A method, apparatus, device, and readable storage medium for simplifying electricity consumption data.

Abstract

This application provides a method, apparatus, device, and readable storage medium for electricity consumption data reduction. The method involves extracting the attributes and value ranges of the electricity consumption data, performing full permutations of each attribute based on its value range to obtain a first rough set, performing attribute reduction on the first rough set based on rough set theory, retaining the key attributes that have the most significant impact on decision-making attributes, and obtaining a full data table through full permutations. The attribute reduction based on this method can effectively reduce the number of attributes in the dataset, achieving the retention of key information while reducing redundancy, thereby simplifying the dataset. The data processing of full permutations and attribute reduction can be completed programmatically, enabling rapid full combination of each attribute and its value range of the business data to obtain all possible combinations, and then obtaining reduced data and data classification rules through a reduction algorithm, significantly improving the efficiency and accuracy of data auditing.

Description

Technical Field

[0001] This invention pertains to electricity data processing technology, and particularly relates to a method, apparatus, device, and readable storage medium for electricity data reduction. Background Technology

[0002] Electricity data auditing refers to the review and verification of electricity consumption data to ensure its accuracy and legality. The purpose of auditing is to check the completeness, consistency, and compliance of electricity consumption data, identify and correct existing problems, and prevent errors and misuse of electricity consumption data.

[0003] Traditional electricity data auditing methods are mostly manual. These involve experts extracting valuable information based on their knowledge, experience, and practical experience to form rules and build a knowledge base. Based on this knowledge base, auditors use rule-based reasoning to audit abnormal data within various marketing business information systems. If abnormal data is found, auditors are assigned to the corresponding site for manual review. However, by this time, the anomaly has often already been identified, lacking pre-emptive prevention and in-process control, making it prone to errors and omissions, thus reducing the accuracy of the audit. Manual auditing also relies heavily on the subjective judgment of auditors, easily leading to non-standard business operation processes and inadequate implementation of regulations and standards, significantly reducing audit efficiency. Summary of the Invention

[0004] In view of this, the present invention aims to propose a method, apparatus, device and readable storage medium for electricity consumption data reduction. By reducing the attributes of electricity consumption data, the classification rules of the data are extracted, thereby improving audit efficiency and realizing pre-audit interception, real-time monitoring during the process and pre-emptive detection of high-risk points in the power marketing system.

[0005] In a first aspect, the present invention proposes a method for simplifying electricity consumption data, comprising:

[0006] Obtain electricity consumption data;

[0007] Extract the various attributes and their value ranges involved in the electricity consumption data;

[0008] Determine the decision attribute and condition attribute among the attributes, and obtain the first rough set by performing a full permutation of the attributes according to their value ranges;

[0009] Analyze the degree of influence of each condition attribute on the decision attribute to obtain the attribute influence analysis results;

[0010] Based on the attribute influence analysis results, attribute reduction is performed on the first rough set to obtain the reduced dataset and data classification rules.

[0011] Furthermore, the analysis of the degree of influence of each conditional attribute on the decision attribute includes:

[0012] The influence of each condition attribute on the decision attribute is analyzed based on the upper and lower approximations of the first rough set.

[0013] Furthermore, based on the upper and lower approximations of the first rough set, the degree of influence of each conditional attribute on the decision attribute is analyzed, including:

[0014] Step S1. Select Conditional Attribute C i , i∈m, where m represents the number of conditional attributes;

[0015] Step S2. Delete the conditional attribute C from each element in the first rough set. i The attribute values ​​are used to obtain the second rough set;

[0016] Step S3. Calculate the upper and lower approximations of the first rough set and the second rough set respectively;

[0017] Step S4. Determine whether the upper and lower approximations of the second rough set have changed relative to the upper and lower approximations of the first rough set. If so, restore the conditional attribute C of each element in the first rough set. i If the attribute value is not found, proceed directly to step S5;

[0018] In step S5, if i ≤ m, let i = i + 1 and return to step S1; otherwise, output the attribute that affects the analysis result.

[0019] Furthermore, attribute reduction of the first rough set based on the attribute influence analysis results includes:

[0020] Construct the positive domain of the first rough set based on the attribute influence analysis results;

[0021] Attribute analysis in the positive domain identifies the attribute that has the greatest impact on the decision attribute, which is denoted as the kernel attribute.

[0022] Reduce all attributes except the kernel attribute to generate a reduced dataset and data classification rules.

[0023] Furthermore, before extracting the various attributes and their value ranges involved in the electricity consumption data, the following steps are also included:

[0024] The electricity consumption data is cleaned and normalized.

[0025] Furthermore, by performing full permutations of each attribute based on its value range, the first rough set is obtained, which includes:

[0026] The arrangement result is obtained by permuting all attributes according to their value range:

[0027] The first rough set is obtained by removing duplicates from the permutation results.

[0028] Furthermore, electricity consumption data includes abnormal business data of the power system.

[0029] Furthermore, the sources of electricity consumption data include one or more of the marketing system, metering system, and production system.

[0030] Secondly, the present invention provides an electricity data reduction device, comprising:

[0031] The data acquisition unit is used to acquire electricity consumption data;

[0032] The attribute extraction unit is used to extract the various attributes and their value ranges involved in the electricity consumption data.

[0033] The attribute permutation unit is used to determine the decision attribute and condition attribute among the attributes. The first rough set is obtained by permuting the attributes according to the value range of each attribute.

[0034] The attribute influence analysis unit is used to analyze the degree of influence of each condition attribute on the decision attribute and obtain the attribute influence analysis results.

[0035] The data reduction element is used to reduce the attributes of the first rough set based on the attribute influence analysis results, thereby obtaining the reduced dataset and classification rules.

[0036] Thirdly, the present invention provides an electronic device including a memory storing computer-executable instructions and a processor, wherein when the computer-executable instructions are executed by the processor, the device performs the steps of the power consumption data reduction method provided in the first aspect.

[0037] Fourthly, the present invention also provides a readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, it implements the various processing flows of the electricity data reduction method provided in the first aspect.

[0038] As can be seen from the above technical solutions, the present invention has the following beneficial effects:

[0039] This invention provides a method, apparatus, device, and readable storage medium for electricity data reduction. The method obtains elements in a rough set by performing full permutations of all attributes of the data. It then uses a rough set attribute reduction method to determine the key attributes that affect decision-making. The data processing of full permutations and attribute reduction can be completed programmatically. It can quickly perform full combinations of all attributes and their value ranges of business data to obtain all possible combinations. Finally, it uses a reduction algorithm to obtain reduced data and data classification rules, which greatly improves the efficiency and accuracy of data auditing. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0041] Figure 1 A flowchart illustrating the implementation of the electricity data reduction method provided in this application embodiment;

[0042] Figure 2 A structural block diagram of the power consumption data reduction device provided in the embodiments of this application;

[0043] Figure 3 This is an electronic device architecture diagram provided for an embodiment of this application. Detailed Implementation

[0044] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0045] Traditional manual auditing methods cannot meet the needs of current marketing auditing work. There is an urgent need for new digital and intelligent auditing methods. By constructing a new auditing model that covers the entire marketing business, process, and process, we can focus on online real-time dynamic monitoring and analysis of important business anomalies such as electricity price execution, business expansion and installation applications, electricity billing, metering data, and concurrent line loss. We can also conduct key audits on key links and factors in marketing auditing work.

[0046] Rough set reduction is a data reduction method in rough set theory used to simplify datasets while preserving key information. It addresses problems of uncertainty and roughness, and is particularly suitable for data analysis in information systems. Key concepts in rough set reduction include "positive domain" and "redundancy." The positive domain refers to the set of samples that accurately determines the decision attribute under given conditions, while redundancy refers to unnecessary information within the sample set. The goal of rough set reduction is to obtain a more compact data description by eliminating redundancy, while maintaining accurate judgments of decision attributes.

[0047] Based on this, the present invention provides a method, apparatus, device and readable storage medium for reducing electricity consumption data through the following embodiments. According to the business control rules, a full permutation and combination intelligent algorithm is used to arrange and combine business items with corresponding business attribute features to form a full abnormal database of business items, business attributes and rules. The attribute reduction algorithm is used to sort out the business process, business links and business item information involved in each link.

[0048] See Figure 1 In one embodiment, this application provides a method for simplifying electricity consumption data, including the following steps:

[0049] Step S110. Obtain electricity consumption data.

[0050] In this step, the electricity consumption data mainly comes from abnormal business data of the power system, such as abnormal phenomena in the quality of marketing work and business results, as well as non-standard data in the marketing management system. The data from these systems are integrated, analyzed and processed, and the processed data is used as the input of the reduction algorithm.

[0051] Specifically, attribute reduction can be performed on critical business anomaly data such as electricity pricing, business expansion applications, electricity billing, metering data, and concurrent line losses before auditing. This data often has multiple attributes; relying on manual auditing would be labor-intensive, subjective, and fail to accurately reflect the correlations between attributes, leading to significant workload for subsequent tasks such as fault analysis. By performing attribute reduction on large-scale electricity consumption data, a subset of attributes is selected from the original attribute set to retain key information while reducing redundancy and improving data processing efficiency.

[0052] In some embodiments, electricity consumption data can be obtained from multiple systems such as marketing, metering, and production under the new power system. For example, data such as the industry, electricity demand, historical electricity consumption records, region, and electricity consumption in different time periods of electricity users can be used to extract abnormal phenomena in the quality of marketing work and business results, as well as non-compliant data in the marketing management system.

[0053] Step S120. Extract the attributes and their value ranges involved in the electricity consumption data.

[0054] In this step, by analyzing electricity consumption data, we can identify the business items and their associated attributes. Specifically, different data objects have different or the same associated attributes, giving each object distinct characteristics. These associated attributes affect the business items. Different business items determine how many categories the electricity consumption database can be divided into. The attribute values ​​of business items are directly influenced by their associated attributes. In other words, each associated attribute can potentially be a factor influencing the attribute values ​​of a business item. Some associated attributes will significantly affect the results, while others will have a less significant impact.

[0055] For example, taking the basic electricity bill calculation method as a business item, its attribute values ​​include "high voltage high metering", "high voltage low metering", and "low voltage low metering". Its associated attributes include user type, user status, electricity consumption behavior, energy structure, etc. Some of these associated attributes will significantly affect the attribute values ​​of the basic electricity bill calculation method, while others will have little impact. Therefore, the associated attributes with significant impact can be used as key attributes and output as data classification rules, while the associated attributes with little impact can be reduced to simplify the data structure and improve data processing efficiency.

[0056] For example, taking the loss allocation method as a business item, its attribute values ​​include "no allocation", "allocated according to the agreement ratio", "allocated according to the capacity ratio", "allocated according to the electricity ratio", "calculated according to the agreement", and "participated in the calculation but not allocated". Its associated attributes include transformer capacity, electricity consumption, electricity usage period, user type, loss rate, etc. Similarly, some of these associated attributes will significantly affect the attribute values ​​of the loss allocation method, while others will have little impact. Therefore, the associated attributes with significant impact can be used as key attributes and output as data classification rules, while the associated attributes with little impact can be reduced to simplify the data structure and improve data processing efficiency.

[0057] Step S130. Determine the decision attribute and condition attribute among the attributes, and perform a full permutation of each attribute according to the value range of each attribute to obtain the first rough set.

[0058] In this step, a full permutation of the business items and their associated attributes is performed, which can calculate all the possible combinations and form a complete data table.

[0059] Specifically, the first rough set is obtained by permuting the decision attribute and condition attribute according to the value range of each attribute, with the business item as the decision attribute and one or more associated attributes as condition attributes.

[0060] In some embodiments, the arrangement of multiple conditional attributes can be considered ordered, and from the perspective of attribute values, the substantive content corresponding to the possible occurrence elements of the first rough set is the same.

[0061] In some embodiments, since the order of conditional attributes does not affect the final output of decision attributes, the order of multiple conditional attributes can be disregarded. However, it is necessary to deduplicate the permutation results before outputting the first rough set.

[0062] For example, suppose business item C has attribute values ​​C1 and C2. Business item C is used as the decision attribute. The associated attributes of business item C are A and B. Attributes A and B are used as condition attributes. Attribute A has attribute values ​​A1 and A2, and attribute B has attribute values ​​B1 and B2. The first rough set is obtained by permuting attributes A, B, and C. There are a total of 2 × 2 × 2 = 8 elements.

[0063] Step S140. Analyze the degree of influence of each condition attribute on the decision attribute, and obtain the attribute influence analysis results.

[0064] In this step, methods such as model-based and rough set theory can be used to calculate the degree of influence of each conditional attribute on the decision attribute, also known as importance. The attribute influence analysis results can present key attributes and non-key attributes. Key attributes are considered to be attributes that frequently appear in the rules and have a significant impact on the decision attribute. The attribute influence analysis results are used as reduction rules for data attribute reduction, so that the dataset retains the key information of the original dataset. The reduced dataset can still maintain an accurate expression of the decision attribute.

[0065] In some embodiments, this application uses rough set theory to analyze the degree of influence of conditional attributes on decision attributes, and analyzes the influence of conditional attributes on the accurate expression of decision attributes through upper and lower approximations of the first rough set.

[0066] Specifically, if the upper and lower approximations of the first rough set do not change when a certain conditional attribute does not exist, it means that the conditional attribute is redundant and can be reduced. Otherwise, it means that the conditional attribute significantly affects the decision attribute, thus affecting the correct representation of the decision by the dataset, and needs to be retained. By traversing the conditional attributes, the minimum attribute set is found so that the positive domain of the knowledge set formed by the dataset maintains the correct representation of the decision.

[0067] The upper approximation refers to the smallest definable set containing the elements of a given set, while the lower approximation is the largest definable set contained in a given set.

[0068] In some embodiments, the influence of each conditional attribute on the decision attribute is analyzed according to the upper and lower approximations of the first rough set. This involves iterating through the conditional attributes one by one, deleting the attribute values ​​corresponding to the elements in the rough set, and then recalculating the upper and lower approximations of the rough set. If the upper and lower approximations of the rough set change after the conditional attribute is deleted, the deleted conditional attribute is restored, and the next conditional attribute is iterated until all conditional attributes have been iterated.

[0069] In some embodiments, analyzing the influence of each conditional attribute on the decision attribute based on the upper and lower approximations of the first rough set may include the following steps:

[0070] Step S141. Select Conditional Attribute C i , i∈m, where m represents the number of conditional attributes.

[0071] Step S142. Delete the conditional attribute C from each element in the first rough set. i The attribute values ​​are used to obtain the second rough set.

[0072] Step S143. Calculate the upper and lower approximations of the first rough set and the second rough set respectively.

[0073] Step S144. Determine whether the upper and lower approximations of the second rough set have changed relative to the upper and lower approximations of the first rough set. If so, restore the conditional attribute C of each element in the first rough set. i If the attribute value is not found, proceed directly to step S145.

[0074] In step S145, if i ≤ m, let i = i + 1 and return to step S141; otherwise, output attributes that affect the analysis results.

[0075] The above traversal process can filter out key attributes that have a significant impact on decision attributes and non-key attributes that have no significant impact, generating attribute impact analysis results for attribute reduction.

[0076] Step S150. Based on the attribute influence analysis results, perform attribute reduction on the first rough set to obtain the reduced dataset and data classification rules.

[0077] In this step, a certain number of attributes are selected as the reduced attribute set, i.e., key attributes, based on the attribute impact analysis results. These attributes should be able to provide information for accurate judgment of decision attributes, while reducing redundancy. Based on the selected attributes, a reduced dataset is generated, which retains the key information of the original dataset but reduces the number of attributes.

[0078] Specifically, the positive domain of the first rough set is constructed using rough set theory to obtain the reduced dataset and data classification rules. After calculating the positive domain of the set, data classification rules can be generated based on this information. The positive domain contains objects that are correctly classified under a given concept. Rules can be extracted from these objects, and these rules describe the classification situation under given conditions.

[0079] For example, attribute reduction of the first rough set involves the following steps:

[0080] Step S151. Construct the positive domain of the first rough set based on the attribute influence analysis results.

[0081] Step S152. Analyze the attributes in the positive domain to determine the attribute that has the greatest impact on the decision attribute, and denote it as the kernel attribute.

[0082] Step S153. Reduce the attributes other than the kernel attribute to generate a reduced dataset and data classification rules.

[0083] The above embodiments describe in detail the implementation process of the electricity data reduction method provided in this application from various aspects. By performing full permutation of each attribute of the data to obtain each element in the rough set, the key attributes affecting the decision attributes are determined using the rough set attribute reduction method. The data processing process of full permutation and attribute reduction can be completed programmatically, which can quickly perform full combination of each attribute and its value range of the business data to obtain all combination cases. Then, the reduction algorithm is used to obtain the reduced data and data classification rules, which greatly improves the efficiency and accuracy of data auditing and can effectively avoid auditing errors caused by the subjective judgment of the auditors.

[0084] To further illustrate the electricity data simplification method provided in this application, a specific example is provided below.

[0085] By analyzing the database tables of the marketing system, a list of business items and related attributes for the business expansion and packaging business data was generated. The business item is "Metering Method," and its related attributes are "User Type" and "User Status." The "User Type" attribute has two values: "Dedicated Transformer User" and "Public Transformer User"; the "User Status" attribute has two values: "Running" and "Disabled"; and the "Metering Method" has three values: "High Voltage High Metering," "High Voltage Low Metering," and "Low Voltage Low Metering." The business items and their related attributes are represented in the following two-dimensional table, Table 1.

[0086] Table 1

[0087] Data item number Data item name Attribute Number Attribute value 1 User type 1-1 Specialized users 1 User type 1-2 public transformer users 2 User Status 2-1 run 2 User Status 2-2 Discontinued 3 Measurement method 3-1 High voltage meter 3 Measurement method 3-2 High voltage low meter 3 Measurement method 3-3 Low pressure low meter

[0088] Based on the value range of each attribute, the business item "Metering Method" and its associated attributes "User Type" and "User Status" are fully permuted to obtain the full data table, as shown in Table 2 below.

[0089] Table 2

[0090] Data Combination User type User Status Measurement method 1 Specialized users run High voltage meter 2 Specialized users run High voltage low meter 3 Specialized users run Low pressure low meter 4 Specialized users Discontinued High voltage meter 5 Specialized users Discontinued High voltage low meter 6 Specialized users Discontinued Low pressure low meter 7 public transformer users run High voltage meter 8 public transformer users run High voltage low meter 9 public transformer users run Low pressure low meter 10 public transformer users Discontinued High voltage meter 11 public transformer users Discontinued High voltage low meter 12 public transformer users Discontinued Low pressure low meter

[0091] Select the business item "Metering Method" as the decision attribute, and the associated attributes "User Type" and "User Status" as condition attributes.

[0092] Delete conditional attributes one by one, and calculate the upper and lower approximations of the dataset before and after the attribute deletion. Determine whether the upper and lower approximations of the dataset change. If the upper and lower approximations change after the attribute deletion, restore the currently deleted attribute item. For example, first delete the attribute "User Type", then calculate the upper and lower approximations of the dataset before and after the attribute deletion. If there is a change, it means that the attribute "User Type" has a significant impact on the decision attribute "Measurement Method", and should be restored and retained as an attribute set of the data. Otherwise, the attribute "User Type" can be considered redundant and can be reduced. Repeat the above deletion and upper and lower approximation calculation process for the attribute "User Status", and then output the attribute impact analysis results.

[0093] Based on rough set theory, attributes to be retained are selected according to the results of attribute influence analysis, the positive domain of the dataset is constructed, and the reduced dataset and data classification rules are generated. This dataset retains the key information of the original dataset, and the data classification rules describe the data classification under given conditions.

[0094] The above-disclosed embodiments describe in detail a method for simplifying electricity consumption data. This method can be implemented using various types of devices. Therefore, the present invention also discloses an electricity consumption data simplification device corresponding to the above method. Specific embodiments are given below for detailed description.

[0095] like Figure 2 As shown, one embodiment of this application provides an electricity data reduction device, including a data acquisition unit 210, an attribute extraction unit 220, an attribute permutation unit 230, an attribute influence analysis unit 240, and a data reduction unit 250. Specifically, it includes the following:

[0096] The data acquisition unit 210 is used to acquire electricity consumption data.

[0097] The attribute extraction unit 220 is used to extract the various attributes and their value ranges involved in the electricity consumption data.

[0098] The attribute permutation unit 230 is used to determine the decision attribute and condition attribute among the attributes, and to perform a full permutation of the attributes according to the value range of each attribute to obtain the first rough set.

[0099] The attribute influence analysis unit 240 is used to analyze the degree of influence of each condition attribute on the decision attribute and obtain the attribute influence analysis results.

[0100] The data is simplified to element 250, which is used to reduce the attributes of the first rough set based on the attribute influence analysis results, so as to obtain the reduced dataset and classification rules.

[0101] The power consumption data reduction device provided in this application embodiment has the same implementation principle and technical effect as the aforementioned method embodiment. For the sake of brevity, any parts not mentioned in the device embodiment can be referred to the corresponding content in the aforementioned method embodiment.

[0102] See Figure 3 This document illustrates a hardware block diagram of an electronic device intended to represent various forms of digital computers, such as laptops, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present application described and / or claimed herein.

[0103] like Figure 3 As shown, the electronic device includes: at least one processor 1, at least one communication interface 2, at least one memory 3, and at least one communication bus 4;

[0104] In this embodiment, the number of processor 1, communication interface 2, memory 3, and communication bus 4 is at least one, and processor 1, communication interface 2, and memory 3 communicate with each other through communication bus 4.

[0105] Processor 1 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention.

[0106] Memory 3 may include high-speed RAM, and may also include non-volatile memory, such as at least one disk storage device;

[0107] The memory stores a program, which the processor can call. The program is used to implement the various processing steps of the aforementioned electricity data reduction scheme.

[0108] This invention also provides a readable storage medium storing a computer program thereon. When the computer program is executed by a processor, it implements various processing flows of the electricity data reduction scheme provided in any possible implementation of the above embodiments and / or in combination with the embodiments.

[0109] The invention has been described in particular detail above with respect to possible scenarios, and those skilled in the art will recognize that the invention can be practiced through other embodiments. Specific naming of components, capitalization of terms, attributes, data structures, or any other programming or structural aspects are not mandatory or important, and the mechanisms or features of implementing the invention may have different names, forms, or procedures. The system can be implemented through a combination of hardware and software (as described), entirely through hardware elements, or entirely through software elements. The specific division of functions among the various system components described herein is merely exemplary and not mandatory; rather, the functions performed by a single system component can be performed by multiple components, or the functions performed by multiple components can be performed by a single component.

[0110] Those skilled in the art should understand that the various steps of the disclosed methods can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using device-executable program code, which can then be stored in a storage device for execution by the computing device. Alternatively, they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Therefore, the embodiments disclosed in this invention are not limited to any specific hardware and software combination.

[0111] The programs (also referred to as programs, software, software applications, or code) executable by these computing devices include machine instructions of a programmable processor and can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. As used herein, the terms “machine-readable medium” and “computer-readable medium” refer to any computer program product, device, and / or apparatus (e.g., disk, optical disk, memory, programmable logic device (PLD)) used to provide machine instructions and / or data to a programmable processor, including machine-readable media that receive machine instructions as machine-readable signals. The term “machine-readable signal” refers to any signal used to provide machine instructions and / or data to a programmable processor.

[0112] Certain aspects of this invention include the process steps and instructions described herein in algorithmic form. It should be noted that the process steps and instructions of this invention can be implemented in software, firmware, and / or hardware, and when implemented in software, they can be downloaded, stored on various operating systems and operated from said platforms.

[0113] Those skilled in the art will understand that the structures shown in the figures are merely block diagrams of some structures related to the present application and do not constitute a limitation on the terminal device to which the present application is applied. Specific terminal devices may include more or fewer components than those shown in the figures, or combine certain components, or have different component arrangements.

[0114] In the description of this specification, the references to terms such as "an embodiment," "some embodiments," "example," "specific example," "a particular implementation," or "possible design," etc., refer to a specific feature, structure, material, or characteristic described in connection with that embodiment or example, which is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0115] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0116] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for simplifying electricity consumption data, characterized in that, include: Obtain electricity consumption data; Extract the attributes and their value ranges involved in the electricity consumption data; Determine the decision attribute and condition attribute among the attributes, and obtain the first rough set by performing a full permutation of the attributes according to their value ranges; The influence of each conditional attribute on the decision attribute is analyzed, specifically based on the upper and lower approximations of the first rough set, as follows: Step S1. Select Conditional Attributes , m represents the number of conditional attributes; Step S2. Delete the conditional attributes from each element in the first rough set. The attribute values ​​are used to obtain the second rough set; Step S3. Calculate the upper and lower approximations of the first rough set and the second rough set respectively; Step S4. Determine whether the upper and lower approximations of the second rough set have changed relative to the upper and lower approximations of the first rough set. If so, restore the conditional attributes of each element in the first rough set. If the attribute value is not found, proceed directly to step S5; In step S5, if i ≤ m, let i = i + 1 and return to step S1; otherwise, output attributes affect the analysis results. Based on the attribute influence analysis results, the first rough set is reduced to obtain a reduced dataset and data classification rules.

2. The method according to claim 1, characterized in that, The attribute reduction of the first rough set based on the attribute influence analysis results includes: Construct the positive domain of the first rough set based on the attribute influence analysis results; Attribute analysis within the positive domain identifies the attribute with the greatest impact on decision attributes, denoted as the kernel attribute. Reduce the attributes other than the kernel attribute to generate a reduced dataset and data classification rules.

3. The method according to claim 1, characterized in that, Before extracting the various attributes and their value ranges involved in the electricity consumption data, the process also includes: The electricity consumption data is cleaned and normalized.

4. The method according to claim 1, characterized in that, The step of permuting all attributes according to their value ranges to obtain the first rough set includes: The arrangement result is obtained by permuting all attributes according to their value range: The first rough set is obtained by removing duplicates from the arrangement results.

5. The method according to claim 1, characterized in that, The electricity consumption data includes abnormal business data of the power system.

6. A device for simplifying electricity consumption data, characterized in that, include: The data acquisition unit is used to acquire electricity consumption data; The attribute extraction unit is used to extract the various attributes and their value ranges involved in the electricity consumption data. The attribute permutation unit is used to determine the decision attribute and condition attribute among the attributes. The first rough set is obtained by permuting the attributes according to the value range of each attribute. The attribute influence analysis unit is used to analyze the degree of influence of each condition attribute on the decision attribute. Specifically, it performs the following analysis process based on the upper and lower approximations of the first rough set: Step S1. Select Conditional Attributes , m represents the number of conditional attributes; Step S2. Delete the conditional attributes from each element in the first rough set. The attribute values ​​are used to obtain the second rough set; Step S3. Calculate the upper and lower approximations of the first rough set and the second rough set respectively; Step S4. Determine whether the upper and lower approximations of the second rough set have changed relative to the upper and lower approximations of the first rough set. If so, restore the conditional attributes of each element in the first rough set. If the attribute value is not found, proceed directly to step S5; In step S5, if i ≤ m, let i = i + 1 and return to step S1; otherwise, output attributes affect the analysis results. The data reduction element is used to reduce the attributes of the first rough set based on the attribute influence analysis results, thereby obtaining the reduced dataset and classification rules.

7. An electronic device, characterized in that, It includes a memory storing computer-executable instructions and a processor, which, when executed by the processor, causes the device to perform the power consumption data reduction method as described in any one of claims 1 to 5.

8. A readable storage medium, characterized in that, It stores a computer program, which, when executed by a processor, implements the electricity data reduction method according to any one of claims 1 to 5.

Images