if the target industry classification is consistent with the industry classification in the user file, indicating that the industry classification in the user file is correct; otherwise, the industry classification in the user profile is incorrect, so the industry classification in the user profile is modified by the target industry classification.
More specifically, when calculating the similarity between the target word vector and each preset word vector, the text similarity between the target word vector and each preset word vector may be calculated by calculating the cosine distance, euclidean distance, Jaccard distance, or edit distance between the target word vector and each preset word vector, assuming that the target word vector is L1 and the preset word vector is L2, and the cosine distance d between the target word vector and each preset word vector is (L1 · L2)/(| L1 |. x | L2|), the smaller the cosine distance, the higher the similarity between the target word vector and each preset word vector is, the more similar the two vectors are. In this way, the word segmentation result of the target word vector "telecom/cloud computing" can be matched to the industry classification of "information transmission, software and information technology service industry".
In addition, in order to further improve the accuracy of modifying the user profile, before the user profile is modified, manual verification can be further performed, and after the manual verification is correct, the industry classification in the user profile is modified by using the target industry classification. After the user file is corrected, the corresponding industry standard curve needs to be re-determined according to the industry classification in the user file, and then the similarity between the power utilization curve to be evaluated and the industry standard curve is re-calculated based on the re-determined industry standard curve.
It should be noted that, if the similarity between the target word vector and each preset word vector is lower than the minimum similarity value, the target industry classification corresponding to the target word vector cannot be determined, and therefore, it is also possible to manually check whether the user profile is abnormal.
Therefore, the user file is corrected according to the method of the embodiment, so that the workload of manual operation can be reduced, the repair is accurate, and the repair efficiency is high.
On the basis of the above embodiment, the embodiment further describes and optimizes the technical solution, and specifically, the method further includes:
and visually displaying the repaired electric quantity data and/or the corrected user file.
Specifically, visualization refers to converting data into graphics or images to be displayed on a screen by using computer graphics and image processing technology; in this embodiment, after the electric quantity data is repaired, the repaired electric quantity data is visually displayed, and/or after the user profile is corrected, the user profile is visually displayed.
More specifically, in actual operation, a visualization worksheet made by Tableau may be used to implement data visualization display, and the specific visualization display manner is not limited in this embodiment. In a specific implementation mode, electric quantity data are collected, the electric quantity data comprise current data, phase data and electric energy data, after data restoration is carried out on the electric quantity data, data curves corresponding to various types of data are respectively determined, and visual display is carried out on the data curves, so that the electric quantity data can be displayed more visually.
In addition, the electric quantity data can be screened through the time screener, the electric quantity data of the target time period are screened, a data curve of the electric quantity data corresponding to the target time period is generated, and visual display is conducted on the electric quantity data of the target time period.
In addition, if the similarity between the power utilization curve to be evaluated and the industry standard power utilization curve is determined not to be equal to the preset similarity threshold, the power utilization curve to be evaluated and the industry standard power utilization curve can be directly displayed in a visualized mode.
In addition, the electric quantity data before restoration and the electric quantity data after restoration can be compared and displayed, the user file before correction and the user file after correction are compared and displayed, and the restored electric quantity data and/or the corrected user file are identified, so that the restoration condition of the electric quantity data and/or the correction condition of the user file can be displayed more intuitively.
It should be understood that, although the steps in the flowcharts related to the above embodiments are shown in sequence as indicated by the arrows, the steps are not necessarily executed in sequence as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a part of the steps in each flowchart related to the above embodiments may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of performing the steps or stages is not necessarily sequential, but may be performed alternately or alternately with other steps or at least a part of the steps or stages in other steps.
In one embodiment, as shown in fig. 4, there is provided an abnormal electricity usage behavior detection apparatus including:
an obtaining module 402, configured to obtain electric quantity data of a user to be evaluated; the electric quantity data comprises current data, phase angle data and electric energy data;
the correcting module 404 is configured to determine an electricity consumption curve to be evaluated according to the electric energy data, and correct a user file of a user to be evaluated when the similarity between the electricity consumption curve to be evaluated and the industry standard curve is lower than a preset similarity threshold;
a determining module 406, configured to obtain, from the electric quantity data, electric quantity data to be detected corresponding to the segment time sequence, and determine whether an outlier exists in the electric quantity data to be detected;
the determining module 408 is configured to determine whether the user to be evaluated has an abnormal power consumption behavior according to detection results of outliers respectively detected by the multiple segment time sequences.
The abnormal electricity consumption behavior detection device provided by the embodiment of the invention has the same beneficial effects as the abnormal electricity consumption behavior detection method.
In one embodiment, the determining module comprises:
the first determining submodule is used for determining the total number of the abnormal time sequences according to the number of the segmented time sequences with outliers in the segmented time sequences;
the first judgment submodule is used for judging that the abnormal electricity utilization behavior exists in the user to be evaluated when the total number of the abnormal time sequences is larger than a preset number threshold;
and the second judging submodule is used for judging the electric quantity data of the user to be evaluated as accidental abnormality when the total number of the abnormal time sequences is less than or equal to a preset number threshold.
In one embodiment, the determining module includes:
the first obtaining submodule is used for determining a segmentation time sequence through a sliding time window and obtaining electric quantity data to be detected corresponding to the segmentation time sequence from the electric quantity data;
the calculation submodule is used for calculating the norm of the electric quantity data to be measured corresponding to the segmented time sequence and the norm difference of the adjacent segmented time sequence;
the second determining submodule is used for determining corresponding statistical characteristics according to the norm and the norm difference;
the reconstruction submodule is used for determining a corresponding first feature vector according to the statistical features and reconstructing the first feature vector into a second feature vector;
and the third determining submodule is used for determining whether the outlier exists in the electric quantity data to be detected in the corresponding segmented time sequence according to whether the reconstruction error of the first characteristic vector and the second characteristic vector is larger than a preset error threshold value.
In one embodiment, the apparatus further comprises:
and the repairing module is used for performing data repairing on the detected electric quantity data corresponding to the outliers.
In one embodiment, the repair module includes:
the second obtaining submodule is used for obtaining the adjacent electric quantity data of the preset quantity adjacent to the outlier;
and the fourth determining submodule is used for determining the average value of the adjacent electric quantity data of the preset quantity and performing data restoration on the electric quantity data of the outliers by using the average value.
In one embodiment, the correction module comprises:
the fifth determining submodule is used for determining an electricity utilization curve to be evaluated according to the electric energy data;
the word segmentation sub-module is used for segmenting words of the user names in the user files of the users to be evaluated when the similarity between the power utilization curve to be evaluated and the industry standard curve is lower than a preset similarity threshold value, and converting the word segmentation result to obtain a target word vector;
the sixth determining sub-module is used for determining a target industry classification corresponding to the target word vector according to the similarity between the target word vector and each preset word vector and the corresponding relation between each preset word vector and the preset industry classification;
and the modification submodule is used for modifying the user file according to the target industry classification if the industry classification in the user file is inconsistent with the target industry classification.
In one embodiment, the apparatus further comprises:
and the visualization module is used for visually displaying the repaired electric quantity data and/or the corrected user file.
For specific limitations of the abnormal electricity consumption behavior detection device, reference may be made to the above limitations on the abnormal electricity consumption behavior detection method, and details thereof are not repeated here. All or part of each module in the abnormal electricity consumption behavior detection device can be realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 5. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing the electric quantity data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of abnormal power usage behavior detection.
Those skilled in the art will appreciate that the architecture shown in fig. 5 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:
acquiring electric quantity data of a user to be evaluated; the electric quantity data comprises current data, phase angle data and electric energy data;
determining an electricity utilization curve to be evaluated according to the electric energy data, and correcting a user file of a user to be evaluated when the similarity between the electricity utilization curve to be evaluated and an industry standard curve is lower than a preset similarity threshold;
acquiring electric quantity data to be detected corresponding to the segmented time sequence from the electric quantity data, and determining whether an outlier exists in the electric quantity data to be detected;
and determining whether the user to be evaluated has abnormal electricity utilization behavior according to the detection results of the outliers respectively detected by the plurality of segmented time sequences.
The computer equipment provided by the embodiment of the invention has the same beneficial effects as the abnormal electricity consumption behavior detection method.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring electric quantity data of a user to be evaluated; the electric quantity data comprises current data, phase angle data and electric energy data;
determining an electricity utilization curve to be evaluated according to the electric energy data, and correcting a user file of a user to be evaluated when the similarity between the electricity utilization curve to be evaluated and an industry standard curve is lower than a preset similarity threshold;
acquiring electric quantity data to be detected corresponding to the segmented time sequence from the electric quantity data, and determining whether an outlier exists in the electric quantity data to be detected;
and determining whether the user to be evaluated has abnormal electricity utilization behavior according to the detection results of the outliers respectively detected by the plurality of segmented time sequences.
The computer-readable storage medium provided by the embodiment of the invention has the same beneficial effects as the abnormal electricity consumption behavior detection method.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. An abnormal electricity consumption behavior detection method, characterized by comprising:
acquiring electric quantity data of a user to be evaluated; wherein the electric quantity data comprises current data, phase angle data and electric energy data;
determining an electricity utilization curve to be evaluated according to the electric energy data, and correcting a user file of the user to be evaluated when the similarity between the electricity utilization curve to be evaluated and an industry standard curve is lower than a preset similarity threshold;
acquiring electric quantity data to be detected corresponding to the segmented time sequence from the electric quantity data, and determining whether an outlier exists in the electric quantity data to be detected;
and determining whether the user to be evaluated has abnormal electricity utilization behavior according to the detection results of the outliers respectively detected by the segmented time sequences.
2. The method according to claim 1, wherein the step of determining whether the user to be evaluated has abnormal power consumption behavior according to the detection results of the outliers respectively detected from the plurality of segmented time series includes:
determining the total number of abnormal time sequences according to the number of the segmented time sequences with outliers in the plurality of segmented time sequences;
when the total number of the abnormal time sequences is larger than a preset number threshold, judging that the user to be evaluated has abnormal electricity utilization behavior;
otherwise, judging that the electric quantity data of the user to be evaluated is sporadic abnormality.
3. The method according to claim 2, wherein the process of obtaining the data of the electric quantity to be measured corresponding to the segmented time series from the data of the electric quantity and determining whether the data of the electric quantity to be measured has the outlier comprises:
determining a segmentation time sequence through a sliding time window, and acquiring electric quantity data to be detected corresponding to the segmentation time sequence from the electric quantity data;
calculating the norm difference between the electric quantity data to be detected corresponding to the segmented time sequence and the norm difference between the adjacent segmented time sequences;
determining corresponding statistical characteristics according to the norm and the norm difference;
determining a corresponding first feature vector according to the statistical features, and reconstructing the first feature vector into a second feature vector;
and determining whether the outlier exists in the electric quantity data to be detected in the corresponding segmented time sequence according to whether the reconstruction error of the first characteristic vector and the second characteristic vector is larger than a preset error threshold.
4. The method according to claim 2, wherein after the determining that the power data of the user to be evaluated is sporadic abnormality, the method further comprises:
and performing data restoration on the detected electric quantity data corresponding to the outliers.
5. The method according to claim 4, wherein the step of performing data recovery on the detected electric quantity data corresponding to the outlier comprises:
acquiring a preset number of adjacent electric quantity data adjacent to the outlier;
and determining the average value of the adjacent electric quantity data of the preset quantity, and performing data restoration on the electric quantity data of the outliers by using the average value.
6. The method according to any one of claims 1 to 5, wherein the process of determining a power consumption curve to be evaluated according to the electric energy data and correcting the user profile of the user to be evaluated when the similarity between the power consumption curve to be evaluated and an industry standard curve is lower than a preset similarity threshold comprises the following steps:
determining the power utilization curve to be evaluated according to the electric energy data;
when the similarity between the power utilization curve to be evaluated and the industry standard curve is lower than the preset similarity threshold, performing word segmentation on the user name in the user file of the user to be evaluated, and converting according to word segmentation results to obtain target word vectors;
determining a target industry classification corresponding to the target word vector according to the similarity between the target word vector and each preset word vector and the corresponding relation between each preset word vector and each preset industry classification;
and if the industry classification in the user file is inconsistent with the target industry classification, modifying the user file according to the target industry classification.
7. The method of claim 6, further comprising:
and visually displaying the repaired electric quantity data and/or the corrected user profile.
8. An abnormal electricity consumption behavior detection apparatus, characterized in that the apparatus comprises:
the acquisition module is used for acquiring the electric quantity data of the user to be evaluated; wherein the electric quantity data comprises current data, phase angle data and electric energy data;
the correction module is used for determining an electricity utilization curve to be evaluated according to the electric energy data and correcting the user file of the user to be evaluated when the similarity between the electricity utilization curve to be evaluated and the industry standard curve is lower than a preset similarity threshold;
the determining module is used for acquiring the electric quantity data to be detected corresponding to the segmented time sequence from the electric quantity data and determining whether the outliers exist in the electric quantity data to be detected;
and the judging module is used for determining whether the user to be evaluated has abnormal power utilization behavior according to the detection results of the outliers respectively detected by the plurality of segmented time sequences.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111069926.2A CN113723861A (en) | 2021-09-13 | 2021-09-13 | Abnormal electricity consumption behavior detection method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111069926.2A CN113723861A (en) | 2021-09-13 | 2021-09-13 | Abnormal electricity consumption behavior detection method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113723861A true CN113723861A (en) | 2021-11-30 |
Family
ID=78683513
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111069926.2A Pending CN113723861A (en) | 2021-09-13 | 2021-09-13 | Abnormal electricity consumption behavior detection method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113723861A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115079634A (en) * | 2022-07-15 | 2022-09-20 | 重庆中环建设有限公司 | Air compression station variable frequency speed regulation system and method based on 5G Internet of things |
| CN115409433A (en) * | 2022-11-02 | 2022-11-29 | 成都宏恒信息科技有限公司 | Depth NLP-based method and device for analyzing portrait of key community personnel |
| CN116433402A (en) * | 2023-04-11 | 2023-07-14 | 国网浙江省电力有限公司 | Analysis processing device, method and storage medium for automatic sales of user electricity fees |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103678766A (en) * | 2013-11-08 | 2014-03-26 | 国家电网公司 | Abnormal electricity consumption client detection method based on PSO algorithm |
| CN110634080A (en) * | 2018-06-25 | 2019-12-31 | 中兴通讯股份有限公司 | Abnormal electricity utilization detection method, device, equipment and computer readable storage medium |
| CN111708739A (en) * | 2020-05-21 | 2020-09-25 | 北京奇艺世纪科技有限公司 | Method and device for detecting abnormality of time series data, electronic device and storage medium |
| CN112541016A (en) * | 2020-11-26 | 2021-03-23 | 南方电网数字电网研究院有限公司 | Power consumption abnormality detection method, device, computer equipment and storage medium |
| CN113284000A (en) * | 2021-04-08 | 2021-08-20 | 南方电网数字电网研究院有限公司 | User electricity data anomaly detection method and device and computer equipment |
-
2021
- 2021-09-13 CN CN202111069926.2A patent/CN113723861A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103678766A (en) * | 2013-11-08 | 2014-03-26 | 国家电网公司 | Abnormal electricity consumption client detection method based on PSO algorithm |
| CN110634080A (en) * | 2018-06-25 | 2019-12-31 | 中兴通讯股份有限公司 | Abnormal electricity utilization detection method, device, equipment and computer readable storage medium |
| CN111708739A (en) * | 2020-05-21 | 2020-09-25 | 北京奇艺世纪科技有限公司 | Method and device for detecting abnormality of time series data, electronic device and storage medium |
| CN112541016A (en) * | 2020-11-26 | 2021-03-23 | 南方电网数字电网研究院有限公司 | Power consumption abnormality detection method, device, computer equipment and storage medium |
| CN113284000A (en) * | 2021-04-08 | 2021-08-20 | 南方电网数字电网研究院有限公司 | User electricity data anomaly detection method and device and computer equipment |
Non-Patent Citations (3)
| Title |
|---|
| 孙毅;李世豪;崔灿;李彬;陈宋宋;崔高颖;: "基于高斯核函数改进的电力用户用电数据离群点检测方法", 电网技术, no. 05, 7 December 2017 (2017-12-07) * |
| 王鹏伍;孙志杰;傅军;周国鹏;: "模糊C均值聚类算法在用电异常稽查中的应用", 华北电力技术, no. 04, 25 April 2016 (2016-04-25) * |
| 龚起航: "面向多导体系统的非侵入式电气量传感器设计与开发", 硕士论文库, no. 11, 16 October 2020 (2020-10-16) * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115079634A (en) * | 2022-07-15 | 2022-09-20 | 重庆中环建设有限公司 | Air compression station variable frequency speed regulation system and method based on 5G Internet of things |
| CN115409433A (en) * | 2022-11-02 | 2022-11-29 | 成都宏恒信息科技有限公司 | Depth NLP-based method and device for analyzing portrait of key community personnel |
| CN116433402A (en) * | 2023-04-11 | 2023-07-14 | 国网浙江省电力有限公司 | Analysis processing device, method and storage medium for automatic sales of user electricity fees |
| CN116433402B (en) * | 2023-04-11 | 2024-03-08 | 国网浙江省电力有限公司 | Analysis processing device, method and storage medium for automatic sales of user electricity fees |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113723861A (en) | Abnormal electricity consumption behavior detection method and device, computer equipment and storage medium | |
| CN108923952B (en) | Fault diagnosis method, equipment and storage medium based on service monitoring index | |
| CN112257755B (en) | Method and device for analyzing running state of spacecraft | |
| CN112416643A (en) | Unsupervised anomaly detection method and unsupervised anomaly detection device | |
| CN112862127B (en) | Sensor data exception handling method and device, electronic equipment and medium | |
| CN110333962B (en) | Electronic component fault diagnosis model based on data analysis and prediction | |
| CN110941648A (en) | Abnormal data identification method, system and storage medium based on cluster analysis | |
| US20230144809A1 (en) | Model operation support system and method | |
| CN112416662A (en) | Multi-time series data anomaly detection method and device | |
| CN115660262B (en) | Engineering intelligent quality inspection method, system and medium based on database application | |
| CN110858072B (en) | Method and device for determining running state of equipment | |
| CN111124732A (en) | Disk fault prediction method, system, device and storage medium | |
| CN114978956A (en) | Method and device for detecting abnormal performance mutation points of network equipment in smart city | |
| CN115034286A (en) | Abnormal user identification method and device based on adaptive loss function | |
| CN112016856B (en) | Comprehensive magnification abnormity identification method and device, metering system and storage medium | |
| CN111783883A (en) | Abnormal data detection method and device | |
| CN117036732A (en) | Electromechanical equipment detection system, method and equipment based on fusion model | |
| US20220278527A1 (en) | Determination of phase connections in a power grid | |
| CN110146634B (en) | Fault diagnosis method, device, equipment and storage medium for oil chromatographic data | |
| CN112949951A (en) | Data prediction method, data prediction device, electronic equipment and storage medium | |
| CN113591396A (en) | Power grid component fault diagnosis method based on naive Bayesian network | |
| CN111767938A (en) | Abnormal data detection method and device and electronic equipment | |
| CN110580494A (en) | Data analysis method based on quantile logistic regression | |
| CN113806495B (en) | Outlier machine detection method and device | |
| CN115408197B (en) | Load data verification method based on streaming processing and multi-source data cross verification |
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 |