User power behavior comprehensive visualization platform

Abstract

The invention provides a user power behavior comprehensive visualization platform. The platform comprises a data access module, a data query module, a data analysis module, a visualization display module and a user interaction module. The user electric quantity information is obtained from the power supply marketing system through the data access module, the data query module extracts the electric power behavior data of the target user according to the query condition input by the user, the data analysis module deeply analyzes the queried data, and the visual display module visually displays the query result and the analysis result in a chart form. And the user interaction module provides an interaction interface between the user and the platform. The invention aims at providing a comprehensive data query function and improving the visualization degree of the power behavior data, and helping a user to quickly and accurately understand the power behavior characteristics and trends.

Description

Technical Field

[0001] The present invention relates to the technical field of electricity consumption behavior visualization, and in particular to a comprehensive visualization platform for user electricity consumption behavior. Background Art

[0002] With the rapid development of smart grids and the rapid growth of power data, traditional power management methods can no longer meet the current needs for power behavior analysis, monitoring and optimization. Existing power management systems mostly display data in text and table formats, lacking intuitiveness and interactivity, making it difficult for users to quickly and accurately understand power behavior characteristics and trends. At the same time, there is a lack of effective means for in-depth analysis of key information such as electricity bill payment and electricity consumption behavior, resulting in unreasonable allocation of power resources and unpredictable risks in electricity bill payment.

[0003] In order to solve the above problems, some power behavior visualization tools have appeared on the market, but most of these tools have single functions and cannot provide comprehensive power behavior data query functions, and cannot meet users' query needs for multi-dimensional data such as electricity bill and electricity quantity rankings, electricity bill payment information, etc. There is a lack of effective means in electricity bill payment analysis, electricity consumption behavior analysis, etc., and it is impossible to provide users with in-depth power behavior characteristics and trend analysis. There are deficiencies in data visualization, unclear chart display, poor interactivity, and it is difficult to help users quickly and accurately understand power data. For this reason, the present invention proposes a user power behavior comprehensive visualization platform. Summary of the invention

[0004] The purpose of the present invention is to propose a comprehensive visualization platform for user power behavior, provide a comprehensive power behavior data query function and improve the visualization of power behavior data.

[0005] To achieve the above objectives, the present invention provides a user power behavior comprehensive visualization platform, including:

[0006] A data access module is used to obtain user power consumption information from the power supply marketing system, wherein the user power consumption information includes the power supply unit, year and month, power consumption category, electricity fee and power consumption;

[0007] A data query module, used to extract the power behavior data of the target user from the user power information obtained by the data access module according to the query conditions input by the user;

[0008] The data analysis module is used to analyze the queried user power behavior data to extract valuable information;

[0009] A visualization display module is used to visualize the target user's power behavior data queried by the data query module and the analysis results of the data analysis module;

[0010] The user interaction module is used to provide an interactive interface between the user and the platform, including the input of query conditions, the display of query results and the viewing of analysis results.

[0011] Preferably, the data access module includes:

[0012] Interface module, which establishes data interface with power supply marketing system and synchronizes data regularly or in real time;

[0013] The data processing module cleans and organizes the raw data to form a data set that can be used for subsequent query and analysis.

[0014] Preferably, the data query module includes:

[0015] The basic query submodule is used to provide basic information query functions for screening and locating target user groups. The basic information includes power supply units, years and months, and electricity consumption categories.

[0016] The logic module is used to filter out corresponding data from the data set according to the query conditions input by the user, and extract the user group data that meets the conditions;

[0017] The result module is used to pass the query result to the data analysis module for analysis and to pass it to the visualization display module for display.

[0018] Preferably, the data query module further includes:

[0019] The ranking classification query submodule is used to support ranking classification queries based on electricity charges, electricity consumption and other dimensions, so as to query the electricity charge and electricity ranking information of a specified number of households;

[0020] The user number query submodule is used to accurately query the electricity bill and power consumption information of a single household through the user number, including peak electricity consumption period, daily / monthly / quarterly electricity consumption and electricity charges, etc.

[0021] Preferably, the data analysis module includes:

[0022] The electricity bill payment analysis submodule is used to analyze the customer's electricity bill payment situation based on the ranking classification and user number query results, including the highest / lowest monthly electricity bill, daily / monthly / quarterly payment information, payment habits, average payment period, arrears habits, number of default payments and total amount of liquidated damages;

[0023] The electricity consumption behavior analysis submodule is used to analyze the user's electricity consumption behavior characteristics, including peak hours, electricity consumption, and electricity fee change trends;

[0024] The trend analysis module is used to analyze the changing trends of users' electricity consumption and electricity charges and predict possible future electricity consumption.

[0025] Preferably, the data analysis module further includes:

[0026] The statistical information module is used to collect statistics on customers' daily / monthly / quarterly payment information, payment habits, average payment period, payment arrears habits, number of default payments, and total amount of liquidated damages;

[0027] The anomaly detection module is used to detect anomalies in users' electricity usage behavior, including sudden increases in electricity charges and abnormal electricity usage.

[0028] Preferably, the visual display module includes:

[0029] The bar chart display submodule is used to display the electricity bill ranking and electricity bill payment information, and intuitively reflect data comparison and trends in the form of a bar chart;

[0030] The line chart display submodule is used to display the time series changes of single-household electricity bill and power consumption information, including peak electricity consumption hours, daily / monthly / quarterly electricity consumption and electricity bills, and presents data change trends in the form of a line chart.

[0031] Preferably, the user interaction module includes:

[0032] The interactive interface module is used for users to select the power supply unit, year, month, and electricity consumption category on the interface, and input through drop-down menus, calendar controls, etc.;

[0033] User feedback module collects user feedback during use.

[0034] The present invention has the following beneficial effects:

[0035] It provides comprehensive data query functions to meet users' query needs for multi-dimensional data such as electricity bill rankings, electricity bill payment information, etc.; through data visualization, it enhances the intuitiveness and interactivity of data, helping users to quickly and accurately understand the characteristics and trends of electricity behavior; deeply analyzes user electricity behavior data, and provides users with effective analysis methods for key information such as electricity bill payment status and electricity usage behavior; through ranking classification query and user number query, it can accurately locate and analyze the electricity behavior of target user groups; statistical information and anomaly detection functions are conducive to the rational allocation of power resources and the prediction of electricity bill payment risks; the design of the user interaction interface improves the user experience and facilitates user operation and acquisition of required information; collects user feedback to provide a basis for continuous optimization and improvement of the platform. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required in the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0037] Figure 1 The figure is a framework diagram of a comprehensive visualization platform for user power behavior in an embodiment of the present invention.

[0038] Figure 2 It is a framework structure diagram of the data access module in an embodiment of the present invention.

[0039] Figure 3 It is a framework structure diagram of the data query module in an embodiment of the present invention.

[0040] Figure 4 Schematic diagram of the data analysis module in an embodiment of the present invention.

[0041] Figure 5 It is a framework structure diagram of the visual display module in an embodiment of the present invention.

[0042] Figure 6 4 is a framework diagram of the user interaction module in an embodiment of the present invention. DETAILED DESCRIPTION

[0043] The detailed description of the accompanying drawings is intended as an illustration of the current embodiments of the present invention and is not intended to represent the only form in which the present invention can be implemented. It should be understood that the same or equivalent functions can be accomplished by different embodiments that are intended to be included in the spirit and scope of the present invention.

[0044] See also Figure 1-6 The embodiment of the present invention provides a comprehensive visualization platform for user power behavior, including

[0045] The data access module is responsible for obtaining user power information from the marketing system, including the original data such as power supply unit, year and month, power consumption category, electricity fee, and power consumption;

[0046] Data query module: The data query module is the entrance of the system. It is responsible for extracting user power behavior data from the marketing system and providing raw materials for the data analysis module. The data query module provides users with flexible data retrieval functions. Users can select different query conditions according to their needs to quickly obtain the required power behavior data.

[0047] Data analysis module: The data analysis module conducts in-depth analysis on the queried data, extracts valuable information, and provides data support for the visualization module. The data analysis module provides users with in-depth data insights, helps users understand their electricity behavior characteristics and payment habits, and provides a basis for formulating electricity management strategies;

[0048] Visualization display module: The visualization display module presents the query and analysis results to users in an intuitive and easy-to-understand way, helping users understand the meaning behind the data and make decisions. The visualization display module converts complex data into intuitive information through a graphical interface, helping users quickly understand the meaning behind the data and improve decision-making efficiency.

[0049] The user interaction module provides an interactive interface between the user and the platform, including the input of query conditions, display of query results, and viewing of analysis results;

[0050] Each submodule in the comprehensive visualization platform of power behavior plays an important role. They work together to achieve comprehensive analysis and visualization of user power behavior. Through this system, users can have a deeper understanding of their power consumption behavior and electricity bill payment, providing strong support for formulating power management strategies and optimizing power resource allocation.

[0051] In this embodiment, preferably, the data access module includes the following modules:

[0052] The interface module establishes a data interface with the marketing system and obtains user power behavior data in real time through API or database connection;

[0053] The data processing module cleans and organizes the raw data to form a data set that can be used for subsequent query and analysis.

[0054] In this embodiment, preferably, the data query module includes the following modules:

[0055] The basic query submodule provides basic information query functions such as power supply unit, year, month, and electricity consumption category, which is used to filter and locate target user groups. Users can quickly find and locate specific user groups or time periods based on this basic information for subsequent data analysis and visualization.

[0056] The logic module filters out the corresponding data from the data set according to the query conditions entered by the user, and extracts the user group data that meets the conditions;

[0057] The result module passes the query results to the visualization display module for analysis and display. Users can view the detailed information of each user, such as user number, electricity usage address, electricity usage category, etc.

[0058] In this embodiment, preferably, the data query module further includes:

[0059] The ranking classification query submodule supports ranking classification query by electricity charges, electricity consumption and other dimensions. It can query the electricity charge and electricity ranking information of a specified number of households. Users can choose to rank and classify by electricity charges or electricity consumption on the interface, and enter the number of households to be ranked. According to the ranking classification and number of households selected by the user, the filtered user data is calculated to obtain the electricity charge and electricity ranking information of each user. The electricity charge and electricity ranking information is displayed using a bar chart. Users can view the ranking, electricity charge and electricity value and other information of each user in the chart. Interactive functions are provided. Users can view more detailed user information or conduct further data analysis by clicking on the columns or labels in the chart, which helps users intuitively understand the electricity charge and electricity distribution of user groups;

[0060] In the user number query submodule, the user can enter a specific user number on the interface, and the system will verify and confirm the validity of the user number. According to the user number, the detailed electricity bill and power consumption information of the user is extracted from the marketing system, including historical electricity consumption data, peak electricity consumption hours, electricity consumption and electricity charges in different time periods, etc. A line chart is used to show the time series changes of the user's electricity bill and power consumption information. The user can view the electricity bill and power consumption data and their changing trends in different time periods in the chart. A data export function is provided, and the user can export the query results in formats such as Excel or CSV for further data processing and analysis.

[0061] In this embodiment, preferably, the data analysis module includes the following modules:

[0062] The electricity bill payment analysis submodule extracts the user's electricity bill payment data from the marketing system according to the user's query conditions or preset rules, conducts in-depth analysis based on the ranking classification and user number query results, analyzes the customer's electricity bill payment situation, calculates the highest / lowest monthly electricity bill, daily / monthly / quarterly payment information, payment habits, average payment period, arrears habits, number of default payments and total amount of liquidated damages and other indicators, and displays the analysis results to the user in the form of tables, charts, etc. The user can view the electricity bill payment situation and its changing trend of each user on the interface. According to the analysis results, users with electricity bill payment risks are warned, and information such as risk level and warning reasons are provided to help users take timely response measures. It can help users understand customers' electricity bill payment behavior, identify potential electricity bill payment risks, and formulate corresponding electricity bill management strategies;

[0063] Specifically, the specific algorithm steps of the electricity fee payment analysis submodule are as follows:

[0064] Step 11: Data extraction;

[0065] According to the query conditions entered by the user or the rules preset by the system, the user's electricity bill payment data is extracted from the power supply marketing system, including user number, payment time, payment amount, payment status (whether overdue) and other information.

[0066] Step 12: Data preprocessing;

[0067] Clean the extracted data to remove invalid and erroneous data records. Format the data to ensure its consistency and accuracy.

[0068] Step 13: Basic statistical analysis;

[0069] Calculate the highest and lowest monthly electricity charges for each user. Collect daily / monthly / quarterly payment information for each user, including the number of payments and the total amount of payments.

[0070] Step 14: Payment habits analysis;

[0071] Analyze the payment time distribution of each user and calculate the average payment period. Count the user's payment frequency and determine the user's payment habits (such as regular payment, overdue payment, etc.).

[0072] Step 15: Analysis of arrears and breach of contract;

[0073] Statistics are collected on the number of times each user has defaulted on payment, the amount of defaulted payment, and the number of defaulted payments. The total amount of defaulted payment for each user is calculated.

[0074] Step 16: Risk level assessment;

[0075] A risk assessment model is established based on indicators such as the number of arrears, the amount of arrears, the number of default payments, and the total amount of liquidated damages. Each user is assessed for risk level and divided into risk levels (such as low risk, medium risk, and high risk).

[0076] Step 17: Early warning mechanism;

[0077] For users with a medium risk or above assessment result, the early warning mechanism is triggered, and an early warning report is generated, including information such as risk level, warning reason, and recommended measures.

[0078] Step 18: Results display;

[0079] The above analysis results are presented to the user in the form of tables, bar charts, line charts, etc. A detailed information viewing function is provided on the interface, and the user can view the electricity bill payment details and its changing trend of a single user.

[0080] Step 19: User interaction;

[0081] Allow users to filter and view the list of users with specific risk levels as needed. Provide data export function, users can export analysis results as reports.

[0082] Step 110: Continuous monitoring and updating;

[0083] Update electricity bill payment data regularly and re-analyze the above to monitor changes in users’ electricity bill payment behavior. Adjust users’ electricity bill payment risk levels and early warning information based on new data and analysis results.

[0084] Through the above steps, the electricity bill payment analysis submodule can effectively help users understand the electricity bill payment situation, identify and warn of electricity bill payment risks, and thus take corresponding management measures.

[0085] The electricity consumption behavior analysis submodule extracts the user's electricity consumption data from the marketing system, including peak electricity consumption hours, electricity consumption and electricity charges, etc., performs time series analysis on the extracted electricity consumption data, calculates indicators such as electricity consumption, electricity charges and their changing trends in different time periods, and extracts the user's electricity consumption behavior characteristics, such as peak electricity consumption hours, electricity consumption fluctuations, etc., based on the time series analysis results. The analysis results are presented to the user in the form of charts. The user can view the electricity consumption behavior characteristics and changing trends of different time periods on the interface to reveal the user's electricity consumption behavior characteristics and changing trends. Based on the analysis results, the user is provided with electricity use optimization suggestions, such as adjusting the peak electricity consumption hours, optimizing the allocation of electricity resources, etc., to improve the efficiency of electricity use;

[0086] Specifically, the specific algorithm steps of the power consumption behavior analysis submodule are as follows:

[0087] Step 21: Data extraction;

[0088] Extract users' electricity consumption data from the power supply marketing system, including user number, electricity consumption, electricity consumption time, electricity charges and other information.

[0089] Step 22: Data preprocessing;

[0090] The extracted electricity consumption data is cleaned to remove abnormal and erroneous data points. The data is normalized to ensure consistency and comparability.

[0091] Step 23: Time series segmentation;

[0092] The electricity consumption data is divided into time units such as day, week, month, and quarter to form a time series data set.

[0093] Step 24: Basic statistical analysis;

[0094] Calculate the electricity consumption and electricity charges for each time period (such as every hour, every day). Collect basic indicators such as total electricity consumption, average electricity consumption, and maximum electricity consumption.

[0095] Step 25: Analysis of peak electricity consumption periods;

[0096] Analyze each time series data set to identify peak electricity consumption hours. Calculate the proportion of peak electricity consumption to total daily electricity consumption.

[0097] Step 26: Power consumption fluctuation analysis;

[0098] Calculate the fluctuation coefficient of electricity consumption and analyze the stability of electricity consumption. Identify the time periods with large fluctuations in electricity consumption and analyze the possible causes of the fluctuations.

[0099] Step 27: Power consumption trend analysis;

[0100] Conduct time series trend analysis on electricity consumption, such as using moving average, exponential smoothing, etc. Identify trends of increasing or decreasing electricity consumption and analyze their sustainability.

[0101] Step 28: Extract electricity consumption behavior features;

[0102] Based on the analysis results, the user's electricity consumption behavior characteristics are extracted, such as normal electricity consumption time periods, peak electricity consumption time periods, electricity consumption fluctuation patterns, etc.

[0103] Step 29: Results display;

[0104] The analysis results are presented to users in the form of line graphs, bar graphs, heat maps, etc. Interactive functions are provided on the interface to allow users to view the characteristics of electricity consumption behavior and its changing trends in different time periods.

[0105] Step 210: Generate optimization suggestions;

[0106] Provide users with suggestions for optimizing electricity usage based on electricity consumption behavior. Analyze peak electricity consumption periods and recommend users to adjust their electricity consumption time or adopt a time-of-use electricity price strategy. Based on electricity consumption fluctuations, recommend users to optimize electricity resource allocation, such as using energy storage equipment.

[0107] Step 211: Continuous monitoring and updating;

[0108] Update electricity usage data regularly and re-perform the above analysis to monitor changes in user electricity usage behavior. Adjust optimization recommendations based on new data and analysis results.

[0109] Through the above steps, the power consumption behavior analysis submodule can help users deeply understand their power consumption behavior, discover potential energy-saving opportunities, and provide specific optimization measures to improve power usage efficiency.

[0110] Trend analysis module, which analyzes the changing trend of users' electricity consumption and electricity charges, and predicts possible future electricity consumption;

[0111] Specifically, the specific algorithm steps of the trend analysis module are as follows:

[0112] Step 31: Data collection and preprocessing;

[0113] Collect the user's electricity consumption and electricity fee history data from the power supply marketing system. Clean the data and deal with missing values, outliers and duplicate data. Normalize or standardize the data for easy analysis.

[0114] Step 32: time series segmentation;

[0115] Divide the collected data into fixed time intervals (such as days, weeks, and months) in chronological order.

[0116] Step 33: Trend detection;

[0117] Use statistical methods (e.g. linear regression, moving average, autocorrelation function) to detect trend components in the data. Identify long-term trends, seasonal trends, and cyclical trends in the data.

[0118] Step 34: Model selection;

[0119] Select an appropriate trend prediction model based on data characteristics, such as ARIMA (autoregressive integrated moving average model), SARIMA (seasonal ARIMA), exponential smoothing model (such as Holt-Winters method), etc.

[0120] Step 35: Model training and verification;

[0121] Use historical data to train the model and evaluate model performance through methods such as cross-validation. Adjust model parameters until the best fitting model is found.

[0122] Step 36: Trend prediction;

[0123] Use the trained model to predict future electricity consumption and electricity charges. Predict electricity consumption and electricity charges for a period of time in the future (such as next month or next quarter).

[0124] Step 37: Prediction result analysis;

[0125] Analyze the forecast results and identify possible trends in electricity consumption and electricity prices. Calculate the confidence interval of the forecast and assess the uncertainty of the forecast.

[0126] Step 38: Results display;

[0127] The forecast results are presented in the form of charts, such as line charts, forecast band charts, etc. Interactive functions are provided on the interface to allow users to view trends in different forecast time periods.

[0128] Step 39: Risk assessment;

[0129] Based on the forecast results, assess the risks that may arise from future electricity usage, such as electricity bill overruns, insufficient power supply, etc. Provide a risk assessment report, including risk levels and potential impacts.

[0130] Step 310: Report and recommendations;

[0131] Prepare trend analysis reports to summarize forecast results and risk assessments. Provide users with electricity management recommendations based on analysis results, such as energy-saving measures, demand response plans, etc.

[0132] Step 311: Continuous monitoring and updating;

[0133] Update data regularly, re-analyze trends and forecasts, and adjust management recommendations and strategies based on the latest data and forecasts.

[0134] Through the above steps, the trend analysis module can help users understand the long-term trend of electricity consumption and electricity charges, and provide scientific predictions and guidance for future electricity use and management.

[0135] In this embodiment, preferably, the data analysis module further includes:

[0136] Statistical information module, which counts customers' daily / monthly / quarterly payment information, payment habits, average payment period, payment arrears habits, number of default payments, total amount of liquidated damages, etc.;

[0137] Specifically, the specific statistical analysis algorithm steps of the statistical information module are as follows:

[0138] Step 41: Data extraction;

[0139] Extract the customer's payment information from the power supply marketing system, including payment time, payment amount, payment status (whether payment is made on time), arrears records, liquidated damages, etc.

[0140] Step 42: data preprocessing;

[0141] Clean the data to remove invalid and erroneous data records. Format the data to ensure data consistency.

[0142] Step 43: Daily payment information statistics;

[0143] Statistics on the payment amount, payment frequency and payment status of each customer on a daily basis. Calculate the average payment amount and payment frequency per day.

[0144] Step 44: Monthly payment information statistics;

[0145] Summarize the payment amount, payment frequency and payment status of each customer on a monthly basis. Calculate the average payment amount, payment frequency and outstanding amount per month.

[0146] Step 45: Quarterly payment information statistics;

[0147] Summarize the payment amount, payment frequency and payment status of each customer by quarter. Calculate the average payment amount, payment frequency and outstanding amount for each quarter.

[0148] Step 46: Payment habits analysis;

[0149] Analyze the payment time distribution of customers and determine the average payment period of customers. Count the number of early payments and overdue payments of customers and analyze payment habits.

[0150] Step 47: Analysis of payment arrears habits;

[0151] Count the number of customers' arrears and the amount of arrears in different time periods. Analyze customers' arrears habits, such as whether they often default and the distribution of arrears amounts.

[0152] Step 48: Default payment analysis;

[0153] Count the number of times a customer defaults on payment and the amount of each default. Calculate the total amount of liquidated damages for the customer.

[0154] Step 49: Generate statistical analysis report;

[0155] The above statistical results should be compiled into a report, including tables and charts. The report should include payment information overview, payment habit analysis, default payment habit analysis and default payment analysis.

[0156] Step 410: display the results;

[0157] Display statistical reports on the user interface, allowing users to view statistical information in different time dimensions (daily, monthly, quarterly). Provide interactive functions, such as filtering data for a specific time period, viewing payment details for a specific customer, etc.

[0158] Step 411: Data monitoring and updating;

[0159] Update statistical information regularly to reflect the latest customer payment status. Adjust marketing strategies and service measures based on statistical analysis results to improve customer payment behavior.

[0160] Through the above steps, the statistical information module can provide power supply companies with detailed customer payment behavior analysis, help companies identify payment risks, optimize customer service, and formulate effective charging strategies.

[0161] Anomaly detection module detects abnormal situations in users' electricity usage behavior, such as sudden increase in electricity bills and abnormal electricity consumption;

[0162] Specifically, the specific algorithm steps of the anomaly detection module are as follows:

[0163] Step 51: Data collection;

[0164] Collect users' electricity consumption and electricity fee historical data from the power supply marketing system.

[0165] Step 52: data preprocessing;

[0166] Clean the data to remove obviously erroneous data points. Normalize or standardize the data to eliminate the impact of dimension.

[0167] Step 53: feature extraction;

[0168] Extract time series features of electricity consumption and electricity costs, such as mean, standard deviation, maximum, minimum, volatility, etc. If possible, extract other relevant features, such as weather data, holiday information, user type, etc.

[0169] Step 54: Establish a baseline model;

[0170] Based on normal electricity consumption behavior data, a baseline model for electricity consumption and electricity charges is established, such as using a time series prediction model (such as ARIMA, SARIMA) or a machine learning model (such as random forest, support vector machine).

[0171] Step 55: define anomaly threshold;

[0172] Based on the prediction results of the benchmark model, the abnormal threshold is defined, which can be a fixed value or a dynamic threshold based on statistical distribution (such as the 3σ principle of normal distribution).

[0173] Step 56: Real-time monitoring and anomaly detection;

[0174] Monitor users’ electricity consumption and electricity bill data in real time. Compare the real-time data with the baseline model predictions and calculate the residual or anomaly score.

[0175] Step 57: abnormality determination;

[0176] If the residual or anomaly score exceeds the predefined threshold, it is considered an abnormal situation. Detailed information such as the time when the abnormality occurred, the duration, and the degree of abnormality are recorded.

[0177] Step 58: abnormal confirmation and feedback;

[0178] Manually confirm the detected anomalies to eliminate false positives. Feedback confirmed anomalies to users, provide anomaly reports and suggestions.

[0179] Step 59: Abnormal analysis;

[0180] Conduct in-depth analysis of abnormal situations to identify possible causes of the abnormalities, such as equipment failure, electricity theft, changes in user behavior, etc.

[0181] Step 510: Exception handling suggestions;

[0182] Based on the abnormal analysis results, provide users with processing suggestions, such as equipment inspection, adjustment of power usage habits, etc.

[0183] Step 511: Model updating and optimization;

[0184] Regularly update the baseline model with new data to improve the accuracy and adaptability of anomaly detection. Optimize anomaly detection algorithms and threshold settings based on user feedback and anomaly handling results.

[0185] Through the above steps, the anomaly detection module can effectively identify anomalies in users' electricity usage behavior, help power supply companies and users to promptly discover and deal with potential problems, thereby improving the stability of the power system and user satisfaction.

[0186] In this embodiment, preferably, the visual display module includes the following modules:

[0187] The bar chart display submodule is used to display data such as electricity charge and electricity quantity ranking, electricity charge payment information, etc. It receives data such as electricity charge and electricity quantity ranking, electricity charge payment information, etc. from the data query and analysis module, configures the style, color, label and other attributes of the bar chart according to the data type and display requirements, uses the chart library (such as ECharts, Highcharts, etc.) to generate the bar chart, and displays it to the user on the interface. The bar chart can intuitively reflect the comparison and trend of the data, helping users quickly understand the meaning behind the data;

[0188] The line chart display submodule is used to display the time series changes of single-household electricity bill and electricity consumption information, including peak electricity consumption periods, daily / monthly / quarterly electricity consumption and electricity charges, etc. This submodule can receive the time series data of single-household electricity bill and electricity consumption information from the data query module, configure the style, color, label, time axis and other attributes of the line chart according to the data type and display requirements, use the chart library to generate a line chart, and display it to the user on the interface. The line chart can clearly show the changing trend of the data and help users understand the characteristics of their electricity consumption behavior and the time distribution pattern.

[0189] In this embodiment, preferably, the user interaction module includes the following modules:

[0190] The interactive interface module designs a concise and clear query interface, where users can select basic information such as power supply unit, year, month, and electricity consumption category, and input information through drop-down menus and calendar controls. It also provides data zooming and panning functions, where users can zoom in or out the data range in the chart by dragging or rolling the mouse wheel, so as to view data change trends in more detail.

[0191] The user feedback module collects user feedback during use and continuously optimizes the platform's functions and user experience.

[0192] In summary, the comprehensive visualization platform for power behavior provided by the present invention not only solves the problems existing in the prior art such as incomplete data query, insufficient data analysis, unclear visualization display, etc., but also provides users with comprehensive, in-depth and intuitive power behavior analysis and visualization services, which is of great significance for improving the efficiency of power resource allocation and reducing the risk of electricity bill payment.

[0193] The embodiments of the present invention have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A comprehensive visualization platform for user power behavior, characterized in that: include: A data access module is used to obtain user power consumption information from the power supply marketing system, wherein the user power consumption information includes the power supply unit, year and month, power consumption category, electricity fee and power consumption; A data query module, used to extract the power behavior data of the target user from the user power information obtained by the data access module according to the query conditions input by the user; The data analysis module is used to analyze the queried user power behavior data to extract valuable information; A visualization display module is used to visualize the target user's power behavior data queried by the data query module and the analysis results of the data analysis module; The user interaction module is used to provide an interactive interface between the user and the platform, including the input of query conditions, the display of query results and the viewing of analysis results.

2. The platform according to claim 1, characterized in that The data access module comprises: Interface module, which establishes data interface with power supply marketing system and synchronizes data regularly or in real time; The data processing module cleans and organizes the raw data to form a data set that can be used for subsequent query and analysis.

3. The platform according to claim 2, characterized in that: The data query module includes: The basic query submodule is used to provide basic information query functions for screening and locating target user groups. The basic information includes power supply units, years and months, and electricity consumption categories. The logic module is used to filter out corresponding data from the data set according to the query conditions input by the user, and extract the user group data that meets the conditions; The result module is used to pass the query result to the data analysis module for analysis and to pass it to the visualization display module for display.

4. The platform according to claim 3, characterized in that: The data query module also includes: The ranking classification query submodule is used to support ranking classification queries based on electricity charges, electricity consumption and other dimensions, so as to query the electricity charge and electricity ranking information of a specified number of households; The user number query submodule is used to accurately query the electricity bill and power consumption information of a single household through the user number, including peak electricity consumption period, daily / monthly / quarterly electricity consumption and electricity charges, etc.

5. The platform according to claim 4, characterized in that The data analysis module includes: The electricity bill payment analysis submodule is used to analyze the customer's electricity bill payment situation based on the ranking classification and user number query results, including the highest / lowest monthly electricity bill, daily / monthly / quarterly payment information, payment habits, average payment period, arrears habits, number of default payments and total amount of liquidated damages; The electricity consumption behavior analysis submodule is used to analyze the user's electricity consumption behavior characteristics, including peak hours, electricity consumption, and electricity fee change trends; The trend analysis module is used to analyze the changing trends of users' electricity consumption and electricity charges and predict possible future electricity consumption.

6. The platform according to claim 5, characterized in that The data analysis module also includes: The statistical information module is used to collect statistics on customers' daily / monthly / quarterly payment information, payment habits, average payment period, payment arrears habits, number of default payments, and total amount of liquidated damages; The anomaly detection module is used to detect anomalies in users' electricity usage behavior, including sudden increases in electricity charges and abnormal electricity usage.

7. The platform according to claim 1, characterized in that The visual display module includes: The bar chart display submodule is used to display the electricity bill ranking and electricity bill payment information, and intuitively reflect data comparison and trends in the form of a bar chart; The line chart display submodule is used to display the time series changes of single-household electricity bill and power consumption information, including peak electricity consumption hours, daily / monthly / quarterly electricity consumption and electricity bills, and presents data change trends in the form of a line chart.

8. The platform according to claim 1, characterized in that The user interaction module comprises: The interactive interface module is used for users to select the power supply unit, year, month, and electricity consumption category on the interface, and input through drop-down menus, calendar controls, etc.; User feedback module collects user feedback during use.

Images