Abnormal power consumption user data storage method and device, electronic equipment and readable medium
By clustering and similarity matrix processing of abnormal electricity users’ data, monitoring and detecting abnormal electricity users’ behaviors in real time, and dynamically updating the database, the problem of manual regular verification of electricity meter cannot monitor abnormal electricity users in real time, and improving the power system stability and safety.
Patent Information
- Application Number
- CN202411155719.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-22
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2044-08-22
AI Technical Summary
In the prior art, manual regular calibration of electricity meter cannot monitor users with abnormal electricity in real time, resulting in reduced stability and safety of the power system, and there are large errors in the data storage of abnormal electricity in users, affecting the normal operation of the power system.
By obtaining the historical user data set of electricity consumption abnormalities and the user data set to be tested, clustering processing and similarity matrix generation, filtering and level division, real-time monitoring and detection of electricity consumption abnormalities, and dynamically update the user database of electricity consumption abnormalities.
It improves the accuracy of detection of abnormal user data for electricity consumption and the stability and safety of the power system, reduces power losses, and ensures the normal operation of the power system.
Smart Images

Figure CN119066580A_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present disclosure relate to the field of computer technology, and in particular to a method, device, electronic device, and readable medium for storing abnormal power consumption user data. Background Art
[0002] With the rapid advancement of the market economy and the rapid development of science and technology, the application scope of smart meters is getting wider and wider, and abnormal electricity consumption is rampant. The scope of abnormal electricity consumption is wide, the number of people is large, and there are more and more high-tech abnormal electricity consumption methods, such as wireless remote control, wired remote control, etc., and the abnormal electricity consumption behavior is also relatively hidden. The classification and real-time detection of user data can improve the stability and security of the power system. In addition, the dynamic update of the abnormal electricity consumption user database can also improve the stability and security of the power system. In addition, when clustering the abnormal electricity consumption user data with a large amount of data, the error of the abnormal electricity consumption user data can be reduced, which can also improve the stability and security of the power system. The abnormal electricity consumption user data storage is a technology for storing abnormal electricity consumption user data. At present, the abnormal electricity consumption user data storage usually adopts the method of manually checking the meter regularly to realize the abnormal electricity consumption user data storage.
[0003] However, when the above method is adopted, the following technical problems often occur:
[0004] First, manual regular calibration of electricity meters cannot monitor the behavior of abnormal electricity users in real time, which may cause power loss in the power system and reduce the stability and security of the power system. Due to the large amount of user data, it is impossible to accurately detect the abnormal electricity user data when detecting abnormal electricity users, resulting in large errors in the storage of abnormal electricity user data, thus affecting the normal operation of the power system.
[0005] Second, after the abnormal electricity usage user data corresponding to at least one behavior detection result is stored in the abnormal electricity usage user database, the abnormal electricity usage user database cannot be dynamically updated, and manual updates are prone to errors and low efficiency, resulting in the inability to fully detect users with abnormal electricity usage, which may cause power loss in the power system and lead to poor stability and security of the power system.
[0006] Third, when clustering a large amount of abnormal electricity consumption user data, it may cause large errors in the corresponding operating behaviors of the determined abnormal electricity consumption user data, resulting in a decrease in the accuracy of the results, thereby reducing the safety and stability of the power system.
[0007] The above information disclosed in this Background section is only for enhancement of understanding of the background of the inventive concept and therefore it may contain information that does not form the prior art that is already known in this country to a person of ordinary skill in the art. Summary of the invention
[0008] The content of this disclosure is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this disclosure is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.
[0009] Some embodiments of the present disclosure propose a method, device, electronic device and readable medium for storing abnormal power consumption user data to solve one or more of the technical problems mentioned in the above background technology section.
[0010] In a first aspect, some embodiments of the present disclosure provide a method for storing data of users with abnormal electricity usage, the method comprising: obtaining a historical data set of users with abnormal electricity usage and a data set of users to be tested, wherein the historical data set of users with abnormal electricity usage in the historical data set of users with abnormal electricity usage comprises: operation behavior data corresponding to the historical users with abnormal electricity usage; clustering the historical data set of users with abnormal electricity usage to obtain a clustering result to determine a target data set of users with abnormal electricity usage; generating a similarity user matrix based on the data set of users to be tested and the target data set of users with abnormal electricity usage; screening the target user data in the similarity user matrix to obtain a screened target user data set; classifying the screened target user data set to obtain a classified target user data set; performing abnormal electricity usage behavior detection on at least one classified target user corresponding to a preset level in the classified target user data set to obtain a behavior detection result set, wherein the behavior detection result in the behavior detection result set represents an abnormal behavior detection result and a normal behavior detection result; issuing an early warning for at least one behavior detection result representing an abnormal behavior detection result in the behavior detection result set, and storing the abnormal electricity usage user data corresponding to at least one behavior detection result representing abnormal electricity usage behavior in an abnormal electricity usage user database.
[0011] In a second aspect, some embodiments of the present disclosure provide a device for storing abnormal power usage user data, the device comprising: an acquisition unit, configured to acquire a historical abnormal power usage user data set and a user data set to be tested, wherein the historical abnormal power usage user data in the above historical abnormal power usage user data set comprises: operation behavior data corresponding to the historical abnormal power usage users; a clustering unit, configured to perform clustering processing on the above historical abnormal power usage user data set to obtain a clustering result to determine a target abnormal power usage user data set; a generation unit, configured to generate a similarity user matrix based on the above user data set to be tested and the above target abnormal power usage user data set; a screening unit, configured to screen the target user data on the above similarity user matrix to obtain a screened result. A selected target user data set; a dividing unit, configured to grade the above-mentioned screened target user data set to obtain a divided target user data set; a detection unit, configured to perform abnormal power usage behavior detection on at least one divided target user corresponding to a preset grade in the above-mentioned divided target user data set to obtain a behavior detection result set, wherein the behavior detection results in the above-mentioned behavior detection result set represent abnormal behavior detection results and normal behavior detection results; a storage unit, configured to issue an early warning for at least one behavior detection result in the above-mentioned behavior detection result set that represents an abnormal behavior detection result, and to store the abnormal power usage user data corresponding to the at least one behavior detection result that represents abnormal power usage behavior in an abnormal power usage user database.
[0012] In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation manner of the above-mentioned first aspect.
[0013] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method described in any implementation manner of the above-mentioned first aspect is implemented.
[0014] The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the abnormal power user data storage method of some embodiments of the present disclosure, the power loss caused by the power system is reduced, the stability and safety of the power system are improved, the accuracy of detecting abnormal power user data is improved, and the normal operation of the power system is facilitated. Specifically, the power loss of the power system is caused, the stability and safety of the power system are reduced, and the abnormal power user data cannot be accurately detected, which affects the normal operation of the power system. The reason is that the manual regular calibration of the electric meter cannot monitor the behavior of the abnormal power user in real time, which may cause the power system to cause power loss, reducing the stability and safety of the power system. Due to the large amount of user data, it is impossible to accurately detect the abnormal power user data when detecting the abnormal power user, resulting in a large error in the abnormal power user data storage, thereby affecting the normal operation of the power system. Based on this, the abnormal power user data storage method of some embodiments of the present disclosure, first, obtains a historical abnormal power user data set and a user data set to be tested, wherein the historical abnormal power user data in the above-mentioned historical abnormal power user data set includes: the operation behavior data corresponding to the historical abnormal power user, thereby providing convenience for subsequent operations. Then, clustering is performed on the above historical abnormal power consumption user data set to obtain clustering results to determine the target abnormal power consumption user data set, thereby clustering a large number of user data, thereby improving the accuracy of detecting abnormal power consumption user data when detecting abnormal power consumption users. Afterwards, a similarity user matrix is generated based on the above user data set to be tested and the above target abnormal power consumption user data set, thereby improving the accuracy of detecting abnormal power consumption user data. It is also convenient to monitor the abnormal power consumption user data in real time, reduce the power loss caused by the power system, and improve the stability and safety of the power system. Secondly, the target user data is screened on the above similarity user matrix to obtain the screened target user data set, thereby improving the efficiency of identifying potential abnormal power consumption users from a large amount of data. Thirdly, the above screened target user data set is graded to obtain the divided target user data set, thereby determining the abnormal power consumption user data by priority, improving the accuracy of detecting the abnormal power consumption user data, and facilitating the normal operation of the power system. Then, abnormal electricity consumption behavior detection is performed on at least one of the divided target users corresponding to the preset level in the divided target user data set to obtain a behavior detection result set, wherein the behavior detection results in the behavior detection result set represent abnormal behavior detection results and normal behavior detection results, thereby monitoring the behavior of users with abnormal electricity consumption in real time. Finally, an early warning is issued for at least one behavior detection result in the behavior detection result set that represents an abnormal behavior detection result, and the abnormal electricity consumption user data corresponding to the at least one behavior detection result representing abnormal electricity consumption behavior is stored in the abnormal electricity consumption user database.As a result, the stability and safety of the power system can be improved. Therefore, the power loss caused by the power system is reduced, the stability and safety of the power system are improved, the accuracy of detecting abnormal power consumption user data is improved, and the normal operation of the power system is facilitated. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.
[0016] Figure 1 is a flowchart of some embodiments of the method for storing abnormal power consumption user data according to the present disclosure;
[0017] Figure 2 is a schematic diagram of the structure of some embodiments of the abnormal power consumption user data storage device according to the present disclosure;
[0018] Figure 3 It is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION
[0019] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.
[0020] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure can be combined with each other.
[0021] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.
[0022] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".
[0023] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.
[0024] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.
[0025] Figure 1 This is a process 100 of some embodiments of the method for storing abnormal power consumption user data of the present disclosure. The method for storing abnormal power consumption user data includes the following steps:
[0026] Step 101: Obtain a historical data set of abnormal electricity consumption users and a data set of users to be checked.
[0027] In some embodiments, the executor of the abnormal electricity usage user data storage method (for example, a computing device) can obtain a historical abnormal electricity usage user data set and a user data set to be tested through a wired connection or a wireless connection, wherein the historical abnormal electricity usage user data in the above-mentioned historical abnormal electricity usage user data set includes: operation behavior data corresponding to the historical abnormal electricity usage users.
[0028] Here, the user data to be checked in the above-mentioned user data set to be checked may refer to user data whose operation behavior data has not been checked. The historical abnormal power usage user data in the above-mentioned historical abnormal power usage user data set includes: operation behavior data corresponding to the historical abnormal power usage user. The above-mentioned operation behavior data may refer to abnormal power usage behavior data.
[0029] It should be noted that the above-mentioned wireless connection methods may include but are not limited to 3G / 4G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other wireless connection methods currently known or to be developed in the future.
[0030] It should be noted that the above-mentioned computing device can be hardware or software. When the computing device is hardware, it can be implemented as a distributed cluster consisting of multiple servers or terminal devices, or it can be implemented as a single server or a single terminal device. For example, the computing device can be the above-mentioned target terminal. When the computing device is embodied as software, it can be installed in the hardware devices listed above. It can be implemented as multiple software or software modules for providing distributed services, for example, or it can be implemented as a single software or software module. No specific limitation is made here.
[0031] Step 102: clustering the above historical abnormal electricity consumption user data set to obtain a clustering result to determine a target abnormal electricity consumption user data set.
[0032] In some embodiments, the execution entity may perform clustering processing on the historical abnormal electricity consumption user data set to obtain a clustering result to determine a target abnormal electricity consumption user data set.
[0033] Here, the target abnormal power consumption user data in the target abnormal power consumption user data set may refer to abnormal power consumption user data with a greater possibility of abnormal power consumption behavior. Here, the clustering process may refer to K-Means clustering process.
[0034] Optionally, the execution subject may perform clustering processing on the historical abnormal electricity consumption user data set through the following steps to obtain a clustering result to determine a target abnormal electricity consumption user data set:
[0035] In the first step, data preprocessing is performed on the above historical abnormal electricity consumption user data set to obtain a preprocessed abnormal electricity consumption user data set.
[0036] Here, the data preprocessing may refer to data cleaning. The preprocessed abnormal power consumption user data set may refer to a set after removing duplicate and redundant abnormal power consumption user data.
[0037] In the second step, preset key features are extracted from the abnormal electricity consumption user data set after the above preprocessing to obtain a key feature set of the abnormal electricity consumption user data.
[0038] Here, the preset key feature may refer to a pre-set key feature. The key feature may refer to a power consumption feature. The key feature may also refer to a power consumption period feature.
[0039] The third step is to perform feature dimensionality reduction on the key feature set of the abnormal electricity consumption user data to obtain the key feature set of the abnormal electricity consumption user data after dimensionality reduction.
[0040] The fourth step is to determine the power usage pattern information corresponding to the above-mentioned pre-processed power usage abnormal user data set based on the above-mentioned key feature set of the power usage abnormal user data after dimensionality reduction, and obtain the power usage pattern information set.
[0041] Here, the above-mentioned power usage pattern information set may include normal power usage pattern information and abnormal power usage pattern information.
[0042] As an example, the execution subject may determine the power usage pattern of the pre-processed abnormal power usage user data set corresponding to the key feature set of abnormal power usage user data after dimensionality reduction to obtain a power usage pattern information set.
[0043] In the fifth step, based on the power consumption pattern information set, a preset number of user data are selected by clustering the pre-processed abnormal power consumption user data set to obtain a selected abnormal power consumption user data set.
[0044] Here, the preset number of clusters may refer to the number of pre-set cluster centers. For example, the preset number of clusters may refer to 10. The user data selection may refer to random selection of user data.
[0045] As an example, the execution subject may delete the abnormal power usage pattern information in the power usage pattern information set to obtain a deleted power usage pattern information set. Then, the pre-processed abnormal power usage user data set is clustered to select a plurality of user data from the deleted power usage pattern information set to obtain a selected abnormal power usage user data set.
[0046] The sixth step is to determine the cluster mean of the abnormal electricity consumption user data set after the above selection, and obtain the cluster mean set corresponding to the abnormal electricity consumption user data.
[0047] Here, the cluster mean may refer to the mean corresponding to the selected abnormal power consumption user data in the selected abnormal power consumption user data set.
[0048] In the seventh step, the selected abnormal electricity usage user data set is removed from the historical abnormal electricity usage user data set to obtain a removed abnormal electricity usage user data set.
[0049] Here, the above-mentioned removal may refer to deletion.
[0050] In the eighth step, for each abnormal power usage user data after removal in the above abnormal power usage user data set, the above abnormal power usage user data after removal is compared with the corresponding cluster mean of each abnormal power usage user data in the corresponding cluster mean set of the abnormal power usage user data, so as to generate a comparison result and obtain a comparison result set.
[0051] Here, the comparison result in the above comparison result set may refer to a result in which the cluster mean of the abnormal power consumption user data after removal is greater than the corresponding cluster mean of the abnormal power consumption user data.
[0052] In a ninth step, in response to determining that the number corresponding to the above comparison result sets is equal to the number corresponding to the preset number of times, the above comparison result sets are merged into clustering results.
[0053] Here, the preset number of times may refer to a preset number of times. For example, the preset number of times may refer to 20 times.
[0054] The tenth step is to filter the abnormal electricity consumption user data based on the above clustering results to obtain the filtered abnormal electricity consumption user data set as the target abnormal electricity consumption user data set.
[0055] The relevant contents in the first step to the tenth step above serve as an inventive point of the present disclosure, and solve the technical problem three mentioned in the background technology: "When clustering the data of abnormal power users with a large amount of data, it may cause the error of the corresponding operation behavior of the determined abnormal power user data to be large, resulting in a decrease in the accuracy of the result, thereby causing a decrease in the safety and stability of the power system". The factors that lead to the decrease in the safety and stability of the power system are often as follows: When clustering the data of abnormal power users with a large amount of data, it may cause the error of the corresponding operation behavior of the determined abnormal power user data to be large, resulting in a decrease in the accuracy of the result, thereby causing a decrease in the safety and stability of the power system. If the above factors are solved, the effect of improving the safety and stability of the power system can be achieved. In order to achieve this effect, in the first step, the above historical abnormal power user data set is preprocessed to obtain the abnormal power user data set after preprocessing. In the second step, the preset key features are extracted from the above preprocessed abnormal power user data set to obtain the key feature set of the abnormal power user data. In the third step, the feature dimension reduction is performed on the key feature set of the abnormal power user data to obtain the key feature set of the abnormal power user data after dimension reduction. In the fourth step, according to the key feature set of the abnormal power consumption user data after the dimensionality reduction, the power consumption mode information corresponding to the abnormal power consumption user data set after the preprocessing is determined to obtain the power consumption mode information set. In the fifth step, according to the power consumption mode information set, the abnormal power consumption user data set after the preprocessing is selected by clustering a plurality of user data to obtain the selected abnormal power consumption user data set. In this way, the amount of abnormal power consumption user data can be reduced. In the sixth step, the cluster mean of the selected abnormal power consumption user data set is determined to obtain the cluster mean set corresponding to the abnormal power consumption user data. In the seventh step, the selected abnormal power consumption user data set is removed from the historical abnormal power consumption user data set to obtain the removed abnormal power consumption user data set. In the eighth step, for each removed abnormal power consumption user data in the removed abnormal power consumption user data set, the cluster mean of the removed abnormal power consumption user data is compared with the cluster mean corresponding to each abnormal power consumption user data in the cluster mean set corresponding to the abnormal power consumption user data to generate a comparison result and obtain a comparison result set. In this way, it is possible to avoid large errors in the operational behaviors corresponding to the determined abnormal power consumption user data, improve the accuracy of the results, and thus improve the safety and stability of the power system. In the ninth step, in response to determining that the number corresponding to the above-mentioned comparison result set is equal to the number corresponding to the preset number of times, the above-mentioned comparison result set is merged into a clustering result. In the tenth step, the above-mentioned clustering results are screened for abnormal power consumption user data to obtain a screened abnormal power consumption user data set as a target abnormal power consumption user data set. In this way, it is possible to reduce the errors in the operational behaviors corresponding to the determined abnormal power consumption user data, and thus improve the safety and stability of the power system.
[0056] Step 103: Generate a similarity user matrix based on the to-be-checked user data set and the target abnormal electricity consumption user data set.
[0057] In some embodiments, the execution entity may generate a similarity user matrix based on the to-be-checked user data set and the target abnormal electricity consumption user data set.
[0058] Here, the similarity user matrix may refer to a matrix composed of similarities between the user data to be checked in the user data set to be checked and the target power consumption abnormality user data in the target power consumption abnormality user data set.
[0059] Optionally, the execution subject may generate a similarity user matrix according to the to-be-checked user data set and the target abnormal power consumption user data set through the following steps:
[0060] The first step is to fill missing values in the above-mentioned user data set to be tested to obtain a filled user data set.
[0061] As an example, the execution subject may perform missing value filling processing on the to-be-tested user data set by an interpolation method to obtain a filled user data set.
[0062] The second step is to perform standardization on the padded user data set to obtain a processed user data set.
[0063] The third step is to determine a similarity user matrix based on the target abnormal electricity consumption user data set and the processed user data set.
[0064] Optionally, the execution subject may determine a similarity user matrix according to the target abnormal power consumption user data set and the processed user data set through the following steps:
[0065] The first step is to clean the target abnormal electricity consumption user data set to obtain a cleaned user data set.
[0066] The second step is to process missing values on the above cleaned user data set to obtain the user data set after missing value processing.
[0067] Here, the above-mentioned missing value processing may refer to missing value filling.
[0068] The third step is to perform data standardization on the user data set after the missing value processing to obtain a standardized user data set.
[0069] In the fourth step, similarity is determined between the standardized user data in the standardized user data set and the processed user data in the processed user data set to obtain a similarity set.
[0070] The fifth step is to construct a similarity matrix based on the above similarity set as a similarity user matrix, wherein the elements corresponding to the above similarity user matrix represent the similarity between the target abnormal power consumption user data in the target abnormal power consumption user data set and the processed user data in the above processed user data set.
[0071] As an example, the execution entity may fill each similarity in the similarity set into an empty matrix to obtain a similarity user matrix.
[0072] Step 104 , screening the target user data of the similarity user matrix to obtain a screened target user data set.
[0073] In some embodiments, the execution entity may filter the target user data on the similarity user matrix to obtain a filtered target user data set.
[0074] Here, the target user data may refer to user data with a greater possibility of abnormal power usage.
[0075] As an example, the execution subject may perform similarity scoring on each user data corresponding to the similarity user matrix to obtain a scoring result set. Then, the user data corresponding to the scoring results in the scoring result set whose scoring results are higher than the preset scoring value is further screened to obtain a screened target user data set. The preset scoring value may refer to a pre-set score value. For example, the preset scoring value may refer to 0.7. The similarity corresponding to the user data is linearly related to the scoring result.
[0076] Step 105 , classify the above-screened target user data set into different levels to obtain a classified target user data set.
[0077] In some embodiments, the execution entity may classify the filtered target user data set into different levels to obtain a classified target user data set.
[0078] Here, the above-mentioned divided target user data set includes: divided high-risk target user data, divided medium-risk target user data, and divided low-risk target user data.
[0079] Optionally, the execution subject may classify the filtered target user data set into different levels through the following steps to obtain a classified target user data set:
[0080] The first step is to perform feature engineering processing on the above-screened target user data set to obtain a processed target user data set.
[0081] The second step is to perform data preprocessing on the above processed target user data set to obtain a preprocessed target user data set.
[0082] Here, the above data preprocessing may refer to data cleaning.
[0083] The third step is to sort the similarities corresponding to the preprocessed target user data in the preprocessed target user data set to obtain a sorted target user data sequence.
[0084] Here, the above sorting may refer to sorting from small to large.
[0085] The fourth step is to classify the sorted target user data sequence according to a preset level threshold to obtain a classified target user data sequence, wherein the classified target user data sequence includes: first risk user data, second risk user data, and third risk user data.
[0086] Here, the preset level threshold may refer to "the first level threshold is 0.8, the second level threshold is 0.5, and the third level threshold is 0.2". The first risk user data corresponds to the first level threshold, and the first risk user data may refer to "high risk" user data. The second risk user data corresponds to the second level threshold, and the second risk user data may refer to "medium risk" user data. The third risk user data corresponds to the third level threshold, and the third risk user data may refer to "low risk" user data.
[0087] The fifth step is to test the above divided target user data sequence to obtain a tested target user data set as the divided target user data set.
[0088] Here, the above inspection may refer to a safety inspection.
[0089] Step 106, performing abnormal power consumption behavior detection on at least one divided target user corresponding to a preset level in the divided target user data set to obtain a behavior detection result set, wherein the behavior detection results in the behavior detection result set represent abnormal behavior detection results and normal behavior detection results.
[0090] In some embodiments, the above-mentioned execution entity can perform abnormal electricity usage behavior detection on at least one divided target user corresponding to a preset level in the above-mentioned divided target user data set to obtain a behavior detection result set, wherein the behavior detection results in the above-mentioned behavior detection result set represent abnormal behavior detection results and normal behavior detection results.
[0091] Here, the preset level may refer to a pre-set level. For example, the preset level may refer to the first level corresponding to "high risk".
[0092] As an example, the execution subject may determine the operation behavior corresponding to at least one of the segmented target users corresponding to the preset level in the segmented target user data set to obtain an operation behavior set. In response to determining that there is abnormal power usage operation behavior in the operation behavior set, the operation behavior set is annotated with abnormal power usage behavior to obtain an annotated operation behavior information set. Then, the annotated operation behavior information set is tested to obtain a behavior detection result set, wherein the behavior detection results in the behavior detection result set represent abnormal behavior detection results and normal behavior detection results.
[0093] Step 107 , issuing an early warning for at least one behavior detection result in the behavior detection result set that represents an abnormal behavior detection result, and storing abnormal power usage user data corresponding to at least one behavior detection result representing abnormal power usage behavior in an abnormal power usage user database.
[0094] In some embodiments, the above-mentioned execution entity can issue an early warning for at least one behavior detection result in the above-mentioned behavior detection result set that represents an abnormal behavior detection result, and store the abnormal power usage user data corresponding to at least one behavior detection result representing abnormal power usage behavior into the abnormal power usage user database.
[0095] Here, the abnormal power usage user database may refer to a database storing abnormal power usage user data. The abnormal behavior detection result may refer to the result of abnormal power usage detected by the behavior.
[0096] Optionally, the execution subject may issue an early warning for at least one behavior detection result representing an abnormal behavior detection result in the behavior detection result set, and store the abnormal power usage user data corresponding to at least one behavior detection result representing abnormal power usage behavior in the abnormal power usage user database through the following steps:
[0097] The first step is to determine a source table corresponding to at least one abnormal power usage user data in the abnormal power usage user database and a condition list corresponding to at least one abnormal power usage user data in the abnormal power usage user database.
[0098] Here, the source table may refer to a data table storing sources corresponding to abnormal power usage user data in the abnormal power usage user database. The source may refer to an address source corresponding to the abnormal power usage user data. The condition list may include but is not limited to at least one of the following: power usage mode condition, time condition.
[0099] In the second step, according to the name of the source table and the conditions in the condition list, the operation behavior information corresponding to the at least one abnormal power usage user data is retrieved from the abnormal power usage user database.
[0100] Here, the database may refer to MySQL. The operation behavior information may refer to abnormal power consumption behavior information. For example, the operation behavior information may refer to reading information of an operation metering device. The metering device may refer to an electric meter device.
[0101] The third step is to perform frequency statistics on the operation behavior information corresponding to the at least one abnormal power consumption user data to obtain a statistical result, wherein the statistical result represents the result of the number of occurrences of each operation behavior information.
[0102] As an example, the execution subject may traverse the operation behavior information corresponding to the at least one abnormal power consumption user data, and store it into an empty dictionary to obtain a dictionary containing the operation behavior information. The key of the dictionary containing the operation behavior information represents the operation behavior information, and the value represents the frequency corresponding to the operation behavior information. Then, for each operation behavior information, in response to determining that the operation behavior information exists in the dictionary containing the operation behavior information, the frequency of the corresponding operation behavior information is increased by one. In response to determining that the operation behavior information does not exist in the dictionary containing the operation behavior information, the operation behavior information is added to the dictionary containing the operation behavior information, and the frequency corresponding to the operation behavior information is initialized. Finally, in response to determining that the traversal is completed, each operation behavior information and the corresponding value in the dictionary containing the operation behavior information are determined as the statistical result.
[0103] The fourth step is to set a preset baseline threshold, wherein the preset baseline threshold represents the baseline maximum value of the frequency of the operation behavior information.
[0104] For example, the preset baseline threshold may be 25.
[0105] In the fifth step, in response to determining that there is a statistical value corresponding to the statistical result greater than the preset baseline threshold in the above statistical results, the operation behavior information corresponding to the statistical value corresponding to the statistical result greater than the preset baseline threshold is marked as abnormal operation behavior information.
[0106] In a sixth step, in response to determining that the operation behavior information is abnormal operation behavior information, a power usage anomaly detection model is created in the power usage anomaly user database.
[0107] Here, the power consumption anomaly detection model may refer to a model for detecting abnormal power consumption behavior of users corresponding to abnormal power consumption user data. The input of the power consumption anomaly detection model may refer to abnormal power consumption user data, and the output of the power consumption anomaly detection model may refer to the abnormal power consumption behavior of abnormal power consumption users.
[0108] In the seventh step, based on the abnormal power usage detection model, the abnormal power usage mode corresponding to the at least one abnormal power usage user data is determined to obtain the abnormal power usage mode corresponding to the abnormal power usage user.
[0109] In the eighth step, according to the abnormal electricity usage mode of the abnormal electricity usage user, an abnormal repair operation is performed on the at least one abnormal electricity usage user data to obtain a user data set after abnormal repair.
[0110] Here, the abnormality repair operation may refer to an operation to avoid abnormal power consumption behavior. For example, the abnormality repair operation may refer to a warning operation. The abnormality repair operation may also refer to an operation to cut off the power supply to the user.
[0111] The ninth step is to determine the conditional parameter information set in the user data set after the above anomaly is repaired.
[0112] Here, the condition parameter information in the above condition parameter information set may refer to power consumption threshold condition information. For example, the condition parameter information in the above condition parameter information set may refer to a power consumption threshold of 900 kWh.
[0113] In the tenth step, in response to determining that the condition parameter information set meets the preset condition information set, the abnormality-repaired user data set is marked to obtain a marked user data set.
[0114] Here, the above-mentioned preset condition may refer to a pre-set condition. For example, the above-mentioned preset condition may refer to the condition of "the power consumption threshold is less than 1000 kWh".
[0115] As an example, the execution subject may mark each abnormality-repaired user data in the abnormality-repaired user data set as “abnormal user data without power consumption” to obtain a marked user data set.
[0116] In the eleventh step, in response to determining that each user corresponding to the marked user data set has accessed the abnormal electricity usage user database, authority verification is performed on each user corresponding to the marked user data set to obtain an authority verification result.
[0117] Here, the above-mentioned authority verification may refer to identity verification.
[0118] In the twelfth step, according to the above permission verification result, the access log information corresponding to each of the above users is stored to obtain an access log information set.
[0119] In the thirteenth step, real-time detection is performed on the marked user data set and the access log information set to obtain a first detection result and a second detection result.
[0120] Here, the first detection result is the detection result of the marked user data set, and the second detection result is the detection result of the access log information set.
[0121] As an example, the execution subject may perform real-time detection on the marked user data set through a monitoring device to obtain a detection result. Here, the monitoring device may refer to a smart meter device.
[0122] In step 14, in response to determining that the first detection result indicates a detection abnormality and the second detection result is abnormal, the abnormal electricity usage user database is updated according to the marked user data set to obtain an updated abnormal electricity usage user database.
[0123] As an example, the above-mentioned execution entity can add the above-mentioned marked user data set to the above-mentioned abnormal electricity usage user database, and eliminate at least one unmarked user data in the above-mentioned abnormal electricity usage user database corresponding to the above-mentioned marked user data set to obtain the abnormal electricity usage user database after elimination as the updated abnormal electricity usage user database.
[0124] The relevant contents in the first step to the fourteenth step above are an inventive point of the present disclosure, which solves the technical problem 2 mentioned in the background technology: "After storing the abnormal power consumption user data corresponding to at least one behavior detection result in the abnormal power consumption user database, the abnormal power consumption user database cannot be dynamically updated, and manual updates are prone to errors and are inefficient, resulting in the inability to fully detect users with abnormal power consumption, which may cause power loss in the power system, resulting in poor stability and safety of the power system.". The factors that lead to poor stability and safety of the power system are often as follows: After storing the abnormal power consumption user data corresponding to at least one behavior detection result in the abnormal power consumption user database, the abnormal power consumption user database cannot be dynamically updated, and manual updates are prone to errors and are inefficient, resulting in the inability to fully detect users with abnormal power consumption, which may cause power loss in the power system, resulting in poor stability and safety of the power system. If the above factors are solved, the effect of improving the stability and safety of the power system can be achieved. In order to achieve this effect, in the first step, a source table corresponding to at least one abnormal power consumption user data in the abnormal power consumption user database and a condition list corresponding to at least one abnormal power consumption user data in the abnormal power consumption user database are determined. In the second step, according to the name of the source table and the conditions in the condition list, the operation behavior information corresponding to the at least one abnormal power consumption user data is called from the abnormal power consumption user database. In the third step, the frequency of the operation behavior information corresponding to the at least one abnormal power consumption user data is counted to obtain the statistical result, wherein the statistical result represents the result of the number of occurrences of each operation behavior information. In this way, users with abnormal power consumption can be fully detected to reduce the possibility of causing power loss to the power system. In the fourth step, a preset baseline threshold is set, wherein the preset baseline threshold represents the baseline maximum value of the frequency of the operation behavior information. In the fifth step, in response to determining that there is a statistical value corresponding to the statistical result greater than the preset baseline threshold in the statistical result, the operation behavior information corresponding to the statistical value corresponding to the statistical result greater than the preset baseline threshold is marked as abnormal operation behavior information. In the sixth step, in response to determining that the operation behavior information is abnormal operation behavior information, an abnormal power consumption detection model is created in the abnormal power consumption user database. In the seventh step, according to the abnormal power consumption detection model, the abnormal power consumption mode corresponding to the at least one abnormal power consumption user data is determined to obtain the abnormal power consumption mode corresponding to the abnormal power consumption user. In the eighth step, according to the abnormal electricity consumption mode of the abnormal electricity consumption user, the abnormal repair operation is performed on the at least one abnormal electricity consumption user data to obtain the abnormal repaired user data set. In the ninth step, the condition parameter information set in the abnormal repaired user data set is determined. In the tenth step, in response to determining that the condition parameter information set meets the preset condition information set, the abnormal repaired user data set is marked to obtain the marked user data set. In this way, the stability and safety of the power system are improved.
[0125] The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the abnormal power user data storage method of some embodiments of the present disclosure, the power loss caused by the power system is reduced, the stability and safety of the power system are improved, the accuracy of detecting abnormal power user data is improved, and the normal operation of the power system is facilitated. Specifically, the power loss of the power system is caused, the stability and safety of the power system are reduced, and the abnormal power user data cannot be accurately detected, which affects the normal operation of the power system. The reason is that the manual regular calibration of the electric meter cannot monitor the behavior of the abnormal power user in real time, which may cause the power system to cause power loss, reducing the stability and safety of the power system. Due to the large amount of user data, it is impossible to accurately detect the abnormal power user data when detecting the abnormal power user, resulting in a large error in the abnormal power user data storage, thereby affecting the normal operation of the power system. Based on this, the abnormal power user data storage method of some embodiments of the present disclosure, first, obtains a historical abnormal power user data set and a user data set to be tested, wherein the historical abnormal power user data in the above-mentioned historical abnormal power user data set includes: the operation behavior data corresponding to the historical abnormal power user, thereby providing convenience for subsequent operations. Then, clustering is performed on the above historical abnormal power consumption user data set to obtain clustering results to determine the target abnormal power consumption user data set, thereby clustering a large number of user data, thereby improving the accuracy of detecting abnormal power consumption user data when detecting abnormal power consumption users. Afterwards, a similarity user matrix is generated based on the above user data set to be tested and the above target abnormal power consumption user data set, thereby improving the accuracy of detecting abnormal power consumption user data. It is also convenient to monitor the abnormal power consumption user data in real time, reduce the power loss caused by the power system, and improve the stability and safety of the power system. Secondly, the target user data is screened on the above similarity user matrix to obtain the screened target user data set, thereby improving the efficiency of identifying potential abnormal power consumption users from a large amount of data. Thirdly, the above screened target user data set is graded to obtain the divided target user data set, thereby determining the abnormal power consumption user data by priority, improving the accuracy of detecting the abnormal power consumption user data, and facilitating the normal operation of the power system. Then, abnormal electricity consumption behavior detection is performed on at least one of the divided target users corresponding to the preset level in the divided target user data set to obtain a behavior detection result set, wherein the behavior detection results in the behavior detection result set represent abnormal behavior detection results and normal behavior detection results, thereby monitoring the behavior of users with abnormal electricity consumption in real time. Finally, an early warning is issued for at least one behavior detection result in the behavior detection result set that represents an abnormal behavior detection result, and the abnormal electricity consumption user data corresponding to the at least one behavior detection result representing abnormal electricity consumption behavior is stored in the abnormal electricity consumption user database.As a result, the stability and safety of the power system can be improved. Therefore, the power loss caused by the power system is reduced, the stability and safety of the power system are improved, the accuracy of detecting abnormal power consumption user data is improved, and the normal operation of the power system is facilitated.
[0126] Further references Figure 2 As an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a method for storing abnormal power consumption user data. These device embodiments are similar to Figure 1 Corresponding to the method embodiments shown, the device can be specifically applied to various electronic devices.
[0127] like Figure 2 As shown, in some embodiments, the abnormal power consumption user data storage device 200 includes: an acquisition unit 201, a clustering unit 202, a generation unit 203, a screening unit 204, a division unit 205, a detection unit 206 and a storage unit 207. The acquisition unit 201 is configured to acquire a historical abnormal power consumption user data set and a to-be-tested user data set, wherein the historical abnormal power consumption user data in the above-mentioned historical abnormal power consumption user data set includes: operation behavior data corresponding to the historical abnormal power consumption user; the clustering unit 202 is configured to perform clustering processing on the above-mentioned historical abnormal power consumption user data set to obtain a clustering result to determine a target abnormal power consumption user data set; the generation unit 203 is configured to generate a similarity user matrix according to the above-mentioned to-be-tested user data set and the above-mentioned target abnormal power consumption user data set; the screening unit 204 is configured to perform target user data screening on the above-mentioned similarity user matrix to obtain a screened target user data set; the division unit 205 is configured to perform target user data screening on the above-mentioned similarity user matrix to obtain a screened target user data set; 05, is configured to grade the above-mentioned filtered target user data set to obtain a graded target user data set; the detection unit 206, is configured to perform abnormal power usage behavior detection on at least one graded target user corresponding to a preset grade in the above-mentioned graded target user data set to obtain a behavior detection result set, wherein the behavior detection results in the above-mentioned behavior detection result set represent abnormal behavior detection results and normal behavior detection results; the storage unit 207, is configured to issue an early warning for at least one behavior detection result in the above-mentioned behavior detection result set that represents an abnormal behavior detection result, and to store the abnormal power usage user data corresponding to at least one behavior detection result that represents abnormal power usage behavior in the abnormal power usage user database.
[0128] It is understood that the units described in the device 200 are similar to those described in the reference Figure 1 Therefore, the operations, features and beneficial effects described above for the method are also applicable to the device 200 and the units included therein, and will not be described in detail here.
[0129] Reference below Figure 3 , which shows a schematic structural diagram of an electronic device (such as a computing device) 300 suitable for implementing some embodiments of the present disclosure. Figure 3 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.
[0130] like Figure 3 As shown, the electronic device 300 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 304. In RAM 303, various programs and data required for the operation of the electronic device 300 are also stored. The processing device 301, ROM 302, and RAM 304 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.
[0131] Typically, the following devices may be connected to the I / O interface 305: input devices 306 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 308 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 309. The communication devices 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 3 The electronic device 300 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 3 Each block shown in the figure may represent one device, or may represent multiple devices as required.
[0132] In particular, according to some embodiments of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from the network through the communication device 309, or installed from the storage device 308, or installed from the ROM 302. When the computer program is executed by the processing device 301, the functions defined in the method of some embodiments of the present disclosure are executed.
[0133] It should be noted that the computer-readable medium recorded in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In some embodiments of the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, device or device. In some embodiments of the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.
[0134] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (Hyper Text Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.
[0135] The above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or it may exist independently without being assembled into the electronic device. The above-mentioned computer-readable medium carries one or more programs. When the above-mentioned one or more programs are executed by the electronic device, the electronic device: obtains a historical abnormal electricity usage user data set and a user data set to be tested, wherein the historical abnormal electricity usage user data in the above-mentioned historical abnormal electricity usage user data set includes: operation behavior data corresponding to the historical abnormal electricity usage users; clusters the above-mentioned historical abnormal electricity usage user data set to obtain clustering results to determine the target abnormal electricity usage user data set; generates a similarity user matrix based on the above-mentioned user data set to be tested and the above-mentioned target abnormal electricity usage user data set; screens the target user data on the above-mentioned similarity user matrix to obtain to a screened target user data set; classify the above-mentioned screened target user data set to obtain a classified target user data set; perform abnormal power usage behavior detection on at least one classified target user corresponding to a preset level in the above-mentioned classified target user data set to obtain a behavior detection result set, wherein the behavior detection results in the above-mentioned behavior detection result set represent abnormal behavior detection results and normal behavior detection results; issue an early warning for at least one behavior detection result in the above-mentioned behavior detection result set that represents an abnormal behavior detection result, and store the abnormal power usage user data corresponding to at least one behavior detection result that represents abnormal power usage behavior in an abnormal power usage user database.
[0136] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0137] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0138] The units described in some embodiments of the present disclosure may be implemented by software or by hardware. The described units may also be provided in a processor, for example, may be described as: a processor comprising: an acquisition unit, a clustering unit, a generation unit, a screening unit, a division unit, a detection unit and a storage unit. Among them, the names of these units do not constitute a limitation on the unit itself in certain circumstances, for example, a clustering unit may also be described as "a unit for clustering the above-mentioned historical abnormal electricity consumption user data set to obtain a clustering result to determine a target abnormal electricity consumption user data set".
[0139] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.
[0140] The above descriptions are only some preferred embodiments of the present disclosure and the explanation of the technical principles used above. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by the specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above invention concept. For example, the above features are replaced with the technical features with similar functions disclosed in the embodiments of the present disclosure (but not limited to) and the technical solutions formed.
Claims
1. A method for storing abnormal power consumption user data, include: Acquire a historical abnormal power consumption user data set and a to-be-tested user data set, wherein the historical abnormal power consumption user data in the historical abnormal power consumption user data set includes: operation behavior data corresponding to the historical abnormal power consumption users; Performing clustering processing on the historical abnormal electricity consumption user data set to obtain a clustering result to determine a target abnormal electricity consumption user data set; Generate a similarity user matrix according to the to-be-checked user data set and the target abnormal power consumption user data set; Screening target user data on the similarity user matrix to obtain a screened target user data set; Classifying the filtered target user data set to obtain a classified target user data set; Performing abnormal power consumption behavior detection on at least one divided target user corresponding to a preset level in the divided target user data set to obtain a behavior detection result set, wherein the behavior detection results in the behavior detection result set represent abnormal behavior detection results and normal behavior detection results; An early warning is issued for at least one behavior detection result in the behavior detection result set that represents an abnormal behavior detection result, and abnormal power usage user data corresponding to at least one behavior detection result representing abnormal power usage behavior is stored in an abnormal power usage user database.
2. The method according to claim 1, in, The generating a similarity user matrix according to the to-be-checked user data set and the target abnormal power consumption user data set comprises: Performing missing value filling processing on the user data set to be checked to obtain a filled user data set; Performing standardization processing on the filled user data set to obtain a processed user data set; A similarity user matrix is determined according to the target abnormal power consumption user data set and the processed user data set.
3. The method according to claim 2, in, The determining of a similarity user matrix according to the target abnormal power consumption user data set and the processed user data set includes: Performing data cleaning on the target abnormal electricity consumption user data set to obtain a cleaned user data set; Performing missing value processing on the cleaned user data set to obtain a missing value processed user data set; Performing data standardization processing on the missing value processed user data set to obtain a standardized user data set; Determining similarity between the standardized user data in the standardized user data set and the processed user data in the processed user data set to obtain a similarity set; According to the similarity set, a similarity matrix is constructed as a similarity user matrix, wherein elements corresponding to the similarity user matrix represent the similarity between the target abnormal power consumption user data in the target abnormal power consumption user data set and the processed user data in the processed user data set.
4. The method according to claim 1, in, The step of classifying the filtered target user data set to obtain a classified target user data set includes: Performing feature engineering processing on the screened target user data set to obtain a processed target user data set; Performing data preprocessing on the processed target user data set to obtain a preprocessed target user data set; Sorting the similarities corresponding to the preprocessed target user data in the preprocessed target user data set to obtain a sorted target user data sequence; According to a preset level threshold, the sorted target user data sequence is graded to obtain a graded target user data sequence, wherein the graded target user data sequence includes: first risk user data, second risk user data, and third risk user data; The divided target user data sequence is tested to obtain a tested target user data set as the divided target user data set.
5. A device for storing user data with abnormal power consumption, include: An acquisition unit is configured to acquire a historical abnormal power consumption user data set and a to-be-tested user data set, wherein the historical abnormal power consumption user data in the historical abnormal power consumption user data set includes: operation behavior data corresponding to the historical abnormal power consumption user; A clustering unit is configured to perform clustering processing on the historical abnormal electricity consumption user data set to obtain a clustering result to determine a target abnormal electricity consumption user data set; A generating unit, configured to generate a similarity user matrix according to the to-be-checked user data set and the target power consumption abnormal user data set; A screening unit is configured to screen the target user data on the similarity user matrix to obtain a screened target user data set; a dividing unit configured to classify the filtered target user data set to obtain a divided target user data set; a detection unit configured to perform abnormal power consumption behavior detection on at least one divided target user corresponding to a preset level in the divided target user data set to obtain a behavior detection result set, wherein the behavior detection results in the behavior detection result set represent abnormal behavior detection results and normal behavior detection results; The storage unit is configured to issue an early warning for at least one behavior detection result in the behavior detection result set that represents an abnormal behavior detection result, and to store abnormal power usage user data corresponding to at least one behavior detection result representing abnormal power usage behavior in an abnormal power usage user database.
6. An electronic device, include: one or more processors; a storage device having one or more programs stored thereon; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 4.
7. A computer readable medium having a computer program stored thereon, in, When the program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.
Citation Information
Patent Citations
Metering online monitoring system based on power user power consumption information acquisition system
CN103532745A
Big consumer abnormal electricity consumption pre-warning system with multiple networks integrated
CN104361452A
Abnormal power consumption detection method and system
CN105630885A
Intelligent power grid abnormal power consumption behavior detection method
CN106296465A
Abnormal power consumption detection method and device, equipment and computer readable storage medium
CN110634080A
