Big data electricity cost real-time accounting abnormality early warning method, system, device and medium

Abstract

The application relates to a big data electricity cost real-time accounting abnormality early warning method, system, device and medium, the method comprises the following steps: acquiring preprocessed multi-source power consumption data and electricity cost accounting related information; fusing the preprocessed multi-source power consumption data and the electricity cost accounting related information to obtain a power consumption feature matrix; generating a composite electricity price rule according to the electricity cost accounting related information, and performing real-time electricity cost accounting according to the power consumption feature matrix and the composite electricity price rule to obtain a cost breakdown; performing power consumption behavior analysis according to the power consumption feature matrix, and performing abnormality judgment in combination with the cost breakdown to obtain an abnormality analysis result; performing abnormality early warning processing according to the abnormality analysis result to obtain an abnormality early warning disposal result. The application has the effect of improving accounting early warning efficiency.

Description

Technical Field

[0001] This invention belongs to the technical field of power information technology and smart grid, and in particular relates to a method, system, equipment and medium for real-time calculation of electricity bills based on big data and early warning of anomalies. Background Technology

[0002] Currently, electricity billing is a crucial part of electricity marketing, and its results directly impact the revenue management of power supply companies and the electricity experience of users. With the widespread application of billing rules such as time-of-use pricing and tiered pricing, and the increasing differentiation in user electricity consumption behavior, electricity billing places higher demands on the timeliness, accuracy, and transparency of electricity consumption data. At the same time, power supply companies also need to keep abreast of changes in user electricity consumption and costs to adapt to the needs of refined electricity billing management.

[0003] Current electricity billing typically uses periodic meter reading and centralized calculation, relying mainly on collected electricity consumption data to generate billing results. This method is prone to problems such as delayed cost feedback, calculation discrepancies, and untimely detection of anomalies when user electricity consumption changes rapidly, billing rules switch, or data fluctuates abnormally. This makes it difficult for users to understand changes in electricity bills in a timely manner and increases the management burden on power supply companies in handling electricity bill disputes and abnormal electricity consumption events. Summary of the Invention

[0004] The purpose of this invention is to provide a method, system, device and medium for real-time electricity bill calculation and early warning of anomalies, in order to solve the technical problem that the existing electricity bill calculation method has low efficiency in managing abnormal electricity bills due to the lag in cost feedback.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: In a first aspect, the present invention provides a method for real-time calculation and early warning of anomalies in big data electricity billing, the method comprising: Obtain preprocessed multi-source electricity consumption data and related information for electricity billing; The preprocessed multi-source electricity consumption data and the electricity billing association information are fused to obtain an electricity consumption feature matrix; A composite electricity price rule is generated based on the electricity billing association information, and a real-time electricity billing is performed based on the electricity consumption feature matrix and the composite electricity price rule to obtain a detailed billing statement. Based on the electricity consumption characteristic matrix, electricity consumption behavior is analyzed, and anomaly judgment is made in conjunction with the cost details to obtain anomaly analysis results; Based on the anomaly analysis results, anomaly warning processing is performed to obtain the anomaly warning handling results.

[0006] By adopting the above technical solutions, and by acquiring preprocessed multi-source electricity consumption data and electricity billing correlation information, it is possible to provide organized basic electricity consumption data and billing correlation basis for electricity billing, thereby reducing calculation errors caused by scattered data sources and inconsistent formats. By fusing the preprocessed multi-source electricity consumption data and electricity billing correlation information, an electricity consumption feature matrix is ​​obtained, which can uniformly represent user electricity consumption status, billing correlation information, and external influencing factors, thereby improving the data integrity of subsequent electricity billing and anomaly analysis. By generating composite electricity price rules based on electricity billing correlation information and combining them with the electricity consumption feature matrix for real-time electricity billing, it is possible to generate detailed cost information according to the user's actual electricity consumption and applicable billing rules, thereby improving the real-time performance and accuracy of electricity billing. By analyzing electricity consumption behavior based on the electricity consumption feature matrix and combining it with cost details for anomaly judgment, it is possible to identify anomalies from both the perspectives of electricity consumption behavior changes and cost changes, thereby improving the accuracy of anomaly judgment. By performing anomaly early warning processing based on the anomaly analysis results, anomaly early warning and handling results can be generated, thereby improving the response and handling efficiency of abnormal events.

[0007] In one example, the present invention can be further configured as follows: obtaining the preprocessed multi-source electricity consumption data and electricity billing related information includes: Obtain power consumption parameters reported by various types of electrical equipment to form multi-source power consumption data to be processed; Add timestamps and device identifiers to the multi-source power consumption data to be processed to obtain identifiable multi-source power consumption data; By accessing user profiles, electricity pricing policies, and meteorological data, the electricity billing information can be obtained. The identified multi-source power consumption data is preprocessed to obtain the preprocessed multi-source power consumption data.

[0008] By adopting the above technical solutions, and by acquiring electricity consumption parameters reported by various types of electrical equipment, it is possible to form multi-source electricity consumption data to be processed, covering different equipment sources, thereby improving the comprehensiveness of electricity consumption data collection. By attaching timestamps and equipment identifiers to the multi-source electricity consumption data to be processed, the collection time and data source of the electricity consumption data can be clearly identified, thereby improving the accuracy of data traceability and subsequent corresponding processing. By accessing user files, electricity pricing policies, and meteorological data, electricity billing calculation-related information can be formed, thereby providing auxiliary basis for electricity pricing rule generation, user association, and anomaly judgment. By preprocessing the identified multi-source electricity consumption data, multi-source electricity consumption data suitable for subsequent fusion and calculation can be obtained, thereby improving the quality of data processing.

[0009] In one example, the present invention can be further configured as follows: preprocessing the identified multi-source electricity consumption data to obtain preprocessed multi-source electricity consumption data includes: Based on the timestamp and the device identifier, the identified multi-source power consumption data is processed to obtain the corresponding multi-source power consumption data. Anomaly detection is performed on the corresponding multi-source power consumption data to obtain valid multi-source power consumption data; The valid multi-source power consumption data is processed by performing missing data completion, range conversion, unit unification, and time zone calibration to obtain the preprocessed multi-source power consumption data.

[0010] By adopting the above technical solutions, and performing data mapping processing on tagged multi-source electricity consumption data based on timestamps and device identifiers, data from different sources and at different collection times can be uniformly mapped, thereby improving the matching accuracy between multi-source data. By performing abnormal data detection on the mapped multi-source electricity consumption data, abnormal data that affects the reliability of accounting can be eliminated or marked, thereby improving the credibility of data participating in subsequent calculations. By performing missing data completion, range conversion, unit unification, and time zone calibration on valid multi-source electricity consumption data, missing data, differences in dimensions and time calibrates can be eliminated, thereby improving the consistency and usability of preprocessed multi-source electricity consumption data.

[0011] In one example, the present invention can be further configured as follows: the electricity billing association information includes user profiles, electricity pricing policies, and meteorological data; the step of fusing the preprocessed multi-source electricity consumption data and the electricity billing association information to obtain an electricity consumption feature matrix includes: Based on the user profiles in the electricity billing association information, the preprocessed multi-source electricity consumption data is associated with users to obtain user-associated electricity consumption data. Based on the time information corresponding to the user-associated electricity consumption data, the user-associated electricity consumption data is fused with the electricity pricing policy and meteorological data in the electricity billing information to obtain fused electricity consumption data; Daily electricity consumption, peak-valley ratio, and power fluctuation coefficient are extracted from the fused electricity consumption data to obtain a set of electricity consumption characteristics. The electricity consumption feature set is matrixed according to the same field structure to obtain the electricity consumption feature matrix.

[0012] By adopting the above technical solutions, and by associating preprocessed multi-source electricity consumption data with users based on user profiles, data collected from the equipment side can be accurately aggregated to the corresponding users, thereby improving the accuracy of user-level electricity billing and electricity consumption analysis. By integrating user-associated electricity consumption data with electricity pricing policies and meteorological data based on time information, the electricity consumption data, billing conditions, and environmental factors for the same time period can be kept consistent, thereby improving the temporal consistency of the integrated electricity consumption data. By extracting daily electricity consumption, peak-valley ratio, and power fluctuation coefficient from the integrated electricity consumption data, a set of electricity consumption characteristics reflecting the scale of electricity consumption, time period structure, and load changes can be formed, thereby improving the ability to characterize user electricity consumption status. By matrixing the set of electricity consumption characteristics according to the same field structure, a unified electricity consumption characteristic matrix can be obtained, which facilitates subsequent real-time accounting, behavior analysis, and anomaly detection.

[0013] In one example, the present invention can be further configured as follows: the electricity billing information includes electricity pricing policies; the step of generating composite electricity pricing rules based on the electricity billing information, and performing real-time electricity billing based on the electricity consumption feature matrix and the composite electricity pricing rules to obtain detailed expense statements includes: The effective time, applicable scope and billing parameters of the electricity price policy are extracted from the electricity billing information to obtain the electricity price rule elements. Based on the electricity price rule elements, a corresponding composite electricity price rule is generated, and the composite electricity price rule is associated with the corresponding effective time to obtain the target composite electricity price rule; The electricity consumption data of users in each electricity consumption period is determined based on the electricity consumption feature matrix. Based on the target composite electricity price rule, the electricity consumption data for each electricity consumption period is used to calculate the cost details.

[0014] By adopting the above technical solutions, the effective time, applicable scope, and billing parameters of the electricity pricing policy can be extracted from the electricity billing information to form electricity pricing rule elements, thereby improving the accuracy of generating composite electricity pricing rules. By generating composite electricity pricing rules based on the electricity pricing rule elements and associating them with the effective time, a target composite electricity pricing rule can be obtained, thus ensuring that the cost calculation matches the current effective electricity pricing policy. By determining the user's electricity consumption data in each electricity consumption period based on the electricity consumption characteristic matrix, the electricity consumption basis corresponding to different billing periods can be clarified, thereby improving the accuracy of time-of-use cost calculation. By calculating the cost based on the electricity consumption data in each electricity consumption period according to the target composite electricity pricing rule, a detailed cost breakdown can be generated, thereby improving the verifiability and transparency of the electricity billing results.

[0015] In one example, the present invention can be further configured as follows: the step of performing electricity consumption behavior analysis based on the electricity consumption feature matrix and combining it with the cost details to determine anomalies and obtain anomaly analysis results includes: Based on the electricity consumption feature matrix, users' electricity consumption fluctuations, peak-valley ratios, and electricity consumption time distribution are extracted to obtain electricity consumption behavior characteristics. Based on the electricity consumption feature matrix, determine the historical concurrent behavior features corresponding to the electricity consumption behavior features, compare the electricity consumption behavior features with the historical concurrent behavior features, and obtain a behavior change report; Based on the aforementioned cost details, determine the user's cost changes during different electricity usage periods; By combining the behavior change report and the cost change information, the abnormal electricity consumption and billing are judged, and the abnormality analysis results are obtained.

[0016] By adopting the above technical solutions, and extracting user electricity consumption fluctuations, peak-valley ratios, and electricity consumption time distribution from the electricity consumption feature matrix, electricity consumption behavior characteristics can be obtained, thereby improving the ability to identify user electricity consumption patterns. By comparing electricity consumption behavior characteristics with historical behavior characteristics of the same period, behavior change reports can be obtained, thereby discovering changes in user electricity consumption status compared to the same period in history. By determining cost change information within different electricity consumption time periods based on cost details, the time source and magnitude of cost changes can be clarified, thereby improving the targeting of billing anomaly analysis. By combining behavior change reports and cost change information to judge electricity consumption anomalies and billing anomalies, anomaly analysis results can be obtained, thereby improving the accuracy and interpretability of anomaly identification.

[0017] In one example, the present invention can be further configured as follows: the abnormality early warning processing based on the abnormality analysis results to obtain the abnormality early warning handling result includes: Based on the anomaly analysis results, determine the anomaly points and the corresponding anomaly cause information; Based on the anomaly analysis results, the anomaly deviation degree, duration, and scope of impact are calculated to obtain an anomaly score; An anomaly level is determined based on the anomaly score, and tiered push notifications are generated according to the anomaly level. The abnormal point, the abnormal cause information, the abnormal level, and the hierarchical push information are associated and recorded to obtain the abnormal early warning and handling result.

[0018] By adopting the above technical solutions, and by determining the anomaly points and causes based on the anomaly analysis results, the objects of anomalies and their cause types can be clearly identified, thereby improving the targeting of anomaly handling. By calculating the anomaly deviation, duration, and scope of impact based on the anomaly analysis results, anomaly scores can be obtained, thereby quantifying the severity of the anomaly event. By determining the anomaly level based on the anomaly score and generating tiered push information, anomalies of different severity can be pushed to the corresponding handling objects, thereby improving the efficiency of early warning response. By associating and recording anomaly points, anomaly cause information, anomaly levels, and tiered push information, anomaly early warning and handling results can be obtained, thereby achieving traceability and auditability of the anomaly handling process.

[0019] In a second aspect, the present invention provides a big data-based real-time electricity billing anomaly early warning system, the system comprising: The acquisition module is used to acquire preprocessed multi-source electricity consumption data and related information for electricity billing. The fusion module is used to fuse the preprocessed multi-source electricity consumption data and the electricity billing association information to obtain an electricity consumption feature matrix; The accounting module is used to generate composite electricity price rules based on the electricity cost accounting association information, and to perform real-time electricity cost accounting based on the electricity consumption feature matrix and the composite electricity price rules to obtain cost details; The analysis module is used to analyze electricity consumption behavior based on the electricity consumption feature matrix and to make anomaly judgments in conjunction with the cost details, so as to obtain anomaly analysis results. The early warning module is used to perform abnormal early warning processing based on the abnormality analysis results and obtain the abnormal early warning handling results.

[0020] By adopting the above technical solutions, and by acquiring preprocessed multi-source electricity consumption data and electricity billing correlation information, it is possible to provide organized basic electricity consumption data and billing correlation basis for electricity billing, thereby reducing calculation errors caused by scattered data sources and inconsistent formats. By fusing the preprocessed multi-source electricity consumption data and electricity billing correlation information, an electricity consumption feature matrix is ​​obtained, which can uniformly represent user electricity consumption status, billing correlation information, and external influencing factors, thereby improving the data integrity of subsequent electricity billing and anomaly analysis. By generating composite electricity price rules based on electricity billing correlation information and combining them with the electricity consumption feature matrix for real-time electricity billing, it is possible to generate detailed cost information according to the user's actual electricity consumption and applicable billing rules, thereby improving the real-time performance and accuracy of electricity billing. By analyzing electricity consumption behavior based on the electricity consumption feature matrix and combining it with cost details for anomaly judgment, it is possible to identify anomalies from both the perspectives of electricity consumption behavior changes and cost changes, thereby improving the accuracy of anomaly judgment. By performing anomaly early warning processing based on the anomaly analysis results, anomaly early warning and handling results can be generated, thereby improving the response and handling efficiency of abnormal events.

[0021] In a third aspect, the present invention provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the aforementioned method for real-time calculation and early warning of abnormalities in big data electricity bills.

[0022] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the aforementioned method for real-time calculation and early warning of abnormalities in big data electricity bills. Attached Figure Description

[0023] The accompanying drawings, which form part of this specification, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an undue limitation of the invention. In the drawings: Figure 1 This is a flowchart of a big data electricity bill real-time calculation anomaly early warning method in an embodiment of the present invention; Figure 2 A comparison chart of anomaly identification accuracy for different user types; Figure 3 A graph showing the relationship between the accuracy of electricity load forecasting and time series; Figure 4 This is a comparison chart of the core performance of the traditional system and the system of this invention; Figure 5 This is a comparison chart of system performance across different scenarios; Figure 6 This is a structural block diagram of the big data electricity bill real-time calculation anomaly early warning system in an embodiment of the present invention; Figure 7 This is a structural block diagram of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0024] The present invention will now be described in detail with reference to the accompanying drawings and embodiments. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0025] The following detailed description is exemplary and intended to provide further detailed explanation of the invention. Unless otherwise specified, all technical terms used in this invention have the same meaning as commonly understood by one of ordinary skill in the art. The terminology used in this invention is for describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention.

[0026] Example 1 like Figure 1 As shown, this invention discloses a method for real-time calculation and early warning of anomalies in big data electricity bills, which specifically includes the following steps: S10: Obtain preprocessed multi-source electricity consumption data and related information for electricity billing.

[0027] Specifically, through the data access process for electricity billing business, multi-source electricity consumption data that has completed basic cleaning, format sorting and time calibration is obtained. At the same time, electricity billing related information that can participate in cost calculation, behavior analysis and anomaly judgment is obtained. This enables subsequent fusion processing to cover electricity consumption status, user attributes, billing rules and external environmental factors on the basis of unified data, avoiding the delay in cost feedback or insufficient basis for anomaly judgment caused by calculating based on only a single electricity consumption data.

[0028] S20: The preprocessed multi-source electricity consumption data and electricity billing information are fused to obtain the electricity consumption feature matrix.

[0029] Specifically, the preprocessed multi-source electricity consumption data and electricity billing information are integrated according to user, device, time, and electricity consumption scenario. This allows the electricity consumption parameters, file attributes, billing rules, and environmental data of the same user or the same metering object within the same time range to form a unified data representation. Then, features that reflect the scale of electricity consumption, the distribution of electricity consumption periods, and the state of power fluctuations are extracted from the integrated data to form an electricity consumption feature matrix that can be used for both real-time accounting and anomaly detection.

[0030] S30: Generate composite electricity price rules based on electricity billing information, and perform real-time electricity billing based on the electricity consumption feature matrix and composite electricity price rules to obtain a detailed billing statement.

[0031] Specifically, the applicable billing rules for the current user are determined from the electricity billing information, and different billing rules are combined into a composite electricity price rule that can cover billing scenarios such as time-of-use, tiered pricing, and power regulation. Then, the cost is calculated based on the electricity consumption and related electricity status reflected in the electricity consumption feature matrix for each time period, so that the electricity consumption, applicable unit price, and amount for each billing period can be recorded synchronously, ultimately forming a detailed cost statement that can be used for anomaly detection and user query.

[0032] S40: Analyze electricity consumption behavior based on the electricity consumption characteristic matrix and combine it with cost details to determine anomalies and obtain anomaly analysis results.

[0033] Specifically, based on the changes in electricity consumption, the ratio of peak and valley electricity consumption, and the distribution of electricity consumption periods reflected in the electricity consumption feature matrix, the current electricity consumption behavior of users is identified. The identification results are then combined with the cost changes in the cost details for analysis. This allows the anomaly judgment to consider whether the electricity consumption behavior deviates significantly from the normal state and whether there are abnormal fluctuations in the cost calculation results. Finally, an anomaly analysis result containing both electricity consumption anomaly and billing anomaly judgments is formed.

[0034] S50: Based on the anomaly analysis results, perform anomaly warning processing to obtain the anomaly warning handling results.

[0035] Specifically, based on the anomaly analysis results, the abnormal objects requiring warning, the degree of anomaly, and the direction of anomaly handling are determined. The anomaly-related information is then classified, organized, and recorded, so that the anomaly warning is no longer limited to a simple prompt, but can form an anomaly warning and handling result that includes the abnormal object, the cause of the anomaly, the anomaly level, and the push information, providing a basis for subsequent user reminders, operation and maintenance verification, auditing, or emergency response.

[0036] In one embodiment, step S10, namely acquiring preprocessed multi-source electricity consumption data and electricity billing related information, includes: S11: Obtain the power consumption parameters reported by various types of electrical equipment to form multi-source power consumption data to be processed.

[0037] Specifically, by adapting to power-consuming and distribution-side devices such as smart meters, transformers, distribution area meters, and environmental sensors, it collects parameter data that can reflect the real-time power consumption status of users, such as voltage, current, active power, reactive power, power factor, and electrical energy. For high-frequency acquisition scenarios, it can continuously collect data from each measuring point according to a preset acquisition cycle, and summarize the power consumption parameters formed by different devices, different metering levels, and different acquisition sources into multi-source power consumption data to be processed, so that the multi-source power consumption data to be processed can cover the basic power consumption status of the user side, distribution area side, and environment side.

[0038] S12: Add timestamps and device identifiers to the multi-source power consumption data to be processed, and obtain multi-source power consumption data with identifiers.

[0039] Specifically, before the multi-source electricity consumption data to be processed enters the subsequent processing, the corresponding collection time and data source identifier are written into each electricity consumption parameter record. The collection time is used to distinguish the sequential relationship of data within different sampling periods, and the device identifier is used to distinguish different sources such as smart meters, transformers, transformer substations, or environmental sensors. This enables data from the same user, the same device, and the same time period to be accurately traced. After communication interruption, data continuity is maintained through local caching and breakpoint resume transmission, ultimately resulting in multi-source electricity consumption data with identifiers.

[0040] S13: Access user profiles, electricity pricing policies, and meteorological data to obtain relevant information for electricity billing.

[0041] Specifically, the system accesses user profiles containing information related to electricity billing, such as user categories, electricity usage characteristics, capacity, and metering relationships. It also accesses electricity pricing policies related to time-of-use pricing, tiered pricing, power regulation rules, and policy effective dates. Additionally, it accesses external data that may affect electricity usage behavior and load changes, such as temperature, humidity, and holiday status. All of this information is then formatted in a unified way, so that user attributes, billing basis, and environmental conditions together form the associated information for electricity billing.

[0042] S14: Preprocess the multi-source power consumption data with labels to obtain preprocessed multi-source power consumption data.

[0043] Specifically, the system performs data sequencing, anomaly identification, missing data completion, range conversion, unit standardization, and time zone calibration on the identified multi-source electricity consumption data. This enables the raw or semi-structured electricity consumption data generated by different acquisition devices to be converted into standardized data suitable for electricity billing and anomaly analysis. For data problems caused by obvious noise, transmission interference, and acquisition gaps, the system first identifies and repairs them before generating pre-processed multi-source electricity consumption data.

[0044] In one embodiment, step S14, namely, preprocessing the tagged multi-source electricity consumption data to obtain preprocessed multi-source electricity consumption data, includes: S141: Based on timestamps and device identifiers, perform data mapping processing on the identified multi-source power consumption data to obtain the corresponding multi-source power consumption data.

[0045] Specifically, the power consumption parameters generated by different devices in the same or adjacent sampling periods are sorted and aligned according to the timestamp, and the metering device, user object or transformer area object corresponding to each data is identified according to the device identifier, so that data such as voltage, current, active power, reactive power and electrical energy at the same sampling time can be collected under the corresponding object. For data with upload delay or interrupted resume, its position in the original collection period is restored according to the timestamp, and finally the corresponding multi-source power consumption data is obtained.

[0046] S142: Perform abnormal data detection on the corresponding multi-source power consumption data to obtain valid multi-source power consumption data.

[0047] Specifically, the continuity and numerical rationality of the corresponding multi-source power consumption data are checked. A sliding window method can be used to compare the continuous collection points of the same object. When multiple consecutive collection points significantly exceed the normal fluctuation range, the corresponding data is marked as invalid data. The data changes caused by sensor fluctuations, communication interference and abnormal power consumption are distinguished. The marked invalid data is not directly involved in the subsequent calculation, thereby retaining the valid multi-source power consumption data that meets the calculation reliability requirements.

[0048] S143: Perform missing data completion, range conversion, unit unification, and time zone calibration on the valid multi-source power consumption data to obtain preprocessed multi-source power consumption data.

[0049] Specifically, for short-term missing data in valid multi-source electricity consumption data, interpolation can be performed to complete the missing data based on adjacent valid collection points before and after the missing point. For the difference in accounting methods between power data and electricity data, active power can be converted into electricity consumption for the corresponding time period according to the sampling period. The unit of measurement used for data from different sources is unified, and time calibration is performed according to the region where the user or equipment is located, so that the final preprocessed multi-source electricity consumption data meets the requirements for subsequent fusion and real-time electricity billing in terms of time, unit, range, and data integrity.

[0050] In one embodiment, in step S20, the electricity billing association information includes user profiles, electricity pricing policies, and meteorological data. The preprocessed multi-source electricity consumption data and the electricity billing association information are fused to obtain an electricity consumption feature matrix, including: S21: Based on the user profiles in the electricity billing information, perform user association on the preprocessed multi-source electricity consumption data to obtain user-associated electricity consumption data.

[0051] Specifically, the user ID, electricity category, capacity information, and metering relationship in the user profile are matched with the preprocessed multi-source electricity data to determine the user object, transformer area object, and metering device corresponding to each set of electricity parameters. This transforms the electricity data originally formed by device source into data content organized by user and electricity scenario. For data with hierarchical relationships between the transformer area master table and the user sub-table, the upper and lower level correspondence is also preserved, ultimately obtaining the user-related electricity data.

[0052] S22: Based on the time information corresponding to the user's associated electricity consumption data, the user's associated electricity consumption data is fused with the electricity price policy and meteorological data in the electricity billing information to obtain fused electricity consumption data.

[0053] Specifically, based on the time of collection of user-related electricity consumption data, the applicable electricity pricing policy within the same time period is matched with the corresponding user's electricity consumption data, and meteorological data within the same time range is matched with user electricity consumption data. This allows the user's electricity consumption, power, applicable electricity pricing conditions, and environmental conditions at different electricity consumption periods to be uniformly expressed. For data spanning days, peak and valley periods, or periods of policy changes, different electricity pricing rules and environmental conditions are matched according to the corresponding time information to ultimately obtain integrated electricity consumption data.

[0054] S23: Extract daily electricity consumption, peak-valley ratio, and power fluctuation coefficient from the integrated electricity consumption data to obtain a set of electricity consumption characteristics.

[0055] Specifically, based on the integrated electricity consumption data, the electricity consumption of users is summarized on a daily basis to obtain the daily electricity consumption that can reflect the scale of users' electricity consumption. The electricity consumption ratio in different electricity price periods is statistically divided into peak, valley and flat periods to obtain the peak and valley ratio that can reflect the preference of electricity consumption periods. The power fluctuation coefficient is calculated based on the fluctuation of power value within the same statistical period. The electricity consumption feature set can simultaneously express the total electricity consumption, the electricity consumption period structure and the degree of power stability.

[0056] S24: Perform matrix processing on the electricity consumption feature set according to the same field structure to obtain the electricity consumption feature matrix.

[0057] Specifically, the electricity consumption feature sets corresponding to different users, different time periods, or different metering objects are arranged in a unified field order, so that the daily electricity consumption, peak-valley ratio, power fluctuation coefficient, and power factor that can be used for subsequent analysis maintain the same field structure. The feature content corresponding to each user or each statistical period is organized into a row or a group of records in the matrix, and finally an electricity consumption feature matrix can be used for real-time electricity billing, electricity consumption behavior analysis, and anomaly judgment.

[0058] In one embodiment, in step S30, the electricity billing information includes electricity pricing policies. A composite electricity pricing rule is generated based on the electricity billing information, and real-time electricity billing is performed based on the electricity consumption feature matrix and the composite electricity pricing rule to obtain a detailed billing statement, including: S31: Extract the effective time, applicable scope and billing parameters of the electricity price policy from the electricity billing information to obtain the electricity price rule elements.

[0059] Specifically, the time range from which the policy takes effect, the scope of application to different user categories or electricity consumption characteristics, and billing parameters such as electricity price periods, tiered electricity consumption ranges, additional fee ratios, and power factor assessment conditions used for fee calculation are extracted from the electricity price policy content in the electricity billing information. This makes these contents form electricity price rule elements that can be called by fee calculation, and the time correspondence between different policy versions is preserved to support subsequent retrospective accounting.

[0060] S32: Generate the corresponding composite electricity price rule based on the electricity price rule elements, and associate the composite electricity price rule with the corresponding effective time to obtain the target composite electricity price rule.

[0061] Specifically, different billing elements such as time-of-use billing, tiered billing, and power regulation billing are combined according to the user's applicable scope, so that the same user can match multiple billing rules at the same accounting cycle. The generated composite electricity price rule is associated with its corresponding effective time, expiration time, and applicable user scope. When the cost calculation occurs within a specific time period, the composite electricity price rule that is valid within the corresponding time range is selected as the target composite electricity price rule.

[0062] S33: Determine the user's electricity consumption data for each electricity consumption period based on the electricity consumption characteristic matrix.

[0063] Specifically, the electricity consumption characteristics corresponding to users, time, and electricity consumption periods in the electricity consumption feature matrix are read. The electricity consumption in each period is statistically divided according to peak, valley, flat, or other electricity pricing policies. Electricity consumption records that span different electricity pricing periods are split and collected according to the collection time, so that the electricity consumption data of users in each electricity consumption period can correspond to the billing period in the target composite electricity pricing rules.

[0064] S34: Calculate the cost of electricity consumption data for each electricity consumption period based on the target composite electricity price rule, and obtain the cost details.

[0065] Specifically, based on the unit price and billing conditions for the corresponding time period in the target composite electricity price rules, the electricity consumption data for each electricity consumption period is calculated. Under the tiered billing scenario, the cost is calculated separately according to the tier interval of the cumulative electricity consumption. Under the power factor adjustment billing scenario, the cost is adjusted in combination with the monthly average power factor or corresponding assessment conditions. The calculated time period, electricity consumption, unit price, amount, and total cost are then compiled to form a detailed cost list that can be displayed, verified, and used for anomaly detection.

[0066] In one embodiment, in step S40, electricity consumption behavior analysis is performed based on the electricity consumption characteristic matrix, and anomaly judgment is made in conjunction with the cost details to obtain anomaly analysis results, including: S41: Extract users' electricity consumption fluctuations, peak-valley ratios, and electricity consumption time distributions from the electricity consumption feature matrix to obtain electricity consumption behavior characteristics.

[0067] Specifically, the daily electricity consumption, peak-valley ratio, and power fluctuation coefficient of users in different statistical periods are read from the electricity consumption feature matrix. Combined with the distribution of electricity consumption time periods, the behavioral characteristics of users' electricity consumption are identified, such as whether it is stable, fluctuating, sudden, concentrated in peak periods, or continuously high. This allows the changes in the scale of electricity consumption, time period preferences, and load stability of the same user in different time ranges to be expressed as electricity consumption behavior characteristics.

[0068] S42: Determine the historical concurrent behavioral characteristics corresponding to the electricity consumption behavior characteristics based on the electricity consumption characteristic matrix, compare the electricity consumption behavior characteristics with the historical concurrent behavioral characteristics, and obtain a behavior change report.

[0069] Specifically, based on the historical periodic feature records of the same user in the electricity consumption feature matrix, the historical periodic behavior features corresponding to the current electricity consumption behavior features in terms of time range and field structure are extracted. The current electricity consumption behavior features are compared with the historical periodic behavior features to obtain a behavior change report that can reflect peak electricity consumption growth, electricity consumption time shift, power fluctuation enhancement or sudden change in electricity consumption pattern, etc., for subsequent anomaly judgment.

[0070] S43: Determine the user's cost changes during different electricity usage periods based on the cost details.

[0071] Specifically, the system reads the user's electricity consumption, unit price, amount, and total cost for different billing periods from the cost details, and statistically analyzes the cost change trend according to daily, hourly, or accounting cycle. It identifies whether the cost increase is caused by increased electricity consumption, changes in the proportion of peak and off-peak periods, tiered pricing, changes in power regulation costs, or changes in electricity price policies, forming cost change information for users in different electricity consumption periods, thus providing a basis for judging billing anomalies at the cost composition level.

[0072] S44: Combine behavior change reports and cost change information to determine electricity consumption anomalies and billing anomalies, and obtain anomaly analysis results.

[0073] Specifically, the changes in electricity consumption patterns reflected in the behavior change report are jointly judged with the changes in the amount reflected in the cost change information. When the characteristics of electricity consumption behavior deviate significantly and the cost change is abnormally synchronized, it is marked as an electricity consumption anomaly. When the cost change does not match the corresponding electricity consumption behavior change or the calculation result deviates significantly from the reference cost, it is marked as a billing anomaly. When it is necessary to combine the predicted reference value for judgment, the predicted power can be calculated based on historical electricity consumption, meteorological data, and holiday markers. The prediction formula is P(t)=a×P(t-1)+b×T(t)+c×H(t)+d×Hl, where P(t) is the predicted power at time t, P(t-1) is the actual power at time t-1, T(t) is the temperature at time t, H(t) is the humidity at time t, Hl is the holiday marker, a is the historical power weight, b is the temperature coefficient, c is the humidity coefficient, and d is the holiday coefficient. Then, the reference cost corresponding to the prediction result is compared with the cost details to finally obtain the anomaly analysis result, such as... Figure 2The comparison chart showing the anomaly identification accuracy for different user types demonstrates that, after combining behavioral change reports and cost change information, the anomaly identification accuracy for residential users, commercial users, industrial users, micro and small enterprises, and remote rural users reached 93%, 95%, 91%, 92%, and 88%, respectively, all exceeding practical standards. Compared to the traditional single-threshold model's identification level of 55% to 65% for different user types, this model better adapts to differences in electricity consumption patterns, load fluctuations, and data collection environments, making the anomaly analysis results more consistent with the actual electricity consumption characteristics of different user types. Figure 3 The diagram showing the relationship between electricity load forecasting accuracy and time series, when using historical power, temperature, humidity, and holiday indicators for electricity load forecasting, shows that the error rates for forecasting time series of 1 to 5 days are approximately 3%, 4.5%, 6%, 7.5%, and 8.5%, respectively. These are all significantly lower than the error rates of traditional forecasting methods under the same time series. This provides a relatively stable reference cost basis for cost details, allowing the deviation between cost change information and forecast costs to be used in judging electricity consumption anomalies and billing anomalies, avoiding reliance solely on current cost details for anomaly identification.

[0074] In one embodiment, step S50, namely, performing anomaly warning processing based on the anomaly analysis results to obtain anomaly warning handling results, includes: S51: Determine the anomaly points and the corresponding anomaly cause information based on the anomaly analysis results.

[0075] Specifically, based on the abnormal users, abnormal time periods, and abnormal types marked in the anomaly analysis results, the user, transformer area, line, or metering equipment corresponding to the abnormal point is located. This is combined with analysis of changes in electricity consumption data, changes in cost details, user records, electricity pricing policies, and meteorological data to determine the cause of the anomaly. When the anomaly involves transformer area or line losses, the line loss rate can be calculated to assist in identifying the source of the anomaly. The total meter reading is the electricity supplied by the main meter of the distribution area within the statistical period. The total sub-meter reading is the sum of the electricity consumption recorded by the sub-meters of users within the same distribution area within the same statistical period. The line loss rate is used to reflect the loss level of the distribution area or line within the statistical period. Abnormal cause information may include reasons such as meter failure, electricity theft, sudden load change, wiring abnormality, or abnormal electricity price execution.

[0076] S52: Calculate the anomaly deviation, duration, and scope of impact based on the anomaly analysis results to obtain an anomaly score.

[0077] Specifically, based on the anomaly analysis results, the difference between the abnormal actual value and the normal reference value is determined, and the anomaly deviation degree D is calculated. The actual value is the actual value of the abnormal object detected during the abnormal period, such as electricity consumption, cost, line loss rate or power factor. The normal value is the reference value of the corresponding user, transformer area or metering object under normal conditions. The duration of the abnormal state is then counted as the duration T, and the number of users, devices or transformer areas involved in the abnormality is counted as the impact range R. D, T and R are substituted into the abnormality scoring formula S=λ×D+μ×T+ν×R, where S is the abnormal score, λ is the deviation weight, μ is the duration weight and ν is the range weight, and finally the abnormal score is obtained.

[0078] S53: Determine the anomaly level based on the anomaly score, and generate tiered push notifications according to the anomaly level.

[0079] Specifically, the anomaly score is compared with the preset anomaly level classification conditions to determine whether the anomaly is a general anomaly, an important anomaly, or an emergency anomaly. For general anomalies, a reminder message is generated for users or remote verification; for important anomalies, a verification message is generated for local electricians or maintenance personnel; and for emergency anomalies, a handling message is generated for the dispatch center, inspectors, or emergency repair personnel. The anomaly point, anomaly time period, anomaly score, anomaly level, and anomaly cause information that needs attention are recorded in the tiered push information, so that anomalies of different severity can be delivered to the corresponding handling objects.

[0080] S54: Link and record the anomaly point, anomaly cause information, anomaly level, and graded push information to obtain the anomaly warning and handling results.

[0081] Specifically, the user, transformer area, line, or equipment information corresponding to the anomaly is linked and recorded with the anomaly cause information, anomaly score, anomaly level, tiered push information, and handling status. Related cost details, electricity usage characteristics, behavior change reports, and anomaly analysis results are also saved as verification evidence. This ensures that the anomaly warning and handling results can support subsequent queries, user objection verification, operation and maintenance processing, audit dispatch, and source tracing audits, ultimately forming a closed-loop record from anomaly identification to warning push and handling traceability. Figure 4 The comparison chart of the core performance of the traditional system and the system of this invention, shown below, demonstrates that after completing real-time electricity billing, anomaly detection, and anomaly warning processing, compared to the traditional monthly billing method, the billing update frequency has increased from once a month to once an hour, the billing error rate has decreased from 0.3% to less than 0.01%, the anomaly identification accuracy has increased from 65% to 92%, the user objection rate has decreased from 3‰ to 0.2‰, and the anomaly handling time has been shortened from 48 hours to 8 hours. This illustrates that forming a continuous processing chain between the generation of billing details, the output of anomaly analysis results, and the recording of anomaly warning processing results can improve the timeliness of billing, the accuracy of anomaly identification, and the efficiency of handling. Figure 5The cross-scenario system performance comparison chart shows that, in application scenarios such as urban core areas, concentrated township areas, remote rural areas, industrial parks, and commercial districts, the data collection success rate remains at 99.9%, 99.5%, 98.8%, 99.8%, and 99.7%, respectively; the calculation latency is approximately 0.8 minutes, 1.0 minutes, 1.2 minutes, 0.9 minutes, and 0.7 minutes, respectively; and the anomaly handling time is approximately 6 hours, 8 hours, 12 hours, 7 hours, and 5 hours, respectively. This indicates that the process from acquiring multi-source electricity consumption data, generating electricity consumption feature matrices, calculating cost details, to recording anomaly warning and handling results can adapt to application scenarios with different communication conditions, user densities, and load complexities.

[0082] Example 2 like Figure 6 As shown, based on the same inventive concept as the above embodiments, the present invention also provides a big data electricity bill real-time calculation anomaly early warning system, including: The acquisition module is used to acquire preprocessed multi-source electricity consumption data and related information for electricity billing. The fusion module is used to fuse preprocessed multi-source electricity consumption data and electricity billing information to obtain an electricity consumption feature matrix; The accounting module is used to generate composite electricity price rules based on electricity bill accounting related information, and to perform real-time electricity bill accounting based on the electricity consumption feature matrix and composite electricity price rules to obtain a detailed expense breakdown; The analysis module is used to analyze electricity consumption behavior based on the electricity consumption characteristic matrix and to make anomaly judgments in conjunction with cost details, so as to obtain anomaly analysis results. The early warning module is used to perform abnormal early warning processing based on the abnormality analysis results and obtain the abnormal early warning handling results.

[0083] Optionally, the acquisition module includes: The parameter acquisition submodule is used to acquire the power consumption parameters reported by various types of power-consuming equipment and form multi-source power consumption data to be processed; The identification submodule is used to add timestamps and device identifiers to the multi-source power consumption data to be processed, so as to obtain multi-source power consumption data with identification. The access submodule is used to access user profiles, electricity pricing policies, and meteorological data to obtain relevant information for electricity billing. The preprocessing submodule is used to preprocess the multi-source power consumption data with labels to obtain the preprocessed multi-source power consumption data.

[0084] Optional, the preprocessing submodule includes: The corresponding unit is used to perform data correspondence processing on the identified multi-source power consumption data based on the timestamp and device identifier to obtain the corresponding multi-source power consumption data. The detection unit is used to detect abnormal data in the corresponding multi-source power consumption data to obtain valid multi-source power consumption data. The calibration unit is used to perform missing data completion, range conversion, unit unification, and time zone calibration on valid multi-source power consumption data to obtain preprocessed multi-source power consumption data.

[0085] Optionally, the fusion module includes: The user association submodule is used to associate users with the preprocessed multi-source electricity consumption data based on the user profiles in the electricity billing association information, and to obtain user-associated electricity consumption data. The corresponding fusion submodule is used to fuse user-associated electricity consumption data with electricity pricing policies and meteorological data in electricity billing information based on the time information corresponding to user-associated electricity consumption data, so as to obtain fused electricity consumption data. The feature extraction submodule is used to extract daily electricity consumption, peak-valley ratio and power fluctuation coefficient from the integrated electricity consumption data to obtain a set of electricity consumption features. The matrix transformation submodule is used to perform matrix transformation on the electricity consumption feature set according to the same field structure to obtain the electricity consumption feature matrix.

[0086] Optionally, the accounting module includes: The element extraction submodule is used to extract the effective time, applicable scope and billing parameters of the electricity price policy from the electricity billing information to obtain the electricity price rule elements. The rule generation submodule is used to generate corresponding composite electricity price rules based on the electricity price rule elements, and associate the composite electricity price rules with the corresponding effective time to obtain the target composite electricity price rule; The electricity consumption determination submodule is used to determine the user's electricity consumption data for each electricity consumption period based on the electricity consumption characteristic matrix; The cost calculation submodule is used to calculate the cost of electricity consumption data for each electricity consumption period based on the target composite electricity price rule, and obtain the cost details.

[0087] Optionally, the analysis module includes: The behavior extraction submodule is used to extract users’ electricity consumption fluctuations, peak-valley ratios and electricity consumption time distributions based on the electricity consumption feature matrix, thereby obtaining electricity consumption behavior characteristics. The synchronous comparison submodule is used to determine the historical synchronous behavior characteristics corresponding to the electricity consumption behavior characteristics based on the electricity consumption characteristic matrix, compare the electricity consumption behavior characteristics with the historical synchronous behavior characteristics, and obtain a behavior change report. The cost analysis submodule is used to determine the cost changes of users during different electricity consumption periods based on cost details. The anomaly detection submodule is used to combine behavior change reports and cost change information to determine electricity consumption anomalies and billing anomalies, and obtain anomaly analysis results.

[0088] Optionally, the early warning module includes: The cause determination submodule is used to determine the anomaly points and the corresponding anomaly cause information based on the anomaly analysis results. The scoring submodule is used to calculate the anomaly deviation degree, duration and scope of impact based on the anomaly analysis results, and obtain the anomaly score. The level determination submodule is used to determine the anomaly level based on the anomaly score and generate tiered push notifications according to the anomaly level. The recording submodule is used to associate and record anomaly points, anomaly cause information, anomaly level, and graded push information to obtain anomaly warning and handling results.

[0089] Example 3 like Figure 7 As shown, the present invention also provides an electronic device 100 for implementing a method for real-time calculation and early warning of abnormalities in big data electricity bills; The electronic device 100 includes a memory 101, at least one processor 102, a computer program 103 stored in the memory 101 and executable on at least one processor 102, and at least one communication bus 104.

[0090] The memory 101 can be used to store the computer program 103. The processor 102 implements the steps of the big data electricity bill real-time calculation anomaly early warning method of Embodiment 1 by running or executing the computer program stored in the memory 101 and calling the data stored in the memory 101.

[0091] The memory 101 may primarily include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created based on the use of the electronic device 100 (such as audio data), etc. In addition, the memory 101 may include non-volatile memory, such as hard disk, RAM, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other non-volatile solid-state storage device.

[0092] At least one processor 102 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Processor 102 may be a microprocessor or any conventional processor. Processor 102 is the control center of electronic device 100, connecting various parts of electronic device 100 via various interfaces and lines.

[0093] The memory 101 in the electronic device 100 stores multiple instructions to implement a method for real-time calculation and early warning of anomalies in big data electricity billing, and the processor 102 can execute multiple instructions to achieve the following: Obtain preprocessed multi-source electricity consumption data and related information for electricity billing; The preprocessed multi-source electricity consumption data and electricity billing information are fused to obtain an electricity consumption feature matrix. Based on the electricity billing information, a composite electricity price rule is generated, and real-time electricity billing is performed based on the electricity consumption feature matrix and the composite electricity price rule to obtain a detailed billing statement. Electricity consumption behavior is analyzed based on the electricity consumption characteristic matrix, and anomaly detection is performed in conjunction with cost details to obtain anomaly analysis results; Anomaly warnings are issued based on the anomaly analysis results, and the anomaly warning handling results are obtained.

[0094] Example 4 If the modules / units integrated in the electronic device 100 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or system capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, and read-only memory (ROM).

[0095] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0096] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A system that specifies functions in one or more boxes.

[0097] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including an instruction set implemented in a process. Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0098] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0099] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, 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.

[0100] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for real-time calculation and early warning of anomalies in big data electricity billing, characterized in that, The method includes: Obtain preprocessed multi-source electricity consumption data and related information for electricity billing; The preprocessed multi-source electricity consumption data and the electricity billing association information are fused to obtain an electricity consumption feature matrix; A composite electricity price rule is generated based on the electricity billing association information, and a real-time electricity billing is performed based on the electricity consumption feature matrix and the composite electricity price rule to obtain a detailed billing statement. Based on the electricity consumption characteristic matrix, electricity consumption behavior is analyzed, and anomaly judgment is made in conjunction with the cost details to obtain anomaly analysis results; Based on the anomaly analysis results, anomaly warning processing is performed to obtain the anomaly warning handling results.

2. The big data electricity bill real-time calculation anomaly early warning method according to claim 1, characterized in that, The acquisition of preprocessed multi-source electricity consumption data and related electricity billing information includes: Obtain power consumption parameters reported by various types of electrical equipment to form multi-source power consumption data to be processed; Add timestamps and device identifiers to the multi-source power consumption data to be processed to obtain identifiable multi-source power consumption data; By accessing user profiles, electricity pricing policies, and meteorological data, the electricity billing information can be obtained. The identified multi-source power consumption data is preprocessed to obtain the preprocessed multi-source power consumption data.

3. The big data electricity bill real-time calculation anomaly early warning method according to claim 2, characterized in that, The preprocessing of the tagged multi-source electricity consumption data to obtain preprocessed multi-source electricity consumption data includes: Based on the timestamp and the device identifier, the identified multi-source power consumption data is processed to obtain the corresponding multi-source power consumption data. Anomaly detection is performed on the corresponding multi-source power consumption data to obtain valid multi-source power consumption data; The valid multi-source power consumption data is processed by performing missing data completion, range conversion, unit unification, and time zone calibration to obtain the preprocessed multi-source power consumption data.

4. The method for real-time calculation and early warning of anomalies in big data electricity billing according to claim 1, characterized in that, The electricity billing information includes user profiles, electricity pricing policies, and meteorological data. The preprocessed multi-source electricity consumption data and the electricity billing information are fused to obtain an electricity consumption feature matrix, including: Based on the user profiles in the electricity billing association information, the preprocessed multi-source electricity consumption data is associated with users to obtain user-associated electricity consumption data. Based on the time information corresponding to the user-associated electricity consumption data, the user-associated electricity consumption data is fused with the electricity pricing policy and meteorological data in the electricity billing information to obtain fused electricity consumption data; Daily electricity consumption, peak-valley ratio, and power fluctuation coefficient are extracted from the fused electricity consumption data to obtain a set of electricity consumption characteristics. The electricity consumption feature set is matrixed according to the same field structure to obtain the electricity consumption feature matrix.

5. The method for real-time calculation and early warning of anomalies in big data electricity billing according to claim 1, characterized in that, The electricity billing information includes electricity pricing policies. The process involves generating composite electricity pricing rules based on this information, and performing real-time electricity billing based on the electricity consumption feature matrix and the composite electricity pricing rules to obtain detailed cost information, including: The effective time, applicable scope and billing parameters of the electricity price policy are extracted from the electricity billing information to obtain the electricity price rule elements. Based on the electricity price rule elements, a corresponding composite electricity price rule is generated, and the composite electricity price rule is associated with the corresponding effective time to obtain the target composite electricity price rule; The electricity consumption data of users in each electricity consumption period is determined based on the electricity consumption feature matrix. Based on the target composite electricity price rule, the electricity consumption data for each electricity consumption period is used to calculate the cost details.

6. The method for real-time calculation and early warning of anomalies in big data electricity billing according to claim 1, characterized in that, The step of analyzing electricity consumption behavior based on the electricity consumption feature matrix and determining anomalies by combining the cost details to obtain anomaly analysis results includes: Based on the electricity consumption feature matrix, users' electricity consumption fluctuations, peak-valley ratios, and electricity consumption time distribution are extracted to obtain electricity consumption behavior characteristics. Based on the electricity consumption feature matrix, determine the historical concurrent behavior features corresponding to the electricity consumption behavior features, compare the electricity consumption behavior features with the historical concurrent behavior features, and obtain a behavior change report; Based on the aforementioned cost details, determine the user's cost changes during different electricity usage periods; By combining the behavior change report and the cost change information, the abnormal electricity consumption and billing are judged, and the abnormality analysis results are obtained.

7. The method for real-time calculation and early warning of anomalies in big data electricity billing according to claim 1, characterized in that, The step of performing anomaly warning processing based on the anomaly analysis results to obtain anomaly warning handling results includes: Based on the anomaly analysis results, determine the anomaly points and the corresponding anomaly cause information; Based on the anomaly analysis results, the anomaly deviation degree, duration, and scope of impact are calculated to obtain an anomaly score; An anomaly level is determined based on the anomaly score, and tiered push notifications are generated according to the anomaly level. The abnormal point, the abnormal cause information, the abnormal level, and the hierarchical push information are associated and recorded to obtain the abnormal early warning and handling result.

8. A big data-based real-time electricity billing anomaly early warning system, characterized in that, The system includes: The acquisition module is used to acquire preprocessed multi-source electricity consumption data and related information for electricity billing. The fusion module is used to fuse the preprocessed multi-source electricity consumption data and the electricity billing association information to obtain an electricity consumption feature matrix; The accounting module is used to generate composite electricity price rules based on the electricity cost accounting association information, and to perform real-time electricity cost accounting based on the electricity consumption feature matrix and the composite electricity price rules to obtain cost details; The analysis module is used to analyze electricity consumption behavior based on the electricity consumption feature matrix and to make anomaly judgments in conjunction with the cost details, so as to obtain anomaly analysis results. The early warning module is used to perform abnormal early warning processing based on the abnormality analysis results and obtain the abnormal early warning handling results.

9. An electronic device, characterized in that, It includes a processor and a memory, wherein the processor is used to execute a computer program stored in the memory to implement the big data electricity bill real-time calculation anomaly early warning method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one instruction, which, when executed by a processor, implements the big data electricity bill real-time calculation anomaly early warning method as described in any one of claims 1 to 7.

Images