Enterprise orderly power utilization monitoring and revenue risk analysis method and system

Abstract

The invention discloses an enterprise orderly power utilization monitoring and revenue risk analysis method and system, and the method comprises the steps: collecting first object data, and building a first monitoring calendar; and establishing a first topological model of the first object. And establishing a feature information base of the second object, and performing clustering analysis on the second feature of the feature information base to obtain a classification level of the second object. According to the enterprise orderly power utilization monitoring and revenue risk analysis method and system provided by the invention, accurate monitoring of an enterprise orderly power utilization plan execution condition is realized, a regional electric energy supply and demand gap is mastered, an orderly power utilization strategy is assisted to be adjusted, and regional power supply stability and power supply quality are improved. And on the other hand, the risk revenue state of the power consumer is accurately analyzed and discriminated, the power supply enterprise is assisted in formulating differentiated power marketing strategies and supervision measures on this basis, the operation risk is avoided, the accuracy of the marketing decision of the power supply enterprise is improved, the ability of the power supply enterprise to prevent the electric charge revenue problem is enhanced, and the management level is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of electricity consumption analysis, and in particular to a method and system for orderly electricity consumption monitoring and revenue risk analysis of an enterprise. Background Art

[0002] With the development of the economy, the electricity load of enterprises and residents has increased significantly, and the electricity demand has shown a "double peak" feature in winter and summer. The peak-to-valley difference has continued to expand, and the difficulty of ensuring power supply has increased year by year. The orderly electricity management carried out by power supply enterprises is not only related to the customer's satisfaction with electricity consumption, but also directly affects the stability of power supply. However, there are potential risks in the electricity consumption behavior of power users. The user's dishonesty will cause great difficulties for the power supply company to recover the electricity fee. In order to prevent the losses that may be caused to the power supply company by the user's dishonest behavior, avoid operating risks, recover electricity fees in time, and discover the irregular behaviors of power users such as overdue payment and illegal electricity use as early as possible, so as to improve the risk prevention ability of electricity fee recovery, it is an urgent need at present. At present, there is a lack of tools and methods for orderly electricity consumption monitoring of enterprises and risk analysis of electricity consumption of users, which is mainly manifested in the data barriers between power supply enterprises and users, data collection lags, and low timeliness of data monitoring. Summary of the invention

[0003] In view of the above-mentioned problems, the present invention is proposed.

[0004] Therefore, the technical problem solved by the present invention is: there is currently a lack of tools and methods for orderly electricity consumption monitoring of enterprises and risk analysis of electricity consumption of users, which is mainly manifested in the existence of data barriers between power supply enterprises and users, delayed data collection, and low timeliness of data monitoring.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a method for orderly electricity consumption monitoring and revenue risk analysis of an enterprise, comprising: collecting first object data and establishing a first monitoring calendar.

[0006] A first topological model of the first object is established.

[0007] A feature information library of the second object is established, and a cluster analysis is performed on the second feature of the feature information library to obtain a classification level of the second object.

[0008] As a preferred solution of the method for orderly electricity consumption monitoring and revenue risk analysis of enterprises described in the present invention, the collecting of first object data and establishing a first monitoring calendar includes associating the first object with the enterprise archives, establishing a first object data list by region, and obtaining the key data fields of the first object.

[0009] A first monitoring calendar is established based on the first object key data field.

[0010] As a preferred solution of the method for orderly power consumption monitoring and revenue risk analysis of enterprises described in the present invention, the first monitoring calendar includes obtaining enterprise power load data, taking each hour as a time node, and establishing an enterprise orderly power consumption monitoring model according to the power restriction requirements for each enterprise in the first monitoring calendar, and calculating the power consumption of the enterprise. Compare the first monitoring calendar, analyze the power consumption deviation, and record the comparison results.

[0011] As a preferred solution of the method for orderly electricity consumption monitoring and revenue risk analysis of enterprises described in the present invention, the establishment of the first topological model of the first object includes establishing a first visual topological model, comparing the current electricity supply and demand status, and recording and analyzing relevant data when an imbalance in electricity supply and demand occurs.

[0012] As a preferred solution of the method for orderly electricity consumption monitoring and revenue risk analysis of an enterprise described in the present invention, the feature information library of the second object includes a label library and a feature portrait of the second object.

[0013] As a preferred solution of the method for monitoring orderly electricity consumption and analyzing revenue risks of enterprises described in the present invention, wherein: the first object includes but is not limited to the orderly electricity consumption plan of the enterprise, the first monitoring calendar includes but is not limited to the orderly electricity consumption calendar of the enterprise, and the first topological model includes a regional electricity supply and demand visualization topological model.

[0014] The second object includes but is not limited to the user's electricity revenue risk, and the second feature is a key feature included in the feature portrait of the second object.

[0015] As a preferred solution of the method for orderly electricity consumption monitoring and revenue risk analysis of enterprises described in the present invention, the cluster analysis includes using a clustering algorithm to group users, identify user groups with similar characteristics, define different degrees of user revenue risk levels, and predict user electricity consumption revenue risk factors based on the user's most recent monthly settlement status.

[0016] A system for monitoring orderly electricity consumption and analyzing revenue risk of an enterprise, characterized by: comprising:

[0017] The collection module collects the first object data and establishes a first monitoring calendar.

[0018] A topology module is established to establish a first topology model of the first object.

[0019] The calculation module establishes a feature information library of the second object, performs cluster analysis on the second feature of the feature information library, and obtains a classification level of the second object.

[0020] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0021] A computer-readable storage medium stores a computer program, which implements the steps of the method described above when executed by a processor.

[0022] The beneficial effects of the present invention are as follows: based on energy big data resources, it solves problems such as data discreteness and data heterogeneity, and realizes correlation analysis of multi-type energy data and real-time monitoring data. Through the application of this patent, on the one hand, it realizes accurate monitoring of the implementation of the orderly power consumption plan of the enterprise, grasps the regional power supply and demand gap, assists in adjusting the orderly power consumption strategy, and improves the regional power supply stability and quality. On the other hand, it realizes accurate analysis and identification of the risk revenue status of power users, and on this basis, assists power supply companies in formulating differentiated power marketing strategies and supervision measures, avoids operating risks, improves the accuracy of marketing decisions of power supply companies, and enhances the ability of power supply companies to prevent electricity fee revenue problems and improves management level. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. 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 creative work. Among them:

[0024] Figure 1 An overall flow chart of a method and system for orderly electricity consumption monitoring and revenue risk analysis for an enterprise provided in the first embodiment of the present invention.

[0025] Figure 2 A flowchart of user electricity revenue risk labeling of a method and system for orderly electricity consumption monitoring and revenue risk analysis for an enterprise provided in the first embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0027] Example 1, reference Figure 1 , Figure 2, which is an embodiment of the present invention, provides a method for orderly electricity consumption monitoring and revenue risk analysis of an enterprise, comprising:

[0028] S1: Collect first object data and establish a first monitoring calendar.

[0029] In the present invention, the first object is the orderly electricity consumption plan of the enterprise, and the first monitoring calendar is the orderly electricity consumption calendar of the enterprise. By associating the orderly electricity consumption plan of the enterprise user with the enterprise archive, establishing a list of orderly electricity consumption enterprises by region, and sorting out the key data fields of the orderly electricity consumption monitoring of the enterprise, including the name of the peak-shifting power-limiting enterprise, the peak-shifting power-limiting time period, the peak-shifting power-limiting electricity, the peak-valley power-limiting electricity, the regional total power-limiting electricity and other data fields. According to the key data information, the enterprise orderly electricity consumption monitoring calendar is established, and the orderly electricity consumption plan and time period of the enterprise are decomposed and matched to the calendar. Based on energy big data, the enterprise power load data is obtained, and each hour is used as the time node. According to the power restriction requirements for each enterprise in the orderly electricity consumption calendar, the power load of each enterprise is associated, and an orderly electricity consumption monitoring model for the enterprise is established. The hourly electricity consumption of the enterprise and the electricity consumption of a certain period are calculated, and the orderly electricity consumption calendar is compared. The execution deviation between the orderly electricity consumption plan of the enterprise and the actual electricity consumption is analyzed, and the comparison results are recorded to assist the power supply enterprise in monitoring and managing the execution effect of the orderly electricity consumption of the enterprise, strengthen the supervision and grasping force, and improve the stability of power supply of the power grid.

[0030] It should be noted that the first object includes but is not limited to the enterprise orderly electricity consumption plan, and may also be the enterprise electricity consumption behavior monitoring plan and the enterprise carbon emission monitoring plan. The corresponding first monitoring calendar may also be the enterprise electricity consumption behavior monitoring calendar and the enterprise carbon emission monitoring plan monitoring calendar.

[0031] In an optional embodiment of the present invention, the first object is an enterprise electricity consumption behavior monitoring plan, which refers to monitoring the daily electricity consumption behavior of the enterprise to ensure that the electricity consumption pattern meets the energy-saving and consumption-reduction requirements set by the power company and meets the grid stability requirements. The monitoring calendar is an enterprise electricity consumption behavior monitoring calendar, which aims to regularly track and record the electricity consumption behavior of the enterprise, and help the power supply company understand the laws of the enterprise's electricity consumption behavior and analyze it.

[0032] The process of collecting the first object data and establishing the first monitoring calendar is as follows:

[0033] First, the enterprise's electricity consumption behavior monitoring plan is associated with the enterprise's archive information, enterprise users are classified by region, and an enterprise electricity consumption behavior monitoring list is created. The data fields include enterprise name, regional information, and electricity consumption behavior pattern (such as peak and valley periods, electricity consumption increase and decrease trends, etc.).

[0034] The main fields are extracted from the monitoring data, such as the frequency of load changes of the enterprise, the electricity consumption pattern in a specific period of time, the number of times the load exceeds the standard, etc., and by screening and classifying these fields, a electricity consumption behavior monitoring calendar is gradually established.

[0035] Combine the power consumption patterns and calendar of the enterprise to build a monitoring model based on time nodes, and record the changes in the power consumption patterns of the enterprise on an hourly, daily or weekly basis. By comparing the set energy-saving indicators, monitor whether it meets the power grid power safety standards. This process helps power companies understand the power consumption patterns of enterprises in different time periods, identify abnormal power consumption behaviors, and take necessary measures.

[0036] In an optional embodiment of the present invention, the first object is a corporate carbon emission monitoring plan. With the improvement of environmental protection requirements, it is increasingly important for enterprises to monitor carbon emissions during electricity use. The corporate carbon emission monitoring plan aims to monitor the carbon emissions generated by corporate electricity use in real time to ensure that they meet carbon emission standards. The monitoring calendar is a corporate carbon emission monitoring calendar that records and evaluates historical data on corporate carbon emissions.

[0037] The process of collecting the first object data and establishing the first monitoring calendar is as follows:

[0038] Collect the carbon emission data generated by the company's electricity consumption, associate it with the company's archive records, and establish a list of corporate carbon emission monitoring data. The data fields may include company name, total electricity consumption, carbon emission coefficient, emission change trend, environmental protection compliance, etc.

[0039] According to the daily electricity consumption and carbon emission data of the enterprise, the enterprise carbon emission monitoring calendar is established by time period. The key fields of the calendar include carbon emission benchmark, electricity consumption limit, carbon emission compliance, seasonal emission fluctuations, etc.

[0040] According to the carbon emission monitoring calendar, a corporate carbon emission monitoring model is constructed. The model calculates the carbon emissions of the company every hour, day or month, and analyzes the deviation between the actual emissions and the set benchmark. This process can provide power companies with data on the company's carbon emission compliance, help supervise and guide the company's emission behavior during electricity use, and thus achieve energy conservation and emission reduction goals.

[0041] S2: Establishing a first topological model of the first object.

[0042] By summarizing the power supply range areas corresponding to power supply enterprises, establishing visual topological models of the transmission and distribution sides, and visually displaying the energy flow on the power supply side and the load on the distribution side, we can compare the current electricity supply and demand status. When there is an imbalance in electricity supply and demand, we can record the electricity supply and demand gap, occurrence time period, daily occurrence frequency, and monthly occurrence frequency. We can analyze the main distribution areas of the unbalanced supply and demand load, the main time periods of the unbalanced supply and demand, the supply and demand gap electricity volume, the enterprises in the areas corresponding to the unbalanced supply and demand load, and count the types and proportions of enterprises, so as to provide a reliable basis for power supply enterprises to adjust orderly electricity consumption strategies and plans.

[0043] S3: Establish a feature information library of the second object, perform cluster analysis on the second feature of the feature information library, and obtain a classification level of the second object.

[0044] In the present invention, the second object is the user's electricity revenue risk, and the feature information library includes a label library and a feature portrait.

[0045] Establishing a user electricity revenue risk label library includes associating key data such as electricity user files, payment information, and electricity consumption, establishing a user revenue risk label library, and labeling user electricity risk lines, including the number of overdue payments, overdue payment periods, overdue amount, and other information. By setting user electricity revenue risk analysis weights, early warning of user overdue payment behavior can be achieved, and a list of companies with revenue risks can be compiled in a timely manner to assist power supply companies in timely adjusting power supply service strategies and collecting electricity charges for different users.

[0046] Establishing a user revenue risk characteristic portrait includes establishing a user revenue risk characteristic portrait through user behavior data, historical records and other relevant information, using clustering algorithms to group users, identifying user groups with similar characteristics, defining different degrees of user revenue risk levels, and predicting user electricity revenue risk factors based on the user's most recent monthly settlement status. The portrait can better understand the customer, optimize the electricity revenue risk control strategy, and improve decision-making efficiency.

[0047] The portrait generation process includes: grouping and modeling the user's payment behavior data to create a portrait, which includes key features such as the frequency of overdue payment cycles, average overdue payment amount, and abnormal electricity consumption. The portrait can identify the user's behavior patterns and distinguish between high-risk and low-risk users. The portrait divides users into different revenue risk levels based on key features. For example, users with long overdue payment cycles and large amounts are classified as high-risk, and users who pay steadily are classified as low-risk, helping power companies to implement user risk warnings.

[0048] The key features in the feature profile include:

[0049] Number of arrears: The number of arrears in history reflects the stability of the user's payment.

[0050] Amount owed: The amount owed each time or the total amount owed by the user, revealing the severity of the risk.

[0051] Arrears cycle: The frequency of users' arrears in different cycles can reflect the cyclical risk of users' payment.

[0052] Abnormal electricity consumption: Sudden or abnormal increases in a user's electricity consumption may reveal the volatility of their ability to pay bills.

[0053] The second object includes but is not limited to the user's electricity revenue risk, and can also be the user's electricity behavior deviation monitoring and user's electricity quality risk assessment.

[0054] In an optional embodiment of the present invention, the second object is user electricity behavior deviation monitoring. The goal of user electricity behavior deviation monitoring is to identify user groups with significant deviations in electricity usage patterns or behaviors, thereby assisting power companies in risk management of users who may cause grid fluctuations or abnormal electricity usage. Establish a user electricity behavior deviation label library, combine power user files with electricity behavior data, and collect user load change data, electricity time period preferences, frequent fluctuations and other information. These data can be obtained from the historical records of smart meters to form a label library of user electricity behavior. The label library contains fields such as power fluctuation frequency, peak and valley load differences, and abnormal power behavior identification. These label fields can help power companies identify possible abnormal features in user electricity behavior and mark users with abnormal load changes. According to the historical data of user behavior and the set deviation threshold, the label value of each user is assigned. For example, the power fluctuation frequency can be classified according to the load fluctuation amplitude of the user over a period of time, and users with frequent fluctuations will be assigned high-risk label values. Establish a user electricity behavior deviation feature portrait. In the process of establishing the feature portrait, the power behavior deviation feature portrait is generated by modeling the user's electricity behavior data. These portraits are based on the behavioral characteristics of users, identifying different electricity usage patterns such as high-frequency fluctuation users, seasonal peak users, and sudden increase users. Based on the data in the tag library, the clustering algorithm is used to divide the user groups, and users with more significant behavioral deviations are classified as high-risk groups, which provides a basis for power companies to implement risk warnings and adjust service strategies. Feature portraits will include feature categories such as the rate of change of electricity usage patterns, fluctuation frequency, and time period characteristics, combined with the analysis weights of each feature to help identify and manage high-risk users. Based on real-time data, feature portraits can be dynamically updated to help power companies understand changes in user behavior in real time so that they can adjust monitoring strategies in a timely manner.

[0055] In an optional embodiment of the present invention, the second object is a user power quality risk assessment. User power quality risk assessment refers to the assessment of the potential risks of different users in terms of power quality, such as users who may cause harmonic pollution to the power grid or users who are sensitive to power fluctuations. Establishing a label library and a feature portrait for this object helps to improve the power grid quality management capabilities. Establish a user power quality risk label library to collect user profile information and their power quality data, including harmonic pollution, reactive power, power frequency fluctuation, etc. By analyzing these data, mark the user's power quality risk. The fields in the label library may include harmonic pollution level, frequency fluctuation value, powerless compensation demand, etc. These labels can describe the user's power quality characteristics and provide a basis for identifying high-risk users. Assign values ​​to labels according to the user's power quality problems. For example, users with frequent harmonic pollution are assigned high-risk labels, or users with greater powerless compensation requirements are marked as users with higher quality risks. Establish a user power quality risk feature portrait, extract information from the user's power quality data and generate a portrait, classify users with high frequency and severe harmonic pollution, and generate a feature portrait of power quality risk. Through feature profiling, users are divided into different power quality risk levels, helping power companies identify user groups that have a greater impact on the quality of the power grid. Feature profiling can be updated based on the real-time power quality changes of users, providing power companies with a basis for dynamically adjusting power quality and ensuring the stability of the power grid.

[0056] When constructing a revenue risk profile, different clustering algorithms can be used to identify user groups with similar risk characteristics, which can be K-means clustering algorithm and hierarchical clustering algorithm.

[0057] K-means is a clustering algorithm based on Euclidean distance. For revenue risk characteristics, users can be divided into several groups by selecting an appropriate K value. The similarity of users in terms of the number of arrears and the amount of arrears is calculated, and similar users are grouped into the same group to help identify high-risk user groups with frequent arrears and large amounts. Through this algorithm, power companies can quickly identify high-risk users and adopt targeted strategies.

[0058] Hierarchical clustering algorithm is a clustering method that aggregates objects layer by layer. In the application of user electricity revenue risk, hierarchical clustering can gradually aggregate users with similar arrears times and amounts layer by layer to form a tree structure. By observing the clustering results at different levels, power companies can identify groups with different degrees of arrears behavior. Hierarchical clustering is particularly suitable for identifying user groups with multi-level risk characteristics, helping power companies to group and manage users according to risk levels.

[0059] The above embodiments also include a system for monitoring orderly electricity consumption and analyzing revenue risks of enterprises, which is specifically:

[0060] The collection module collects the first object data and establishes a first monitoring calendar.

[0061] A topology module is established to establish a first topology model of the first object.

[0062] The calculation module establishes a feature information library of the second object, performs cluster analysis on the second feature of the feature information library, and obtains a classification level of the second object.

[0063] The computer device may be a server. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data cluster data of the power monitoring system. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for orderly power consumption monitoring and revenue risk analysis of an enterprise is implemented.

[0064] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0065] Example 2 is an embodiment of the present invention, which provides a method and system for orderly electricity consumption monitoring and revenue risk analysis of an enterprise. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through simulation experiments.

[0066] In order to verify the effectiveness of a method for orderly electricity consumption monitoring and revenue risk analysis of enterprises, this experiment monitors and analyzes the electricity consumption plan and revenue risk of enterprises based on the energy big data platform. The experiment will compare the differences between the method of the present invention and the traditional manual statistical method in terms of electricity consumption monitoring accuracy, revenue risk assessment accuracy, data processing efficiency, etc.

[0067] Subjects:

[0068] Existing technology: Traditional manual statistical methods manually analyze corporate electricity loads, fail to achieve real-time data monitoring and dynamic risk warnings, and are prone to cause deviations in corporate electricity plans and delayed revenue risk assessments.

[0069] The present invention: establishes an orderly electricity consumption monitoring model for enterprises, dynamically collects enterprise electricity load data, and constructs an electricity consumption monitoring calendar and topology model; based on user feature portraits, cluster analysis and grading of enterprise revenue risks are performed to generate revenue risk warnings.

[0070] Experimental steps:

[0071] Data collection and calendar monitoring model establishment: In the present invention, the system collects enterprise archive information and power load data, establishes an orderly power consumption calendar for the enterprise, and associates the peak power restriction and peak-valley power restriction demands with the real-time load data of the enterprise. The traditional method requires manual recording, and the data update frequency is low, making it difficult to grasp the power consumption status of the enterprise in a timely manner. The system of the present invention updates the power load data every hour and calculates the power consumption deviation in real time.

[0072] Topological model and supply and demand balance analysis: In the present invention, the energy flow in the power supply area is displayed through the topological model to monitor the balance of power supply and demand. When the supply and demand are unbalanced, the system automatically records the load gap and the distribution area of ​​the power gap. The existing methods rely on manual recording when supply and demand problems occur, which can easily lead to untimely responses. The present invention realizes automatic analysis and recording through dynamic monitoring.

[0073] Feature profiling and cluster analysis: To assess the revenue risk of enterprises, the present invention establishes feature profiling based on data such as the enterprise's electricity consumption behavior and payment history, and divides the risk level through cluster analysis. Traditional methods are mostly static analysis and fail to identify high-risk enterprises in a timely manner. The system of the present invention calculates the risk level by time period clustering, generates risk warnings, and outputs them to the decision-making layer. The experimental results are shown in Table 1.

[0074] Table 1 Experimental results

[0075]

[0076] The table data shows that the present invention has significant advantages in enterprise electricity consumption monitoring and revenue risk analysis, and the specific analysis is as follows:

[0077] The traditional method relies on manual statistics, and the accuracy of electricity consumption monitoring is about 80%. The present invention improves the accuracy to 95% through automated data collection and dynamic monitoring, which is an improvement of 18.75%.

[0078] The traditional method updates data once a day, resulting in information lag. The present invention updates data 24 times per hour, increasing the data update frequency by 2300%, ensuring the real-time nature of power consumption monitoring.

[0079] The accuracy of traditional methods in risk warning is only 70%. The present invention uses feature profiling and clustering algorithms to increase the accuracy of risk warning to 93%, an improvement of 32.86%, effectively improving the accuracy of risk identification.

[0080] In the prior art, data processing takes about 60 minutes per day. The present invention shortens the time to 5 minutes through automated processing, and the processing efficiency is improved by 91.67%.

[0081] The traditional method has a deviation rate of up to 15% due to update lag. The deviation rate of the present invention is reduced to 5%, and the optimization range is 66.67%, which effectively improves the accuracy of the execution of the enterprise's electricity consumption plan.

[0082] The maintenance cost of the traditional manual system is relatively high, with an annual maintenance cost of about 50,000 yuan. The maintenance cost of the system of the present invention is 30,000 yuan, saving 40%.

[0083] The traditional method has a low recognition rate of 60% for enterprise revenue risk. The present invention uses feature portrait recognition to achieve a recognition rate of 90%, which is an improvement of 50%.

[0084] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for orderly electricity consumption monitoring and revenue risk analysis for an enterprise, characterized in that: include: Collecting first object data and establishing a first monitoring calendar; Establishing a first topological model of the first object; A feature information library of the second object is established, and a cluster analysis is performed on the second feature of the feature information library to obtain a classification level of the second object.

2. The method for orderly electricity consumption monitoring and revenue risk analysis of an enterprise according to claim 1, characterized in that: The collecting of the first object data and establishing the first monitoring calendar includes associating the first object with the enterprise archive, establishing a first object data list by region, and obtaining key data fields of the first object; A first monitoring calendar is established based on the first object key data field.

3. The method for orderly monitoring of electricity consumption and analyzing revenue risk of an enterprise according to claim 2, characterized in that: The first monitoring calendar includes obtaining enterprise electricity load data, taking each hour as a time node, associating it with the electricity load of each enterprise according to the power restriction requirements for each enterprise in the first monitoring calendar, establishing an enterprise orderly electricity consumption monitoring model, and calculating the enterprise electricity consumption; comparing the first monitoring calendar, analyzing the electricity consumption deviation, and recording the comparison results.

4. The method for orderly monitoring of electricity consumption and analyzing revenue risk of an enterprise according to claim 3, characterized in that: The establishing of the first topological model of the first object includes establishing a first visual topological model, comparing the current power supply and demand status, and recording and analyzing relevant data when an imbalance in power supply and demand occurs.

5. The method for orderly monitoring of electricity consumption and analyzing revenue risk of an enterprise according to claim 4, characterized in that: The feature information library of the second object includes a label library and a feature portrait of the second object.

6. The method for orderly monitoring of electricity consumption and analyzing revenue risk of an enterprise according to claim 5, characterized in that: The first object includes but is not limited to an orderly power consumption plan of an enterprise, the first monitoring calendar includes but is not limited to an orderly power consumption calendar of an enterprise, and the first topological model includes a regional power supply and demand visualization topological model; The second object includes but is not limited to the user's electricity revenue risk, and the second feature is a key feature included in the feature portrait of the second object.

7. The method for orderly electricity consumption monitoring and revenue risk analysis of an enterprise according to claim 6, characterized in that: The cluster analysis includes using a clustering algorithm to group users, identify user groups with similar characteristics, define different levels of user revenue risk, and predict user electricity revenue risk factors based on the user's most recent monthly settlement status.

8. A system for monitoring orderly electricity consumption and analyzing revenue risk of an enterprise using the method according to any one of claims 1 to 7, characterized in that: A collection module, collecting first object data and establishing a first monitoring calendar; Establishing a topology module to establish a first topology model of the first object; The calculation module establishes a feature information library of the second object, performs cluster analysis on the second feature of the feature information library, and obtains a classification level of the second object.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images