Personalized inspection report generation method and device based on user behaviors

Abstract

The invention provides a personalized inspection report generation method and device based on user behaviors, and relates to the technical field of power grids. According to the invention, by analyzing the historical power consumption data of the user, the power consumption behavior characteristics such as the average power consumption, the peak-valley power consumption ratio, the payment habit and the business change characteristics of the user are obtained, personalized classification is carried out based on the power consumption behavior characteristics, the inspection category and the inspection item are determined, and personalized classification of the user is realized. And then the historical power consumption data is inspected based on the inspection category, and the personalized inspection report is generated, so that different personalized inspection reports are generated for different users, the difference of different users in power consumption behaviors is comprehensively considered, the users do not need to analyze and process by themselves, and the inspection efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power grid, and in particular to a method and device for generating personalized audit reports based on user behavior. Background Art

[0002] In the power industry, auditing is an important means to ensure the legality and compliance of power supply, improve operational efficiency and protect the rights and interests of users. Traditional auditing methods often rely on manual review of large amounts of power consumption data, which is not only time-consuming and labor-intensive, but also prone to omissions or errors due to human factors, which in turn affects the efficiency and accuracy of auditing.

[0003] With the development of smart grids, audit work is also developing towards automation. Power companies analyze a large amount of historical data during users' electricity consumption and automatically generate audit reports, thereby improving audit efficiency. However, the current way of generating audit reports mostly relies on unified standards and templates, ignoring the differences in electricity consumption behavior between different users. Unified audit reports are difficult to accurately reflect the actual electricity consumption and potential problems of different users, and users are required to analyze and handle them by themselves, resulting in low audit efficiency.

[0004] For example, for users with high electricity consumption and obvious peak-to-valley differences, the traditional audit method that uses unified standards and templates may not be able to effectively identify whether they have abnormal electricity consumption behavior or energy-saving potential; and for users whose payment habits and business changes frequently, important audit clues may be missed due to lack of timely tracking. Summary of the invention

[0005] The present invention provides a method and device for generating personalized audit reports based on user behavior, which can generate personalized audit reports for different users and improve audit efficiency.

[0006] In a first aspect, the present invention provides a method for generating personalized audit reports based on user behavior, the method comprising: obtaining historical electricity consumption data of users to be audited; the historical electricity consumption data includes electricity consumption, electricity bill payment records and business change records; based on the historical electricity consumption data, feature extraction is performed to determine electricity consumption behavior characteristics; electricity consumption behavior characteristics include average electricity consumption, peak-to-valley electricity consumption ratio, payment habits and business change characteristics; based on the electricity consumption behavior characteristics of the user, personalized classification is performed to obtain the audit category of the user to be audited; wherein each audit category corresponds to multiple audit items; based on the audit category of the user to be audited, the historical electricity consumption data is audited to determine the audit result of the user to be audited; based on the audit result of the user to be audited, a personalized audit report for the user to be audited is generated.

[0007] In a possible implementation, based on the historical electricity consumption data, feature extraction is performed to determine the characteristics of electricity consumption behavior, including: dividing the historical period of the historical electricity consumption data into time periods to determine multiple time windows; based on the historical electricity consumption data of each time window, the average electricity consumption is calculated; the average electricity consumption includes the long-term average electricity consumption and the short-term average electricity consumption, and the short-term average electricity consumption includes the average electricity consumption during the off-peak period and the average electricity consumption during the peak period; based on the average electricity consumption, the sum of the electricity consumption during the peak period in each time window and the sum of the electricity consumption during the off-peak period are calculated; based on the electricity consumption during the peak period in each time window, the average electricity consumption during the peak period in each time window is calculated. The peak-to-valley electricity consumption ratio of each time window is calculated by summing up the electricity consumption during high and low periods and the sum of the electricity consumption during low and high periods. Based on the historical electricity consumption data, the user's payment records are analyzed, and the frequency of various payment behaviors of the users to be audited is counted, and the payment behaviors include on-time payment, overdue payment and early payment. Based on the frequency of various payment behaviors of the users to be audited, the payment habits of the users to be audited are determined. Based on the historical electricity consumption data, the user's business change records are analyzed, and the business change information of the users to be audited is counted, and the business change information includes the business change type and business change frequency. Based on the business change information of the users to be audited, the business change characteristics are determined.

[0008] In one possible implementation, personalized classification is performed based on the user's electricity usage behavior characteristics to obtain the audit category of the user to be audited, including: performing standardization processing based on the electricity usage behavior characteristics to obtain standard characteristics of the electricity usage behavior; inputting the standard characteristics of the electricity usage behavior into a preset classification model to obtain the audit category of the user to be audited; and determining multiple audit items based on the audit category and the electricity usage behavior characteristics.

[0009] In a possible implementation, before performing personalized classification based on the user's electricity usage behavior characteristics and obtaining the audit category of the user to be audited, it also includes: obtaining historical electricity usage data of multiple users and the audit categories of multiple users; performing feature extraction on the historical electricity usage data of each user to determine the electricity usage behavior characteristics of each user; determining multiple training samples with the electricity usage behavior characteristics of each user as input and the audit category of each user as output; and performing training based on the multiple training samples to obtain a preset classification model.

[0010] In one possible implementation, the audit results include electricity consumption analysis results, payment record analysis results, business change review results, contract terms review results and comprehensive evaluation results; based on the audit category of the user to be audited, the historical electricity consumption data is audited to determine the audit results of the user to be audited, including: determining the electricity consumption analysis results based on the historical electricity consumption data, average electricity consumption and peak-to-valley electricity consumption ratio; determining the payment record analysis results based on the historical electricity consumption data and payment habits; determining the business change review results and contract terms review results based on the historical electricity consumption data and business change characteristics; determining the comprehensive evaluation results based on the electricity consumption analysis results, payment record analysis results, business change review results and contract terms review results.

[0011] In one possible implementation, a personalized audit report for the user to be audited is generated based on the audit results of the user to be audited, including: determining a report template based on the audit results, audit categories, and multiple audit items; determining data to be filled in based on the audit results and historical electricity consumption data; generating an initial report based on the report template and the data to be filled in; determining display features of each key point in the initial report based on the audit results; the display features include font format and display color; rendering the initial report based on the display features of each key point to obtain a personalized audit report for the user to be audited.

[0012] In a possible implementation, the method also includes: performing time series analysis based on the electricity consumption behavior characteristics of the user to be audited, determining the electricity consumption time series vector of the user to be audited, the electricity consumption time series vector including the electricity consumption behavior characteristics at each moment in the historical period; based on the electricity consumption time series vector of the user to be audited, predicting the predicted electricity consumption data of the user to be audited; the predicted electricity consumption data including the electricity consumption behavior characteristics at each moment in the future period; and updating the personalized audit report based on the predicted electricity consumption data.

[0013] In one possible implementation, after updating the personalized audit report based on the predicted electricity consumption data, it also includes: monitoring the real-time electricity consumption data of the user to be audited; generating real-time electricity consumption characteristics of the user to be audited based on the real-time electricity consumption data; monitoring the real-time electricity consumption of the user to be audited based on the updated personalized audit report and the real-time electricity consumption characteristics, and determining whether there is any abnormality in the real-time electricity consumption of the user to be audited; if there is any abnormality in the real-time electricity consumption of the user to be audited, recording the real-time electricity consumption data in the time period with the abnormality, and performing a personalized audit based on the real-time electricity consumption data in the time period with the abnormality, and generating a personalized audit report.

[0014] In one possible implementation, after generating a personalized audit report for the user to be audited based on the audit results of the user to be audited, the method further includes: receiving feedback information sent by the user, the feedback information being used to indicate the content and items that the user has doubts about in the personalized audit report; parsing the questionable content and items fed back by the user based on the feedback information; determining the historical electricity consumption data, electricity consumption behavior characteristics and audit results related to the questionable content and items based on the personalized audit report, as well as the questionable content and items; and generating a personalized supplementary report based on the historical electricity consumption data, electricity consumption behavior characteristics and audit results related to the questionable content and items.

[0015] In a second aspect, an embodiment of the present invention provides a personalized audit report generation device based on user behavior, the generation device comprising: a communication module, used to obtain historical electricity consumption data of the user to be audited; the historical electricity consumption data includes electricity consumption, electricity bill payment records and business change records; a processing module, used to extract features based on the historical electricity consumption data, and determine electricity consumption behavior characteristics; electricity consumption behavior characteristics include average electricity consumption, peak-to-valley electricity consumption ratio, payment habits and business change characteristics; based on the user's electricity consumption behavior characteristics, personalized classification is performed to obtain the audit category of the user to be audited; wherein each audit category corresponds to multiple audit items; based on the audit category of the user to be audited, the historical electricity consumption data is audited to determine the audit result of the user to be audited; based on the audit result of the user to be audited, a personalized audit report for the user to be audited is generated.

[0016] In a third aspect, an embodiment of the present invention provides an electronic device, comprising a memory and a processor, the memory storing a computer program, the processor being used to call and run the computer program stored in the memory to perform the steps of the method described in the first aspect and any possible implementation method of the first aspect.

[0017] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and wherein when the computer program is executed by a processor, the steps of the method described in the first aspect and any possible implementation method of the first aspect are implemented.

[0018] The present invention provides a method and device for generating personalized audit reports based on user behavior. The present invention obtains the user's average power consumption, peak-to-valley power consumption ratio, payment habits, business change characteristics and other power consumption behavior characteristics by analyzing the user's historical power consumption data, and performs personalized classification based on the power consumption behavior characteristics, determines the audit category and audit items, and realizes personalized classification of users. Afterwards, the historical power consumption data is audited based on the audit category to generate personalized audit reports, and different personalized audit reports are generated for different users, comprehensively considering the differences in power consumption behavior of different users, without the need for users to analyze and process by themselves, and improving the audit efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0020] Figure 1 It is a flowchart of a method for generating a personalized audit report based on user behavior provided by an embodiment of the present invention;

[0021] Figure 2 It is a structural schematic diagram of a personalized audit report generation device based on user behavior provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0022] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0023] In the description of the present invention, unless otherwise specified, " / " means "or", for example, A / B can mean A or B. "And / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, "at least one" and "plurality" refer to two or more. The words "first", "second", etc. do not limit the quantity and execution order, and the words "first", "second", etc. do not limit them to be different.

[0024] In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a concrete way for easy understanding.

[0025] In addition, the terms "including" and "having" and any variations thereof mentioned in the description of this application are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or modules is not limited to the listed steps or modules, but may optionally include other steps or modules that are not listed, or may optionally include other steps or modules that are inherent to these processes, methods, products or devices.

[0026] In order to make the purpose, technical solutions and advantages of the present invention more clear, the following will be described through specific embodiments in conjunction with the accompanying drawings of the present invention.

[0027] As described in the background art, the current audit method using a unified audit report has the technical problem of requiring users to perform analysis and processing by themselves and having low audit efficiency.

[0028] To solve this technical problem, Figure 1 As shown, the embodiment of the present invention provides a method for generating a personalized audit report based on user behavior. The method includes steps S101-S105.

[0029] S101. Obtain historical electricity consumption data of the user to be audited.

[0030] In the embodiment of the present application, the historical electricity consumption data includes electricity consumption, electricity bill payment records and business change records.

[0031] Exemplarily, the user's electricity consumption is used to reflect the user's historical electricity consumption, which can be obtained through electricity meters, power supply company systems, and third-party platforms. Electricity meters include smart meters and ordinary meters. Smart meters can upload electricity consumption data to the company's data system in real time or at regular intervals for easy query and monitoring. The power supply company's data system records the electricity consumption information of each user. Historical electricity consumption data can be obtained from the power supply company during the audit process. Users can also pay electricity bills and query electricity consumption through third-party platforms, which can provide historical electricity consumption data.

[0032] Exemplarily, the embodiment of the present invention can obtain the user's electricity payment record and service change record by querying the database of the power supply company.

[0033] Among them, business change records include abnormal marketization changes (name change, transfer and classification change) - non-market users are changed to marketization users through the name change, transfer and classification change process. Abnormal marketization changes (account merging) - marketization users merge accounts with ordinary purchasing users. Abnormal marketization changes (household separation) - marketization users are changed to agent power purchasing users in the household separation process. Abnormal marketization changes (capacity increase) - marketization users are changed to agent power purchasing users in the capacity increase process, or the capacity increase part is billed separately and is an agent power purchasing user. The marketization attribute classification does not match the marketization type of the metering point - in the new installation or classification change process, the market attribute classification does not match the marketization type of the metering device. The marketization attribute classification does not match the electricity consumption category - the electricity consumption category is selected as large industry or general industry and commerce, but the marketization attribute classification is non-marketization. The capacity applied for capacity reduction recovery is inconsistent with the capacity selected for investigation - the operating capacity applied for capacity reduction recovery is inconsistent with the sum of the nameplate capacity of the receiving equipment. The capacity applied for capacity reduction is inconsistent with the capacity selected for investigation - the application capacity in the capacity reduction process is inconsistent with the nameplate capacity of the receiving equipment. Warning of insufficient balance of electricity bills - the balance of electricity bills of users covered by fee control or users not covered is insufficient to pay the electricity bills expected within three days. Warning of irregular breach handling - the breach handling in the breach electricity use and electricity theft management process does not comply with regulations. Warning of abnormal subsidies for new photovoltaic installations and capacity increases - in the process of new installations or capacity increases for photovoltaic users, the name of the electricity price corresponding to the power generation gateway metering point is incorrect. Unrefunded electricity bills for newly cancelled users - in the process of account cancellation, users still have pre-collected balances and the balance is more than twice the electricity bill issued last month. Abnormal implementation of peak electricity prices (monthly) - regularly screen high-voltage users to check whether the peak electricity prices are correctly implemented. Abnormal implementation of peak electricity prices (daily) - daily screening of new changes in high-voltage users to check whether the peak electricity prices are correctly implemented. Abnormal subsidies for distributed photovoltaic capacity increases - after distributed photovoltaic users increase capacity across the year, there is only one subsidized electricity price. Abnormal subsidies for new photovoltaic installations and capacity increases - after the new installation or capacity increase process of photovoltaic households is archived, the name of the electricity price corresponding to the power generation gateway metering point is incorrect. Error in the calculation of basic electricity charges for users with single power supply and multiple metering points - For users with single power supply and multiple metering points who charge basic electricity charges according to the actual maximum demand, the demand value mode is not "sum". Industrial and commercial users changed to residential users - the situation where industrial and commercial users changed to residential users. Arrears warning - after the high-voltage user issues the electricity bill, it still has not paid the bill 24 hours before the 4th of the next month. Metering specialty - including over-capacity electricity consumption and overdue application verification warning. Reverse power warning - use the collected indications to screen users who generate reverse active power. Distributed photovoltaic over-capacity users - obtain the list of distributed photovoltaic over-capacity users pushed by the collection system.

[0034] S102: Extract features based on historical electricity consumption data to determine electricity consumption behavior characteristics.

[0035] In the embodiment of the present application, the electricity usage behavior characteristics include average electricity usage, peak-to-valley electricity usage ratio, payment habits, and business change characteristics.

[0036] In some embodiments, the average power consumption is the average power consumption of the user within a certain period of time (such as a month, quarter, or year). The average power consumption includes the long-term average power consumption and the short-term average power consumption. The short-term average power consumption includes the average power consumption during the off-peak period and the average power consumption during the peak period.

[0037] In some embodiments, the peak-to-valley electricity consumption ratio is the ratio of electricity consumption during peak hours to electricity consumption during off-peak hours, and is used to reflect the user's electricity consumption period preference.

[0038] In some embodiments, the payment habits include payment time, payment channel, stability of payment amount, etc., reflecting the user's electricity bill payment behavior pattern. Payment behavior includes on-time payment, overdue payment, and early payment.

[0039] In some embodiments, the service change characteristics include the frequency and type of information such as changes in the user's electricity usage characteristics, adjustments to electricity usage capacity, and replacement of electricity meters.

[0040] As a possible implementation manner, step S102 may be specifically implemented as steps S1021-S1029.

[0041] S1021. Divide the historical periods of the historical electricity consumption data into time periods and determine multiple time windows.

[0042] S1022. Calculate average power consumption based on the historical power consumption data of each time window.

[0043] S1023. Based on the average power consumption, calculate the sum of the power consumption during the peak period and the sum of the power consumption during the off-peak period in each time window.

[0044] S1024. Calculate the peak-to-valley power consumption ratio of each time window based on the sum of the power consumption during the peak period and the sum of the power consumption during the valley period in each time window.

[0045] S1025. Analyze the user's payment records based on historical electricity consumption data, and count the frequency of various payment behaviors of the users to be audited.

[0046] In some embodiments, payment behaviors include on-time payments, overdue payments, and early payments.

[0047] S1026. Determine the payment habits of the user to be audited based on the frequency of various payment behaviors of the user to be audited.

[0048] S1027. Based on the historical electricity consumption data, analyze the user's business change records and compile statistics on the business change information of the users to be audited.

[0049] In some embodiments, the service change information includes the service change type and the service change frequency.

[0050] S1028. Determine business change characteristics based on the business change information of the user to be audited.

[0051] S103: Based on the user's electricity usage behavior characteristics, perform personalized classification to obtain the audit category of the user to be audited.

[0052] Among them, each audit category corresponds to multiple audit items.

[0053] In some embodiments, the audit categories include normal electricity users, high energy consumption users, inefficient electricity users, irregular electricity users, defaulting electricity users, potential electricity thieves, and energy-saving model users.

[0054] Among them, normal electricity users have stable electricity consumption, good payment habits, and no obvious abnormal electricity consumption behavior. The electricity consumption of high-energy-consuming users is much higher than the average level, and there may be aging or overuse of equipment. Inefficient electricity users have low electricity efficiency, such as using a large number of high-energy-consuming equipment and having a large number of appliances in standby mode. Irregular electricity users have irregular electricity usage patterns and large fluctuations in electricity consumption, which may be related to the users' special living habits. Defaulting electricity users have problems such as overdue payment of electricity bills and unauthorized changes in the nature or capacity of electricity use. The electricity consumption of potential electricity thieves is abnormally low, which is inconsistent with the electricity equipment declared by the users, and there may be suspicion of electricity theft. Model energy-saving households have high electricity efficiency, actively participate in energy-saving activities, and use energy-saving equipment.

[0055] In some embodiments, the audit items include power consumption analysis, peak-to-valley power consumption ratio analysis, payment record analysis, business change review, contract terms review, equipment usage review, abnormal behavior identification, energy-saving suggestions, etc.

[0056] Among them, power consumption analysis is to check whether the user's power consumption exceeds the maximum capacity specified in the contract. Analyze the trend of power consumption and identify whether there are abnormal fluctuations. Peak-to-valley power consumption ratio analysis is to check whether the user's power consumption ratio during peak hours and off-peak hours is reasonable. Evaluate whether the user has fully utilized the time-of-use electricity price policy. Payment record analysis is to check the user's electricity bill payment record to check whether there is overdue payment or arrears. Analyze payment habits to see if there is room for improvement. Business change review is to check the user's business change record to confirm whether the change procedures are complete. Verify whether the user has handled capacity increase, capacity reduction and other businesses in accordance with the prescribed procedures. Contract terms review is to check the contract terms signed between the user and the power company to ensure that the user complies with relevant regulations. Check whether there is any violation of the contract terms. Equipment usage inspection is to check whether the electrical equipment used by the user meets the energy-saving standards. Evaluate whether the user has reasonably used the various services provided by the smart grid. Abnormal behavior identification is to identify whether the user's power consumption pattern is abnormal through time series analysis and other methods. Check whether there is unreasonable power consumption behavior, such as stealing electricity, private wiring, etc. Energy-saving suggestions are to provide personalized energy-saving suggestions based on the user's power consumption behavior characteristics. Recommend energy-saving products and services suitable for users.

[0057] As a possible implementation manner, step S103 may be specifically implemented as steps S1031 - S1033 .

[0058] S1031. Perform standardization processing based on the electricity usage behavior characteristics to obtain standard characteristics of the electricity usage behavior.

[0059] S1032. Input the standard features of electricity usage behavior into a preset classification model to obtain the audit category of the user to be audited.

[0060] In some embodiments, the preset classification model is obtained by training with historical electricity usage data of multiple users and the audit categories of the multiple users, and is used to predict the audit category of the user.

[0061] S1033. Determine multiple audit items based on the audit category and electricity usage behavior characteristics.

[0062] For example, for normal electricity users, the audit items include electricity consumption trend analysis and bill payment records. Electricity consumption trend analysis: monitor the trend of electricity consumption changes to confirm that there are no abnormal fluctuations. Bill payment records: check the records of electricity bills paid on time to ensure that there are no outstanding bills.

[0063] For example, for high energy consumption households, the audit items include power equipment review, energy-saving suggestions and peak-valley power consumption analysis. Power equipment review: Check whether there are high energy consumption equipment in the user's home and evaluate its efficiency. Energy-saving suggestions: Provide energy-saving transformation suggestions, such as replacing high-efficiency appliances. Peak-valley power consumption analysis: Analyze whether the user effectively utilizes the peak-valley electricity price strategy.

[0064] For example, for inefficient electricity users, the audit items include standby power detection and electricity behavior guidance. Standby power detection: Detect the standby power of the user's home appliances to reduce unnecessary energy consumption. Electricity behavior guidance: Provide improvement suggestions, such as turning off unused appliances in a timely manner.

[0065] For example, for irregular electricity users, the audit items include power usage pattern analysis and anomaly detection. Power usage pattern analysis: In-depth analysis of the user's power usage pattern to find out the regularity. Anomaly detection: Detect whether there is an abnormal power usage pattern, such as frequent power outages and restarts.

[0066] For example, for users who violate the contract, the audit items include contract terms verification, business change review and overdue payment reminder. Contract terms verification: Check whether the user has violated the terms of the power supply contract. Business change review: Check whether the user has handled the business change in accordance with the prescribed procedures. Overdue payment reminder: urge payment of overdue electricity bills.

[0067] For example, for potential electricity thieves, the audit items include comparative analysis of electricity consumption, on-site inspection and nighttime electricity consumption monitoring. Comparative analysis of electricity consumption: compare with historical data and similar users to identify abnormally low electricity consumption. On-site inspection: check the user line connection status on site to find out whether there is any illegal access to the power grid. Nighttime electricity consumption monitoring: pay special attention to electricity consumption at night, because electricity thieves may use more electricity during this time period.

[0068] For example, for energy-saving model households, the audit items include evaluation of the effectiveness of energy-saving measures, application of reward mechanisms, and sharing of best practices. Evaluation of the effectiveness of energy-saving measures: evaluate the actual effect of the energy-saving measures taken by users. Application of reward mechanisms: confirm whether the user meets the conditions for receiving energy-saving rewards. Sharing of best practices: encourage users to share their energy-saving experiences with other users.

[0069] S104. Based on the audit category of the user to be audited, audit the historical electricity consumption data to determine the audit result of the user to be audited.

[0070] In some embodiments, the audit results include electricity consumption analysis results, payment record analysis results, business change review results, contract terms review results and comprehensive evaluation results.

[0071] Exemplarily, the power consumption analysis results include power consumption trend analysis results, peak-to-valley power consumption ratio analysis results, power consumption rationality assessment results and abnormal power consumption detection results.

[0072] Among them, power consumption trend analysis: check the user's power consumption trend over time to identify whether there is an abnormal increase or decrease. Peak-valley power consumption ratio analysis: analyze the user's power consumption ratio during peak hours and off-peak hours to determine whether the user has reasonably utilized the peak-valley electricity price policy. Power consumption rationality assessment: compare the user's power consumption with the power consumption equipment reported by the user to assess whether the power consumption is reasonable. Abnormal power consumption detection: use anomaly detection algorithms to identify abnormal situations in the user's power consumption pattern, such as sudden increases or decreases in power consumption.

[0073] For example, the payment record analysis results include payment habit assessment results, arrears review results, and payment frequency analysis results. Payment habit assessment: Statistics of the user's payment records, including the number of on-time payments, overdue payments, and early payments. Arrears review: Check whether the user has an arrears record and whether there is a long-term failure to pay electricity bills. Payment frequency analysis: Analyze the user's payment frequency to determine whether there is an abnormal payment pattern.

[0074] Exemplarily, the business change review results include the change record verification results, change frequency analysis results, and change compliance review results. Change record verification: Check the user's business change records to confirm whether each change complies with the prescribed process. Change frequency analysis: Count the user's business change frequency to determine whether there are frequent changes. Change compliance review: Ensure that each business change of the user complies with the contract terms and relevant laws and regulations.

[0075] For example, the contract clause review results include the contract clause verification results, the breach of contract inspection results, and the clause applicability assessment results. Contract clause verification: Check the contract clauses between the user and the power company one by one to ensure that the user complies with all clauses. Breach of contract inspection: Check whether the user has violated the contract clauses, such as increasing the power load without authorization. Clause applicability assessment: Evaluate whether the contract clauses are applicable to the user's current power usage.

[0076] For example, the comprehensive assessment results include comprehensive scores, recommended measures and risk level assessment. Comprehensive score: Based on the above analysis results, a comprehensive score is given to evaluate the user's overall electricity usage behavior. Recommended measures: Based on the comprehensive assessment results, specific improvement suggestions or warning measures are put forward. Risk level assessment: Based on the comprehensive assessment results, the user's risk level is rated to facilitate subsequent focus or management.

[0077] As a possible implementation manner, step S104 may be specifically implemented as steps S1041 - S1044 .

[0078] S1041. Determine the power consumption analysis result based on the historical power consumption data, average power consumption and peak-to-valley power consumption ratio.

[0079] S1042. Determine payment record analysis results based on historical electricity usage data and payment habits.

[0080] S1043. Based on historical electricity consumption data and business change characteristics, determine the business change review results and contract terms review results.

[0081] S1044. Determine the comprehensive evaluation results based on the electricity consumption analysis results, payment record analysis results, business change review results and contract terms review results.

[0082] S105. Generate a personalized audit report for the user to be audited based on the audit result of the user to be audited.

[0083] As a possible implementation manner, step S105 may be specifically implemented as steps S1051 - S1055 .

[0084] S1051. Determine the report template based on the audit results, audit category, and multiple audit items.

[0085] Exemplarily, each audit category corresponds to a report template. The embodiment of the present invention can determine the corresponding report template based on the audit category, and then modify the report template according to the audit result and multiple audit items to determine the final report template.

[0086] S1052. Based on the audit results and historical electricity consumption data, determine the data to be filled.

[0087] Exemplarily, the embodiment of the present invention can filter the historical electricity consumption data based on the audit results to determine the data to be filled in. For example, if the audit result shows that the user has an arrears record, the embodiment of the present invention can filter out the electricity consumption and electricity bill payment records related to the arrears record in the historical electricity consumption data to obtain the data to be filled in.

[0088] S1053. Generate an initial report based on the report template and the data to be filled.

[0089] Exemplarily, the embodiment of the present invention can fill the data to be filled into the report template one by one to generate an initial report.

[0090] S1054. Based on the audit results, determine the display characteristics of each key point in the initial report.

[0091] In some embodiments, the display characteristics include font format and display color.

[0092] For example, the embodiment of the present invention can determine the type of each key point in the initial report based on the audit results, such as power consumption mode, payment delay, non-compliant change, etc., and set different display features for each type. According to the type of each key point, the display feature of each key point is determined.

[0093] S1055. Render the initial report based on the display characteristics of each key point to obtain a personalized audit report for the user to be audited.

[0094] The present invention provides a method for generating a personalized audit report based on user behavior. By analyzing the user's historical electricity consumption data, the user's average electricity consumption, peak-to-valley electricity consumption ratio, payment habits, business change characteristics and other electricity consumption behavior characteristics are obtained, and personalized classification is performed based on the electricity consumption behavior characteristics, and the audit category and audit items are determined, thereby realizing personalized classification of users. Afterwards, the historical electricity consumption data is audited based on the audit category to generate a personalized audit report, thereby realizing the generation of different personalized audit reports for different users, comprehensively considering the differences in electricity consumption behavior of different users, and eliminating the need for users to analyze and process by themselves, thereby improving the audit efficiency.

[0095] Optionally, the method for generating personalized audit reports based on user behavior provided in an embodiment of the present invention further includes steps S201-S204 before step S103.

[0096] S201. Obtain historical electricity consumption data of multiple users and audit categories of multiple users.

[0097] S202: Extract features from each user's historical electricity usage data to determine each user's electricity usage behavior features.

[0098] S203: Taking the electricity consumption behavior characteristics of each user as input and the audit category of each user as output, a plurality of training samples are determined.

[0099] S204: Perform training based on multiple training samples to obtain a preset classification model.

[0100] In this way, the embodiment of the present invention can train a preset classification model before auditing the user to be audited, thereby facilitating the audit.

[0101] Optionally, the method for generating personalized audit reports based on user behavior provided in an embodiment of the present invention further includes steps S301-S303.

[0102] S301. Based on the electricity consumption behavior characteristics of the user to be audited, a time series analysis is performed to determine the electricity consumption time series vector of the user to be audited.

[0103] In some embodiments, the electricity usage time series vector includes electricity usage behavior characteristics at each moment in the historical period.

[0104] S302: Based on the electricity consumption time series vector of the user to be audited, predict the predicted electricity consumption data of the user to be audited.

[0105] In some embodiments, the predicted electricity usage data includes electricity usage behavior characteristics at each moment in a future period.

[0106] As a possible implementation method, the embodiment of the present invention can split the power consumption time series vector of the user to be audited, and determine multiple training samples, wherein each training sample takes the power consumption time series vector of the first time period as input and takes the power consumption time series vector of the second time period after the first time period as output. A neural network is trained based on the multiple training samples to obtain a prediction model. The first time period is any time period in the historical period.

[0107] In this way, the embodiment of the present invention can input the electricity consumption time series vector of the user to be audited into the prediction model to obtain the predicted electricity consumption data for the future period.

[0108] S303. Update the personalized audit report based on the predicted electricity consumption data.

[0109] In this way, the embodiment of the present invention can predict the electricity usage data of future time periods through the user's historical electricity usage data, and update the personalized audit report to facilitate the user to observe the electricity usage situation in the future time periods.

[0110] Optionally, the method for generating personalized audit reports based on user behavior provided in an embodiment of the present invention further includes steps S401-S404 after step S303.

[0111] S401. Monitor the real-time electricity consumption data of the users to be audited.

[0112] S402: Generate real-time electricity consumption characteristics of the user to be audited based on the real-time electricity consumption data.

[0113] S403: Based on the updated personalized audit report and the real-time power usage characteristics, the real-time power usage of the user to be audited is monitored to determine whether there is any abnormality in the real-time power usage of the user to be audited.

[0114] S404. If the real-time electricity usage of the user to be audited is abnormal, the real-time electricity usage data in the period of time when the abnormality exists is recorded, and based on the real-time electricity usage data in the period of time when the abnormality exists, a personalized audit is performed to generate a personalized audit report.

[0115] In this way, the embodiment of the present invention can compare the real-time power usage characteristics with the predicted power usage to determine whether the user's power usage is abnormal, thereby facilitating real-time auditing of the user's power usage and improving auditing efficiency.

[0116] Optionally, the method for generating personalized audit reports based on user behavior provided in an embodiment of the present invention further includes steps S501-S504 after step S105.

[0117] S501: Receive feedback information sent by a user.

[0118] In some embodiments, the feedback information is used to indicate the content and items that the user has doubts about in the personalized audit report.

[0119] S502: Based on the feedback information, analyze the questionable content and questionable items fed back by the user.

[0120] S503. Based on the personalized audit report, as well as the questionable content and questionable items, determine the historical electricity consumption data, electricity consumption behavior characteristics and audit results related to the questionable content and questionable items.

[0121] S504: Generate a personalized supplementary report based on the historical electricity consumption data, electricity consumption behavior characteristics and audit results related to the questionable content and questionable items.

[0122] In this way, the embodiment of the present invention can update the personalized audit report according to the user's concerns and needs, meet the user's needs, enhance the user experience, and further improve the audit efficiency.

[0123] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0124] The following is an embodiment of the device of the present invention. For details not described in detail therein, reference may be made to the corresponding method embodiment described above.

[0125] Figure 2 The structure diagram of a device for generating a personalized audit report based on user behavior provided by an embodiment of the present invention is shown. The generating device 600 includes a communication module 601 and a processing module 602 .

[0126] Communication module 601, used to obtain historical electricity consumption data of the user to be audited; the historical electricity consumption data includes electricity consumption, electricity bill payment records and business change records;

[0127] Processing module 602 is used to extract features based on historical electricity consumption data and determine electricity consumption behavior characteristics; electricity consumption behavior characteristics include average electricity consumption, peak-to-valley electricity consumption ratio, payment habits and business change characteristics; based on the user's electricity consumption behavior characteristics, personalized classification is performed to obtain the audit category of the user to be audited; wherein each audit category corresponds to multiple audit items; based on the audit category of the user to be audited, the historical electricity consumption data is audited to determine the audit results of the user to be audited; based on the audit results of the user to be audited, a personalized audit report for the user to be audited is generated.

[0128] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for generating personalized audit reports based on user behavior, characterized in that: include: Obtain historical electricity consumption data of users to be audited; The historical electricity consumption data includes electricity consumption, electricity fee payment records and business change records; Based on the historical electricity consumption data, feature extraction is performed to determine electricity consumption behavior characteristics; The electricity consumption behavior characteristics include average electricity consumption, peak-to-valley ratio, payment habits and business change characteristics; Based on the electricity consumption behavior characteristics of the user, a personalized classification is performed to obtain the audit category of the user to be audited; wherein each audit category corresponds to multiple audit items; Based on the audit category of the user to be audited, audit the historical electricity consumption data to determine the audit result of the user to be audited; Based on the audit results of the user to be audited, a personalized audit report for the user to be audited is generated.

2. The method for generating a personalized audit report based on user behavior according to claim 1, characterized in that: The extracting features based on the historical electricity usage data to determine the electricity usage behavior features includes: Dividing the historical periods of the historical electricity consumption data into time periods to determine multiple time windows; Based on the historical electricity consumption data of each time window, the average electricity consumption is calculated; the average electricity consumption includes the long-term average electricity consumption and the short-term average electricity consumption, and the short-term average electricity consumption includes the average electricity consumption during the off-peak period and the average electricity consumption during the peak period; Based on the average power consumption, calculate the sum of power consumption during peak hours and the sum of power consumption during off-peak hours in each time window; Based on the sum of the electricity consumption during the peak period and the sum of the electricity consumption during the valley period in each time window, the peak-valley electricity consumption ratio of each time window is calculated; Based on the historical electricity consumption data, analyze the user's payment records and count the frequencies of various payment behaviors of the user to be audited, wherein the payment behaviors include on-time payment, overdue payment and early payment; Determining the payment habits of the user to be audited based on the frequency of various payment behaviors of the user to be audited; Based on the historical electricity consumption data, analyzing the user's service change records, and collecting statistics on the service change information of the user to be audited, wherein the service change information includes the service change type and service change frequency; Based on the business change information of the user to be audited, the business change characteristics are determined.

3. The method for generating a personalized audit report based on user behavior according to claim 1, characterized in that: The personalized classification based on the electricity consumption behavior characteristics of the user to obtain the audit category of the user to be audited includes: Based on the electricity usage behavior characteristics, standardization processing is performed to obtain standard characteristics of the electricity usage behavior; Input the standard features of the electricity usage behavior into a preset classification model to obtain the audit category of the user to be audited; Based on the audit category and the electricity usage behavior characteristics, the multiple audit items are determined.

4. The method for generating a personalized audit report based on user behavior according to claim 1, characterized in that: Before performing personalized classification based on the electricity usage behavior characteristics of the user to obtain the audit category of the user to be audited, the method further includes: Obtaining historical electricity consumption data of multiple users and audit categories of the multiple users; Extract features from each user's historical electricity consumption data to determine each user's electricity consumption behavior characteristics; Taking the electricity consumption behavior characteristics of each user as input and the audit category of each user as output, multiple training samples are determined; Based on the multiple training samples, training is performed to obtain the preset classification model.

5. The method for generating a personalized audit report based on user behavior according to claim 1, characterized in that: The audit results include electricity consumption analysis results, payment record analysis results, business change review results, contract terms review results and comprehensive evaluation results; The auditing of the historical electricity consumption data based on the audit category of the user to be audited to determine the audit result of the user to be audited includes: Determining the power consumption analysis result based on the historical power consumption data, the average power consumption and the peak-to-valley power consumption ratio; Determining the payment record analysis result based on the historical electricity usage data and payment habits; Based on the historical electricity consumption data and business change characteristics, determine the business change review results and contract terms review results; The comprehensive evaluation result is determined based on the electricity consumption analysis results, payment record analysis results, business change review results and contract terms review results.

6. The method for generating a personalized audit report based on user behavior according to claim 1, characterized in that: Generating a personalized audit report for the user to be audited based on the audit result of the user to be audited includes: Determine a report template based on the audit result, the audit category, and the multiple audit items; Based on the audit result and the historical electricity consumption data, determine the data to be filled; Generate an initial report based on the report template and the data to be filled; Based on the audit results, determine the display characteristics of each key point in the initial report; the display characteristics include font format and display color; Based on the display characteristics of the key points, the initial report is rendered to obtain a personalized audit report for the user to be audited.

7. The method for generating a personalized audit report based on user behavior according to claim 1, characterized in that: The method further comprises: Based on the electricity consumption behavior characteristics of the user to be audited, a time series analysis is performed to determine the electricity consumption time series vector of the user to be audited, wherein the electricity consumption time series vector includes the electricity consumption behavior characteristics at each moment in the historical period; Based on the power consumption time series vector of the user to be audited, predict the predicted power consumption data of the user to be audited; the predicted power consumption data includes power consumption behavior characteristics at each moment in the future period; Based on the predicted electricity usage data, the personalized audit report is updated.

8. The method for generating a personalized audit report based on user behavior according to claim 7, characterized in that: After updating the personalized audit report based on the predicted electricity consumption data, the method further includes: Monitor the real-time electricity consumption data of the user to be audited; Based on the real-time electricity consumption data, generating the real-time electricity consumption characteristics of the user to be audited; Based on the updated personalized audit report and the real-time power consumption characteristics, the real-time power consumption of the user to be audited is monitored to determine whether there is any abnormality in the real-time power consumption of the user to be audited; If the real-time electricity usage of the user to be audited is abnormal, the real-time electricity usage data in the period of abnormality is recorded, and based on the real-time electricity usage data in the period of abnormality, a personalized audit is performed to generate a personalized audit report.

9. The method for generating a personalized audit report based on user behavior according to claim 1, characterized in that: After generating a personalized audit report of the user to be audited based on the audit result of the user to be audited, the method further includes: Receiving feedback information sent by the user, wherein the feedback information is used to indicate the content and items that the user has doubts about in the personalized audit report; Based on the feedback information, analyzing the questionable content and questionable items of the user feedback; Based on the personalized audit report, as well as the questionable content and questionable items, determine the historical electricity consumption data, electricity consumption behavior characteristics and audit results related to the questionable content and questionable items; Generate a personalized supplementary report based on the historical electricity consumption data, electricity consumption behavior characteristics and audit results related to the questionable content and questionable items.

10. A personalized audit report generation device based on user behavior, characterized in that: include: A communication module is used to obtain the historical electricity consumption data of the user to be audited; the historical electricity consumption data includes electricity consumption, electricity fee payment records and business change records; A processing module, used for extracting features based on the historical electricity consumption data to determine electricity consumption behavior features; The electricity consumption behavior characteristics include average electricity consumption, peak-to-valley electricity consumption ratio, payment habits and business change characteristics; based on the electricity consumption behavior characteristics of the user, personalized classification is performed to obtain the audit category of the user to be audited; wherein each audit category corresponds to multiple audit items; based on the audit category of the user to be audited, the historical electricity consumption data is audited to determine the audit results of the user to be audited; based on the audit results of the user to be audited, a personalized audit report for the user to be audited is generated.

Images